The embodiment of the invention provides a traffic index prediction method based on a decoupling space-time neural network, and belongs to the technical field of data processing, and the method specifically comprises the steps: obtaining traffic index data of each road section in a road network, carrying out the preprocessing of the traffic index data, obtaining an input data set, and dividing the input data set into a training set, a verification set and a test set; defining a traffic index prediction problem and a prediction target; constructing a traffic index prediction model based on the decoupling space-time neural network according to the traffic index prediction problem and the prediction target; training a traffic index prediction model by using the training set; setting an evaluation index, evaluating the space-time neural network model based on the decoupling framework obtained by training by using the verification set and the test set, and when an evaluation result accords with the evaluation index, obtaining a trained traffic index prediction model; and inputting historical traffic index data of the target road network into the trained traffic index prediction model to obtain a prediction result. Through the scheme disclosed by the invention, the prediction efficiency and accuracy are improved.

    本公开实施例中提供了一种基于解耦时空神经网络的交通指标预测方法,属于数据处理技术领域,具体包括:获取路网中各路段的交通指标数据并进行预处理得到输入数据集,随后将其划分为训练集、验证集和测试集;定义交通指标预测问题和预测目标;根据交通指标预测问题和预测目标构建基于解耦时空神经网络的交通指标预测模型;使用训练集训练交通指标预测模型;设定评价指标,并使用验证集与测试集对训练得到的基于解耦框架的时空神经网络模型进行评估,当评估结果符合评价指标时,得到训练好的交通指标预测模型;将目标路网的历史交通指标数据输入训练好的交通指标预测模型,得到预测结果。通过本公开的方案,提高了预测效率和精准度。


    Access

    Download


    Export, share and cite



    Title :

    Traffic index prediction method based on decoupling space-time neural network


    Additional title:

    一种基于解耦时空神经网络的交通指标预测方法


    Contributors:

    Publication date :

    2024-09-13


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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 / 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



    Space-time heterogeneous decoupling method based on multi-mode traffic flow prediction

    SENG DEWEN / WU MEI / LIN HUAI | European Patent Office | 2024

    Free access

    Traffic flow prediction method based on space-time neural network

    YANG YU / GUO GUIBING | European Patent Office | 2024

    Free access

    Distributed traffic flow prediction method and system based on space-time decoupling

    ZHOU HAIBO / ZHANG YUAN / XU YUNTING et al. | European Patent Office | 2023

    Free access

    Space-time ARIMA traffic prediction method based on neural network

    LIN XINLONG / WANG MEIHUA / ZHONG CHENGHUA | European Patent Office | 2025

    Free access

    Traffic flow prediction method based on decoupling fusion network

    CHEN JING / PAN SHIXIANG | European Patent Office | 2024

    Free access