A multi-objective tourism route planning model based on strength pareto evolutionary algorithm

In the era of booming artificial intelligence, its powerful data analysis and decision-making ability brings new ways for tourism route planning. Therefore, the study proposes a multi-objective tourism route planning model based on Strength Pareto Evolutionary Algorithm (SPEA). For tourism interest point prediction, a hypergraph learning model is constructed to capture user intent through multi-parallel hypergraph convolution. For tourism route planning, the model takes into account user experience, total trip cost and trip redundancy time, and adopts improved SPEA with local search strategy for multi-objective optimization. The results show that the point-of-interest prediction model has an accuracy of 0.91, a recall of 0.89, and an F1 value of 0.90, which is better than the comparison model. The travel route planning model converges best when the heuristic results account for 30%, and outperforms the greedy optimization model and the original scheme in terms of travel cost, trip duration and user experience. The study shows that the model can effectively balance multiple factors and provide quality experience for travelers. The research results will help promote the development of personalized tourism services and enhance the overall competitiveness of the tourism industry.