Traffic flow prediction method based on spatio-temporal data embedding

Abstract

The invention discloses a traffic flow prediction method based on spatio-temporal data embedding. The method comprises the following steps: acquiring historical traffic flow data; performing spatio-temporal data embedding based on historical traffic flow data, wherein the spatio-temporal data embedding comprises the following steps: performing interval representation of traffic flow: determining an interval to which each traffic flow belongs, and converting the determined interval into a corresponding traffic flow interval; generating traffic flow vectors: taking all the traffic flow intervals as input data, and converting the input data into embedded data, namely corresponding traffic flow vectors, by adopting a Word2vec model; time features are extracted based on the traffic flow vector to obtain a node feature matrix, and correlation between the electronic police devices is extracted to obtain a dynamic association graph; and inputting the node feature matrix and the dynamic association graph into a graph convolutional neural network to obtain a prediction result output by the graph convolutional neural network. According to the method, implicit correlation between traffic flows can be quantified and measured, high-level time features and a dynamic association graph are extracted for effective modeling, and accurate and stable traffic flow prediction is obtained.

Description

technical field [0001] The application belongs to the technical field of traffic flow prediction, and in particular relates to a traffic flow prediction method based on spatiotemporal data embedding. Background technique [0002] Traffic flow forecasting is a typical task in spatiotemporal forecasting, which aims to predict future traffic flow based on historical traffic flow. Traffic flow prediction can not only predict potential road congestion to help managers guide traffic in time, but also help travelers plan ahead or adjust their travel routes. Therefore, it is imperative to achieve accurate and stable traffic flow prediction. However, obtaining accurate traffic flow prediction results is still a great challenge due to the complex spatiotemporal dependence of traffic flow. [0003] Currently, deep learning has been widely used in various fields because it can combine simple but nonlinear modules to generate multi-level deep representations of raw input data. Recentl...

AI Technical Summary

Problems solved by technology

[0004] However, the simple images in the CNN model cannot accurately represent the real structure of the traffic network because the traffic network has an irregular non-Euclidean topology

Therefore, the traditional CNN cannot effectively extract the complex spatial features of the traffic network

Second, although most of the existing GCN-based research can obtain good prediction results, it only constructs a static graph with fixed weights, which cannot accurately reflect the correlation between sensors that change over time.

Images