Knowledge graph-based collaborative recommendation method, apparatus and device, and storage medium

Abstract

The invention discloses a knowledge graph-based collaborative recommendation method, apparatus and device, and a storage medium, and the method comprises the following steps: obtaining score data of afirst target for an article; preprocessing the scoring data; constructing a knowledge graph related to the article based on the preprocessed scoring data, and obtaining an article label; obtaining the similarity between the first target and other targets according to the article label; and obtaining a similar target according to the similarity between the first target and other targets, and recommending preferred articles of the similar target to the first target. Compared with the prior art, the invention has the advantages that the steps are simple and convenient, the design is reasonable,expert annotation is not needed while the cold start problem is solved, the labor and time cost is greatly reduced, and favorite articles can be recommended to users according to the interests of theusers.

Description

technical field [0001] The present invention relates to the technical field of computer software, in particular to a collaborative recommendation method, device, device and storage medium based on knowledge graphs. Background technique [0002] In the era of big data, people often fall into the predicament of information overload. At this time, the recommendation system came into being and was quickly applied successfully in music, movies, e-commerce and other fields. The recommendation system can accurately recommend music, movies or products that users are interested in, which not only helps users save a lot of time, but also efficiently sells products. Therefore, the recommendation system has received extensive attention from the industry and academia. At present, the recommendation system mainly adopts the content recommendation method and the collaborative recommendation method. The content recommendation method converts items into content vectors and then calculates th...

AI Technical Summary

Problems solved by technology

At present, the recommendation system mainly adopts the content recommendation method and the collaborative recommendation method. The content recommendation method converts items into content vectors and then calculates their similarity to recommend items similar to specific user preferences. However, this method requires expert annotation, which will result in Huge manpower, time and other costs; the collaborative recommendation method has a cold start problem

Images