The article recommends a method, device, computer equipment and storage medium

By constructing a structural relationship graph network between users and articles and using a gradient descent optimization strategy to calculate similarity, the problem of inaccurate recommendations in traditional article retrieval methods is solved, achieving more accurate article recommendations.

CN116842171BActive Publication Date: 2026-06-09INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
INDUSTRIAL AND COMMERCIAL BANK OF CHINA
Filing Date
2023-07-07
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

In existing technologies, traditional article retrieval methods struggle to accurately recommend articles that meet user needs, especially for inexperienced researchers, often returning a large number of similar articles, resulting in low recommendation accuracy.

Method used

By acquiring user personal information and article content information, a heterogeneous information network is constructed, a structural relationship graph network between users and articles is established, a gradient descent optimization strategy is used to determine proximity information, similarity is calculated based on the article recommendation graph network, and the articles with the highest similarity are selected.

Benefits of technology

It improves the accuracy and comprehensiveness of the correlation between users and articles, ensuring that recommended articles better meet user needs and avoiding inaccurate recommendations due to lack of experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116842171B_ABST
    Figure CN116842171B_ABST
Patent Text Reader

Abstract

The application relates to an article recommendation method and device, computer equipment and a storage medium. The application relates to the technical field of big data and artificial intelligence. The method comprises the following steps: obtaining personal information of a user and content information of a plurality of articles; extracting each interest point data of the content information of each article, identifying each feature point data of the personal information of the user, and establishing a structural relationship graph network of the user and each article based on each interest point data of each article and each feature point data of the user through a heterogeneous information network; determining the proximity information of the user and each article in the structural relationship graph network through a gradient descent optimization strategy, obtaining an article recommendation graph network of the user and each article, and calculating the similarity of each article and the user based on the article recommendation graph network, screening the article with the highest similarity as the recommended article of the user. The method can improve the accuracy of recommending articles meeting the user's demand to the user.
Need to check novelty before this filing date? Find Prior Art