基于IPD的机器学习模型开发管理流程  

IPD-based Machine Learning Model Development Management Process

作　　者：王灿 李韶武 吕微 WANG Can;LI Shaowu;LYU Wei(Longyuan(Beijing)Wind Power Engineering Technology Company,Beijing 100034,China)

机构地区：[1]龙源(北京)风电工程技术公司,北京100034

出　　处：《风力发电》2020年第4期11-14,共4页Wind Power

摘　　要：机器学习模型应用广泛性的增加,对于机器学习模型管理流程的需求也会随之增长,为了高效的管理机器学习模型,缩短研发周期、降低成本、提高模型质量,本文提出了基于IPD的机器学习模型管理流程。同时提出机器学习模型管理的关键在于要用闭环的、进化的思路至关重要。The increased application of machine learning models will increase the demand for machine learning model management processes.In order to efficiently manage machine learning models,shorten the development cycle,reduce costs,and improve model quality,this paper proposes IPD-based machine learning Model management process.At the same time,it is proposed that the key to the management of machine learning models is to use closed-loop,evolutionary ideas.

关 键 词：集成产品开发 IPD 机器学习 管理流程 生命周期 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]