The invention discloses a road intersection congestion prediction method based on a time point process neural network model. The method comprises the following steps: firstly, in a spatial correlation modeling process, constructing a spatial correlation module by fusing spatial region congestion change modes of a plurality of intersections to a single intersection level; secondly, in the dual-granularity time correlation modeling process, the time granularity of a congestion event is captured through a time point process and further integrated with a gating circulation network unit, a new neural point process gating circulation unit is constructed, modeling is conducted on congestion under different time granularities through the new neural point process gating circulation unit, and the time granularities of the congestion event are obtained; a dual-granularity time correlation module is obtained; and finally, based on the sequence, obtaining a sequence architecture and a space-time correlation module, establishing a space-time point process neural network model, performing parameter optimization, and realizing multi-step prediction of the congestion event. The method provided by the invention has the advantage of high prediction precision aiming at the refined congestion event prediction between the urban intersection lanes and in the signal period.

    本发明公开了一种基于时间点过程神经网络模型的道路交叉口拥堵预测方法。它包括如下步骤,首先,在空间关联建模过程中,通过将多个交叉口的空间区域拥堵变化模式融合到单个交叉口级,构建空间关联模块;其次,在双粒度时间关联建模过程中,通过时间点过程捕获拥堵事件时间粒度,并进一步与门控循环网络单元集成、构建新的神经点过程门控循环单元,通过新的神经点过程门控循环单元,分别对拥堵在不同时间粒度下建模,得到双粒度时间关联模块;最后,基于序列得到序列架构和时空关联模块建立时空点过程神经网络模型,进行参数优化,实现拥堵事件的多步预测。本发明具有针对精细化的城市交叉口车道间、信号周期内拥堵事件预测,预测精度高的优点。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Road intersection congestion prediction method based on time point process neural network model


    Weitere Titelangaben:

    基于时间点过程神经网络模型的道路交叉口拥堵预测方法


    Beteiligte:
    WANG JIANLONG (Autor:in) / YI CHONGZHENG (Autor:in) / ZHANG LI (Autor:in) / MA RUI (Autor:in) / WU XUEYU (Autor:in) / ZHANG HANG (Autor:in) / ZHU XIANZHANG (Autor:in) / LIU CHENGKUN (Autor:in)

    Erscheinungsdatum :

    2023-06-23


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Urban road congestion space-time prediction method based on graph process neural network

    WANG JIANLONG / YI CHONGZHENG / ZHANG LI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    CONGESTION POINT PREDICTION DEVICE AND CONGESTION POINT PREDICTION METHOD

    KIM NAM HYUK | Europäisches Patentamt | 2023

    Freier Zugriff

    Traffic intersection congestion prediction method based on machine learning

    XU WENBO / LIAO ZHIZHOU / HU SIQUAN et al. | Europäisches Patentamt | 2020

    Freier Zugriff


    Road congestion situation prediction method considering congestion superposition effect

    SONG GUOHUA / ZANG JINRUI / FEI WENPENG et al. | Europäisches Patentamt | 2020

    Freier Zugriff