基于大数据的企业生产周期预测方法  

Enterprise Production Cycle Prediction Method Based on Big Data

作　　者：王福荣[1] WANG Furong(Shaanxi Technical College of Finance and Economics,Xianyang 712000,China)

机构地区：[1]陕西财经职业技术学院,陕西咸阳712000

出　　处：《系统仿真技术》2024年第3期313-316,共4页System Simulation Technology

摘　　要：为提高企业资源规划效率及生产周期预测准确率,设计了一种基于密度峰值聚类的网络学习模型。该学习方法通过寻找密度峰值来估计网络参数,利用基于MapReduce的并行过程训练网络,从而提升网络训练效率及预测准确度。通过案例分析,所提方法的平均绝对偏差(mean absolute dviation,MAD)和标准差(standard deviation,SD)分别达到2.25×10^(-4)和1.78×10^(-4)。In order to improve the efficiency of enterprise resource planning and the accuracy of production cycle prediction,a network learning model based on density peak clustering is designed.In this learning method,the network parameters are estimated by searching for the density peak,and the parallel process based on MapReduce is used to train the network,so as to improve the network training efficiency and prediction accuracy.In case analysis,the standard deviation and mean absolute dviation of the proposed method reach 2.25×10^(−4) and 1.78×10^(−4) respectively.

关 键 词：物联网 大数据 企业资源规划 生成周期时间 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]