Method and device for predicting pedestrian flow

Abstract

The embodiment of the invention provides a method and a device for predicting pedestrian flow, and relates to the technical field of pedestrian flow prediction. The method for predicting the pedestrian flow comprises the following steps: predicting the pedestrian flow of a to-be-tested target area by utilizing the original data sequence and a preset ARIMA model to obtain a first prediction result;when the first prediction result shows that predicted visitor flow data cannot be generated or the predicted visitor flow data is displayed abnormally, predicting visitor flow of the to-be-detected target area according to the original data sequence and a preset linear regression model to obtain a second prediction result. Due to the fact that the change trend of the pedestrian flow is often uncertain, an accurate prediction result can be obtained no matter how large the change trend of the pedestrian flow changes or tends to be stable, and the accuracy of pedestrian flow prediction is improved.

Description

technical field [0001] The present application relates to the technical field of people flow prediction, in particular, to a method and device for predicting people flow. Background technique [0002] Because the amount of people flow and the change trend are easily disturbed and affected by external factors such as weather and other factors, once it is affected, the trend of increase or decrease of the number of people will change greatly, that is, the change trend of the flow of people is relatively large; but in some specific areas The changing trend of the flow of people at the same time every day is in a stable state. Commonly used algorithms for predicting the flow of people include simple average method, moving average method, and exponential smoothing method. [0003] Such as the moving average method, which can smooth out the impact of sudden fluctuations in the data on the forecast results. The larger the number of periods of the moving average method, the better ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiment of the present application is to provide a method and device for predicting the flow of people. When the prediction result cannot be obtained by using the ARIMA model, the linear regression model is used for prediction. No matter whether the change trend of the flow of people changes greatly or tends to be stable, it can Obtain accurate prediction results, improve the accuracy of people flow prediction, and solve the problem that the existing single algorithm cannot accurately predict the flow of people

Images