Software Technology for “Distributed electronic review of documents in a blockchain system, and computerized scoring based upon textual and visual feedback.”

Blockchain Fintech – Shahid N. Shah, Netspective Communications LLC

Abstract for “Distributed electronic review of documents in a blockchain system, and computerized scoring based upon textual and visual feedback.”

“A blockchain-configured system and a method to facilitate an expertise-driven review and scoring electronic documents in crowdsourced environments. The system comprises a server computer, memory circuit and processing circuit. The processor circuit is connected to the memory circuit. It also includes or is coupled with a credentialing machine. A scoring module for expert evaluation is also included in the system. The system also includes a document scoring and reviewing engine that is coupled with the processing circuit. The document review and scoring module assigns an aggregate score for the electronic document. This is based upon the sum of the review ratings from crowdsourced experts and the aggregate scores of each crowdsourced expert based on the set attributes, including one or more credentialed experts, reputation of experts, and the officiality.

Background for “Distributed electronic review of documents in a blockchain system, and computerized scoring based upon textual and visual feedback.”

“Technical Field”

“The embodiments are generally related to electronic document validation and, more specifically, crowdsourced electronic document review/scoring utilizing textual and visual feedback from reviewers.”

“Description of Related Art”

Many organizations offer financial aid and other rewards, such as grants. For valuable ideas. Many organizations don’t know how to select the most valuable ideas from the many ideas that have been submitted for evaluation. Many times, the feedback is not textual. Therefore, relying only on review comments and textual feedback may not suffice for a proper evaluation. This makes evaluation difficult and less reliable for these organizations.

“There is therefore a need to develop a system and method for electronic document review and scoring that uses different types of visual and written reviews from reliable and verified sources.”

“This embodiment presents a distributed blockchain-based architecture-based system in communication network. The system comprises a memory circuit that is communicatively connected with the communication network to store a plurality digital profiles associated to a plurality crowdsourced experts and further store a plurality digital segments associated with each of these digital profiles. These digital profiles and segmented digital profile are created using a plurality digital sources and electronically linked across the communication networks. A credentialing engine is included in the system to enable a plurality crowdsourced respondents to respond and credential each expert. The credentialing engine also contributes to credentialing the expert’s digital profile upon collation of credentialed segmented online profiles. Credentialing of the expert’s segmented digital profiles is done by a number of respondents through a computerized crowdsourcing algorithm. Crowdsourcing index shows the number of experts credentialed by respondents and it dynamically grows with increasing number of respondents. To determine the attributes of experts, the system has an expert scoring module. The set of attributes comprises one or more of crowdsourced credentialed expert knowledge. It is based on the credentialing and reputation of experts from the respondents. Officiality indicates a job or position of experts in a relevant field. Each attribute may have a different weight assigned by computer. An expert scoring module calculates the aggregate score of an expert using the associated weights and one or more attributes. Electronic document scoring engine is also included in the system. This allows crowdsourced experts to review and comment on electronic documents and give their opinion. Crowdsourced experts could have a score that is higher than a threshold. Natural language processing-based (NLP) analysis engine is used to process comments and reviews based on textual information. This engine can be used in conjunction with crowdsourced experts for textual review of electronic documents. The document scoring engine also includes a visual scoring engines for visual and non-textual reviews and feedback from crowdsourced experts. The visual scoring engine is controlled by an eye tracks processor that receives inputs from the respective eye tracking systems of crowdsourced experts. This processor then processes the inputs to assign a review score based upon predefined eye track patterns. A micro expressions processor is part of the visual scoring engine to receive information indicative of micro facial expressions extracted from respective micro expressions sensors that are associated with computing devices used by crowdsourced experts. The micro expressions processor is comprised of an image processing circuitry with associated memory. It interprets the micro facial expressions and compares them to predefined facial patterns in order to assign a review score. Further, the document scoring engine can associate an aggregate score to electronic documents based on the aggregation and visual review scores of individual textual and visually reviewed documents. This is done by processing the textual and visual reviews of crowdsourced experts who have reviewed the document. A graphical user interface is provided by the document scoring engine that displays an output indicative of the aggregate score of each document reviewed by crowdsourced experts. It also includes information about who and how many times the document was reviewed. A device for expert identity validation is included in the system to verify identities of crowdsourced experts prior to or during review. The expert identity validation apparatus includes a device patterns assessment tool to extract and process the device information from the computing devices of crowdsourced experts. It also verifies the extracted information against predefined crowdsourced expert information. The network patterns assessment device is part of the expert identity validation device. It receives and processes network information from the appropriate agent devices that are associated with the crowdsourced devices. This information can then be verified with the predefined network information for the respective crowdsourced specialists. For processing validation, the expert identity validation device also includes a geospatial mapping tool to perform geotagging of crowdsourced experts as well as documents. Geo-tagging is performed using geo-spatial data received from a GPS-based device. The expert identity validation devices includes a facial expression validation unit to process facial expressions from the respective facial expression sensors that are associated with the computing devices used by crowdsourced experts. It also verifies identity according to the predefined facial patterns. The facial expression validation unit includes a digital acquisition device and multichannel amplifiers that pre-process and amplify signals sent by facial expression sensors.

“The embodiments and their various features and beneficial details are described in detail with the help of the accompanying drawings. They are also illustrated in the following description. To not obscure the embodiments, we have omitted descriptions of well-known components. These examples are provided to aid in understanding the various ways the embodiments can be used and to make it easier for those skilled in the art to use the methods. The examples are not meant to limit the scope of the embodiments described herein.

“In the following detailed description, we refer to the accompanying drawings which form a part of this document. These are used to illustrate specific embodiments that can be practiced. These embodiments are also known as “examples” in this document. These embodiments, also referred to herein as “examples”, are sufficiently detailed to allow those skilled in art to use them. It is also to be understood that embodiments can be combined or that other embodiments may have been utilized.

“In this document the terms?a?” or?an? are used. “The terms?a????? or?an?? are used in this document. As is usual in patent documents, they are used to include more than one. The term “or” is used in this document. This document uses the term?or? to mean a?nonexclusive? Unless otherwise stated.

“FIG. “FIG. The ecosystem 100 can facilitate the implementation of an expertise-driven review and scoring (also known as electronic document review system, EDRS) 102 for electronic documents in a crowdsourced system 106. An ecosystem 100 could include a server computer 108 that is connected to the electronic documents review and scoring system (EDRS) 102. The EDRS system 102 could include an expert attributes assessment engine 110 and an expert scoring module 112. A document scoring module 114 may also be included. A processing circuit 116 may be added to the ecosystem 100. A memory circuit 118 may be added to the ecosystem 100.

“In one embodiment, the ecosystem 100 facilitates crowdsourced review and scoring electronically by a plurality crowdsourced experts or reviewers. A set of attributes may be used to shortlist the reviewers. This allows them to evaluate the documents and assign a score. Expert attributes engine 110 may define and consider these attributes. These attributes could include, for example, crowdsourced credentials, crowdsourcing index and officiality. Crowdsourced credentialing can indicate a level of credentialing by multiple respondents. For example, it could be indicative that the expert or reviewer has scored the expert based on credentialing or the expert profile of multiple respondents. Crowdsourcing index can be used to indicate the level of crowdsourcing, which is the number of experts credentialing them. An embodiment of the crowdsourcing index effect on an expert might show a non-linear relationship between expert score and number of experts credentialed. The relationship could be exponential, for example. An official title may indicate a position held at an organization. A person’s reputation can indicate how trustful an organization or community is in an expert.

Each attribute may have a different weight in the examples. The assignment of weights to experts’ attributes may be influenced by parameters such as document type, complexity, expert profiles, country and location of the expert, importance and scoring objectives, and so forth. For example, the highest weight can be assigned to officials, credentialed expertise, reputation, and so forth.

“The expert scoring module 112 could facilitate cumulative scoring of an expertise based on defined attributes and the assessment of each expert using the attributes engine 110. The scoring module 112 could assign a score to an expert using a cumulative ranking of experts for each attribute and taking into account the weightages of those attributes. There may be sub-modules or engines within the expert scoring module 112 that can help in evaluating an expert’s score according to each attribute. As will be explained later, the expert-scoring module 112 may also include a credentialing system and reputation assessment engine.

“The document scoring module 112 assigns a score for the document based upon an associated cumulative score that is based on the scores of each crowdsourced expert/reviewer. Expert scoring module 112. The cumulative score calculated from the scores of the plurality crowdsourced experts may account for the impact of crowdsourcing using the expert scoring module 112. This may have a non-linear effect upon the final cumulative score. The crowdsourcing index can be statistically defined for different numbers of experts who have reviewed a document. A crowdsourcing index 1 can be used to multiply the crowdsourcing impact. A crowdsourcing index of 1.2 could be used for a range between 21-40. A crowdsourcing index of 1.5 could be used for a range between 41-60. Another example is that the crowdsourcing index can be dynamically determined with an increase in effect for each additional crowdsourced expert involved in the review process. A mathematical relationship can be used to determine the crowdsourcing index in such cases. This relationship could be described as an exponential increase in crowdsourcing index value and an increase in number of reviewers.

“The memory circuit number 118 stores a variety of common profiles that are associated with crowdsourced experts. Further, the memory circuit 118 stores a number of federated profiles that are associated with each common profile. The federated profiles and the common profiles are created using a variety of federated sources spread across the crowdsourced network (106). We will discuss the common and federated profiles later.

“The processing circuit 112 includes various processing components. It is capable of processing tasks such as aggregating profiles and federating common profiles. Rating and scoring experts, assessing review, scoring the documents, and other tasks, as described in this document. The processing circuit 116 could, for example, be combined with the expert attributes engine 110 and expert scoring module 112. These modules can perform these and other tasks.

“In one example, the crowdsourced social network could be a blockchain-configured social integrity network. This means that experts, reviewers, or participants can connect with the blockchain-configured social integrity network via distributed access points. All participants have access to different systems and subsystems of the ecosystem 100 in distributed fashion. They can manage, share and edit, annotate, and review documents simultaneously within the authorized access rules.

The blockchain-configured ecosystem and its components, also known as a “smart contract based distributive integrity network”, may not require an operator for centralized information exchange (IE). All participants can have access to distributed ledgers to ensure a secure exchange, without trust breaches, and all may be able to see the distributed ledgers. This allows for disintermediation, as human participants can be removed from the chain of participants (entities). The documents to be reviewed are stored in a variety of locations on the blockchain, which allows participants to access them simultaneously. This makes it possible for participants to update and review the documents almost instantly. Blockchain-configured ecosystem offers a secure, distributed, and disintermediated framework that enables the integration and support of information across a variety of stakeholders and uses. Blockchain-configured digital ecosystem provides a secure and distributed platform for patient digital identities. It allows access to personal connected health devices, home health devices, storage devices and servers hosting documents. The use of private keys and public keys is secured by cryptography. This protects identity of participants and reviewers. Because the blockchain-configured digital ecosystem is distributed, it allows for shared data that provides real-time updates to all authorized entities. This makes the network accessible to all authorized parties without the need of a central authority or exchange. We will discuss the blockchain-configured ecosystem in more detail with subsequent figures.

“FIG. “FIG.2.2, with reference to FIG. 2. Referring to FIG. This environment includes a number of experts 202a-202d (collectively referred as 202) and a number of respondents 204a-204c (collectively referred as 204) that are connected to a crowdsourced network. 106. The network 106 is connected to a credentialing system (206), which is accessible by experts 202 and respondents 204 via the network. This can be done, for example, through a portal or web-based interface (not shown in FIG. 2).”

“The network 106 may use a wireline, a wired communication channel, or both. A wireless communications network can include, but is not limited to, a digital cell network such as the Global System for Mobile Telecommunications network (GSM), Personal Communication System network (PCS), or any other wireless communication network. A wire line communication network could include, but is not limited to, a Public Switched Telephone Network, proprietary local and long-distance communications network, or any other wireline communications network. The network 106 could also include digital data networks such as one or two local area networks (LANS), one, or more wide-area networks (WANS), or both LANS/WANS, to enable interaction with credentialing system (206). The crowdsourced network 106 may contain one or more networks. These networks can include public networks like the Internet and private networks. They may use any protocol or technology such as Ethernet, Token Ring or Transmission Control Protocol/Internet Protocol (TCP/IP) to allow interaction with credentialing system. The network 106 may be a social integrity network that is blockchain-configured.

One or more of the experts 202 may include a doctor, surgeon, physician assistant, or other healthcare professionals. One or more of the respondents 204 could include a doctor, doctor, surgeon or healthcare expert. They may also include any other healthcare professional or organization like a hospital. Any other person may also be interested in the credentialing and accreditation process for the experts. Multiple industry-related agencies (e.g. hospitals, nursing centres, research institutes and financial companies), financial agencies, transportation agencies, energy-related agencies, etc., can also access the system to obtain credentialing or verification services from the system. The credentialing information obtained by respondents 204 may be used to provide services to these agencies by the system 206.

“Experts 202 and respondents204 could be connected to, for example with any type of electronic data processor or communication device, or a client device, connected to the communications network. Personal computer systems such as laptops, desktops, servers, computer systems on the network, computer networks, personal digital assistants, wireless communications devices, mobile electronic devices, tablets, and other electronic data processing systems are all examples of an electronic data processing device or client device. Client devices and data processing systems may include hardware/software computing devices that can perform computational tasks such as profile creation, modification and verification. These tasks can be done via a standalone application, via a Web browser graphical user interface (“GUI”) or via a Rich Internet Interface (?RII?). A computer program that is part of an online social network system may implement the embodiments herein. This embodiment may also be implemented using distributed blockchain-configured architecture. The credentialing system 206 may be used with a client device that is equipped with a Web browser or any other Web-enabled device. It can connect to the crowdsourced network 106 using a Windows, Macintosh or UNIX operating system.

“The credentialing model 206 allows for the creation of profiles of experts 202, including details about them. These profiles can then be stored in the system.206. These details can include personal information, education history, and other similar information. These profiles can then be shared with multiple respondents 204 and experts202 according to set standards, preferences and rules that allow for a federated exchange capability. This allows distinct parts of the profiles to be credentialed, accredited or verified and can be shared or exchanged with experts 202 and respondents 204 in an federated fashion. Further, the system 206 provides credentialing and verification capabilities that allow each expert 202 to be credentialed by another expert or respondents 204 in order to use credentialed profiles created by agencies or organizations. The system 206 may also allow for the creation of a federated model of profiles. This allows the credentialed segments or sections of profiles to be credentialed or verified by distinct federated respondents (204 in the crowdsourced network 106) so that crowdsourcing increases trust, authenticity, and reliability in credentialing and credentialed information.

