Abstract: Under the background of e-commerce, customer orders show the characteristics of multiple varieties, small batch, high frequency and so on, which brings great challenges to the warehouse picking work. In order to improve the efficiency of picking, a multi-objective zone picking model that minimizes the total service time, optimal zone workload balance and achieve the highest secondary sorting efficiency is designed under the batching strategy of the complete splitting of the order and walking strategy of the combinatorial optimization. Due to the contradiction among the three objective functions, the nondominated sorting genetic algorithm II (NSGA-II) is designed to solve the multi-objective optimization model. Through numerical experiments, it is found that when the order batch environment is 1,4, the total service time is reduced by 43.88%, the balance is improved by 84.61%,respectively, compared with the traditional partition picking system without splitting orders. The influence of the number of zones, the total number of orders and the order batch environment on the system efficiency is analyzed.