Traffic condition prediction method, electronic equipment and storage medium

Abstract

The invention relates to a traffic condition prediction method, electronic equipment and a storage medium, and belongs to the field of artificial intelligence. The traffic condition prediction method comprises the steps of obtaining time sequence traffic data collected by an ETC portal system, carrying out the data preprocessing of the time sequence traffic data, and obtaining time sequence traffic features; writing the time sequence traffic characteristics into a big data platform through Spark Streaming; using spark Jar on a big data platform for reading time sequence traffic characteristics, and training a flow model and a speed model through an expansion causal convolutional neural network algorithm; and predicting the traffic flow and the vehicle speed based on the trained flow model and speed model. According to the embodiment of the invention, the collected vehicle data is comprehensive, and the accuracy of traffic condition prediction can be improved; a distributed data processing technology is applied, so that the real-time performance of the data can be improved, a large amount of data can be quickly processed, and the efficiency is high; and an expansion causal convolutional neural network algorithm is adopted, so that resources can be saved, and the training speed is increased.

Description

technical field [0001] This application relates to the field of artificial intelligence, in particular to a traffic condition prediction method, an electronic device and a storage medium. Background technique [0002] From the analysis of the construction and operation of smart expressways in various provinces, it is still facing the problems of rapid growth in demand but relatively lagging service capabilities, lack of effective means, and inaccurate data. At present, vehicle-road coordination technology is still in the research stage, it is very difficult to promote, and there is a lack of effective means for information services. [0003] For the learning model of traffic conditions, the current method is to train the model based on the data of the mobile phone App, but this solution has great limitations: a large number of mobile apps need to be opened to collect vehicle driving data, but not opened The vehicle data of the mobile app will not be collected, so the lack o...

AI Technical Summary

Problems solved by technology

[0003] For the learning model of traffic conditions, the current method is to train the model based on the data of the mobile phone App, but this solution has great limitations: a large number of mobile apps need to be opened to collect vehicle driving data, but not opened The vehicle data of the mobile app will not be collected, so the lack of a large amount of data will result in insufficient fitting of the model, a

Images