首页> 外国专利> Impact explanatory variable identification device, impact explanatory variable identification method, and impact explanatory variable identification program

Impact explanatory variable identification device, impact explanatory variable identification method, and impact explanatory variable identification program

机译:影响解释性可变识别设备,影响解释性可变识别方法,并影响解释性可变识别程序

摘要

PROBLEM TO BE SOLVED: To determine which of several explanatory variables used for making a prediction has an influence when an objective variable becomes abnormal. SOLUTION: A basic prediction model for obtaining an objective variable from an explanatory variable, a correct answer probability acquisition means 32 for obtaining a correct answer probability of the objective variable obtained by this basic prediction model, and an all ideal explanatory variable calculation means 33 for calculating all ideal explanatory variables. The importance acquisition means 34 for obtaining the importance of the explanatory variables for each of the explanatory variables, the correct answer probability acquisition means 35 for abnormal detection to obtain the correct answer probability at the time of abnormality detection, the corrected correct answer probability acquisition means 36, and each of the explanatory variables. The difference correct answer probability acquiring means 37 for obtaining the difference correct answer probability which is the difference between the corrected correct answer probability and the correct answer probability at the time of abnormality detection, and the dividing means 38 for dividing the difference correct answer probability by the importance for each of the explanatory variables. The influence degree acquisition means 39 for acquiring the influence degree for determining which of the explanatory variables affected the abnormality based on the result of the division means. [Selection diagram] FIG. 9
机译:要解决的问题:确定用于制造预测的几个解释变量中的哪些因素时的目标变量变得异常。解决方案:从解释变量获得目标变量的基本预测模型,用于获得通过该基本预测模型获得的物镜变量的正确答案概率的正确答案概率获取装置32,以及所有理想的解释性变量计算装置33计算所有理想的解释变量。用于获得每个解释变量的解释变量的重要性的重要性获取装置34,用于异常检测的正确答案概率采集装置35在异常检测时获得正确的答案概率,校正的正确答案概率采集方法36,以及每个解释性变量。差异正确答案概率获取装置37用于获得差异正确答案概率,这是在异常检测时校正的正确答案概率和正确答案概率之间的差异,以及用于除去差异正确答案概率的分割装置38每个解释性变量的重要性。影响程度采集装置39获取确定基于分割装置的结果影响到异常的影响程度。 [选择图]图。 9.

著录项

  • 公开/公告号JP2021157475A

    专利类型

  • 公开/公告日2021-10-07

    原文格式PDF

  • 申请/专利权人 東芝情報システム株式会社;

    申请/专利号JP20200056842

  • 发明设计人 村松 久;牧野 真一;

    申请日2020-03-26

  • 分类号G06N20;

  • 国家 JP

  • 入库时间 2022-08-24 21:31:55

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号