Rule Based System

What is a Rule Based System?

Computers cannot speak and understand language in the same way humans do. The nuances of semantics, diction, and intent are too broad for a computer to understand directly. Instead, humans give the computer a set of rules which define the way to process incoming information. While there are specific forms of rule-based systems in which the computer assists in the defining of its rules, however that machine learning approach is often thought to be separate when understanding rule based systems. 

How does a Rule Based System work?

Rule based systems begin with humans programming a set of instructions into a computer. Rule based systems are often different from each other in practice, while remaining similar in principle. For example, a doctor may incorporate the assistance of a computer with a rule based system for aiding the diagnosis process. Alternatively, a rule based system may be applied to game strategy, helping guide a chess player for example. 

Source

Every rule based system contains four basic components. Firstly, the system contains a set of rules, also known as the rule base, and acts as the domain of knowledge for the computer. Second, there is an interference engine, also called the semantic reasoner. This component is responsible for interpretation of the rules and taking action accordingly. The interference engine works in three steps: match, conflict-resolution, and act. Third, the system contains a temporary working memory, with which the interference engine executes a production system program. Lastly, the rule based system contains a user interface, allowing humans to continue to add, subtract, or change the ways in which input and output signals are received and sent.