Software Technology for Platform for processing messages to automate Phish detection

ACTIMIZE LTD. (Ra’anana, IL)

To detect suspicious or unauthorised financial transactions, a graph convolutional network to prevent financial crimes, a separate node is created for each person, account such as each account, each individual, every address (e.g. email address), etc. Additional attributes are available for aggregate transactions where the node is the sender where the node functions as a receiver that use a particular channel (e.g. ATM); and transactions that are of a certain kind (e.g. online money transfer). In certain embodiments, the attributes exclude data specific to transactions in order to minimize the amount of data required and hence provide more effective computer usage. This technique can be utilized for many purposes such as the prevention of money laundering. Additional options and systems to identify criminals are also offered.

Financial institutions–including banks, brokerage firms and insurance companies–have legal and business pressures to fight money laundering and other illegal activity. Financial institutions must report any suspicious activity that could be related to terrorist financing to the law. The relevant laws currently include the Bank Secrecy Act and the USA PATRIOT Act in the United States, the Third EU Directive in Europe, Articles on theCriminalization of money Laundering in Japan and other countries. As such, anti-money laundering (AML) compliance officers have to create and maintain an effective transaction monitoring program to keep up to date with the latest laws and manage their AML program’s costs. Reputational damage and fines could be incurred due to any errors.

Fraudulent transactions, such as transfer or withdrawals that are not authorized, may lead to large financial losses as well as reputational losses.

Authorities may need to be notified of suspicious patterns, actions and transactions in line with corporate regulations, local laws, and/or international and national laws. The reports must be submitted within a certain period of time, like 48 hours. 48 hours.

Financial institutions use computers to store financial data on financial transactions and also perform some transactions such as Electronic Fund Transfers (EFT), credit card transactions, and more. Computers are able to spot suspicious transactions and activity, as well as to identify unusual transactions.

In light of the massive amount of data that need to be processed to spot suspicious activity, and also the short deadlines dictated by law or requirements, improved computer techniques are sought to prevent financial crimes.

This section describes some aspects of the invention.

Certain embodiments of the disclosed disclosure employ methods of machine learning that are that are based on Artificial Neural Networks (ANN) to identify suspicious activity and identify the pertinent accounts, people and companies, as well as devices (e.g. computers, phones, NetworkInterface Cards, etc. ), addresses or other entities. In some embodiments, it is also possible to calculate the risk score for an entity that is associated with an illegal activity.

Machine learning (ML) is, as is widely known, can give reliable results for any problem. This depends on the Artificial Neural Network’s (ANN) kind and the data preparation. the kind of data input to the ANN. Additionally, machine learning algorithms aren’t always efficient if the ANN algorithms are complicated and the volume of data being processed is huge. In the field of financial crime prevention the ability to detect suspicious activity quickly is crucial to stop illicit flow of cash or othervaluables. It is also important in training the system to make sense of shifting legal, political and business landscapes. High processing speed and reliable results could be two different goals. This is because more specific data could be required, and thus need a slower processing.

The creators of the technique found out that Graph Convolutional Neural Networks can be employed to improve accuracy and speed, if that the input information for financial transactions is properly prepared. The technique employs graphs to depict financial data. GCN graphs are arranged in such a manner that certain data is linked with graph nodes (vertices) as well as other data is linked to graph edges. GCN performance and reliability is affected by the type of data that is associated with each edge or node. It is important to decide on the type of information you would like to link to each node. In certain documents, edges are used to represent transactions between entities and nodes represent entities. It is also possible to use multiple nodes to represent the related details about an entity. In some instances the account’s entity is represented with only one node. The account’s owner, however, is represented using an additional node. An edge is used to indicate the ownership relationship between the two nodes. A family or business relationship between two parties may be also represented with an edge. Certain embodiments employ separate nodes to indicate accounts and other nodes for parties. They can also be used to represent devices, addresses or other details. An address can either be a full street address, or it could be a portion of it (e.g. a country name and/or a city name and/or a portion). An address can also be an IP address, an email address or a layer-2 address, or some other address recognized in computer networks. This representation is thought to enhance GCN reliability for many GCN types, according to the current information.

In some embodiments, information could be duplicated in various node types. For example, an account owner’s name could be provided both in the owner’s node as well as in the account’s node. In other cases, the data isn’t duplicated: the account owner, the device as well as the device. are described and identified only in the relevant nodes.

