System and method for classifying and resolving software production incidents

Patent metadata

Field	Value
Publication number	US-10067760-B2
Application number	US-201615069633-A
Country	US
Kind code	B2
Filing date	Mar 14, 2016
Priority date	Jan 18, 2016
Publication date	Sep 4, 2018
Grant date	Sep 4, 2018

Abstract

A system and method for classifying and resolving software production incident tickets includes receiving an incident ticket, extracting a plurality of keywords from the incident ticket, and deriving a query vector corresponding to the incident ticket based on the plurality of keywords. The system and method further comprises classifying the incident ticket into at least one of a positive mechanization incident ticket and a negative mechanization incident ticket based on a comparison of the query vector and a plurality of vectors derived from a plurality of past incident tickets. The plurality of vectors are derived based on a plurality of keywords and their corresponding occurrences in the plurality of past incident tickets.

First claim

What is claimed is:

1. A method for classifying software production incident tickets, the method comprising:
extracting, by a processor, a plurality of keywords from an incident ticket; deriving, by the processor, a query vector corresponding to the incident ticket based on the plurality of keywords; and
classifying, by the processor, the incident ticket into at least one of a positive mechanization incident ticket and a negative mechanization incident ticket based on a comparison of the query vector and a plurality of vectors derived from a plurality of past incident tickets, wherein the comparison comprises at least
adjusting the size of query vector by populating the query vector with dummy keywords, such that the query vector is of the same size as a vector from the plurality of vectors with which the comparison is to be performed, and
adjusting the placement of the keywords within the query vector such that the adjusted keywords correspond to the placements of similar keywords within the vector from the plurality of vectors, and wherein the plurality of vectors are derived based on a plurality of keywords, and their corresponding occurrences in the plurality of past incident tickets, wherein the adjusted keywords are in the same positions as the similar keywords within the vector from the plurality of vectors.

2. The method of claim 1 , wherein the extracting the plurality of keywords further comprises pre-processing, by the processor, the incident ticket for stemming or for removing at least one stop word.

3. The method of claim 1 , further comprising determining, by the processor, a unique number representation for each of the plurality of keywords.

4. The method of claim 1 , further comprising deriving the plurality of vectors from the plurality of past incident tickets by:
categorizing, by the processor, the plurality of past incident tickets in an incident repository into at least two category based on a mechanization status;
extracting, by the processor, for each category the plurality of keywords from the plurality of past incident tickets; and
deriving, by the processor, for each category the plurality of vectors based on the plurality of keywords and their corresponding occurrences in plurality of past incident tickets.

5. The method of claim 4 , wherein the deriving the plurality of vectors further comprises deriving, by the processor, the plurality of vectors for at least one of all keywords, noun keywords, or verb keywords.

6. The method of claim 4 , wherein the deriving the plurality of vectors further comprises deriving, by the processor, the plurality of vectors for at least one of a mode, a median, or a range for the plurality of keywords.

7. The method of claim 4 , wherein the deriving the plurality of vectors further comprises normalizing, by the processor, each of the plurality of vectors.

8. The method of claim 1 , wherein the classifying further comprises performing, by the processor, a nearest neighbor classification based on at least one of a similarity and a dissimilarity between the query vector and the plurality of vectors.

9. The method of claim 8 , wherein the similarity comprises a cosine similarity, wherein the dissimilarity comprises a Euclidean distance, and wherein the performing the nearest neighbor classification further comprises determining, by the processor, a decision parameter based on the cosine similarity and the Euclidean distance.

10. The method of claim 1 , wherein the classifying further comprises deriving, by the processor, one or more feature matrices based on the plurality of vectors and comparing the query vector and the one or more feature matrices.

11. The method of claim 1 , further comprising resolving, by the processor, the incident ticket using an existing solution for the positive mechanization incident ticket by:
identifying, by the processor, the existing solution from a plurality of existing solutions indexed in a knowledge repository based on the incident ticket; and
invoking, by the processor, one or more scripts associated with the existing solution.

12. The method of claim 11 , further comprising updating, by the processor, the incident repository with the incident ticket and, for the positive mechanization incident ticket, with the existing solution.

13. A software production incident ticket classification computing apparatus comprising memory and one or more processors configured to be capable of executing programmed instructions stored in the memory to:
extract a plurality of keywords from an incident ticket;
derive a query vector corresponding to the incident ticket based on the plurality of keywords;
classify the incident ticket into at least one of a positive mechanization incident ticket and a negative mechanization incident ticket based on a comparison of the query vector and a plurality of vectors derived from a plurality of past incident tickets, wherein the comparison comprises at least
adjusting the size of query vector by populating the query vector with dummy keywords, such that the query vector is of the same size as a vector from the plurality of vectors with which the comparison is to be performed, and
adjusting the placement of the keywords within the query vector such that the adjusted keywords correspond to the placements of similar keywords within the vector from the plurality of vectors, and wherein the plurality of vectors are derived based on a plurality of keywords and their corresponding occurrences in the plurality of past incident tickets, wherein the adjusted keywords are in the same positions as the similar keywords within the vector from the plurality of vectors.

14. The apparatus of claim 13 , wherein the one or more processors are further configured to be capable of executing the programmed instructions stored in the memory to determine a unique number representation for each of the plurality of keywords.

15. The apparatus of claim 13 , wherein the one or more processors are further configured to be capable of executing the programmed instructions stored in the memory to:
derive the plurality of vectors from the plurality of past incident tickets that further comprises programmed instructions to:
categorize the plurality of past incident tickets in an incident repository into at least two category based on a mechanization status;
extract for each category the plurality of keywords from the plurality of past incident tickets; and
derive for each category the plurality of vectors based on the plurality of keywords and their corresponding occurrences in plurality of past incident tickets.

16. The apparatus of claim 15 , wherein the derive the plurality of vectors further comprises the one or more processors being further configured to be capable of executing the programmed instructions stored in the memory to:
derive the plurality of vectors for at least one of all keywords, noun keywords, or verb keywords.

17. The apparatus of claim 15 , wherein the derive the plurality of vectors further comprises the one or more processors being further configured to be capable of executing the programmed instructions stored in the memory to:
derive the plurality of vectors for at least one of a mode, a median, or a range for the plurality of keywords.

18. The apparatus of claim 13 , wherein the classify the incident ticket into at least one of the positive mechanization incident ticket and the negative mechanization incident ticket further comprises the one or more processors being further configured to be capable of executing the programmed instructio

Assignees

• Wipro Ltd

Inventors

• Ryali Premchand
• Guruswamappa Shivamurthy Harave
• Balasubramanian Ramkumar

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06F8/20

  Software design · CPC title

• G06F8/60 Primary

  Software deployment · CPC title

• G06F16/353

  into predefined classes · CPC title

• G06N5/00

  Computing arrangements using knowledge-based models · CPC title