Traffic congestion state propagation prediction and early warning system and method based on city portrait

Abstract

The invention discloses a traffic congestion state prediction and early warning system and method based on city portraits, comprising the following modules: a data collection and processing module, a deep learning module, a historical record module and a front-end display module; Record the traffic information of each street and intersection; abstract the street as an edge in the undirected graph, abstract the intersection as a point in the undirected graph, organize the traffic information of the street and intersection into edge weights and point weights, and input them into In the deep learning model of the dynamic graph, a real-time city portrait is constructed to predict the propagation of urban traffic congestion at the next moment, and report early warning information to the congested area.

Description

technical field [0001] The invention relates to a system and method for forecasting and early warning of traffic congestion state based on city portraits, and belongs to the field of information technology. Background technique [0002] With the development of urbanization, by 2050, studies estimate that 6 billion people will live in cities, and urban transportation is closely related to social pain points such as people's livelihood, economy, education, and housing, and is closely related to the development and prosperity of a city , only a safe and efficient traffic environment can play a positive role in promoting the development of the city. At present, the main streets of the city are equipped with traffic supervision cameras, which can clearly record information such as vehicles and pedestrians passing through the streets. These data provide conditions for the further development of urban traffic supervision. Congestion is one of the most serious problems affecting ur...

AI Technical Summary

Problems solved by technology

However, the traditional recurrent neural network has a long-term dependence problem. As time goes by, the recurrent neural network gradually loses the memory of the early input, and the predictions made only refer to the latest input data. When there are more data, the data spanning The longer the time, the more obvious the long-term dependence becomes

Images