The invention provides a traffic time prediction model training method, a traffic time prediction method, and equipment. The training method comprises the following steps: constructing intersections and road section features and track features; obtaining a road segment feature vector and an intersection feature vector; inputting an intersection feature matrix, the a road segment feature matrix, an intersection adjacency matrix, and a road segment adjacency matrix corresponding to each preset time step length into an intersection and road segment spatial-temporal feature extraction network according to a time sequence; inputting the outputted and updated intersection feature matrix and road segment feature matrix corresponding to a single preset time step length, and a sequence formed by intersections and road segments in the historical track into a traffic time prediction model, and outputting a prediction result of target traffic time of a route starting in the future preset step length time for training. According to the traffic time prediction model training method, the traffic time prediction method, and the equipment provided by the invention, the traffic time prediction model is trained by jointly modeling the characteristics of the intersections and the road segments, and the accuracy of traffic time prediction is improved.

    本发明提供一种通行时间预测模型训练方法、通行时间预测方法及设备,该训练方法包括:构建路口和路段特征及轨迹特征;获取路段特征向量及路口特征向量;将对应于各个预设时间步长的路口特征矩阵、路段特征矩阵、路口邻接矩阵及路段邻接矩阵按照时序顺序输入到路口和路段时空特征提取网络;将输出的更新后的单个预设时间步长对应的路口特征矩阵和路段特征矩阵、历史轨迹中路口和路段组成的序列输入到通行时间预测模型,输出未来预设步长时间内出发的路线的目标通行时间的预测结果进行训练。本发明提供的通行时间预测模型训练方法、通行时间预测方法及设备,通过联合建模路口和路段的特征,训练通行时间预测模型,提升通行时间预测的准确度。


    Access

    Download


    Export, share and cite



    Title :

    Traffic time prediction model training method, traffic time prediction method, and equipment


    Additional title:

    通行时间预测模型训练方法、通行时间预测方法及设备


    Contributors:
    YAN HUAN (author) / LI YONG (author) / JIN DEPENG (author)

    Publication date :

    2021-12-07


    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 / 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




    Training method of traffic prediction model, traffic prediction method and related equipment

    HU MENGHAO / ZHENG QINGFANG / SHAN QIBEN et al. | European Patent Office | 2025

    Free access

    Traffic flow prediction model training method, traffic flow prediction method, device and equipment

    GU JUNHUA / CHEN CHEN / LEI WEI et al. | European Patent Office | 2023

    Free access

    Training method of traffic situation prediction model, traffic situation prediction method and equipment

    ZHANG LEI / ZHANG WENHU / XU XUEJIE et al. | European Patent Office | 2024

    Free access

    Traffic track prediction model training method, traffic track prediction method and related device

    GAN BING / ZHANG MAOHUA / LIAO RUIYI | European Patent Office | 2024

    Free access