A method, device and storage medium for extracting high-income taxi drivers and their experience trajectories

Abstract

The present invention relates to a method, device and storage medium for extracting high-income taxi drivers and their experience trajectories. Based on the taxi trajectories data, the present invention divides the trajectories data according to time periods and passenger loading status, and calculates the mileage, time, Income, etc. are used to make a preliminary judgment on the income of taxi drivers. Further, according to the distribution of the congested area, the trajectory spline method is used to make a secondary judgment on the driver type, and the trajectory interpolation method based on the intersection coordinates is used to quickly restore the high-income drivers who have been screened. For the corresponding trajectory, the extracted driving trajectory is used as a sample set, and through spatial grid analysis, it is mapped to the trajectory distribution histogram to form an image expression method of trajectory distribution.

Description

A high-income taxi driver and its experience trajectory extraction method, equipment and storage storage medium technical field The present invention relates to a kind of extraction method, equipment and storage medium of high-income taxi driver and experience track thereof, It belongs to the technical field of navigation systems. Background technique [0002] With the development of urban traffic, the congestion index of road sections during commuting peak hours is increasing. taxi as city It is an important part of the city's public transportation and plays an important service function during peak hours. However, due to the occurrence of different regions Congestion makes its dispatching function limited, and residents often encounter the problem of "difficulty in ordering a taxi" or "driving without a car" when traveling during peak hours. However, high-income taxi drivers can use their own driving experience to formulate appropriate driving strategies during p...

AI Technical Summary

Problems solved by technology

This scheme does not fully consider the characteristics of the huge amount of taxi trajectory data, the low requirement for recovery accuracy, and the basic matching with the road network when recovering the trajectory. The mining of the characteristics of high-income drivers' driving trajectories and the consideration of spatio-temporal correlation Not enough, incomplete and uneven trajectory information will also cause certain errors in the selection of targets and the output of results, and the areas obtained by the usual direct clustering method often lack specific characteristics of spatial distribution, which is helpful for the guidance of taxi drivers' travel routes. Insufficient meaning

Images