Traffic jam prediction method and system based on jam portrait

Abstract

The invention discloses a traffic jam prediction method and system based on a jam portrait. The method comprises the steps of obtaining traffic data, and obtaining the jam portrait data of a traffic bottleneck point in the traffic data according to the traffic data, wherein the jam portrait data reflects the road condition state of the traffic bottleneck point; determining congestion portrait feature parameters of the traffic bottleneck point according to the congestion portrait data of the traffic bottleneck point; and performing congestion prediction on the traffic data according to the congestion portrait feature parameters to obtain a prediction result which is used for traffic management. According to the invention, the traffic data can be predicted based on the congestion portrait, the obtained prediction result can be used for active traffic guidance management, the police basis of the traffic police can be determined according to the prediction result, a basis can be provided for optimization timing of signals and the like, and a basis can also be provided for travel route planning.

Description

technical field [0001] The invention relates to the technical field of traffic congestion prediction, in particular to a traffic congestion prediction method and system based on a congestion portrait. Background technique [0002] The existing technologies that can predict traffic congestion in real time can be roughly divided into three categories, one is simulation prediction based on macroscopic traffic demand data through dynamic traffic allocation; the other is traffic congestion prediction based on big data analysis; the third is based on real-time traffic Microsimulation predictions of the data. The current traffic congestion prediction methods basically have low prediction accuracy, insufficient real-time prediction results, and need to rely on a large number of sample data, and the existing traffic data collection equipment is also difficult to meet the prediction needs, the collected data types are single, and the data The accuracy is relatively low, and it is dif...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a traffic congestion prediction method and system based on congestion portraits, aiming to solve the problem that the current traffic congestion prediction methods in the prior art basically have low prediction accuracy, insufficient real-time prediction results, and need to rely on a large amount of sample data. Some traffic data collection equipment is also difficult to meet the needs of forecasting, the type of data collected is single, and the data accuracy is relatively low, making it difficult to ensure the accuracy of forecasting

Images