ACCENTURE GLOBAL SOLUTIONS LIMITED (Dublin, IE)
Embodiments enable the prevention and mitigation of network faults. Information associated with nodes in the network can be collected and utilized to generate Network Analytical Records (NARs). A model can be executed against the NARs to identify faults that are associated to one or more nodes in the network. Tickets are generated in anticipation of faults and stored in an inventory database for tickets. To anticipate the actions that can be taken to fix any ticket’s flaws the tickets can be scrutinized. The information on the ticket can be used to study the tickets and create record of the ticket’s analytical data (TARs). A second model can be executed against the TARs forecasting actions to correct the predicted faults. Predicted actions can be used to reduce the negative impact the faults have on the network. This may include preventive maintenance, or even minimizing the effect of the faults by using the predicted actions.
Connectivity and network uptime are the two most important elements in the operation of networks. The industry faces unique issues in terms of continuous connectivity because of all connected devices, applications and services accessible via the Internet. Telecommunications services are being consolidated around a single medium for information transfer that is data. Voice, mobile communications and other value-added services that were previously developed around general packet radio service (GPRS) and its related services are now merged to data as a medium. Similarly,traditional video and allied services are also merged to data as transfer medium. This represents a paradigm shift in telecommunications, however other methods of communication and transfer like wired or fiber cables, have always used data as a transfer medium.
The merging of various services and data is leading to the restructuring of the telecom backhaul infrastructure. A single network will provide the data backbone while last-mile distribution of data will happen via the appropriate channels. These include wireless through mobile 3G/4G/5G networks as well as distribution POP (Point of Presence) devices for fiber-based communications, and wireless through mobile 3G/4G/5G mobile devices. The management and aggregation of multiple layers within a single network poses specific challenges for services and operations. This includes the maintenance and upkeep of prioritised connections, downtime, network traffic management, repair and servicing, aswell as difficulties in managing network traffic and downtime. The integration of various communications technologies also increases thecomplexity needed to ensure continuity of service.
Due to the above-mentioned complexity that are present, repair and service actions are usually performed in a reactive and manual manner. For example, service/repair actions are performed after an event of failure to a network element, ratherthan in a manner which prevents the failure from occurring from occurring in the first place, or in a predictive manner that allows repair work to be completed faster. Secondly, due to non-availability of a unified view of alarms for network elements, disconnections, and ticketevents and repair actions carried out by a service technician is uninformed and is based on personal experiences.
The invention relates to computer-readable storage media, as well as systems for predicting faults (e.g. disconnections, failures etc.). In nodes of a network. A monitoring system may record information about faults and alert users when they occur. Monitoring systems can also check the state of network devices and nodes, such as to record the temperature, CPU usage rates, memory utilization, and similar. A fault mitigation device may get information on the status of the nodes, as well as the detected faults. This information may be used to generate data from the network analysis records (NARs). The NARs could contain a number of metrics (e.g. KPIs,.) that are associated with the nodes in the monitored network as well as information that is associated with various types of faults. NARs can be compared to the first model which predicts failures (e.g. failure events) and identified one or more nodes of the network likely to suffer from the expected failure events in the near future. The fault mitigation devices can generate tickets for the predicted faults and then store the tickets in databases (e.g. an internal database, or a ticket management database).
The fault mitigation device could also be configured to analyze historical tickets to derive data that can be used to create an alphabetical dictionary which can be used to anticipate actions to reduce or eliminate identified faults. Analyzing historical tickets can involve the creation of tokens based on ticket data, finding out the frequency of tokens and identifying dependencies between verbs and nouns in the tickets. The frequency of tokens and the verb-noun dependency information could be used to create a dictionary. This information could then be used for extracting actions from tickets that have been used in the past. Fuzzy logic, for instance could be utilized to extract actions and tag historical tickets using the specifics of the actions that have been extracted. A model can be trained to analyse tickets from the past by being able to collect historical ticket action data and tag them.
The devices for fault mitigation can be set up to produce tickets analytical records (TARs) that are based on different types of ticket data. The TARs could be evaluated against a second model configured to distinguish self-healable tickets(i.e., tickets that have been associated with failure events which will be resolved automatically and without additional actions) and tickets that are not self-healable. Another model can be used to analyze non-self-healable tickets and predict the steps required to fix the failure events.
The preceding paragraphs have described broadly the features and technical advantages of this invention so that the more detailed description of the invention that follows will be easier to comprehend. Additional features and advantages of theinvention will be described in the following paragraphs, which constitute the subject of the claims of the invention. It should be understood by those who are skilled in the art that the concept and particular embodiment described can be used as a basis for modifying ordesigning other structures for carrying out the same purpose as the present invention. People who are skilled in the art must be aware that similar structures aren’t incompatible with the spirit and scope outlined in the claims appended. The novel features which are considered to be distinctive of the invention, both as to its method of operation and organization of operation, along with further objects and advantages are better understood by the following descriptionwhen considered in conjunction with the accompanying drawings. Each illustration is designed to demonstrate and explain the invention, and should not be used to limit the scope of its scope.
Click here to view the patent on USPTO website.
Get Patents with PatentPC
What is a patent?
How to Search for Patents
- 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.