The invention discloses a traffic road network abnormal situation spatio-temporal evolution method fused with causal inference, which comprises the following steps: acquiring multi-source traffic road network data, screening characteristic variables based on spatio-temporal association and causal effect of a traffic road network, and constructing a data set; constructing an anti-fact graph attention network model based on an encoder and decoder structure; and training the anti-fact graph attention network model by using the data set, inputting to-be-detected traffic road network data into the trained anti-fact graph attention network model, and obtaining an abnormal situation detection recognition result and a time-space evolution situation of the traffic road network. According to the method, causal inference and space-time correlation are combined, an anti-fact graph attention network model is constructed, the change of traffic network data can be responded in time, the abnormal situation is monitored and recognized in real time, the accuracy, reliability and real-time performance of traffic network abnormal situation detection are improved, and the traffic network abnormal situation detection efficiency is improved. And better support and guarantee are provided for formulating and implementing a traffic management emergency response scheme.

    本发明公开了一种融合因果推断的交通路网异常态势时空演化方法,包括:获取多源交通路网数据,基于交通路网的时空关联和因果效应,筛选特征变量,构建数据集;基于编码器和解码器结构,构建反事实图注意力网络模型;利用数据集对反事实图注意力网络模型进行训练,将待检测的交通路网数据输入训练好的反事实图注意力网络模型,获得交通路网的异常态势检测识别结果及时空演化情形。该方法结合了因果推断和时空关联,构建反事实图注意力网络模型,其可以及时响应交通路网数据的变化,对异常态势进行实时监测和识别,其提高了交通路网异常态势检测的精确度、可靠性和实时性,为交通管理应急响应方案的制定及实施带来了更好的支持与保障。


    Access

    Download


    Export, share and cite



    Title :

    Traffic network abnormal situation spatio-temporal evolution method fusing causal inference


    Additional title:

    一种融合因果推断的交通路网异常态势时空演化方法


    Contributors:
    MA XIAOLEI (author) / LI TIANQI (author) / TAN ERLONG (author) / CUI ZHIYONG (author)

    Publication date :

    2024-06-14


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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





    Traffic abnormal flow causal detection method and device

    SONG XUAN / GAO HAOTIAN / FAN ZIPEI et al. | European Patent Office | 2023

    Free access

    Spatio-Temporal Evolution of Traffic Congestions on Urban Freeways

    Chen, X. / Li, R. / Lu, H. et al. | British Library Conference Proceedings | 2009


    Spatio-Temporal Evolution of Traffic Congestions on Urban Freeways

    Chen, Xiqun / Li, Ruimin / Lu, Huapu et al. | ASCE | 2009