A track data stop recognition method and system

Abstract

The invention relates to the technical field of trajectory data processing, in particular to a trajectory data remaining recognition method and system. The trajectory data remaining recognition method comprises the following steps that a, a remarkable remaining subsection, a motion subsection and an uncertain subsection in trajectory data are recognized; b, on the basis of life basic rules and trajectory subsection adjacent relations, attribution type decision rules of the uncertain subsection are set; c, on the basis of the attribution type decision rules, whether the uncertain subsection belongs to the remaining subsection or the motion subsection is judged; c, the remarkable remaining subsection and the uncertain subsection determined remaining subsection are combined, and a final remaining subsection is obtained. By introducing the uncertain subsection, remaining in the trajectory data is recognized step by step, so that the influence caused by false motion on remaining recognition is lowered, and accuracy and recall rate on the number and time of the recognition result are improved.

Description

technical field [0001] The present invention relates to the technical field of track data processing, in particular to a track data stop recognition method and system. Background technique [0002] With the advancement of science and technology, mobile phones have been highly integrated into people's daily life. The use of mobile phones is always communicating with nearby signal base stations, making it possible to continuously track the location of each individual at the large-scale crowd level. In recent years, large-scale mobile phone trajectory data has been widely used in population dynamic distribution [1], urban regional function detection [2], traffic demand assessment [3], regional epidemic spread [4] and control, and urban crowd activity patterns [5, 6] and other fields, with an unprecedented sample size, it provides a new observation perspective for many social and economic phenomena, and also provides a new way to perceive the functional status of spatial locati...

AI Technical Summary

Problems solved by technology

In the case of sparse time sampling, the time sampling interval is relatively large. Since the jump is often performed at a nearby base station, the speed index is within the normal range, and it is difficult to realize the identification of "false movement", which leads to the stay identification based on mobile phone trajectory data. The method has low precision and recall

Images