“The credentialing system (206) as shown includes a federal profile manager 208 and segmenting or federation engines 210. A certification engine 212 is also included. These are discussed in detail below.

“The federated profiles manager 208 can receive profile creation information from the plurality experts 202. The federated manager 208 will maintain the information received from experts 202 and make changes as required by the experts. The federated profile manger 208 can be linked to multiple sources of information, such as their social networks, educational institutions, work environments, and other relevant information. The federated profile manger 208 collects information across a variety of sources for each expert 202 and compiles the records and information into a single profile of each expert 202 that is associated with and communicates with the system. For example, the profile manager 208 may gather information from federated sources like Linkedin and Myspace, About.Me or education institutions. The system 206’s common profile may be viewed by experts 202, respondents.204, relevant organizations, and any other entities or persons associated with the system.206. The distributed access points of the Blockchain-configured architecture may be accessed by the experts 202, respondents 204, relevant organizations and any other person or entity for near-real-time management or review of process. The federated profile administrator 208 may be able to automatically retrieve profile information from social networks in some embodiments. The federated profile manager may, in some instances, keep information submitted by experts 202.

“The federated profiles manager 208 may enable the experts 202 maintain their profiles in system 206. It protects the information in their profiles from unauthorised access and connects their personal profiles. Further, the credentialing system (206) may allow the profiles and any information to be searchable by both the experts 202 or the respondents 204. The experts 202 can then access the portal or user interface via a web-based interface. After completing an initial registration, the experts 202 may create and update their profiles using the user interface. The experts 202 can then register by filling out a registration form. They will need to enter an email address and a password. After completing the registration form, experts 202 can create their profiles and fill in the information. Profiles describe the user’s past, experiences, abilities, titles, roles and skills, as well as their goals, objectives, employment organizations, work stations, and other relevant information. Experts 202 can add contacts to their database by entering contact information and relationship information. They also have the option of linking to the contact’s profile on the system. The experts 202 may authorize the use of the contact information in the credentialing system. Experts 202 might not wish to have their address book integrated into the system 206. The experts’ address book could be uploaded but not integrated into credentialing system.106. This would make it difficult for others to see. Contact information and profiles can be stored in either a central or distributed database. The system 206 could include or be linked to a profile database 214, which may contain the information relevant to the profiles of experts 202.

“In certain embodiments, once expert 202 joins the network106 and subscribes to the credentialing program 206, all information in the profiles are available for credentialing or verification, accreditation, etc. So that all profiles can be credentialed from the multitude of crowdsourced respondents, 204 the system 206 can verify them and credential them. Credentialing can also be used to determine whether the profiles are accurate, reliable, trustworthy, genuine, fraudulent, or authentic.

“In other embodiments, once the plurality 202 experts join the network 106 the profiles are divided into distinct sections or segments that are referred to by the federation 210 as federated profiles. The segmenting engine210 can receive common profiles from profile manager 208 and then segment them into federated segments, portions, or profiles. The federation engine210, for example, breaks down a common expert profile into multiple federated profiles. This is based on similarities in the content of the federated profils. Crowdsourced respondents 204 treat the federated profiles as separate profiles to allow them to be credentialed separately. A common profile P may contain the following details:

“For simplicity of description, some details are not included in the profile. However, many other details can be included without limitation. The segmenting engine 220 may be used to separate the profile into different federated profiles. In some embodiments, for example, the profile above may be divided by the segmenting engine 220 into several federated profiles, such as the one below.

“A single profile can be segmented by segmenting engine210 in 35 discrete federated profiles, which are different in one or another way. The segmenting engine 210 can be set up to segment a single profile in as many federated profiles and as many different ways as possible, according to various embodiments. The entire information in a single profile is then divided into multiple federated profiles. The above-mentioned common profile can be converted into 35 federated profiles. After segmentation, the federated profiles can be communicated to federated profile manager (208). The federated profile manager208 stores both common profiles and federated profiles associated to the experts or professionals 202 in the profiles database 214.

“The segmenting engine210 may contain hardware and software components that can perform computational tasks related to the segmentation of common profiles into federated profiles. The segmenting engine210 may then be used to further group the segments or federated federated profiles into groups for the same experts. 202 This allows the groups to include similar federated profiles that are based on specific parameters. The work experience federated profile segments 27, 30 and 33 which define different companies where an expertise was employed, may be combined to create a new type of profile. This is referred to as a sub-profile. Similar to the above, other groups can be created to create sub-profiles that are based on different combinations of profile segments or segments. Credentialing system 206 allows for easy maintenance of common profiles, sub-profiles, and federated profiles by the same experts. This provides a three-level profile management facility. This document does not limit the use of the terms portion, segment, and federated profile.

“The credentialing systems 206 also includes the certification engine 212, which is coupled with the segmentation engine 220 and the federated profiles manager 208. The certification engine 212, which allows crowdsourced respondents (204), to respond to the classified and segmented profiles of the plurality 202 experts, 202 and to credential them, is designed to do this. Credentialing each segment or federated profile associated with an expert202a of the plurality 202 is necessary to credential the entire expert202a profile. The exemplary profile, as shown above, includes 35 segments. Credentialing each segment has an impact on the overall credentialing for the whole profile. If all thirty-five segments have been credentialed by one or more respondents, 204, trust can be established about the profile information. The information could be considered true or authentic. The trust in each segment increases as more people or respondents from the plurality crowdsourced respondents204 verify the information. The crowdsourcing index can also be used to measure and account for the level of crowdsourcing. The crowdsourcing index could have an exponential or non-linear relationship to the number of experts crowdsourcing. As more experts are credentialed, the trust and reliability of expert credentials may rise non-linearly. Crowdsourcing can help credentialing be more accurate and reliable than if it is done from a limited number of sources. The accuracy of the overall profile can be calculated based on the cumulative effect of accuracy from all federated profiles. If the first ten segments of the above common profile are verified, and the rest of the segments are not verified by respondents 204, it may not result in a high level of accuracy. Credentialing and verification may still be required for the remaining segments, but this could be acceptable to some extent. The overall profile could be deemed inaccurate if all 25 segments are rejected by respondents 204. The credentialing of the expert 202a may also be highly authentic and reliable, as the discrete federated profiles are credentialed by the multitude of crowdsourced respondents.

“The certification engine 212 is designed to certify the stored profiles of experts 202, such as engineers or physicians. Experts 202 must verify their credentials for use by different agencies. They can also use the certificates to submit forms to companies, such as for hiring purposes, document review, or other purposes. Credentialing information for a specific expert 202 is first input as a common profile. Then, each federated profile is segmented and credentialed individually using the crowdsourced network of multiple respondents 204. Credentialing information for each profile is valid, more accurate, and more acceptable than the single verified profile. However, special attention might not be given to every record in the common profile. Crowdsourcing is more reliable than single verifications by one source. According to certain embodiments, each segment may have a number of credentialing sources that credential a particular federated account. This is to indicate the accuracy of the credentialing information. A federated profile may be considered acceptable if it is credentialed by 18 sources within the network. The credentialing information, such as who and when credentialed a federated profile, may be linked to each segment’s credentialing. This allows authenticity to be assessed by associating the overall impact of the credentialing of the federated profiles, trust factor about the source that verified, and relevance about when the verification was performed. In such embodiments, a multiscaled and cumulative score can be calculated and multi-scaled or cumulative credentialing may take place based on that multi-scaled cumulative score. A single federated profile can be verified by a plurality of crowdsourced respondents (204). Therefore, the credentialing system206 could determine the extent of inconsistency among multiple credentialing by different respondents 204 for the identical federated profile. The system 206 can be used to calculate an index of consistency based on the distribution of credentialing among the various respondents 204. The credentialing system may generate a map showing the extent and coverage of inconsistencies between the various responses and credentialing for similar federated profiles. This map, together with the inconsistency indicator, can be used to determine the level of trust in overall credentialing for the same federated profile. This may be repeated for each federated profile for a common expert profile, such as 202a. It may also determine an overall index for inconsistency, overall distribution map, and overall trust factor for that profile.

“In some embodiments, different agencies, such as document reviewing agencies and ideas evaluation agencies, may use the credentialing data, index of consistency, and distribution map, as obtained from system 206. Credentialing information can include information about who was credentialed or verified, what verifications were used, the trust factor associated each verification, as well as information on the relationship between a respondent and an expert, such as 202a or any other factor. The credentialing information can be submitted to experts 202 along with other forms. You can include information about your personal history, education, affiliations with hospitals, institutes, etc. Credentialing is possible. Credentialed information can include the person’s name and address as well as practice specialties, appointment status and associations. Credentialed information also includes credentials (including educational background and residency programs), state licensing information and information about malpractice liability insurance. Personal and professional references are also possible. The federated profile manager, 208 may store all of this information in the profiles database.

“In certain embodiments, the certification engine may be coupled with or include a profiles certificate database 216. As discussed above, the credentials information may be included in the profiles certification database 216. The profiles certification database database 216 may, in some embodiments, be contained within the profiles database 214. This allows for the storage of both the credentials or certification information.

“In certain embodiments, when creating a common profile and uploading information to the database, each professional may need to complete a separate application form. The application form information may be provided to the profiles database 214, which may contain expert profile information. The information can be stored in a series of expert profiles that are logically organized and may be used to segment the data using the segmenting engine 220. The segmenting engine 210 may initiate the process of segmenting automatically if new or updated information is available. If the past information has been modified, the segmentation task can be performed again to update the profile and credential the new federated profiles. If this happens, it may be necessary to revise only the relevant credentialing based on the updated information rather than rejecting all federated profiles and associated credentialing information.

“FIG. “FIG. The credentialing system (206) in accordance to an embodiment is illustrated in FIGS. The system 206 can include a profile management and certification server 302, as shown. Profile management server 302 contains a profile information collection module 306, a federated profile manager (208), and the profile segmenting engines 210.

“The profile information collection module 306 can be used to generate information about the plurality experts 202. The profile information collection module 306 may be stored separately from the Federated Profile Manager 208, while other embodiments allow it to be integrated with or coupled with the Federationed Profile Manager 208. By distributing application forms via a graphical user interface, experts 202 have the ability to generate the profile information for the plurality of experts. The experts 202 can then fill out the forms and submit them with the system. The federated profile manager can transform the information into profiles. Segmenting engine 210 can then use the profile information to perform the task of segmenting the common profiles into the federated profils associated with each expert 202.

The profile certification server 304 can be communicatively linked to or included with the profile management server 302. The profile certification server (304) may contain the certification engine, segment rating engine 308, or a profile rating engines 310. A segment certification engine 312, and a profile engine 314 may be included in the certification engine 212.

“The segment certification engine 312, may be used to credential or certificate the federated profiles that are associated with the common profiles of each expert 202. The segment certification engine 312 allows crowdsourced respondents (204), to respond to the federated profile associated with the common profiles of the plurality 202 experts and credential them. Credentialing each of these federated profiles with the common profiles for each expert 202 is necessary to credential the entire profile of experts 202 after collation of credentialed profiles. Credentialing the respective federated profile increases in trust as more people or respondents from the crowdsource respondents 204 verify the information. Crowdsourcing could allow credentialing of federated profiles to be more accurate and reliable. The credentialing of the discrete federated profiles associated to an expert 202 is based on the plurality crowdsourced respondents. 204 This credentialing may be considered highly authentic, reliable, and acceptable by agencies and third parties. The crowdsourcing index could also be used to account for the impact of crowdsourced credentialing, as previously discussed.

“The segment certification engine 312, which certifies the stored federated profiles of experts 202, is designed to verify their credentials. In some embodiments, each segment may have a number of credentialing sources associated with it. This is to show the accuracy of the credentialing information. The relevant information regarding credentialing such a who, when, and whereabouts of credentialing may be associated with each credentialing for each of the segments. This allows authenticity to be assessed by associating the overall impact of the credentialed federated profile’s credentialing, credentialed number, trust factor about the source, relevance about the source, and the time they were verified. In such embodiments, a multiscaled and cumulative score can be calculated and multi-scaled or cumulative credentialing may take place based on that multi-scaled cumulative score.

“The information regarding credentialing for individual federated profiles associated with an expert, such as 202a, may have an impact on the overall credentialing. Individual credentialing from federated segments can contribute to the overall credentialing for the common profile. For example, the credentialing may be determined by the credentialing associated with each credentialing. Credentialing for the overall common profile is determined by the combined contribution taking into account weightage effects of each credentialing. The profile certification engine 314 may perform the task of credentialing an overall common profile that is associated with an expert, such as 202a. The profile certification engine 314 can, for example, facilitate credentialing the entire profile based on the combined effect of credentialing the federated profiles that are associated with the expert profile. The profile certification engine 314 can receive information relevant to credentialing each of the associated federated profile with a common profile. It may then associate the defined weightages to each profile and perform cumulative credentialing for the common profile. An embodiment may determine the weightages based on parameters set by the service provider that operates the system 206. These embodiments may allow for weightages to be determined based on past experience or current knowledge about the importance of credentialing in different segments. When applying for a job, accuracy in credentialing information may be more important than information about hobbies or work history. The objective use of credentialing information can influence the determination of weightages and thus the overall credentialing. In some embodiments, the credentialing process may include a score that indicates the impact of the objective. An agency may require the credentialing information to determine the weightages in some embodiments. In such cases, the profile certificate engine 314 can credentialize the common profile in a custom-defined manner, as well as in conjunction with the objective score.

The segment rating engine 308 is also part of the profile certification server 304. “The segment rating engine 308 can assign a rating to each credentialed profile. It is based on the credentialing provided by the crowdsourced plurality 204. The rating depends on the level of trust and accuracy associated with credentialing the federated profiles. The rating will depend on the following: who credentialed the federated profiles, when they were credentialed and how many times. Relevance of respondents 204 to the federated profiles, relationship between the respondents 204 and the expert, such as 202 of the credentialed profile.

“The profile rating engine 310 may also be included in the profile certification server 304. The profile rating engine (310) is used to assign a rating to an entire profil based on the credentialing of each federated profile and the ratings associated with each federated profile as determined cumulatively by the segment rating engines 208.

“Profile management server 302 can be coupled to the profile database 214 in order to store information relevant to the profiles of multiple experts 202. The profiles database 214, which may be coupled with the federated manager 208, can store information in the profiles database 221; the federated manager 208 will then keep the information in the profile database 214.

The profile certification server 304 can be linked to the profiles database 216. The credentials database 216 stores information relevant to credentialing, such as the certification status of the federated profiles or common profiles that are associated with the plurality 202 of experts. The certification status could include verification in progress, verified segment, verified profile and segment rejections. The certification engine 212 and the profiles database 221 may be combined with the certification database 216.

