The invention relates to a traffic accident number prediction method and system based on a multivariate time series model. The accident prediction method comprises the following steps: 1, obtaining road traffic accident data, traffic violation data, traffic law enforcement data, holiday and festival data and weather data; 2, constructing a sample data set; 3, establishing an accident prediction model based on a vector autoregression model; and 4, inputting holiday and festival conditions and weather conditions of a plurality of days in which the number of traffic accidents needs to be predicted into the accident prediction model, and predicting the number of daily traffic accidents in the plurality of days. Compared with the prior art, the method has the advantages that the prediction result is more accurate and reliable, and the effective utilization rate of traffic law enforcement resources is improved.

    本发明涉及一种基于多元时间序列模型的交通事故数预测方法及系统,其中事故预测方法包括:步骤1:获取道路交通事故数据、交通违法数据、交通执法数据、节假日数据和天气数据;步骤2:构建样本数据集;步骤3:建立基于向量自回归模型的事故预测模型;步骤4:将需要预测交通事故数的若干天的节假日情况和天气条件输入事故预测模型,预测这若干天中每天的交通事故数。与现有技术相比,本发明具有预测结果更加准确可靠、有利于提高交通执法资源有效利用率等优点。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic accident number prediction method and system based on multivariate time sequence model


    Weitere Titelangaben:

    一种基于多元时间序列模型的交通事故数预测方法及系统


    Beteiligte:
    FENG MINGJIE (Autor:in) / WANG XUESONG (Autor:in)

    Erscheinungsdatum :

    2021-12-10


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

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



    Towards a multivariate, similarity-based traffic accident typology

    Gundy, C. / Institut National de Recherche sur les Transports et leur Securite | British Library Conference Proceedings | 1989


    Traffic accident prediction method and system

    RYU JE HA / PARK SEONG SU / JEONG DAE HYEON et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Traffic accident prediction method

    CHEN MING / ZHONG HUIJIAN / LIN JING et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Training method of traffic accident prediction model and traffic accident prediction method and device

    WANG NIANMING / CHEN YANG / ZHOU MINGKE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Prediction system for traffic accident

    BACK JU YONG | Europäisches Patentamt | 2019

    Freier Zugriff