Social relation modeling method based on moving track

Abstract

The invention discloses a social relation modeling method based on a moving track, and the method comprises the following steps: 1), recording track points of a user according to a preset time interval in a set time period according to the collected track data of the user, and forming a timestamp sequence of a user track; 2) judging whether the users meet according to the timestamp sequence of each user track, and if so, recording a meeting record vector between every two users; 3) constructing a social relation model based on the movement track according to the encountering record vector; and4) calculating the social relationship strength among the users according to the social relationship model, and dividing the mobile communities to which the users belong. According to the method, thesocial relation intensity is measured by calculating the encountering times and the encountering time between different mobile users, the social relation intensity is converted into the weighted social relation network, and therefore different user communities are constructed, and help is provided for more accurate position service based on tracks.

Description

technical field [0001] The invention relates to social network technology, in particular to a method for modeling social relations based on moving tracks. Background technique [0002] With the maturity of portable devices and positioning technology, the amount of trajectory data is increasing. Large-scale trajectory data depicts the spatiotemporal dynamics of individuals and groups, and contains behavioral information of humans, vehicles, and animals. How to extract potential and meaningful knowledge from them has become a new research hotspot and problem in the field of data mining. The location prediction of mobile users is the premise of providing location-based services, and the social relationship of mobile users hidden in trajectory data is potentially useful information, which can improve the accuracy of mobile pattern mining and mobile location prediction. How to measure the strength of social relations between people in a social network has always been a difficult...

AI Technical Summary

Problems solved by technology

These methods have certain limitations. First, because in reality, the relationship strength between mobile nodes is not only related to the number of encounters, but also related to the duration of each encounter. The choice of different complex network community discovery algorithms has a greater impact on the results, so Constructing a suitable social relationship model and community discovery algorithm is a problem worthy of research

Images