Automatic generation of actionable recommendations from problem reports

Patent metadata

Field	Value
Publication number	US-9250993-B2
Application number	US-201313874390-A
Country	US
Kind code	B2
Filing date	Apr 30, 2013
Priority date	Apr 30, 2013
Publication date	Feb 2, 2016
Grant date	Feb 2, 2016

Abstract

Methods and arrangements for handling information technology tickets. A plurality of information technology tickets are received. The tickets are clustered into categories, and a problem area is identified with respect to at least one of the categories. At least one recommendation is automatically generated for addressing the problem area. Other variants and embodiments are broadly contemplated herein.

First claim

What is claimed is:

1. A method of handling information technology tickets, said method comprising:
utilizing at least one processor to execute computer code configured to perform the steps of:
receiving a plurality of information technology tickets;
preprocessing the plurality of information technology tickets;
clustering via applying at least one clustering technique, the preprocessed plurality of information technology tickets into categories, wherein each category comprises technology tickets having at least one common characteristic;
identifying a problem area for recommendation generation with respect to at least one of the categories, wherein said identifying comprises building a discrete probability distribution with respect to a plurality of problem areas and calculating an entropy value with respect to each of the problem areas; and
automatically generating at least one recommendation for addressing the problem area.

2. The method according to claim 1 , wherein said preprocessing comprises cleansing the tickets.

3. The method according to claim 1 , wherein said preprocessing comprises performing template and keyword extraction with respect to the tickets.

4. The method according to claim 1 , wherein said clustering comprises applying at least two clustering techniques and merging results from the techniques.

5. The method according to claim 4 , wherein the two techniques comprise at least one technique selected from the group consisting of: a lingo clustering technique, and a hierarchical N-gram clustering technique.

6. The method of claim 4 , wherein the merging comprises using at least one heuristic to combine resulting clusters of each of the at least two clustering techniques into at least one category.

7. The method according to claim 1 , wherein said identifying comprises correlating the problem area with respect to at least one pre-defined metric.

8. The method according to claim 1 , wherein said generating comprises providing at least one item for further investigation, via said identifying comprising determining a specificity and diversity of at least one distribution with respect to the problem area.

9. The method of claim 8 , wherein said identifying further comprises ranking the plurality of problem areas based upon the entropy values, wherein the problem areas with a high entropy value are shown for specificity and problems areas with a low entropy value are shown for diversity.

10. The method according to claim 1 , wherein said identifying further comprises ranking the plurality of problem areas based upon the entropy values.

11. An apparatus for handling information technology tickets, said apparatus comprising:
at least one processor; and
a computer readable storage medium having computer readable program code embodied therewith and executable by the at least one processor, the computer readable program code comprising:
computer readable program code that receives a plurality of information technology tickets;
computer readable program code that preprocesses the plurality of information technology tickets;
computer readable program code that clusters via applying at least one clustering technique, the preprocessed plurality of information technology tickets into categories, wherein each category comprises technology tickets having at least one common characteristic;
computer readable program code that identifies a problem area for recommendation generation with respect to at least one of the categories, wherein said identifying comprises building a discrete probability distribution with respect to a plurality of problem areas and calculating an entropy value with respect to each of the problem areas; and
computer readable program code that automatically generates at least one recommendation for addressing the problem area.

12. A computer program product for handling information technology tickets, said computer program product comprising:
a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code that receives a plurality of information technology tickets;
computer readable program code that preprocesses the plurality of information technology tickets;
computer readable program code that clusters via applying at least one clustering technique, the preprocessed plurality of information technology tickets into categories, wherein each category comprises technology tickets having at least one common characteristic;
computer readable program code that identifies a problem area for recommendation generation with respect to at least one of the categories, wherein said identifying comprises building a discrete probability distribution with respect to a plurality of problem areas and calculating an entropy value with respect to each of the problem areas; and
computer readable program code that automatically generates at least one recommendation for addressing the problem area.

13. The computer program product according to claim 12 , wherein said computer readable program code is configured to cleanse the tickets.

14. The computer program product according to claim 12 , wherein said computer readable program code that preprocesses comprises template and keyword extraction with respect to the tickets.

15. The computer program product according to claim 12 , wherein said computer readable program code applies at least two clustering techniques and merges results from the techniques.

16. The computer program product according to claim 15 , wherein the two techniques comprise at least one technique selected from the group consisting of: a lingo clustering technique, and a hierarchical N-gram clustering technique.

17. The computer program product according to claim 12 , wherein said computer readable program code that identifies comprises correlating the problem area with respect to at least one pre-defined metric.

18. The computer program product according to claim 12 , wherein said computer readable program code that generates comprises providing at least one item for further investigation, via said to identify comprising determining a specificity and diversity of at least one distribution with respect to the problem area.

19. The computer program product according to claim 18 , wherein said computer readable program code that identifies further comprises ranking the plurality of problem areas based upon the entropy values.

20. A method comprising:
accepting a plurality of information technology tickets;
finding an unstructured attribute in each of the information technology tickets;
clustering, applying at least one clustering technique, the information technology tickets into groups based on the unstructured attribute, wherein each group comprises technology tickets having at least one common characteristic; and
said clustering comprising applying at least two clustering methods and merging results of the at least two clustering methods
identifying a problem area for recommendation generation with respect to at least one of the categories, wherein said identifying comprises building a discrete probability distribution with respect to a plurality of problem areas and calculating an entropy value with respect to each of the problem areas.

Assignees

• IBM
• Globalfoundries Inc

Inventors

• Mani Senthil K K
• Sankaranarayanan Karthik
• Sinha Vibha S
• Visweswariah Karthik

Classifications

• G06F17/30598

  Physics · mapped topic

• 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

• G06F16/285 Primary

  Clustering or classification · CPC title