<?xml version="1.0" encoding="UTF-8"?>
<article article-type="research-article" dtd-version="1.3" xml:lang="ru" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="https://metafora.rcsi.science/xsd_files/journal3.xsd">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">moitvivt</journal-id>
      <journal-title-group>
        <journal-title xml:lang="ru">Моделирование, оптимизация и информационные технологии</journal-title>
        <trans-title-group xml:lang="en">
          <trans-title>Modeling, Optimization and Information Technology</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="epub">2310-6018</issn>
      <publisher>
        <publisher-name>Издательство</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="doi">10.26102/2310-6018/2025.50.3.027</article-id>
      <article-id pub-id-type="custom" custom-type="elpub">2001</article-id>
      <title-group>
        <article-title xml:lang="ru">Интеграция RAG-системы для автоматизации поиска связей показателей и мероприятий национальных проектов</article-title>
        <trans-title-group xml:lang="en">
          <trans-title>Integration of the RAG system for automation of search links of indicators and activities of national projects</trans-title>
        </trans-title-group>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0002-8664-9817</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Каширина</surname>
              <given-names>Ирина Леонидовна</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Kashirina</surname>
              <given-names>Irina Leonidovna</given-names>
            </name>
          </name-alternatives>
          <email>kashirina@mirea.ru</email>
          <xref ref-type="aff">aff-1</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0003-7550-8917</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Кириллов</surname>
              <given-names>Вадим Витальевич</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Kirillov</surname>
              <given-names>Vadim Vitalievich</given-names>
            </name>
          </name-alternatives>
          <email>kirillov@mirea.ru</email>
          <xref ref-type="aff">aff-2</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-9632-7806</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Албычев</surname>
              <given-names>Александр Сергеевич</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Albychev</surname>
              <given-names>Alexander Sergeevich</given-names>
            </name>
          </name-alternatives>
          <email>_albychevas@roskazna.ru</email>
          <xref ref-type="aff">aff-3</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0003-1804-0761</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Старичкова</surname>
              <given-names>Юлия Викторовна</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Starichkova</surname>
              <given-names>Julia Viktorovna</given-names>
            </name>
          </name-alternatives>
          <email>starichkova@mirea.ru</email>
          <xref ref-type="aff">aff-4</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-8560-1937</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Магомедов</surname>
              <given-names>Шамиль Гасангусейнович</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Magomedov</surname>
              <given-names>Shamil Gasanguseinovich</given-names>
            </name>
          </name-alternatives>
          <email>magomedov_sh@mirea.ru</email>
          <xref ref-type="aff">aff-5</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0002-5638-8361</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Червяков</surname>
              <given-names>Александр Александрович</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Chervyakov</surname>
              <given-names>Alexander Alexandrovich</given-names>
            </name>
          </name-alternatives>
          <email>achervyakov@roskazna.ru</email>
          <xref ref-type="aff">aff-6</xref>
        </contrib>
      </contrib-group>
      <aff-alternatives id="aff-1">
        <aff xml:lang="ru">МИРЭА - Российский технологический университет</aff>
        <aff xml:lang="en">MIREA – Russian Technological University</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-2">
        <aff xml:lang="ru">МИРЭА - Российский технологический университет</aff>
        <aff xml:lang="en">MIREA – Russian Technological University</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-3">
        <aff xml:lang="ru">Федеральное Казначейство МИРЭА - Российский технологический университет</aff>
        <aff xml:lang="en">Federal Treasury MIREA – Russian Technological University</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-4">
        <aff xml:lang="ru">МИРЭА - Российский технологический университет</aff>
        <aff xml:lang="en">MIREA – Russian Technological University</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-5">
        <aff xml:lang="ru">МИРЭА - Российский технологический университет</aff>
