Trajectory similarity calculation method based on space-time pyramid matching

Abstract

The invention discloses a trajectory similarity calculation method based on space-time pyramid matching, and the method comprises the following steps: S1, carrying out the query according to a user number and given time, and obtaining the original trajectory data of a user; S2, preprocessing the original trajectory data; S3, on the basis of a Google S2 algorithm, carrying out spatial coding on the longitude and latitude, and establishing time codes according to different time granularities; S4, for each time granularity and each space granularity, calculating trajectory similarity under each time-space granularity; and S5, endowing different weights to different space-time granularities, and calculating the total similarity.

Description

Technical field [0001] The present invention relates to a temporal analysis and data mining, and more specifically, to a trajectory based on temporal pyramid matching similarity calculation method. Background technique [0002] Now, with the rapid development of networking technology and mobile Internet, ubiquitous positioning means such as sensors, GPS positioning means, like a smart card trajectory data generated by the mass. Track mining has become a hot topic in the city computer computing applications. Based on the user's mobile trajectory mining can provide critical technical support for the community areas of public security, intelligent transportation, demographics sector. Behind this is to rely on large spatial and temporal data support the application of technology. [0003] Mobile users are authorized to track data mainly from the "positioning" of the rights of APP mobile GPS track data and signaling data carriers. GPS track data is an active data that only in the case...

AI Technical Summary

Problems solved by technology

Since the GPS data is uniformly sampled, while the mobile signaling trajectory data is non-uniformly sampled, this makes it impossible to use traditional measurement methods such as Euclidean distance and Bhattacharyian distance to directly measure the trajectory similarity based on mobile signaling.

The DTW distance is calculated according to the method of dynamic programming so that the sum of the distances of all corresponding points in the two sequences is the smallest. Although it is not limited by whether the number of trajectory points is the same, the computational complexity is high; the longest common subsequence LCSS method is not sensitive to noise , but similar to DTW, only the sequence of the trajectory is considered, and the temporal characteristics of the trajectory are not considered

The Frechet distance is a description method based on spatial path similarity, which focuses on taking the path space distance into consideration, making it more efficient for the evaluation of the similarity of curves with a certain spatial timing. For signaling trajectory data, there is a ping-pong effect (trajectory points drift between adjacent base stations in a short period of time), this method is not suitable for signaling data

Images