The invention discloses a traffic flow prediction method and system based on a graph neural network, and relates to the technical field of traffic prediction, and the method comprises the steps: obtaining the historical traffic flow data of a to-be-predicted road segment, and obtaining the historical actual traffic flow data; carrying out statistics on the vehicle residual quantity at the intersection of the to-be-predicted road section to obtain residual quantity data; establishing a first prediction model based on the residual volume data and the historical actual traffic flow data; acquiring the driving-in vehicle data and the driving-out vehicle data of the road section to be predicted, and establishing a second prediction model; obtaining residual quantity data of vehicles at the intersection of the road section to be predicted at the current moment, comparing the residual quantity data with built-in residual quantity standard data, and if the residual quantity data is smaller than the built-in residual quantity standard data, performing prediction based on a first prediction model to obtain a prediction result; and if the residual volume data is greater than the built-in residual volume standard data, predicting the to-be-predicted road section based on a second prediction model to obtain a prediction result. The method has the effect of improving the accuracy of the prediction result.
本申请公开了基于图神经网络的交通流量预测方法及系统,涉及交通预测技术领域,该方法包括获取待预测路段的历史车流数据并得到历史实际车流数据;对待预测路段路口的车辆残余量进行统计得到残余量数据;基于残余量数据和历史实际车流数据建立第一预测模型;获取待预测路段的驶入车辆数据和驶出车辆数据并建立第二预测模型;获取当前时刻的待预测路段路口的车辆的残余量数据并与内置残余量标准数据进行比较,若残余量数据小于内置残余量标准数据,则基于第一预测模型进行预测,得到预测结果;若残余量数据大于内置残余量标准数据,则基于第二预测模型以对待预测路段进行预测得到预测结果。本申请具有提高预测结果准确性的效果。
Traffic flow prediction method and system based on graph neural network
基于图神经网络的交通流量预测方法及系统
2024-09-10
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES |
Traffic flow prediction method based on graph neural network
European Patent Office | 2024
|Traffic flow prediction method based on dynamic graph neural network
European Patent Office | 2022
|Airport traffic flow prediction method based on graph neural network
European Patent Office | 2023
|Graph neural network traffic flow prediction method based on deep learning
European Patent Office | 2023
|Traffic flow space-time prediction method based on graph neural network
European Patent Office | 2024
|