The invention discloses a traffic flow prediction method, equipment, a storage medium and a device, and the method comprises the steps: obtaining a current traffic flow topological graph, and predicting the future traffic flow information through a preset time-space diagram convolution network model based on the current traffic flow topological graph, the preset space-time diagram convolutional network model is used for predicting traffic flow information from a time dimension and a space dimension; according to the method, the current traffic flow topological graph is learned from the time dimension and the space dimension through the preset space-time diagram convolutional network model to predict the future traffic flow information, and the long-term dependence of the traffic flow information under the time dimension and the space dimension can be found even if the prediction time is prolonged, so that the prediction precision is improved.
本发明公开了一种交通流预测方法、设备、存储介质及装置,该方法包括:获取当前交通流拓扑图,基于当前交通流拓扑图通过预设时空图卷积网络模型预测未来交通流信息,预设时空图卷积网络模型用于从时间维度和空间维度预测交通流信息;由于本发明通过预设时空图卷积网络模型从时间维度和空间维度对当前交通流拓扑图进行学习来预测未来交通流信息,即使预测时间变长也能发现交通流信息在时间维度和空间维度下的长期依赖性,从而提高预测的精度。
Traffic flow prediction method, equipment, storage medium and device
交通流预测方法、设备、存储介质及装置
2023-09-19
Patent
Electronic Resource
Chinese
Traffic flow prediction method and device, equipment and storage medium
European Patent Office | 2024
|Traffic flow prediction method and device, equipment and storage medium
European Patent Office | 2024
|Traffic flow prediction method and device, equipment and storage medium
European Patent Office | 2025
|Traffic flow prediction method, device, equipment, storage medium and product
European Patent Office | 2025
|Traffic flow prediction method and device, equipment and storage medium
European Patent Office | 2024
|