Traffic flow prediction method and equipment based on graph Gaussian process, and medium

The invention discloses a traffic flow prediction method and equipment based on a graph Gaussian process, and a medium. The method carries out the flow statistics of flow data, and carries out the prediction of the mean value and variance of a traffic flow according to a designed prediction algorith...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHAO HANQIN, FAN JINBIN, YANG JIANDANG, SU JIE, LIU YONG, ZHANG LI
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a traffic flow prediction method and equipment based on a graph Gaussian process, and a medium. The method carries out the flow statistics of flow data, and carries out the prediction of the mean value and variance of a traffic flow according to a designed prediction algorithm. According to the method, time and space features of traffic flow are comprehensively considered, space features are represented through graph aggregation Gaussian processes, time feature representation is performed on multiple graph aggregation Gaussian processes by using a deep convolution Gaussian process, so that a complete traffic flow model is constructed, and a road traffic flow prediction model can be obtained through training; when the prediction precision of the model is insufficient due to external disturbance, the model correction method can be used for carrying out post-correction processing on the model. The result shows that the constructed model can accurately predict the traffic flow data and can