The invention provides a traffic flow prediction method and device based on local-global spatio-temporal feature fusion. The method comprises the steps from the first step to the fifth step. According to the method, global time information of traffic speed prediction is obtained while time sequence information sequence correlation is considered, the learning ability of the model is improved by fusing time and space local and non-local information, and the model has higher prediction precision.
本发明提供了一种基于局部‑全局时空特征融合的交通流量预测方法及设备,所述方法包括:步骤一至步骤五。本发明在兼顾时序信息顺序相关的同时获取了交通速度预测的全局时间信息,通过融合时间和空间局部与非局部信息提升模型的学习能力,模型具有更高的预测精度。
Traffic flow prediction method and device based on local-global spatial-temporal feature fusion
基于局部-全局时空特征融合的交通流量预测方法及设备
2023-06-23
Patent
Electronic Resource
Chinese
IPC: | 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 / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung |
Full-period traffic flow prediction method based on spatial-temporal feature deep fusion
European Patent Office | 2025
|European Patent Office | 2023
|Traffic flow prediction method and system based on non-embedded spatial-temporal feature fusion
European Patent Office | 2024
|