Hierarchical Privacy-Preserving Recommender System and Operation Method Based on the Recommender System

Abstract

The invention discloses a recommendation system with a hierarchical privacy protection function and an operation method on the basis of the recommendation system. The recommendation system comprises a client / browser, a database of the client / browser, a proxy server, a database of the proxy server, a plurality of recommendation servers and databases of the recommendation servers. Interfaces for exchanging data with the servers can be provided by the client / browser and the database of the client / browser, personal information and service requests which are inputted by users can be received, the personal information can be stored in the database of the client / browser, the service requests can be transmitted to the proxy server, and recommendation results fed by the recommendation servers can be displayed for the users; the service requests of the users can be received by the proxy server and the database of the proxy server, the proxy server and the database of the proxy server can respond to the service requests, the recommendation results of the recommendation servers can be received, and recommendation can be carried out for the users according to the recommendation results; project resources in the recommendation system can be stored and managed by the recommendation servers and the databases of the recommendation servers, and recommendation which meets the service requests of the users can be collaboratively generated according to score information of the users. The recommendation system and the operation method have the advantage that privacy of the users can be protected when the recommendation system is used in application scenes such as recommendation, query and small data cold start.

Description

technical field [0001] The invention belongs to the field of data mining, and in particular relates to a hierarchical privacy protection recommendation system and an operation method based on the recommendation system. Background technique [0002] With the rise of the Internet and the popularization of various smart terminals, all kinds of information generated by people have been digitized on a large scale, resulting in an exponential explosion of digital information. Faced with the knowledge and rules contained in massive data, data mining and recommendation systems emerged as the times require. Some online e-commerce, music, movies, social networking and other websites also mostly develop and apply recommendation systems or modules. While these recommender systems or modules are being used, more and more people pay attention to the privacy protection of recommender systems. [0003] The privacy protection of existing recommender systems mainly involves the following is...

AI Technical Summary

Problems solved by technology

[0006] One of the technical problems to be solved by the present invention is to provide a recommendation system to solve the problems of incomplete protection levels and low user participation in existing privacy protection technologies

Images