Context sensing recommendation system and method based on federal learning

Abstract

The invention discloses a context awareness recommendation system and method based on federal learning, and provides a user-defined data cooperation protocol module which is used for splicing user score data and context information to obtain user data containing the context information and sending the user data to a client. The client trains a local recommendation model according to the user data and the server weight parameters, and sends the local model weight parameters to a central server. The central server aggregates the local model weight parameters of all the clients to obtain new server weight parameters such that a round of training is completed. Te local recommendation model is trained for multiple times until the local recommendation model converges. The trained local recommendation model is used for processing the new user data to obtain recommendation content for the user. According to the method, the federal learning technology is applied to the recommendation system, and the context information is combined in the recommendation system, so that the privacy of the user is protected, and the recommendation accuracy is relatively high.

Description

technical field [0001] The invention relates to the field of recommendation systems, in particular to a context-aware recommendation system and method based on federated learning. Background technique [0002] In the field of recommendation systems, traditional privacy protection methods mainly include data anonymization, encryption technology and differential privacy. Data anonymization technology is a method to anonymize the data in the data set. It first divides the attributes of each piece of data into three categories, which uniquely identify the identification attributes of the individual. Together, they can determine the quasi-identification attributes of the individual and the needs. Protected sensitive properties. The anonymized data set will have its identification attributes hidden, and at the same time, a certain degree of fuzzing will be performed on the identification attributes (such as changing age to range, removing the last two digits of zip code, etc.), s...

AI Technical Summary

Problems solved by technology

[0006]Aiming at the above-mentioned deficiencies in the prior art, the present invention provides a context-aware recommendation system and method based on federated learning by applying federated learning technology in the recommended system , and the context information is combined in the recommendation system, which solves the problem that the existing recommendation system using the federated learning framework does not make good use of the context information. The present invention achieves high recommendation accuracy while protecting user privacy

Images