The invention provides an in-out station traffic flow collaborative prediction method and system for an expressway toll station, and belongs to the technical field of traffic flow prediction, and the method comprises the steps: obtaining the historical in-out station traffic flow data and the in-out station traffic flow data before festivals and holidays of the expressway toll station in a to-be-detected region; on the basis of the obtained historical inbound and outbound traffic flow data of the holidays and festivals and the obtained pre-holiday inbound and outbound traffic flow data, time sequence augmentation matrixes of inbound and outbound traffic flows of the holidays and festivals are constructed respectively; based on the obtained time sequence augmentation matrix of the incoming and outgoing traffic flows, obtaining an incoming and outgoing traffic flow collaborative prediction result through a pre-trained traffic flow collaborative prediction model based on a space-time attention interaction network; the problems that a traditional prediction method is low in prediction precision due to the fact that a traditional method cannot adapt to uncertainty and burstiness of traffic flow in an abnormal scene, and a traditional prediction model based on deep learning only considers short-time prediction, and the total prediction time span is small are effectively solved.

    本发明提供了用于高速公路收费站的进出站交通流协同预测方法及系统,其属于交通流预测技术领域,包括:获取待测区域高速公路收费站节假日历史进出站交通流数据和节前进出站交通流数据;基于获得的节假日历史进出站交通流数据和节前进出站交通流数据,分别构建节假日进站和出站交通流的时间序列增广矩阵;基于获得的进站和出站交通流的时间序列增广矩阵,通过预先训练的基于时空注意力交互网络的交通流协同预测模型,获得进出站交通流协同预测结果;有效解决了传统方法无法适应非常态场景下交通流的不确定性和突发性,导致传统预测方法的预测精度较低,以及传统基于深度学习的预测模型仅考虑短时预测,预测总时间跨度较小的问题。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Collaborative prediction method and system for entry and exit traffic flow of highway toll station


    Weitere Titelangaben:

    用于高速公路收费站的进出站交通流协同预测方法及系统


    Beteiligte:
    ZHANG YUNFAN (Autor:in) / CHAI QINGGANG (Autor:in) / DING XIAO'E (Autor:in) / XU RUN (Autor:in) / HAN ZHONGYI (Autor:in) / LYU MENGQI (Autor:in) / WANG CHENGCHENG (Autor:in) / WANG CHAO (Autor:in)

    Erscheinungsdatum :

    28.03.2025


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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



    Road section main line toll station exit traffic jam prediction method and system

    YANG TONG / ZHANG YUN / XIANG PENGCHENG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Method and system for inducing vehicles at exit of highway ramp toll station

    PENG BAIYAO / ZHANG LEXING / LI ENKAI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Highway unmanned toll station toll guidance system

    WANG XIAOBO / ZHAO CONG / CHEN JIN | Europäisches Patentamt | 2024

    Freier Zugriff