Refinement of a predicted event based on explainability data

Patent metadata

Field	Value
Publication number	US-2020250548-A1
Application number	US-201916269125-A
Country	US
Kind code	A1
Filing date	Feb 6, 2019
Priority date	Feb 6, 2019
Publication date	Aug 6, 2020
Grant date	—

Abstract

Systems, computer-implemented methods, and computer program products that can facilitate refinement of a predicted event based on explainability data are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an interpreter component that identifies a probable cause of a predicted event based on explainability data. The computer executable components can further comprise an enrichment component that executes a diagnostic analysis based on the probable cause.

First claim

What is claimed is:

1 . A system, comprising:
a memory that stores computer executable components; and a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
an interpreter component that identifies a probable cause of a predicted event based on explainability data; and
an enrichment component that executes a diagnostic analysis based on the probable cause.

2 . The system of claim 1 , wherein the probable cause comprises at least one of an event type corresponding to the explainability data or correlating events corresponding to the explainability data.

3 . The system of claim 1 , wherein the explainability data comprises at least one of probability of the predicted event, a feature contributing to the predicted event, a weight of the feature contributing to the predicted event, or timing of the predicted event.

4 . The system of claim 1 , wherein the computer executable components further comprise a recommender component that validates the predicted event based on at least one of the diagnostic analysis or domain data.

5 . The system of claim 1 , wherein the computer executable components further comprise a recommender component that recommends a remediation action based on at least one of the predicted event, the explainability data, the probable cause, the diagnostic analysis, or domain data, thereby facilitating improved processing performance associated with at least one of the processor or a processing unit associate with the system.

6 . The system of claim 1 , wherein the computer executable components further comprise a refinement component that refines at least one of the predicted event or a remediation action based on a correlation between the predicted event and occurrence of the predicted event.

7 . A computer-implemented method, comprising:
identifying, by a system operatively coupled to a processor, a probable cause of a predicted event based on explainability data; and executing, by the system, a diagnostic analysis based on the probable cause.

8 . The computer-implemented method of claim 7 , wherein identifying comprises, identifying, by the system, at least one of an event type corresponding to the explainability data or correlating events corresponding to the explainability data.

9 . The computer-implemented method of claim 7 , wherein the explainability data comprises at least one of probability of the predicted event, a feature contributing to the predicted event, a weight of the feature contributing to the predicted event, or timing of the predicted event.

10 . The computer-implemented method of claim 7 , further comprising, validating, by the system, the predicted event based on at least one of the diagnostic analysis or domain data.

11 . The computer-implemented method of claim 7 , further comprising, recommending, by the system, a remediation action based on at least one of the predicted event, the explainability data, the probable cause, the diagnostic analysis, or domain data, thereby facilitating improved processing performance associated with at least one of the processor or a processing unit associate with the system.

12 . The computer-implemented method of claim 7 , further comprising, refining, by the system, at least one of the predicted event or a remediation action based on a correlation between the predicted event and occurrence of the predicted event.

13 . A computer program product facilitating a predicted event refinement process based on explainability data, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
identify, by the processor, a probable cause of a predicted event based on explainability data; and execute, by the processor, a diagnostic analysis based on the probable cause.

14 . The computer program product of claim 13 , wherein the program instructions are further executable by the processor to cause the processor to identify, by the processor, at least one of an event type corresponding to the explainability data or correlating events corresponding to the explainability data.

15 . The computer program product of claim 13 , wherein the program instructions are further executable by the processor to cause the processor to validate, by the processor, the predicted event based on at least one of the diagnostic analysis or domain data.

16 . The computer program product of claim 13 , wherein the program instructions are further executable by the processor to cause the processor to recommend, by the processor, a remediation action based on at least one of the predicted event, the explainability data, the probable cause, the diagnostic analysis, or domain data.

17 . The computer program product of claim 13 , wherein the program instructions are further executable by the processor to cause the processor to refine, by the processor, at least one of the predicted event or a remediation action based on a correlation between the predicted event and occurrence of the predicted event.

18 . A system, comprising:
a memory that stores computer executable components; and a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise: an explanation component that generates explainability data corresponding to a predicted event; and an automation engine component that evaluates accuracy of the predicted event based on the explainability data and supplemental data.

19 . The system of claim 18 , wherein the supplemental data comprises at least one of an event type corresponding to the explainability data, correlated events corresponding to the explainability data, diagnostics data, or domain data.

20 . The system of claim 18 , wherein the automation engine component enriches at least one of the predicted event or the explainability data based on the supplemental data.

21 . The system of claim 18 , wherein the automation engine component validates or refines the predicted event based on the supplemental data.

22 . A computer-implemented method, comprising:
generating, by a system operatively coupled to a processor, explainability data corresponding to a predicted event; and evaluating, by the system, accuracy of the predicted event based on the explainability data and supplemental data.

23 . The computer-implemented method of claim 22 , wherein the evaluating comprises, evaluating, by the system, accuracy of the predicted event based on at least one of the explainability data, an event type corresponding to the explainability data, correlated events corresponding to the explainability data, diagnostics data, or domain data.

24 . The computer-implemented method of claim 22 , further comprising, enriching, by the system, at least one of the predicted event or the explainability data based on the supplemental data.

25 . The computer-implemented method of claim 22 , further comprising, validating or refining, by the system, the predicted event based on the supplemental data.

Assignees

• IBM

Inventors

• Shwartz Larisa
• Bagehorn Frank
• Hwang Jinho
• Paraiso Marcos Vinicius L
• Bigaj Rafal
• Venkatesan Vidhya Shankar
• Wiesmann Rothuizen Dorothea
• Mahamuni Amol Bhaskar

Classifications

• G06N5/045

  Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F11/0793 Primary

  Remedial or corrective actions (recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40) · CPC title

• G06F11/079

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06F11/0712

  in a virtual computing platform, e.g. logically partitioned systems · CPC title