The invention is applicable to the technical field of intelligent traffic, provides a real-time traffic speed prediction method and system based on a graph convolutional network, and aims to construct a spatial graph and a semantic graph, divide the spatial graph and the semantic graph into a global dimension and a local dimension as the input of a model, and predict the traffic speed in real time. The multi-level capture of global information and local information in the whole traffic topological graph is realized, the similarity between nodes can be conveniently fused into the algorithm, the model optimization is facilitated, and the algorithm performance is improved.
本发明适用智能交通技术领域,提供了一种基于图卷积网络的交通速度实时预测方法及系统,本方法的目的在于通过构建空间图和语义图,并将空间图和语义图分为全局和局部两个维度作为模型的输入,实现了对整个交通拓扑图中全局信息和局部信息的多层次捕获,便于将节点间的相似性融入算法中,有利于优化模型,提高算法性能。
Traffic speed real-time prediction method and system based on graph convolutional network
一种基于图卷积网络的交通速度实时预测方法及系统
2023-08-29
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 |
European Patent Office | 2023
|Space-time ARMA graph convolutional network traffic flow prediction method
European Patent Office | 2024
|