Multi-Model Fusion Optimization for Cargo Volume Forecasting and Sorting Efficiency in E-Commerce Logistics Networks

Abstract

With the rapid development of the logistics industry and the growing material needs of the people, the rational planning of e-commerce logistics networks has become increasingly important. In the process of studying e-commerce logistics networks, the sorting efficiency of sorting centers is also one of the research directions that cannot be ignored. Both cargo prediction and sorting efficiency prediction have great research value for logistics networks. This article focuses on the sorting center of e-commerce logistics network, mainly studying the prediction of cargo volume and the scheduling of sorting center employees. This article establishes an LSTM neural network model for prediction, and imports data from different sorting centers into the LSTM neural network model for prediction training. At the same time, new and deleted routes were identified, corresponding data was extracted, and an additional Analytic Hierarchy Process (AHP) model was established to explore the relationships between logistics network sorting centers and between sorting centers, as well as between sorting centers and goods. The weights of edge weight coefficients, edge weight coefficients, and sorting center strength were determined.