KEA 2.0 : An Internet based Expert System Development Tool
An improved version of the above described KEA system has been developed to function as an Internet based agent.
This aims to overcome the problem of restricted access for experts as well as increasing the number of presented cases.
KEA 2 was therefore completely rewritten using the Microsoft programming language Visual c++ 6.0.
The software requires Microsoft Windows operating system and client / server functionality.
The server side utilizes DBMS (Microsoft SQL Server).
MCRDR can be represented as an n-ary tree.
MCRDR evaluates all the rules in the first level of KB.
It then evaluates the rules at the next level of refinement for each rule that was satisfied and so on.
The process stops when there are no more children to evaluate or when none of these rules can be satisfied by the case in hand.
It thus ends up with multiple paths, with each path representing a particular refinement sequence and hence multiple conclusions.
The structure of an MCRDR knowledge base can be drawn as an n-ary tree with each node representing a rule.
The MCRDR base for KEA2.0 is built and maintained by the experts.
A new case is added into the knowledge base system when a user's query is not satisfactorily handled,
i.e. the case (query) has been classified incorrectly or does not exist in the rule tree.
Thus, the knowledge acquisition for the system is achieved by adding the new cases upon the occurrence of an error in the system,
or more accurately when a request can not be classified properly.
Since the KEA is accessible via the WWW the knowledge acquisition can take place at any time and from any location.
|