        <aff xml:lang="en">MIREA – Russian Technological University</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-6">
        <aff xml:lang="ru">Федеральное Казначейство</aff>
        <aff xml:lang="en">Federal Treasury</aff>
      </aff-alternatives>
      <pub-date pub-type="epub">
        <day>01</day>
        <month>01</month>
        <year>2026</year>
      </pub-date>
      <volume>1</volume>
      <issue>1</issue>
      <elocation-id>10.26102/2310-6018/2025.50.3.027</elocation-id>
      <permissions>
        <copyright-statement>Copyright © Авторы, 2026</copyright-statement>
        <copyright-year>2026</copyright-year>
        <license license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/">
          <license-p>This work is licensed under a Creative Commons Attribution 4.0 International License</license-p>
        </license>
      </permissions>
      <self-uri xlink:href="https://moitvivt.ru/ru/journal/article?id=2001"/>
      <abstract xml:lang="ru">
        <p>В условиях возрастающей сложности управления Национальными проектами, направленными на достижение Национальных целей развития РФ, актуальной задачей становится автоматизация анализа взаимосвязей между запланированными в рамках этих проектов мероприятиями и показателями, которые отражают степень достижения поставленных в проекте задач. Традиционные методы ручной обработки документов характеризуются высокой трудоемкостью, субъективностью и значительными временными затратами, что обусловливает необходимость разработки интеллектуальных систем поддержки принятия решений. В данной статье представлен подход к автоматизации анализа связей и показателей национальных проектов, который позволяет автоматически выявлять и верифицировать семантические связи «мероприятие-показатель» в документах национальных проектов, значительно повышая эффективность аналитической работы. Данный подход основан на использовании Retrieval-Augmented Generation (RAG) системы, сочетающей локально адаптированную языковую модель с технологиями векторного поиска. Работа демонстрирует, что интеграция RAG-подхода с векторным поиском и учетом онтологии проектов позволяет достичь необходимой точности и релевантности анализа. Особую ценность системе придает не только способность генерировать интерпретируемые обоснования выявленных связей, но и возможность определять ключевые мероприятия, влияющие на достижение показателей сразу нескольких национальных проектов, включая те из них, чье воздействие на реализацию данных показателей неочевидно. Предложенное решение открывает новые возможности для цифровизации государственного управления и может быть адаптировано для других задач, например, определения рисков реализации мероприятий и генерации новых мероприятий.</p>
      </abstract>
      <trans-abstract xml:lang="en">
        <p>In the context of the increasing complexity of managing national projects aimed at achieving the National Development Goals of the Russian Federation, an urgent task is to automate the analysis of the relationships between the activities planned within these projects and the indicators that reflect the degree of achievement of the objectives set in the project. Traditional methods of manual document processing are characterized by high labor intensity, subjectivity and significant time costs, which necessitates the development of intelligent decision support systems. This article presents an approach to automating the analysis of links and indicators of national projects, which allows for automatic detection and verification of semantic links "event-indicator" in national project documents, significantly increasing the efficiency of analytical work. This approach is based on the use of the Retrieval-Augmented Generation (RAG) system, which combines a locally adapted language model with vector search technologies. The work demonstrates that the integration of the RAG approach with vector search and taking into account the project ontology allows achieving the required accuracy and relevance of the analysis. The system is particularly valuable not only for its ability to generate interpretable justifications for the identified links, but also for its ability to identify key events that affect the achievement of indicators for several national projects at once, including those whose impact on the implementation of these indicators is not obvious. The proposed solution opens up new opportunities for the digitalization of public administration and can be adapted for other tasks, such as identifying risks in the implementation of events and generating new events.</p>
      </trans-abstract>
      <kwd-group xml:lang="ru">
        <kwd>RAG-системы</kwd>
        <kwd>большие языковые модели</kwd>
        <kwd>национальные проекты</kwd>
        <kwd>семантический поиск</kwd>
        <kwd>автоматизация</kwd>
        <kwd>национальные цели</kwd>
        <kwd>искусственный интеллект в государственном управлении</kwd>
      </kwd-group>
      <kwd-group xml:lang="en">
