Information recommendation method and device based on collaborative sampling of knowledge graph and adjacency graph

By constructing collaborative knowledge graphs and adjacency graph collaborative sampling technology, difficult negative samples are generated and multi-head graph attention network training is used to solve the problems of user-project interaction sparseness and high-order semantic information not captured, and the accuracy of the recommendation system and user preference perception ability are improved.

CN120561384AActive Publication Date: 2025-08-29HUAQIAO UNIVERSITY
5 Cites 4 Cited by

Patent Information

Application Number
CN202511062405.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-31
Publication Date
2025-08-29
Estimated Expiration
2045-07-31

AI Technical Summary

Technical Problem

There are problems in the existing recommendation system with user-project interaction sparseness, insufficient semantic information of knowledge graphs being sufficiently captured, and false negative case interference and insufficient sample distinction in traditional negative sampling methods, which affect the modeling effect of user implicit preferences and complex item associations.

Method used

By building a collaborative knowledge graph, combining adjacency graph collaborative sampling technology, difficult negative samples are generated and trained using multi-head graph attention networks, high-order information is captured, embedded representation is optimized, and the triple loss mechanism is used to improve the robustness and generalization capabilities of the model.

Benefits of technology

It significantly improves the model's ability to distinguish fine-grained semantics, enhances the semantic understanding and generalization recommendation efficiency of the recommendation system, and improves recommendation accuracy and user's implicit preference perception ability.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides an information recommendation method and device based on collaborative sampling of a knowledge graph and an adjacent graph, and relates to the technical field of information recommendation. According to the method, the triple is constructed by obtaining the historical interaction data of the user, and the triple is fused with the project attribute graph to construct the collaborative knowledge graph; performing expression alignment through projection transformation to obtain initial embedding expression; performing multi-hop neighbor sampling through biased random walk to obtain a multi-hop neighbor set; determining a neighbor which is most similar to the embedding representation of the positive sample item as an anchor neighbor; then linear interpolation is carried out, and the embedding representation of the difficult negative sample is synthesized; on the basis of the multi-head graph attention network, training by adopting a positive sample and a synthesized difficult negative sample, and aggregating to obtain an updated embedded representation; and calculating an interaction probability based on the updated embedded representation, and generating a recommended item for the user. According to the method, the problems of user-project interaction sparsity and false negative example interference are effectively solved, and stronger semantic comprehension and generalization ability are provided for a recommendation system.
Need to check novelty before this filing date? Find Prior Art