METHOD FOR INFORMATION PROCESSING AND MODIFICATION OF THRESHOLD PARAMETERS OF RULES IN A MIVAR EXPERT SYSTEM USING LARGE LANGUAGE MODELS

Dou L.1,2

About the authors

Dou L.1,2

1Bauman Moscow State Technical University 105005, 2-ya Baumanskaya st. bld. 5, building 1, Moscow, Russia 2JSC M. A. Kartsev Research Institute of Computing Systems, 117437, Profsoyuznaya st. bld. 108, Moscow, Russia

Download PDF

UDC: 004.89 + 004.021 + 007.52
DOI: 10.24412/2413-7383-2025-4-39-194-205
Language: Russian

Abstract: The aim of the work is to automate the change of threshold parameters of rules in a multi-dimensional expert system using large language models. A method for dynamically changing the threshold parameters of mivar rules based on the DeepSeek large language model is proposed, which ensures a constant change in the mivar knowledge base through human-machine interaction. The method is aimed at a scenario of threshold parameter changes, in which historical data is analyzed to adjust these parameters. The scientific novelty lies in the creation of a comprehensive method of human - machine interaction that systematizes procedures for changing parameters using advanced capabilities of large language models, which ensures higher performance of multi-dimensional expert systems in real dynamic conditions.

Keywords: algorithm, expert system, mivar, mivar expert system, large language model, automatic updating of the knowledge base, artificial intelligence, parameter changes.

