Transcript Artificial Intelligence and Expert Systems

Knowledge-Based Systems
in Business Workshop
PAIW-April 2003
Jay E. Aronson
Professor of Management Information
Systems
AI Faculty Fellow
Director: Master of Internet Technology
Program
MIS@Terry College of Business
[email protected]
706/542-0991
www.terry.uga.edu/people/jaronson/
Jay E. Aronson: KBS inBusiness Workshop: PAIW April 2003
1
Material Adapted From
Turban, Efraim, and Jay E. Aronson,
Decision Support Systems and
Intelligent Systems, Prentice Hall,
Upper Saddle River, NJ, 6th edition,
2001/7th edition, 2004.
2
Outline








Artificial intelligence
Expert system/knowledge-based systems
Knowledge Engineering
Knowledge Acquisition
Knowledge Representation
Inferencing
Expert Systems Practicum
Intelligent Systems Development
3
Artificial Intelligence
(Simple Definition)
Behavior by a machine that, if
performed by a human being, would
be called intelligent
4
AI Objectives


Make machines smarter (primary
goal)
Understand what intelligence is
(Nobel Laureate purpose)
 Make
machines more
useful (entrepreneurial
purpose)
5
AI Represents Knowledge
as Sets of Symbols
A symbol is a string of characters that
stands for some real-world concept
Examples




Product
Defendant
0.8
Chocolate
6
How AI Works

AI Programs Manipulate Symbols to Solve
Problems

Symbols and Symbol Structures Form
Knowledge Representation

Artificial Intelligence Dealings Primarily
with Symbolic, Nonalgorithmic Problem
Solving Methods
7
Some Major AI Areas








Expert Systems
Natural Language Processing
Speech Understanding
(Smart) Robotics and Sensory Systems
Neural Computing
Fuzzy Logic
Genetic Algorithms
Intelligent Software Agents
8
Expert Systems/KnowledgeBased Systems


Attempt to Imitate Expert Reasoning
Processes and Knowledge in Solving
Specific Problems
Most Popular Applied AI Technology
– Enhance Productivity
– Augment Work Forces


Narrow Problem-Solving Domain or Tasks
Qualitative Problem-Solving Aspects
9
Expert Systems

Provide Direct Application of
Expertise

Expert Systems Do Not Replace
Experts, But
– Makes their Knowledge and Experience
More Widely Available
– Permits Non Experts to Work Better
10
Expert Systems





Expertise
Transferring Expertise
Inferencing
Rules
Explanation Capability
11
Human Expert Behaviors








Recognize and formulating the
problem
Solve problems quickly and properly
Explain the solution
Learn from experience
Restructure knowledge
Break rules
Determine relevance
Degrade gracefully
12
Transferring Expertise

Objective of an expert system
– To transfer expertise from an expert to a computer
system and
– Then on to other humans (nonexperts)

Activities
–
–
–
–

Knowledge acquisition
Knowledge representation
Knowledge inferencing
Knowledge transfer to the user
Knowledge is stored in a knowledge base
13
Inferencing



Reasoning (Thinking)
The computer is programmed so
that it can make inferences
Performed by the Inference
Engine
14
Rules

IF-THEN-ELSE

Explanation Capability
– By the justifier, or explanation
subsystem

ES versus Conventional Systems
15
Structure of Expert Systems


Development Environment
Consultation (Runtime)
Environment
16
Three Major ES
Components
User Interface
Inference
Engine
Knowledge
Base
17
All ES Components









Knowledge Acquisition Subsystem
Knowledge Base
Inference Engine
User Interface
Blackboard (Workplace)
Explanation Subsystem (Justifier)
Knowledge Refining System
User
Most ES do not have a Knowledge Refinement
Component
18
Knowledge Base


The knowledge base contains the knowledge
necessary for understanding, formulating,
and solving problems
Two Basic Knowledge Base Elements
– Facts
– Special heuristics, or rules that direct the use of
knowledge
– Knowledge is the primary raw material of ES
– Incorporated knowledge representation
19
Inference Engine



The brain of the ES
The control structure (rule
interpreter)
Provides methodology for
reasoning
20
User Interface


Language processor for friendly,
problem-oriented communication
NLP, or menus and graphics
21
The Human Element
in Expert Systems




Expert
Knowledge Engineer
User
Others
22
How Expert Systems Work
Major Activities of
ES Implementation and Use
 Development
 Consultation
 Improvement
23
ES Shell


Includes All Generic ES
Components
But No Knowledge
– EMYCIN from MYCIN
– (E=Empty)
24
Expert Systems (Rule-Based)
Shells/Software Development
Packages









