The invention proposes a traffic prediction method based on dynamic causal analysis and space-time adaptive fusion graph learning, and the method comprises the steps: S1, carrying out the feature extraction of a traffic data sample through a sensor, carrying out the preprocessing of the features of the traffic data sample, and obtaining a traffic feature data set; s2, carrying out topological structure on the traffic network, and defining a traffic prediction task; s3, based on the definition of a traffic prediction task, capturing long-range time dependence characteristics of historical traffic data through a gating expansion time convolution module; s4, based on the traffic feature data set, utilizing a mixed graph learning module to carry out spatial feature fusion; s5, capturing a node-level space-time adaptive trend by using a space-time adaptive module based on the time and space characteristics, and obtaining the output of the STAM module; and S6, connecting the output of the STAM module to an output layer through jump connection to generate a prediction result. According to the method, deep spatial-temporal characteristics between traffic nodes are better captured, and the interpretability and accuracy of the model are improved.
本发明提出了一种基于动态因果分析和时空自适应融合图学习的交通预测方法,步骤包括:S1:利用传感器进行交通数据样本的特征,并对交通数据样本的特征进行预处理,得到交通特征数据集;S2:对交通网络进行拓扑结构,并对交通预测任务进行定义;S3:基于交通预测任务定义,通过门控扩张时间卷积模块捕获历史交通数据长范围的时间依赖特征;S4:基于交通特征数据集,利用混合图学习模块进行空间特征融合;S5:基于时间与空间特征,利用时空自适应模块捕获节点级的时空自适应趋势,得到STAM模块的输出;S6:通过跳跃连接以将STAM模块的输出连接到输出层生成预测结果。本发明更好地捕捉了交通节点之间的深层时空特征,提高了模型的可解释性和准确性。
Traffic prediction method based on dynamic causal analysis and space-time adaptive fusion graph learning
一种基于动态因果分析和时空自适应融合图学习的交通预测方法
2024-11-29
Patent
Electronic Resource
Chinese
IPC: | 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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
European Patent Office | 2024
|Space-time adaptive dynamic graph convolutional network traffic flow prediction method
European Patent Office | 2024
|Traffic flow prediction method based on adaptive dynamic fusion graph convolutional network
European Patent Office | 2024
|European Patent Office | 2025
|European Patent Office | 2025
|