The invention provides a traffic flow time sequence prediction method and device, a computer system and a computer readable storage medium, and the method comprises the following steps: obtaining a historical traffic flow time sequence in response to a traffic flow prediction instruction; inputting the historical traffic flow time sequence into a classification model to obtain classification labels; obtaining a target prediction model according to the corresponding classification labels; and inputting the historical traffic flow time sequence into the prediction model to obtain a correspondingpredicted traffic flow time sequence. According to the method, firstly, machine learning is carried out on a large number of training time sequences, the mapping relation between statistical characteristics of the training time sequences and the corresponding optimal prediction model is mastered, and a classification model is generated according to the mapping relation and used for outputting theprediction model most matched with the traffic flow time sequence to be detected. Finally, the traffic flow time sequence to be detected is predicted by using the most matched prediction model so asto achieve the purpose of improving the accuracy of the prediction result.

    本发明提供一种车流量时间序列的预测方法、装置、计算机系统及计算机可读存储介质,所述方法包括以下步骤:响应于车流量预测指令,获取历史车流量时间序列;将所述历史车流量时间序列输入分类模型以获取分类标签;根据所述对应的分类标签获取目标预测模型;将所述历史车流量时间序列输入所述预测模型,得到对应的预测车流量时间序列。本发明首先通过对大量训练时间序列进行机器学习,掌握训练时间序列的统计特征与其对应的最佳预测模型之间的映射关系,根据该映射关系生成分类模型,用于输出与待测的车流量时间序列最匹配的预测模型。最后待测的车流量时间序列利用最匹配的预测模型进行预测,以达到提高预测结果准确性的目的。


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow time series prediction method and device


    Additional title:

    车流量时间序列的预测方法及预测装置


    Contributors:
    DUAN HONGYUN (author) / PENG CHEN (author) / WANG WEI (author)

    Publication date :

    2020-07-10


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    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 / G06K Erkennen von Daten , RECOGNITION OF DATA / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Short-term traffic flow prediction method based on time series decomposition

    WANG WEI / ZHOU WEI / HUA XUEDONG | European Patent Office | 2020

    Free access

    Traffic flow time series decomposition method

    WANG WEI / ZHOU WEI / WANG YUJIE et al. | European Patent Office | 2020

    Free access

    TRAFFIC FLOW TIME SERIES PREDICTION BASED ON STATISTICS LEARNING THEORY

    Ding, A. / Zhao, X. / Jiao, L. et al. | British Library Conference Proceedings | 2002


    Traffic flow time series prediction based on statistics learning theory

    AiLing Ding, / XiangMo Zhao, / LiCheng Jiao, | IEEE | 2002


    DeepTFP: Mobile Time Series Data Analytics based Traffic Flow Prediction

    Chen, Yuanfang / Chen, Falin / Ren, Yizhi et al. | ArXiv | 2017

    Free access