The invention provides a DGCN-based travel time prediction method, and the method comprises the following steps: S1, building a travel time prediction model based on a dynamic graph convolutional network model, sampling the nearest 15 min, 30 min and 60 min data of each day, and sampling the nearest traffic while reducing the data dimensions of features; s2, in order to establish a dynamic spatial relationship of the traffic road network, estimating an adjacent matrix of the current neighbor time of the road network by adopting an attention mechanism; lSTM is adopted to learn time correlation, and internal correlation between sequences of an adjacent matrix Ld is explored; according to the method, a route recommendation model based on travel time prediction and congestion area avoidance is provided, the road section travel time of the urban road network is subjected to short-time prediction by using the dynamic graph neural network based on historical gate data and a road network topological structure, and the travel time can be predicted by combining the road network dynamic actual condition and the flow characteristics, so that the road network travel time prediction efficiency is improved. The congestion degree of the congested road section is relieved, shortest path recommendation is provided for travelers, and the experience feeling is improved.

    本发明提供了基于DGCN的行程时间预测方法,包括以下步骤:S1:建立以动态图卷积网络模型为主的行程时间预测模型,对每天最近邻15min、30min、60min的数据进行采样,在减少特征的数据维度的同时对最近的交通进行采样;S2:为建立动态的交通路网的空间关系,采用注意力机制对路网当前近邻时间的邻接矩阵进行估计;采用LSTM来学习时间相关,探索邻接矩阵Ld的序列之间的内在关联;本发明提出基于行程时间预测及拥堵区避让的路径推荐模型,基于历史卡口数据和路网拓扑结构,使用动态图神经网络对城市路网的路段行程时间进行短时预测,并通过结合路网动态实际状况和流量特征,能够预测行程时间,减缓拥堵路段的拥堵程度,对出行者提供最短路径推荐,提高体验感。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    DGCN-based travel time prediction method


    Weitere Titelangaben:

    基于DGCN的行程时间预测方法


    Beteiligte:
    XING XUE (Autor:in) / LI XIAOYU (Autor:in) / ZHAI YAQI (Autor:in) / MU TIAN'AO (Autor:in) / WANG BIN (Autor:in) / WANG FEI (Autor:in)

    Erscheinungsdatum :

    2022-11-29


    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



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

    NISHIMURA SHIGEKI | Europäisches Patentamt | 2018

    Freier Zugriff

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

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

    Freier Zugriff

    Travel Time Prediction

    Wang, Jianwei / Zou, Nan / Chang, Gang-Len | Transportation Research Record | 2008



    Travel time prediction method and system

    YUAN YITAO / LI CHANGLIANG / XIE WEN | Europäisches Patentamt | 2022

    Freier Zugriff