Knowledge engineering is a field of artificial intelligence (AI) that tries to emulate the judgment and behavior of a human expert in a given field.
Knowledge engineering is the technology behind the creation of expert systems to assist with issues related to their programmed field of knowledge. Expert systems involve a large and expandable knowledge base integrated with a rules engine that specifies how to apply information in the knowledge base to each particular situation. The systems may also incorporate machine learning so that they can learn from experience in the same way that humans do. Expert systems are used in various fields including healthcare, customer service, financial services, manufacturing and the law.Content Continues Below
Using algorithms to emulate the thought patterns of a subject matter expert, knowledge engineering tries to take on questions and issues as a human expert would. Looking at the structure of a task or decision, knowledge engineering studies how the conclusion is reached. A library of problem-solving methods and a body of collateral knowledge are used to approach the issue or question. The amount of collateral knowledge can be very large. Depending on the task and the knowledge that is drawn on, the virtual expert may assist with troubleshooting, solving issues, assisting a human or acting as a virtual agent.
Scientists originally attempted knowledge engineering by trying to emulate real experts. Using the virtual expert was supposed to get you the same answer as you would get from a human expert. This approach was called the transfer approach. However, the expertise that a specialist required to answer questions or respond to issues posed to it needed too much collateral knowledge: information that is not central to the given issue but still applied to make judgments.
A surprising amount of collateral knowledge is required to enable analogous reasoning and nonlinear thought. Currently, a modeling approach is used where the same knowledge and process need not necessarily be used to reach the same conclusion for a given question or issue. Eventually, it is expected that knowledge engineering will produce a specialist that surpasses the abilities of its human counterparts.