Implementation of Personalized Scenic Spot Recommendation Algorithm Based on Generalized Regression Neural Network for 5G Smart Tourism System

Abstract

On the basis of the analysis of the evolution dynamics and the process of smart tourism service, this paper constructs the evolutionary game model of smart tourism service and reveals the evolution mechanism of smart tourism service based on the network platform. Based on the strategic main line of “advantages,” it proposes the design ideas and overall framework of the smart tourism service model based on the network platform, including the smart tourism information interactive service model, the element collaborative service model, and the value cocreation service model. The comparison of recommendation results shows that the recommendation error of the genetically improved generalized regression neural network algorithm is reduced, and the recommendation accuracy is better than that of the unimproved generalized regression neural network algorithm. In the recommendation scenario of click-through rate recommendation, the existing recommendation models are difficult to meet the functions of memory and generalization at the same time and cannot fully mine and combine low-level features, and the model parameters of the deep learning model are difficult to learn under the high-dimensional sparse data set of the recommendation system. To solve the problem of generalization, this paper proposes a deep CTR recommendation model based on the gradient boosting tree and factorization machine. It can fully mine low-level feature information and automatically realize low-level feature combination, which can better learn model parameters on high-dimensional sparse data sets, and the recommendation results are no longer overgeneralized. In this paper, simulation experiments are carried out on the data set, and the related recommendation models are compared. The experimental results show that the model proposed in this paper achieves better results in both the AUC (area under ROC curve) evaluation index and the cross-entropy evaluation index.

Intelligent Geo-Tour Route Recommendation Algorithm Based on Feature Text Mining and Spatial Accessibility Model

“…4.6.6. Superiority of the Proposed Algorithm Through analysis, it can be concluded that the proposed algorithm has significant advantages over the methods used in the literature [5][6][7][8][9][10][11][12] and the commonly used electronic map methods used in tour route planning, as follows:…”

“…This method finally improved the collaborative filtering algorithm's performance and increased the recommendation accuracy. Lin [6] proposed a depth CTR recommendation model based on the gradient lifting tree and factor decomposer, which improved the performance of the recommendation system. Pacheco et al [7] brought forward a deep-learning recommendation system on scenic spots based on the Internet of Things and improved the system's performance.…”

“…Based on the analysis of existing studies, the proposed algorithm has significant advantages over the literature [5][6][7][8][9][10][11][12].…”

“…The algorithms constructed in references [6,7] aim to improve the AUC (area under the ROC curve), cross entropy, recall, accuracy, etc. of recommendation algorithms, and they still make improvements from the perspective of optimizing algorithm performance, ignoring the core issues of interest matching and maximizing dynamic benefits.…”

Design and Implementation of a Personalized Tourism Recommendation System Based on the Data Mining and Collaborative Filtering Algorithm

“…Tourism data mining provides various strategies and techniques to ensure the safety and security of users while traveling. The data mining process improves the communication services for the tourists that reduce the latency rate in the searching process [ 8 ]. Tourism filtering is a process that delivers travel information to tourists.…”