METHOD AND SYSTEM FOR AUTOMATICALLY IDENTIFYING ISSUES IN ONE OR MORE TICKETS OF AN ORGANIZATION

• US 20170262858A1
• Filed: 03/31/2016
• Published: 09/14/2017
• Est. Priority Date: 03/11/2016
• Status: Active Grant

• Current Assignee: Wipro Limited
• Original Assignee: Wipro Limited
• Inventors: Rajaram, Venkatakrishnan, Konnayar, Narayanan Ramani, Chakraborty, Ria, Soundararajan, Malathi Bellam
• Granted Patent: US 9,984,376 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/226 Validation
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06Q 30/016 After-sales

Abstract

The present disclosure relates to method and system for automatically identifying one or more issues in one or more tickets of an organization. An issue identification system retrieves a sequence pattern from ticket data received from one or more data sources. The issue identification system generates one or more first sub-sequence patterns of the n-grams from the sequence pattern. Further, frequency of occurrence and Part-of-Speech (POS) weightage of each of the one or more first sub-sequence patterns of the n-grams are determined by the issue identification system. A first score is determined for each of the one or more first sub-sequence patterns of the n-grams based on both the frequency and the POS weightage. Upon determining the first score, the issue identification system identifies one or more issues in the one or more tickets automatically based on the first sub-sequence pattern of the n-grams associated with a highest first score.

Claims

1. A method for automatically identifying one or more issues in one or more tickets of an organization, the method comprising:

receiving, by an issue identification system, ticket data of one or more tickets related to a service category from one or more data sources;

generating, by the issue identification system, one or more first sub-sequence patterns of n-grams for the one or more tickets from a sequence pattern retrieved from the ticket data;

determining, by the issue identification system, a frequency of occurrence of each of the one or more first sub-sequence patterns of the n-grams and a Part-of-Speech (POS) weightage of the one or more first sub-sequence patterns of the n-grams;

determining, by the issue identification system, a first score for each of the one or more first sub-sequence patterns of the n-grams based on the frequency of occurrence and the POS weightage; and

identifying, by the issue identification system, automatically, one or more issues in the one or more tickets based on the first sub-sequence pattern of the n-grams associated with a highest first score.

2. The method as claimed in claim 1, wherein determining the POS weightage comprises:

assigning, by the issue identification system, a POS tag to each of one or more words in the one or more first sub-sequence patterns of the n-grams, to form a combination of the POS tags for each of the one or more first sub-sequence patterns; and

assigning, by the issue identification system, a predefined weightage for the combination of the POS tags for each of the one or more first sub-sequence patterns.

3. The method as claimed in claim 2, wherein the predefined weightage is assigned based on a predefined priority associated with each of the one or more combinations of the POS tags.

4. The method as claimed in claim 1, wherein the ticket data comprises ticket Identification (ID), description of one or more issues, the service category of the one or more tickets and other data related to the one or more tickets.

5. The method as claimed in claim 1, wherein the one or more first sub-sequence patterns are generated by retaining order of words in the sequence pattern;

6. The method as claimed in claim 1 further comprises:

identifying, by the issue identification system, the sequence pattern corresponding to the one or more first sub-sequence patterns of the n-grams having the first score less than a predefined value for each of the one or more tickets;

generating, by the issue identification system, one or more second sub-sequence patterns of the n-grams by removing one or more words in the sequence pattern in order of occurrence, wherein a distance value is associated with each of the one or more second sub-sequence patterns based on the one or more words removed in the sequence pattern;

determining, by the issue identification system, a frequency of occurrence of each of the one or more second sub-sequence patterns of the n-grams and a POS weightage of the one or more second sub-sequence patterns of the n-grams;

determining, by the issue identification system, a second score for each of the one or more second sub-sequence patterns of the n-grams based on the frequency of occurrence and the POS weightage of the one or more second sub-sequence patterns of the n-grams; and

updating, by the issue identification system, automatically, the one or more issues in the one or more tickets by merging the second sub-sequence pattern with a highest second score with the first sub-sequence pattern with the highest first score.

7. The method as claimed in claim 6, wherein determining the POS weightage comprises:

assigning, by the issue identification system, a POS tag to each of one or more words of the one or more second sub-sequence patterns of the n-grams to form a combination of the POS tags for each of the one or more second sub-sequence patterns; and

assigning, by the issue identification system, a predefined weightage for the combination of the POS tags for each of the one or more second sub-sequence patterns.

8. The method as claimed in claim 7, wherein the predefined weightage is assigned based on a predefined priority associated with each of the one or more combinations of the POS tags.

