Knowledge-based systems

A knowledge-based system ( WBS) is an intelligent information system that is in the knowledge shown by methods of knowledge representation and modeling and harnessed. The term is often used interchangeably or used as a generic term for expert systems, it can be but also more generally hold for all systems based on knowledge.

Classification

Knowledge-based systems can be considered as a special kind of programming systems, with which a new programming methodology will be advantageous. They are mainly used to solve problems that are difficult to accomplish algorithmic, imperative way.

The inference engine is a calculation mechanism for given with the knowledge base programs. By entering knowledge, the inference engine is programmed. The knowledge is represented declaratively. It consists of factual knowledge (similar to the data in a traditional database ) as well as knowledge of rules, for example in the form of production rules ( if ..., then ... ) present symbolic.

The knowledge-based systems include:

  • Rule-based systems
  • Expert Systems
  • Software Agents

A knowledge-based system is:

  • Easier to understand, because it is sufficient to understand the independent, manageable units of knowledge
  • Easily correctable, because it is sufficient to verify the accuracy of the individual units of knowledge and to change them if necessary,
  • Easier to update according to the growth in knowledge, especially with very diffuse subjects.

In most cases, expert systems are knowledge-based systems, even if they could be theoretically developed on different principles. However, it is not every knowledge-based system already an expert system. This requires some additional components that provide the overall system has the ability to problem solving addition with such use properties that this actually an expert can be replaced.

Components / ingredients

The core components of a knowledge-based system are:

  • Knowledge base - knowledge is stored here in declarative form, the knowledge includes facts, rules and generic ( problem area ), as well as case-specific ( problem solving case ) knowledge
  • Inference - knowledge of the knowledge base is processed here, while new facts and rules are derived
  • User interface (User Inferface ) - interface for communication with the user or the knowledge engineer

These are mainly used for complex applications - for example, expert systems - yet:

  • Knowledge acquisition component - ability to build and expand the knowledge base ( manual or automatic)
  • Explanation component - Gives the user information on finding a solution, so that they can understand ( How and Why )

Purpose

  • Data interpretation
  • Monitoring
  • Diagnosis
  • Therapy
  • Planning
  • Design
  • Forecast

For example, knowledge-based systems are used in medical computer science, from the data of a patient problem-solving (eg which diagnosis which therapy ) derive. Other applications and examples are described in detail with expert system.

Development methods

For the planning and implementation of a WBS are various planning and development methods. Here are:

  • KADS - Amsterdam
  • Protégé - Stanford
  • Artificial intelligence
Declaration (computer programming)
826874
de