Chapter Four

Knowledge Application Systems:

Systems that Utilize Knowledge

1
 Outline

 Technologies for Applying Knowledge

 Types of Knowledge Application Systems

 Developing Knowledge Application Systems

2
 Technologies for Applying Knowledge

• Knowledge application systems are typically enabled by intelligent

technologies.
• Both mechanisms and technologies can support knowledge application
systems by facilitating the knowledge management processes of routines and
direction.
• Mechanisms facilitating direction include help desks, and support centers;

• whereas mechanisms facilitating routines include organizational policies,

work practices, and standards.

3
 Technologies for Applying Knowledge
• Artificial Intelligence (AI) is useful as a facilitating technology for
knowledge management.
• AI refers to enabling computers to perform tasks that resemble/look like
human thinking ability.
• Definitions for AI range from:

• systems that act like humans,

• systems that think like humans,

• systems that think rationally,

• to systems that act rationally.

4
 Technologies for Applying Knowledge
• Systems that act like humans refer to those that pass the Turing Test, which
refers to a computer passing a test by a human interrogator, who cannot tell
whether the responses came from a person or not.
• Demonstrate human intelligence.

• The Turing Test is a method of inquiry in AI for determining whether or not a

computer is capable of thinking like a human being
• Systems that think like humans refer to a computer program whose input to
output behavior matches those of humans, for example when solving problems,
like playing chess or performing a medical diagnosis.

5
 Cont..
• Systems that think rationally refer to those that follow a specific logic to
solve a problem.
• Finally, systems that act rationally refer to those computer agents that
are expected to have specific characteristics that enable them to operate
autonomously within their environments, and even adapt to change in the
face of uncertainty.

6
 Technologies for Applying Knowledge
• knowledge-based systems is one of the areas in AI that has the greatest
popularity and which refers as knowledge application systems.
• Other areas of research within AI include natural language understanding,
classification, diagnostics, machine learning, planning and scheduling,
robotics, and computer vision.
• Next we describe the two most relevant intelligent technologies that underpin
the development of knowledge application systems: rule-based expert systems
and case-based reasoning

7
 Rule-Based Systems
• The development of knowledge-based systems had been based on the use of rule
or models to represent the domain knowledge.
• The development of such systems requires the collaboration of a subject matter
expert with a knowledge engineer, the latter being responsible for the elicitation
and representation of the expert`s knowledge.
• The process of developing knowledge application systems requires eliciting the
knowledge from the expert and representing it in a form that is usable by
computers. This process is called knowledge engineering.
• Knowledge engineers typically build knowledge application systems by first
interviewing in detail the domain expert and representing the knowledge more
commonly in a set of experiential or rules-of-thumb.

8
 Rule-Based Systems
• Experts develop these rules-of-thumb over years of practical experience at
solving problems.
• In order for the computer to understand these rules-of-thumb, we represent
them as production rules or IF-THEN statements.
• For example: IF the number of employees is less than 500, THEN the firm is a
small business.
• The IF portion is the condition (also premise or antecedent), which tests the
truth-value of a set of assertions.
• If the statement is true, the THEN part of the rule (also action, conclusion, or
consequence) is also inferred as a fact.

9
 Rule-Based Systems
• A classic example of a rule-based system is the domain-specific expert
system that uses rules to make deductions or choices.
• For example, an expert system might help a doctor choose the correct
diagnosis based on a cluster of symptoms
• Rule-based systems have some disadvantages.

• One is that in many circumstances, the number of rules that may be needed to
properly represent the domain may be quite large.
• Expert systems with such a large number of rules offer many disadvantages,
namely
1. Difficulty in coding, verifying, validating, and maintaining the rules; and
2. Reduction in the efficiency of the inference engine executing the rules .

10
 Case-Based Reasoning
• Case-based reasoning (CBR) is the process of solving new problems
based on the solutions of similar past problems.
• It is an experience-based approach to solving new problems by adapting
previously successful solutions to similar/identical problems.
• CBR is an AI technique designed to mimic/resemble/imitate human
problem solving.
• In CBR, the “intelligent” reuse of knowledge formal ready-solved
problems, or cases, relies on the premise that the more similar two
problems are, the more similar their solutions will be.

11
 Case-Based Reasoning
• Its goal is to mimic the way humans solve problems. When faced with a
new problem, humans search their memories for past problems
resembling the current problem and adapt the prior solution to “fit” the
current problem.
• CBR is a method of analogical reasoning that utilizes old cases or
experiences in an effort to solve problems, critique solutions, explain
anomalous/irregular situations, or interpret situations.

12
 Case-Based Reasoning
 Four step process:

• Retrieve- Gathering from memory an experience closest to the current problem.

• Search for the most similar case to the current problems

• Reuse- Suggesting a solution based on the experience and adapting it to meet

the demands of the new situation.
• Adaptation of solution of the most similar case to the current problem

• Revise- Evaluating the use of the solution in the new context.

• Check for correctness of the adaptation

• Retain- Storing this new problem-solving method in the memory system.

• Saving of accepted solution together with the problem as a separate case in the memory.

