This paper provides a comparative analysis of the experience of developing domestic mathematical and software for creating the most complex and in–demand classes of dynamic intelligent systems operating in real time: dynamic integrated expert systems (IES) and real-time intelligent decision support systems (RT IDSS). The conceptual and functional features of the original problem-oriented methodology of automated software construction for a wide class of applied IESs (static, dynamic, tutoring) with extensible functionality and scalable architecture based on the integration of models, methods, and tools of knowledge-based systems (expert systems) with methods and tools from other fields are investigated knowledge. The methods of implementing this methodology within the framework of the Workbench class tools supporting it in the form of an intelligent software environment of the AT-TECHNOLOGY tool complex are considered and the features of prototyping technology for applied IES, including dynamic IES, using the basic components of the environment (technological knowledge base, intelligent planner, ontology of typical IES architectures, etc.) are described. A comparison is made of methods and technologies for constructing dynamic IES and RT IDSS, commensurate with each other in terms of the composition and complexity of the architecture, classes of problems to be solved, the presence of NON-factors, and other parameters (the formulation of the decision-making problem, the features of taking temporal factors into account when modeling inference, the features of architecture and individual components, modeling the external environment). It is noted that for RT IDSS, the issues of automation and intellectualization of software development processes, especially at the time-consuming stages of system analysis and design, were not raised, unlike dynamic IES, developed based on a problem-oriented methodology and intelligent software environment tools that provide instrumental support for all stages of the software design, development and maintenance cycle of applied IES. Using the example of the RT IDSS architecture, a new experimental task is set, the purpose of which is to explore the conceptual, functional and technological possibilities of using a well-tested problem-oriented methodology and technology for automated software construction of dynamic IES using the intelligent software environment of the AT-TECHNOLOGY workbench. The main advantages are related to reducing the complexity and intellectual burden on developers, reducing risks and percentage of erroneous actions, project deadlines, etc. aspects of the influence of the human factor on the software development of applied intelligent systems. The preliminary results of experimental software modeling of the prototyping processes of the basic components of the RT IDSS architecture presented in the paper (building a model of the RT IDSS architecture, developing a standard design procedure, etc.) have shown, in practice, the complete acceptability of the basic provisions of the problem-oriented methodology provided for dynamic IES and for automating the processes of building RT IDSS using an intelligent software environment of instrumental the AT-TECHNOLOGY workbench.
Rybina et al. (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: