Method for pushing information, electronic device

Patent metadata

Field	Value
Publication number	US-11809505-B2
Application number	US-202217824595-A
Country	US
Kind code	B2
Filing date	May 25, 2022
Priority date	May 28, 2021
Publication date	Nov 7, 2023
Grant date	Nov 7, 2023

Abstract

A method for pushing information, and an electronic device are disclosed. The method includes: obtaining a plurality of initial pages containing document content; predicting, based on the document content in the plurality of initial pages, an effective rate for pushing information using each initial page; selecting, based on the effective rate, at least one candidate page from the plurality of initial pages and extracting a first keyword from the document content of the at least one candidate page; and determining a target page for mounting information to be pushed from the at least one candidate page, based on a matching degree between a second keyword of the information to be pushed and the first keyword.

First claim

What is claimed is:

1. A method for pushing information, comprising:
obtaining a plurality of initial pages containing document content;
predicting, based on the document content in the plurality of initial pages, an effective rate for pushing information using each initial page;
selecting, based on the effective rate, at least one candidate page from the plurality of initial pages and extracting a first keyword from the document content of each candidate page; and
determining a target page for mounting information to be pushed from the at least one candidate page, based on a matching degree between a second keyword of the information to be pushed and the first keyword.

2. The method according to claim 1 , wherein predicting, based on the document content in the plurality of initial pages, the effective rate for pushing information using each initial page comprises:
extracting feature information of the document content of each initial page; and
for each initial page, obtaining the effective rate output by a trained recognition model by inputting the feature information into the trained recognition model, wherein a correspondence between the feature information and the effective rate is learned by the trained recognition model.

3. The method according to claim 2 , wherein the trained recognition model is obtained by:
obtaining a sample page and monitoring a visit to the sample page;
determining an actual visit effective rate based on a visit record obtained by the monitoring;
obtaining a labeled sample page by labeling the sample page based on the actual visit effective rate; and
training an initial recognition model based on the labeled sample page, until a difference between the effective rate as output by the trained recognition model and the actual visit effective rate is minimalized.

4. The method according to claim 1 , wherein selecting the at least one candidate page from the plurality of initial pages based on the effective rate, comprises:
determining the initial page whose effective rate is greater than a first threshold as one candidate page.

5. The method according to claim 4 , after determining the target page for mounting the information to be pushed from the at least one candidate page, further comprising:
monitoring a visit to the target page for mounting the information to be pushed; and
increasing the first threshold in response to determining, based on a visit record obtained by the monitoring, that at least one indicator satisfies a predetermined condition.

6. The method according to claim 1 , wherein determining the target page for mounting the information to be pushed from the at least one candidate page based on the matching degree between the second keyword of the information to be pushed and the first keyword, comprises:
determining the candidate page whose matching degree is greater than a second threshold as the target page.

7. The method according to claim 6 , after determining the target page for mounting the information to be pushed from the at least one candidate page, further comprising:
monitoring a visit to the target page for mounting the information to be pushed; and
increasing the second threshold in response to determining, based on a visit record obtained by the monitoring, that at least one indicator satisfies a predetermined condition.

8. The method according to claim 2 , wherein extracting the first keyword from the document content of each candidate page, comprises:
obtaining the first keyword corresponding to each candidate page by performing keyword extraction on the document content of each candidate page using the trained recognition model.

9. The method according to claim 1 , before determining the target page for mounting the information to be pushed from the at least one candidate page based on the matching degree between the second keyword of the information to be pushed and the first keyword, further comprising:
obtaining a keyword tag of the information to be pushed, wherein the keyword tag is configured in response to a user action; and
determining the second keyword of the information to be pushed based on the keyword tag.

10. The method according to claim 1 , before determining the target page for mounting the information to be pushed from the at least one candidate page based on the matching degree between the second keyword of the information to be pushed and the first keyword, further comprising:
querying a correspondence between push information and keywords based on the information to be pushed, to determine target push information that matches the information to be pushed; and
determining a keyword corresponding to the target push information as the second keyword of the information to be pushed.

11. A method for pushing information, comprising:
sending a search request comprising a search keyword to a server;
receiving request response information, wherein the request response information comprises a search result corresponding to the search keyword, the search result comprises a link to a target page, and the target page is obtained according to the method of claim 1 ;
displaying the search result; and
obtaining and displaying the target page in response to a triggering operation on the link to the target page in the search result.

12. An electronic device, comprising:
at least one processor; and
a memory communicatively connected with the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is caused to execute the method for pushing information comprising:
obtaining a plurality of initial pages containing document content;
predicting, based on the document content in the plurality of initial pages, an effective rate for pushing information using each initial page;
selecting, based on the effective rate, at least one candidate page from the plurality of initial pages and extracting a first keyword from the document content of each candidate page; and
determining a target page for mounting information to be pushed from the at least one candidate page, based on a matching degree between a second keyword of the information to be pushed and the first keyword.

13. The device according to claim 12 , wherein predicting, based on the document content in the plurality of initial pages, the effective rate for pushing information using each initial page comprises:
extracting feature information of the document content of each initial page; and
for each initial page, obtaining the effective rate output by a trained recognition model by inputting the feature information into the trained recognition model, wherein a correspondence between the feature information and the effective rate is learned by the trained recognition model.

14. The device according to claim 13 , wherein the trained recognition model is obtained by:
obtaining a sample page and monitoring a visit to the sample page;
determining an actual visit effective rate based on a visit record obtained by the monitoring;
obtaining a labeled sample page by labeling the sample page based on the actual visit effective rate; and
training an initial recognition model based on the labeled sample page, until a difference between the effective rate as output by the trained recognition model and the actual visit effective rate is minimalized.

15. The device according to claim 12 , wherein selecting the at least one candidate page from the plurality of initial pages based on the effective rate, comprises:
determini

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Liu Xihuan
• Shao Shichen
• Li Yongheng
• Li Mengze
• Chen Shan

Classifications

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/958

  Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking · CPC title

• G06F16/9538

  Presentation of query results · CPC title

• G06F16/9558

  Details of hyperlinks; Management of linked annotations · CPC title

• G06F16/335

  Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536) · CPC title