Corvid Exsys
K-Vision
KnowledgePro
XpertRule KBS
G2
Guru
CLIPS
JESS
Many More: Free and Costly
25
Problem Areas Addressed by
Expert Systems










Interpretation systems
Prediction systems
Diagnostic systems
Design systems
Planning systems
Monitoring systems
Debugging systems
Repair systems
Instruction systems
Control systems
26
Expert Systems Benefits










Improved Decision Quality
Increased Output and Productivity
Decreased Decision Making Time
Increased Process(es) and Product Quality
Capture Scarce Expertise
Can Work with Incomplete or Uncertain
Information
Enhancement of Problem Solving and
Decision Making
Improved Decision Making Processes
Knowledge Transfer to Remote Locations
Enhancement of Other MIS
27
Lead to




Improved decision making
Improved products and customer
service
Sustainable strategic advantage
May enhance organization’s
image
28
Problems and Limitations of
Expert Systems







Knowledge is not always readily available
Expertise can be hard to extract from
humans
Expert system users have natural cognitive
limits
ES work well only in a narrow domain of
knowledge
Knowledge engineers are rare and expensive
Lack of trust by end-users
ES may not be able to arrive at valid
conclusions
29
Expert System Success Factors

Most Critical Factors
– Champion in Management
– User Involvement and Training

Plus
– The level of knowledge must be sufficiently high
– There must be (at least) one cooperative expert
– The problem must be qualitative (fuzzy) not
quantitative
– The problem must be sufficiently narrow in scope
– The ES shell must be high quality, and naturally
store and manipulate the knowledge
– A friendly user interface
– Important and difficult enough problem
30
For Success
1. Business applications justified by
strategic impact (competitive
advantage)
2. Well-defined and structured
applications
31
Keep Going!
32
Knowledge Acquisition
Knowledge Engineering
Knowledge acquisition, representation,
validation, inferencing, explanation
and maintenance
– Involves the cooperation of human experts
– Synergistic effect
33
Knowledge Engineering
Process Activities





Knowledge Acquisition
Knowledge Validation
Knowledge Representation
Inferencing
Explanation and Justification
34
Knowledge Engineering Process
Knowledge
validation
(test cases)
Sources of knowledge
(experts, others)
Knowledge
Acquisition
Knowledge
base
Encoding
Knowledge
Representation
Explanation
justification
Inferencing
35
Knowledge Acquisition
Methods

Manual (Interviews)

Semiautomatic (Expert-driven)

Automatic (Computer Aided Induction driven)
36
Interviews


Most Common Knowledge
Acquisition: Face-to-face
interviews
Interview Types
– Unstructured (informal)
– Semi-structured
– Structured
37
Recommendation
Before a knowledge engineer interviews the
expert(s)
1. Interview a less knowledgeable (minor)
expert
– Helps the knowledge engineer
•
•
•
•
•
•
Learn about the problem
Learn its significance
Learn about the expert(s)
Learn who the users will be
Understand the basic terminology
Identify readable sources
2. Next read about the problem
3. Then, interview the expert(s) (much more
effectively)
38
Induction/Knowledge Table
Example


Induction tables (knowledge
maps) focus the knowledge
acquisition process
Choosing a hospital clinic facility
site
39
Induction Table (Knowledge Map) Example
Population
Density
People /
Square Mile
>= 2000
Density
over How
Many Sq.
mi
Numeric,
Region Size
>=4
Number of
Near (within 2
miles)
Competitors
0, 1, 2, 3, ...
Average
Family
Income
Near Public
Transportation?
Decision
(Choices)
Numeric,
$ / Year
Yes, No
Yes, No
0
Yes
>=3500
>=4
1
Yes
>=2
No
<30,000
No
40
Knowledge Table Exercise

Choose a restaurant for lunch in Athens
41
Keep Going!
42
Knowledge Representation
Once acquired,
knowledge
must be organized for use
43
Introduction



A good knowledge representation naturally
represents the problem domain
An unintelligible knowledge representation
is wrong
Most artificial intelligence systems consist of
– Knowledge Base
– Inference Mechanism (Engine)
44

Knowledge Base
– Forms the system's intelligence source
– Inference mechanism uses to reason and draw
conclusions


Inference mechanism: Examines the
knowledge base to answer questions, solve
problems or make decisions within the
domain
Many knowledge representation schemes
– Can be programmed and stored in memory
– Are designed for use in reasoning

Major knowledge representation schemas:
– Production rules
– Frames
45
Production Rules

