Method and system for providing semantics based technical support

• US 10,049,102 B2
• Filed: 12/15/2016
• Issued: 08/14/2018
• Est. Priority Date: 06/26/2014
• Status: Active Grant

• Current Assignee: HCL Technologies Limited
• Original Assignee: HCL Technologies Limited
• Inventors: Prasad, Dhanyamraju S U M, Prakash K, Satya Sai, Chacko, Simy, Ramaraju, Sekhar, Sholayyappan, Shiva
• Primary Examiner(s): Hang, Vu B
• Application Number:
  US15/379,925
• Publication Number:
  US 20170132210A1
• Time in Patent Office: 607 Days
• CPC Class Codes: G06F 11/07 Responding to the occurrence of a fault, e.g. fault tolerance
• CPC Class Codes: G06F 11/0748 in a remote unit communicating with a single-box computer node experiencing an error/fault remote testing G06F11/2294
• CPC Class Codes: G06F 11/0793 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 Class Codes: G06F 16/2228 Indexing structures
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 50/00 Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism healthcare informatics G16H
• CPC Class Codes: G06Q 50/20 Education

Abstract

Disclosed is a system for providing semantics based technical support to a user. A keyword extraction module extracts a set of keywords from a plurality of knowledge content and a plurality of bug content. A matrix generation module generates a keyword-content matrix comprising a similarity score computed for each keyword corresponding to each knowledge content. The matrix generation module further decomposes the keyword-content matrix into one or more sub-matrices. A vector coordinates identification module determines a first set of vector coordinates for each knowledge content of the plurality of knowledge content and a second set of vector coordinates for a bug-query received from a user in real-time. A similarity measure module computes a cosine similarity measure of the bug-query with each knowledge content to identify at least one knowledge content relevant to the bug-query. The knowledge identification module further provides the at least one knowledge content to the user.

Claims

1. A method for providing semantics based technical support to a user, the method comprising:

extracting, by a processor, a set of keywords from a plurality of knowledge content and a plurality of bug content stored in a knowledge repository and a bug repository respectively;

performing, by the processor, Latent Semantics Indexing (LSI) on the set of keywords, in order to index the set of keywords, wherein the set of keywords are indexed based on a set of predefined rules;

generating, by the processor, a keyword-content matrix comprising a similarity score computed for each keyword, of the set of keywords, corresponding to each knowledge content present in the knowledge repository, wherein the similarity score indicates a frequency of occurrence pertaining to each keyword in each of the plurality of knowledge content;

decomposing, by the processor, the keyword-content matrix into one or more sub-matrices, wherein the keyword-content matrix is decomposed based on a low-rank approximation method;

determining, by the processor,

a first set of vector coordinates for each knowledge content of the plurality of knowledge content, and

a second set of vector coordinates for a bug-query received from a user in real-time, wherein the second set of vector coordinates are determined by performing the LSI on the bug-query,

and wherein the first set of vector coordinates and the second set of vector coordinates are determined based on the one or more sub-matrices;

computing, by the processor, a cosine similarity measure of the bug-query with each knowledge content stored in the knowledge repository, wherein the cosine similarity is computed based on the first set of vector coordinates and the second set of vector coordinates and a predefined formulation;

identifying, by the processor, at least one knowledge content, from the knowledge repository, having the cosine similarity measure greater than a threshold value; and

providing, by the processor, the at least one knowledge content to the user thereby providing semantics based technical support to a user.

2. The method of claim 1, wherein the set of keywords is extracted based on at least one of a frequency of occurrence, proximity between various keywords, synonyms, acronyms, and polysemy.

3. The method of claim 1, wherein the LSI is performed on the set of keywords by using one of decomposition methods including a low rank approximation method, a dimensionality reduction method, an Eigen vectors method.

4. The method of claim 1, wherein the set of predefined rules comprises use of stop words, tokenization of text, lowercasing of text, sorting of the set of keywords in alphabetical order.