9. The method as claimed in claim 6 further comprises:

comparing, by the issue identification system, each of the one or more words in at least one of the first and the second sub-sequence patterns of the n-grams with one or more predefined domain keywords;

obtaining, by the issue identification system, at least one of the one or more first subsequence patterns and the one or more second sub-sequence patterns comprising the one or more predefined domain keywords as at least one of a representative first sub-sequence pattern and representative second sub-sequence pattern; and

identifying, by the issue identification system, automatically, one or more issues in each of the one or more tickets based on at least one of the representative first sub-sequence pattern and representative second sub-sequence pattern.

10. An issue identification system for automatically identifying one or more issues in one or more tickets of an organization, the issue identification system comprising:

a processor; and

a memory communicatively coupled to the processor, wherein the memory stores the processor-executable instructions, which, on execution, causes the processor to;

receive ticket data of one or more tickets related to a service category from one or more data sources;

generate one or more first sub-sequence patterns of n-grams for the one or more tickets from a sequence pattern retrieved from the ticket data;

determine frequency of occurrence of each of the one or more first sub-sequence patterns of the n-grams and a Part-of-Speech (POS) weightage of the one or more first sub-sequence patterns of the n-grams;

determine a first score for each of the one or more first sub-sequence patterns of the n-grams based on the frequency of occurrence and the POS weightage; and

identify automatically, one or more issues in the one or more tickets based on the first sub-sequence pattern of the n-grams associated with a highest first score.

11. The issue identification system as claimed in claim 10, wherein the ticket data comprises ticket Identification (ID), description of one or more issues, the service category of the one or more tickets and other data related to the one or more tickets.

12. The issue identification system as claimed in claim 10, wherein the processor is further configured to determine the POS weightage by:

assigning POS tags to each of one or more words of the one or more first sub-sequence patterns of the n-grams to form a combination of the POS tags for each of the one or more first sub-sequence patterns; and

assigning a predefined weightage for the combination of the POS tags for each of the one or more first sub-sequence patterns.

13. The issue identification system as claimed in claim 12, wherein the processor assigns the predefined weightage based on a predefined priority associated with each of the one or more combinations of the POS tags.

14. The issue identification system as claimed in claim 10, wherein the processor generates the one or more first sub-sequence patterns by retaining order of words in the sequence pattern.

15. The issue identification system as claimed in claim 10, wherein the processor is further configured to:

identify the sequence pattern corresponding to the one or more first sub-sequence patterns of the n-grams having the first score less than a predefined value for each of the one or more tickets;

generate one or more second sub-sequence patterns of the n-grams by removing one or more words in the sequence pattern in order of occurrence, wherein a distance value is associated with each of the one or more second sub-sequence patterns based on the one or more words removed in the sequence pattern;

determine a frequency of occurrence of each of the one or more second sub-sequence patterns of the n-grams and a POS weightage of the one or more second sub-sequence patterns of the n-grams;

determine a second score for each of the one or more second sub-sequence patterns of the n-grams based on the frequency of occurrence and the POS weightage of the one or more second sub-sequence patterns of the n-grams; and

update automatically, the one or more issues in the one or more tickets by merging the second sub-sequence pattern with a highest second score with the first sub-sequence pattern with the highest first score.

16. The issue identification system as claimed in claim 15, wherein the processor is further configured to determine the POS weightage by:

assigning POS tags to each of one or more words of the one or more second sub-sequence patterns of the n-grams to form a combination of the POS tags for each of the one or more second sub-sequence patterns; and

assigning a predefined weightage for the combination of the POS tags for each of the one or more second sub-sequence patterns.

17. The issue identification system as claimed in claim 16, wherein the processor assigns the predefined weightage based on a predefined priority associated with each of the one or more combinations of the POS tags.

18. The issue identification system as claimed in claim 15, wherein the processor is further configured to:

compare each of the one or more words in at least one of the first or the second sub-sequence patterns of the n-grams with one or more predefined domain keywords;

obtain at least one of the one or more first subsequence patterns and the one or more second sub-sequence patterns comprising the one or more predefined domain keywords as a pattern with the highest score based on the comparison; and

identify automatically, one or more issues in each of the one or more tickets based on the pattern with the highest score.

19. A non-transitory computer readable medium including instructions stored thereon that when processed by at least one processor causes an issue identification system to perform operations comprising:

receiving ticket data of one or more tickets related to a service category from one or more data sources;

generating one or more first sub-sequence patterns of n-grams for the one or more tickets from a sequence pattern retrieved from the ticket data;

determining a frequency of occurrence of each of the one or more first sub-sequence patterns of the n-grams and a Part-of-Speech (POS) weightage of the one or more first sub-sequence patterns of the n-grams;

determining a first score for each of the one or more first sub-sequence patterns of the n-grams based on the frequency of occurrence and the POS weightage; and

identifying automatically, one or more issues in the one or more tickets based on the first sub-sequence pattern of the n-grams associated with a highest first score.