The invention relates to the field of traffic flow prediction, in particular to a traffic flow prediction method and device based on an enhanced multi-component cyclic graph attention network. According to the method and the device, firstly, a traffic flow prediction model is constructed, and the traffic flow prediction model is used for capturing periodic time migration characteristics appearing in traffic flow; constructing a traffic flow prediction architecture based on an encoder-decoder, combining one-dimensional convolution with a long short-term memory (LSTM) network through a time correlation learning device (TCL), and capturing time features of traffic flow; capturing the spatial features of the traffic flow through a graph attention network GAT; and finally, combining a time correlation learning device TCL with a graph attention network GAT, and obtaining the spatial-temporal correlation of the traffic network by using periodic time migration characteristics appearing in the traffic flow, so that the traffic flow prediction effectiveness is higher, and the accuracy is higher.
本发明涉及交通流预测领域,具体涉及一种基于增强多分量循环图注意网络的交通流预测方法及装置。该方法及装置首先构建交通流预测模型,使用交通流预测模型捕获交通流中出现的周期性时间偏移特征;再构建基于编码器‑解码器的交通流预测架构,通过时间相关学习器TCL将一维卷积与长短期记忆网络LSTM相结合,捕获交通流的时间特征;通过图注意力网络GAT捕获交通流的空间特征;最后将时间相关学习器TCL与图注意力网络GAT相结合并利用交通流中出现的周期性时间偏移特征获取交通路网的时空相关性,交通流预测的有效性更强,准确性更高。
Traffic flow prediction method and device based on enhanced multi-component cyclic graph attention network
基于增强多分量循环图注意网络的交通流预测方法及装置
2023-09-22
Patent
Electronic Resource
Chinese
IPC: | 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 / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Traffic flow prediction method based on cyclic attention coupled graph convolutional network
European Patent Office | 2020
|European Patent Office | 2024
|Traffic flow prediction based on graph attention network
SPIE | 2024
|European Patent Office | 2023
|Traffic flow prediction method based on graph attention convolution network
European Patent Office | 2020
|