Ocena predyspozycji operatora w zadaniach decyzyjnych w inteligentnym systemie interakcji z urządzeniami technicznymi

W artykule przedstawiono nową koncepcję oceny predyspozycji operatora w zadaniach decyzyjnych w inteligentnych systemach interakcji z urządzeniami technicznymi. Opracowany inteligentny system dokonuje analizy, sprawdzania i oceny predyspozycji operatora oraz nadzorowania i optymalizacji procesu oceny. System oceny predyspozycji przedstawiono w przykładowym zastosowaniu w systemie interakcji za pomocą mowy i języka naturalnego pomiędzy urządzeniami technicznymi i ich operatorami, który zawiera inteligentne mechanizmy służące do identyfikacji biometrycznej operatora, rozpoznawania słów składowych i całych komunikatów operatora, analizy składni i skutków poleceń, oceny bezpieczeństwa poleceń, nadzorowania procesu, oraz oceny reakcji operatora.

In this paper, a new concept of assessment of operator's ability for decision making tasks in intelligent interaction systems with technical devices is presented. The developed intelligent system performs analyses, evaluation and assessment of operator's ability, as well as supervision and optimization of the assessment process. The assessment system of operator's ability is presented in exemplary application in an interaction system by speech and natural language between technical devices and their operators, which consists of the intelligent mechanisms of operator biometric identification, speech recognition, word and command recognition, command meaning and effect analysis, command safety assessment, process supervision, and operator reaction assessment. In the paper, a review of selected issues is carried out with regards to intelligent interaction layers (Fig. 1), process supervision systems (Fig. 2), intelligent interaction systems (Figs. 3, 4), assessment of operator's ability for decision making tasks (Figs. 5, 6, 7), as well as recognition and evaluation of speech commands in natural language. Application of hybrid neural networks allows recognition of commands in natural language with similar meanings but different lexico-grammatical patterns, which will undoubtedly be the most important way of interaction between humans and devices. The condition of the effectiveness of the presented system is to equip it with mechanisms of command meaning and effect analysis, as well as safety assessment. The condition for safe communication between operators and technical devices is analyzing the state of the technical device and process before the command is given and using artificial intelligence for effect analysis and safety assessment of the command. The development of a basis of building and applying systems of control, supervision and optimization of processes which communicate an operator with a technical device, is an important goal. These systems allow remote control of the process quality by an operator being in any distance. It is very significant for development of new effective and flexible methods of control. The system for remote control, supervision and optimization provides an innovative solution using more complete advantages of applied technological processes nowadays. The presented solution can belong to attempts of creation of the standard of mobile applications for control, supervision and optimization of processes using two-way speech communication between technical devices and their operators.