A location-based method for identifying user relationships in mobile social networks

Abstract

The invention discloses a location-based recognition method for user relations in a mobile social network. The method comprises the steps that the mobile social network is established based on user data, a factor graph model is established through feature extraction of user behaviors, and then model parameter learning and multi-relation concurrent deduction are carried out, so that the user relations can be obtained. Specifically, the user data is pre-processed, so that sampling data is acquired; user behavior features including interactive behavior features and spatial behavior features are extracted according to the sampling data; an interaction factor, a space factor and a group factor of the user relations are obtained; the factor graph model is established; the parameter learning training is conducted aiming at the factor graph model; and the trained factor graph model is used for relation recognition through a multi-relation concurrent deduction method, so that the user multi-relations can be obtained. The method disclosed by the invention considers interactive features of space locations, users' surrounding environments, and interactive effects in family and colleague relations, so that accuracy of the relation recognition can be increased.

Description

technical field [0001] The invention relates to a method for identifying user relationship, in particular to a method for identifying user relationship in a location-based mobile social network. Background technique [0002] Relation identification is one of the key issues in social network research. In social networks, people are often connected by different types of relationships (family, colleagues, friends, etc.), and analyzing the types of relationships is of great significance in many fields. For example, in the field of marketing, accurate marketing recommendations can be made by analyzing the relationship between the user's family and colleagues; in the field of security, by knowing the relationship between family members and friends of criminals, it can help relevant departments find clues and carry out more efficient Suspect investigation. With the large-scale popularization of mobile phones, the population coverage of mobile call data is close to 100%, which pro...

AI Technical Summary

Problems solved by technology

[0005] 1. Extraction of spatial relationship features: At present, the identification methods of social network relationships mostly use network topology features to determine the relationship, but lack of consideration for the impact of user spatial behavior characteristics on the relationship to be identified;

[0006] 2. Recognition of multivariate relationships based on graph model: The current relationship recognition methods generally adopt traditional recognition methods, such as decision tree, SVM and other methods, which do not fully consider the network characteristics of the relationship recognition data;

[0007] 3. Judgment of multiple relationships: The current relationship recognition methods generally judge a single relationship, such as friend and non-friend relationship, without considering the interaction between different relationships in the inference recognition process to improve the accuracy of model recognition

Images