The invention discloses a cycle adaptive graph convolution circulation network traffic flow prediction method comprising the following steps: learning traffic flow cycle characteristics through cycle sequence representation obtained by a plurality of different cycle sub-modules of a pre-training model, and mining the spatial correlation between traffic flows by using an adaptive graph convolution module; and finally, traffic flow prediction is carried out through periodic capture, so that the prediction precision of the traffic flow can be greatly improved.
本发明公开了一种周期自适应图卷积循环网络交通流预测方法,通过预训练模型的多个不同周期子模块获得的周期序列表征来学习交通流的周期特性,并利用自适应图卷积模块挖掘交通流之间的空间相关性,最后通过周期捕获来进行交通流预测,能大大提高交通流的预测精度。
Periodic adaptive graph convolution circulation network traffic flow prediction method
一种周期自适应图卷积循环网络交通流预测方法
2023-12-26
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 / 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 | 2023
|Traffic flow prediction method based on graph attention convolution network
European Patent Office | 2020
|European Patent Office | 2023
|Double-end graph convolution traffic flow prediction method with graph learning
European Patent Office | 2023
|Graph convolution and multipath neural network prediction method for traffic prediction
European Patent Office | 2023
|