The invention discloses a traffic flow prediction device constructed based on a dynamic space-time interlaced graph, which belongs to the field of intelligent traffic systems, and comprises the following steps: on the basis of obtaining a training sample, a standardized sample and a combined sample, performing attention screening operation and construction space and time dependence operation; the graph convolution features of the time step t are obtained through the space graph convolution module, the space-time interlaced graph convolution module, the feature fusion module and the time sequence feature extraction module, and the traffic flow prediction data of the future H time steps are predicted according to the time feature Ht, so that the prediction efficiency and precision are improved, the traffic jam is relieved, and the traffic flow prediction efficiency is improved. And reliable traffic planning suggestions are provided for daily commuting.
本发明公开了一种基于动态时空交错图构建的交通流量预测装置,属于智能交通系统领域,包括,在获取训练样本、标准化样本和合并样本的基础上,经过注意力筛选操作,构建空间及时间依赖操作,通过空间图卷积模块、时空交错图卷积模块、特征融合模块后和时序特征提取模块得到时间步t的图卷积特征,根据时间特征Ht预测未来H个时间步的交通流量预测数据,提升了预测效率和精度,帮助缓解交通拥堵,为日常通勤提供可靠的交通规划建议。
Traffic flow prediction device constructed based on dynamic space-time interlaced graph
一种基于动态时空交错图构建的交通流量预测装置
2023-08-01
Patent
Electronic Resource
Chinese
Space-time adaptive dynamic graph convolutional network traffic flow prediction method
European Patent Office | 2024
|Traffic flow prediction method based on dynamic multi-graph space-time synchronization network
European Patent Office | 2024
|Traffic Flow Prediction Based on Dynamic Time Slot Graph Convolution
Transportation Research Record | 2025
|European Patent Office | 2024
|European Patent Office | 2025
|