The invention discloses a traffic flow prediction method based on a time-space diagram convolutional network, and the method employs a time sequence convolutional network to simulate the time sequence correlation of a traffic flow, and combines an attention mechanism to enhance the depiction capability of a model on the dynamic time sequence dependence of the traffic flow under different time granularities. A diffusion diagram convolutional network based on a self-adaptive adjacency matrix is established in an airspace, and local space correlation characteristics of nodes and global space information of a road network are captured by using a data driving mode; compared with the prior art, the system can monitor the complex traffic condition in real time, predict the traffic condition in a period of time in the future, assist related management departments in road scheduling and traffic dispersion, improve the traffic efficiency of urban roads, and reduce the occurrence of traffic safety accidents.
本发明公开了一种时空图卷积网络的交通流量预测方法,并利用时序卷积网络模拟交通流的时序关联,并结合注意力机制增强模型对交通流在不同时间粒度下动态时序依赖的刻画能力;在空域搭建了基于自人适应邻接矩阵的扩散图卷积网络,利用数据驱动方式捕获节点的局部空间关联特征和路网的全局空间信息;可以对较为复杂的交通状况进行实时监测,并预测未来一段时间的交通情况,辅助有关管理部门进行道路调度及交通疏导,可以提高城市道路的通行效率,减少交通安全事故的发生。
Traffic flow prediction method of space-time diagram convolutional network
一种时空图卷积网络的交通流量预测方法
2024-02-20
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / 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 |
Traffic flow prediction method based on space-time diagram convolutional network
Europäisches Patentamt | 2022
|Traffic flow prediction method based on space-time diagram convolutional network
Europäisches Patentamt | 2023
|Traffic flow prediction method based on Transform space-time diagram convolutional network
Europäisches Patentamt | 2022
|Traffic flow prediction method based on multi-space-time diagram convolutional network
Europäisches Patentamt | 2021
|Traffic flow prediction method based on multi-view space-time diagram convolutional network
Europäisches Patentamt | 2023
|