The invention relates to an urban traffic data prediction method based on causal classification depolarization, belongs to the technical field of spatio-temporal data mining, and provides an urban traffic data prediction method based on causal classification depolarization. The influence of urban spatio-temporal data distribution skewness on causal mining is corrected through causal intervention, a spatio-temporal causal relationship hidden in observation data is recovered, a causal graph is learned by adopting priori information such as a spatial proximity relationship and a time position, and a spatio-temporal causal transmission mechanism crossing different time slices is introduced to enhance spatio-temporal causal characterization, so that the causal mining accuracy is improved. Therefore, the accuracy and the robustness of urban traffic data prediction are remarkably improved, and the accuracy, the robustness and the generalization ability of the prediction model are effectively improved.

    本发明涉及一种基于因果分类去偏的城市交通数据预测方法,属于时空数据挖掘技术领域,本发明提出了一种基于因果分类去偏的城市交通数据预测方法,利用空间邻接关系和时间位置,通过因果干预修正城市时空数据分布偏态在因果挖掘上的影响,恢复隐藏在观测数据中的时空因果关系,采纳空间邻近性关系和时间位置等先验信息学习因果图,并引入了跨越不同时间片段的时空因果传递机制,以强化时空因果表征,从而显著提升了城市交通数据预测的精确度与稳健性,有效提升了预测模型的精度、鲁棒性和泛化能力。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Urban traffic data prediction method based on causal classification depolarization


    Weitere Titelangaben:

    一种基于因果分类去偏的城市交通数据预测方法


    Beteiligte:
    HE QIRONG (Autor:in) / DENG PAN (Autor:in) / ZHOU QISHUN (Autor:in) / LIU JUNTING (Autor:in) / ZHAO YU (Autor:in) / YU SHAOHAN (Autor:in) / DU JIALONG (Autor:in)

    Erscheinungsdatum :

    08.04.2025


    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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Urban traffic data prediction method based on space-time causal prediction of continuous learning

    DENG PAN / ZHAO YU / PEI YUNCHANG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Public traffic flow prediction method combining urban interest points and space-time causal relationship

    DENG PAN / LIU YAN / WANG MULAN et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Dynamic traffic bottleneck prediction method based on causal anonymous migration

    CHEN JUN / WANG ZHENGCHENG / HU LIJING et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Granger Causal Inference for Interpretable Traffic Prediction

    Zhang, Lei / Fu, Kaiqun / Ji, Taoran et al. | IEEE | 2022


    A LIDAR-based Traffic Data Classification Framework for Indian Urban Traffic

    J, Prajwal Shettigar / Tangirala, Arun K / Vanajakshi, Lelitha Devi | Springer Verlag | 2025