Content recommendation method and system

By constructing the historical browsing item map and similarity calculation of user sessions, the problem of insufficient personalization of traditional content recommendation systems is solved, and more accurate content recommendation results are achieved.

CN119311945AActive Publication Date: 2025-01-14CCCC(XIAMEN)INFORMATION CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411429298.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-14
Publication Date
2025-01-14
Estimated Expiration
2044-10-14

AI Technical Summary

Technical Problem

The traditional content recommendation system is insufficiently personalized and has low recommendation accuracy, which cannot effectively meet users' personalized content recommendation needs.

Method used

By constructing a historical browsing item graph for each session of the user, compute the similarity between the current session and the historical session, and construct the access matrix based on the similarity and adjacency matrix, recommending the content that is most relevant to the current browsing item.

Benefits of technology

Improve the accuracy and personalization of content recommendations. Through session granular recommendations, combined with graph embedding and degree matrix, the accuracy of similarity calculations is enhanced, thereby providing more accurate content recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119311945A_ABST
    Figure CN119311945A_ABST
Patent Text Reader

Abstract

The invention relates to the field of content recommendation, in particular to a content recommendation method and system, and the method specifically comprises the steps: constructing a historical browsing item graph of each session of each user, obtaining a browsing record of a current session of a current user, and constructing a browsing item graph of the current session; wherein the feature vector of the node in the browsing item graph is generated based on the content of the browsing item, the residence time of the user on the browsing item and the operation aiming at the browsing item; calculating the similarity between the current session browsing item graph and the historical browsing item graph based on the degree matrix of the current session browsing item graph and the historical browsing item graph, selecting a preset number of historical browsing item graphs with the maximum similarity, and constructing an access matrix according to the similarity and the adjacent matrix of the selected historical browsing item graph; and when the user clicks a new browsing item, determining a browsing item to be recommended from the access matrix based on the browsing item which is currently browsed and the new browsing item. According to the invention, the recommendation accuracy is effectively improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Personalized session recommendation method and system

    CN113569139A

  • Session recommendation method and device based on user personalized modeling and medium

    CN114862496A

  • Personalized recommendation system and method based on knowledge graph and collaborative filtering

    CN118227884A