Development of an Intelligent Assistant for Applying Standardized Distributed Business Models

Context and relevance. In the context of the digital transformation of the global economy, industrial digital platforms and ecosystems based on standardized distributed business models play a key role. The theoretical foundation of the study is the Reference Architectural Model Industrie 4.0 (RAMI 4.0), which enables the integration of production assets into a multidimensional structure. Objective. To develop an AI assistant for automating data entry into the RAMI 4.0 reference model and updating knowledge bases in distributed ecosystems. Hypothesis. Intelligent classification of elements, determination of coordinates in the RAMI cube, and validation based on ontological models will automate the creation of knowledge bases about production assets and enhance the efficiency of cyber-physical systems management. Methods and materials. Theoretical-information analysis of the concepts of the standardized RAMI 4.0 model in accordance with IEC 62890 and other knowledge modeling standards; formalization of the AI assistant functions using data arrays and knowledge bases on production assets; modeling of information exchange processes between participants in industrial digital platform ecosystems. The prototype was implemented on the Google Colab platform using Python libraries (Scikit-learn, NLTK, OWL API). Fuzzy logic methods were applied to process textual and linguistic data about production assets. Results. An ontological model of the RAMI 4.0 reference model has been developed, with its concepts, predicates, and subclasses defined for the first time; the functions of the AI assistant have been formalized along with operations on data; a data structure has been proposed for integrating the AI assistant with ERP systems. Conclusions. The AI assistant enables automated knowledge base population, contributing to the formation of ecosystems of production enterprises and consortia operating with Industry 4.0 technologies.

1. Антонов И.В., Воронов М.В. Метод автоматизированного построения онтологии предметной области. Моделирование и анализ данных. 2011. № 1. С. 116-130.
   Antonov, I. V., & Voronov, M. V. (2011). Metod avtomatizirovannogo postroeniya ontologii predmetnoi oblasti [Method for automated construction of a domain ontology]. Modelirovanie i analiz dannykh, (1), 116–130. (In Russ.)
2. Дли М. И., Черновалова М. В., Соколов А. М., Моргунова Э. В. Нечеткая динамическая онтологическая модель для поддержки принятия решений по управлению энергоемкими системами на основе прецедентов // Прикладная информатика. Т. 18. № 5 (107). С. 59-76.
   Dli, M. I., Chernovalova, M. V., Sokolov, A. M., & Morgunova, E. V. (2023). Fuzzy dynamic ontological model for decision support of energy-intensive systems management based on precedents. Journal of Applied Informatics, 18 (5), 59–76. (In Russ.). https://doi.org/10.37791/2687-0649-2023-18-5-59-76.
3. Каленов О.Е. Унифицированные цифровые бизнес-модели участников платформ и экосистем. Вестник Российского экономического университета имени Г. В. Плеханова. 2022;(3):52-59. https://doi.org/10.21686/2413-2829-2022-3-52-59.
   Kalenov, O. E. (2022). Unified digital business-models of platform and ecosystem participants. Vestnik of the Plekhanov Russian University of Economics, (3), 52–59. (In Russ.). https://doi.org/10.21686/2413-2829-2022-3-52-59.
4. Куравский, Л.С., Одинцов, Д.А., Михайловский, М.А. (2025). Эволюционные алгоритмы подбора запросов и проверки корректности ответов интеллектуальных ассистентов. Моделирование и анализ данных, 15(4), 7—26. https://doi. org/10.17759/mda.2025150401
   Kuravsky, L. S., Odintsov, D. A., & Mikhailovsky, M. A. (2025). Evolutionary algorithms to generate prompts and verify responses of intelligent assistants. Modelling and Data Analysis, 15(4), 7–26. (In Russ.). https://doi.org/10.17759/mda.2025150401.
5. Поляков Б.Ю. Семантический анализ результатов выполнения тестовых заданий. Моделирование и анализ данных. 2025. Т. 15. № 4. С. 156-164.
   Polyakov, B.Y. (2025). Semantic analysis of test responses using synthetic data generation. Modelling and Data Analysis, 15(4), 156—164. (In Russ.). https://doi. org/10.17759/mda.2025150410
6. Фомин И. Н. Применение онтологических моделей и баз знаний для разработки киберфизических систем в соответствии с референтной моделью RAMI0 Прикладная информатика. 2025. Т. 20. № 4 (118). С. 110–131. DOI: 10.37791/2687-0649-2025-20-4-110-131.
   Fomin, I. N. (2025). Application of ontological models and knowledge bases for the development of cyber-physical systems in accordance with the RAMI 4.0 reference model. Journal of Applied Informatics, 20 (4), 110–131. (In Russ.). https://doi.org/10.37791/2687-0649-2025-20-4-110-131.
7. Awad, R., Heppner, G., Roennau, A., & Bordignon, M. (2016). ROS engineering workbench based on semantically enriched app models for improved reusability. In 2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA), 1–9. https://doi.org/10.1109/ETFA.2016.7733581.
8. Bader, S. R., Grangel-González, I., Nanjappa, P., Vidal, M.-E., & Maleshkova, M. (2020). A knowledge graph for Industry 4.0. In The Semantic Web: ESWC 2020 Satellite Events, 1–16. https://doi.org/10.1007/978-3-030-62327-2_1.
9. Megow, J. (2020). Reference architecture models for Industry 4.0, smart manufacturing and IoT. PaiCE.
10. Müller, J. M. (2019). Antecedents to digital platform usage in Industry 4.0 by established manufacturers. Sustainability, 11 (4), Article 1121. https://doi.org/10.3390/su11041121.
11. Pauli, T., Fielt, E., & Matzner, M. (2021). Digital industrial platforms. Business & Information Systems Engineering, 63, 181–190. https://doi.org/10.1007/s12599-020-00681-w.
12. Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of EMNLP-IJCNLP, 3982–3992. https://doi.org/10.18653/v1/D19-1410.
13. Rong, K., Lin, Y., Du, W., & Yang, S. (2023). Business ecosystem-oriented business model in the digital era. Technology Analysis & Strategic Management. https://doi.org/10.1080/09537325.2023.2191743.
14. Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., & Wei, F. (2022). Text Embeddings by Weakly-Supervised Contrastive Pre-training (E5). https://doi.org/10.48550/arXiv.2212.03533.
15. Xiao, S., Liu, Z., Zhang, P., & Muennighoff, N. (2024). C-Pack: Packed Resources for General Text Embedding (BGE). arXiv:2309.07597v5 [cs.CL] 24 Sep 2024.
16. Yahya, M., Shah, S. H., Khattak, H. A., Shafiq, M. O., & Khan, M. A. (2021). Semantic web and knowledge graphs for Industry 4.0. Applied Sciences, 11(11), Article 5110. https://doi.org/10.3390/app11115110.