The invention discloses a periodic sensing space-time adaptive hypergraph neural network traffic prediction method, and belongs to the technical field of traffic prediction. According to the method, a time multi-period module is designed on the basis of the multi-period of traffic time sequence data in the time dimension to capture the time dependence and period characteristics of the traffic time sequence data, and the time period module converts 1D traffic time sequence data into 2D structure data; a multi-head attention mechanism is utilized to capture changes in a corresponding traffic time sequence data period and during weeks, and multi-period characteristics are dynamically combined. In the spatial dimension, a spatial self-adaptive hypergraph module is designed by using the capability of capturing high-order interaction between nodes of the hypergraph neural network, the hypergraph neural network and the weight are selected adaptively for different traffic data sources, the specific mode and the high-order relationship of the traffic network nodes are captured, and the accuracy of traffic prediction is improved.

    本发明公开了周期性感知的时空自适应超图神经网络交通预测方法,属于交通预测技术领域。本方法在时间维度上基于交通时序数据的多周期性设计了一个时间多周期模块来捕获交通时序数据的时间依赖性和周期特性,时间周期模块将1D交通时序数据转换为2D结构数据,利用多头注意力机制捕捉相应交通时序数据周期内和周期间的变化,动态合并多周期特性。在空间维度上,利用超图神经网络捕捉节点间高阶交互的能力设计了空间自适应超图模块,针对不同的交通数据源自适应地选择超图神经网络和权重,捕获交通路网节点的特定模式和高阶关系,提高了交通预测的准确性。


    Access

    Download


    Export, share and cite



    Title :

    Periodically perceived space-time adaptive hypergraph neural network traffic prediction method


    Additional title:

    周期性感知的时空自适应超图神经网络交通预测方法


    Contributors:
    YUAN GUAN (author) / ZHAO WENZHU (author) / ZHANG YANMEI (author) / BING RUI (author) / LU RUIDONG (author)

    Publication date :

    2024-10-08


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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



    Traffic flow prediction method and device based on adaptive hypergraph convolutional neural network

    LIANG JUN / LOU SHUNJIE / WANG WENHAI | European Patent Office | 2023

    Free access

    Traffic prediction method and system based on adaptive hypergraph

    ZHU CHAO / ZHU RUI / LI TONG et al. | European Patent Office | 2023

    Free access

    Transform-fused hypergraph neural network-based high-speed station traffic flow prediction method

    LI LING / LIU NING / SU BO et al. | European Patent Office | 2024

    Free access

    Deep learning traffic flow prediction method based on time perception hypergraph

    HE ZHIXIANG / GONG MENGZAN | European Patent Office | 2024

    Free access

    Equivalent hypergraph construction method for traffic flow prediction

    WANG FENG / CAO YUHANG / ZHANG JIEYIN et al. | European Patent Office | 2025

    Free access