The invention discloses a traffic flow prediction method based on an interactive dynamic diffusion diagram convolutional network, the interactive dynamic diffusion diagram convolutional network comprises a space-time interaction dynamic diagram generator, a stacked space-time block, a jump connection and a multi-layer perceptron, and traffic data is input into the space-time interaction dynamic diagram generator; the method comprises the following steps of: acquiring heterogeneous space-time correlation of traffic data, generating a space-time dynamic graph, inputting the traffic data and the space-time dynamic graph into stacked space-time blocks to acquire time and space characteristics in a traffic network, converging the time and space characteristics acquired by each space-time block through jump connection, and then acquiring the time and space characteristics in the traffic network through a multi-layer sensor. And obtaining a prediction result. The heterogeneous spatial-temporal correlation of the traffic sequence is extracted, the periodicity of the traffic network is captured when the spatial features of the traffic sequence are extracted, the graph structure of the traffic network is dynamically updated, and traffic flow prediction can be more accurately carried out.

    本发明公开了一种基于交互式动态扩散图卷积网络的交通流量预测方法,所述交互式动态扩散图卷积网络包括时空交互动态图生成器、堆叠的时空快、跳跃连接和多层感知器,将交通数据输入时空交互动态图生成器,以捕获交通数据的异质时空相关性,生成时空动态图,将交通数据和时空动态图输入堆叠的时空块,以捕获交通网络中的时间和空间特征,最后将各个时空块捕获的时间和空间特征通过跳跃连接进行汇聚,然后通过多层感知器,得到预测结果。本发明提取出交通序列的异质时空相关性,并在提取交通序列的空间特征时捕获到交通网络的周期性,并动态更新交通网络的图结构,能够更加准确地进行交通流量预测。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method based on interactive dynamic diffusion diagram convolutional network


    Additional title:

    一种基于交互式动态扩散图卷积网络的交通流量预测方法


    Contributors:
    ZHANG SHUAI (author) / YU WANGZHI (author) / PENG QIFAN (author) / WU CHENHAO (author) / LEE HAE KWANG (author) / ZHA LI (author) / ZHANG WENYU (author) / ZHANG YIXIANG (author) / JING XIN (author)

    Publication date :

    2024-07-26


    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 based on interactive adaptive space-time diagram convolutional network

    SHI QUAN / CAO CHENYANG / BAO YINXIN et al. | European Patent Office | 2024

    Free access

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

    JIANG CONG / SONG YUN / DENG ZELIN et al. | European Patent Office | 2023

    Free access

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

    JIANG YUNLIANG / XIA RENHUAN / ZHANG XIONGTAO et al. | European Patent Office | 2022

    Free access

    Traffic flow prediction method of space-time diagram convolutional network

    TENG FEI / WANG ZIDAN / QIAO LU et al. | European Patent Office | 2024

    Free access

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

    SHI QUAN / DAI JUNMING / SHEN QINQIN et al. | European Patent Office | 2021

    Free access