In some instances, the financial data are processed before being passed to the GCN. Aggregation is used to decrease the volume of data processed by the GCN and thus to increase processing speed, while decreasing memoryrequirements. Generally, aggregation results in the loss of data, which can reduce the reliability of the result. Information that is not essential should be removed and essential information preserved for the detection of suspicious entities. In some embodiments of aggregation according to the present disclosure, the amount of money derived from the individual transactions that are performed over an aforementioned time period are grouped into averages and/or medians, maxima, minima, and/or any other aggregated value. For a given entity (e.g. account) Separate aggregation is performed for transactions in which the entity is a source of transactions and separate aggregation is used for transactions in which the entity is a destination. Additionally, separate aggregation can be performed for each method of transaction (e.g. online banking, ATM, etc.) and/or every type of transaction (e.g. and/or each type of transaction (e.g.) which involves the entity. The aggregation technique is able to preserve the essential information to give more accurate results.

The invention is not limited in its application to the advantages or characteristics that are described above. Furthermore, certain embodiments utilize one or more , but not all of the methods described above. In certain embodiments however, entities and nodes can be described in the same manner as described above, however the aggregation does not happen at the source or in the destination. In other examples, the aggregation process is carried out as described above, but the nodes are defined in a more straightforward manner, e.g. Each account is associated with an independent node. However the account owners as well as other information are not kept separately, but are instead stored as attributes of each account node. Other embodiments and variations are within the range of the invention as described in the disclosure in this document.

Click here to view the patent on USPTO website.

 

Get Patents with PatentPC

What is a patent?

Patents are granted by the government to safeguard an invention. It grants the inventor the exclusive right to create, use and sell the idea. Society is benefited when new technology is introduced to market. Benefits can be realized in the direct sense, since it can allow people to do previously impossible things. Or indirectly, by the economic benefits (business growth and employment) which the invention provides.

Patent protection is demanded out by many universities and pharmaceutical companies to protect their development and research. Patents can be granted for the creation of a product, process or method of creating new materials. Patent protection is granted to any invention that is valuable unique, innovative, and not yet known by other people in the same field.

Patents are a way to honor inventors who have commercially profitable inventions. They serve as a motivator for inventors to come up with new ideas. Small businesses and inventors can rest assured that they will get an income from the investment they make in technology advancement through patents. It means that they can earn money from their work.

Patents are a crucial part of businesses with the ability to:

Secure your products and services.

Increase the value, appearance, and visibility of your products on the market;

Differentiate yourself and your products from others.

Get business and technical details.

Beware of accidentally downloading third-party content or losing important information, original outputs, or any other outputs that are creative.

Patents transform the knowledge of inventors into an asset that can be sold, which creates new opportunities for job creation through joint ventures and licensing.

Investors in the development and commercialization of technology will find small-scale businesses that have patent protection more appealing.

Patenting can lead to new ideas and inventions. This information can encourage the development of new ideas and may be eligible for patent protection.

Patents can serve as an obstacle to unscrupulous third parties profiting from an invention’s successes.

Patent-protected technology revenues that are commercially viable can be used to finance technological research and development (R&D) that can increase the chance of better technology in future.

Intellectual property ownership is a way to convince lenders and investors that there are real opportunities to market your product. One patent that is powerful could lead to many financing opportunities. Patents as well as other IP assets are able to be used as collateral or security to finance debt. You can also show investors the patents you own to boost the value of your business. Forbes and other publications have reported that every patent could add anything from $500,000 to a million dollars in company valuation.

Start-ups require a well-designed business plan that is built on the IP to demonstrate that your product/service is unique or superior to others. Investors will be impressed when you have IP rights are secure or are in the process of becoming secure and if they are supportive of your business strategy.

It is crucial to protect an invention before submitting a patent application. The public disclosure of an invention before it is filed can often destroy its novelty and render it unpatentable. Disclosures that are filed prior to filing, like for investors, test-marketing, or other business partners should be done only after signing a confidentiality contract.

There are numerous types of patents. Understanding them is crucial to protect your invention. Utility patents are for inventions and processes that are new. Design patents cover ornamental designs. Utility patents are best to protect the proprietor from copies and competitors. Utility patents are often issued to improve or alter existing inventions. Utility patents also cover enhancements and modifications in existing inventions. A process patent will cover the acts or methods of performing a particular act. However, a chemical composition could be an amalgamation of ingredients.

What is the length of time a patent will last? Patents that are utility-related last for 20 years from the earliest date of filing, however their expiration dates can be extended due to delays in the patent office such as.

Are you thinking of patenting your ideas? As patents are only granted to applicants who file first, you need to file quickly – call a patent attorney at PatentPC to file your invention now!

When you are writing your patent application when you are writing a patent application, it is recommended that you conduct an internet search for patents, since the search can provide an understanding of other people’s concepts. This can help you limit the extent of your invention. Furthermore, you’ll be aware of the current state of technology in your area of invention. This will allow you to know the extent of your invention and prepare you for the filing of your patent application.

