End-user development of knowledge bases for semi-automated formation of task cards

Abstract

The complexity of creating artificial intelligence applications remains high. One of the factors that cause such complexity is the high qualification requirements for developers in the field of programming. Development complexity can be reduced by using methods and tools based on a paradigm known as End-user development. One of the problems that requires the application of the methods of this paradigm is the development of intelligent systems for supporting the search and troubleshooting onboard aircraft. Some tasks connected with this problem are identified, including the task of dynamic formation of task cards for troubleshooting in terms of forming a list of operations. This paper presents a solution to this problem based on some principles of End-user development: model-driven development, visual programming, and wizard form-filling. In particular, an extension of the Prototyping expert systems based on transformations technology, which implements the End-user development, is proposed in the context of the problem to be solved for Sukhoi Superjet aircraft. The main contribution of the work is as follows: expanded the main technology method by supporting event trees formalism (as a popular expert method for formalizing scenarios for the development of problem situations and their localization); created a domain-specific tool (namely, Extended event tree editor) for building standard and extended event trees, including for diagnostic tasks; developed a module for supporting transformations of XML-like event tree representation format for the knowledge base prototyping system – Personal knowledge base designer. A description of the proposed extension and the means of its implementation, as well as an illustrative example, are provided.

End-user engineering of ontology-based knowledge bases

“…In [21], an end-user development approach based on model-driven development, visual programming, and wizard form-filling is proposed to develop intelligent systems for supporting the search and troubleshooting onboard aircrafts. The approach is domain-specific as it is based on the use of event trees for formalizing scenarios for problem situations.…”