Method and apparatus for responding to an inquiry

• US 9,489,450 B2
• Filed: 11/10/2015
• Issued: 11/08/2016
• Est. Priority Date: 10/27/2005
• Status: Active Grant

• Current Assignee: Shopify Incorporated
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Feng, Junlan, Gilbert, Mazin, Hakkani-Tur, Dilek, Tur, Gokhan
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US14/937,115
• Publication Number:
  US 20160062959A1
• Time in Patent Office: 364 Days
• Field of Search: 704/1, 704/9, 707/3, 707/5
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3331 Query processing
• CPC Class Codes: G06F 16/338 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/194 Calculation of difference between files
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G09B 5/00 Electrically-operated educational appliances working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F

Abstract

Disclosed is a method and apparatus for responding to an inquiry from a client via a network. The method and apparatus receive the inquiry from a client via a network. Based on the inquiry, question-answer pairs retrieved from the network are analyzed to determine a response to the inquiry. The QA pairs are not predefined. As a result, the QA pairs have to be analyzed in order to determine whether they are responsive to a particular inquiry. Questions of the QA pairs may be repetitive and, without more, will not be useful in determining whether their corresponding answer responds to an inquiry.

Claims

1. A method comprising:

retrieving, by a web server, data from a web page;

generating, by the web server, question and answer pairs based on the data;

generating, by the web server, meta-level features for a question and answer pair based on the data and based on other meta-level features of other question and answer pairs; and

determining, by the web server, a response to an inquiry from an end user device based on analysis of the meta-level features and based on the question and answer pairs.

2. The method of claim 1, wherein the data from the web page identifies subject matter of the web page.

3. The method of claim 2, wherein the determining the response to the inquiry from the end user device is further based on a rating associated with each respective question and answer pair.

4. The method of claim 1, the generating question and answer pairs further comprising:

resolving, by the web server, a pronominal anaphora of a specific question and answer pair using question and answer pairs preceding the specific question and answer pair listed on the web page.

5. The method of claim 1, further comprising:

generating, by the web server, a follow-up question based on the inquiry from the end user device; and

clarifying, by the web server, the inquiry from the end user device based on a response to the follow-up question.

6. The method of claim 5, wherein the determining the response to the inquiry from the end user device is further based on the response to the follow-up question.

7. The method of claim 1, wherein the generating question and answer pairs based on the data comprises identifying question and answer pairs using a frequently asked questions template.

8. A web server comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising;

retrieving data from a web page;

generating a plurality of question and answer pairs based on the data;

generating meta-level features for a question and answer pair of the plurality of question and answer pairs based on the data and based on other meta-level features of other question and answer pairs of the plurality of question and answer pairs; and

determining a response to a question from an end user device based on analysis of the meta-level features and based on the plurality of question and answer pairs.

9. The web server of claim 8, wherein the data from the web page identifies subject matter of the web page.

10. The web server of claim 9, wherein the determining the response to the question from the end user device is further based on a rating associated with each respective question and answer pair.

11. The web server of claim 8, the generating the plurality of question and answer pairs further comprising:

resolving a pronominal anaphora of a specific question and answer pair using question and answer pairs preceding the specific question and answer pair listed on the web page.

12. The web server of claim 8, the operations further comprising:

generating a follow-up question based on the question from the end user device; and

clarifying the question from the end user device based on a response to the follow-up question.

13. The web server of claim 12, wherein the determining the response to the question from the end user device is further based on the response to the follow-up question.

14. The web server of claim 8, wherein the generating the plurality of question and answer pairs based on the data comprises identifying question and answer pairs using a frequently asked questions template.

15. A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

retrieving data from a web page retrieved over a network;

generating question and answer pairs based on the data;

generating meta-level features for a question and answer pair based on the data and based on other meta-level features of other question and answer pairs; and

determining a response to a question from an end user device based on analysis of the meta-level features and based on the question and answer pairs.

16. The non-transitory machine-readable storage medium of claim 15, wherein the data from the web page identifies subject matter of the web page.

17. The non-transitory machine-readable storage medium of claim 16, wherein the determining the response to the question from the end user device is further based on a rating associated with each respective question and answer pair.

18. The non-transitory machine-readable storage medium of claim 15, the generating question and answer pairs further comprising:

resolving, by the web server, a pronominal anaphora of a specific question and answer pair using question and answer pairs preceding the specific question and answer pair listed on the web page.

19. The non-transitory machine-readable storage medium of claim 15, the operations further comprising:

generating, by the web server, a follow-up question based on the question from the end user device; and

clarifying, by the web server, the question from the end user device based on a response to the follow-up question.

20. The non-transitory machine-readable storage medium of claim 19, wherein the determining the response to the question from the end user device is further based on the response to the follow-up question.