The certified profiles database 312 may also be linked to the profile certification server 304. The certified profiles database 312 could be further coupled with the profiles certification database 215. The certified profiles database 216, which can be used to store verified profiles, may be set up to hold profiles. A preference or set of rules may allow an entity or agency direct access to the certified profile database 316. An entity could be a medical entity, such as a hospital or nursing center, doctor or physician, or a healthcare department. It may also belong to another industry, such as the financial sector, energy or transportation, or any other agency or third party. Further information may be stored in the credential database 316 or certified profile. This includes personal demographics, work history, education, affiliations to hospitals, or other institutions, etc. One or more experts 202 that correspond to one or more verified profiles.

The profiles database 214, certified profiles database 216, and certified profiles database 312 can be linked to a profile sources database 314. Information about the profiles database 214, certified profiles database 216, and certified profiles database 312 may be linked to the crowdsourced network. This information could also include information about the sources that respond to the credentialing requests. In the crowdsourced network, for example, the plurality 204 of respondents may credential the profile federated profiles. The profiles sources database 314 could store their details, including their names and other information. It may also include information about their relationship to the experts 202. This information may include the time and place of credentialing and any other pertinent information.

“Example: The profiles database 214, certification database for profiles 216, and certified profiles database 312 can all be blockchain-configured so that they are accessible by entities (experts and respondents 204) and any other agency through the distributed plurality access points simultaneously. This allows them to view or reflect reviews and any changes during the review process in close real-time.

“FIG. “FIG. Another embodiment of the credentialing systems 206 is illustrated in FIGS. As discussed above, the credentialing system may also include the profile management and certification servers 302 and 304. Further, the system 206 could include an auto-validation engines 402 and 304. Further, the auto-validation engine 402. is communicatively connected to a social network platform 404. Information related to experts 202 is stored on the social network platform 404. The social networking platform 404 might host experts 202’s social profiles. Here, experts 202 can store and update their personal, professional, and other details, as well as communicate with other social network contacts, such friends, relatives, or other networking contacts.

“The auto-validation engines 402 and 212 are configured to further certify the credentialing of federated profiles. The auto-validation engine 404 performs the second level certification using information from the social networking site 404 about one or more experts 202. An expert like 202 a could be associated with a social network website, such as Linkedin or Facebook. Each social networking site may have a different expert 202a. The information from social networking profiles can be used to verify the credentialing of expert 202a for specific profiles.

“In one embodiment, the credentialing of the respondents 204 is used for associating a rating and defining a level trust for the common profiles and the federated profiles. Further verification using the information from the social profiles 202 of experts may add another rating or score for the federated profile. This may allow the level of trust to be established about the plurality 202 of experts and their federated and shared profiles based upon the cumulative effect of credentialing, the auto validation of federated profiles, and the common profiles. Based on the individual scores of the respondents 204, the cumulative score may determine a net rating as well as overall credentialing for the federated profiles. Agencies, organizations, or other entities may access the federated profiles and common profiles together with information relevant to the credentialing or the auto-validation to establish a level of trust in credentialed information.

“The auto-validation engine 402 may contain application programming interfaces (APIs), 406, a social network engine 408, or a module for updating profiles 410.

“The social network engine 408 is linked to one or more social media servers 412. The social networking engine 408, which can be controlled by the 412 social network server, is designed to process the credentialing system’s request 206. It retrieves information from social profiles and verifies the common and credentialed profiles using the information from these profiles. Social networking engine 408 is communicatively connected to the social network platform 404 via the social network server 412, to allow interfacing the system 206 and the social media service or platform. The social network server 412 can provide a programmatic interface through the network 106 to allow access to the social profiles of the system 206. The social networking server 412 might store social data about the experts 202 from the social profiles hosted on the social networking platform 404. This data can be used to link the social data with credentialed federated profiles to verify or update the credentialing via auto-validation.

“The APIs 406 and 407 may be used by the social networking engine 408. To verify the federated segments associated to the plurality of expert 202, based on information in each expert’s social profile maintained by the social network platform 404. The social profiles created by the social networking platform are different from the federated profiles or common profiles of experts or professionals 202 maintained by federated profile managers 208. APIs 406 allow auto-validation that determines the extent of mapping between information in two different profiles, one maintained by the federated manager 208 and one maintained on the social networking platform. Social networking platforms 404 can include multiple social networking sources. Social networking sources could include, without limitation, social networking websites, educational institutes, employers’ databases, etc. An expert like 202 a could be associated with one or several of these or other similar social network sources on the social networking platform 404. The APIs 406 can be used to link federated profiles with one or more distinct social networking platforms 404 sources. This creates a unique identifier that associates a separate source of social networking platform 404 with a federated profile.

“The profile update module 410 can be used to modify or update profiles based upon further verification of the auto-validated federated profiles. The auto-validation module 410 can request to modify federated profiles, sometimes after credentialing has been completed by respondents 204. In some cases, however, this may be done after the experts 202 have granted permission. The profile update module 410 can be communicatively connected to the profile management system 302, so that the federated profile manger 208 can store and maintain modified federated profiles.

In one embodiment, the social networking site 404 can be described as a network that has an arbitrary number of computers connected to it. Registered social profiles allow users to access the social network 404 from a variety of computers. Social network 404 allows users to post and share online profiles, data, and clinical reviews simultaneously from any of the arbitrary many computers, including a respondent’s, expert’s, patient’s, or clinical provider’s.

“The social network platform 404 could include one or more social networks sources. These sources could be social networking websites, educational institutes, employers’ portals or databases, hiring agencies’ portals and other sources that can help create a socially aware network. Linkedin and MySpace are just a few examples of social networking sites.

“A service provider can deploy the credentialing systems 206 and provide credentialing and services to different organizations or agencies. This could include a hiring agency or recruitment and selection department or agency, document, inventions or ideas scoring and scoring and evaluation agents, an entity like a hospital, medical institute, research institute education institute, transportation company or energy department, financial institution, and so on. These systems can be used in-house by organizations like document or inventions, ideas scoring and evaluation organisations for the evaluation of ideas and documents. A profile of an expert, such as 202a, may be submitted to the service provider. This information may be stored in system 206. The service provider can verify and credential the profile details and other information submitted by expert 202a. They may also store information relevant to the credentialing process of expert 202a. A crowdsourced network of 106 people may be used by the service provider, including the respondent 204a or author 204a, who could also be any expert or any of those 204. The service provider, expert202a, and respondent/authorizer 204a can connect over the network106 via a web-based user interface that could serve as a portal. The portal or interface may provide a subscription section through which the entities such as the expert 202 a, agency, or the respondent/authorizer 204 a may associate them with the credentialing system 206. Each section may have different sections for the expert 202a, respondent (204 a), and agency. After subscription, expert 202a can submit his details to system 206 and/or create an account.

“Profile information may be visible publicly in certain embodiments, or may be made visible by the specific respondent for credentialing purposes and to receive responses from the respondent. 204a About the expert 202a The system 206 may store the profile information. It may be credentialed or verified in whole or in parts, as described above. The portal section devoted to such agencies may allow the agency to obtain accreditation or credentialing information about the expert 202. The agency can access the web-based portal to obtain credentialing information, as well as other information, by visiting the single central system 206. It may also be able to view the profiles of experts and other information. The credentialing is performed by the server 108 from a crowdsourced network 202. This means that the accuracy and reliability of the credentials and authenticity, as well as the reliability and reliability of the profile information, may be greater. Therefore, agencies can have greater trust in the information. The credentialing is more precise because the profile information is divided into federated profiles. This means that the agency can easily determine which information has been verified or pending verification. The agency may be able to determine who verified a particular profile in federated form, when it was verified and how many verifications were performed for that profile. The present system 206 may make credentialing easier, faster, more reliable, accurate, and more manageable.

“FIG. “FIG. The flowchart below illustrates how to facilitate crowdsourced and multilevel credentialing through the network. This may involve receiving profile information from multiple crowdsourced experts 202 at 502. This information could include personal, educational, and work history details. This may include collating the information to create a common profile for each expert 202. Another embodiment of the method involves experts 202 submitting the information in an automated and clearly defined manner through a web interface. A profile is created automatically upon submission of information and/or subscription to the credentialing software 206. At step 504, the method may also include the segmentation of the common profile associated to each of the plurality 202 experts into a plurality federated profile. This means that one set federated profile is created from the common profile associated to an expert, such as 202 a. The system 206 maintains two types of profiles. One is a common profile, and the other is federated. This method could also allow the public to view the federated profile so that they can be viewed by the crowdsourced group of respondents 204 and other experts 202. Further, the method could include receiving responses from the plurality crowdsourced respondents 204 regarding the federated profile at step 506 via a distributed blockchain-configured network. These responses could be used to credential the federated profiles. The system 206 might allow respondents 204 to credential information in federated profiles. The credentialing of federated profiles will be more reliable and accurate the more credentialing is done by respondents 204 individually, the more verifications are performed.

“The answers may be used to determine certification or credentialing information in the federated profiles as well as the common profiles. Credentialing can be linked to each federated profile individually. It may also be verified as incorrect or correct. Crowdsourced credentialing allows for certification of each federated profile by one or more respondent 204 to create an effect that combines certification at multiple levels. A first level certification can be made by a respondent like 204 who certifies a specific federated profile. A second level certification can be performed by another respondent 204, b who certifies or verifies the same profile. Multi-level certification or credentialing can also be done. The cumulative effect of certification permits the association of a cumulative segment rating, or cumulative federated profil rating, to each of each expert 202’s federated profiles. Each of the responses associated to federated profile are associated with attributes that define the source and respondent who certify the profiles. Also, the date of certification by respondent. The terms credentialing, verification, certification and verification can all be used interchangeably in the document. After credentialing the profiles by respondents 204, the method may also include assigning a rating to both the common and federated profiles. This system and method allow multi-level credentialing. They can execute the crowdsourced credentialing process as well as credential the federated profiles and the common profiles.

“In some embodiments, auto-validating the responses or credentialing done in by the plurality 204 may be included to further certify each respondent’s information 204 for each of their federated profiles at Step 508. Auto-validation can be done through one or more social networking platforms 404 that associate an expert, such as 202a, through a social network profile of the expert. This method can also include refining each federated profile rating or associating a separate rating using a mapping between each federated profile and the social networking profile at step 511. This method could also facilitate access for multiple entities to obtain responses that identify credentialing, certification and the refined rating or associated rating via the web-based portal in the crowdsourced network at Step 512. The agency may then retrieve the credentialed information of the service provider via the system 206. They may not have to verify individual expert information from multiple sources.

“In certain embodiments, auto-validating could include searching a social network database that is associated with the social media sources to verify the information about each federated profile. The method may also suggest a federated update if there is a mismatch between the search information and the profile. This method could also include suggesting that the social networking profile be updated to the social media platform 404. This allows service providers to work with social networking sources. They may also exchange information about each other, so that both sides can benefit from the credentialing process.

“In some embodiments, respondents may include one or several profile owners or other experts or persons.”

“In certain embodiments, the method may use the plurality o application programming interfaces (APIs 406) to verify information associated with each of federated profiles. This is done from the social profiles maintained by the social network platform 404. The APIs 406 can be modified to link each federated profile to one or multiple distinct sources of social networking platform 404. This will allow for a unique identifier to be maintained which associates a distinct source of social networking platform 404 with the respective federated account.

“In accordance to an embodiment herein the system 206 can be configured for social crowdsourced credentialing by certified professionals 202.”

“According to an embodiment herein the experts or professionals 202 may be credentialed or accredited by the system206 before they can work in practice locations such as hospitals or other industries.”

“In certain embodiments, experts with credentialed expertise may be used to evaluate and score documents. Documents can contain text, media and any other type digital content. The document may also include fragments or textual portions of media or other digital content. An embodiment allows for the scoring and commenting on various attributes to be done on an entire document or media. In some embodiments, review and scoring can be performed for portions of entire documents, media or other digital content.

“In accordance herewith, the system 206 can be configured to create federated profiles or federated credentialing database that may allow multiple parties (e.g. respondents 204) to crowdsource and socially credential professionals 202.”

“In accordance to an embodiment herein the system 206 can be configured so that it facilitates disintermediating credentialing services, such as allowing hospitals and practices to use them. To share each other’s credentialing using the distributed, social, crowdsourced and blockchain-configured distributed architecture. The system 206 allows the creation of profiles by experts 202.

“The system 206 can be configured to allow profiles to be created. These profiles may be shared and credentialing information can also be exchanged among different agencies or parties. One embodiment of the credentialing system206 allows credentialing between specific agencies. For example, if hospital A (first respondent or agency) trusts hospital, B (second respondent or agency), then the first agency credential is a part of the professional’s profile and the second agency credential is a part of the profile. These agencies can create a more precise profile using the system206 than they could individually by sharing their credentialing information in the form of responses. The common profile is the original profile created by experts 202. The profile can then be divided into federated profiles so that each agency may credential at most one of these federated profiles. The agencies can then credentialed the credentialed profiles. This allows the system 100 to complete an overall accreditation of the profile. The trust factor between the credentialing parties, agencies, or respondents may also be considered by the system 100 204. In the above example, the first agency might identify the second agency as a trusted source. Therefore, any profile credentialed or issued by the second agency could be accepted by the first agency. The agencies 110 can work together to credential and accredit each other by using the system 100 internally in certain embodiments without the need for a service provider.

“In one embodiment, the system206 may allow respondents 204 to disagree with each other. One respondent could credential a single profile in one way, while another respondent might credential the same profile in another way. This means that credentialing done by the second respondent may contradict the credentialing done by the first respondent for the same federated account. In such situations, the system 206 may be able to allow for the association of a degree or difference between the credentialing patterns offered 404 by two or more respondents. An expert, such as 202a, or an agency may use the associated metrics or degrees of disagreement to determine a level or trust for a specific credentialing in relation to a particular profile or federated. The system 206 may allow you to view the credentialing responses of both or more such respondents 204.

According to an embodiment, the system206 may permit a profile owner who is an expert such as202 to challenge the manner in which credentialing is done by one or more respondents to 204 for his federated profile or common profile. Any profile owner, who may be one of the experts 202, can offer his comments through the system. These remarks can be viewed by others. The system 206 can update, modify, delete, or retain the credentialing inputs of the respondents 204 based on these remarks.

