Application of Improved Multi-Objective Evolutionary Algorithm in Intelligent Tourism Interest Point Recommendation and Itinerary Planning

In the context of boost of tourism and transportation, people's needs for the quality of tourism services are also increasing. Traditional scenic spot recommendations and itinerary planning methods cannot meet the personalized needs of tourists. Therefore, to achieve personalized services for tourist attractions and itineraries, this study introduces weakly correlated adaptive evolutionary algorithms and archival strategy algorithms to improve multi-objective optimization algorithms. It proposes an adaptive multi-objective evolutionary algorithm model for interest point recommendation and a multi-objective archival ant colony algorithm model for itinerary planning. Through experiments, it has been shown that the research algorithm is 10% higher than the improved algorithm in the accuracy analysis of recommended values for tourist attraction popularity features. In the accuracy analysis of recommended values for tourist attraction social network features, the research algorithm is 22.2% higher than the improved algorithm. In travel planning, the time required to study the algorithm model is minimized and kept below 200 unit values. The convergence speed of the algorithm model studied in this study is faster, and the optimal solution can be found within 100, while traditional algorithms require 140 iterations for finding the optimal solution. In summary, the two algorithm models can markedly enhance the intelligence and personalization level of tourism services.