Scenic spot passenger flow volume prediction method and system based on hybrid optimization RBF neural network

Abstract

The invention discloses a scenic spot passenger flow volume prediction method and system based on a hybrid optimization RBF neural network, which are used in the field of scenic spot management, and the prediction process adopts a radial basis function neural network and a hybrid optimization algorithm, and comprises the steps of data collection, data preprocessing, model establishment, center andvariance determination, global optimization, local optimization and passenger flow prediction. Compared with the traditional BP neural network, the RBF neural network adopted by the method has stronger generalization ability and higher approximation precision, is more suitable for the field, and improves the timeliness of prediction. The hybrid optimization improves the prediction accuracy through the global search capability of the fish swarm algorithm and the local convergence of the particle swarm algorithm. The invention can more accurately predict the number of tourists in each scenic spot in the next few days, and provides help for scenic spot managers to make decisions.

Description

technical field [0001] The invention relates to a tourism management system, in particular to a method and system for predicting passenger flow in a scenic spot based on a hybrid optimized RBF neural network. Background technique [0002] In recent years, with the improvement of people's living standards, the tourism industry has developed vigorously. However, with the increase in the number of tourists, especially during the peak tourist period, the reception capacity of scenic spots does not match the influx of tourists, which makes the management of domestic scenic spots more difficult during holidays, beyond the controllable range of scenic spots, and affects the tourist experience of tourists In severe cases, it may endanger the personal and property safety of tourists. Therefore, there is an urgent need for a method that can predict the tourist flow of the scenic spot in the future peak tourist season. The scenic spot manager takes effective preventive measures in adv...

AI Technical Summary

Problems solved by technology

First, due to the continuous increase of historical data, model training time is also increasing, making it difficult to guarantee the timeliness of prediction; second, the accuracy of prediction is related to features and prediction models, and the accuracy rate is not ideal due to the characteristics and training models

There are currently many methods for predicting passenger flow in scenic spots, which provide some help for the decision-making of scenic spot managers, but the timeliness and accuracy of the prediction model are hardly ideal

Images