Systems and methods for incident response using artificial intelligence for information technology operations

Patent metadata

Field	Value
Publication number	US-2024154877-A1
Application number	US-202218053235-A
Country	US
Kind code	A1
Filing date	Nov 7, 2022
Priority date	Nov 7, 2022
Publication date	May 9, 2024
Grant date	—

Abstract

Systems and methods for incident response using artificial intelligence for information technology operations are disclosed. In one embodiment, a method may include an incident response computer program executed by an electronic device: (1) receiving an incident ticket for an incident involving a computer product or a computer system within an organization from a service management platform for the computer product or the computer system; (2) providing incident information from the incident ticket to a trained incident response machine learning engine, wherein the trained incident response machine learning engine is trained to predict a solution for the incident based on historical incident data; (3) receiving, from the trained incident response machine learning engine, a predicted solution for the incident; and (4) providing the predicted solution to the service management platform. The service management platform provides the predicted solution to the computer product or the computer system.

First claim

What is claimed is:

1 . A method for incident response using artificial intelligence for information technology operations, comprising:
receiving, by an incident response computer program executed by an electronic device, an incident ticket for an incident involving a computer product or a computer system within an organization from a service management platform for the computer product or the computer system; providing, by the incident response computer program, incident information from the incident ticket to a trained incident response machine learning engine, wherein the trained incident response machine learning engine is trained to predict a solution for the incident based on historical incident data; receiving, by the incident response computer program and from the trained incident response machine learning engine, a predicted solution for the incident; and providing, by the incident response computer program, the predicted solution to the service management platform; wherein the service management platform provides the predicted solution to the computer product or the computer system.

2 . The method of claim 1 , wherein the incident ticket identifies a description of the incident and/or a labelling of product/incident type.

3 . The method of claim 1 , further comprising training the trained incident response machine learning engine, comprising:
retrieving, by the incident response computer program, the historical incident data comprising a plurality of prior incidents; training, by the incident response computer program, the trained incident response machine learning engine using a first portion of the historical incident data; verifying, by the incident response computer program, the training of the trained incident response machine learning engine using a second portion of the historical incident data; and deploying, by the incident response computer program, the verified incident response machine learning engine to a production environment.

4 . The method of claim 3 , wherein the historical incident data comprises, for each of the plurality of prior incidents, a description of the prior incident, a labelling of a product involved in the prior incident, a system involved in the prior incident, an individual involved in the prior incident, a team involved in the prior incident, a time and date of the prior incident, solutions to the prior incident, and/or results of the solution.

5 . The method of claim 4 , wherein the historical incident data further comprises, for the plurality of prior incidents, network environment data at the time of the prior incident.

6 . The method of claim 1 , wherein the predicted solution comprises a self-service troubleshooting guide for the predicted solution, product frequently asked questions (FAQs) for the predicted solution, solution instructions for the predicted solution, scripts for the predicted solution, patches for the predicted solution, configurations for the predicted solution, and/or solution articles for the predicted solution.

7 . The method of claim 1 , further comprising:
receiving, by the incident response computer program, feedback for the predicted solution; and re-training, by the incident response computer program, the trained incident response machine learning engine with the feedback.

8 . A method for incident response using artificial intelligence for information technology operations, comprising:
receiving, by an incident response computer program executed by an electronic device, a plurality of incident tickets for incidents involving computer products or computer systems within an organization from a service management platform for the computer products or the computer systems; predicting, by the incident response computer program executed by an electronic device and using a trained incident response machine learning engine that is trained to predict a category for each incident ticket, a category for each of the plurality of incident tickets; clustering, by the incident response computer program, the plurality of incident tickets into common incident clusters according to the categories; ranking, by the incident response computer program, the common incident clusters based on a number of incident tickets in each common incident cluster; and prioritizing, by the incident response computer program, improvement of production quality for programs or applications based on the ranking.

9 . The method of claim 8 , wherein the incident ticket identifies a description of the incident and/or a labelling of product/incident type.

10 . The method of claim 8 , wherein the categories comprise a common issue, a common software program, a common computer system, a common geography, and a common solution.

11 . The method of claim 8 , wherein the common incident clusters are further ranked based on a severity or impact of the incident in each common incident cluster.

12 . A system, comprising:
a plurality of computer products or computer systems; a service management platform in communication with each of the plurality of computer systems; a solution knowledge base; and an electronic device executing an incident response computer program and a trained incident response machine learning engine; wherein:
the incident response computer program receives an incident ticket for an incident involving one of the plurality of computer products or computer systems from the service management platform for the computer product or the computer system;
the incident response computer program provides incident information from the incident ticket to the trained incident response machine learning engine, wherein the trained incident response machine learning engine is trained to predict a solution for the incident based on historical incident data;
the incident response computer program receives, from the trained incident response machine learning engine, a predicted solution for the incident;
the incident response computer program provides the predicted solution to the service management platform; and
the service management platform provides the predicted solution to the computer product or the computer system.

13 . The system of claim 12 , wherein the incident ticket identifies a description of the incident and/or a labelling of product/incident type.

14 . The system of claim 12 , wherein the trained incident response machine learning engine is trained by the incident response computer program receiving the historical incident data, training the trained incident response machine learning engine using a first portion of the historical incident data, verifying the training of the trained incident response machine learning engine using a second portion of the historical incident data, and deploying the verified incident response machine learning engine to a production environment.

15 . The system of claim 14 , wherein the historical incident data comprises, for a plurality of prior incidents, a description of the prior incident, a labelling of the product involved in the prior incident, a system involved in the prior incident, an individual involved in the prior incident, a team involved in the prior incident, a time and date of the prior incident, solutions to the prior incident, and/or results of the solution.

16 . The system of claim 15 , wherein the historical incident data further comprises, for the plurality of prior incidents, network environment data at the time of the prior incident.

17 . The system of claim 12 , wherein the predicted solution comprises a self-service trouble

Assignees

• Jpmorgan Chase Bank Na

Inventors

• L Ajayaghosh
• Sharma Vineet K
• Chen Guangjing
• Zhang David
• Appukuttan Nivead
• Huang Xiaobo

Classifications

• H04L41/0654

  using network fault recovery (ring fault isolation or reconfiguration in loop networks without recovery actions by a network management system H04L12/437) · CPC title

• H04L41/16 Primary

  using machine learning or artificial intelligence · CPC title

• H04L41/5074

  Handling of user complaints or trouble tickets · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• H04L41/06

  Management of faults, events, alarms or notifications · CPC title