Vehicle stop point clustering method, device and equipment and storage medium

Abstract

The invention discloses a vehicle parking point clustering method and device, equipment and a storage medium. The method comprises the steps of extracting parking point data of a vehicle according to historical trajectory data of the vehicle; clustering the stop point data through a density peak clustering algorithm to obtain a plurality of stop point clusters; calculating the similarity between the grids in each stop point cluster according to the historical driving track of the vehicle; and performing connectivity segmentation on each stop point cluster according to the similarity between the grids to obtain segmented stop point clusters. According to the vehicle stop point clustering method provided by the embodiment of the invention, on the basis of carrying out density peak value clustering on the vehicle stop points, by combining an actual business scene, the inter-grid similarity matrix based on the vehicle stop sequence is introduced, the clustering result is further segmented, and the region boundary closer to the real situation is obtained.

Description

technical field [0001] The present invention relates to the technical field of vehicle track data mining, in particular to a method, device, equipment and storage medium for clustering vehicle stops. Background technique [0002] In the Internet of Vehicles technology, vehicle parking analysis is an important link. Accurately analyzing the vehicle's parking behavior and parking location is helpful to understand the vehicle's driving behavior. Due to the stop analysis of trucks, it is possible to determine the operating routes of trucks, logistics parks, gas stations, maintenance points, enterprises, etc. that often stop. Therefore, the docking analysis of trucks is of great value to logistics transactions and truck supply chains. [0003] In the existing technology, some clustering algorithms are often used to cluster the stops of vehicles. However, in actual application scenarios, simply using clustering algorithms cannot divide two adjacent high-density areas, such as two...

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, some clustering algorithms are often used to cluster the stops of vehicles. However, in actual application scenarios, simply using clustering algorithms cannot divide two adjacent high-density areas, such as two factory areas next to each other. There are many stops for trucks. At this time, the clustering algorithm will gather into one cluster, which does not meet the actual needs.

Unable to restore the frequently parked areas and boundaries of vehicles

Images