Elecitation of Knowledge from Multiple Experts Using Network Inference
Elecitation of Knowledge from Multiple Experts Using Network Inference
复制标题
使用网络推理从多位专家那里获取知识
DOI：
10.1109/69.634748
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
W. Wallace
中科院分区：
文献类型：
--
作者：
R. Rush;W. Wallace
从多个专家那里获取知识通常需要使用群体，因此受到群体动力学固有问题的影响。我们提出了一种用于多专家知识获取的技术，该技术不依赖于使用组，并且可以利用通信和计算中的技术进步，即，互联网该方法使用影响图来表示单个专家对问题情况的理解，并开发了多个专家影响图（MEID），专家知识的复合表示。在回顾了当前多个专家知识获取的方法之后，我们正式定义了MEID，描述了它的构造方式，并讨论了它的解释。我们继续审查的问题，在实施该技术所面临的，并给出一个说明性的例子。最后，我们强调需要为决策辅助工具的用户提供由这些辅助工具产生的规则质量的可辩护措施。MEID方法旨在作为这一方向的第一步。
Eliciting knowledge from multiple experts usually entails the use of groups, and thus is subject to the problems inherent in group dynamics. We present a technique for multiple expert knowledge acquisition that does not rely upon the use of groups and can take advantage of technological advances in communications and computing, i.e., the Internet. The approach uses influence diagrams to represent the individual expert's understanding of the problem situation and develops a Multiple Expert Influence Diagram (MEID), a composite representation of the experts' knowledge. Following a review of present methods for multiple expert knowledge elicitation, we formally define the MEID, describe its manner of construction, and discuss its interpretation. We continue with a review of the issues to be faced in implementation of the technique, and give an illustrative example. Finally, we emphasize the need to provide users of decision aids with defensible measures of the quality of the rules produced by these aids. The MEID-approach is intended to serve as a first step in this direction.