        <kwd>RAG systems</kwd>
        <kwd>large language models</kwd>
        <kwd>national projects</kwd>
        <kwd>semantic search</kwd>
        <kwd>automation</kwd>
        <kwd>national goals</kwd>
        <kwd>artificial intelligence in public administration</kwd>
      </kwd-group>
      <funding-group>
        <funding-statement xml:lang="ru">Работа выполнена в рамках Государственного задания на 2025 год паспорта № 6381-25 по научно-методическому и ресурсному обеспечению системы образования на тему: «Научно-методическое обеспечение работ по анализу деятельности управления общественными финансами Российской Федерации с применением искусственного интеллекта».</funding-statement>
        <funding-statement xml:lang="en">The work was completed within the framework of the State assignment for 2025, passport No. 6381-25 on scientific, methodological and resource support of the education system on the topic: "Scientific and methodological support for work on the analysis of the activities of public finance management of the Russian Federation using artificial intelligence".</funding-statement>
      </funding-group>
    </article-meta>
  </front>
  <back>
    <ref-list>
      <title>References</title>
      <ref id="cit1">
        <label>1</label>
        <mixed-citation xml:lang="ru">Lewis P., Perez E., Piktus A., et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In: Advances in Neural Information Processing Systems  33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 06–12 December 2020, Online. 2020. https://doi.org/10.48550/arXiv.2005.11401</mixed-citation>
      </ref>
      <ref id="cit2">
        <label>2</label>
        <mixed-citation xml:lang="ru">Mishra A., Vishwakarma S. Analysis of TF-IDF Model and Its Variant for Document Retrieval. In: 2015 International Conference on Computational Intelligence and Communication Networks (CICN), 02–14 December 2015, Jabalpur, India. IEEE; 2015. P. 772–776. https://doi.org/10.1109/CICN.2015.157</mixed-citation>
      </ref>
      <ref id="cit3">
        <label>3</label>
        <mixed-citation xml:lang="ru">Mikolov T., Sutskever I., Chen K., Corrado G.S., Dean J. Distributed Representations of Words and Phrases and Their Compositionality. In: Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013, 05–08 December 2013, Lake Tahoe, NV, USA. 2013. https://doi.org/10.48550/arXiv.1310.4546</mixed-citation>
      </ref>
      <ref id="cit4">
        <label>4</label>
        <mixed-citation xml:lang="ru">Ouyang L., Wu J., Jiang X., et al. Training Language Models to Follow Instructions with Human Feedback. In: Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, 28 November – 9 December 2022, New Orleans, LA, USA. 2022. https://doi.org/10.48550/arXiv.2203.02155</mixed-citation>
      </ref>
      <ref id="cit5">
        <label>5</label>
        <mixed-citation xml:lang="ru">Guu K., Lee K., Tung Z., Pasupat P., Chang M.-W. REALM: Retrieval-Augmented Language Model Pre-Training. arXiv. URL: https://doi.org/10.48550/arXiv.2002.08909 [Accessed 13th May 2025].</mixed-citation>
      </ref>
      <ref id="cit6">
        <label>6</label>
        <mixed-citation xml:lang="ru">Gao Yu., Xiong Yu., Gao X., et al. Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv. URL: https://doi.org/10.48550/arXiv.2312.10997 [Accessed 13th May 2025].</mixed-citation>
      </ref>
      <ref id="cit7">
        <label>7</label>
        <mixed-citation xml:lang="ru">Brown T.B., Mann B., Ryder N., et al. Language Models are Few-Shot Learners. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 06–12 December 2020, Online. 2020. https://doi.org/10.48550/arXiv.2005.14165</mixed-citation>
      </ref>
      <ref id="cit8">
        <label>8</label>
        <mixed-citation xml:lang="ru">Eremeev M., Vorontsov K.V. Lexical Quantile-Based Text Complexity Measure. In: Proceedings of the International Conference on Recent Advances in Natural Language Processing, RANLP 2019, 02–04 September 2019, Varna, Bulgaria. INCOMA Ltd.; 2019. P. 270–275. https://doi.org/10.26615/978-954-452-056-4_031</mixed-citation>
      </ref>
      <ref id="cit9">
        <label>9</label>
        <mixed-citation xml:lang="ru">Jin R., Du J., Huang W., et al. A Comprehensive Evaluation of Quantization Strategies for Large Language Models. In: Findings of the Association for Computational Linguistics, ACL 2024, 11–16 August 2024, Bangkok, Thailand. Association for Computational Linguistics; 2014. P. 12186–12215.</mixed-citation>
      </ref>
      <ref id="cit10">
        <label>10</label>
        <mixed-citation xml:lang="ru">Izacard G., Grave E. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, EACL 2021, 19–23 April 2021, Online. Association for Computational Linguistics; 2021. P. 874–880. https://doi.org/10.48550/arXiv.2007.01282</mixed-citation>
      </ref>
    </ref-list>
    <fn-group>
      <fn fn-type="conflict">
        <p>The authors declare that there are no conflicts of interest present.</p>
      </fn>
    </fn-group>
  </back>
</article>