Analysis of distribution path optimization algorithm based on big data technology

The traditional e-commerce logistics distribution path optimization algorithm has the problem of a long time to find the optimal path. To solve this problem, this paper designs an e-commerce logistics distribution path optimization algorithm in the context of big data, introduces NSGA-II evolutionary algorithm for solving multi-objective optimization problems, combines improved genetic algorithm to solve multi objective terminal distribution path optimization model in new retail mode to obtain the Pareto optimal solution set of the research problem in this paper, and then establishes a multi-objective function for logistics distribution path optimization through five aspects: weight index, time efficiency index, customer importance index. In this paper, in the process of using the ant colony algorithm to solve the optimization of the end-delivery path of e-commerce logistics, global pheromone update rules such as the ant-perimeter model will be used for the pheromone update in the ant pathfinding process. Then, the multi-objective function of logistics distribution path optimization is established by five aspects: weight index, timeliness index, customer importance index, time window index, total path index, and finally, the distribution target weights are set to find the better distribution path in the objective function according to the different demands of e-commerce logistics, to complete the e-commerce logistics distribution path optimization. We were able to save 6.6% on the route optimized by the ant colony algorithm over the empirical route under the condition of path optimization with the ant colony algorithm. The experimental comparison results show that the designed e-commerce logistics distribution path optimization algorithm in the context of big data is shorter than the traditional algorithm to find the optimal path, which can reduce the e-commerce logistics distribution time and has certain practical application significance.(c) 2022 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).