Knowledge based agents in AI

Artificial IntelligenceMachine LearningDatabase

Knowledge-based agents represent searchable knowledge that can be reasoned. These agents maintain an internal state of knowledge, take decisions regarding it, update the data, and perform actions on this data based on the decision. Basically, they are intelligent and respond to stimuli like how humans react to different situations.

Examples − Based on the user's question (that behaves as the external stimuli), they provide an answer from their knowledge base (the data warehouse where they store basic knowledge) that provides a satisfactory answer to the user’s question.

Knowledge Base Features

It has the below-mentioned features −

Knowledge base (KB)

It is one of key components of a knowledge-based agent. It stores facts and data pertaining to the real-world.

Inference Engine (IE)

It is a knowledge-based system engine that helps infer new knowledge from the existing data within the system.

Actions performed by an agent

When the knowledge-based agent needs to be updated, the inference system comes into picture. It uses a ‘Ask-Tell’ mechanism wherein new data is inferred from pre-existing data. Agent has a knowledge base which contains base knowledge that performs certain actions when it is called.

Actions performed by the knowledge base Agent

It ‘Tells’ its recognitions from its environment and imparts to the knowledge base what it requires.

It ‘Asks’ the knowledge base what actions to perform. It receives answers from the knowledge base. Based on the action selected, the agent executes the action.

Knowledge Base Approaches

A knowledge base can use two approaches −

  • Declarative Approach − Starting with an empty knowledge base, the agents ‘tells’ or fills the knowledge base with data.

  • Procedural Approach − The necessary behaviors are directly converted into code in an empty knowledge-base.

Updated on 14-Oct-2022 11:35:51