The invention discloses an urban flow prediction method based on flow-POI causal relationship reasoning, and the method comprises the steps: collecting data, including travel flow data and POI data, of a plurality of cities at different time and different geographic positions; dividing the collected data into fine-grained data with time and space dimensions; for travel flow data and POI data, capturing a causal relationship between the travel flow data and the POI data by using a causal convolutional network based on an attention mechanism; pOI key factors influencing traffic changes are combined with spatio-temporal features extracted by the LSTM and GCN networks to serve as input of a full-connection layer, and the purpose of traffic prediction is achieved. According to the method, the influence of different POIs on the long-term development change of the travel flow is introduced from the angle of causal inference, the problems that the influence between the POIs and the flow is complex and key factors of the POIs influencing the flow change are difficult to determine are solved, meanwhile, the space-time characteristics of the flow data are fully utilized, and prediction of the urban flow is achieved.
本发明公开了一种基于流量‑POI因果关系推理的城市流量预测方法,包括:采集多个城市的不同时间、不同地理位置的数据,包括出行流量数据和POI数据;将采集的数据划分成细粒度的具有时间和空间维度的数据;针对出行流量数据和POI数据,使用基于注意力机制的因果卷积网络捕获二者的因果关系;将影响流量变化的POI关键因子结合LSTM和GCN网络提取到的时空特征作为全连接层的输入完成流量预测的目标。本发明从因果推断的角度引入了不同POI对出行流量长期发展变化影响的方法,解决了POI和流量之间影响复杂、影响流量变化的POI关键因子难以确定的难题,同时充分利用了流量数据的时空特性,实现了对城市流量的预测。
Urban flow prediction method based on flow-POI causal relationship reasoning
基于流量-POI因果关系推理的城市流量预测方法
2023-05-12
Patent
Electronic Resource
Chinese
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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
European Patent Office | 2022
|2-dimensional flow prediction based intelligent urban traffic-flow prediction method
European Patent Office | 2016
|British Library Conference Proceedings | 2000
|Traffic flow prediction method based on space-time causal attention network
European Patent Office | 2024
|