Claims:WE CLAIM
1. A method for generating an optimized result set, the method comprising:
determining, by a response generating device, a vector representation for each of a plurality of input keywords extracted from an input query;
determining, by the response generating device, a plurality of representative keywords corresponding to the plurality of input keywords from a keyword database based on the vector representation for each of the plurality of input keywords and a vector representation for each of a plurality of keywords in the keyword database;
determining, by the response generating device, a score for a plurality of response candidates corresponding to the input query based on a relative importance score and a similarity score for each of the plurality of representative keywords present in the plurality of response candidates; and
generating, by the response generating device, a result set from the plurality of response candidates based on the score.

2. The method of claims 1, further comprising creating the keyword database during a training phase, wherein the keyword database comprises the plurality of keywords, the vector representation for each of the plurality of keywords, and a relative importance score for each of the plurality of keywords.

3. The method of claim 1, wherein the vector representation for a keyword is determined based on one or more locations of the keyword in a contextual space in a training data using a machine learning algorithm, wherein the training data comprises at least one of a domain data and a generic data.

4. The method of claim 1, wherein the relative importance score for a keyword is determined based on a frequency of occurrence of the keyword in a training data, wherein the training data comprises at least one of a domain data and a generic data.

5. The method of claim 4, wherein the relative importance score is normalized based on a minimum relative importance score and a maximum relative importance score for the training data.

6. The method of claim 1, further comprising determining a normalized relative importance score for each of the plurality of representative keywords with respect to the input query based on a sum of relative importance scores for the plurality of input keywords, wherein determining the score comprises determining the score based on the normalized relative importance score for each of the plurality of representative keywords.

7. The method of claim 1, wherein determining the plurality of representative keywords comprises:
determining a similarity score between each of the plurality of input keywords and each of the plurality of keywords in the keyword database based on the vector representation for each of the plurality of input keywords and the vector representation for each of the plurality of keywords; and
determining the plurality of representative keywords corresponding to the plurality of input keywords based on the similarity score.

8. The method of claim 1, further comprising determining the plurality of response candidates from a knowledge database based on the input query using one or more search algorithm, and wherein the knowledge database comprises at least one of a domain data and a generic data.

9. The method of claim 1, wherein the result set comprises one or more optimal response candidates along with a corresponding confidence level.

10. The method of claim 9, wherein the confidence level is determined using a fuzzy inference system based on the score and a number of input keywords substituted by the representative keywords.

11. A system for generating an optimized result set, the system comprising:
at least one processor; and
a computer-readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
determining a vector representation for each of a plurality of input keywords extracted from an input query;
determining a plurality of representative keywords corresponding to the plurality of input keywords from a keyword database based on the vector representation for each of the plurality of input keywords and a vector representation for each of a plurality of keywords in the keyword database;
determining a score for a plurality of response candidates corresponding to the input query based on a relative importance score and a similarity score for each of the plurality of representative keywords present in the plurality of response candidates; and
generating a result set from the plurality of response candidates based on the score.

12. The system of claim 11, wherein the operations further comprise creating the keyword database during a training phase, wherein the keyword database comprises the plurality of keywords, the vector representation for each of the plurality of keywords, and a relative importance score for each of the plurality of keywords.

13. The system of claim 11, wherein the vector representation for a keyword is determined based on one or more locations of the keyword in a contextual space in a training data using a machine learning algorithm, wherein the training data comprises at least one of a domain data and a generic data.

14. The system of claim 11, wherein the relative importance score for a keyword is determined based on a frequency of occurrence of the keyword in a training data, wherein the training data comprises at least one of a domain data and a generic data, and wherein the relative importance score is normalized based on a minimum relative importance score and a maximum relative importance score for the training data.

15. The system of claim 11, wherein the operations further comprise determining a normalized relative importance score for each of the plurality of representative keywords with respect to the input query based on a sum of relative importance scores for the plurality of input keywords, and wherein determining the score comprises determining the score based on the normalized relative importance score for each of the plurality of representative keywords.

16. The system of claim 11, wherein determining the plurality of representative keywords comprises:
determining a similarity score between each of the plurality of input keywords and each of the plurality of keywords in the keyword database based on the vector representation for each of the plurality of input keywords and the vector representation for each of the plurality of keywords; and
determining the plurality of representative keywords corresponding to the plurality of input keywords based on the similarity score.

17. The system of claim 11, wherein the operations further comprise determining the plurality of response candidates from a knowledge database based on the input query using one or more search algorithm, and wherein the knowledge database comprises at least one of a domain data and a generic data.

18. The system of claim 11, wherein the result set comprises one or more optimal response candidates along with a corresponding confidence level, and wherein the confidence level is determined using a fuzzy inference system based on the score and a number of input keywords substituted by the representative keywords.

Dated this 12th day of March, 2016

Swetha SN
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
This disclosure relates generally to information retrieval, and more particularly to system and method for generating an optimized result set based on vector based relative importance measure (VRIM).