How to Search for Patents

Patent searches are the first step towards obtaining your patent. You can do a google patent search or do a USPTO search. Patent-pending is the name used to describe the product that has been covered by the patent application. You can use for the public pair to locate the patent application. Once the patent office has approved your application, you will be able to do an examination of the patent number to find the patent that was issued. Your product is now patentable. You can also utilize the USPTO search engine. See below for details. A patent lawyer or attorney can advise you on the procedure. In the US, patents are issued by the US trademark and patent office or by the United States patent and trademark office, which is also responsible for examining trademark applications.

Are you interested in similar patents? These are the steps to follow:

1. Create a list of terms for your invention according to its function, composition, or use.

Start by writing down a concise, precise description of your idea. Avoid using generic terms like “device”, “process” or “system”. Instead, consider synonyms to the terms you chose initially. Next, note important technical terms and keywords.

To help you recognize the key words and concepts, try the following questions.

• What’s the goal of this invention? Is it a utilitarian device or an ornamental design?
• Is inventing a method to come up with something or to perform a function? Does it constitute an item?
• What is the basis of the invention? What is the physical structure of the invention?
• What is the goal of the invention?
• What are the terms and phrases in the field of technology used to describe an invention’s nature? A technical dictionary can assist you to find the appropriate terms.

2. Utilize these terms to locate relevant Cooperative Patent Classifications at the Classification Text Search Tool. If you are unable to determine the correct classification to describe your invention, look through the class Schemas (class schedules). If you do not get results using the Classification Text Search, you may want to consider replacing the words that describe your invention using synonyms.

3. Review 3. Go over the CPC Classification Definition for the CPC Classification Definition to verify the accuracy of the CPC classification that you have discovered. If the chosen classification includes a blue square with an “D” at its left, the hyperlink will direct you to the CPC description of the classification. CPC classification definitions can help determine the relevant classification’s scope and therefore you’re sure to select the one you consider to be the most relevant. In addition the definitions may include some tips for searching and other information which could be helpful for further investigation.

4. The Patents Full-Text Database and the Image Database allow you to search for patent documents that have the CPC classification. By focusing your search on abstracts and representative drawings, you can narrow down your search to the most relevant patent publications.

5. This collection of patent publication is the most appropriate to examine for connections with your invention. Pay close attention to the specifications and claims. It is possible to find additional patents by referring to the patent examiner and the applicant.

6. Retrieve published patent applications with the CPC classification you selected in Step 3 in the Applications Full-Text and Image Database. You can apply the same strategy of searching as Step 4, narrowing your search results down to the most relevant patent applications by examining the abstract and drawings that appear on each page. After that, you must review every patent application that has been published with care with particular attention paid to the claims and other drawings.

7. You can find additional US patent publications using keyword searching in the AppFT and PatFT databases, as well as search for patents classified as that are not issued by the United States according to below. Additionally, you can use web search engines to search for non-patent-related patent disclosures in literature about inventions. For instance:

• Add keywords to your search. Keyword searches may turn up documents that are not well-categorized or have missed classifications during Step 2. For example, US patent examiners often supplement their classification searches with keyword searches. Think about the use of technical engineering terminology rather than everyday words.
• Search for foreign patents using the CPC classification. Then, re-run the search using international patent office search engines such as Espacenet, the European Patent Office’s worldwide patent publication database of over 130 million patent publications. Other national databases include:
• European Patent Office (EPO) provides esp@cenet to access a network of Europe’s patent databases with access to machine translation of European patents. 
• Japan Patent Office (JPO) – with access to machine translations of Japanese patents.
• World Intellectual Property Organization (WIPO) offers PATENTSCOPE with a full-text search of published international patent applications and machine translations for some documents, as well as a list of international patent databases.
• Korean Intellectual Property Rights Information Service (KIPRIS)
• State Intellectual Property Office (SIPO) with machine translation of Chinese patents.
• Other International Intellectual Property Offices with online patent databases include Australia, Canada, Denmark, Finland, France, Germany, Great Britain, India, Israel, Netherlands, Norway, Sweden, Switzerland, and Taiwan.
• Search non-patent literature. Inventions can be made public in many non-patent publications. It is recommended that you search journals, books, websites, technical catalogs, conference proceedings, and other print and electronic publications.

To review your search, you can hire a registered patent attorney to assist. A preliminary search will help one better prepare to talk about their invention and other related inventions with a professional patent attorney. In addition, the attorney will not spend too much time or money on patenting basics.