...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Knowledge and information systems >Dynamic evaluation of the development process of knowledge-based information systems
【24h】

Dynamic evaluation of the development process of knowledge-based information systems

机译：动态评估基于知识的信息系统的开发过程

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Codifying expert domain knowledge is a difficult and expensive task. To evaluate the quality of the outcome, often the same domain expert or a colleague of similar expertise is relied on to undertake a direct evaluation of the knowledge-based system or indirectly by preparing appropriate test data. During an incremental knowledge acquisition process, a data stream is available, and the knowledge base is observed and amended by an expert each time it produces an error. Using the kept record of the system's performance, we propose an evaluation process to estimate its effectiveness as it gets evolved. We instantiate this process for an incremental knowledge acquisition methodology, Ripple Down Rules. We estimate the added value in each knowledge base update. Using these values, the decision makers in the organisation employing the knowledge-based information system can apply a cost-benefit analysis of the continuation of the incremental knowledge acquisition process. They can then determine when this process, involving keeping an expert online, should be terminated. As a result, the expert is not kept on-line longer than it is absolutely necessary. Hence, a major expense in deploying the information system - the cost of keeping a domain expert on-line - is reduced.
机译：整理专家领域知识是一项困难且昂贵的任务。为了评估结果的质量，通常依赖同一领域的专家或具有类似专业知识的同事对基于知识的系统进行直接评估，或者通过准备适当的测试数据进行间接评估。在增量式知识获取过程中，数据流可用，并且每次产生错误时，专家都会观察并修改知识库。利用系统性能的记录，我们提出了一个评估过程，以评估其发展过程的有效性。我们使用渐进式知识获取方法Ripple Down Rules实例化此过程。我们估计每个知识库更新中的增加值。使用这些值，采用基于知识的信息系统的组织中的决策者可以对增量知识获取过程的持续进行成本效益分析。然后，他们可以确定何时终止涉及专家在线的此过程。结果，专家的在线时间不会超过绝对必要的时间。因此，减少了部署信息系统的主要费用-保持领域专家在线的成本-。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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