Condition-Action Pairs
– IF this condition (or premise or antecedent) occurs,
– THEN some action (or result, or conclusion, or
consequence) will (or should) occur
– IF the stop light is red AND you have stopped,
THEN a right turn is OK
46




Each production rule in a knowledge base
represents an autonomous chunk of expertise
When combined and fed to the inference
engine, the set of rules behaves
synergistically
Rules can be viewed as a simulation of the
cognitive behavior of human experts
Rules represent a model of actual human
behavior
47
Forms of Rules

IF premise, THEN conclusion
– IF your income is high, THEN your chance of being
audited by the IRS is high
48
More on Rules

Inclusion of ELSE
– IF your income is high, OR your deductions are
unusual, THEN your chance of being audited by the
IRS is high, OR ELSE your chance of being audited
is low

More Complex Rules
– IF credit rating is high AND salary is more than
$30,000, OR assets are more than $75,000, AND pay
history is not "poor," THEN approve a loan up to
$10,000, and list the loan in category "B.”
– Action part may have more information: THEN
"approve the loan" and "refer to an agent"
49
Advantages of Rules

Easy to understand (natural form of
knowledge)

Easy to derive inference and explanations

Easy to modify and maintain

Easy to combine with uncertainty

Rules are frequently independent
50
Limitations of Rules

Complex knowledge requires many rules

Builders like rules (hammer syndrome)

Search limitations in systems with many
rules
51
Multiple Knowledge Representations


Rules + Frames
Others
Knowledge Representation Must Support



Acquiring knowledge
Retrieving knowledge
Reasoning
52
Considerations for
Evaluating a Knowledge
Representation




Naturalness, uniformity and
understandability
Degree to which knowledge is explicit
(declarative) or embedded in procedural code
Modularity and flexibility of the knowledge
base
Efficiency of knowledge retrieval and the
heuristic power of the inference procedure
53




No single knowledge representation method
is ideally suited by itself for all tasks
Multiple knowledge representations: each
tailored to a different subtask
Production rules and frames works well in
practice
Object-oriented knowledge representations
– Hypermedia
54
Keep Going!
55
Inference Techniques
56
Reasoning in Artificial Intelligence





Knowledge must be processed (reasoned with)
Computer program accesses knowledge for inferencing
Inference engine or control program
Rule interpreter (in rule-based systems)
Directs search through the knowledge base
57
Inferencing with Rules:
Forward and Backward Chaining
– Firing a rule: When all of the rule's hypotheses (the
“if parts”) are satisfied
– Can check every rule in the knowledge base in a
forward or backward direction
– Continues until no more rules can fire, or until a
goal is achieved
58
Forward and Backward Chaining
– Chaining: Linking a set of pertinent rules
– Search process: directed by a rule interpreter
approach:
• Forward chaining. If the premise clauses match the
situation, then the process attempts to assert the conclusion
• Backward chaining. If the current goal is to determine the
correct conclusion, then the process attempts to determine
whether the premise clauses (facts) match the situation
59
Backward Chaining

Goal-driven - Start from a potential conclusion
(hypothesis), then seek evidence that supports
(or contradicts) it

Often involves formulating and testing
intermediate hypotheses (or subhypotheses)
60
Forward Chaining

Data-driven - Start from available information
as it becomes available, then try to draw
conclusions

What to use?
– If all facts available up front (as in auditing) forward chaining
– Diagnostic problems - backward chaining
61
Representing Uncertainty

Numeric

Graphic

Symbolic
62
Numeric Uncertainty Representation

Scale (0-1, 0-100)
– 0 = Complete uncertainty
– 1 or 100 = Complete certainty


Problems with Cognitive Biases
People May be Inconsistent at Different Times
63
Keep Going!
64
Expert Systems Demo

EXSYS (Corvid)
65
Keep Going!
66
Intelligent Systems
Development

(Rapid) Prototyping
67

Prototyping:
ES Development Life Cycle
(PADI)
Nonlinear process
Planning
Analysis
Design
Implementation
Prototype
68
Software Classification:
Technology Levels
Expert System Applications (Specific ES)
Shells
Hybrid Systems
Support Tools, Facilities,
and Construction Aids
Programming Languages
69
Rapid Prototyping
and a Demonstration Prototype

Build a small prototype

Test, improve, expand

Demonstrate and analyze feasibility

Complete design
70
Rapid Prototyping





Crucial to ES development
Small-scale system
Includes knowledge representation
Small number of rules
For proof of concept
71
What We’ve Done

Basic definitions/methods/ideas

Advanced definitions/methods/ideas

How to KBS/ES

KBS/ES with a business focus

Very rich area – still much potential in business
72
Questions
Comments
Opinions
Coffee?
73