UDC 004.891
ASPECTS OF THE DEVELOPMENT OF QUESTION AND ANSWER SYSTEM ARCHITECTUREFOR BIG DATA PROCESSING BASED ON NEURAL NETWORK MODELING
L. A. Demidova, Dr. in technical sciences, Full Professor, Department of Corporate Information Systems, Institute of Information Technologies, MIREA – Russian Technological University, Moscow, Russia;
orcid.org/0000-0003-4516-3746, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
N. A. Moroshkin, post-graduate student, Department of Corporate Information Systems, Institute of Information Technologies, MIREA – Russian Technological University, Moscow, Russia;
orcid.org/0009-0002-8787-2452, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The article discusses the aspects of neural network question-answer modeling based on visual data, which has recently become increasingly popular. The aim of this work is to develop and justify the architecture of a question-answering system in the context of working with streaming big data or end-to-end applications. Two architectures of a question-answer system are presented for end-to-end queries and for stream processing in the context of the problem being solved of neural network question-answer modeling based on visual data.
Key words: : visual question-answer modeling, multimodality, artificial neural networks, end-to-end architecture, stream data processing architecture