CONTEXT-AWARE QUESTION ANSWERING SYSTEM

• US 20130262501A1
• Filed: 03/30/2012
• Published: 10/03/2013
• Est. Priority Date: 03/30/2012
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: Marie-Aude Aufaure, Nicolas Kuchmann-Beauger
• Inventors: THOLLOT, RAPHAEL, KUCHMANN-BEAUGER, NICOLAS, AUFAURE, MARIE-AUDE
• Granted Patent: US 8,935,277 B2
• Time in Patent Office: Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/24535 of sub-queries or views
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence

Abstract

A question is received to be answered by a question answering (QA) system. The question may be a business intelligence question that is expressed in a natural language. The question is parsed. The parsed question is matched to a pattern from a number of patterns. A technical query associated with the matched pattern is processed to retrieve data relevant to the question from a number of data sources. The QA system generates an answer to the question based on retrieved data. In one aspect, the QA system generates answers based contextual information.

Claims

1. A computer implemented method to generate an answer to a request for information, the method comprising:

receiving the request for information expressed in natural language;

parsing the request;

based on the parsed request, generating a graph representing syntactic structure of the received request for information;

enriching the graph based on the parsed request for information with at least one semantic annotation of at least one business entity identified in the request for information, where the business entity is defined in a semantic layer of a plurality of data sources;

matching the parsed request for information to a pattern from a plurality of patterns of features included in the request;

processing by the computer a technical query associated with the pattern from the plurality of patterns to retrieve data relevant to the request for information from the plurality of data sources; and

generating the answer to the request for information based on the retrieved data.

3. The method of claim 1, wherein generating the answer further comprises:

creating a visualization of the answer based on the retrieved data.

4. The method of claim 1, further comprising:

generating an answer to a follow-up request for information, wherein the follow-up request for information refers to the request for information.

5. The method of claim 1, further comprising:

triggering at least one operator of a situational recommender system to generate the answer, and

recommending the generated answer.

6. The method of claim 1, further comprising:

ranking one or more generated answers, and

adding the ranked one or more answers to a situation of a user, wherein the one or more answers correspond to the request for information and the request for information is posed by the user.

7. The method of claim 1, wherein recommending the answer further comprises:

generating the answer based on a situation of a user to resolve ambiguities in the request for information, where the request for information is posed by the user.

2. (canceled)

8. A question-answering computer system to generate an answer to a request for information, the system including:

at least one processor and memory to execute program code related to;

receive the request for information expressed in natural language;

parse the request;

based on the parsed request, generate a graph representing syntactic structure of the received request for information;

enrich the graph based on the parsed request for information with at least one semantic annotation of at least one business entity identified in the request for information, where the business entity is defined in a semantic layer of a plurality of data sources;

match the parsed request for information to a pattern from a plurality of patterns of features included in the request;

process by the computer a technical query associated with the pattern from the plurality of patterns to retrieve data relevant to the request for information from the plurality of data sources; and

generate the answer to the request for information based on the retrieved data.

10. The system of claim 8, wherein generating the answer further comprises:

rendering a visualization of the answer based on the retrieved data.

11. The system of claim 8, further comprising:

generating an answer to a follow-up request for information, wherein the follow-up request for information refers to the request for information.

12. The system of claim 8, further comprising:

triggering at least one operator of a situational recommender system to generate the answer, and

recommending the generated answer.

13. The system of claim 8, further comprising:

ranking one or more generated answers, and

adding the ranked one or more answers to a situation of a user, wherein the one or more answers correspond to the request for information and the request for information is posed by the user.

14. The method of claim 8, wherein recommending the answer further comprises:

generating the answer based on a situation of a user to resolve ambiguities in the request for information, where the request for information is posed by the user.

9. (canceled)

15. A non-transitory computer readable medium storing instructions thereon, which when executed by a processor cause a computer system to:

receive the request for information expressed in natural language;

parse the request;

based on the parsed request, generate a graph representing syntactic structure of the received request for information;

enrich the graph based on the parsed request for information with at least one semantic annotation of at least one business entity identified in the request for information, where the business entity is defined in a semantic layer of a plurality of data sources;

match the parsed request for information to a pattern from a plurality of patterns of features included in the request;

process by the computer a technical query associated with the pattern from the plurality of patterns to retrieve data relevant to the request for information from the plurality of data sources; and

generate the answer to the request for information based on the retrieved data.

17. The non-transitory computer readable medium of claim 15, further comprising:

generating an answer to a follow-up request for information, wherein the follow-up request for information refers to the request for information.

18. The non-transitory computer readable medium of claim 15, further comprising:

triggering at least one operator of a situational recommender system to generate the answer, and

recommending the generated answer.

19. The non-transitory computer readable medium of claim 15, further comprising:

ranking one or more generated answers, and

adding the ranked one or more answers to a situation of a user, wherein the one or more answers correspond to the request for information and the request for information is posed by the user.

20. The non-transitory computer readable medium of claim 15, wherein recommending the answer further comprises:

generating the answer based on situation of a user to resolve ambiguities in the request for information, where the request for information is posed by the user.

16. (canceled)