货量预测与分拣人员排班问题的数学模型  

A Mathematical Model for Predicting Cargo Volume and Scheduling Sorting Personnel

作　　者：晋守博[1] 韩冉 张文迪 李洋 JIN Shoubo;HAN Ran;ZHANG Wendi;LI Yang(School of Mathematics and Statistics,Suzhou University,Suzhou Anhui 23400,China)

机构地区：[1]宿州学院数学与统计学院,安徽宿州234000

出　　处：《德州学院学报》2025年第2期48-52,共5页Journal of Dezhou University

基　　金：安徽省高校自然科学研究项目(2022AH040207);宿州学院质量工程项目(szxy2022xnjys01,szxy2023zcsf09)。

摘　　要：随着网购数量的增多,电商物流分拣中心对于合理安排值班人员以提高效率的诉求越来越强烈。利用时间序列预测和优化模型,研究了分拣人员的最优排班问题。首先,通过ACF(autocorrelation function)及PACF(partial autocorrelation function)图像及白噪声检验判断数据是否平稳,对于不平稳的数据进行对数、差分变换,计算处理后数据的p,q阶数,并利用ARIMA(autoregressive integrated moving average model)模型对未来的货量数据进行预测。然后,当分拣线路发生变化时,借助NARX(non-linear autoregressive with exogenous inputs)神经网络预测模型预测出新增和缺失线路分拣中心货量。研究结论指出,依据每日总包裹数量的不同可以分为三种情况,通过均分与取整运算,并利用平均筛选法给出了分拣中心人员的最优排班策略。研究结果表明通过精确的货量预测和可靠的数学模型,可以准确地求出最优的人力资源配置数量。With the increasing number of online shopping,the demand for reasonable arrangement of on-duty personnel in e-commerce logistics sorting centers to improve efficiency is becoming more and more intense.In this paper,the time series prediction and optimization model is used to study the optimal scheduling of sorters.ACF(autocorrelation function)and PACF(partial autocorrelation function)images and white noise test were used to determine whether the time series data were stationary,logarithmic and differential transformations were carried out for the nonstationary data,and then the p-order and q-order of the processed data were calculated,and the ARIMA(autoregressive integrated moving model)model was used to predict the future volume data.When the sorting route changes,the NARX(non-linear autoregressive with exogenous inputs)neural network prediction model is used to predict the cargo volume of newly added and absent sorting centers.The research conclusion ultimately points out that there are three situations based on the total number of packages per day,and the optimal scheduling strategy for sorting center personnel can be obtained through averaging and rounding operations,as well as using the average screening method.The results indicate that accurate prediction of cargo volume and reliable mathematical models can accurately determine the optimal number of human resource allocation.

关 键 词：货量预测 人员排班 ARIMA模型 平均筛选法 

分 类 号：O213[理学—概率论与数理统计]