一种基于STGCN-Transformer混合模型的高速公路交通流预测方法
By using the STGCN-Transformer hybrid model, which combines multiple adjacency matrices and algorithms, the problem of insufficient spatiotemporal dependence in highway traffic flow prediction is solved, achieving higher accuracy and stability in traffic flow prediction, adapting to sudden events, and improving the practicality and robustness of prediction.
CN121661828BActive Publication Date: 2026-07-17ROAD TRAFFIC SAFETY RES CENT THE MINIST OF PUBLIC SECURITY OF THE PEOPLES REPUBLIC OF CHINA
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ROAD TRAFFIC SAFETY RES CENT THE MINIST OF PUBLIC SECURITY OF THE PEOPLES REPUBLIC OF CHINA
- Filing Date
- 2025-12-05
- Publication Date
- 2026-07-17
Smart Images
Figure CN121661828B_ABST
Abstract
本发明公开了一种基于STGCN‑Transformer混合模型的高速公路交通流预测方法，属于智能交通技术领域，方法包括：通过高速公路门架系统获取数据，构建路网拓扑图；协同构建欧氏距离、连通性及时序相似性三类邻接矩阵以多维刻画空间关系；采用可学习式时间信息嵌入与node2vec算法分别表征时序位置特征与全局路网结构信息；将上述特征输入时序Transformer模块与空间图卷积模块进行联合训练，得到混合模型；在预测阶段，通过动态图卷积模块自适应融合静态图与实时节点表示，生成动态图结构并输出流量预测结果。本发明能够全面提升交通流预测的精度、对复杂时空依赖的刻画能力以及对动态交通状态的适应性。
Need to check novelty before this filing date? Find Prior Art