Group recommendation method and device, electronic equipment and storage medium
By generating a relationship structure chart in the social network and performing node feature extraction and correlation prediction, the problem of inaccurate group recommendation is solved, and more accurate group recommendation is achieved.
CN120256742APending Publication Date: 2025-07-04TENCENT TECHNOLOGY (SHENZHEN) CO LTD
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202410006904.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-03
- Publication Date
- 2025-07-04
AI Technical Summary
Technical Problem
The existing group recommendation methods are inaccurate in social networks and cannot effectively improve the accuracy of group recommendations.
Method used
By obtaining the association relationship between multiple feature nodes in the content platform, generating a relationship structure chart, extracting node features, determining the candidate groups of the target object, and predicting the correlation degree based on the characteristics of the object and the group, thereby determining the target recommended group.
Benefits of technology
Improve the accuracy of group recommendations, and enhance the accuracy of candidate group determination by fusing the object and group characteristics generated by global data.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention relates to the technical field of machine learning, in particular to a group recommendation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a relation structure diagram; performing node feature extraction on the plurality of element nodes based on the association relationship among the plurality of element nodes to obtain an object feature corresponding to the object node and a group feature corresponding to the group node; determining a candidate group corresponding to the target object based on the object feature corresponding to the object node and the group feature corresponding to the group node; performing association degree prediction based on the object attribute information of the target object and the group attribute information of the candidate group to obtain a predicted association degree of the target object and the candidate group; and determining a target recommendation group from the candidate groups based on the predicted association degree of the target object and the candidate groups. The accuracy of group recommendation can be improved.
Need to check novelty before this filing date? Find Prior Art