Recommendations for remedial actions

Patent metadata

Field	Value
Publication number	US-12282386-B2
Application number	US-202318519822-A
Country	US
Kind code	B2
Filing date	Nov 27, 2023
Priority date	Sep 24, 2021
Publication date	Apr 22, 2025
Grant date	Apr 22, 2025

Abstract

Described systems and techniques determine causal associations between events that occur within an information technology landscape. Individual situations that are likely to represent active occurrences requiring a response may be identified as causal event clusters, without requiring manual tuning to determine cluster boundaries. Consequently, it is possible to identify root causes, analyze effects, predict future events, and prevent undesired outcomes, even in complicated, dispersed, interconnected systems.

First claim

What is claimed is:

1. A computer-implemented method for recommending remedial actions, the method comprising:
receiving a plurality of source alarms and a plurality of target remedial actions;
extracting features from event graphs representing the plurality of source alarms and the plurality of target remedial actions;
processing the features using a remedial action recommendation (RAR) model, wherein the RAR model is continuously trained based on previous features from a plurality of previous source alarms, features from a plurality of previous target remedial actions, implicit feedback, and explicit feedback;
outputting ranked recommended remedial actions to a user interface that enables a selection of at least one of the recommended remedial actions to initiate performance of the selection; and
in response to the selection, performing an automation associated with the selected one of the recommended remedial actions to respond to the plurality of source alarms and providing implicit feedback to the RAR model based on the selection.

2. The computer-implemented method as in claim 1 , wherein the ranked recommended remedial actions include a confidence value.

3. The computer-implemented method as in claim 1 , wherein the implicit feedback includes positive reinforcement implicit feedback when a target remedial action from the plurality of target remedial actions closes a corresponding source alarm from the plurality of source alarms.

4. The computer-implemented method as in claim 1 , wherein the implicit feedback includes negative reinforcement implicit feedback.

5. The computer-implemented method as in claim 1 , wherein the implicit feedback includes feedback received without manual intervention.

6. The computer-implemented method as in claim 1 , wherein the explicit feedback includes a selected response from a user.

7. A computer program product for recommending remedial actions, the computer program product being tangibly embodied on a non-transitory computer-readable medium and including executable code that, when executed, causes a computing device to:
receive a plurality of source alarms and a plurality of target remedial actions;
extract features from event graphs representing the plurality of source alarms and the plurality of target remedial actions;
process the features using a remedial action recommendation (RAR) model, wherein the RAR model is continuously trained based on previous features from a plurality of previous source alarms, features from a plurality of previous target remedial actions, implicit feedback, and explicit feedback;
output ranked recommended remedial actions to a user interface that enables a selection of at least one of the recommended remedial actions to initiate performance of the selection; and
in response to the selection, perform an automation associated with the selected one of the recommended remedial actions to respond to the plurality of source alarms and provide implicit feedback to the RAR model based on the selection.

8. The computer program product of claim 7 , wherein the ranked recommended remedial actions include a confidence value.

9. The computer program product of claim 7 , wherein the implicit feedback includes positive reinforcement implicit feedback when a target remedial action from the plurality of target remedial actions closes a corresponding source alarm from the plurality of source alarms.

10. The computer program product of claim 7 , wherein the implicit feedback includes negative reinforcement implicit feedback.

11. The computer program product of claim 7 , wherein the implicit feedback includes feedback received without manual intervention.

12. The computer program product of claim 7 , wherein the explicit feedback includes a selected response from a user.

13. A system for recommending remedial actions, comprising:
at least one processor; and
a non-transitory computer readable medium comprising instructions that, when executed by the at least one processor, cause the system to implement a remediation generator that is configured to:
receive a plurality of source alarms and a plurality of target remedial actions;
extract features from event graphs representing the plurality of source alarms and the plurality of target remedial actions;
process the features using a remedial action recommendation (RAR) model, wherein the RAR model is continuously trained based on previous features from a plurality of previous source alarms, features from a plurality of previous target remedial actions, implicit feedback, and explicit feedback;
output ranked recommended remedial actions to a user interface that enables a selection of at least one of the recommended remedial actions to initiate performance of the selection; and
in response to the selection, perform an automation associated with the selected one of the recommended remedial actions to respond to the plurality of source alarms and provide implicit feedback to the RAR model based on the selection.

14. The system of claim 13 , wherein the ranked recommended remedial actions include a confidence value.

15. The system of claim 13 , wherein the implicit feedback includes positive reinforcement implicit feedback when a target remedial action from the plurality of target remedial actions closes a corresponding source alarm from the plurality of source alarms.

16. The system of claim 13 , wherein the implicit feedback includes negative reinforcement implicit feedback.

17. The system of claim 13 , wherein the implicit feedback includes feedback received without manual intervention.

18. The system of claim 13 , wherein the explicit feedback includes a selected response from a user.

Assignees

• Bmc Software Inc
• Bmc Helix Inc

Inventors

• Garapati Sai Eswar
• Giral Erhan

Classifications

• H04L41/145

  involving simulating, designing, planning or modelling of a network · CPC title

• H04L41/0636

  based on a decision tree analysis · CPC title

• G06N3/08

  Learning methods · CPC title

• G06F11/0769

  Readable error formats, e.g. cross-platform generic formats, human understandable formats · CPC title

• G06F11/0709

  in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems · CPC title