Social network friend recommending method based on multiple personal characteristic hybrid architecture

Abstract

The invention discloses a social network friend recommending method based on multiple personal characteristic hybrid architecture. The method comprises: defining intimacy degree characteristics according to attribute information of users in conjunction with inter-user interactive information, constructing an intimacy degree probability transfer matrix, and introducing a random walk model to calculate inter-user interaction degree scores; on this basis, defining personal node characteristics of the users, using a weighted average method to assign different weights to the characteristics, and using a random walk algorithm to obtain a Top-N recommendation list for recommending. The method of the invention has the advantages that attribute information and interactive information of users are fully considered, interest characteristics of the users are considered, behavior characteristics of the users in a social network are also considered, real friend needs of the users can be truly reflected through these personal network characteristics and node characteristics, and friend recommending accuracy is greatly improved.

Description

technical field [0001] The invention relates to a personalized friend recommendation model in a social network, in particular to a social network friend recommendation method based on a mixed architecture of multiple personalized features. This method combines the attribute information of users and the interaction information between users to define the characteristics of intimacy, construct the probability transition matrix of intimacy, and introduce the random walk model to calculate the score value of the interaction degree between users. On this basis, define the user's personalized node characteristics, use the weighted average method to assign different weights to them, and finally use the random walk algorithm to get the Top-N recommendation list for recommendation. Based on this, a unified personalized friend recommendation model is constructed to realize personalized friend recommendation. Background technique [0002] Recommendation is an effective way to search f...

AI Technical Summary

Problems solved by technology

These methods are widely used in major recommendation systems, but these methods ignore the user's personalized characteristics and interactive information between users, such as @, comments, forwarding, likes, etc.

Images