Method and apparatus for responding to an inquiry

• US 9,213,758 B2
• Filed: 03/19/2014
• Issued: 12/15/2015
• Est. Priority Date: 10/27/2005
• Status: Active Grant

• Current Assignee: Shopify Incorporated
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Feng, Junlan Jr., Gilbert, Mazin, Hakkani-Tur, Dilek, Tur, Gokhan
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US14/219,537
• Publication Number:
  US 20140205985A1
• Time in Patent Office: 636 Days
• Field of Search: 704/1, 704/9, 707706-780
• 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 for responding to an inquiry comprising:

generating question and answer pairs based on a comparison of a first web page to a second web page;

identifying meta-level features of the question and answer pairs, wherein meta-level features of a particular question and answer pair are based on meta-level features of a related question and answer pair;

receiving an inquiry from a user;

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

presenting the plurality of responses to the user.

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

linguistic pre-processing of a specific question and answer pair to generate a linguistic tag; and

associating the linguistic tag with the specific question and answer pair.

3. The method of claim 1 further comprising:

receiving an input identifying a selection of a particular response from among the plurality of responses; and

updating a measure of eligibility of the particular response to be a response to the inquiry in response to the selection of the particular response.

4. The method of claim 1 further comprising:

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

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

5. The method of claim 4 wherein the determining a plurality of responses to the inquiry is further based on the clarifying the inquiry from the user.

6. The method of claim 1 wherein the generating question and answer pairs further comprises comparison of a first layout associated with the first web page and a second layout associated with the second web page.

7. The method of claim 1 wherein meta-level features of a particular question and answer pair comprise a location of the particular question and answer pair on a web page that includes the particular question and answer pair, a resolution of a pronomial anaphora using preceding question and answer pairs, and relevant named entities.

8. An apparatus for responding to an inquiry, the apparatus comprising:

a processor; and

a memory to store computer program instructions, the computer program instructions when executed on the processor cause the processor to perform operations comprising;

generating question and answer pairs based on a comparison of a first web page to a second web page;

identifying meta-level features of the question and answer pairs, wherein meta-level features of a particular question and answer pair are based on meta-level features of a related question and answer pair;

receiving an inquiry from a user;

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

presenting the plurality of responses to the user.

9. The apparatus of claim 8, the analysis of meta-level features comprises:

linguistic pre-processing of a specific question and answer pair to generate a linguistic tag; and

associating the linguistic tag with the specific question and answer pair.

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

receiving an input identifying a selection of a particular response from among the plurality of responses; and

updating a measure of eligibility of the particular response to be a response to the inquiry in response to the selection of the particular response.

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

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

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

12. The apparatus of claim 11 wherein the determining a plurality of responses to the inquiry is further based on the clarifying the inquiry from the user.

13. The apparatus of claim 8 wherein the generating question and answer pairs further comprises comparison of a first layout associated with the first web page and a second layout associated with the second web page.

14. The apparatus of claim 8 wherein meta-level features of a particular question and answer pair comprise a location of the particular question and answer pair on a web page that includes the particular question and answer pair, a resolution of a pronomial anaphora using preceding question and answer pairs, and relevant named entities.

15. A computer readable storage device storing computer program instructions for responding to an inquiry, which, when executed on a processor, cause the processor to perform operations comprising:

generating question and answer pairs based on a comparison of a first web page to a second web page;

identifying meta-level features of the question and answer pairs, wherein meta-level features of a particular question and answer pair are based on meta-level features of a related question and answer pair;

receiving an inquiry from a user;

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

presenting the plurality of responses to the user.

16. The computer readable storage device of claim 15, the analysis of meta-level features comprising:

linguistic pre-processing of a specific question and answer pair to generate a linguistic tag; and

associating the linguistic tag with the specific question and answer pair.

17. The computer readable storage device of claim 15, the operations further comprising:

receiving an input identifying a selection of a particular response from among the plurality of responses; and

updating a measure of eligibility of the particular response to be a response to the inquiry in response to the selection of the particular response.

18. The computer readable storage device of claim 15, the operations further comprising:

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

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

19. The computer readable storage device of claim 18 wherein the determining a plurality of responses to the inquiry is further based on the clarifying the inquiry from the user.

20. The computer readable storage device of claim 15 wherein the generating question and answer pairs further comprises comparison of a first layout associated with the first web page and a second layout associated with the second web page.