“In certain embodiments, the system 206 may establish desirable standards for crowdsourced respondents to code of conduct. The system 206 can either cancel enrollment or delete credentialing information from respondents 204. The system 206 can permanently prevent such respondents from credentialing any experts or professionals associated with the system. The system 206 can be configured in one embodiment to allow crowdsourced credentialing, as long as it adheres to the established standards of credentialing. The certification engine 212, which allows multiple respondents 204 to respond, may credential them only when they meet the standards of conduct. The certification engine 212 can record the details of respondents 204 in case of a breach and then use that information to assist with future credentialing.

“In certain embodiments, the system 206 may facilitate the tracking of experts’ codes of conduct and ethical violations. The system 206 could be used to link the profiles of experts 202 to information relevant to their code of conduct, past ethical behavior, and any other information regarding the experts. This information can be gathered from many sources, or it may be reported by any other reliable expert or person, or any member of crowdsourced network106 or any subscriber to the system 206. These ethical lapses can be corrected in the common profiles of experts 202. Based on this ethical information, it is possible to update or change the credentialed profiles. If there are ethical lapses, the credentialing information for a doctor may be invalidated. The profile can be updated to reflect the ethical lapses or removed from the system 206 by one or more respondents 204.

“FIG. “FIG. 6, with reference to FIGS. FIGS. 1-5 illustrate an expert scoring module 112 according to an embodiment herein. The expert scoring module 112 determines the set of attributes that experts 202 will need. The expert scoring module 112 can be combined with or may include expert attributes engine 110 to determine the set of attributes for experts 202. The set of attributes for the experts 202 could include the crowdsourced credentialed expert determined by the credentialing engine or system 206 based upon the credentialing the federated profiles and common profiles of experts 202 by respondents 204, as discussed in conjunction with other figures. The credentialed competence of experts 202 is determined by a plurality crowdsourced respondents. This determines the extent of credentialed knowledge and the ability of experts 202 to review defined documents for which the credentialed expert is needed as an attribute. Credentialed expertise is a dynamic and non-linear parameter for scoring experts 202 to review documents based upon crowdsourcing.

“In one embodiment, the set attributes for an expert such 202a may include the reputation and trust of the expert. A reputation assessment engine 602 can be used to determine the reputation of experts 202 and indicate trust among relevant communities. For example, reputation can be measured by experts’ interactions with other experts on expert networking sites, information-exchange platforms, or other knowledge interaction platforms. An expert 202 may, for instance, interact with other experts in the same field as medical equipment design via a knowledge platform. This interaction could consist of asking questions related to medical equipment design and then submitting responses to them. Interactions like these can lead to the building or destroying of the reputation of experts 202. The reputation assessment engine 602 can help you determine the ways in which your reputation is being built or destroyed. The reputation assessment engine 602 can, for example, evaluate and assess the reputation of expert 202a based upon the quality of his questions, the quality of his answers to others’ questions, or the quality of review that the expert 202a has done for others’ answers. In such cases, the reputation of the expert 202a may be measured by counting the number of positive votes received from the community, the number of negative votes within the community, and neutral votes in response to any interaction by the expert. An embodiment allows for any positive vote, such as a comment, remark, or vote, to be added to a question by expert 202a. Any negative vote, such as a dislike comment, comment, or vote, may result in expert losing 10 points from his reputation. An embodiment allows the expert to earn 20 points for every positive vote on an answer he posts. A negative vote may result in him losing 20 points. An embodiment allows the expert to earn 25 points for a positive review of an answer. However, others may vote against the expert and cause him to lose 25 points. Other embodiments allow for other methods of assessing the reputation. The reputation assessment engine may tie the reputation of expert 202a to a specific field or community. The reputation assessment engine 602 might assign 50 reputation to an expert in the community of medical equipments design, but the same expert 202a could be assigned a reputation?20 in medical device programming. You can define the reputation as both positive and negative value points. The positive points may indicate a community’s trust in the expert, while the negative points could indicate a decrease in trust.

Voting can be used to determine the trust level. Votes can be cast in fractional or integral numbers, such as +3, +3.5 and?2, or?4.2. This will result in an average summation of all votes weighted with reputation assessment parameters (such above), that determine how many reputation points were earned with each interaction.

“Once reputation assessment engine 602 has evaluated the reputation of an expert 202-202 a in a specific field or community (which is the same or similar to the subject of the review), document scoring module 112 can use that reputation as an expert attribute to determine the score of the document. Experts 202 and the reputations of experts202 who are from the same or related fields or communities to the document under review are not considered in such cases. They are used by the document scoring module 112 to determine the validity and authenticity of documents reviewed and scored after the aggregation and analysis of reputations from different experts 202.

“In certain embodiments, reputation assessment engine 602 can also be capable of aggregating different discrete reputations of individual crowdsourced expert 202 connected over blockchain-configured networks so as to determine an aggregate reputation of a group crowdsourced expert 202 used for evaluation, review, and scoring of documents. The aggregate score could be a net equivalent score that can also be associated with crowdsourced experts202 to show the reputation of all the experts 202 who contributed to document review and scoring.

“In an embodiment, one can determine the reputation by querying corporate databases when the users are internal and looking at the past performance records based upon previous projects.”

“The set may contain an officiality that indicates a job or the designation of an expert 202a in a related job. The scoring module 112 could include or be combined with an officiality engine 604 which determines the officiality of experts 202. For example, ratings may be assigned to specific hierarchical positions that can be used to assign an officiality score to an expert. These officiality scores may be determined by the officiality engine 604 for each crowdsourced expert 202. The officiality engine 604 can be used in some instances to determine an aggregate officiality score of the crowdsourced experts 202 who contribute to reviewing and scoring the document. The aggregate score can be a net equivalent score that is associated with crowdsourced experts202 to indicate the officiality and contribution of all crowdsourced experts202 to document review and scoring. Officiality is a qualitative or quantitative evaluation of the crowdsourced expert community 202 in the context of these embodiments. This validates the scores provided by experts 202.

“In an embodiment, attributes are assigned different weights by a weigh module 606 Information about the assigned weights of experts for particular document reviews and scoring may be stored within the memory circuit 118. This information can then be retrieved by weight module 606 when the document has been reviewed and scored by scoring module 112 or the experts 202. The weight module 606 can identify the degree of importance and relevance of an expert attribute in an electronic document and assigns a weight to each one based on that level of significance. An example: The credentialed expert is weighed first by the weight 606 followed closely by the officiality. Meanwhile, reputation is weighed last by the weight module of the three exemplary attributes.

“Aside from expertise, reputation, and officiality, there may be other attributes such as geographic presence, which is indicative of spatial relations, such as if a person has been living in a certain area for a specified time or if they have spousal, family, or close relationships with experts. A good relationship with an expert, for example, could be considered an attribute.

“In this example, the weight module 606 can be adapted to dynamically alter weights and assign weights based on the type or document being reviewed. This could be determined based on the content and document type of the document. The complexity of the content of the document may also be considered when determining the weight. The weight module 606 can define content parameters that could influence the weight assignment process. It will then dynamically assign weights to the attributes of experts 202 for document scoring and review. The weight module 606 can, for example, dynamically associate weights to allow for review of both the entire document and intra-document federated areas. A first set may be associated with various expert attributes to allow for the review of a section of a document. A second set of different weights can be associated to another section. The credentialed expertise might be the most weighted in the first weights while the reputation could be the highest in the second weights.

“In certain embodiments, expert scoring module 112 calculates an aggregate score for an expert 202a based upon one or more attributes such as credentialed expertise and officiality in conjunction with the assigned weights. An expert score is a rating that indicates expert suitability to review and score a specific document.

“FIG. “FIG.7, with reference to FIGS. 7 through 6, shows a document scoring module (114) in accordance to an exemplary embodiment. Each crowdsourced expert 202 reviews the document scoring module 114 and gives it a document rating. A document scoring module 114 may allow for document review and scoring, but only those experts 202 with a minimum aggregate score of 202 can access it. Document scoring module 114 assigns an aggregate score to each electronic document. This is based on the sum of the reviews 202 by crowdsourced experts and the aggregate scores of each crowdsourced expert 202 based 202 on a set of attributes, including the credentialed expertise, reputation, and officiality. A plurality of crowdsourced expert 202 can assign document scores based on an effect of crowdsourcing index. This may not be linear with the crowdsourcing score. Crowdsourcing index can be used to determine credentialing or expert expertise. It may also be indicative of a degree crowdsourcing. The crowdsourcing index can be used in some embodiments to correspond with the crowdsourcing index for experts credentialing.

“The embodiments provide a multilevel crowdsourcing-based and calculated document scoring derived from the use of a nonlinearly relational parameter. This parameter defines a nonlinear relationship between the multilevel crowdsourcing on the experts score, and the documents scores in the various discrete levels. Multi-level crowdsourcing can include two levels. The first level may include credentialing an expert 202 by a plurality crowdsourced respondents 202, and the second level includes scoring an electronic document by crowdsourced credentialed specialists 202 that have at least a minimum aggregate expert score derived in the first level.

“In some embodiments, the document scoring module 114 includes a document aggregate score assessment engine 702, comment analysis module 704, comment aggregator 706, semantics and analytics engine 708, and document classification/tagging module 710.”

“In certain embodiments, the document aggregate scoring engine 702 calculates an aggregate score for the document based upon individual scores from the document by crowdsourced experts.202 A non-linear crowdsourcing index may also be used by the document aggregate score assessment engine 702 to determine the aggregate score. The comment analysis module 704 can analyze the comments made by experts 202 during the review of the documents. These comments can be used as a learning tool and knowledge repository when evaluating the document in depth. A subjective comment section may be added to the aggregate score for reviewers at second-level. The comment analysis module 704 can be combined with or may include the comment aggregater 706. The comment aggregator 706 may combine comments from different experts 202. The comment aggregator 706 might collate comments from different experts 202. The comment aggregator 704 and the comment analysis module 704 can be combined to enable comments classification, collation and analysis. This is possible by using various semantics, analytics and learning algorithms, functions and programs, as well as programming them with different functions, tools, and programs. The review comments are used to infer logical consequences by the semantics engine 708. To generate more relevant results, the semantics engine 708 uses semantics and machine-learning tools to determine intent and context meaning of terms in review comments. The document classification/tagging module 710 may determine a relevant category or taxonomy class and accordingly tag the document for the classified category. A number of factors may influence the category selection, such as technology areas and sub-areas, reviews, value of content, and other factors.

The comment aggregator 706, the comment analysis module 704, as well as the semantics analysis engine 708 may all be collectively referred to by Natural Language Processing-based Analysis Engine (NLP-based engine) 712. NLP-based analysis engines 712 and 711 may be used to process comments and textual information-based reviews.

“The document scoring module 112 also includes a visual scoring engine 714 to process visual and non-language feedback as well as reviews by experts 202 during electronic document review. FIG. illustrates various components of the visual score engine 714. 8. This article discusses the visual scoring engine 714, and visual reviews by experts 202. It also refers to various figures and a particular reference to FIGS. 7, 8

“The visual scoring engine 714 could include an eye tracks processor 802, an image processor 806, a micro expressions process 804, and neural networks 808. The inputs to the eye tracks processor 802 could be received from an eye movements track device or an image processor 806, and neural networks 808. The eye tracking system 810 can be set up to measure eye movements quickly and may be controlled using software and a microprocessor. A camera may also be included in the eye tracking system 810. A quadrant detector may be part of the hardware of the eye tracking device 810. This can detect the relative direction in which the expert’s eyes move. The quadrant detector’s output may be processed by the microprocessor, under the control software subsystems. The eye tracking device 810 can record the entire review session as well as the eye movements during the session. A digital file with the session, including eye movements and tracks, may be sent to the eye tracks processor 802 for further processing and scoring by the visual scoring engines 714. The data from the eye track processor 810 may be processed by the visual scoring engine 714 using special purpose processing circuitry. Software subsystems can also be used to interpret the data indicating eye movements and tracks. The eye tracks processor 802 can convert the data to high-level interpretations that indicate time lapse on particular sections of the document under consideration, repeat reading, coherence of eye focus and scrolling speed. These interpretations can be compared to predefined and stored eye patterns or vocabulary. Predefined eye patterns or vocabularies can also indicate particular interpretations and associated scores. The eye tracks processor 802 might associate a review score with the eye track data to indicate the quality of review based upon eye movements. The eye tracks processor 802 can process the eye tracking data and convert it to high-level interpretations in order to reveal basic mental states such as expert202a.

“The eye tracking information can be used to identify points of interest within an image or text of the document under review. A content provider might present an image or text to be reviewed. The eye tracking information could then be used to determine which parts of the image or text information are most interesting to the expert and associate a visual score with predefined interpretations and eye tracks patterns that may indicate visual feedback and quality review of the content.

“The visual scoring engines 714 and 804 may also include the microexpressions processor 804, which may receive data indicative micro expressions from the micro sensors 812. This may be associated to a computing device used by an expert, such as 202a. When the expert reviews a document the micro expressions scanner 812 may capture facial expressions and micro expressions throughout the review process, and transmit that information to the visual scoring engines 714 which houses the micro expressions processing 804. The image processor 806 may include the micro expressions processor 804 which can interpret facial expressions and micro expressions from the microexpressions sensor 812. The micro expressions processor 804 may be included in the image processor 806. The image processor 806 may contain the micro expressions processing 804 as a discrete component. They can be connected communicatively or operatively, in this example.

“The computing device of expert 202 a may be linked to the micro expressions sensor 812. The micro expressions sensor 812 can be used to detect gestures and human expressions, and transmit this information to the microexpressions processor 804. The micro expressions sensor 812 can be embedded in a camera, or optical sensor. The micro expressions sensor 812 can be used for face detection, recognition, image acquisition and video capture.

The image processor 806 could contain image processing circuitry as well as an associated memory. The micro expressions sensor 812 data may be received by the image processor 806. It can perform various processing tasks, such as normalizing and extracting facial images with different imaging filters. Image pre-processing may include cropping, resizing, lighting and coloring to extract facial features. It also might remove unwanted features like hair, background or extra features from facial expressions sensor data 812. This data does not provide any information about facial expressions. The image processor 806 produces an output that can be used by micro expressions processor 804 for interpretation of micro expressions. This is done using mathematical algorithms, without limitations. These interpretations can be used to identify facial characteristics, emotions, gestures, and moods. These micro expressions can be used to identify facial characteristics, moods and emotions, as well as gestures. These are collectively called micro expressions. The facial expressions sensor 812 reads micro movements of the bodies of experts 202 to determine their meaning. This information is taken by the micro expression processor 804 as input and then interpreted by complex algorithms using either statistical approaches, artificial intelligence, and neural networks 808. The micro expressions processor 804 can be used to identify the human face and any associated facial characteristics. The micro expressions processor 804 can detect faces from a variety of video frames and extract facial expressions and movements to an output file.

