Vehicle OD prediction method, device and equipment and storage medium

Abstract

The invention discloses a vehicle OD prediction method which comprises the steps: obtaining a vehicle trajectory data sample, obtaining vehicle parking point data according to the trajectory data sample, and inputting the vehicle parking point data into a DBSCAN model for clustering, generating a clustered class cluster, constructing OD priori data according to the class cluster, constructing an OD prediction model through the OD priori data and a Bayesian formula, and predicting the vehicle OD through the OD prediction model. With application of the method, the vehicle OD can be predicted according to the vehicle trajectory data, prediction of trucks with large trajectory data volume and long time span is particularly more accurate and the implementation mode is simpler.

Description

technical field [0001] The present invention relates to the technical field of intelligent transportation, in particular to a method, device, equipment and storage medium for vehicle OD prediction. Background technique [0002] With the development of intelligent transportation technology, vehicle OD prediction has very important practical significance. For example, by predicting the departure and destination of the truck, the information of the logistics station along the way can be transmitted to the truck management personnel, and the logistics along the way The goods information in the site is transmitted to the truck management personnel, so as to facilitate the transportation and management of the goods by the truck management personnel. [0003] At present, the method of vehicle OD prediction is to preprocess the vehicle trajectory data into a trajectory vector, and construct a priori road segment flow matrix and road segment travel time matrix, calculate the OD prior...

AI Technical Summary

Problems solved by technology

[0003] At present, the method of vehicle OD prediction is to preprocess the vehicle trajectory data into a trajectory vector, and construct a priori road segment flow matrix and road segment travel time matrix, calculate the OD prior matrix, and use the OD prior matrix and road segment flow, road segment travel time matrix Solve the OD prediction model based on time, traffic distribution relationship, etc. The trajectory data processed by this method are mostly the trajectory data of private cars. For truck data with a long time span, the accuracy of truck OD prediction is relatively low

Images