首页> 外国专利> METHOD FOR PROVIDING AN EXPLANATION DATASET FOR AN AI MODULE, COMPUTER-READABLE STORAGE MEDIUM, DEVICE AND SYSTEM

METHOD FOR PROVIDING AN EXPLANATION DATASET FOR AN AI MODULE, COMPUTER-READABLE STORAGE MEDIUM, DEVICE AND SYSTEM

机译:提供AI模块,计算机可读存储介质,设备和系统的解释数据集的方法

摘要

It is difficult to explain the decisions of AI modules to a user. The invention relates to methods for providing an explanation dataset (2) for an AI-module (31), comprising the steps of: - receiving a user dataset (20), which specifies at least one input dataset (21) for an AI module (31), wherein the AI module (31) is designed to calculate an output dataset (3) for the input dataset (21), wherein the user dataset (20) comprises at least one target specification (25) which specifies a value of a data item (26) in an output dataset (3) of the AI module (31); - loading at least one optimization task (16) which specifies a particular metric (14) and/or a similarity metric (15); - computing at least one solution for the at least one optimization task (16) as an explanation dataset (2) taking the user dataset (20) and the AI module (31) into consideration and applying at least one optimization method (17), wherein the AI module (31) is designed to compute for the explanation dataset (2) an output dataset (3) which comprises the data item (26) specified by the target specification (25); - providing the explanation dataset (2) for the AI module (31).
机译:很难向用户解释AI模块的决定。本发明涉及用于为AI模块(31)提供解释数据集(2)的方法,包括: - 接收用户数据集(20),其指定AI模块的至少一个输入数据集(21) (31),其中AI模块(31)被设计为计算输入数据集(21)的输出数据集(3),其中用户数据集(20)包括至少一个目标规范(25),其指定值AI模块(31)的输出数据集(3)中的数据项(26); - 加载至少一个优化任务(16),它指定特定的度量标准(14)和/或相似度量(15); - 计算至少一个优化任务(16)的至少一个解决方案,作为考虑用户数据集(20)和AI模块(31)的说明数据集(2)考虑并应用至少一个优化方法(17),其中AI模块(31)被设计为计算用于解释数据集(2)的输出数据集(3),该输出数据集(3)包括由目标规范(25)指定的数据项(26); - 为AI模块(31)提供解释数据集(2)。

著录项

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