Friend recommendation method and system introducing attention mechanism and storage medium

Abstract

The invention discloses a friend recommendation method introducing an attention mechanism. The friend recommendation method comprises the following steps: carrying out the feature extraction of a userpair which comprises a target user and a candidate user, and obtaining multi-dimensional feature information; dynamically weighting the multi-dimensional feature information through an attention mechanism to obtain an output result; and performing friend recommendation according to the output result. The friend recommendation method introducing an attention mechanism improves the practicability and effectiveness of a recommendation function. The friend recommendation method and system introducing the attention mechanism and the storage medium can be widely applied to the Internet technology.

Description

technical field [0001] The invention relates to Internet technology, in particular to a friend recommendation method, system and storage medium introducing an attention mechanism. Background technique [0002] In recent years, with the rapid development of Internet technology, online social network platforms have been fully popularized, and users can conduct convenient information exchange and information sharing through social network platforms. However, as the number of users continues to increase, more and more information can be obtained, and a large amount of redundant information will affect the use of users. Therefore, a recommendation system has emerged, which can discover and recommend content in line with interests to users from massive amounts of information, helping to alleviate the problem of information overload, and has been extensively studied today. [0003] Traditional content-based recommendation methods, which only learn simple linear relationships betwe...

AI Technical Summary

Problems solved by technology

However, in actual situations, target users usually do not pay attention to all the features of the recommended items. For example, in the friend recommendation task in social networks, different users will choose friends according to different characteristics, and some users choose users with similar research fields. become friends, and most of the friends of some users are from the same school, so the existing friend recommendation methods cannot accurately obtain the different preferences of different users, and cannot give reasonable recommendation results according to the user's attention to different characteristics. Poor functionality and effectiveness

Images