System and method of automated fault correction in a network environment

{
  "publication_number": "US2020204428A1",
  "country": "US",
  "kind": "A1",
  "title": "System and method of automated fault correction in a network environment",
  "abstract": "Automated fault correction in a network environment comprises identifying a pattern in a set of network events and generating a set of substantiating data for the identified patterns. The method can also identify an occurrence probability value for each network event and generate root cause data based on a ranking for the network events using a set of parameters including the occurrence probability. The method can also be directed to performing a regression of the root cause data against a set of historic data and selecting the root cause with a predefined accuracy as an acceptable candidate. The acceptable candidate is then provided for assisted learning for automated fault correction.",
  "claims": [
    "1. A method of automated fault correction in a network environment; comprising identifying a pattern in a set of network events; generating a set of substantiating data for the identified pattern; determining an occurrence probability value for each network event; generating root cause data based on a ranking for the network events using a set of parameters including the occurrence probability; performing a regression of the root cause data against a set of historic data; selecting the root cause with a predefined accuracy as an acceptable candidate; and presenting the acceptable candidate for assisted learning for automated fault correction. 2. The method of claim 1, wherein a topology data, a historical alarm and a historical event data set are used to automatically identify patterns in network events. 3. The method of claim 1, wherein the substantiating data is generated based on the topology and a set of time stamp data. 4. The method of claim 1, wherein the root cause is identified using the historic event data comprising a set of parameters. 5. The method of claim 4, wherein the set of parameters include one or more of an occurrence probability rank, severity, chronological order and a topological relationship value. 6. The method of claim 1 wherein the accuracy of the identified root cause is validated based on the historic event data. 7. The method of claim 6, wherein the historical even data set is used to validate the predicted root cause by regression. 8. The method of claim 7, wherein the validated root cause predicted is marked for the accuracy value with respect to the validation set of historical known root cause data. 9. The method of claim 1, wherein the predefined accuracy value is provided as an initial acceptable performance indicator. 10. The method of claim 9, wherein the predefined accuracy value is provided over one of a network, a user interface, or as a prebuild value. 11. The method of claim 6, wherein the identified root cause is presented for assisted learning for automated fault correction. 12. A system for automated fault correction in a network environment; comprising a processor; and a memory coupled to the processor configured to be capable of executing programmed instructions comprising and stored in the memory to: identify a pattern in a set of network events; generate a set of substantiating data for the identified pattern; identify an occurrence probability value for each network event; generate root cause data based on a ranking for the network events using a set of parameters including the occurrence probability; perform a regression of the root cause data against a set of historic data; select the root cause with a predefined accuracy as an acceptable candidate; and present the acceptable candidate for assisted learning for automated fault correction. 13. The system of claim 12, wherein a topology data, a historical alarm and a historical event data set are used to automatically identify patterns in network events. 14. The system of claim 12, wherein the substantiating data is generated based on the topology and a set of time stamp data. 15. The system of claim 12, wherein the root cause is identified using the historic event data comprising a set of parameters. 16. The system of claim 15, wherein the set of parameters include one or more of an occurrence probability rank, severity, chronological order and a topological relationship value. 17. The system of claim 12 wherein the accuracy of the identified root cause is validated based on the historic event data. 18. The system of claim 17, wherein a historical known root cause data set is used to validate the predicted root cause by regression. 19. The system of claim 18, wherein the validated root cause predicted is marked for the accuracy value with respect to other the validation set of historical known root cause data. 20. The system of claim 17, wherein: a predefined accuracy value is provided as an initial acceptable performance indicator; the predefined accuracy value may be provided over a network, a user interface, or as a prebuild value in the system; and the predicted root cause is presented for supervised learning for automated fault correction."
  ],
  "description_excerpt": "The field relates to automated fault correction in a network environment. More specifically, it involves identifying root cause and using a learning model to provide automated fault correction.\n\nComputer networks for many applications are evolving to become more mobile and decentralized. One such application for computer networks is that of battlefield management. Current battlefield management computer networks have addressed to varying extents the fusion of network management systems, information assurance systems, and information dissemination management systems from the perspective of providing a comprehensive status of the deployed network.\n\nIn typical computer networks, when an event is detected, the operator is alerted, a trouble ticket is opened, and if necessary, the ticket is escalated to a person skilled in the art. Finally, a user or operator resolves the issue, and the trouble ticket is closed. Throughout this process, operators may make annotations to the ticket, indicating steps taken towards problem resolution. During the time it takes to isolate one fault event and resolve it, any other events of varying severity can be detected, especially in a large, dynamic network. This can quickly result in significant service and network availability problems, as well as information overload for the operator or user responsible for resolving the fault event.\n\nPreviously, when network maintenance was entirely dependent on network domain experts, all network logs flowed directly to the Network Operations Centers (NOC) manned by network domain experts.",
  "cpc": [
    "G06F 11/079",
    "G06F 11/0793",
    "G06N 20/00",
    "H04L 29/14",
    "H04L 41/0631",
    "H04L 41/12",
    "H04L 69/40"
  ],
  "ipc": [
    "G06F 11/07",
    "G06N 20/00",
    "H04L 41/12",
    "H04L 69/40"
  ],
  "assignees": [
    "Infosys Ltd"
  ],
  "inventors": [
    "Sreekanth Sreedevi Sasidharan",
    "Anu Rajagopal",
    "Shilpa Sasi",
    "Pinky Painadath Jose",
    "Anoop Pothen Varghese",
    "Shankar Kishan Jayakumaran Nair"
  ],
  "filing_date": "2019-12-05",
  "publication_date": "2020-06-25",
  "priority_date": "2018-12-06",
  "application_number": "US-201916704962-A",
  "family_id": "68808126",
  "cited_by_count": 15
}