The invention belongs to the technical field of intelligent transportation and relates to a traffic road event prediction method based on graph embedding. The method comprises the following steps: acquiring speed data and related attribute data of a road with historical traffic events in a specified time period; carrying out data fusion after normalization processing; then, establishing a graph embedding model based on a GraphSAGE graph embedding algorithm for training to obtain an embedding vector of a road, and carrying out dimensionality reduction; taking dimension-reduced data as sample points; fitting a probability density model; and finally, normalizing and fusing the speed data and the related attribute data of the road of which the traffic event needs to be predicted in the specified time period, obtaining the embedded vector of the road through the trained graph embedding model, performing dimensionality reduction, inputting data subjected to dimensionality reduction into thefitted probability density model, obtaining a probability value required to be predicted, and performing visual display. A urban traffic management decision of urban managers is facilitated, a trafficoperation order is kept stable, urban traffic pressure is relieved, and urban residents can go out more conveniently.

    本发明属于智能交通技术领域,涉及一种基于图嵌入的交通道路事件预测方法,首先获取历史发生交通事件的道路指定时段的速度数据和相关属性数据,归一化处理后进行数据融合,然后建立基于GraphSAGE图嵌入算法的图嵌入模型进行训练以获得道路的嵌入向量并进行降维,再将降维的数据作为样本点,拟合概率密度模型,最后将需要预测交通事件的道路在指定时段的速度数据和相关属性数据进行归一化处理和融合,经训练好的图嵌入模型获得道路的嵌入向量并降维,降维后的数据输入到拟合好的概率密度模型中,获得需要预测的概率值并进行可视化展示。本发明有利于城市管理者对于城市交通的管理决策,维持交通运行秩序稳定,缓解城市交通压力,让城市居民出行更加便捷。


    Access

    Download


    Export, share and cite



    Title :

    Traffic road event prediction method based on graph embedding


    Additional title:

    一种基于图嵌入的交通道路事件预测方法


    Contributors:
    WU XIANGPING (author) / PING LIJUN (author) / XU DONGSHI (author)

    Publication date :

    2020-10-13


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / 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 / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Multi-source data-based traffic event road network traffic capacity attenuation prediction method

    HAN ZHIYUE / WU YITAO / WANG LING et al. | European Patent Office | 2025

    Free access

    Traffic flow prediction method and system based on directed graph spatio-temporal information embedding

    RUI YIKANG / WU GUANWEN / ZHAO YAN et al. | European Patent Office | 2024

    Free access

    Road traffic state prediction method and device based on graph attention network

    LEI TIAN / DING YUXIN / GONG LEI et al. | European Patent Office | 2025

    Free access


    Road traffic safety prediction method based on dynamic graph attention space-time network

    JIA ZHAOHONG / YUAN JIE / YANG BO | European Patent Office | 2024

    Free access