The invention discloses an urban main road speed prediction method based on big data and deep learning. The method comprises the following steps: calling an Amap API (Application Program Interface) to collect urban main road map data; collecting vehicle latitude and longitude coordinates and vehicle speed data in a vehicle-mounted GPS device (a new energy vehicle slave TBOX device), and performing road matching on each vehicle; calculating road average passing speed according to a road matching result, and establishing a road passing speed characteristic matrix by taking the road average passing speed as a characteristic; expanding a time dimension to create a road space-time passing speed characteristic matrix; utilizing a convolutional neural network model to extract road space-time passing speed features, and training the model to achieve main road passing speed prediction in a short time in the future. According to the road speed prediction method, few vehicle data features are needed, road matching is achieved through latitude and longitude coordinates, and vector operation is reduced; the road passing speed is calculated by using the vehicle speed, and the prediction model considers the relevance between time and space, so that the prediction accuracy and reliability are improved.

    本发明公开了一种基于大数据和深度学习的城市主干道路速度预测方法。本发明调用高德地图API收集城市主干道路地图数据;收集车载GPS设备(新能源汽车从TBOX装置)中的车辆经纬度坐标和车辆速度数据,对每辆车进行道路匹配;根据道路匹配结果计算道路平均通行速度,并以此为特征建立道路通行速度特征矩阵;拓展时间维度创建道路时空通行速度特征矩阵;利用卷积神经网络模型提取道路时空通行速度特征,通过对该模型的训练实现未来短时间内主干道路通行速度预测。本发明的道路速度预测方法所需要的车辆数据特征少,利用经纬度坐标实现道路匹配,减少矢量运算;利用车速计算道路通行速度,且预测模型考虑了时间与空间的关联性,提高了预测准确性和可靠性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Urban main road speed prediction method based on big data and deep learning


    Weitere Titelangaben:

    一种基于大数据和深度学习的城市主干道路速度预测方法


    Beteiligte:
    ZHONG JIE (Autor:in) / WANG LEI (Autor:in) / HUANG CHAO (Autor:in)

    Erscheinungsdatum :

    2021-06-11


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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



    Urban road traffic state prediction system based on deep learning

    HAO WEI / YI KEFU / GAO ZHIBO et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Urban road vehicle speed prediction method

    FAN ZIDE / HUANG FEILONG / SUN YI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Urban-Road Average-Speed Prediction Method Based on Graph Convolutional Networks

    Wang, Xuemei / Chen, Ying / Zhang, Jinlei | Transportation Research Record | 2023


    Urban road traffic flow prediction method and device based on space-time deep learning model

    JIA TAO / YAN PENGGAO | Europäisches Patentamt | 2020

    Freier Zugriff