The invention discloses a multi-view fusion spatial-temporal dynamic graph convolutional network traffic flow prediction method, which comprises the following steps of: starting from spatial relevance and time sequence similarity, comprehensively mining multivariate spatial relevance among road network nodes, capturing a dependency relationship between local spatial structure and global spatial relevance in the road network nodes, and predicting the traffic flow of the road network nodes according to the dependency relationship between the local spatial structure and the global spatial relevance. Firstly, historical traffic flow data is used as input, and a spatial embedding matrix and a time embedding matrix are added into a traffic flow sequence. Secondly, inputting the processed historical traffic flow sequence into an encoder comprising a time local convolution multi-head self-attention module and a spatial multi-view dynamic graph convolution module, and extracting spatial-temporal characteristics through the encoder; and finally, the historical traffic flow sequence containing the spatial embedding matrix and the time embedding matrix and the output of the encoder are input into a decoder to generate future traffic flow data, so that accurate flow prediction under various time windows is realized, and the accuracy of urban traffic flow prediction is improved.

    本发明公开了一种多视角融合的时空动态图卷积网络交通流量预测方法,该方法从空间关联性与时序相似性出发,全面地挖掘路网节点之间多元的空间关联,捕捉路网节点中局部空间结构和全局空间相关性之间的依赖关系,首先使用历史的交通流量数据作为输入,将空间嵌入矩阵和时间嵌入矩阵添加至交通流量序列之中。其次将处理后的历史交通流量序列输入包含时间局部卷积多头自注意力模块和空间多视角动态图卷积模块编码器,通过编码器提取时空特征。最后将包含空间嵌入矩阵和时间嵌入矩阵的历史交通流量序列和编码器的输出,输入解码器生成未来的交通流量数据,实现了在多种时间窗口下的准确流量预测,提高了城市交通流量预测的准确性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Multi-view fusion space-time dynamic graph convolutional network urban traffic flow prediction method


    Weitere Titelangaben:

    多视角融合的时空动态图卷积网络城市交通流量预测方法


    Beteiligte:
    YUAN GUAN (Autor:in) / ZHAO WENZHU (Autor:in) / ZHANG YANMEI (Autor:in) / ZHOU YONG (Autor:in) / NIU QIANG (Autor:in)

    Erscheinungsdatum :

    2023-10-24


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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 based on multi-view dynamic graph convolutional network

    HUANG XIAOHUI / YE YUMING / LING JIAHAO et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Traffic flow prediction method of space-time attention graph convolutional network based on multi-feature fusion

    CHEN YAJUN / DING ZHIMING / GUO LIMIN | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method based on multi-view space-time diagram convolutional network

    GU JUNHUA / JI ZHENLEI / ZHANG YAJUAN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Multibranch Adaptive Fusion Graph Convolutional Network for Traffic Flow Prediction

    Xin Zan / Jasmine Siu Lee Lam | DOAJ | 2023

    Freier Zugriff

    Traffic flow prediction method based on space-time complex graph convolutional network

    SHI QUAN / BAO YINXIN / SHEN QINQIN et al. | Europäisches Patentamt | 2022

    Freier Zugriff