Autonomous contextual software support anomaly detection and playbook automation

Patent metadata

Field	Value
Publication number	US-11625237-B2
Application number	US-202117337836-A
Country	US
Kind code	B2
Filing date	Jun 3, 2021
Priority date	Jun 3, 2021
Publication date	Apr 11, 2023
Grant date	Apr 11, 2023

Abstract

A computer generates a profile, where the profile comprises one or more programs to monitor. The computer determines a baseline for each of the one or more programs by collecting one or more values associated with a normal operation for each of the one or more programs. The computer detects an anomaly based on deviation of the one or more values from the normal operation. Based on identifying a playbook for the anomaly, the computer applies the playbook on the program from the one or more programs. The computer organizes chat services based on identifying one or more members associated with the anomaly.

First claim

What is claimed is:

1. A processor-implemented method for software anomaly management, the method comprising:
generating a profile, wherein the profile comprises one or more programs to monitor;
determining a baseline for each of the one or more programs by collecting one or more values associated with a normal operation for each of the one or more programs;
detecting an anomaly based on deviation of the one or more values from the normal operation;
based on identifying a playbook for resolving the anomaly, automatically applying source code from the playbook on a program from the one or more programs; and
organizing chat services based on identifying one or more members associated with the anomaly;
identifying the playbook for the anomaly is by a trained neural network.

2. The method of claim 1 , further comprising:
in response to determining the playbook does not exist for the anomaly:
generating a new playbook based on data extracted from the chat services; and
storing the new playbook in playbook repository.

3. The method of claim 1 , wherein detecting the anomaly based on deviation of the one or more values from the normal operation further comprises:
monitoring the one or more values in real time; and
determining the deviation of the one or more values from the normal operation using a Gaussian distribution approach.

4. The method of claim 1 , wherein identifying one or more members associated with the anomaly is by topical correlation performed on previous chats to identify the one or more members.

5. The method of claim 4 , wherein the topical correlation is performed using a Word2Vec method.

6. The method of claim 1 , wherein applying the playbook on the program further comprises:
injecting the source code of the playbook in a sandbox environment.

7. A computer system for software anomaly management, the computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and
program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
generating a profile, wherein the profile comprises one or more programs to monitor;
determining a baseline for each of the one or more programs by collecting one or more values associated with a normal operation for each of the one or more programs;
detecting an anomaly based on deviation of the one or more values from the normal operation;
based on identifying a playbook for resolving the anomaly, automatically applying source code from the playbook on a program from the one or more programs; and
organizing chat services based on identifying one or more members associated with the anomaly;
identifying the playbook for the anomaly is by a trained neural network.

8. The computer system of claim 7 , further comprising:
in response to determining the playbook does not exist for the anomaly:
generating a new playbook based on data extracted from the chat services; and
storing the new playbook in playbook repository.

9. The computer system of claim 7 , wherein detecting the anomaly based on deviation of the one or more values from the normal operation further comprises:
monitoring the one or more values in real time; and
determining the deviation of the one or more values from the normal operation using a Gaussian distribution approach.

10. The computer system of claim 7 , wherein identifying one or more members associated with the anomaly is by topical correlation performed on previous chats to identify the one or more members.

11. The computer system of claim 10 , wherein the topical correlation is performed using a Word2Vec method.

12. The computer system of claim 7 , wherein applying the playbook on the program further comprises:
injecting the source code of the playbook in a sandbox environment.

13. A computer program product for software anomaly management, the computer program product comprising:
one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor, the program instructions comprising:
program instructions to generate a profile, wherein the profile comprises one or more programs to monitor;
program instructions to determine a baseline for each of the one or more programs by collecting one or more values associated with a normal operation for each of the one or more programs;
program instructions to detect an anomaly based on deviation of the one or more values from the normal operation;
based on identifying a playbook for resolving the anomaly, automatically applying source code from the playbook on a program from the one or more programs; and
program instructions to organize chat services based on identifying one or more members associated with the anomaly;
program instructions to identify the playbook for the anomaly is by a trained neural network.

14. The computer program product of claim 13 , further comprising:
in response to determining the playbook does not exist for the anomaly:
program instructions to generate a new playbook based on data extracted from the chat services; and
program instructions to store the new playbook in playbook repository.

15. The computer program product of claim 13 , wherein detecting the anomaly based on deviation of the one or more values from the normal operation further comprises:
monitoring the one or more values in real time; and
determining the deviation of the one or more values from the normal operation using a Gaussian distribution approach.

16. The computer program product of claim 13 , wherein identifying one or more members associated with the anomaly is by topical correlation performed on previous chats to identify the one or more members.

17. The computer program product of claim 16 , wherein the topical correlation is performed using a Word2Vec method.

Assignees

• IBM

Inventors

• Decrop Clement
• Fox Jeremy R
• Gunjal Richard Daniel
• Silverstein Zachary A

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• H04L12/1818

  Conference organisation arrangements, e.g. handling schedules, setting up parameters needed by nodes to attend a conference, booking network resources, notifying involved parties · CPC title

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• H04L63/1425

  Traffic logging, e.g. anomaly detection · CPC title