Revolutionizing E-Commerce Logistics: AI-Driven Path Optimization for Sustainable Success

The traditional approach to logistics path planning is hindered by lengthy procedures. In this study, we explore the multi-objective optimization of logistics management, considering the conventional path and time efficiency indices alongside shelf safety and stability as additional objective functions. Based on particle swarm optimization (PSO), we optimize objective functions for internal path planning, scheduling timeliness, and shelf safety and stability. We then determine optimal routes under varying order demands using PSO and ultimately optimize the final path using dynamic programming and spline function restrictions to meet actual demand. Empirical results indicate that the proposed solution method outperforms other calculation methods, such as genetic algorithm (GA) and simulated annealing (SA), demonstrating over 10% improvement in time and total distance consumption. Further practical application tests demonstrate that the model in this study has a beneficial impact on all five distinct types of orders through efficient deployment optimization.