The invention discloses an urban traffic flow prediction model construction method based on heterogeneous data fusion. Wherein a prediction model combining a convolutional neural network GCN and a gating cycle unit GRU is adopted for the traffic direct correlation data, the GCN is mainly used for capturing spatial characteristics between nodes, and the GRU is mainly used for capturing time dependence; a network embedding model is adopted for traffic indirect related data, and a network can process more urban data through spatial domain feature embedding and time domain feature embedding, so that the accuracy of traffic flow prediction of a deep learning model is improved; experiments on a real data set show that compared with a traditional traffic prediction method, the embedded and fused external factors are effective in a prediction task.
本发明公开了基于异构数据融合的城市交通流预测模型构建方法;其中对交通直接相关数据采用的是卷积神经网络GCN与门控循环单元GRU的结合的预测模型,GCN主要用于捕获节点间的空间特性,GRU主要用于捕获时间依赖;对交通间接相关数据采用的是网络嵌入模型,通过空域特征嵌入和时域特征嵌入,使网络可以处理更多的城市数据,从而提升深度学习模型对交通流预测的准确性;在真实数据集上的实验表明,与传统的交通预测方法相比,嵌入融合外部因素在在预测任务中有效。
Urban traffic flow prediction model construction method based on heterogeneous data fusion
基于异构数据融合的城市交通流预测模型构建方法
2023-07-14
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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 |
Urban traffic flow prediction method based on multi-source data fusion
European Patent Office | 2020
|Urban intersection traffic flow prediction method based on multi-source data fusion
European Patent Office | 2021
|Urban traffic prediction method and system based on spatio-temporal data flow fusion analysis
European Patent Office | 2020
|Traffic speed prediction method based on traffic flow data fusion and system
European Patent Office | 2021
|Urban traffic travel time prediction method for multi-source heterogeneous data
European Patent Office | 2022
|