The invention discloses an urban road congestion space-time prediction method based on a graph process neural network. Road network diagram structure information is embedded into a time point process model to form a scale value space-time diagram process neural network model, so that the time point process model not only can capture dependency of events on time, but also can capture remote space correlation information between urban road network congestion events, and therefore, the time point process model can be applied to urban road network congestion events. And meanwhile, by considering the space-time propagation mode of the urban road network congestion event, the traditional graph convolution network is expanded, and a new graph propagation convolution kernel P-GCN for sensing the congestion mode change is formed, so that the graph convolution kernel can sense the congestion mode change, and the generalization ability of a scale value space-time diagram process neural network model is improved. The urban road congestion prediction method has the advantages of improving the accuracy, stability and prediction efficiency of urban road congestion prediction.

    本发明公开了一种基于图过程神经网络的城市道路拥堵时空预测方法。它将路网图结构信息嵌入到时间点过程模型内部,形成标值时空图过程神经网络模型,使时间点过程模型不仅能够捕获事件在时间上的依赖,同时能够捕获城市道路网络拥堵事件之间的远程空间关联信息,同时通过顾及城市道路网络拥堵事件的时空传播模式,对传统的图卷积网络进行扩展,形成新的感知拥堵模式变化的图传播卷积核P‑GCN,使得图卷积核能够感知拥堵模式变化,提升标值时空图过程神经网络模型的泛化能力。本发明具有提升城市道路拥堵预测准确性、稳定性及预测效率的优点。


    Access

    Download


    Export, share and cite



    Title :

    Urban road congestion space-time prediction method based on graph process neural network


    Additional title:

    一种基于图过程神经网络的城市道路拥堵时空预测方法


    Contributors:
    WANG JIANLONG (author) / YI CHONGZHENG (author) / ZHANG LI (author) / WU XUEYU (author) / PENG JUN (author)

    Publication date :

    2023-12-22


    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 / 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



    Road intersection congestion prediction method based on time point process neural network model

    WANG JIANLONG / YI CHONGZHENG / ZHANG LI et al. | European Patent Office | 2023

    Free access

    Urban traffic flow space-time prediction scheme based on graph convolutional neural network

    ZHANG RONGQING / WANG HANQIU / LI BING | European Patent Office | 2021

    Free access


    Urban road network congestion mode recognition method and device based on space-time characteristics, and medium

    XIE JINGCHENG / HE SHANGQIU / LIN WENXIA et al. | European Patent Office | 2021

    Free access