5. The method of claim 1 further comprises

maintaining, by the processor, a bug repository comprising the at least one knowledge content provided to the user corresponding to the bug-query, wherein the bug repository is maintained to provide the at least one knowledge content when a new bug-query, identical to the bug-query, is received from any user, and

updating, by the processor, the bug repository with the at least one knowledge content provided to the user corresponding to the new bug-query, distinct from the bug-query.

6. A system for providing semantics based technical support to a user, the system comprising:

a processor; and

a memory coupled to the processor, wherein the processor is capable of executing a plurality of modules stored in the memory, and wherein the plurality of modules comprising;

a keyword extraction module for extracting a set of keywords from a plurality of knowledge content and a plurality of bug content stored in a knowledge repository and a bug repository respectively;

an indexing module for performing Latent Semantics Indexing (LSI) on the set of keywords, in order to index the set of keywords, wherein the set of keywords are indexed based on a set of predefined rules;

a matrix generation module for

generating a keyword-content matrix comprising a similarity score computed for each keyword, of the set of keywords, corresponding to each knowledge content present in the knowledge repository, wherein the similarity score indicates a frequency of occurrence pertaining to each keyword in each of the plurality of knowledge content;

decomposing the keyword-content matrix into one or more sub-matrices, wherein the keyword-content matrix is decomposed based on a low-rank approximation method;

an vector coordinates identification module for determining

a first set of vector coordinates for each knowledge content of the plurality of knowledge content, and

a second set of vector coordinates for a bug-query received from a user in real-time, wherein the second set of vector coordinates are identified by performing the LSI on the bug-query,

and wherein the first set of vector coordinates and the second set of vector coordinates are identified based on the one or more sub-matrices;

a similarity measure module for computing a cosine similarity measure of the bug-query with each knowledge content stored in the knowledge repository, wherein the cosine similarity is computed based on the first set of vector coordinates and the second set of vector coordinates and a predefined formulation;

a knowledge identification module for

identifying at least one knowledge content, from the knowledge repository, having the cosine similarity measure greater than a threshold value; and

providing the at least one knowledge content to the user thereby providing semantics based technical support to a user.

7. The system of claim 6, wherein the set of keywords is extracted based on at least one of a frequency of occurrence, proximity between various keywords, synonyms, acronyms, and polysemy.

8. The system of claim 6, wherein the LSI is performed on the set of keywords by using one of decomposition methods including a low rank approximation method, a dimensionality reduction method, an Eigen vectors method.

9. The system of claim 6, wherein the set of predefined rules comprises use of stop words, tokenization of text, lowercasing of text, and sorting of the set of keywords in alphabetical order.

10. A non-transitory computer readable medium embodying a program executable in a computing device for providing semantics based technical support to a user, the program comprising a program code:

a program code for extracting a set of keywords from a plurality of knowledge content and a plurality of bug content stored in a knowledge repository and a bug repository respectively;

a program code for performing Latent Semantics Indexing (LSI) on the set of keywords, in order to index the set of keywords, wherein the set of keywords are index based on a set of predefined rules;

a program code for generating a keyword-content matrix comprising a similarity score computed for each keyword, of the set of keywords, corresponding to each knowledge content present in the knowledge repository, wherein the similarity score indicates a frequency of occurrence pertaining to each keyword in each of the plurality of knowledge content;

a program code for decomposing the keyword-content matrix comprising into one or more sub-matrices, wherein the keyword-content matrix is decomposed based on a low-rank approximation method;

a program code for determining

a first set of vector coordinates for each knowledge content of the plurality of knowledge content, and

a second set of vector coordinates for a bug-query received from a user in real-time, wherein the second set of vector coordinates are identified by performing the LSI on the bug-query,

and wherein the first set of vector coordinates and the second set of vector coordinates are identified based on the one or more sub-matrices;

a program code for computing a cosine similarity measure of the bug-query with each knowledge content stored in the knowledge repository, wherein the cosine similarity is computed based on the first set of vector coordinates and the second set of vector coordinates and a predefined formulation;

a program code for identifying at least one knowledge content, from the knowledge repository, having the cosine similarity measure greater than a threshold value; and

a program code for providing the at least one knowledge content to the user thereby providing semantics based technical support to a user.