Recommendation method and device, equipment and storage medium

Abstract

The invention discloses a recommendation method and device, equipment and a storage medium. The method comprises the following steps: according to the historical behavior data of a target user and feature vectors of historical articles in pre-determined feature vectors of a plurality of articles, determining the target user according to the feature vectors; and determining a feature vector of thetarget user according to the historical behavior data, determining a target recommended article recommended to the target user according to the similarity between the feature vector of the target userand the feature vectors of the plurality of articles, and recommending the target recommended article to the target user. According to the recommendation method, the feature vectors of the multiple articles are determined in advance, it is achieved that only the feature vector of the target user needs to be determined during recommendation, then the target recommended articles are determined based on the similarity of the feature vector of the target user and the feature vectors of the articles, the calculated amount during recommendation is reduced, and the recommendation real-time performance is improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of big data processing, and in particular to a recommendation method, device, equipment and storage medium. Background technique [0002] With the continuous development of big data processing technology, recommendation systems that recommend items to users are more and more widely used. The items here can be multimedia items such as movies, music, and albums. [0003] At present, common recommendation algorithms include collaborative filtering matrix decomposition recommendation model, such as the matrix decomposition recommendation model in the machine learning open source software Spark MLlib. The input data of the matrix decomposition recommendation model is the user's scoring data on the item, that is, the data in the three-column format, "user, item, score". The score here can be an explicit score, such as 1 to 5 points, or an implicit score, such as the viewing time. The m...

AI Technical Summary

Problems solved by technology

[0005] The invention provides a recommendation method, device, equipment and storage medium to solve the technical problem of low real-time performance in the current recommendation method

Images