Study on Influencing Factors of Tourist Flow in Scenic Spots Based on Big Data

Abstract

Abstract Tourism in China is a thriving industry. For the past few years, the growth of rural tourism was an important emphasis for many areas, which has had a positive impact on rural economies. Chinese people's attention to tourism cultures has shifted dramatically in the period of economic worldwide and the quick propagation of network data. Currently, popular tourism activities are now more attractive. Studying the allocation of tourism activities in terms of avoiding overpopulation and wasteful use of assets in tourist hotspots is a popular subject in the area of tourism. With the use of tourist activity information, this article expands a big data platform focused on spatial and temporal distribution (STD) features and presents a data mining technique founded on revamped genetic-coalesced convolutional neural network with fine-tuned long short-term memory (RG-CCNN-FLSTM) technique to forecast tourist activity in STD aspect. The distribution of tourist traffic can be successfully regulated; the goal of equitable distribution of tourism assets accomplished, and the establishment of intellectual tourism should be further boosted by providing the prediction results back to scenic spot workers in real-time. Using the simulation results, we may conclude that data mining is highly adaptable and accurate. The proposed technique here can lessen the negative effects induced by the unequal distribution of tourism activity and conceptual direction for a better-functioning tourism economy, according to this research. The findings of this article are presented in graphical forms by employing the Origin tool.