TriPlan: an interactive visual analytics approach for better tourism route planning

Abstract

Continuous research and development of novel tourism routes is necessary for tourism service providers to improve the tourist experience and industrial competitiveness. However, the route planning is cumbersome due to the time-consuming, extensive, and costly field study. Most of the existing route planning studies focus on recommending tourism routes for users based on attraction characteristics or tourist behavior features, which are generally unexplainable due to the black-box approaches they use. Other solutions allow users to customize itineraries through an interactive interface but often lack guidance from the aspect of route evaluation or destination image perception. In this paper, we thoroughly discuss the requirements and design tasks with domain experts and propose TriPlan, an interactive visual analytics system that provides intuitive planning guidance for tourism product developers. We design and improve multiple coordinated visualizations to facilitate analysis from the perspectives of overall route pattern and individual destination image. We also develop a hierarchical planning view to display the structural information of a plan. In addition, we introduce an automatic route optimization algorithm and multiple interactions to assist users in optimizing and adjusting the itineraries. Finally, we evaluate the usability and effectiveness of our system through three case studies and quantitative and qualitative interviews with the domain experts on real-world datasets. Graphical abstract Electronic supplementary material The online version of this article (10.1007/s12650-022-00861-8) contains supplementary material, which is available to authorized users.

Uncertain multi-objective programming model of tourist route considering tourist preference

“…The methods for solving the tourism route programming model mainly include exact algorithms, heuristic algorithms, and meta-heuristic algorithms. Among them, the most commonly used meta-heuristic algorithms are the genetic algorithm, the particle swarm algorithm, the ant colony algorithm, and the simulated annealing algorithm [31]. In this study, the ant colony algorithm was selected to address the problem with the following parameters: the number of ants was 50 and the number of iterations was 200.…”

“…Jos'e et al considered the construction of group routes, the cost and time constraints associated with each participant, the choice of transport modes from one location to another, and the heterogeneous preferences in the group to construct a GRASP to solve the travel itinerary programming problem for groups of tourists with different preferences [23]. Zhang Xinyi et al proposed an interactive visual analytics system that provided intuitive planning guidance for tourism product developers [31]. Lu Bing et al described a model of the discrete particle swarm algorithm based on geographic coordinates to solve the tourism route problem [18].…”

Digital Tourism Recommendation and Route Planning Model Design Based on RippleNet and Improved GA

“…Zhang et al designed an interactive visual analysis system for tourism RP by communicating and discussing with industry experts, which introduced an automatic route optimization algorithm and multiple interactions to help users optimize and adjust their itineraries. Finally, the usability and effectiveness of the method were evaluated with the help of case studies and expert interviews [12]. Xu et al used historical traveler data and data from the public road network to extract tourist preferences, point-of-interest relationships, and edge attraction values in order to better optimize the tourism RP technique.…”

“…Zhang et al [12] High interactivity The planning results are rough, and the model has poor granularity Xu et al [13] The model explores the interests and preferences of users…”

“…The global optimal solution of the multi-objective optimization problem, or the person with the highest fitness value in the population, is found through non-stop iteration in the GA, which is designed to resemble the mechanism of superiority and inferiority in nature [30]. The study uses roulette selection method for individual selection, and the probability i p of being selected is calculated in Equation (12). In this equation, i f denotes the fitness value of the individual in the population.…”