The invention discloses a dynamic graph structure attention mechanism short-time traffic flow prediction method, and relates to the technical field of intelligent traffic, and the method comprises the steps: taking a sensor on a traffic road section as a node, taking a road section connected with the sensor as an edge, and carrying out the pre-modeling of a traffic map, and obtaining the traffic map; constructing a dynamic graph structure attention mechanism short-term traffic flow prediction model; inputting traffic flow data in the traffic map into the dynamic graph structure attention mechanism short-term traffic flow prediction model, and performing back propagation through a graph neural network to learn traffic flow features; inputting traffic flow data in a traffic map of a to-be-predicted area into the trained dynamic graph structure attention mechanism short-term traffic flow prediction model to obtain a short-term traffic flow prediction result; in a comprehensive view, the traffic flow prediction accuracy is improved by extracting the time features and the space features of the traffic and then continuously updating the traffic map, so that traffic emergencies are added in the flow prediction.

    本发明公开了一种动态图结构注意力机制短时交通流预测方法,涉及智能交通技术领域,本发明包括将交通路段的上的传感器作为节点,传感器与传感器相连的路段作为边对交通图进行预建模,获得交通图;构建动态图结构注意力机制短时交通流预测模型;将交通图中的交通流数据输入动态图结构注意力机制短时交通流预测模型,通过图神经网络进行反向传播学习交通流特征;将待预测区域的交通图中的交通流数据输入训练后的动态图结构注意力机制短时交通流预测模型,获得短时交通流预测结果;综合来看,本发明通过提取交通的时间特征,和空间特征,然后不断更新交通图,从而在流量预测中加入交通突发事件,来提高交通流预测的准确性。


    Access

    Download


    Export, share and cite



    Title :

    Dynamic graph structure attention mechanism short-term traffic flow prediction method


    Additional title:

    一种动态图结构注意力机制短时交通流预测方法


    Contributors:
    LOU JUNGANG (author) / WU XUHONG (author) / SHEN QING (author) / ZHAO KANG (author)

    Publication date :

    2023-12-22


    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



    Fusion attention mechanism bidirectional LSTM for short-term traffic flow prediction

    Li, Zhihong / Xu, Han / Gao, Xiuli et al. | Taylor & Francis Verlag | 2024




    Traffic flow short-term prediction method

    XIAO HONGBO / XIAO JIANHUA / PENG XIAONING et al. | European Patent Office | 2024

    Free access

    Attention mechanism‐based model for short‐term bus traffic passenger volume prediction

    Zhenyu Mei / Wanting Yu / Wei Tang et al. | DOAJ | 2023

    Free access