The invention discloses a traffic prediction transfer learning method based on a space-time diagram self-attention model. The method comprises the following steps: converting historical traffic data and an urban traffic road network structure into a high-dimensional space-time representation vector through a data embedding layer; the high-dimensional space-time representation vector is converted into a space-time feature vector after space-time self-attention block coding through the space-time encoders, and output of the space-time encoders from the first layer to the Lth layer is connected through jump to obtain a final space-time feature vector; and inputting the final spatio-temporal feature vector into an output layer to obtain predicted traffic data. According to the method, short-distance and long-distance spatial correlation in a traffic network can be captured at the same time, dynamic modeling of spatial correlation of traffic data is completed, time and spatial information is integrated, and a cross-city depth space-time prediction task is achieved.
本发明公开了一种基于时空图自注意力模型的交通预测迁移学习方法,包括:通过数据嵌入层将历史交通数据和城市交通路网结构转化为高维时空表示向量;通过时空编码器将高维时空表示向量转换为时空自注意力块编码后的时空特征向量,并将第一层至第L层时空编码器的输出通过跳跃连接,得到最终的时空特征向量;将最终的时空特征向量输入至输出层,得到预测的交通数据。本发明能够同时捕获交通路网中的短距离和长距离的空间相关性,完成了对交通数据的空间相关性的动态建模,同时整合了时间和空间信息,实现了跨城市的深度时空预测任务。
Traffic prediction transfer learning method based on space-time diagram self-attention model
基于时空图自注意力模型的交通预测迁移学习方法
2022-11-29
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 / 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 |
Traffic flow prediction method based on space-time diagram transfer learning
European Patent Office | 2023
|Traffic prediction method and device based on dynamic space-time diagram convolution attention model
European Patent Office | 2021
|Attention-based dynamic space-time diagram convolution traffic flow prediction system and method
European Patent Office | 2023
|Traffic flow speed prediction method based on attention space-time diagram convolutional network
European Patent Office | 2023
|European Patent Office | 2023
|