Cognitive Interactive Search Based on Personalized User Model and Context

• US 20160196336A1
• Filed: 01/02/2015
• Published: 07/07/2016
• Est. Priority Date: 01/02/2015
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Allen, Corville O., Rodriguez, Laura J.
• Application Number:
  US14/588,547
• Publication Number:
  US 20160196336A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Mechanisms, in a Question and Answer (QA) system, are provided for performing a personalized context based search of a corpus of information. A question is received, by the QA system, from a first user via a source device. A first user profile associated with the first user, which specifies a personality trait of the first user, is retrieved. First candidate answers to the original question are generated based on a search of a corpus and second users having a similar personality trait to the personality trait of the first user are identified. Similar questions to that of the original question, which were previously submitted to the QA system by the one or more second users are identified. Second candidate answers based on the one or more similar questions are generated by the QA system. A final answer based on the first candidate answers and the second candidate answers is generated and output to the user via the source device.

Claims

1. A method, in a data processing system implementing a Question and Answer (QA) system, for performing a personalized context based search of a corpus of information, comprising:

receiving, by the QA system, from a first user via a source device, an original question for processing by the QA system to generate an answer result;

retrieving, by the QA system, a first user profile associated with the first user, wherein the first user profile specifies a personality trait of the first user;

generating, by the QA system, one or more first candidate answers to the original question based on a search of a corpus of electronic content;

identifying, by the QA system, one or more second users having a similar personality trait to the personality trait of the first user;

identifying, by the QA system, one or more similar questions, similar to that of the original question, previously submitted to the QA system by the one or more second users;

generating, by the QA system, one or more second candidate answers based on the one or more similar questions;

generating, by the QA system, a final answer based on the one or more first candidate answers and one or more second candidate answers; and

outputting, by the QA system, the answer to the user via the source device.

2. The method of claim 1, wherein the one or more second users are second users logically connected to the first user by a common context.

3. The method of claim 2, wherein the corpus of electronic content comprises a portion of electronic content associated with the common context.

4. The method of claim 3, wherein the first user profile comprises an identifier of a context associated with the first user, and wherein the method further comprises selecting the common context and the portion of electronic content associated with the common context based on the context identified in the first user profile.

5. The method of claim 4, wherein the first user profile comprises a plurality of identifiers of contexts associated with the first user, and wherein the common context is selected based on a correlation of features of the original question with an identified context in the first user profile.

6. The method of claim 2, wherein the common context comprises an online community with which the first user and the one or more second users are associated.

7. The method of claim 2, wherein the common context comprises at least one of electronic objects accessed by the first user and the one or more second users within a historical time frame, electronic communications exchanged between the first user and the one or more second users, or electronic communications exchanged between a plurality of the one or more second users.

8. The method of claim 1, wherein generating one or more second candidate answers based on the one or more similar questions comprises:

identifying one or more portions of the one or more similar questions that align with the personality trait of the first user; and

generating one or more supplemental queries based on the identified portions of the one or more similar questions.

9. The method of claim 8, wherein generating one or more second candidate answers based on the one or more similar questions further comprises performing an interactive exchange between the QA system and a client computing device of the first user that outputs a listing of the one or more portions to the first user and receives a selection from the first user of at least one portion in the one or more portion for use in generating supplemental queries, wherein the one or more supplemental queries are generated based on the selected at least one portion.

10. The method of claim 8, wherein generating one or more second candidate answers based on the one or more similar questions further comprises:

applying the one or more supplemental queries to the corpus to generate the one or more second candidate answers; and

generating a ranked listing of candidate answers comprising the one or more first candidate answers and the one or more second candidate answers.

11. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a data processing system implementing a Question and Answer (QA) system, causes the data processing system to:

receive, by the QA system, from a first user via a source device, an original question for processing by the QA system to generate an answer result;

retrieve, by the QA system, a first user profile associated with the first user, wherein the first user profile specifies a personality trait of the first user;

generate, by the QA system, one or more first candidate answers to the original question based on a search of a corpus of electronic content;

identify, by the QA system, one or more second users having a similar personality trait to the personality trait of the first user;

identify, by the QA system, one or more similar questions, similar to that of the original question, previously submitted to the QA system by the one or more second users;

generate, by the QA system, one or more second candidate answers based on the one or more similar questions;

generate, by the QA system, a final answer based on the one or more first candidate answers and one or more second candidate answers; and

output, by the QA system, the answer to the user via the source device.

12. The computer program product of claim 11, wherein the one or more second users are second users logically connected to the first user by a common context.

13. The computer program product of claim 12, wherein the corpus of electronic content comprises a portion of electronic content associated with the common context.

14. The computer program product of claim 13, wherein the first user profile comprises an identifier of a context associated with the first user, and wherein the computer readable program further causes the data processing system to select the common context and the portion of electronic content associated with the common context based on the context identified in the first user profile.

15. The computer program product of claim 14, wherein the first user profile comprises a plurality of identifiers of contexts associated with the first user, and wherein the common context is selected based on a correlation of features of the original question with an identified context in the first user profile.

16. The computer program product of claim 12, wherein the common context comprises an online community with which the first user and the one or more second users are associated.

17. The computer program product of claim 12, wherein the common context comprises at least one of electronic objects accessed by the first user and the one or more second users within a historical time frame, electronic communications exchanged between the first user and the one or more second users, or electronic communications exchanged between a plurality of the one or more second users.

18. The computer program product of claim 11, wherein the computer readable program further causes the data processing system to generate one or more second candidate answers based on the one or more similar questions at least by:

identifying one or more portions of the one or more similar questions that align with the personality trait of the first user; and

generating one or more supplemental queries based on the identified portions of the one or more similar questions.

19. The computer program product of claim 18, wherein the computer readable program further causes the data processing system to generate one or more second candidate answers based on the one or more similar questions at least by performing an interactive exchange between the QA system and a client computing device of the first user that outputs a listing of the one or more portions to the first user and receives a selection from the first user of at least one portion in the one or more portion for use in generating supplemental queries, wherein the one or more supplemental queries are generated based on the selected at least one portion.

20. An apparatus comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement a Question and Answer (QA) system and perform the following operations;

receive, by the QA system, from a first user via a source device, an original question for processing by the QA system to generate an answer result;

retrieve, by the QA system, a first user profile associated with the first user, wherein the first user profile specifies a personality trait of the first user;

generate, by the QA system, one or more first candidate answers to the original question based on a search of a corpus of electronic content;

identify, by the QA system, one or more second users having a similar personality trait to the personality trait of the first user;

identify, by the QA system, one or more similar questions, similar to that of the original question, previously submitted to the QA system by the one or more second users;

generate, by the QA system, one or more second candidate answers based on the one or more similar questions;

generate, by the QA system, a final answer based on the one or more first candidate answers and one or more second candidate answers; and

output, by the QA system, the answer to the user via the source device.