Information recommendation method, device and equipment and computer readable storage medium

Abstract

The invention discloses an information recommendation method, which comprises the steps of obtaining a to-be-trained model according to a training task when a federation center receives the training task; distributing the to-be-trained model to each terminal device, so that each terminal device trains the to-be-trained model by utilizing a user browsing information data set of the terminal deviceto obtain a training model; receiving the training model uploaded by each terminal device; performing average calculation on each training model to obtain an information recommendation model; issuingthe information recommendation model to each terminal device, so that each terminal device performs information recommendation by using the information recommendation model. According to the information recommendation method, the development cost of the information recommendation system can be effectively reduced, and meanwhile, efficient information recommendation services are provided for users.The invention furthermore discloses an information recommendation device and equipment, and a computer readable storage medium, which all have the above beneficial effects.

Description

technical field [0001] The present application relates to the technical field of the Internet, in particular to an information recommendation method, and also to an information recommendation device, device, and computer-readable storage medium. Background technique [0002] With the rapid development of e-commerce platforms and Internet technology, people have entered the era of information overload, and it has become more and more difficult to find the knowledge they are interested in from a large amount of information. Most of the existing information recommendation systems are based on machine learning and deep learning technology, using learning models to achieve information recommendation. However, for large-scale user and business data, it is necessary to build a big data platform to achieve parallel computing, which leads to the consumption of a large amount of computing resources and increases the cost of platform construction; moreover, the data recommendation base...

AI Technical Summary

Problems solved by technology

However, for large-scale user and business data, it is necessary to build a big data platform to achieve parallel computing, which leads to the consumption of a large amount of computing resources and increases the cost of platform construction; moreover, the data recommendation based on the learning model needs to be implemented during the model training process. Collecting a large amount of user information not only makes the user privacy not guaranteed, but also the data collection process is cumbersome and inefficient

Images