Prediction method of road traffic flow based on graph convolution network

Abstract

The invention provides a prediction method of a road traffic flow based on a graph convolution network. The method comprises the following steps of collecting vehicle GPS data in the past period of time; integrating the vehicle GPS data with actual road network information data to obtain a road traffic flow characteristic matrix, and converting a road and a road intersection point in the actual road network through line graph conversion to generate a road adjacency matrix; and based on the road adjacency matrix and the road traffic flow characteristic matrix, acquiring a predicted value of traffic flow data of the road in the next time period by using a spatial characteristic and a time characteristic of traffic flow data of the integrated road of a GCN network and an LSTM network. Through integrally using the spatial characteristic of the road traffic flow data extracted by GCN and the time characteristic of the road traffic flow data extracted by LSTM, and combining a time period characteristic and a weather characteristic, the road traffic flow data is predicted, and a prediction effect is better than the prediction effect acquired through using only time characteristic or the spatial characteristic.

Description

technical field [0001] The invention relates to the technical field of transportation, in particular to a method for predicting road traffic flow based on a graph convolutional network. Background technique [0002] Transportation is the lifeblood of the national economy. Transportation technology is facing major strategic needs. We need to realize the sharing of transportation information and the effective connection of various transportation modes, and improve the technical level of transportation operation and management. As the number of motor vehicles continues to increase, the road system is under increasing pressure, and the status of intelligent transportation systems is becoming more and more prominent. Intelligent transportation systems make people, cars (or moving objects), roads and the environment live in harmony, so intelligent transportation systems are considered to be one of the effective methods to solve traffic problems such as road traffic congestion, red...

AI Technical Summary

Problems solved by technology

The main disadvantage of this algorithm is that although CNN is introduced to extract spatial features, CNN evenly divides the map and counts the traffic flow in each segment. This data division method does not conform to the real characteristics of road traffic flow data.

Images