The invention discloses a traffic prediction method based on a continuous evolution graph neural controlled differential equation, and the method comprises the following steps: carrying out the preprocessing of a given traffic data sequence, and constructing a training sample; the method comprises the following steps: constructing a traffic prediction model, generating a randomly initialized node embedding and time continuous control path, generating a spatial dependency evolution component based on the control path, generating a spatial dependency static component based on node embedding, and fusing the two components to obtain a continuous evolution diagram. Constructing a graph nerve controlled differential equation based on the continuous evolution graph, and solving to obtain a traffic data predicted value; training a traffic prediction model by using the training sample; and performing traffic prediction by using the trained traffic prediction model. According to the method, continuous time dependence of traffic data and spatial dependence continuously evolved along with time can be captured at the same time, the traffic prediction precision is effectively improved, and the method has wide application prospects in the fields of logistics transportation, smart cities, intelligent traffic systems and the like.

    本发明公开了一种基于连续演化图神经受控微分方程的交通预测方法,包括以下步骤:对给定的交通数据序列进行预处理,构建训练样本;构建交通预测模型,生成随机初始化的节点嵌入和时间上连续的控制路径,基于控制路径生成空间依赖演化分量,基于节点嵌入生成空间依赖静态分量,将两个分量融合得到连续演化图,基于连续演化图构建图神经受控微分方程并求解得到交通数据预测值;利用训练样本对交通预测模型进行训练;利用训练好的交通预测模型进行交通预测。本发明方法能够同时捕获交通数据连续的时间依赖和随时间连续演化的空间依赖,有效提升交通预测精度,在物流运输、智慧城市和智能交通系统等领域具有广阔的应用前景。


    Access

    Download


    Export, share and cite



    Title :

    Traffic prediction method based on continuous evolution graph neural controlled differential equation


    Additional title:

    一种基于连续演化图神经受控微分方程的交通预测方法


    Contributors:
    CHEN LING (author) / WU JIAJIA (author)

    Publication date :

    2024-02-13


    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



    Accidental traffic anomaly detection method based on fusion graph convolution gated neural differential equation

    ZANG DI / ZHAO JIAYI / LONG BAICHAO et al. | European Patent Office | 2024

    Free access

    Traffic prediction method based on graph neural network

    XUE QINGYAO / WANG BONING / LIU YUFENG et al. | European Patent Office | 2024

    Free access

    Traffic flow prediction method and device based on dynamic ordinary differential graph neural network

    DU SHENGDONG / YANG TAO / HU JIE et al. | European Patent Office | 2024

    Free access

    Traffic flow prediction method based on graph neural network

    PENG LAIHU / WU BAOWEN / QI YUBAO et al. | European Patent Office | 2024

    Free access

    SDN traffic prediction method based on graph neural network

    LI GUOYAN / SHANG YIHUI / JU HAO et al. | European Patent Office | 2024

    Free access