Recommendation method, system and electronic device based on network representation learning

Abstract

The present application relates to a recommendation method, system and electronic device for learning based on network representation. The method comprises the following steps: step a: constructing auser-article co-occurrence network based on a bipartite graph network and a single projection image; step b: For the user-article co-occurrence network, defining search strategy to get neighbor nodesof each user node and item node. C, according to each user node, article node and respective neighbor node, obtaining vector representation of each user node and article node by using representation learning on network; Step d: according to the vector representation of each user node and the article node, obtaining the most relevant article node of each user node through vector calculation, and recommending the most relevant article to each user according to the calculation result. The present application alleviates the problem of sparsity of collaborative filtering, makes the recommendation system more interpretable, and greatly alleviates the problem of scalability in collaborative filtering.

Description

technical field [0001] The present application belongs to the technical field of data mining and recommendation, and in particular relates to a recommendation method, system and electronic equipment based on network representation learning. Background technique [0002] With the advent of the era of big data, the recommendation system has attracted more and more attention. It is excellent in helping people quickly filter data and solve the problem of information overload. Similar item recommendation, music recommendation of NetEase Cloud Music, etc. Nowadays, the recommendation system has been widely developed and has penetrated into all aspects of people's daily life, such as: music recommendation, movie recommendation, e-commerce, mobile phone applications, etc. [0003] With the popularity of recommendation systems, various recommendation methods have been proposed: including content-based recommendation, collaborative filtering, graph-based recommendation, etc. Among t...

AI Technical Summary

Problems solved by technology

[0006] However, collaborative filtering often suffers from sparsity and scalability issues

First of all, in real life, users have very little rating information on items. Many inactive users rate few items or many unpopular items get few ratings, and the rating information is concentrated on a few popular items. , therefore, the scoring matrix is ​​very sparse and irregularly distributed in practice

Secondly, the recommendation system often recommends different items to different users, so as to realize individualized needs. However, for different users to make different recommendations, the recommendation process requires global calculation, and as the number of users and items continues to increase, the global calculation Consumption becomes ever-increasing, making scalability a major concern

Images