Method and system for extracting group behavior characteristics of mobile phone track data clustering

Abstract

The invention provides a method and system for extracting group behavior characteristics of mobile phone track data clustering. Time sequence tracks of individuals are obtained by acquiring mobile phone track data, the spatial repeatability and time periodicity of the time sequence track of each individual are counted, and the to-be-processed track data is generated; individual active points are extracted from the to-be-processed track data, candidate active point track data corresponding to each individual is obtained, simplification and completion processing are carried out on the candidateactive point track data, and active point track data of each individual is obtained; the similarity between the active point track data of the individuals is calculated; a plurality of active point tracks belonging to different track types are obtained according to the similarity, and the group behavior characteristics are extracted. According to the method and the system, high-efficiency processing of the mobile phone track data and intelligent extraction of a space-time multi-resolution behavior pattern are achieved, and large-scale human activity analysis is supported.

Description

technical field [0001] The present invention relates to the technical field of track data analysis and processing, in particular to a method and system for extracting group behavior characteristics of mobile phone track data clustering. Background technique [0002] Mobile phone trajectory data records the time and location of individuals, contains a large amount of individual activities and travel information, and shows considerable potential in the fields of online car-hailing scheduling, intelligent transportation, urban planning, and mobile location services. Mining patterns in large-scale mobile phone trajectory data can discover the rules of individual activities, describe the refined interaction process between residents and buildings, POIs, etc., and provide basic human activity data support for data-driven urban planning and urban intelligent operation. [0003] However, the mobile phone trajectory data in the prior art is limited by spatial positioning methods such...

AI Technical Summary

Problems solved by technology

[0003] However, the mobile phone trajectory data in the prior art is limited by spatial positioning methods such as GPS and WiFi. The spatial positioning accuracy generally ranges from tens of meters to several kilometers, and the time sampling interval ranges from seconds to several hours. Important semantic information such as activity type and activity time is difficult to perform efficient trajectory clustering, and it is very difficult to find group behavior patterns

Images