Research on multi-objective dynamic vehicle pickup and delivery route planning based on customer value

For the problem of multi-supplier and multi-rider instant delivery in food delivery systems, this paper classifies customer consumption behavior based on customer satisfaction and establishes a multi-objective vehicle routing optimization model that minimizes total cost and the proportion of overdue orders, based on customer value. An improved Student Psychology-Based Optimization (SPBO) algorithm is proposed to solve the problem. The algorithm incorporates repair strategies, strong and weak perturbations, and a memory mechanism to enhance both local and global search capabilities. To verify the effectiveness of the designed algorithm, test cases are developed to compare this algorithm with other algorithms through experiments. The experimental results show that the proposed improved SPBO algorithm can find the most reasonable delivery routes. Additionally, to verify the effectiveness of the customer value model, a comparative experiment was conducted between schemes with and without customer value classification. The results demonstrate that the delivery service based on customer value classification significantly reduces instances of delays and greatly improves customer satisfaction, providing a new solution to the instant delivery routing problem.