A Deep Intelligent Ant Colony-Based Approach to Personalized and Customized Route Optimization for Smart Tourism

Abstract

To enhance the travel experience of tourists and make the shortest travel personalized route, an innovative personalized route optimization method based on a deep, intelligent ant colony is proposed. The algorithm considers the tourists' travel time, cost constraints, and the experience of attractions. It establishes the objective function of tourists' personalized route optimization to maximize the utility of their travel and tourism activities and minimize the total path. Based on the attention mechanism neural network, the objective function feature matrix is extracted, which is used to replace the heuristic information matrix of the ant colony algorithm, and at the same time, the guidance information of the target point is added to understand the optimization of the ant colony algorithm. The optimized algorithm solves the objective function and obtains the optimization results of the personalized, customized route for intelligent tourism. The test results show that the method can calculate the feature matrix between different attractions, and the time reduction rate is between 44.6% and 68.2%; it can complete the optimization of personalized routes under other circumstances; it can obtain the shortest route planning results under the condition of guaranteeing the maximum utility of tourists, and the actual multi-objective shortest path proximity and single-objective average degree of realization are above 93.36%.