Root cause analysis

Patent metadata

Field	Value
Publication number	US-10970158-B2
Application number	US-201916545096-A
Country	US
Kind code	B2
Filing date	Aug 20, 2019
Priority date	Aug 26, 2016
Publication date	Apr 6, 2021
Grant date	Apr 6, 2021

Abstract

A method and system for performing a root cause analysis. A central processing unit (CPU) tracks a focal point of a user's eye gaze. The CPU correlates the focal point of the user's eye gaze to a viewing position of a display device displaying a file that includes event data being viewed by the user. The CPU identifies, as a function of the viewing position, events of interest in the event data and an amount of time that the event data is viewed by the user. The CPU outputs, as a function of a linear regression model, an interest score pertaining to one or more events of interest that were previously identified as a function of the user's eye gaze. The interest score is a probability of each identified event of interest being a root cause of a defect.

First claim

What is claimed is:

1. A method for performing a root cause analysis, said method comprising:
tracking, by a central processing unit (CPU), a focal point of a user's eye gaze;
correlating, by the CPU, the focal point of the user's eye gaze to a viewing position of a display device displaying a file that includes event data being viewed by the user;
identifying, by the CPU, as a function of the viewing position, events of interest in the event data and an amount of time that the event data is viewed by the user;
identifying, by the CPU, an emotive expression of the user during an amount of time the user's eye glaze is focused on the viewing position,
inserting, by the CPU, a numerical value assigned to the viewing position, the amount of time, the emotive expression and text of the event data, into a linear regression model; and
outputting, by the CPU, as a function of the linear regression model, an interest score pertaining to one or more events of interest that were previously identified as a function of the user's eye gaze, said interest score being a probability of each identified event of interest being a root cause of a defect.

2. The method of claim 1 , said method further comprising:
recording, by the CPU, recordation data of the user's eye gaze while viewing the event data of the file.

3. The method of claim 1 , wherein the file including event data is selected from the group consisting of a log file, a configuration file, and source code.

4. The method of claim 1 , wherein the linear regression model outputs a value of the interest score between 0-1 inclusively.

5. The method of claim 1 , said method further comprising:
generating a color-coded tag in the file, based on severity of the one or more events of interest.

6. The method of claim 1 , said method further comprising:
tagging, by the CPU, each event of interest within the file with a tag as a function of each interest score.

7. The method of claim 1 , wherein the closer the emotive expression of the user is to a center of a Plutchik wheel of emotion, the higher is the probability that one or more of the identified events of interest is the root cause of the defect.

8. A computer program product comprising:
one or more computer readable hardware storage devices having computer readable program code stored therein, said program code containing instructions executable by a central processing unit (CPU) to implement a method for performing a root cause analysis, said method comprising:
tracking, by the CPU, a focal point of a user's eye gaze;
correlating, by the CPU, the focal point of the user's eye gaze to a viewing position of a display device displaying a file that includes event data being viewed by the user;
identifying, by the CPU, as a function of the viewing position, events of interest in the event data and an amount of time that the event data is viewed by the user;
identifying, by the CPU, an emotive expression of the user during an amount of time the user's eye glaze is focused on the viewing position,
inserting, by the CPU, a numerical value assigned to the viewing position, the amount of time, the emotive expression and text of the event data, into a linear regression model; and
outputting, by the CPU, as a function of the linear regression model, an interest score pertaining to one or more events of interest that were previously identified as a function of the user's eye gaze, said interest score being a probability of each identified event of interest being a root cause of a defect.

9. The computer program product of claim 8 , said method further comprising:
recording, by the CPU, recordation data of the user's eye gaze while viewing the event data of the file.

10. The computer program product of claim 8 , wherein the file including event data is selected from the group consisting of a log file, a configuration fife, and source code.

11. The computer program product of claim 8 , wherein the linear regression model outputs a value of the interest score between 0-1 inclusively.

12. The computer program product of claim 8 , said method further comprising:
generating a color-coded tag in the file, based on severity of the one or more events of interest.

13. The computer program product of claim 8 , said method further comprising:
tagging, by the CPU, each event of interest within the file with a tag as a function of each interest score.

14. The computer program product of claim 8 , wherein the closer the emotive expression of the user is to a center of a Plutchik wheel of emotion, the higher is the probability that one or more of the identified events of interest is the root cause of the defect.

15. A computer system, comprising: a central processing unit (CPU); a memory device coupled to the CPU; and a computer readable storage device coupled to the processor, wherein the storage device contains program code executable by the CPU via the memory device to implement a method for performing a root cause analysis, said method comprising:
tracking, by the CPU, a focal point of a user's eye gaze;
correlating, by the CPU, the focal point of the user's eye gaze to a viewing position of a display device displaying a file that includes event data being viewed by the user;
identifying, by the CPU, as a function of the viewing position, events of interest in the event data and an amount of time that the event data is viewed by the user;
identifying, by the CPU, an emotive expression of the user during an amount of time the user's eye glaze is focused on the viewing position,
inserting, by the CPU, a numerical value assigned to the viewing position, the amount of time, the emotive expression and text of the event data, into a linear regression model; and
outputting, by the CPU, as a function of the linear regression model, an interest score pertaining to one or more events of interest that were previously identified as a function of the user's eye gaze, said interest score being a probability of each identified event of interest being a root cause of a defect.

16. The computer system of claim 15 , said method further comprising:
recording, by the CPU, recordation data of the user's eye gaze while viewing the event data of the file.

17. The computer system of claim 15 , wherein the file including event data is selected from the group consisting of a log file, a configuration file, and source code.

18. The computer system of claim 15 , wherein the linear regression model outputs a value of the interest score between 0-1 inclusively.

19. The computer system of claim 15 , said method further comprising:
generating a color-coded tag in the file, based on severity of the one or more events of interest.

20. The computer system of claim 15 , said method further comprising:
tagging, by the CPU, each event of interest within the file with a tag as a function of each interest score.

Assignees

• IBM

Inventors

• Cunico Hernan A
• Dunne Jonathan
• O'Connor Jeremiah
• Silva Asima

Classifications

• G06F11/079 Primary

  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

• G06F3/013

  Eye tracking input arrangements (G06F3/015 takes precedence) · CPC title

• G06F3/012

  Head tracking input arrangements · CPC title

• G06F3/023

  Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes · CPC title

• G06F11/0787

  Storage of error reports, e.g. persistent data storage, storage using memory protection · CPC title