Cross-domain privacy protection method, system and device for advertisement recommendation and medium

By encrypting and storing user behavior data on local devices and generating cross-domain joint feature vectors using privacy intersection and differential privacy techniques, the advertising recommendation model is split and deployed to edge nodes and local devices. This solves the problems of privacy leakage, security risks, and network burden in advertising recommendation systems, and improves the accuracy of recommendations and user experience.

CN120874122APending Publication Date: 2025-10-31ANHUI SANQI JIYU NETWORK TECH CO LTD
0 Cites 5 Cited by

Patent Information

Application Number
CN202511072200.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-01
Publication Date
2025-10-31

AI Technical Summary

Technical Problem

Existing advertising recommendation systems rely on third-party cookies, leading to privacy leaks, security risks, network burden, and user experience issues, which affect user trust and recommendation effectiveness.

Method used

By encrypting and storing user behavior data on local devices, privacy intersection and differential privacy techniques are used to generate cross-domain joint feature vectors. The advertising recommendation model is split and deployed to edge nodes and local devices for encrypted computation and federated learning, ensuring that the data does not leave the domain while generating effective feature vectors.

Benefits of technology

It enables cross-domain data utilization and user privacy protection, improves the accuracy and real-time performance of advertising recommendations, enhances user trust and security, and reduces network burden and the impact of frequent data exchange.

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

Abstract

The invention discloses a cross-domain privacy protection method and system for advertisement recommendation, equipment and a medium, and the method specifically comprises the steps: carrying out the encryption matching of user behavior data and anonymized equipment data, and generating an initial cross-domain joint feature vector; fusing the initial cross-domain joint feature vector and the disturbance feature vector to form a target cross-domain joint feature vector; splitting a pre-trained advertisement recommendation model into a feature coding sub-module and a reasoning sub-module, deploying the feature coding sub-module to a user adjacent edge node, and retaining the reasoning sub-module in a user local device; and based on the target cross-domain joint feature vector, performing calculation of the feature coding sub-module and calculation of the reasoning sub-module, and uploading the encrypted hidden layer feature vector to a federated learning aggregation server for global model updating. According to the method, cross-domain data utilization and user privacy protection in an advertisement recommendation process are realized, and effective feature vectors are generated for personalized advertisement recommendation while data are guaranteed not to be out of a domain.
Need to check novelty before this filing date? Find Prior Art