Expert System
Expert systems are complex AI programs which solves expert task problems also called expert level problems which are normally solved by human experts.
To solve problems, Expert systems requires
- Substantial domain knowledge base which must be built as efficiently as possible.
- Reasoning Mechanisms
- Explanatory Facility
Architecture of a Typical Expert System
Knowledge Base
- The knowledge base contains the relevant knowledge necessary for understanding, formulating and solving problems. It includes two basic elements
- facts such as the problem situation and the theory of the problem area, and
- special heuristics or rules that direct the use of knowledge to solve specific problems in a particular domain. The heuristics express the informal judgmental knowledge in an application area. Knowledge is primary raw material of expert system.
Inference Engine
- The brain of expert system is the inference engine, which is also known as the control structure or the rule interpreter.
- This is a computer program that provides a methodology for reasoning about the information in the knowledge base
- Reasoning using forward chaining backward chaining or some combination of two. Because the ES are usually written as rule-based system, forward chaining, backward chaining or some combination of two is usually used. MYCIN used backward chaining to discover what organisms were presents then it used forward chaining to reason from the organisms to a treatment regime.
User
- User of the designed system.
- Expert system contain a language processor for friendly, problem-oriented communication between the user and the computer. This communication can best be carried out in a natural language.
Explanation Facility
- People will not accept results unless they have been convinced of the accuracy of the reasoning process that produced these result. For example; In medicine, a doctor must accept the ultimate responsibility for a diagnosis, even if that diagnosis was arrived at with considerable help from a program. Thus, it is important that the reasoning process used in such programs proceed in understandable steps and enough meta-knowledge (knowledge about the reasoning process) be available so the explanations of those steps can be generated.
Knowledge Engineer
- Interviews Domain Expert to obtain knowledge
Examples of Expert System
- MYCIN
- PROSPECTOR
- DESIGN ADVISOR
Types of problem domains that ES can solve
Broadly, there are 6 categories of problem domains the ES can solve.
- Inferring Category
I. Interpretation : Inferring situation descriptions from sensors
II. Prediction : Inferring consequences of given situations
III. Diagnosis : Inferring malfunction from observable
IV. Monitoring : Comparing observations to expectations
V. Repair : Recovering from malfunctions
- Design : Configuring objects subject to constraints
- Optimization : Improving open design
Planning : Designing action