The aim of the work is to develop mathematical and algorithmic software for automatic updating of rules in the mivar expert system using large language models. In the course of this research, mathematical and algorithmic software was developed for dynamic and automatic updating of rules. The software is used to solve the problem of the delay in updating the rules of the knowledge base of the traditional mivar expert system and the long time required for manual updating. The mathematical and algorithmic support in this study is based on the ability to generate large language models, including four algorithms. Trigger algorithm based on confidence estimation; algorithm for generating hints; algorithm for secure verification; algorithm for introducing rules. The scientific novelty of the work consists in the development of four algorithms that provide automatic dynamic updating of rules in a global expert system using large language models. Experiments show that the mathematical and algorithmic software used in this study can effectively improve the mivar expert systems ability to update rules autonomously. 95.8 % of unknown scenarios were processed, and the accuracy of rule generation reached 91.3 %. The knowledge base update cycle has been reduced from several hours to several seconds. This study proves the advantages of using LLM as an external intelligent service for implementing automatic updating of the rules of the knowledge base of the mivar expert system.
1. Varlamov O.O. Evolutionary databases and knowledge bases for adaptive synthesis of intelligent systems. Mivar information space. Moscow: Radio i svyaz; 2002. 286 p. (In Russ.).
2. Platonov Yu.G. Analysis of the Prospects for the Transition of Information Systems to a Service-Oriented Architecture. Problems of Computer Science. 2011;(4):56–65. (In Russ.).
3. Shen Q., Gong Sh., Varlamov O.O., Adamova L.E., Balenko E.G. Dynamic robot path planning based on semantic object detection using mivar expert system. Problems of Artificial Intelligence. 2024;(4):164–176. (In Russ.). https://doi.org/10.24412/2413-7383-2024-4-164-176
4. Kotsenko A.A. Development of models of mivar logic space to provide three-dimensional movement of autonomous robots. In: MIVAR '24: Collection of scientific articles, 18–20 April 2024, Moscow, Russia. Moscow: INFRA-M; 2024. P. 361–366. (In Russ.).
5. Chibirova M.O. Analysis of existing approaches in developing decision support systems: ontology and mivar nets. Automation and Control in Technical Systems. 2014;(1-2):44–60. (In Russ.).
6. Dou L. Decision-making model for fire detection based on pattern recognition and mivar expert system. Control Systems and Information Technology. 2025;(3):59–65. (In Russ.).
7. Dou L. On the development of algorithmic software for creating and updating rules of a GPT-based mivar expert system. In: MIVAR '25: Proceedings, 17–19 April 2025, Moscow, Russia. Moscow: INFRA-M; 2025. P. 415–417. (In Russ.).
8. Hanney K., Keane M.T. The adaptation knowledge bottleneck: How to ease it by learning from cases. In: Case-Based Reasoning Research and Development: Second International Conference on Case-Based Reasoning (ICCBR-97), 25–27 July 1997, Providence, RI, USA. Berlin, Heidelberg: Springer; 1997. P. 359–370. https://doi.org/10.1007/3-540-63233-6_506
9. Dou L. Creation of a multimodal fire detection system and application in the mivar expert system. Information and Education: Borders of Communication. 2025;(17):223–227. (In Russ.).
10. Zhang X., Sun W., Chen K., Jiang R. A multimodal expert system for the intelligent monitoring and maintenance of transformers enhanced by multimodal language large model fine-tuning and digital twins. IET Collaborative Intelligent Manufacturing. 2024;6(4). https://doi.org/10.1049/cim2.70007
11. Chibirova M. Analysis of existing approaches: ontology, cognitive maps and mivar nets. Radio Industry. 2015;(3):55–66. (In Russ.).
12. Lutskovich A.I., Vasilyev V.I., Vulfin A.M., Kirillova A.D., Sulavko A.E. Automated system for analyzing weakly structured threat intelligence data using large language models. Information and Control Systems. 2025;(2):50–67. (In Russ.).
13. Hu W., Xu Y., Li Y., et al. BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(3):2256–2264. https://doi.org/10.1609/aaai.v38i3.27999
14. Khadiev A.M. Development and practical realization of mivar inference machine. Radio Industry. 2015;(3):79–89. (In Russ.).
15. Kotsenko A.A. Analysis of application of mivar nets in the format of bipartite and tripartite graphs for automated process control systems. In: MIVAR '24: Collection of scientific articles, 18–20 April 2024, Moscow, Russia. Moscow: INFRA-M; 2024. P. 432–438. (In Russ.).
16. Gavrilov L.Y., Ulyashin V.V., Popov M.Y. Research the possibilities of large linguistic models for creating multi-dimensional knowledge bases. In: IIASU'24 – Artificial intelligence in management, control, and data processing systems: Proceedings of the III All-Russian scientific conference: Volume 2, 30 October – 01 November 2024, Moscow, Russia. Moscow: Izdatel'skii dom KDU; 2025. P. 23–31. (In Russ.).
17. Danilyuk A.V., Kim R.I. On the application of MivarGPT for automating the creation of mivar knowledge bases and mechanical engineering artificial intelligence. In: IIASU'23 – Artificial intelligence in management, control, and data processing systems: Proceedings of the II All-Russian scientific conference: Volume 3, 27–28 April 2023, Moscow, Russia. Moscow: Izdatel'skii dom KDU; 2023. P. 568–573. (In Russ.).
18. Du S.Q., Tang S.J., Wang W.X., Li X.M., Guo R.Z. Tree-GPT: Modular Large language Model expert system for forest remote sensing image understanding and interactive analysis. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2023;48(1):1729–1736. https://doi.org/10.5194/isprs-archives-xlviii-1-w2-2023-1729-2023
19. Lammert Ja., Dreyer T.F., Lörsch A.M., et al. Large language models for precision oncology: Clinical decision support through expert-guided learning. Journal of Clinical Oncology. 2024;42(16_suppl). https://doi.org/10.1200/jco.2024.42.16_suppl.e13609
20. Schuerkamp R., Ahlstrom H., Giabbanelli Ph.J. Automatically resolving conflicts between expert systems: An experimental approach using large language models and fuzzy cognitive maps from participatory modeling studies. Knowledge-Based Systems. 2025;313. https://doi.org/10.1016/j.knosys.2025.113151
21. Awasthi Y., Garikayi T., Fundisi L.T., Mukhalela B. A Comparative Study: Evaluating ChatGPT and DeepSeek AI Tools in Practice. International Journal of Open Information Technologies. 2025;13(5):67–70.
22. Dou L. Method for information processing and modification of threshold parameters of rules in a mivar expert system using large language models. Problems of Artificial Intelligence. 2025;(4):194–205. (In Russ.). https://doi.org/10.24412/2413-7383-2025-4-39-194-205
