The invention provides a public traffic flow prediction method combining urban interest points and a space-time causal relationship, and belongs to the technical field of traffic flow prediction. The method comprises the following steps: firstly, periodically preprocessing public traffic flow data; secondly, performing information extraction on geographic coordinate data of the urban interest points and completing classification of station groups; and finally, a deep learning model based on a space-time causal relationship is utilized to predict the public traffic station flow of a future time window, and different station groups use different trainable parameters. According to the method, the problem that the complex space-time causal relationship of urban traffic cannot be effectively handled in traditional traffic flow prediction is solved, the external factor interest points of the traffic system are integrated into the construction and training stages of the deep learning model, and the method is suitable for urban public traffic flow prediction and has good prediction accuracy and small errors.
本发明提供了一种结合城市兴趣点和时空因果关系的公共交通流量预测方法,属于交通流预测技术领域。本发明方法首先对公共交通流量数据进行周期性预处理;其次,对城市兴趣点地理坐标数据进行信息提取并完成站点群的分类;最后,利用一个基于时空因果关系的深度学习模型对未来时间窗的公共交通站点流量做出预测,其中不同的站点群将使用不同的可训练参数。本发明的应用解决了传统交通流量预测中无法有效应对城市交通复杂时空因果关系的问题,还将交通系统外部因素兴趣点融入了深度学习模型的构建和训练阶段,适用于城市的公共交通流量预测,具有很好的预测准确性和较小的误差。
Public traffic flow prediction method combining urban interest points and space-time causal relationship
一种结合城市兴趣点和时空因果关系的公共交通流量预测方法
2022-10-18
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 |
Urban traffic data prediction method based on space-time causal prediction of continuous learning
European Patent Office | 2023
|Traffic flow prediction method based on space-time causal attention network
European Patent Office | 2024
|Urban flow prediction method based on flow-POI causal relationship reasoning
European Patent Office | 2023
|IEEE | 2003
|British Library Conference Proceedings | 2003
|