The invention discloses a traffic flow spatio-temporal data prediction method, system and device and a medium, and belongs to the field of spatio-temporal data prediction. According to the method, a space-time diagram neural network is used for modeling a dynamic space relationship of traffic flow data of a plurality of sensors, and the problem that the dynamic space relationship cannot be modeled in an existing method is solved; the method comprises the following steps: modeling a time dependency relationship of traffic flow data by using a two-layer neural random partial differential equation, modeling noise explicitly, and simultaneously extracting a time domain and features of the time domain by solving an ordinary differential equation in a frequency domain during simplification; three kinds of information including the dynamic space relation, the time domain features and the time domain features are fused, and the prediction accuracy of the traffic flow can be effectively improved.

    本发明公开一种交通流量时空数据预测方法、系统、设备及介质,属于时空数据预测领域。该方法使用时空图神经网络建模多个传感器的交通流量数据的动态空间关系,克服了现有方法无法建模动态空间关系的问题;利用两层神经随机偏微分方程建模交通流量数据的时间依赖关系,将噪声显式得建模出来,并在化简时,通过求解频域中的常微分方程,从而同时提取时域和时域的特征;融合动态空间关系、时域特征和时域特征三种信息,能够有效提高交通流量的预测准确率。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow spatio-temporal data prediction method, system, device and medium


    Weitere Titelangaben:

    一种交通流量时空数据预测方法、系统、设备及介质


    Beteiligte:
    XIA YUANQING (Autor:in) / YAN TIJIN (Autor:in) / GONG HENGHENG (Autor:in) / ZHAN YUFENG (Autor:in) / DAI LI (Autor:in) / SUN ZHONGQI (Autor:in) / ZHAI DIHUA (Autor:in) / GUO ZEHUA (Autor:in) / WU CHUGE (Autor:in) / LI YIRAN (Autor:in)

    Erscheinungsdatum :

    2023-08-15


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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



    Traffic flow prediction method for multivariate traffic flow spatio-temporal data information

    LI LIN / CHEN HAOJI / CHEN KANG et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Spatio-Temporal AutoEncoder for Traffic Flow Prediction

    Liu, Mingzhe / Zhu, Tongyu / Ye, Junchen et al. | IEEE | 2023


    Traffic flow prediction method and device fusing multi-source spatio-temporal data, and storage medium

    DENG XINGDONG / LI GUANYAO / LIU YANG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic flow prediction method based on spatio-temporal information fusion and storage medium

    ZOU TINGTING / LYU WENXIU / LIU XIANGYU | Europäisches Patentamt | 2024

    Freier Zugriff

    Global spatio‐temporal dynamic capturing network‐based traffic flow prediction

    Haoran Sun / Yanling Wei / Xueliang Huang et al. | DOAJ | 2023

    Freier Zugriff