The invention discloses a traffic flow prediction method based on double graph convolution, and belongs to the technical field of traffic flow prediction, and the method comprises the steps: obtaining historical traffic flow data, converting the historical traffic flow data into a space-time diagram and a space-time hypergraph, and carrying out the processing through a DGCM dynamic graph convolution module and a DHGCM dynamic hypergraph convolution module, and then dynamic edge generation is carried out by using the dynamic interaction module, and finally processing is carried out by using the prediction module to obtain a traffic flow prediction result. According to the invention, through the fusion graph convolution module, the hypergraph convolution module and the dynamic interaction module, a multiple space-time graph convolution structure is constructed, the traffic flow model fusing the space-time characteristics is established, and through the hypergraph convolution module, the capability of processing and understanding high-dimensional space-time information of the traffic flow model fusing the space-time characteristics is expanded. And through the dynamic interaction module, the capture of the traffic flow model fusing the spatial and temporal characteristics on the traffic network time and space change sensitivity is enhanced, so that the prediction result of the traffic flow is more accurate.

    本发明公开了一种基于双重图卷积的交通流量预测方法,属于交通流量预测技术领域,包括:获取历史交通流量数据,并转换为时空图和时空超图,分别利用DGCM动态图卷积模块和DHGCM动态超图卷积模块进行处理,然后利用动态交互模块进行动态边生成,最后利用预测模块进行处理,得到交通流量预测结果。本发明通过融合图卷积模块、超图卷积模块以及动态交互模块,构建了多重时空图卷积结构,建立了融合时空特征的交通流量模型,通过超图卷积模块,扩展了融合时空特征的交通流量模型处理和理解高维时空信息的能力,通过动态交互模块,增强了融合时空特征的交通流量模型对交通网络时间和空间变化敏感性的捕捉,使交通流量的预测结果更准确。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method based on double graph convolution


    Additional title:

    基于双重图卷积的交通流量预测方法


    Contributors:
    HUI BO (author) / GONG JING (author) / ZHANG LIZONG (author) / LU GUANGXI (author) / LIU GUIJUN (author)

    Publication date :

    2024-09-03


    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



    Double-end graph convolution traffic flow prediction method with graph learning

    REN QIANQIAN / LI ZILONG / ZHANG YANG et al. | European Patent Office | 2023

    Free access

    Traffic flow prediction method based on graph attention convolution network

    ZHENG HONG / ZHANG SIKAI / LIU JIAMOU et al. | European Patent Office | 2020

    Free access

    Regional bridge group traffic flow prediction method based on full connection graph and double convolution

    SHI PENG / ZHANG AIDONG / LIU LUQI et al. | European Patent Office | 2025

    Free access

    Traffic prediction method based on dynamic graph convolution

    FAN JIN / WENG WENCHAO / TIAN HAO et al. | European Patent Office | 2023

    Free access

    Dynamic graph convolution traffic speed prediction method

    LIU QILIANG / YUAN HAOTAO / YANG LIU et al. | European Patent Office | 2020

    Free access