Method and apparatus for providing aggregate result of question-and-answer information

Patent metadata

Field	Value
Publication number	US-2019251087-A1
Application number	US-201816215423-A
Country	US
Kind code	A1
Filing date	Dec 10, 2018
Priority date	Nov 28, 2017
Publication date	Aug 15, 2019
Grant date	—

Abstract

A method and apparatus for providing an aggregate result of question-and-answer information are provided. An embodiment of the method includes: acquiring a search expression inputted by a user, and determining an entity corresponding to the search expression; and pushing aggregate information corresponding to the entity to the user. The aggregate information includes: a question-answer pair corresponding to each tag of the entity. When the user searches for information on a given aspect of the entity, the aggregate information containing question-answer pairs on a plurality of aspects of the entity is pushed to the user. Thus, the user may acquire information on the plurality of aspects of the entity.

First claim

What is claimed is:

1 . A method for providing an aggregate result of question-and-answer information, comprising:
acquiring a search expression inputted by a user, and determining an entity corresponding to the search expression; and pushing aggregate information corresponding to the entity to the user, the aggregate information including: a question-answer pair corresponding to each tag of the entity.

2 . The method according to claim 1 , wherein before the determining an entity corresponding to the search expression, the method further comprises:
acquiring a plurality of question-answer pairs corresponding to a tag of a given entity from a plurality of websites, and clustering, according to semantic similarity between answers in the plurality of question-answer pairs corresponding to the tag of the given entity, the answers in the plurality of question-answer pairs corresponding to the tag of the given entity to obtain an answer clustering result; selecting an optimum answer from the answer clustering result; and using the question-answer pair to which the selected optimum answer belongs as the question-answer pair corresponding to the tag of the given entity.

3 . The method according to claim 2 , wherein the selecting an optimum answer from the answer clustering result comprises:
selecting the optimum answer from the answer clustering result based on an attribute of an answer in the answer clustering result, wherein the attribute includes: a confidence coefficient of a website to which the answer belongs, a confidence coefficient of an answering user to which the answer belongs, and comments on the answer.

4 . The method according to claim 3 , further comprising:
generating a search result page, wherein the search result page includes initial presentation contents corresponding to the aggregate information, and the initial presentation contents include a tag item respectively representing the each tag of the entity, wherein the tag item is bound with the question-answer pair corresponding to the tag represented by the tag item in the aggregate information, and the question-answer pair corresponding to the tag represented by the tag item is presented to the user when a preset operation is performed on the tag item; and pushing the search result page to the user.

5 . The method according to claim 4 , wherein the aggregate information further includes: the website to which the question-answer pair corresponding to the each tag of the entity belongs, and user information of the answering user to which the answer in the question-answer pair corresponding to the each tag of the entity belongs.

6 . An apparatus for providing an aggregate result of question-and-answer information, comprising:
at least one processor; and a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising: acquiring a search expression inputted by a user, and determining an entity corresponding to the search expression; and pushing aggregate information corresponding to the entity to the user, the aggregate information including: a question-answer pair corresponding to each tag of the entity.

7 . The apparatus according to claim 6 , wherein before the determining an entity corresponding to the search expression, the operations further comprise:
acquiring a plurality of question-answer pairs corresponding to a tag of a given entity from a plurality of websites, and clustering, according to semantic similarity between answers in the plurality of question-answer pairs corresponding to the tag of the given entity, the answers in the plurality of question-answer pairs corresponding to the tag of the given entity to obtain an answer clustering result; selecting an optimum answer from the answer clustering result; and using the question-answer pair to which the selected optimum answer belongs as the question-answer pair corresponding to the tag of the given entity.

8 . The apparatus according to claim 7 , wherein the selecting an optimum answer from the answer clustering result comprises:
selecting the optimum answer from the answer clustering result based on an attribute of an answer in the answer clustering result, wherein the attribute includes: a confidence coefficient of a website to which the answer belongs, a confidence coefficient of an answering user to which the answer belongs, and comments on the answer.

9 . The apparatus according to claim 8 , further comprising:
generating a search result page, wherein the search result page includes initial presentation contents corresponding to the aggregate information, and the initial presentation contents include a tag item respectively representing the each tag of the entity, wherein the tag item is bound with the question-answer pair corresponding to the tag represented by the tag item in the aggregate information, and the question-answer pair corresponding to the tag represented by the tag item is presented to the user when a preset operation is performed on the tag item; and push the search result page to the user.

10 . The apparatus according to claim 9 , wherein the aggregate information further includes: the website to which the question-answer pair corresponding to the each tag of the entity belongs, and user information of the answering user to which the answer in the question-answer pair corresponding to the each tag of the entity belongs.

11 . A non-transitory computer-readable storage medium storing a computer program, the computer program when executed by one or more processors, causes the one or more processors to perform operations, the operations comprising:
acquiring a search expression inputted by a user, and determining an entity corresponding to the search expression; and pushing aggregate information corresponding to the entity to the user, the aggregate information including: a question-answer pair corresponding to each tag of the entity.

Assignees

• Beijing Baidu Netcom Sci & Tec

Inventors

• Lin Yiming
• Guo Hui
• Dai Xiangying
• Luo Yu
• Chen Liang

Classifications

• G06F16/3329

  Natural language query formulation · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/24578

  using ranking · CPC title

• G06F16/24522 Primary

  Translation of natural language queries to structured queries · CPC title

• G06F16/953

  Querying, e.g. by the use of web search engines · CPC title