The interpretation of facial expressions could reveal information about the review done by experts 202. The microexpressions processor 804 can store predefined expression patterns in a memory circuit. This may be used to match the processed micro expressions with facial inputs to determine the expert’s review thoughts via visual feedback. These micro expressions can be used to interpret review thoughts that may otherwise be hidden or suppressed in textual reviews or text-based comments.

Summary for “Distributed electronic review of documents in a blockchain system, and computerized scoring based upon textual and visual feedback.”

“Technical Field”

“The embodiments are generally related to electronic document validation and, more specifically, crowdsourced electronic document review/scoring utilizing textual and visual feedback from reviewers.”

“Description of Related Art”

Many organizations offer financial aid and other rewards, such as grants. For valuable ideas. Many organizations don’t know how to select the most valuable ideas from the many ideas that have been submitted for evaluation. Many times, the feedback is not textual. Therefore, relying only on review comments and textual feedback may not suffice for a proper evaluation. This makes evaluation difficult and less reliable for these organizations.

“There is therefore a need to develop a system and method for electronic document review and scoring that uses different types of visual and written reviews from reliable and verified sources.”

“This embodiment presents a distributed blockchain-based architecture-based system in communication network. The system comprises a memory circuit that is communicatively connected with the communication network to store a plurality digital profiles associated to a plurality crowdsourced experts and further store a plurality digital segments associated with each of these digital profiles. These digital profiles and segmented digital profile are created using a plurality digital sources and electronically linked across the communication networks. A credentialing engine is included in the system to enable a plurality crowdsourced respondents to respond and credential each expert. The credentialing engine also contributes to credentialing the expert’s digital profile upon collation of credentialed segmented online profiles. Credentialing of the expert’s segmented digital profiles is done by a number of respondents through a computerized crowdsourcing algorithm. Crowdsourcing index shows the number of experts credentialed by respondents and it dynamically grows with increasing number of respondents. To determine the attributes of experts, the system has an expert scoring module. The set of attributes comprises one or more of crowdsourced credentialed expert knowledge. It is based on the credentialing and reputation of experts from the respondents. Officiality indicates a job or position of experts in a relevant field. Each attribute may have a different weight assigned by computer. An expert scoring module calculates the aggregate score of an expert using the associated weights and one or more attributes. Electronic document scoring engine is also included in the system. This allows crowdsourced experts to review and comment on electronic documents and give their opinion. Crowdsourced experts could have a score that is higher than a threshold. Natural language processing-based (NLP) analysis engine is used to process comments and reviews based on textual information. This engine can be used in conjunction with crowdsourced experts for textual review of electronic documents. The document scoring engine also includes a visual scoring engines for visual and non-textual reviews and feedback from crowdsourced experts. The visual scoring engine is controlled by an eye tracks processor that receives inputs from the respective eye tracking systems of crowdsourced experts. This processor then processes the inputs to assign a review score based upon predefined eye track patterns. A micro expressions processor is part of the visual scoring engine to receive information indicative of micro facial expressions extracted from respective micro expressions sensors that are associated with computing devices used by crowdsourced experts. The micro expressions processor is comprised of an image processing circuitry with associated memory. It interprets the micro facial expressions and compares them to predefined facial patterns in order to assign a review score. Further, the document scoring engine can associate an aggregate score to electronic documents based on the aggregation and visual review scores of individual textual and visually reviewed documents. This is done by processing the textual and visual reviews of crowdsourced experts who have reviewed the document. A graphical user interface is provided by the document scoring engine that displays an output indicative of the aggregate score of each document reviewed by crowdsourced experts. It also includes information about who and how many times the document was reviewed. A device for expert identity validation is included in the system to verify identities of crowdsourced experts prior to or during review. The expert identity validation apparatus includes a device patterns assessment tool to extract and process the device information from the computing devices of crowdsourced experts. It also verifies the extracted information against predefined crowdsourced expert information. The network patterns assessment device is part of the expert identity validation device. It receives and processes network information from the appropriate agent devices that are associated with the crowdsourced devices. This information can then be verified with the predefined network information for the respective crowdsourced specialists. For processing validation, the expert identity validation device also includes a geospatial mapping tool to perform geotagging of crowdsourced experts as well as documents. Geo-tagging is performed using geo-spatial data received from a GPS-based device. The expert identity validation devices includes a facial expression validation unit to process facial expressions from the respective facial expression sensors that are associated with the computing devices used by crowdsourced experts. It also verifies identity according to the predefined facial patterns. The facial expression validation unit includes a digital acquisition device and multichannel amplifiers that pre-process and amplify signals sent by facial expression sensors.

“The embodiments and their various features and beneficial details are described in detail with the help of the accompanying drawings. They are also illustrated in the following description. To not obscure the embodiments, we have omitted descriptions of well-known components. These examples are provided to aid in understanding the various ways the embodiments can be used and to make it easier for those skilled in the art to use the methods. The examples are not meant to limit the scope of the embodiments described herein.

“In the following detailed description, we refer to the accompanying drawings which form a part of this document. These are used to illustrate specific embodiments that can be practiced. These embodiments are also known as “examples” in this document. These embodiments, also referred to herein as “examples”, are sufficiently detailed to allow those skilled in art to use them. It is also to be understood that embodiments can be combined or that other embodiments may have been utilized.

“In this document the terms?a?” or?an? are used. “The terms?a????? or?an?? are used in this document. As is usual in patent documents, they are used to include more than one. The term “or” is used in this document. This document uses the term?or? to mean a?nonexclusive? Unless otherwise stated.

“FIG. “FIG. The ecosystem 100 can facilitate the implementation of an expertise-driven review and scoring (also known as electronic document review system, EDRS) 102 for electronic documents in a crowdsourced system 106. An ecosystem 100 could include a server computer 108 that is connected to the electronic documents review and scoring system (EDRS) 102. The EDRS system 102 could include an expert attributes assessment engine 110 and an expert scoring module 112. A document scoring module 114 may also be included. A processing circuit 116 may be added to the ecosystem 100. A memory circuit 118 may be added to the ecosystem 100.

“In one embodiment, the ecosystem 100 facilitates crowdsourced review and scoring electronically by a plurality crowdsourced experts or reviewers. A set of attributes may be used to shortlist the reviewers. This allows them to evaluate the documents and assign a score. Expert attributes engine 110 may define and consider these attributes. These attributes could include, for example, crowdsourced credentials, crowdsourcing index and officiality. Crowdsourced credentialing can indicate a level of credentialing by multiple respondents. For example, it could be indicative that the expert or reviewer has scored the expert based on credentialing or the expert profile of multiple respondents. Crowdsourcing index can be used to indicate the level of crowdsourcing, which is the number of experts credentialing them. An embodiment of the crowdsourcing index effect on an expert might show a non-linear relationship between expert score and number of experts credentialed. The relationship could be exponential, for example. An official title may indicate a position held at an organization. A person’s reputation can indicate how trustful an organization or community is in an expert.

Each attribute may have a different weight in the examples. The assignment of weights to experts’ attributes may be influenced by parameters such as document type, complexity, expert profiles, country and location of the expert, importance and scoring objectives, and so forth. For example, the highest weight can be assigned to officials, credentialed expertise, reputation, and so forth.

“The expert scoring module 112 could facilitate cumulative scoring of an expertise based on defined attributes and the assessment of each expert using the attributes engine 110. The scoring module 112 could assign a score to an expert using a cumulative ranking of experts for each attribute and taking into account the weightages of those attributes. There may be sub-modules or engines within the expert scoring module 112 that can help in evaluating an expert’s score according to each attribute. As will be explained later, the expert-scoring module 112 may also include a credentialing system and reputation assessment engine.

“The document scoring module 112 assigns a score for the document based upon an associated cumulative score that is based on the scores of each crowdsourced expert/reviewer. Expert scoring module 112. The cumulative score calculated from the scores of the plurality crowdsourced experts may account for the impact of crowdsourcing using the expert scoring module 112. This may have a non-linear effect upon the final cumulative score. The crowdsourcing index can be statistically defined for different numbers of experts who have reviewed a document. A crowdsourcing index 1 can be used to multiply the crowdsourcing impact. A crowdsourcing index of 1.2 could be used for a range between 21-40. A crowdsourcing index of 1.5 could be used for a range between 41-60. Another example is that the crowdsourcing index can be dynamically determined with an increase in effect for each additional crowdsourced expert involved in the review process. A mathematical relationship can be used to determine the crowdsourcing index in such cases. This relationship could be described as an exponential increase in crowdsourcing index value and an increase in number of reviewers.

“The memory circuit number 118 stores a variety of common profiles that are associated with crowdsourced experts. Further, the memory circuit 118 stores a number of federated profiles that are associated with each common profile. The federated profiles and the common profiles are created using a variety of federated sources spread across the crowdsourced network (106). We will discuss the common and federated profiles later.

“The processing circuit 112 includes various processing components. It is capable of processing tasks such as aggregating profiles and federating common profiles. Rating and scoring experts, assessing review, scoring the documents, and other tasks, as described in this document. The processing circuit 116 could, for example, be combined with the expert attributes engine 110 and expert scoring module 112. These modules can perform these and other tasks.

“In one example, the crowdsourced social network could be a blockchain-configured social integrity network. This means that experts, reviewers, or participants can connect with the blockchain-configured social integrity network via distributed access points. All participants have access to different systems and subsystems of the ecosystem 100 in distributed fashion. They can manage, share and edit, annotate, and review documents simultaneously within the authorized access rules.

The blockchain-configured ecosystem and its components, also known as a “smart contract based distributive integrity network”, may not require an operator for centralized information exchange (IE). All participants can have access to distributed ledgers to ensure a secure exchange, without trust breaches, and all may be able to see the distributed ledgers. This allows for disintermediation, as human participants can be removed from the chain of participants (entities). The documents to be reviewed are stored in a variety of locations on the blockchain, which allows participants to access them simultaneously. This makes it possible for participants to update and review the documents almost instantly. Blockchain-configured ecosystem offers a secure, distributed, and disintermediated framework that enables the integration and support of information across a variety of stakeholders and uses. Blockchain-configured digital ecosystem provides a secure and distributed platform for patient digital identities. It allows access to personal connected health devices, home health devices, storage devices and servers hosting documents. The use of private keys and public keys is secured by cryptography. This protects identity of participants and reviewers. Because the blockchain-configured digital ecosystem is distributed, it allows for shared data that provides real-time updates to all authorized entities. This makes the network accessible to all authorized parties without the need of a central authority or exchange. We will discuss the blockchain-configured ecosystem in more detail with subsequent figures.

“FIG. “FIG.2.2, with reference to FIG. 2. Referring to FIG. This environment includes a number of experts 202a-202d (collectively referred as 202) and a number of respondents 204a-204c (collectively referred as 204) that are connected to a crowdsourced network. 106. The network 106 is connected to a credentialing system (206), which is accessible by experts 202 and respondents 204 via the network. This can be done, for example, through a portal or web-based interface (not shown in FIG. 2).”

“The network 106 may use a wireline, a wired communication channel, or both. A wireless communications network can include, but is not limited to, a digital cell network such as the Global System for Mobile Telecommunications network (GSM), Personal Communication System network (PCS), or any other wireless communication network. A wire line communication network could include, but is not limited to, a Public Switched Telephone Network, proprietary local and long-distance communications network, or any other wireline communications network. The network 106 could also include digital data networks such as one or two local area networks (LANS), one, or more wide-area networks (WANS), or both LANS/WANS, to enable interaction with credentialing system (206). The crowdsourced network 106 may contain one or more networks. These networks can include public networks like the Internet and private networks. They may use any protocol or technology such as Ethernet, Token Ring or Transmission Control Protocol/Internet Protocol (TCP/IP) to allow interaction with credentialing system. The network 106 may be a social integrity network that is blockchain-configured.

One or more of the experts 202 may include a doctor, surgeon, physician assistant, or other healthcare professionals. One or more of the respondents 204 could include a doctor, doctor, surgeon or healthcare expert. They may also include any other healthcare professional or organization like a hospital. Any other person may also be interested in the credentialing and accreditation process for the experts. Multiple industry-related agencies (e.g. hospitals, nursing centres, research institutes and financial companies), financial agencies, transportation agencies, energy-related agencies, etc., can also access the system to obtain credentialing or verification services from the system. The credentialing information obtained by respondents 204 may be used to provide services to these agencies by the system 206.

“Experts 202 and respondents204 could be connected to, for example with any type of electronic data processor or communication device, or a client device, connected to the communications network. Personal computer systems such as laptops, desktops, servers, computer systems on the network, computer networks, personal digital assistants, wireless communications devices, mobile electronic devices, tablets, and other electronic data processing systems are all examples of an electronic data processing device or client device. Client devices and data processing systems may include hardware/software computing devices that can perform computational tasks such as profile creation, modification and verification. These tasks can be done via a standalone application, via a Web browser graphical user interface (“GUI”) or via a Rich Internet Interface (?RII?). A computer program that is part of an online social network system may implement the embodiments herein. This embodiment may also be implemented using distributed blockchain-configured architecture. The credentialing system 206 may be used with a client device that is equipped with a Web browser or any other Web-enabled device. It can connect to the crowdsourced network 106 using a Windows, Macintosh or UNIX operating system.

“The credentialing model 206 allows for the creation of profiles of experts 202, including details about them. These profiles can then be stored in the system.206. These details can include personal information, education history, and other similar information. These profiles can then be shared with multiple respondents 204 and experts202 according to set standards, preferences and rules that allow for a federated exchange capability. This allows distinct parts of the profiles to be credentialed, accredited or verified and can be shared or exchanged with experts 202 and respondents 204 in an federated fashion. Further, the system 206 provides credentialing and verification capabilities that allow each expert 202 to be credentialed by another expert or respondents 204 in order to use credentialed profiles created by agencies or organizations. The system 206 may also allow for the creation of a federated model of profiles. This allows the credentialed segments or sections of profiles to be credentialed or verified by distinct federated respondents (204 in the crowdsourced network 106) so that crowdsourcing increases trust, authenticity, and reliability in credentialing and credentialed information.

“The credentialing system (206) as shown includes a federal profile manager 208 and segmenting or federation engines 210. A certification engine 212 is also included. These are discussed in detail below.