References

1. Varlamov O. O. Evolutionary databases and knowledge. Mivar information space / O. O. Varlamov // Izvestiya SFU. Technical sciences. – 2007. – № 5(77). – Pp. 77-81.
2. Platonov Yu. G. Analysis of the prospects for the transition of information systems to a service-oriented architecture / Yu. G. Platonov // Problems of computer Science. – 2011. – № 4(12). – Pp. 56-65.
3. Shen Ts. Dynamic trajectory planning of a robot based on semantic object detection using a mivar expert system / Ts. Shen, Sh. Gong, O. O. Varlamov et al. // Problems of artificial intelligence. – 2024. – № 4(35). – Pp. 164-176. – DOI 10.24412/2413-7383-2024-4-164-176.
4. Kotsenko A. A. Development of models of mivar logical space to ensure three-dimensional movement of autonomous robots / A. A. Kotsenko // MIVAR'24: Collection of scientific articles, Moscow, April 18-20, 2024. – Moscow: INFRA-M, 2024. – pp. 361-366.
5. Wang S. A novel maritime autonomous navigation decision-making system: Modeling, integration, and real ship trial / S. Wang, Y. Zhang, X. Zhang et. al. //Expert Systems with Applications. – 2023. – Т. 222. – С. 119825.
6. Dou, L. A decision-making model for fire detection based on pattern recognition and a mivar expert system. Dow // Management systems and information technologies. – 2025. – № 3(101). – Pp. 59-65.
7. Dou L. A Multimodal Target Detection Method Based on the MES and the Improved BEV Perception Algorithm / L. Dou, O. O. Varlamov, A. A. Kotsenko // 7th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), Moscow, 08-10 April 2025. Vol. 7. – IEEE: Institute of Electrical and Electronics Engineers, 2025. – DOI 10.1109/REEPE63962.2025.10970859.
8. Dou L. On the development of algorithmic software for creating and updating the rules of a GPT-based mivar expert system. Dow // Mivar '25: Reports, Moscow, April 17-19, 2025. – Moscow: INFRA-M, 2025. – pp. 415-417.
9. Dou L. Creation of a multimodal fire detection system and application in a multi-fire expert system. Preschool educational institution // Information and education: the boundaries of communication. – 2025. – № 17(25). – Pp. 223-227.
10. Zhang X. A multimodal expert system for the intelligent monitoring and maintenance of transformers enhanced by multimodal language large model fine‐tuning and digital twins / X. Zhang, W. Sun, K. Chen et. al. //IET Collaborative Intelligent Manufacturing. – 2024. – Т. 6. – №. 4. – С. e70007.
11. Gavrilov L. Ya. Investigation of the possibilities of large linguistic models for creating mivar knowledge bases / L. Ya. Gavrilov, V. V. Ulyashin, M. Yu. Popov // IIASU'24 – Artificial intelligence in automated control and data processing systems: Collection of articles of the III All–Russian Scientific Conference: in 3 volumes, Moscow, October 30 - 01 In 2024. – Moscow: KDU Publishing House, LLC, 2025. – pp. 23-31.
12. Lutskovich A. I. Automated system for analyzing weakly structured cyber intelligence data using large language models / A. I. Lutskovich, V. I. Vasiliev, A.M. Vulfin et al. // Information and control systems. – 2025. – № 2(135). – Pp. 50-67. – DOI 10.31799/1684-8853-2025-2-50-67. – EDN QFQTPU.
13. Hu W. BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions / W. Hu, Y. Xu, Yi. Li et. al. // Proceedings of the AAAI Conference on Artificial Intelligence. – 2024. – Vol. 38, No. 3. – P. 2256-2264. – DOI 10.1609/aaai.v38i3.27999.
14. Wang Y. A novel fractional structural adaptive grey Chebyshev polynomial Bernoulli model and its application in forecasting renewable energy production of China / Y. Wang, R. Nie, P. Chi et. al. // Expert Systems with Applications. – 2022. – Vol. 210. – P. 118500. – DOI 10.1016/j.eswa.2022.118500.
15. Liao HL. Deepseek large - scale model: technical analysis and development prospect / HL. Liao // Journal of Computer Science and Electrical Engineering. – 2025. – Vol. 7, No. 1. – DOI 10.61784/jcsee3035.
16. Cube A. Ah. Analiz primeneniya для АСУТП миварных сетей в formate двудольных и трехдольных графов / А. Ah. Kocenko / / MIVAR ' 24: Сборник научных статей, Москва, 18-20 April 2024 года. - Moscow: infra-m, 2024. - S. 432-438.
17. Daniel A. W. About the application MivarGPT для автоматизации создания миварных базнаний и машиностроительного искусственного интеллекта / А. W. Daniel, R. And. Kim / / Искусственный интеллект в автоматизированных системах управления и обработки данных: сборник статей Всероссийской научной конференции, Moscow, 27-28 April 2023. - Moscow: истательский дом КДУ, Добросвет, 2023. - S. 568-573.
18. Burnashev R. A. Expert system building tools based on dynamically updated knowledge / R. A. Burnashev, I. Amer, A. I. Enikeev // The International Scientific and Practical Conference on Mathematical Modeling, Programming and Applied Mathematics, Veliky Novgorod, 27–28 июня 2019 года. – Bristol: Institute of Physics Publishing, 2019. – P. 012008. – DOI 10.1088/1742-6596/1352/1/012008. Д Доу Л.
19. Paredes R. Collaborative update of a rule-based expert system for HIV-1 genotypic resistance test interpretation / R. Paredes, P. L. Tzou, P. M. Grant et. al. // PLoS ONE. – 2017. – Vol. 12, No. 7. – P. e0181357. – DOI 10.1371/journal.pone.0181357.
20. Ko H. Machine learning and knowledge graph based design rule construction for additive manufacturing / H. Ko, P. Witherell, Ya. Lu et. al. // Additive Manufacturing. – 2021. – Vol. 37. – P. 101620. – DOI 10.1016/j.addma.2020.101620.
21. Melicke Ch. Anytime bottom-up rule learning for large-scale knowledge graph completion / Ch. Meilicke, M. W. Chekol, P. Betz et. al. // The VLDB Journal. – 2024. – Vol. 33, No. 1. – P. 131-161. – DOI 10.1007/s00778-023-00800-5.
22. Yang Sh Radiology report generation with a learned knowledge base and multi-modal alignment / Sh. Yang, X. Wu, Sh. Ge et. al. // Medical Image Analysis. – 2023. – Vol. 86. – P. 102798. – DOI 10.1016/j.media.2023.102798.
23. Du S. Q. Tree-GPT: modular Large language Model expert system for forest remote sensing image understanding and interactive analysis / S. Q. Du, S. J. Tang, W. X. Wang et. al. // The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. – 2023. – Vol. XLVIII-1/W2-2023. – P. 1729-1736. – DOI 10.5194/isprs-archives-xlviii-1-w2-2023-1729-2023.
24. Lammert Ja. Large language models for precision oncology: Clinical decision support through expert- guided learning / Ja. Lammert, T. F. Dreyer, A. M. Lörsch et. al. // Journal of Clinical Oncology. – 2024. – Vol. 42, No. 16_suppl. – P. e13609. – DOI 10.1200/jco.2024.42.16_suppl.e13609. – EDN RMHUZU.
25. Awasthi Y. K. A Comparative Study: Evaluating ChatGPT and DeepSeek AI Tools in Practice / Y. K. Awasthi, T. Garikayi, L. T. Fundisi et. al. // International Journal of Open Information Technologies. – 2025. – Vol. 13, No. 5. – P. 67-70.
26. Gao Yu. A study on building a Knowledge Graph for making decisions on compliance with restrictive measures and measures to counter illegal sanctions in the field of Russian natural gas based on the DeepSeek / Yu AI model. Gao // Bulletin of the V.A. Musin Center of Law. – 2025. – No. 2. – pp. 21-29. – DOI 10.61525/S0035542-6.
27. Емельянов В. OpenAI vs DeepSeek. Сравнительный анализ популярных нейросетей / В. Емельянов, Н. Емельянова // Системный администратор. – 2025. – № 3(268). – С. 68-71.
28. Giske C. G. GPT-4-based AI agents—the new expert system for detection of antimicrobial resistance mechanisms / C. G. Giske, M. Bressan, F. Fiechte et. al. //Journal of Clinical Microbiology. – 2024. – Т.
29. – №. 11. – С. e00689 -24.
30. Mercer S. Brief analysis of DeepSeek R1 and its implications for Generative AI / S. Mercer, S. Spillard, D. P. Martin // SuperIntelligence - Robotics - Safety & Alignment. – 2025. – Vol. 2, No. 1. – DOI 10.70777/si.v2i1.11097.
31. Muntinov K. D. The use of LLM on the example of ChatGPT, DeepSeek, Grok for evaluating students' work / K. D. Muntinov // Bulletin of M. Kozybaev Moscow State University. – 2025. – № 2(66). – Pp. 220-230. – DOI 10.54596/10.54596/2958-0048-2025-2-220-230.
32. Golubinsky A. N. Automatic generation of annotations of scientific articles based on large language models

Issue: 4(39)'2025
Section: SYSTEM ANALYSIS, CONTROL AND INFORMATION PROCESSING, STATISTICS
How to cite: Dou L.1,2. 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 (39). - P. 194-205. - https://paijournal.guiaidn.ru/en/2025/4(39)-17.html

Back to issue 4(39)'2025