Method and apparatus for processing consultation information

Patent metadata

Field	Value
Publication number	US-11663248-B2
Application number	US-202117302385-A
Country	US
Kind code	B2
Filing date	Apr 30, 2021
Priority date	Mar 26, 2020
Publication date	May 30, 2023
Grant date	May 30, 2023

Abstract

Embodiments of the present disclosure provide a method and apparatus for processing consultation information. A specific implementation of the method includes: pushing, in response to receiving consultation information of a first user, a questionnaire corresponding to the consultation information to the first user; acquiring a questionnaire result corresponding to the questionnaire and submitted by the first user; inputting the questionnaire result into a preset consultation model, to obtain a first consultation result; pushing the questionnaire result and the first consultation result to a second user; and in response to receiving a second consultation result provided by the second user based on the questionnaire result and the first consultation result, pushing the second consultation result to the first user.

First claim

What is claimed is:

1. A method for processing consultation information, comprising:
pushing, in response to receiving consultation information of a first user, a questionnaire corresponding to the consultation information to the first user, wherein the consultation information includes a consultation content type and a target consultation question;
acquiring a questionnaire result corresponding to the questionnaire and submitted by the first user;
inputting the questionnaire result into a preset consultation model, to obtain a first consultation result;
pushing the questionnaire result and the first consultation result to a second user; and
in response to receiving a second consultation result provided by the second user based on the questionnaire result and the first consultation result, pushing the second consultation result to the first user,
wherein the method further comprises:
searching in a preset consultation database for a preset consultation question matching the target consultation question, wherein the preset consultation database includes preset consultation questions and preset consultation results corresponding to the preset consultation questions, and the preset consultation question matching the target consultation question refers to that a matching degree between the preset consultation question and the target consultation question is greater than a first preset threshold;
in response to determining that a first preset consultation question matching the target consultation question is found in the preset consultation database, pushing a preset consultation result corresponding to the first preset consultation question to the first user;
in response to determining that the preset consultation question matching the target consultation question is not found in the preset consultation database, searching in the preset consultation database for candidate preset consultation questions having association degrees with the target consultation question greater than a second preset threshold value, and pushing the candidate preset consultation questions to the first user; and
acquiring a second preset consultation question selected by the first user from the candidate preset consultation questions, and pushing a preset consultation result corresponding to the second preset consultation question to the first user, and wherein the method further comprises:
pushing common consultation questions having frequencies of being consulted greater than a preset threshold value and consultation results corresponding to the common consultation questions to the first user;
in response to detecting that the first user performs a preset association confirmation operation on a consultation result of a third consultation question, inputting the third consultation question, the consultation result corresponding to the third consultation question, and the questionnaire result into the preset consultation model to obtain a third consultation result; and
pushing the obtained third consultation result to the second user.

2. The method according to claim 1 , wherein the pushing, in response to receiving the consultation information of the first user, the questionnaire corresponding to the consultation information to the first user comprises:
in response to receiving the consultation information of the first user, searching in a pre-stored questionnaire set for a target questionnaire corresponding to the type of the consultation content; and
pushing the target questionnaire to the first user.

3. The method according to claim 1 , wherein the questionnaire includes a structured questionnaire, the structured questionnaire being used for collecting basic information of a user related to consultation information of the user.

4. The method according to claim 1 , wherein searching in the preset consultation database for the preset consultation question matching the target consultation question, wherein the preset consultation question matching the target consultation question refers to that the matching degree between the preset consultation question and the target consultation question is greater than the first preset threshold, comprises:
calculating a similarity between the target consultation question and each preset consultation question in the consultation database to obtain a similarity value, and using the similarity as the matching degree.

5. The method according to claim 1 , wherein searching in the preset consultation database for the candidate preset consultation questions having association degrees with the target consultation question greater than the second preset threshold value comprise:
recognizing a keyword included in the target consultation question;
searching in the preset consultation database for a preset consultation question containing the same keyword; and
using the preset consultation question containing the same keyword as a candidate preset consultation question having an association degree with the target consultation question greater than the second preset threshold value.

6. An electronic device, comprising:
one or more processors; and
a storage apparatus, configured to store one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement operations of the method according to claim 1 .

7. The device according to claim 6 , wherein the pushing, in response to receiving the consultation information of the first user, the questionnaire corresponding to the consultation information to the first user comprises:
in response to receiving the consultation information of the first user, searching in a pre-stored questionnaire set for a target questionnaire corresponding to the type of the consultation content; and
pushing the target questionnaire to the first user.

8. The device according to claim 6 , wherein the questionnaire includes a structured questionnaire, the structured questionnaire being used for collecting basic information of a user related to consultation information of the user.

9. The device according to claim 6 , wherein searching in the preset consultation database for the preset consultation question matching the target consultation question, wherein the preset consultation question matching the target consultation question refers to that the matching degree between the preset consultation question and the target consultation question is greater than the first preset threshold, comprises:
calculating a similarity between the target consultation question and each preset consultation question in the consultation database to obtain a similarity value, and using the similarity as the matching degree.

10. The device according to claim 6 , wherein searching in the preset consultation database for the candidate preset consultation questions having association degrees with the target consultation question greater than the second preset threshold value comprise:
recognizing a keyword included in the target consultation question;
searching in the preset consultation database for a preset consultation question containing the same keyword; and
using the preset consultation question containing the same keyword as a candidate preset consultation question having an association degree with the target consultation question greater than the second preset threshold value.

11. A non-transitory computer readable medium, storing a computer program, wherein the program, when executed by a processor, causes the processor to perform the method according to claim 1 .

12. A method for processing consultation information, performed by a first server, comprising:
sending con

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Zhu Dongwei
• Huang Haifeng
• Lu Chao
• Wu Jialin
• Xia Yuan
• Shi Xueying
• Li Xiaoqin
• Hu Xiaoming

Classifications

• G06F16/3329

  Natural language query formulation · CPC title

• G06F16/3326 Primary

  using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/34

  Browsing; Visualisation therefor (browsing or visualisation for clustering or classification G06F16/358) · CPC title

• G06F16/338

  Presentation of query results · CPC title