“The federated profiles manager 208 can receive profile creation information from the plurality experts 202. The federated manager 208 will maintain the information received from experts 202 and make changes as required by the experts. The federated profile manger 208 can be linked to multiple sources of information, such as their social networks, educational institutions, work environments, and other relevant information. The federated profile manger 208 collects information across a variety of sources for each expert 202 and compiles the records and information into a single profile of each expert 202 that is associated with and communicates with the system. For example, the profile manager 208 may gather information from federated sources like Linkedin and Myspace, About.Me or education institutions. The system 206’s common profile may be viewed by experts 202, respondents.204, relevant organizations, and any other entities or persons associated with the system.206. The distributed access points of the Blockchain-configured architecture may be accessed by the experts 202, respondents 204, relevant organizations and any other person or entity for near-real-time management or review of process. The federated profile administrator 208 may be able to automatically retrieve profile information from social networks in some embodiments. The federated profile manager may, in some instances, keep information submitted by experts 202.

“The federated profiles manager 208 may enable the experts 202 maintain their profiles in system 206. It protects the information in their profiles from unauthorised access and connects their personal profiles. Further, the credentialing system (206) may allow the profiles and any information to be searchable by both the experts 202 or the respondents 204. The experts 202 can then access the portal or user interface via a web-based interface. After completing an initial registration, the experts 202 may create and update their profiles using the user interface. The experts 202 can then register by filling out a registration form. They will need to enter an email address and a password. After completing the registration form, experts 202 can create their profiles and fill in the information. Profiles describe the user’s past, experiences, abilities, titles, roles and skills, as well as their goals, objectives, employment organizations, work stations, and other relevant information. Experts 202 can add contacts to their database by entering contact information and relationship information. They also have the option of linking to the contact’s profile on the system. The experts 202 may authorize the use of the contact information in the credentialing system. Experts 202 might not wish to have their address book integrated into the system 206. The experts’ address book could be uploaded but not integrated into credentialing system.106. This would make it difficult for others to see. Contact information and profiles can be stored in either a central or distributed database. The system 206 could include or be linked to a profile database 214, which may contain the information relevant to the profiles of experts 202.

“In certain embodiments, once expert 202 joins the network106 and subscribes to the credentialing program 206, all information in the profiles are available for credentialing or verification, accreditation, etc. So that all profiles can be credentialed from the multitude of crowdsourced respondents, 204 the system 206 can verify them and credential them. Credentialing can also be used to determine whether the profiles are accurate, reliable, trustworthy, genuine, fraudulent, or authentic.

“In other embodiments, once the plurality 202 experts join the network 106 the profiles are divided into distinct sections or segments that are referred to by the federation 210 as federated profiles. The segmenting engine210 can receive common profiles from profile manager 208 and then segment them into federated segments, portions, or profiles. The federation engine210, for example, breaks down a common expert profile into multiple federated profiles. This is based on similarities in the content of the federated profils. Crowdsourced respondents 204 treat the federated profiles as separate profiles to allow them to be credentialed separately. A common profile P may contain the following details:

“For simplicity of description, some details are not included in the profile. However, many other details can be included without limitation. The segmenting engine 220 may be used to separate the profile into different federated profiles. In some embodiments, for example, the profile above may be divided by the segmenting engine 220 into several federated profiles, such as the one below.

“A single profile can be segmented by segmenting engine210 in 35 discrete federated profiles, which are different in one or another way. The segmenting engine 210 can be set up to segment a single profile in as many federated profiles and as many different ways as possible, according to various embodiments. The entire information in a single profile is then divided into multiple federated profiles. The above-mentioned common profile can be converted into 35 federated profiles. After segmentation, the federated profiles can be communicated to federated profile manager (208). The federated profile manager208 stores both common profiles and federated profiles associated to the experts or professionals 202 in the profiles database 214.

“The segmenting engine210 may contain hardware and software components that can perform computational tasks related to the segmentation of common profiles into federated profiles. The segmenting engine210 may then be used to further group the segments or federated federated profiles into groups for the same experts. 202 This allows the groups to include similar federated profiles that are based on specific parameters. The work experience federated profile segments 27, 30 and 33 which define different companies where an expertise was employed, may be combined to create a new type of profile. This is referred to as a sub-profile. Similar to the above, other groups can be created to create sub-profiles that are based on different combinations of profile segments or segments. Credentialing system 206 allows for easy maintenance of common profiles, sub-profiles, and federated profiles by the same experts. This provides a three-level profile management facility. This document does not limit the use of the terms portion, segment, and federated profile.

“The credentialing systems 206 also includes the certification engine 212, which is coupled with the segmentation engine 220 and the federated profiles manager 208. The certification engine 212, which allows crowdsourced respondents (204), to respond to the classified and segmented profiles of the plurality 202 experts, 202 and to credential them, is designed to do this. Credentialing each segment or federated profile associated with an expert202a of the plurality 202 is necessary to credential the entire expert202a profile. The exemplary profile, as shown above, includes 35 segments. Credentialing each segment has an impact on the overall credentialing for the whole profile. If all thirty-five segments have been credentialed by one or more respondents, 204, trust can be established about the profile information. The information could be considered true or authentic. The trust in each segment increases as more people or respondents from the plurality crowdsourced respondents204 verify the information. The crowdsourcing index can also be used to measure and account for the level of crowdsourcing. The crowdsourcing index could have an exponential or non-linear relationship to the number of experts crowdsourcing. As more experts are credentialed, the trust and reliability of expert credentials may rise non-linearly. Crowdsourcing can help credentialing be more accurate and reliable than if it is done from a limited number of sources. The accuracy of the overall profile can be calculated based on the cumulative effect of accuracy from all federated profiles. If the first ten segments of the above common profile are verified, and the rest of the segments are not verified by respondents 204, it may not result in a high level of accuracy. Credentialing and verification may still be required for the remaining segments, but this could be acceptable to some extent. The overall profile could be deemed inaccurate if all 25 segments are rejected by respondents 204. The credentialing of the expert 202a may also be highly authentic and reliable, as the discrete federated profiles are credentialed by the multitude of crowdsourced respondents.

“The certification engine 212 is designed to certify the stored profiles of experts 202, such as engineers or physicians. Experts 202 must verify their credentials for use by different agencies. They can also use the certificates to submit forms to companies, such as for hiring purposes, document review, or other purposes. Credentialing information for a specific expert 202 is first input as a common profile. Then, each federated profile is segmented and credentialed individually using the crowdsourced network of multiple respondents 204. Credentialing information for each profile is valid, more accurate, and more acceptable than the single verified profile. However, special attention might not be given to every record in the common profile. Crowdsourcing is more reliable than single verifications by one source. According to certain embodiments, each segment may have a number of credentialing sources that credential a particular federated account. This is to indicate the accuracy of the credentialing information. A federated profile may be considered acceptable if it is credentialed by 18 sources within the network. The credentialing information, such as who and when credentialed a federated profile, may be linked to each segment’s credentialing. This allows authenticity to be assessed by associating the overall impact of the credentialing of the federated profiles, trust factor about the source that verified, and relevance about when the verification was performed. In such embodiments, a multiscaled and cumulative score can be calculated and multi-scaled or cumulative credentialing may take place based on that multi-scaled cumulative score. A single federated profile can be verified by a plurality of crowdsourced respondents (204). Therefore, the credentialing system206 could determine the extent of inconsistency among multiple credentialing by different respondents 204 for the identical federated profile. The system 206 can be used to calculate an index of consistency based on the distribution of credentialing among the various respondents 204. The credentialing system may generate a map showing the extent and coverage of inconsistencies between the various responses and credentialing for similar federated profiles. This map, together with the inconsistency indicator, can be used to determine the level of trust in overall credentialing for the same federated profile. This may be repeated for each federated profile for a common expert profile, such as 202a. It may also determine an overall index for inconsistency, overall distribution map, and overall trust factor for that profile.

“In some embodiments, different agencies, such as document reviewing agencies and ideas evaluation agencies, may use the credentialing data, index of consistency, and distribution map, as obtained from system 206. Credentialing information can include information about who was credentialed or verified, what verifications were used, the trust factor associated each verification, as well as information on the relationship between a respondent and an expert, such as 202a or any other factor. The credentialing information can be submitted to experts 202 along with other forms. You can include information about your personal history, education, affiliations with hospitals, institutes, etc. Credentialing is possible. Credentialed information can include the person’s name and address as well as practice specialties, appointment status and associations. Credentialed information also includes credentials (including educational background and residency programs), state licensing information and information about malpractice liability insurance. Personal and professional references are also possible. The federated profile manager, 208 may store all of this information in the profiles database.

“In certain embodiments, the certification engine may be coupled with or include a profiles certificate database 216. As discussed above, the credentials information may be included in the profiles certification database 216. The profiles certification database database 216 may, in some embodiments, be contained within the profiles database 214. This allows for the storage of both the credentials or certification information.

“In certain embodiments, when creating a common profile and uploading information to the database, each professional may need to complete a separate application form. The application form information may be provided to the profiles database 214, which may contain expert profile information. The information can be stored in a series of expert profiles that are logically organized and may be used to segment the data using the segmenting engine 220. The segmenting engine 210 may initiate the process of segmenting automatically if new or updated information is available. If the past information has been modified, the segmentation task can be performed again to update the profile and credential the new federated profiles. If this happens, it may be necessary to revise only the relevant credentialing based on the updated information rather than rejecting all federated profiles and associated credentialing information.

“FIG. “FIG. The credentialing system (206) in accordance to an embodiment is illustrated in FIGS. The system 206 can include a profile management and certification server 302, as shown. Profile management server 302 contains a profile information collection module 306, a federated profile manager (208), and the profile segmenting engines 210.

“The profile information collection module 306 can be used to generate information about the plurality experts 202. The profile information collection module 306 may be stored separately from the Federated Profile Manager 208, while other embodiments allow it to be integrated with or coupled with the Federationed Profile Manager 208. By distributing application forms via a graphical user interface, experts 202 have the ability to generate the profile information for the plurality of experts. The experts 202 can then fill out the forms and submit them with the system. The federated profile manager can transform the information into profiles. Segmenting engine 210 can then use the profile information to perform the task of segmenting the common profiles into the federated profils associated with each expert 202.

The profile certification server 304 can be communicatively linked to or included with the profile management server 302. The profile certification server (304) may contain the certification engine, segment rating engine 308, or a profile rating engines 310. A segment certification engine 312, and a profile engine 314 may be included in the certification engine 212.

“The segment certification engine 312, may be used to credential or certificate the federated profiles that are associated with the common profiles of each expert 202. The segment certification engine 312 allows crowdsourced respondents (204), to respond to the federated profile associated with the common profiles of the plurality 202 experts and credential them. Credentialing each of these federated profiles with the common profiles for each expert 202 is necessary to credential the entire profile of experts 202 after collation of credentialed profiles. Credentialing the respective federated profile increases in trust as more people or respondents from the crowdsource respondents 204 verify the information. Crowdsourcing could allow credentialing of federated profiles to be more accurate and reliable. The credentialing of the discrete federated profiles associated to an expert 202 is based on the plurality crowdsourced respondents. 204 This credentialing may be considered highly authentic, reliable, and acceptable by agencies and third parties. The crowdsourcing index could also be used to account for the impact of crowdsourced credentialing, as previously discussed.

“The segment certification engine 312, which certifies the stored federated profiles of experts 202, is designed to verify their credentials. In some embodiments, each segment may have a number of credentialing sources associated with it. This is to show the accuracy of the credentialing information. The relevant information regarding credentialing such a who, when, and whereabouts of credentialing may be associated with each credentialing for each of the segments. This allows authenticity to be assessed by associating the overall impact of the credentialed federated profile’s credentialing, credentialed number, trust factor about the source, relevance about the source, and the time they were verified. In such embodiments, a multiscaled and cumulative score can be calculated and multi-scaled or cumulative credentialing may take place based on that multi-scaled cumulative score.

“The information regarding credentialing for individual federated profiles associated with an expert, such as 202a, may have an impact on the overall credentialing. Individual credentialing from federated segments can contribute to the overall credentialing for the common profile. For example, the credentialing may be determined by the credentialing associated with each credentialing. Credentialing for the overall common profile is determined by the combined contribution taking into account weightage effects of each credentialing. The profile certification engine 314 may perform the task of credentialing an overall common profile that is associated with an expert, such as 202a. The profile certification engine 314 can, for example, facilitate credentialing the entire profile based on the combined effect of credentialing the federated profiles that are associated with the expert profile. The profile certification engine 314 can receive information relevant to credentialing each of the associated federated profile with a common profile. It may then associate the defined weightages to each profile and perform cumulative credentialing for the common profile. An embodiment may determine the weightages based on parameters set by the service provider that operates the system 206. These embodiments may allow for weightages to be determined based on past experience or current knowledge about the importance of credentialing in different segments. When applying for a job, accuracy in credentialing information may be more important than information about hobbies or work history. The objective use of credentialing information can influence the determination of weightages and thus the overall credentialing. In some embodiments, the credentialing process may include a score that indicates the impact of the objective. An agency may require the credentialing information to determine the weightages in some embodiments. In such cases, the profile certificate engine 314 can credentialize the common profile in a custom-defined manner, as well as in conjunction with the objective score.

The segment rating engine 308 is also part of the profile certification server 304. “The segment rating engine 308 can assign a rating to each credentialed profile. It is based on the credentialing provided by the crowdsourced plurality 204. The rating depends on the level of trust and accuracy associated with credentialing the federated profiles. The rating will depend on the following: who credentialed the federated profiles, when they were credentialed and how many times. Relevance of respondents 204 to the federated profiles, relationship between the respondents 204 and the expert, such as 202 of the credentialed profile.

“The profile rating engine 310 may also be included in the profile certification server 304. The profile rating engine (310) is used to assign a rating to an entire profil based on the credentialing of each federated profile and the ratings associated with each federated profile as determined cumulatively by the segment rating engines 208.

“Profile management server 302 can be coupled to the profile database 214 in order to store information relevant to the profiles of multiple experts 202. The profiles database 214, which may be coupled with the federated manager 208, can store information in the profiles database 221; the federated manager 208 will then keep the information in the profile database 214.

The profile certification server 304 can be linked to the profiles database 216. The credentials database 216 stores information relevant to credentialing, such as the certification status of the federated profiles or common profiles that are associated with the plurality 202 of experts. The certification status could include verification in progress, verified segment, verified profile and segment rejections. The certification engine 212 and the profiles database 221 may be combined with the certification database 216.

The certified profiles database 312 may also be linked to the profile certification server 304. The certified profiles database 312 could be further coupled with the profiles certification database 215. The certified profiles database 216, which can be used to store verified profiles, may be set up to hold profiles. A preference or set of rules may allow an entity or agency direct access to the certified profile database 316. An entity could be a medical entity, such as a hospital or nursing center, doctor or physician, or a healthcare department. It may also belong to another industry, such as the financial sector, energy or transportation, or any other agency or third party. Further information may be stored in the credential database 316 or certified profile. This includes personal demographics, work history, education, affiliations to hospitals, or other institutions, etc. One or more experts 202 that correspond to one or more verified profiles.

