What is an expert system?
a computerised system that attempts to reproduce the decision-making process of an expert human being.
they are designed to try and replicate the judgement of a human who has expert knowledge in a field
Expert systems are capable of.. (10)
1: Interpreting input
2: Instructing / assisting a human
3: Advising
4: Explaining
5: Diagnosing
6: Demonstrating
7: Deriving solutions
8: Suggesting alternative options
9: Predicting results
10: Justifying conclusion
Expert systems are not capable of.. (4)
1: Substituting / replacing humans
2: Human capabilities
3: Producing accurate output if knowledge base is inadequate
4: Refining knowledge (making changes to improve result)
Knowledge base (+ 2 types)
a database that allows the storage and retrieval of knowledge provided by experts
factual knowledge: widely shared, general knowledge
heuristic knowledge: more personal, acquired through experience or reasoning
Rule base
a set of rules used to produce a decision.
used by the inference engine^ as a base for decisions
each rule contains IF…THEN and sometimes AND, OR
Inference engine
makes judgements and reasoning using the knowledge base and user responses
produces reasoning based on rule base^
User interface
The way the user interacts with the expert system.
Have a range of selection processes or typing methods to allow the user to provide responses.
Advantages of expert systems (5)
- Provide answers to questions that are outside a user’s knowledge
- Aid professionals in areas where their knowledge is weaker
- Consistent answers
- 24/7 access
- Reduce time taken to solve a problem (quicker than human interaction)
Disadvantages of expert systems (4)
- Do not have common sense, cannot have creative approach
- Errors in the inference engine / knowledge base will cause result to have errors
- Any changing environment’s info must be manually updated
- Expensive (time and effort duh)
