Method of automated standardization of metallic names based on the LLM model

Authors

DOI:

https://doi.org/10.31649/1681-7893-2026-51-1-33-40

Keywords:

Large Language Models (LLM), data standardization, fasteners, Prompt Engineering, Few-Shot Learning, database automation

Abstract

The article presents a method for the automated standardization of unstructured technical names for fasteners using Large Language Models (LLMs). The system architecture is based on the local inference of the Mistral-7B model via the LM Studio server, ensuring the confidentiality of industrial data. A comparative analysis is conducted between the «Instructor» method utilizing Pydantic validation and a proprietary direct JSON serialization method based on Few-Shot Prompting. Experimental results demonstrate that precise prompt engineering and in-context learning achieve 100% accuracy in generating names aligned with international DIN/ISO and DSTU standards. The proposed solution automates the updating of SQLite3 databases, minimizes human error, and provides correct multilingual localization of technical nomenclature. This approach significantly enhances data quality and operational efficiency within supply chain management systems.

Author Biographies

V.Yu. Starzhynskyiy, Vinnytsia National Technical University

Аспірант групи 126-23а, факультет інтелектуальних інформаційних технологій та автоматизації

O.V. Bisikalo, Vinnytsia National Technical University

Доктор технічних наук, професор, завідувач кафедри Автоматизації та інтелектуальних інформаційних технологій

References

Hazen, B. T., Boone, C. A., Ezell, J. D., & Jones-Farmer, L. A. (2014). Data quality for data science, predictive analytics, and business intelligence in supply chain management: An introduction to the problem and suggestions for research. International Journal of Production Economics, 154, 72-80.

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.

Friedl, J. E. (2006). Mastering Regular Expressions. O'Reilly Media. https://www.oreilly.com/library/view/mastering-regular-expressions/0596528124/

Liu, J. (2023). Instructor: Structured Extraction using LLMs. GitHub Repository. https://github.com/567-labs/instructor

Weng, L. (2023). LLM Powered Autonomous Agents. OpenAI Blog / Lil'Log. https://lilianweng.github.io/posts/2023-06-23-agent/

Pydantic Team. (2024). Validation Decorators and Models. URL: https://docs.pydantic.dev/latest/concepts/models/#basic-model-usage

Brown, T. B., et al. (2020). Language Models are Few-Shot Learners. arXiv:2005.14165. URL: https://arxiv.org/abs/2005.14165

JSON.org. (2024). The JSON Data Interchange Standard (ECMA-404). URL: https://www.json.org/json-en.html

Starzhynskyi, V., Bisikalo, O. (2025). Using local LLM models for standardization and multilingual translation of technical product names. Measuring and computing devices in technological processes, 84(4), pp. 407–415. doi: 10.31891/2219-9365-2025-84-49.

Starzhynskyi, V. Bisikalo, O. Using local LLM models for standardization of hardware names. VNTKP VNTU. Faculty of Intellectual Information Technologies and Automation, Ukraine, Mar. 2026. Available at: <https://conferences.vntu.edu.ua/index.php/all-fksa/all-fksa-2026/paper/view/27436/22723>. Date accessed: 06 Mar. 2026.

Bisikalo, O.; Kharchenko, V.; Kovtun, V.; Krak, I.; Pavlov, S. Parameterization of the Stochastic Model for Evaluating Variable Small Data in the Shannon Entropy Basis. Entropy 2023, 25, 184.

Intellectual technologies in medical diagnostics, treatment and rehabilitation: monograph / [S.V. Pavlov, O.G. Avrunin, S.M. Zlepko, E.V. Bodianskyi and others]; edited by S. Pavlov, O. Avrunin. – Vinnytsia: PP “TD “Edelweiss and K”, 2019. – 260 p.

Downloads

Abstract views: 13

Published

2026-06-18

How to Cite

[1]
V. Starzhynskyiy and O. Bisikalo, “Method of automated standardization of metallic names based on the LLM model”, Опт-ел. інф-енерг. техн., vol. 51, no. 1, pp. 33–40, Jun. 2026.

Issue

Section

OptoElectronic/Digital Methods and Systems for Image/Signal Processing

Metrics

Downloads

Download data is not yet available.