13
 Case-Based Reasoning
A typical case-based knowledge application system will consist of the
following processes:

• Search the case library for similar cases. This implies utilizing a search engine
that examines only the appropriate cases and not the entire case library, as it
may be quite large.
• Select and retrieve the most similar case(s). New problems are solved by first
retrieving previously experienced cases. This implies having a means to
compare each examined case to the current problem, quantifying their similarity,
and somehow ranking them in decreasing order of similarity.
• Adapt the solution for the most similar case. If the current problem and the
most similar case are not similar enough, then the solution may have to be
adapted to fit the needs of the current problem. The new problem will be
solved with the aid of an old solution that has been adapted to the new problem.
14
 Case-Based Reasoning
• Apply the generated solution and obtain feedback. Once a solution or
classification is generated by the system, it must be applied to the problem.
• Its effect on the problem is fed back to the CBR system for classification of its
solution (as success or failure).
• Add the newly solved problem to the case library. The new experience is likely
to be useful in future problem solving. This step requires identifying if the new
case is worth adding to the library and placing it in the appropriate location in
the case library.

15
 Constraint-Based Reasoning
• Constraint-based reasoning is an AI technique that uses essentially “what
cannot be done” to guide the process of finding a solution.
• This technique is useful in naturally constrained tasks such as planning and
scheduling.
• problem solving technique that, when given a set of variables and constraints
on these variables, can find a set of values that satisfy all the constraints.
• For example, to schedule a meeting all the individuals that need to attend must
be available at the same time, otherwise the “availability constraint” will be
violated.

16
 Model-Based reasoning
• Model-based reasoning is an intelligent reasoning technique that uses a model of
an engineered system to simulate its normal behavior.
• Create a simulation, or model, of a device, system, or situation and use the
model to find explanations for the system's behavior.
• The simulated operation is compared with the behavior of a real system and
noted discrepancies can lead to a diagnosis;
• Example: In a self-driving car system, the model-based reasoning approach involves
creating a model of the environment, including the road, obstacles, traffic signs, and
signals. The model contains information about speed limits, traffic rules, and the car's
capabilities. Using this model, the system reasons about the current state, predicts
possible future states, and makes decisions such as when to accelerate, brake, or change
lanes based on the model's constraints and objectives.

17
 Diagrammatic Reasoning
• Diagrammatic reasoning is an artificial intelligence technique that aims to understand
concepts and ideas using diagrams that represent knowledge
• understanding of concepts and ideas through the use of diagrams and imagery, versus
linguistic or algebraic representations
• instrumental in developing systems such as Gelernter’s Geometry Machine

18
 Types of Knowledge Application Systems
• Knowledge Application Systems support the process through which some
individuals utilize knowledge possessed by other individuals without actually
acquiring, or learning, that knowledge.
• Knowledge application systems include:
– Help desk systems: An IT help desk is a software platform that helps users
solve their problems through single (or multiple) points of contact.
– enables the companies to resolve customer grievances faster and efficiently
by simply automating the complaint resolution process
– Decision-support systems
– Expert systems:
• Advisory Systems
• fault diagnosis or troubleshooting systems

19
 An expert system

• An expert system is software that attempts to provide an answer to a

problem, or clarify uncertainties where normally one or more human
experts would need to be consulted.
• It is a computer program that is designed to mimic the decision-making
ability of a decision-maker.
• It organizes a set of knowledge about a particular subject. It contains facts
and judgmental knowledge which gives it the ability to guess like a human.
• Expert systems are most common in a specific problem domain, and is a
traditional application and/ or subfield of artificial intelligence.

20
 An expert system (cont.…)
• There are set of rules on which it makes decisions using an if-else
structure.
• A wide variety of methods can be used to simulate the performance
of the expert however common to most are:
– The creation of a knowledge base which uses some knowledge
representation formalism to capture the subject matter expert's
knowledge.
– A process of gathering that knowledge from the subject matter
expert's and codifying it according to the formalism, which is
called knowledge engineering. 21
 An expert system (cont.…)
• Components of Expert System:
– The knowledge base in an expert system represents facts and rules. It contains
knowledge in specific domains along with rules in order to solve problems and
form procedures that are relevant to the domain.
– Inference Engine: The most basic function of the inference engine is to
acquire relevant data from the knowledge base, interpret it, and find a
solution to the user’s problem. Inference engines also have explanatory and
debugging abilities.
– Knowledge acquisition and learning module: This component functions to
allow the expert systems to acquire more data from various sources and
store it in the knowledge base.
– User interface: This component is essential for a non-expert user to interact
with the expert system and find solutions.
– Explanation module: As the name suggests, this module helps in providing
the user with an explanation of the achieved conclusion..

22
 A Decision Support System (DSS)
• DSS is a class of information systems (including but not limited to
computerized systems) that support business and organizational decision-
making activities.
• It is intended to help decision makers to compile useful information from a
combination of raw data, documents, personal knowledge, or business
models to identify and solve problems and make decisions.
• It is an interactive, flexible and adaptable computer system. It is specially
developed for supporting the solution of a non-structured management
problem for improved decision-making.

