Traffic flow prediction method and device

Abstract

The invention provides a traffic flow prediction method and device. The traffic flow prediction method comprises the steps of: firstly acquiring traffic flow feature data of a target road segment in each of a plurality of historical time periods; secondly, screening effective traffic flow feature data from the traffic flow feature data in each historical time period, and determining the weight ofthe effective traffic flow feature data in each historical time period; and finally, based on the determined effective traffic flow feature data and the corresponding weight, predicting the traffic flow of the target road section. According to the traffic flow prediction method and the device, the effective traffic flow feature data is screened, and the weight of the effective traffic flow featuredata is combined, so that the accurate traffic flow can be predicted, and the defect of large prediction deviation in the prior art is overcome.

Description

technical field [0001] The present application relates to the technical field of forecasting and calculation, and in particular, to a method and device for forecasting traffic flow. Background technique [0002] With the continuous development of the economy and the continuous improvement of people's living standards, people's travel is increasingly dependent on online car-hailing or self-driving travel. The ensuing problem is that traffic congestion is becoming more and more serious, which leads to a decline in travel efficiency. Therefore, timely and accurate acquisition of traffic flow information on the road is helpful for users to plan their itinerary in advance based on the traffic flow information, travel at off-peak times, and improve travel efficiency. [0003] Most of the current traffic flow prediction methods are based on linear models or tree models. Although the above methods can predict the traffic flow of a certain road section, they cannot reasonably integra...

AI Technical Summary

Problems solved by technology

[0003] At present, most of the traffic flow prediction methods are based on linear models or tree models. Although the above methods can predict the traffic flow of a certain road section, the deviation of the predicted traffic flow is large due to the inability to reasonably integrate context information.

Images