The invention discloses a travel time prediction method based on a dynamic Bayesian network, and provides an explanatory travel time prediction method with high precision and good reliability by comprehensively analyzing a road network traffic state space-time association relationship and constructing the dynamic Bayesian network through a transition probability, a conditional probability of an observation value and an initial state. The method is oriented to urban traffic roads, the traffic operation state incidence relation is mined based on network connection vehicle data, the complex dependency relation between the dynamic Bayesian network representation hidden variable and the travel time observation value is established, and the purpose of accurately predicting the travel time in real time is achieved. The technical scheme is as follows: 1) representing a road traffic network state; 2) analyzing traffic state spatial correlation; 3) analyzing traffic state time correlation; 4) establishing a road network state dynamic equation; 5) establishing a travel time observation model; 6) establishing a travel time prediction model based on the dynamic Bayesian network; and 7) evaluating the travel time prediction effect.

    本发明公开了一种基于动态贝叶斯网络的行程时间预测方法,综合分析道路网络交通状态时空关联关系,通过转换概率、观测值的条件概率和初始状态构建动态贝叶斯网络,提供一种精度高、可靠性好的解释性行程时间预测方法。本方法面向城市交通道路,基于网联车辆数据挖掘交通运行状态关联关系,建立动态贝叶斯网络表征隐藏变量和行程时间观测值之间复杂依赖关系,达到行程时间实时、准确预测的目的。技术方案为:1)表征道路交通网络状态;2)解析交通状态空间相关性;3)解析交通状态时间相关性;4)建立路网状态动态性方程;5)建立行程时间观测模型;6)建立基于动态贝叶斯网络的行程时间预测模型;7)行程时间预测效果评价。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Travel time prediction method based on dynamic Bayesian network


    Weitere Titelangaben:

    一种基于动态贝叶斯网络的行程时间预测方法


    Beteiligte:
    CHEN PENG (Autor:in) / WANG QIAOJIA (Autor:in)

    Erscheinungsdatum :

    18.04.2023


    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



    Bayesian Combination of Travel Time Prediction Models

    van Hinsbergen, C. P. IJ. / van Lint, J. W. C. | Transportation Research Record | 2008


    TRAVEL TIME PREDICTION PROGRAM, TRAVEL TIME PREDICTION DEVICE, AND TRAVEL TIME PREDICTION METHOD

    NISHIMURA SHIGEKI | Europäisches Patentamt | 2018

    Freier Zugriff


    Estimating Travel Time Distributions by Bayesian Network Inference

    Prokhorchuk, Anatolii / Dauwels, Justin / Jaillet, Patrick | IEEE | 2020


    TRAVEL TIME PREDICTION METHOD, TRAVEL TIME PREDICTION DEVICE, AND PROGRAM

    SHINAGAWA AKIO / TAMAI KYOHEI / IKEDA YUICHI | Europäisches Patentamt | 2016

    Freier Zugriff