The invention provides a traffic flow prediction method and system for an attention space-time synchronization graph convolutional network, and the method comprises the steps: constructing a graph network, and converting a space-time network prediction problem into a mapping function which is used for predicting future data according to historical data; on the basis of the graph network and the mapping function, a traffic flow prediction model of the attention space-time synchronization graph convolutional network is constructed, and the traffic flow prediction model comprises a plurality of stacked space-time hybrid synchronization layers and is used for capturing complex long-term and short-term space-time correlation through circulation and sending the complex long-term and short-term space-time correlation to a full-connection layer so as to output a prediction result; wherein the time-space hybrid synchronization layer comprises two graph convolutional network layers and an attention time-space synchronization module, and each time-space hybrid synchronization layer performs feature embedding on time and space. The method can effectively capture the spatial-temporal correlation of dynamic changes in the traffic network, enhances the transmission of road network node information, and improves the accuracy and robustness of traffic flow prediction.

    本发明提供一种注意力时空同步图卷积网络的交通流量预测方法及系统,包括:构建图网络,并将时空网络预测问题转化为映射函数,映射函数用于根据历史数据预测未来数据;基于图网络和映射函数,构建注意力时空同步图卷积网络的交通流量预测模型,交通流量预测模型包括有多个堆叠的时空混合同步层,用于通过循环捕获复杂长短期时空相关性,并送入全连接层,以输出预测结果;其中,时空混合同步层包括两个图卷积网络层和一个注意力时空同步模块,每层所述时空混合同步层分别对时间和空间进行特征嵌入。本发明能够有效捕捉交通网络中动态变化的时空相关性,增强路网节点信息的传递,提高交通流量预测的准确性和鲁棒性。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow prediction method and system of attention time-space synchronization graph convolutional network


    Additional title:

    注意力时空同步图卷积网络的交通流量预测方法及系统


    Contributors:
    XIA DAWEN (author) / WEI XIAODUO (author) / LI HUAQING (author) / TANG HANLIN (author) / LIU HAITAO (author) / WANG ZIQIANG (author) / AO YUCE (author) / ZHANG WENYONG (author) / XU HAILONG (author) / DENG LI (author)

    Publication date :

    2023-12-29


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS




    Traffic flow prediction method and system based on time-space synchronization dynamic graph attention network

    XIA DAWEN / LIN ZHAN / LI HUAQING et al. | European Patent Office | 2024

    Free access

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

    CHEN YAJUN / DING ZHIMING / GUO LIMIN | European Patent Office | 2023

    Free access

    Traffic flow prediction method based on time attention circulation graph convolutional neural network

    FAN WENDONG / SHU MIN / SONG YUN et al. | European Patent Office | 2023

    Free access