Fuzzy clustering-based time-aware position recommendation method for position-oriented social network

Abstract

The invention discloses a fuzzy clustering-based time-aware position recommendation method for a position-oriented social network. The method comprises the following steps of 1, acquiring user sign-indata information including user information, position information and time information; 2, extracting access position geographic features through the position information, extracting user time features through the time information, obtaining user feature vectors according to the access position geographic features and the user time features, and then obtaining position recommendations based on auser fuzzy clustering algorithm; calculating the position attraction of each position in each time period according to the time information and the position information, and then obtaining position recommendation based on the position attraction; 3, predicting an access value of the user to each unsigned-in under time perception through a collaborative filtering method according to the position recommendation; 4, giving a target user and time, and screening each access value Top-which is not signed in; and recommending the user according to the position of N.

Description

technical field [0001] The invention relates to the field of position recommendation in social networks, in particular to a time-aware position recommendation method based on fuzzy clustering for position social networks. Background technique [0002] In the context of massive information, the recommendation system can realize information screening according to user preferences, effectively solving the problem of information overload. The recommendation system can solve the problem of information overload, which has attracted widespread attention in the industry. Location recommendation is a location-based social network ( LBSN: An application in Location based Social Network), which aims to recommend geographical locations that may be of interest to users, and is an important means to realize the personalized needs of users and solve the problem of information filtering. [0003] LBSN is a new social network after the integration of location service and traditional social n...

AI Technical Summary

Problems solved by technology

[0006] (1) The current recommendation algorithm in the location-based social network mainly realizes recommending a suitable location to a single user. However, it does not comprehensively consider the influence of contextual information such as time and geographic location on location recommendation, which restricts the timeliness and accuracy of recommendation to a certain extent. sex;

[0007] (2) Based on the user collaborative filtering method, without considering the group characteristics of users, recommend users in similar groups, but recommend target users based on the similarity of all users, which will make those irrelevant users also Add it to the recommendation evaluation, and further increase the complexity of calculation;

Images