A vehicle destination prediction method and system based on user behavior

Abstract

The invention discloses a vehicle destination prediction method and system based on user behavior. The method includes the steps of: when the vehicle is detected to be started, obtain the current time and the current location of the vehicle, and send them to a cloud server; the cloud server adopts a well-trained The vehicle destination prediction model, after predicting the destination of the user's vehicle travel, returns the predicted destination to the corresponding vehicle. The present invention can automatically predict the destination when the user starts the vehicle, and the timeliness is good. Moreover, the present invention predicts the user's destination on the cloud server without occupying local storage and computing resources. When it is necessary to update the prediction model, it only needs to The cloud server can be updated, which can ensure the accuracy of the prediction, and does not need to be changed for each vehicle. The application and promotion are more convenient and fast, and can be widely used in the intelligent transportation industry.

Description

technical field [0001] The invention relates to the field of intelligent traffic information processing, in particular to a vehicle destination prediction method and system based on user behavior. Background technique [0002] With the development of intelligent vehicle technology, currently, during the driving process of the vehicle, the destination prediction based on the driving trajectory of the user's vehicle can provide important reference information for the user's driving. At present, the main scheme of vehicle destination prediction is to predict the destination of the vehicle according to the trajectory of the vehicle in combination with the historical data of the vehicle. This kind of prediction method needs to combine the trajectory of the vehicle to predict the destination. The prediction can only be made after the vehicle departs for a period of time, and it is impossible to predict the destination when the vehicle departs, and the timeliness is poor. In addit...

AI Technical Summary

Problems solved by technology

At present, the main scheme of vehicle destination prediction is to predict the destination of the vehicle according to the trajectory of the vehicle in combination with the historical data of vehicle driving. This kind of prediction method needs to combine the trajectory of the vehicle to predict the destination. The prediction can only be made after the vehicle departs for a period of time, it is impossible to predict the destination when the vehicle departs, and the timeliness is poor

In addition, in the current forecasting scheme, local forecasting is mainly performed on the vehicle side. The forecasting model is stored locally, which requires more local storage and computing resources, and cannot be updated in time, resulting in low forecasting accuracy.

Images