23
 A Decision Support System…
• Typical information that a decision support application might gather and
present are:
– Inventories of all of your current information assets (including legacy and
relational data sources, and data warehouses),
– Comparative sales figures between one week and the next,

– Projected revenue figures based on new product sales assumptions.

• Types of Decision Support systems are Document-driven, Data-driven,

Knowledge-driven, Model-driven, and Communication-driven.
• Applications include medical diagnosis, business management, agriculture,
rail projects, and many more.
• Examples: GPS route planning, Crop-planning, ERP dashboards, and others.
24
 Expert System Vs decision support system
 Expert System:

 An expert system is built using knowledge and expertise in a specific domain or

field.
 It aims to replicate the decision-making abilities of a human expert by using
rules, algorithms, and heuristics.
 It is typically used to provide solutions or make recommendations based on the
inputs provided by the user.
 The system can also explain its reasoning and provide justification for its
recommendations. Example: A medical diagnosis expert system that uses
patient symptoms and medical knowledge to suggest possible illnesses and
treatments.
25
 DSS
 A decision support system focuses on helping users analyze data and information to
make informed decisions.
 It provides tools and techniques to process and evaluate data, visualize trends, and
perform various analytical calculations. It is primarily used by decision-makers to
interpret information, explore alternatives, and develop insights.
 The system does not possess a fixed set of rules or domain expertise but provides
features to assist decision-making.
 Example: A business analytics decision support system that integrates data from
various sources, enables users to develop and compare scenarios, and generates reports
and visualizations for strategic decision-making.
 In summary, an expert system relies on domain-specific knowledge and rules to
provide recommendations or solutions, while a decision support system focuses on
providing tools and analysis capabilities to help users make decisions based on data
and information. 26
Developing Knowledge
Application Systems
 Knowledge engineering (KE)
Knowledge
• KE is the process of building a knowledge base Acquisition
(Extract the
through extracting the knowledge from the human Knowledge)
expert and/or documents and/or data.
• Knowledge engineering is the process of:
Knowledge
– Extracting the knowledge from the human Representation
(choose KR Method &
expert or codified documents or data. reasoning strategy)

– Choosing knowledge representation formalism

– Choosing reasoning & problem solving
strategy. Knowledge
base
28
 Knowledge engineering (KE)

• A knowledge engineer is someone who investigates a particular

domain, determines what concepts are important in that domain, &
creates a formal representation of the objects & relations in the
domain.
• A knowledge engineer has to decide what objects & relations are
worth representing, and which relations hold among which objects.

29
 The Two Main Tasks of Knowledge Engineer
• Knowledge capture/acquisition

– The knowledge engineer interview the domain experts to be educated about

the domain and to elicit the required knowledge, in a process called
knowledge acquisition.
– Alternatively, the KE has to consult codified materials or else apply data
mining to extract hidden knowledge from large data
• Knowledge Representation

– Techniques such as logic are a powerful tool for KR and reasoning. However,
such techniques consists of only the syntax, semantics and proof theory.
– KR techniques do not offer any guidance as to what facts should be expressed,
nor what vocabulary should be used to express them
– Knowledge base is used to store facts and rules.
30
 Developing knowledge application system
• Developing a Case-Based Reasoning (CBR) knowledge application system involves a
series of steps to ensure a successful implementation.
 Problem Analysis: Identify the problem domain where the CBR system will be
applied. Determine the specific knowledge or expertise required to solve the
problem using CBR.
 Case Base Design: Create a case base, which is a repository of past problem-solving
cases. These cases should cover a wide range of scenarios and include relevant
attributes, such as symptoms, diagnoses, treatments, and outcomes.
 Case Representation: Develop a case representation scheme to structure and
organize the information within each case.
 Similarity Measurement: Define a similarity function that calculates the similarity
between a new problem and the cases in the case base.
 Retrieval Strategy
 Adaptation and Solution Generation: that modifies the retrieved cases to fit the
current problem context
 Case Learning:
 User Interface:
 Integration and Deployment: Integrate the CBR knowledge application system into
the existing infrastructure or deploy it as a standalone application. 31
•
Cont..
Developing rule based reasoning knowledge application system
 Identify the domain: Choose the specific domain or area of expertise where the RBR
system will be implemented.
 Gather knowledge sources: Collect the relevant rules, facts, and expert knowledge
from domain experts or existing documentation.
 Formalize rules: Convert the collected knowledge into a formal rule-based
representation.
 Develop the inference engine: Implement the reasoning engine responsible for
applying the rules and making decisions based on given inputs.
 Design the user interface: Create an intuitive and user-friendly interface to interact
with the Knowledge Application System.
 Integrate with data sources: Connect the RBR system with relevant data sources,
such as databases or external APIs, to retrieve the required data for rule evaluation.
 Test and validate: verifying the correctness of rule execution, evaluating the system's
performance, and validating the system's output against known test cases or expert
opinion.
 Refine and optimize: Continuously improve the system by incorporating feedback
from users, refining the rules, and optimizing the overall performance.
 Deploy and maintain:
32
 Group - Assignment I (10%)
• Review paper/article which is conducted on expert
systems, decision support systems, and knowledge-based
systems.

33