Traffic characteristic prediction method and system and storage medium

Abstract

The invention relates to a traffic feature prediction method, which is realized based on a deep learning model GA-GCN, and comprises the following steps: obtaining a historical traffic feature data set; preprocessing the historical traffic characteristic data set; dividing the historical traffic characteristic data set according to a fixed time interval; training a deep learning model GA-GCN by using each divided historical traffic feature data set; and ending the training, and predicting the traffic features in the test set by using the trained deep learning model GA-GCN to obtain a prediction result.

Description

technical field [0001] The present invention relates to the technical field of intelligent transportation, and more specifically, to a traffic characteristic prediction method, system and storage medium. Background technique [0002] Urban public transportation system is an important part of modern urban transportation. Timely and accurate traffic forecast is becoming more and more important in the control and guidance of urban traffic, and it is an indispensable part of today's social life. The traditional methods of traffic forecasting cannot meet the medium-term and long-term forecasting tasks, and the traditional methods do not consider some dependencies of time and space, so it is difficult to predict accurately. According to the survey, in 2015, the average American spent 48 minutes a day on the road. Therefore, real-time traffic forecasting is necessary for both citizens and governments. [0003] In order to solve the problem of traffic forecasting, the best effect ...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a traffic feature prediction method aimed at the technical features of large amount of calculation and low accuracy existing in the...

Images