Standard

An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG. / Grekhova, Anastasiya; Palchunov, Dmitry; Shishkin, Alexander и др.

2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE). Institute of Electrical and Electronics Engineers Inc., 2025. стр. 1-6.

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование

Harvard

Grekhova, A, Palchunov, D, Shishkin, A & Zaitsev, A 2025, An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG. в 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE). Institute of Electrical and Electronics Engineers Inc., стр. 1-6, 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering, Новосибирск, Российская Федерация, 14.11.2025. https://doi.org/10.1109/APEIE66761.2025.11289384

APA

Grekhova, A., Palchunov, D., Shishkin, A., & Zaitsev, A. (2025). An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG. в 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE) (стр. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APEIE66761.2025.11289384

Vancouver

Grekhova A, Palchunov D, Shishkin A, Zaitsev A. An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG. в 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE). Institute of Electrical and Electronics Engineers Inc. 2025. стр. 1-6 doi: 10.1109/APEIE66761.2025.11289384

Author

Grekhova, Anastasiya ; Palchunov, Dmitry ; Shishkin, Alexander и др. / An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG. 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE). Institute of Electrical and Electronics Engineers Inc., 2025. стр. 1-6

BibTeX

@inproceedings{35be3551083c46159cf71f1afe3fcb42,
title = "An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG",
abstract = "The increasing volume of regulatory documentation in construction and engineering complicates decision-making and raises the risk of errors and non-compliance. Existing search systems fail to provide sufficient semantic understanding of user needs, while large language models suffer from hallucinations and incomplete answers. This paper presents a hybrid intelligent assistant that integrates retrieval-augmented generation, ontological modeling, and multi-agent architecture to address these limitations. The system extracts entities and situations from regulatory documents to build an ontological domain model, enabling both semantic interpretation and automated consistency verification of generated responses. Vector similarity measures are combined with concept-level ontological relationships to improve retrieval accuracy. A multi-agent architecture ensures modularity and scalability, supporting document analysis, query history tracking, personalized response generation based on user context, and precise reference linking to primary sources. The proposed approach is evaluated in the construction domain, where practitioners must simultaneously consider standards at multiple regulatory levels. The practical contribution lies in reducing compliance costs and risks while increasing efficiency in handling complex multi-level regulatory frameworks. Future research will focus on cross-domain implementation and comprehensive evaluation of system performance.",
keywords = "нормативные документы, интеллектуальный ассистент, онтологическое моделирование, семантический поиск, Retrieval-Augmented Generation (RAG), мультиагентные системы, автоматизация обеспечения соответствия требованиям, Regulatory documents, intelligent assistant, ontological modeling, semantic search, Retrieval-Augmented Generation, multi-agent systems, compliance automation",
author = "Anastasiya Grekhova and Dmitry Palchunov and Alexander Shishkin and Alexander Zaitsev",
note = "A. Grekhova, D. Palchunov, A. Shishkin and A. Zaitsev, {"}An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG,{"} 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE), Novosibirsk, Russian Federation, 2025, pp. 1-6, doi: 10.1109/APEIE66761.2025.11289384. This work was supported by a grant for research centers, provided by the Analytical Center for the Government of the Russian Federation in accordance with the subsidy agreement (agreement identifier 000000D730324P540002) and the agreement with the Novosibirsk State University dated December 27, 2023 No. 70-2023-001318.; 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering, APEIE ; Conference date: 14-11-2025 Through 16-11-2025",
year = "2025",
month = nov,
day = "18",
doi = "10.1109/APEIE66761.2025.11289384",
language = "English",
isbn = "979-8-3315-5917-5",
pages = "1--6",
booktitle = "2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

RIS

TY - GEN

T1 - An Intelligent Assistant for Working with Regulatory Documents Based on Ontological Modeling and RAG

AU - Grekhova, Anastasiya

AU - Palchunov, Dmitry

AU - Shishkin, Alexander

AU - Zaitsev, Alexander

N1 - Conference code: 17

PY - 2025/11/18

Y1 - 2025/11/18

N2 - The increasing volume of regulatory documentation in construction and engineering complicates decision-making and raises the risk of errors and non-compliance. Existing search systems fail to provide sufficient semantic understanding of user needs, while large language models suffer from hallucinations and incomplete answers. This paper presents a hybrid intelligent assistant that integrates retrieval-augmented generation, ontological modeling, and multi-agent architecture to address these limitations. The system extracts entities and situations from regulatory documents to build an ontological domain model, enabling both semantic interpretation and automated consistency verification of generated responses. Vector similarity measures are combined with concept-level ontological relationships to improve retrieval accuracy. A multi-agent architecture ensures modularity and scalability, supporting document analysis, query history tracking, personalized response generation based on user context, and precise reference linking to primary sources. The proposed approach is evaluated in the construction domain, where practitioners must simultaneously consider standards at multiple regulatory levels. The practical contribution lies in reducing compliance costs and risks while increasing efficiency in handling complex multi-level regulatory frameworks. Future research will focus on cross-domain implementation and comprehensive evaluation of system performance.

AB - The increasing volume of regulatory documentation in construction and engineering complicates decision-making and raises the risk of errors and non-compliance. Existing search systems fail to provide sufficient semantic understanding of user needs, while large language models suffer from hallucinations and incomplete answers. This paper presents a hybrid intelligent assistant that integrates retrieval-augmented generation, ontological modeling, and multi-agent architecture to address these limitations. The system extracts entities and situations from regulatory documents to build an ontological domain model, enabling both semantic interpretation and automated consistency verification of generated responses. Vector similarity measures are combined with concept-level ontological relationships to improve retrieval accuracy. A multi-agent architecture ensures modularity and scalability, supporting document analysis, query history tracking, personalized response generation based on user context, and precise reference linking to primary sources. The proposed approach is evaluated in the construction domain, where practitioners must simultaneously consider standards at multiple regulatory levels. The practical contribution lies in reducing compliance costs and risks while increasing efficiency in handling complex multi-level regulatory frameworks. Future research will focus on cross-domain implementation and comprehensive evaluation of system performance.

KW - нормативные документы

KW - интеллектуальный ассистент

KW - онтологическое моделирование

KW - семантический поиск

KW - Retrieval-Augmented Generation (RAG)

KW - мультиагентные системы

KW - автоматизация обеспечения соответствия требованиям

KW - Regulatory documents

KW - intelligent assistant

KW - ontological modeling

KW - semantic search

KW - Retrieval-Augmented Generation

KW - multi-agent systems

KW - compliance automation

UR - https://www.scopus.com/pages/publications/105031772907

U2 - 10.1109/APEIE66761.2025.11289384

DO - 10.1109/APEIE66761.2025.11289384

M3 - Conference contribution

SN - 979-8-3315-5917-5

SP - 1

EP - 6

BT - 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering

Y2 - 14 November 2025 through 16 November 2025

ER -

ID: 75609819