Granted Patent B2

US 11,507,451 · App. 17/206,292 · Granted Nov 22, 2022

Inventors: Jayanth Kumar Reddy Perneti (Horamavu, IN); Vindhya Gangaraju (Davanagere, IN)

Assignee: Dell Products L.P.

G06F11/0793G06F11/0751G06F16/215G06N20/00

Abstract

Claims (71)

1. A method for managing bugs, the method comprising:

obtaining, by a bug deduplication system, a set of bugs;

performing an encoding on each section of a first bug of the set of bugs to obtain encoded sections, wherein the encoded sections comprise a first encoded section and a second encoded section, wherein each section of the first bug comprises a portion of an issue associated with the first bug, and wherein the encoded sections are generated using a neural network algorithm;

applying a first classification model to the first encoded section to obtain a first section score;

applying a second classification model to the second encoded section to obtain a second section score;

generating a confidence score based on the first encoded section and the second encoded section; and

providing the confidence score to a client,

wherein the client initiates a corrective action for the first bug based on the confidence score.

2. The method of claim 1 , further comprising:

prior to performing the encoding:

performing a format conversion on each bug in the set of bugs to obtain a set of reformatted bugs,

wherein the first bug is a reformatted bug of the set of reformatted bugs.

3. The method of claim 1 ,

wherein the set of bugs is associated with an application,

wherein the application is monitored using a bug tracking system operatively connected to the bug deduplication system, and

wherein the set of bugs is obtained from the bug tracking system.

4. The method of claim 1 , wherein the first classification model is generated using a machine learning model applied to first encoded sections of a first portion of the set of bugs, wherein the first encoded sections do not include the first encoded section.

5. The method of claim 4 , wherein the first bug is associated with a second portion of the set of bugs.

6. The method of claim 1 , wherein a section of the first bug comprises at least one of: structured information, a summary of the first bug, and a long description.

7. The method of claim 1 , further comprising:

performing a second encoding on each section of a second bug of the set of bugs to obtain additional encoded sections, wherein the additional encoded sections comprise a third encoded section and a fourth encoded section;

applying a third classification model to the third encoded section to obtain a third section score;

applying a fourth classification model to the fourth encoded section to obtain a fourth section score;

generating a second confidence score based on the third encoded section and the fourth encoded section.

8. The method of claim 7 , further comprising:

making a determination that the confidence score and the second confidence score meet a confidence threshold, and

based on the determination, sending a bug deduplication report to the client, wherein the confidence score and the second confidence score are specified in the bug deduplication report.

9. A non-transitory computer readable medium comprising computer readable program code, which when executed by a computer processor enables the computer processor to perform a method for managing bugs, the method comprising:

obtaining, by a bug deduplication system, a set of bugs;

performing an encoding on each section of a first bug of the set of bugs to obtain encoded sections, wherein the encoded sections comprise a first encoded section and a second encoded section, wherein each section of the first bug comprises a portion of an issue associated with the first bug, and wherein the encoded sections are generated using a neural network algorithm;

applying a first classification model to the first encoded section to obtain a first section score;

applying a second classification model to the second encoded section to obtain a second section score;

generating a confidence score based on the first encoded section and the second encoded section; and

providing the confidence score to a client,

wherein the client initiates a corrective action for the first bug based on the confidence score.

10. The non-transitory computer readable medium of claim 9 , the method further comprising:

prior to performing the encoding:

performing a format conversion on each bug in the set of bugs to obtain a set of reformatted bugs,

wherein the first bug is a reformatted bug of the set of reformatted bugs.

11. The non-transitory computer readable medium of claim 9 ,

wherein the set of bugs is associated with an application,

wherein the application is monitored using a bug tracking system operatively connected to the bug deduplication system, and

wherein the set of bugs is obtained from the bug tracking system.

12. The non-transitory computer readable medium of claim 9 , wherein the first classification model is generated using a machine learning model applied to first encoded sections of a first portion of the set of bugs, wherein the first encoded sections do not include the first encoded section.

13. The non-transitory computer readable medium of claim 12 , wherein the first bug is associated with a second portion of the set of bugs.

14. The non-transitory computer readable medium of claim 9 , wherein a section of the first bug comprises at least one of: structured information, a summary of the first bug, and a long description.

15. The non-transitory computer readable medium of claim 9 , the method further comprising:

performing a second encoding on each section of a second bug of the set of bugs to obtain additional encoded sections, wherein the additional encoded sections comprise a third encoded section and a fourth encoded section;

applying a third classification model to the third encoded section to obtain a third section score;

applying a fourth classification model to the fourth encoded section to obtain a fourth section score;

generating a second confidence score based on the third encoded section and the fourth encoded section.

16. The non-transitory computer readable medium of claim 9 , the method further comprising:

making a determination that the confidence score and the second confidence score meet a confidence threshold, and

based on the determination, sending a bug deduplication report to the client, wherein the confidence score and the second confidence score are specified in the bug deduplication report.

17. A system comprising:

a processor; and

memory comprising instructions, which when executed by the processor, perform a method comprising:

obtaining, by a bug deduplication system, a set of bugs;

performing an encoding on each section of a first bug of the set of bugs to obtain encoded sections, wherein the encoded sections comprise a first encoded section and a second encoded section, wherein each section of the first bug comprises a portion of an issue associated with the first bug, and wherein the encoded sections are generated using a neural network algorithm;

applying a first classification model to the first encoded section to obtain a first section score;

applying a second classification model to the second encoded section to obtain a second section score;

generating a confidence score based on the first encoded section and the second encoded section; and

providing the confidence score to a client,

wherein the client initiates a corrective action for the first bug based on the confidence score.

18. The system of claim 17 , wherein the first classification model is generated using a machine learning model applied to first encoded sections of a first portion of the set of bugs, wherein the first encoded sections do not include the first encoded section.

19. The system of claim 17 , wherein a section of the first bug comprises at least one of:

structured information, a summary of the first bug, and a long description.

20. The system of claim 17 , the method further comprising:

performing a second encoding on each section of a second bug of the set of bugs to obtain additional encoded sections, wherein the additional encoded sections comprise a third encoded section and a fourth encoded section;

applying a third classification model to the third encoded section to obtain a third section score;

apply a fourth classification model to the fourth encoded section to obtain a fourth section score.

Assignments (10)

Continuity (1)