The invention discloses a channel operation state deduction prediction method based on multi-source information deep fusion, and the method comprises the steps: processing data collected by a geomagnetic detector disposed at a road segment, and generating the road segment flow and speed information of a node of the road segment; performing data preprocessing on the floating car data on the road section; preprocessing information of meteorological and geological disasters; constructing a dynamic graph neural network according to the characteristics of the geomagnetic detector and the floating car data, and capturing the time and space characteristics of the traffic data; a knowledge graph is constructed according to information of weather and address disasters, and features of a channel extreme environment are represented; and coding the knowledge graph, inputting the coded knowledge graph into the graph neural network model, and predicting an index representing a channel operation state. According to the method, a multi-source data fusion method is applied to characterize and deduce and predict the traffic situation of the hidden channel, and a methodology is provided for researching a traffic comprehensive emergency guarantee technology under extreme environment complex disasters.

    本发明公开了一种基于多源信息深度融合的通道运行状态推演预测方法,包括:对路段部署的地磁检测器采集的数据进行处理,生成该路段节点的路段流量、速度信息;对路段上的浮动车数据进行数据预处理;对气象、地质灾害的信息进行预处理;根据地磁检测器以及浮动车数据的特征构建动态图神经网络,捕捉交通数据的时间、空间特征;根据气象、地址灾害的信息构建知识图谱,表征通道极端环境的特征;将知识图谱进行编码,输入图神经网络模型中,对表征通道运行状态的指标进行预测。本发明通过运用多源数据融合的方法,对进藏通道的交通态势进行表征并进行推演预测,对于研究极端环境复杂灾害下交通综合应急保障技术提供了方法论。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Channel operation state deduction prediction method based on multi-source information deep fusion


    Weitere Titelangaben:

    一种基于多源信息深度融合的通道运行状态推演预测方法


    Beteiligte:
    ZHOU XIAOJING (Autor:in) / ZHU WENKAI (Autor:in) / LI XU (Autor:in)

    Erscheinungsdatum :

    13.02.2024


    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



    Method and device for multi-train operation trend deduction

    WANG RONGSHENG / ZHANG QI / YUAN ZHIMING et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Regional road network vehicle path reconstruction deduction method and system based on multi-source data fusion

    ZHUANG LIJIAN / QIN JINQING / AN RU et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    METHOD AND DEVICE FOR MULTI-TRAIN OPERATION TREND DEDUCTION

    WANG RONGSHENG / ZHANG QI / YUAN ZHIMING et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Parking lot advanced prediction method based on multi-source information fusion

    CHEN XINGWEN / RAO LIUWEI / LIU YAN | Europäisches Patentamt | 2024

    Freier Zugriff

    Traffic operation state monitoring method and device based on multi-source data fusion

    JIANG WEIHAO / YE SAIMIN | Europäisches Patentamt | 2022

    Freier Zugriff