Method and system for predicting passenger flow volume of scenic area and storage medium

Abstract

The invention provides a method and system for predicting the passenger flow volume of a scenic area and a storage medium, and belongs to the technical field of data statistics. The method comprises:acquiring historical passenger flow data and historical air temperature data of a scenic area; associating the daily passenger flow volume in the historical passenger flow volume data with the daily maximum temperature and the daily minimum temperature in the historical temperature data to generate associated data; according to a plurality of preset class values, adopting the K-means clustering method to divide the whole year time of the scenic area into a plurality of intervals according to the associated data; for each interval, recombining the associated data, and further performing normalization processing on the combined associated data; dividing each processed associated data into a training set and a corresponding test set; respectively training the initial neural network by adopting the training set; processing the corresponding test set by adopting the trained neural network to obtain the prediction precision of the passenger flow volume under the current category; and predicting the passenger flow volume of the scenic area according to the category with the highest prediction precision.

Description

technical field [0001] The present invention relates to the technical field of data statistics, in particular to a method, system and storage medium for predicting passenger flow in a scenic spot. Background technique [0002] The short-term passenger flow forecasting of scenic spots is one of the key issues in the management of current scenic spots. The current short-term passenger flow forecasting models of scenic spots include traditional time series models, BP neural network models, support vector machines, etc., and models optimized by algorithms . However, we are currently facing the problem of large fluctuations in passenger flow, and there are obvious seasonal factors in the characteristics of passenger flow throughout the year. Therefore, when using various models to predict passenger flow for a period of time in the future, there will be forecasts for low and peak seasons The problem of too large difference in accuracy. Contents of the invention [0003] The pu...

AI Technical Summary

Problems solved by technology

However, we are currently facing the problem of large fluctuations in passenger flow, and there are obvious seasonal factors in the characteristics of passenger flow throughout the year. Therefore, when using various models to predict passenger flow for a period of time in the future, there will be forecasts for low and peak seasons The problem of too large difference in precision

Images