The profiles database 214, certified profiles database 216, and certified profiles database 312 can be linked to a profile sources database 314. Information about the profiles database 214, certified profiles database 216, and certified profiles database 312 may be linked to the crowdsourced network. This information could also include information about the sources that respond to the credentialing requests. In the crowdsourced network, for example, the plurality 204 of respondents may credential the profile federated profiles. The profiles sources database 314 could store their details, including their names and other information. It may also include information about their relationship to the experts 202. This information may include the time and place of credentialing and any other pertinent information.

“Example: The profiles database 214, certification database for profiles 216, and certified profiles database 312 can all be blockchain-configured so that they are accessible by entities (experts and respondents 204) and any other agency through the distributed plurality access points simultaneously. This allows them to view or reflect reviews and any changes during the review process in close real-time.

“FIG. “FIG. Another embodiment of the credentialing systems 206 is illustrated in FIGS. As discussed above, the credentialing system may also include the profile management and certification servers 302 and 304. Further, the system 206 could include an auto-validation engines 402 and 304. Further, the auto-validation engine 402. is communicatively connected to a social network platform 404. Information related to experts 202 is stored on the social network platform 404. The social networking platform 404 might host experts 202’s social profiles. Here, experts 202 can store and update their personal, professional, and other details, as well as communicate with other social network contacts, such friends, relatives, or other networking contacts.

“The auto-validation engines 402 and 212 are configured to further certify the credentialing of federated profiles. The auto-validation engine 404 performs the second level certification using information from the social networking site 404 about one or more experts 202. An expert like 202 a could be associated with a social network website, such as Linkedin or Facebook. Each social networking site may have a different expert 202a. The information from social networking profiles can be used to verify the credentialing of expert 202a for specific profiles.

“In one embodiment, the credentialing of the respondents 204 is used for associating a rating and defining a level trust for the common profiles and the federated profiles. Further verification using the information from the social profiles 202 of experts may add another rating or score for the federated profile. This may allow the level of trust to be established about the plurality 202 of experts and their federated and shared profiles based upon the cumulative effect of credentialing, the auto validation of federated profiles, and the common profiles. Based on the individual scores of the respondents 204, the cumulative score may determine a net rating as well as overall credentialing for the federated profiles. Agencies, organizations, or other entities may access the federated profiles and common profiles together with information relevant to the credentialing or the auto-validation to establish a level of trust in credentialed information.

“The auto-validation engine 402 may contain application programming interfaces (APIs), 406, a social network engine 408, or a module for updating profiles 410.

“The social network engine 408 is linked to one or more social media servers 412. The social networking engine 408, which can be controlled by the 412 social network server, is designed to process the credentialing system’s request 206. It retrieves information from social profiles and verifies the common and credentialed profiles using the information from these profiles. Social networking engine 408 is communicatively connected to the social network platform 404 via the social network server 412, to allow interfacing the system 206 and the social media service or platform. The social network server 412 can provide a programmatic interface through the network 106 to allow access to the social profiles of the system 206. The social networking server 412 might store social data about the experts 202 from the social profiles hosted on the social networking platform 404. This data can be used to link the social data with credentialed federated profiles to verify or update the credentialing via auto-validation.

“The APIs 406 and 407 may be used by the social networking engine 408. To verify the federated segments associated to the plurality of expert 202, based on information in each expert’s social profile maintained by the social network platform 404. The social profiles created by the social networking platform are different from the federated profiles or common profiles of experts or professionals 202 maintained by federated profile managers 208. APIs 406 allow auto-validation that determines the extent of mapping between information in two different profiles, one maintained by the federated manager 208 and one maintained on the social networking platform. Social networking platforms 404 can include multiple social networking sources. Social networking sources could include, without limitation, social networking websites, educational institutes, employers’ databases, etc. An expert like 202 a could be associated with one or several of these or other similar social network sources on the social networking platform 404. The APIs 406 can be used to link federated profiles with one or more distinct social networking platforms 404 sources. This creates a unique identifier that associates a separate source of social networking platform 404 with a federated profile.

“The profile update module 410 can be used to modify or update profiles based upon further verification of the auto-validated federated profiles. The auto-validation module 410 can request to modify federated profiles, sometimes after credentialing has been completed by respondents 204. In some cases, however, this may be done after the experts 202 have granted permission. The profile update module 410 can be communicatively connected to the profile management system 302, so that the federated profile manger 208 can store and maintain modified federated profiles.

In one embodiment, the social networking site 404 can be described as a network that has an arbitrary number of computers connected to it. Registered social profiles allow users to access the social network 404 from a variety of computers. Social network 404 allows users to post and share online profiles, data, and clinical reviews simultaneously from any of the arbitrary many computers, including a respondent’s, expert’s, patient’s, or clinical provider’s.

“The social network platform 404 could include one or more social networks sources. These sources could be social networking websites, educational institutes, employers’ portals or databases, hiring agencies’ portals and other sources that can help create a socially aware network. Linkedin and MySpace are just a few examples of social networking sites.

“A service provider can deploy the credentialing systems 206 and provide credentialing and services to different organizations or agencies. This could include a hiring agency or recruitment and selection department or agency, document, inventions or ideas scoring and scoring and evaluation agents, an entity like a hospital, medical institute, research institute education institute, transportation company or energy department, financial institution, and so on. These systems can be used in-house by organizations like document or inventions, ideas scoring and evaluation organisations for the evaluation of ideas and documents. A profile of an expert, such as 202a, may be submitted to the service provider. This information may be stored in system 206. The service provider can verify and credential the profile details and other information submitted by expert 202a. They may also store information relevant to the credentialing process of expert 202a. A crowdsourced network of 106 people may be used by the service provider, including the respondent 204a or author 204a, who could also be any expert or any of those 204. The service provider, expert202a, and respondent/authorizer 204a can connect over the network106 via a web-based user interface that could serve as a portal. The portal or interface may provide a subscription section through which the entities such as the expert 202 a, agency, or the respondent/authorizer 204 a may associate them with the credentialing system 206. Each section may have different sections for the expert 202a, respondent (204 a), and agency. After subscription, expert 202a can submit his details to system 206 and/or create an account.

“Profile information may be visible publicly in certain embodiments, or may be made visible by the specific respondent for credentialing purposes and to receive responses from the respondent. 204a About the expert 202a The system 206 may store the profile information. It may be credentialed or verified in whole or in parts, as described above. The portal section devoted to such agencies may allow the agency to obtain accreditation or credentialing information about the expert 202. The agency can access the web-based portal to obtain credentialing information, as well as other information, by visiting the single central system 206. It may also be able to view the profiles of experts and other information. The credentialing is performed by the server 108 from a crowdsourced network 202. This means that the accuracy and reliability of the credentials and authenticity, as well as the reliability and reliability of the profile information, may be greater. Therefore, agencies can have greater trust in the information. The credentialing is more precise because the profile information is divided into federated profiles. This means that the agency can easily determine which information has been verified or pending verification. The agency may be able to determine who verified a particular profile in federated form, when it was verified and how many verifications were performed for that profile. The present system 206 may make credentialing easier, faster, more reliable, accurate, and more manageable.

“FIG. “FIG. The flowchart below illustrates how to facilitate crowdsourced and multilevel credentialing through the network. This may involve receiving profile information from multiple crowdsourced experts 202 at 502. This information could include personal, educational, and work history details. This may include collating the information to create a common profile for each expert 202. Another embodiment of the method involves experts 202 submitting the information in an automated and clearly defined manner through a web interface. A profile is created automatically upon submission of information and/or subscription to the credentialing software 206. At step 504, the method may also include the segmentation of the common profile associated to each of the plurality 202 experts into a plurality federated profile. This means that one set federated profile is created from the common profile associated to an expert, such as 202 a. The system 206 maintains two types of profiles. One is a common profile, and the other is federated. This method could also allow the public to view the federated profile so that they can be viewed by the crowdsourced group of respondents 204 and other experts 202. Further, the method could include receiving responses from the plurality crowdsourced respondents 204 regarding the federated profile at step 506 via a distributed blockchain-configured network. These responses could be used to credential the federated profiles. The system 206 might allow respondents 204 to credential information in federated profiles. The credentialing of federated profiles will be more reliable and accurate the more credentialing is done by respondents 204 individually, the more verifications are performed.

“The answers may be used to determine certification or credentialing information in the federated profiles as well as the common profiles. Credentialing can be linked to each federated profile individually. It may also be verified as incorrect or correct. Crowdsourced credentialing allows for certification of each federated profile by one or more respondent 204 to create an effect that combines certification at multiple levels. A first level certification can be made by a respondent like 204 who certifies a specific federated profile. A second level certification can be performed by another respondent 204, b who certifies or verifies the same profile. Multi-level certification or credentialing can also be done. The cumulative effect of certification permits the association of a cumulative segment rating, or cumulative federated profil rating, to each of each expert 202’s federated profiles. Each of the responses associated to federated profile are associated with attributes that define the source and respondent who certify the profiles. Also, the date of certification by respondent. The terms credentialing, verification, certification and verification can all be used interchangeably in the document. After credentialing the profiles by respondents 204, the method may also include assigning a rating to both the common and federated profiles. This system and method allow multi-level credentialing. They can execute the crowdsourced credentialing process as well as credential the federated profiles and the common profiles.

“In some embodiments, auto-validating the responses or credentialing done in by the plurality 204 may be included to further certify each respondent’s information 204 for each of their federated profiles at Step 508. Auto-validation can be done through one or more social networking platforms 404 that associate an expert, such as 202a, through a social network profile of the expert. This method can also include refining each federated profile rating or associating a separate rating using a mapping between each federated profile and the social networking profile at step 511. This method could also facilitate access for multiple entities to obtain responses that identify credentialing, certification and the refined rating or associated rating via the web-based portal in the crowdsourced network at Step 512. The agency may then retrieve the credentialed information of the service provider via the system 206. They may not have to verify individual expert information from multiple sources.

“In certain embodiments, auto-validating could include searching a social network database that is associated with the social media sources to verify the information about each federated profile. The method may also suggest a federated update if there is a mismatch between the search information and the profile. This method could also include suggesting that the social networking profile be updated to the social media platform 404. This allows service providers to work with social networking sources. They may also exchange information about each other, so that both sides can benefit from the credentialing process.

“In some embodiments, respondents may include one or several profile owners or other experts or persons.”

“In certain embodiments, the method may use the plurality o application programming interfaces (APIs 406) to verify information associated with each of federated profiles. This is done from the social profiles maintained by the social network platform 404. The APIs 406 can be modified to link each federated profile to one or multiple distinct sources of social networking platform 404. This will allow for a unique identifier to be maintained which associates a distinct source of social networking platform 404 with the respective federated account.

“In accordance to an embodiment herein the system 206 can be configured for social crowdsourced credentialing by certified professionals 202.”

“According to an embodiment herein the experts or professionals 202 may be credentialed or accredited by the system206 before they can work in practice locations such as hospitals or other industries.”

“In certain embodiments, experts with credentialed expertise may be used to evaluate and score documents. Documents can contain text, media and any other type digital content. The document may also include fragments or textual portions of media or other digital content. An embodiment allows for the scoring and commenting on various attributes to be done on an entire document or media. In some embodiments, review and scoring can be performed for portions of entire documents, media or other digital content.

“In accordance herewith, the system 206 can be configured to create federated profiles or federated credentialing database that may allow multiple parties (e.g. respondents 204) to crowdsource and socially credential professionals 202.”

“In accordance to an embodiment herein the system 206 can be configured so that it facilitates disintermediating credentialing services, such as allowing hospitals and practices to use them. To share each other’s credentialing using the distributed, social, crowdsourced and blockchain-configured distributed architecture. The system 206 allows the creation of profiles by experts 202.

“The system 206 can be configured to allow profiles to be created. These profiles may be shared and credentialing information can also be exchanged among different agencies or parties. One embodiment of the credentialing system206 allows credentialing between specific agencies. For example, if hospital A (first respondent or agency) trusts hospital, B (second respondent or agency), then the first agency credential is a part of the professional’s profile and the second agency credential is a part of the profile. These agencies can create a more precise profile using the system206 than they could individually by sharing their credentialing information in the form of responses. The common profile is the original profile created by experts 202. The profile can then be divided into federated profiles so that each agency may credential at most one of these federated profiles. The agencies can then credentialed the credentialed profiles. This allows the system 100 to complete an overall accreditation of the profile. The trust factor between the credentialing parties, agencies, or respondents may also be considered by the system 100 204. In the above example, the first agency might identify the second agency as a trusted source. Therefore, any profile credentialed or issued by the second agency could be accepted by the first agency. The agencies 110 can work together to credential and accredit each other by using the system 100 internally in certain embodiments without the need for a service provider.

“In one embodiment, the system206 may allow respondents 204 to disagree with each other. One respondent could credential a single profile in one way, while another respondent might credential the same profile in another way. This means that credentialing done by the second respondent may contradict the credentialing done by the first respondent for the same federated account. In such situations, the system 206 may be able to allow for the association of a degree or difference between the credentialing patterns offered 404 by two or more respondents. An expert, such as 202a, or an agency may use the associated metrics or degrees of disagreement to determine a level or trust for a specific credentialing in relation to a particular profile or federated. The system 206 may allow you to view the credentialing responses of both or more such respondents 204.

According to an embodiment, the system206 may permit a profile owner who is an expert such as202 to challenge the manner in which credentialing is done by one or more respondents to 204 for his federated profile or common profile. Any profile owner, who may be one of the experts 202, can offer his comments through the system. These remarks can be viewed by others. The system 206 can update, modify, delete, or retain the credentialing inputs of the respondents 204 based on these remarks.

“In certain embodiments, the system 206 may establish desirable standards for crowdsourced respondents to code of conduct. The system 206 can either cancel enrollment or delete credentialing information from respondents 204. The system 206 can permanently prevent such respondents from credentialing any experts or professionals associated with the system. The system 206 can be configured in one embodiment to allow crowdsourced credentialing, as long as it adheres to the established standards of credentialing. The certification engine 212, which allows multiple respondents 204 to respond, may credential them only when they meet the standards of conduct. The certification engine 212 can record the details of respondents 204 in case of a breach and then use that information to assist with future credentialing.

