The invention discloses an efficient space-time traffic flow prediction method. The method comprises the following steps: S1, obtaining historical traffic flow time sequence data of road nodes in a given road network graph structure; the historical traffic flow time sequence comprises a series of node speeds of the road nodes corresponding to the preset sampling time; dividing the historical traffic flow time sequence data into a spatio-temporal data training set and a spatio-temporal data prediction set according to a preset proportion; s2, constructing a space-time traffic flow prediction model, and training the space-time traffic flow prediction model according to the space-time data training set to obtain a space-time traffic flow prediction optimization model; and S3, on the basis of the space-time traffic flow prediction optimization model, current traffic flow time sequence data is predicted and concentrated according to the space-time data so as to realize prediction of future space-time traffic flow. According to the method, the problems of inaccuracy of traffic flow prediction, errors of long-term traffic flow prediction and the like caused by low time and space correlation degree and missing traffic flow data due to the fact that space-time correlation characteristics in the road traffic flow data are not fully excavated in the road traffic flow prediction of a traditional road traffic prediction method are solved.
本发明公开了一种高效的时空交通流预测方法,所述方法包括以下步骤:S1:获取给定道路网络图结构中道路节点的历史交通流时间序列数据;历史交通流时间序列包括各道路节点对应预设采样时间下的一系列节点速度;并将所述历史交通流时间序列数据按预设比例划分为时空数据训练集与时空数据预测集;S2:构建时空交通流预测模型,并根据所述时空数据训练集对时空交通流预测模型进行训练,获取时空交通流预测优化模型;S3:基于时空交通流预测优化模型,根据时空数据预测集中当前交通流时间序列数据,以实现对未来时空交通流的预测。本发明解决了传统的道路交通预测方法在道路交通流预测中,没有充分挖掘出道路交通流数据中的时空关联特征,存在对时间和空间关联度低、交通流数据缺失而造成的交通流预测不准确性,长期交通流预测的误差性等问题。
Efficient space-time traffic flow prediction method
一种高效的时空交通流预测方法
2024-08-23
Patent
Electronic Resource
Chinese
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 |
Traffic flow prediction method based on space-time sequence
European Patent Office | 2025
|Traffic flow prediction method based on space-time neural network
European Patent Office | 2024
|Traffic flow prediction method based on space-time attention mechanism
European Patent Office | 2024
|Traffic flow prediction method based on space-time attention network
European Patent Office | 2023
|