Order Batch Optimization Based on Improved K-Means Algorithm

Abstract

Aiming at the shortcomings of the K-Means algorithm in the traditional K-Means algorithm, the DBSCAN algorithm is used to divide the order set according to the density, and obtain the batch number K value and the initial cluster center point. Based on this, the improved K-Means algorithm is used for optimization. Based on the real environment and instance data, the established batch assignment batch model is simulated. The experimental results show that the density-based K-Means clustering algorithm can effectively shorten the picking time and improve the warehouse logistics operation.