“In certain embodiments, the system 206 may facilitate the tracking of experts’ codes of conduct and ethical violations. The system 206 could be used to link the profiles of experts 202 to information relevant to their code of conduct, past ethical behavior, and any other information regarding the experts. This information can be gathered from many sources, or it may be reported by any other reliable expert or person, or any member of crowdsourced network106 or any subscriber to the system 206. These ethical lapses can be corrected in the common profiles of experts 202. Based on this ethical information, it is possible to update or change the credentialed profiles. If there are ethical lapses, the credentialing information for a doctor may be invalidated. The profile can be updated to reflect the ethical lapses or removed from the system 206 by one or more respondents 204.

“FIG. “FIG. 6, with reference to FIGS. FIGS. 1-5 illustrate an expert scoring module 112 according to an embodiment herein. The expert scoring module 112 determines the set of attributes that experts 202 will need. The expert scoring module 112 can be combined with or may include expert attributes engine 110 to determine the set of attributes for experts 202. The set of attributes for the experts 202 could include the crowdsourced credentialed expert determined by the credentialing engine or system 206 based upon the credentialing the federated profiles and common profiles of experts 202 by respondents 204, as discussed in conjunction with other figures. The credentialed competence of experts 202 is determined by a plurality crowdsourced respondents. This determines the extent of credentialed knowledge and the ability of experts 202 to review defined documents for which the credentialed expert is needed as an attribute. Credentialed expertise is a dynamic and non-linear parameter for scoring experts 202 to review documents based upon crowdsourcing.

“In one embodiment, the set attributes for an expert such 202a may include the reputation and trust of the expert. A reputation assessment engine 602 can be used to determine the reputation of experts 202 and indicate trust among relevant communities. For example, reputation can be measured by experts’ interactions with other experts on expert networking sites, information-exchange platforms, or other knowledge interaction platforms. An expert 202 may, for instance, interact with other experts in the same field as medical equipment design via a knowledge platform. This interaction could consist of asking questions related to medical equipment design and then submitting responses to them. Interactions like these can lead to the building or destroying of the reputation of experts 202. The reputation assessment engine 602 can help you determine the ways in which your reputation is being built or destroyed. The reputation assessment engine 602 can, for example, evaluate and assess the reputation of expert 202a based upon the quality of his questions, the quality of his answers to others’ questions, or the quality of review that the expert 202a has done for others’ answers. In such cases, the reputation of the expert 202a may be measured by counting the number of positive votes received from the community, the number of negative votes within the community, and neutral votes in response to any interaction by the expert. An embodiment allows for any positive vote, such as a comment, remark, or vote, to be added to a question by expert 202a. Any negative vote, such as a dislike comment, comment, or vote, may result in expert losing 10 points from his reputation. An embodiment allows the expert to earn 20 points for every positive vote on an answer he posts. A negative vote may result in him losing 20 points. An embodiment allows the expert to earn 25 points for a positive review of an answer. However, others may vote against the expert and cause him to lose 25 points. Other embodiments allow for other methods of assessing the reputation. The reputation assessment engine may tie the reputation of expert 202a to a specific field or community. The reputation assessment engine 602 might assign 50 reputation to an expert in the community of medical equipments design, but the same expert 202a could be assigned a reputation?20 in medical device programming. You can define the reputation as both positive and negative value points. The positive points may indicate a community’s trust in the expert, while the negative points could indicate a decrease in trust.

Voting can be used to determine the trust level. Votes can be cast in fractional or integral numbers, such as +3, +3.5 and?2, or?4.2. This will result in an average summation of all votes weighted with reputation assessment parameters (such above), that determine how many reputation points were earned with each interaction.

“Once reputation assessment engine 602 has evaluated the reputation of an expert 202-202 a in a specific field or community (which is the same or similar to the subject of the review), document scoring module 112 can use that reputation as an expert attribute to determine the score of the document. Experts 202 and the reputations of experts202 who are from the same or related fields or communities to the document under review are not considered in such cases. They are used by the document scoring module 112 to determine the validity and authenticity of documents reviewed and scored after the aggregation and analysis of reputations from different experts 202.

“In certain embodiments, reputation assessment engine 602 can also be capable of aggregating different discrete reputations of individual crowdsourced expert 202 connected over blockchain-configured networks so as to determine an aggregate reputation of a group crowdsourced expert 202 used for evaluation, review, and scoring of documents. The aggregate score could be a net equivalent score that can also be associated with crowdsourced experts202 to show the reputation of all the experts 202 who contributed to document review and scoring.

“In an embodiment, one can determine the reputation by querying corporate databases when the users are internal and looking at the past performance records based upon previous projects.”

“The set may contain an officiality that indicates a job or the designation of an expert 202a in a related job. The scoring module 112 could include or be combined with an officiality engine 604 which determines the officiality of experts 202. For example, ratings may be assigned to specific hierarchical positions that can be used to assign an officiality score to an expert. These officiality scores may be determined by the officiality engine 604 for each crowdsourced expert 202. The officiality engine 604 can be used in some instances to determine an aggregate officiality score of the crowdsourced experts 202 who contribute to reviewing and scoring the document. The aggregate score can be a net equivalent score that is associated with crowdsourced experts202 to indicate the officiality and contribution of all crowdsourced experts202 to document review and scoring. Officiality is a qualitative or quantitative evaluation of the crowdsourced expert community 202 in the context of these embodiments. This validates the scores provided by experts 202.

“In an embodiment, attributes are assigned different weights by a weigh module 606 Information about the assigned weights of experts for particular document reviews and scoring may be stored within the memory circuit 118. This information can then be retrieved by weight module 606 when the document has been reviewed and scored by scoring module 112 or the experts 202. The weight module 606 can identify the degree of importance and relevance of an expert attribute in an electronic document and assigns a weight to each one based on that level of significance. An example: The credentialed expert is weighed first by the weight 606 followed closely by the officiality. Meanwhile, reputation is weighed last by the weight module of the three exemplary attributes.

“Aside from expertise, reputation, and officiality, there may be other attributes such as geographic presence, which is indicative of spatial relations, such as if a person has been living in a certain area for a specified time or if they have spousal, family, or close relationships with experts. A good relationship with an expert, for example, could be considered an attribute.

“In this example, the weight module 606 can be adapted to dynamically alter weights and assign weights based on the type or document being reviewed. This could be determined based on the content and document type of the document. The complexity of the content of the document may also be considered when determining the weight. The weight module 606 can define content parameters that could influence the weight assignment process. It will then dynamically assign weights to the attributes of experts 202 for document scoring and review. The weight module 606 can, for example, dynamically associate weights to allow for review of both the entire document and intra-document federated areas. A first set may be associated with various expert attributes to allow for the review of a section of a document. A second set of different weights can be associated to another section. The credentialed expertise might be the most weighted in the first weights while the reputation could be the highest in the second weights.

“In certain embodiments, expert scoring module 112 calculates an aggregate score for an expert 202a based upon one or more attributes such as credentialed expertise and officiality in conjunction with the assigned weights. An expert score is a rating that indicates expert suitability to review and score a specific document.

“FIG. “FIG.7, with reference to FIGS. 7 through 6, shows a document scoring module (114) in accordance to an exemplary embodiment. Each crowdsourced expert 202 reviews the document scoring module 114 and gives it a document rating. A document scoring module 114 may allow for document review and scoring, but only those experts 202 with a minimum aggregate score of 202 can access it. Document scoring module 114 assigns an aggregate score to each electronic document. This is based on the sum of the reviews 202 by crowdsourced experts and the aggregate scores of each crowdsourced expert 202 based 202 on a set of attributes, including the credentialed expertise, reputation, and officiality. A plurality of crowdsourced expert 202 can assign document scores based on an effect of crowdsourcing index. This may not be linear with the crowdsourcing score. Crowdsourcing index can be used to determine credentialing or expert expertise. It may also be indicative of a degree crowdsourcing. The crowdsourcing index can be used in some embodiments to correspond with the crowdsourcing index for experts credentialing.

“The embodiments provide a multilevel crowdsourcing-based and calculated document scoring derived from the use of a nonlinearly relational parameter. This parameter defines a nonlinear relationship between the multilevel crowdsourcing on the experts score, and the documents scores in the various discrete levels. Multi-level crowdsourcing can include two levels. The first level may include credentialing an expert 202 by a plurality crowdsourced respondents 202, and the second level includes scoring an electronic document by crowdsourced credentialed specialists 202 that have at least a minimum aggregate expert score derived in the first level.

“In some embodiments, the document scoring module 114 includes a document aggregate score assessment engine 702, comment analysis module 704, comment aggregator 706, semantics and analytics engine 708, and document classification/tagging module 710.”

“In certain embodiments, the document aggregate scoring engine 702 calculates an aggregate score for the document based upon individual scores from the document by crowdsourced experts.202 A non-linear crowdsourcing index may also be used by the document aggregate score assessment engine 702 to determine the aggregate score. The comment analysis module 704 can analyze the comments made by experts 202 during the review of the documents. These comments can be used as a learning tool and knowledge repository when evaluating the document in depth. A subjective comment section may be added to the aggregate score for reviewers at second-level. The comment analysis module 704 can be combined with or may include the comment aggregater 706. The comment aggregator 706 may combine comments from different experts 202. The comment aggregator 706 might collate comments from different experts 202. The comment aggregator 704 and the comment analysis module 704 can be combined to enable comments classification, collation and analysis. This is possible by using various semantics, analytics and learning algorithms, functions and programs, as well as programming them with different functions, tools, and programs. The review comments are used to infer logical consequences by the semantics engine 708. To generate more relevant results, the semantics engine 708 uses semantics and machine-learning tools to determine intent and context meaning of terms in review comments. The document classification/tagging module 710 may determine a relevant category or taxonomy class and accordingly tag the document for the classified category. A number of factors may influence the category selection, such as technology areas and sub-areas, reviews, value of content, and other factors.

The comment aggregator 706, the comment analysis module 704, as well as the semantics analysis engine 708 may all be collectively referred to by Natural Language Processing-based Analysis Engine (NLP-based engine) 712. NLP-based analysis engines 712 and 711 may be used to process comments and textual information-based reviews.

“The document scoring module 112 also includes a visual scoring engine 714 to process visual and non-language feedback as well as reviews by experts 202 during electronic document review. FIG. illustrates various components of the visual score engine 714. 8. This article discusses the visual scoring engine 714, and visual reviews by experts 202. It also refers to various figures and a particular reference to FIGS. 7, 8

“The visual scoring engine 714 could include an eye tracks processor 802, an image processor 806, a micro expressions process 804, and neural networks 808. The inputs to the eye tracks processor 802 could be received from an eye movements track device or an image processor 806, and neural networks 808. The eye tracking system 810 can be set up to measure eye movements quickly and may be controlled using software and a microprocessor. A camera may also be included in the eye tracking system 810. A quadrant detector may be part of the hardware of the eye tracking device 810. This can detect the relative direction in which the expert’s eyes move. The quadrant detector’s output may be processed by the microprocessor, under the control software subsystems. The eye tracking device 810 can record the entire review session as well as the eye movements during the session. A digital file with the session, including eye movements and tracks, may be sent to the eye tracks processor 802 for further processing and scoring by the visual scoring engines 714. The data from the eye track processor 810 may be processed by the visual scoring engine 714 using special purpose processing circuitry. Software subsystems can also be used to interpret the data indicating eye movements and tracks. The eye tracks processor 802 can convert the data to high-level interpretations that indicate time lapse on particular sections of the document under consideration, repeat reading, coherence of eye focus and scrolling speed. These interpretations can be compared to predefined and stored eye patterns or vocabulary. Predefined eye patterns or vocabularies can also indicate particular interpretations and associated scores. The eye tracks processor 802 might associate a review score with the eye track data to indicate the quality of review based upon eye movements. The eye tracks processor 802 can process the eye tracking data and convert it to high-level interpretations in order to reveal basic mental states such as expert202a.

“The eye tracking information can be used to identify points of interest within an image or text of the document under review. A content provider might present an image or text to be reviewed. The eye tracking information could then be used to determine which parts of the image or text information are most interesting to the expert and associate a visual score with predefined interpretations and eye tracks patterns that may indicate visual feedback and quality review of the content.

“The visual scoring engines 714 and 804 may also include the microexpressions processor 804, which may receive data indicative micro expressions from the micro sensors 812. This may be associated to a computing device used by an expert, such as 202a. When the expert reviews a document the micro expressions scanner 812 may capture facial expressions and micro expressions throughout the review process, and transmit that information to the visual scoring engines 714 which houses the micro expressions processing 804. The image processor 806 may include the micro expressions processor 804 which can interpret facial expressions and micro expressions from the microexpressions sensor 812. The micro expressions processor 804 may be included in the image processor 806. The image processor 806 may contain the micro expressions processing 804 as a discrete component. They can be connected communicatively or operatively, in this example.

“The computing device of expert 202 a may be linked to the micro expressions sensor 812. The micro expressions sensor 812 can be used to detect gestures and human expressions, and transmit this information to the microexpressions processor 804. The micro expressions sensor 812 can be embedded in a camera, or optical sensor. The micro expressions sensor 812 can be used for face detection, recognition, image acquisition and video capture.

The image processor 806 could contain image processing circuitry as well as an associated memory. The micro expressions sensor 812 data may be received by the image processor 806. It can perform various processing tasks, such as normalizing and extracting facial images with different imaging filters. Image pre-processing may include cropping, resizing, lighting and coloring to extract facial features. It also might remove unwanted features like hair, background or extra features from facial expressions sensor data 812. This data does not provide any information about facial expressions. The image processor 806 produces an output that can be used by micro expressions processor 804 for interpretation of micro expressions. This is done using mathematical algorithms, without limitations. These interpretations can be used to identify facial characteristics, emotions, gestures, and moods. These micro expressions can be used to identify facial characteristics, moods and emotions, as well as gestures. These are collectively called micro expressions. The facial expressions sensor 812 reads micro movements of the bodies of experts 202 to determine their meaning. This information is taken by the micro expression processor 804 as input and then interpreted by complex algorithms using either statistical approaches, artificial intelligence, and neural networks 808. The micro expressions processor 804 can be used to identify the human face and any associated facial characteristics. The micro expressions processor 804 can detect faces from a variety of video frames and extract facial expressions and movements to an output file.

The interpretation of facial expressions could reveal information about the review done by experts 202. The microexpressions processor 804 can store predefined expression patterns in a memory circuit. This may be used to match the processed micro expressions with facial inputs to determine the expert’s review thoughts via visual feedback. These micro expressions can be used to interpret review thoughts that may otherwise be hidden or suppressed in textual reviews or text-based comments.

Click here to view the patent on Google Patents.