Method and apparatus for responding to an inquiry

• US 10,115,056 B2
• Filed: 10/06/2016
• Issued: 10/30/2018
• 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:
  US15/287,387
• Publication Number:
  US 20170024648A1
• Time in Patent Office: 754 Days
• Field of Search: 704 1, 704 9, 704 10
• 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 similar to one another even for very different subjects, and without additional contextual and meta-level information, are not useful in determining whether their corresponding answer responds to an inquiry.

Claims

1. A method comprising:

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

receiving, by the web server, an inquiry from an end user device; and

determining, by the web server, a response to the inquiry based on the plurality of question and answer pairs and based on analysis of meta-level features of the plurality of question and answer pairs.

2. The method of claim 1, the generating meta-level features further comprising:

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

3. The method of claim 2, wherein the meta-level features comprise one of a location of the question and answer pair, relation of the question and answer pair to another question and answer pair of the plurality of question and answer pairs, and a relevant named entity.

4. The method of claim 1, wherein the determining the response to the inquiry is further based on a rating associated with each respective question and answer pair.

5. The method of claim 1, further comprising:

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

clarifying, by the web server, 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, further comprising:

generating question and answer pairs based on the data, the generating question and answer pairs comprising identifying question and answer pairs using a frequently asked questions template.

8. An apparatus comprising:

a processor; and

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

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

receiving an inquiry from an end user device; and

determining a response to the inquiry based on the plurality of question and answer pairs and based on analysis of meta-level features of the plurality of question and answer pairs.

9. The apparatus of claim 8, the generating meta-level features further comprising:

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

10. The apparatus of claim 9, wherein the meta-level features comprise one of a location of the question and answer pair, relation of the question and answer pair to another question and answer pair of the plurality of question and answer pairs, and a relevant named entity.

11. The apparatus of claim 8, wherein the determining the response to the inquiry is further based on a rating associated with each respective question and answer pair.

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

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

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

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

14. The apparatus of claim 8, the operations further comprising:

generating question and answer pairs based on the data, the generating question and answer pairs comprising 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:

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

receiving an inquiry from an end user device; and

determining a response to the inquiry based on the plurality of question and answer pairs and based on analysis of meta-level features of the plurality of question and answer pairs.

16. The non-transitory machine-readable storage medium of claim 15, the generating meta-level features further comprising:

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

17. The non-transitory machine-readable storage medium of claim 16, wherein the meta-level features comprise one of a location of the question and answer pair, relation of the question and answer pair to another question and answer pair of the plurality of question and answer pairs, and a relevant named entity.

18. The non-transitory machine-readable storage medium of claim 15, wherein the determining the response to the inquiry is further based on a rating associated with each respective question and answer pair.

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 inquiry; and

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