Personalized multi-view federal recommendation system

Abstract

The invention discloses a personalized multi-view federal recommendation system, which comprises a central server and a plurality of user clients, and any user client comprises a training module and a prediction module; wherein the training module comprises a data distribution sub-module, a gradient calculation sub-module, a gradient aggregation sub-module, a model updating sub-module, a model fine tuning sub-module, a user data warehouse and an article data warehouse which cooperate with one another to complete execution of a training algorithm, and a user sub-model and an article sub-model are obtained; and the prediction module comprises a semantic calculation sub-module, an interactive calculation sub-module, a probability aggregation sub-module, a probability sorting sub-module, a recommendation output sub-module, a user model warehouse and an article model warehouse which cooperate with one another to complete execution of a prediction algorithm and obtain a recommended article sequence corresponding to any user client. According to the method, the scene adaptability is higher, the feature mining of the underlying model is deeper, the data source covered by the original input is wider, and the localization fine tuning of the global model is better.

Description

technical field [0001] The invention belongs to the field of data science and big data technology, and specifically relates to a personalized multi-view federated recommendation system for privacy protection based on multi-view learning, meta-learning and federated learning. [0002] technical background [0003] With the rapid development of information technology and Internet technology, people have entered an era of information overload from an era of information scarcity. Taking the e-commerce platform as an example, in order to meet the various needs of users, the amount of product information expands rapidly. On the one hand, users often get lost in the massive product information space, unable to find the products they need quickly and smoothly; The double problem of platform profitability is difficult. In this context, the recommendation system came into being. After more than 20 years of accumulation and precipitation, recommendation systems have been widely used ...

AI Technical Summary

Problems solved by technology

It jointly trains the resume features of several users and the browsed target job features, and finally achieves job matching while protecting resume privacy, but it is only applicable to the scenario of human resource management

[0010] (2) The federated recommendation method proposed by some technologies is based on traditional models and algorithms, but fails to combine cutting-edge neural networks

It uses the early collaborative filtering model as the underlying algorithm to train users and products and the similarity between products, and clusters and ranks products according to the similarity, but does not fully mine user representations.

[0011] (3) The federated recommendation method proposed by some technologies is aimed at a single interactive data, but fails to solve the user cold start problem

It only uses the user behavior data matrix as the training data source to generate the item recall set corresponding to the user data to be predicted. However, new users often do not have historical data, which leads to the user cold start problem.

[0012] (4) The federated recommendation method proposed by some technologies trains a shared global model, but fails to adapt to the differences of clients

Images