<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">nbsprot</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник войск РХБ защиты</journal-title><trans-title-group xml:lang="en"><trans-title>Journal of NBC Protection Corps</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2587-5728</issn><issn pub-type="epub">3034-2791</issn><publisher><publisher-name>27 Научный центр</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.35825/2587-5728-2026-10-1-78-92</article-id><article-id custom-type="elpub" pub-id-type="custom">nbsprot-442</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ОХРАНА РЕЗУЛЬТАТОВ ИНТЕЛЛЕКТУАЛЬНОЙ ДЕЯТЕЛЬНОСТИ ВОЙСК РХБ ЗАЩИТЫ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>PROTECTION OF INTELLECTUAL PROPERTY IN CBRN DEFENSE TROOPS</subject></subj-group></article-categories><title-group><article-title>Промпт-инжиниринг для выявления патентоспособных технических решений в научных публикациях</article-title><trans-title-group xml:lang="en"><trans-title>Prompt engineering for identifying patentable technical solutions in scientific publications</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0004-3193-1032</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Супотницкий</surname><given-names>М. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Supotnitskiy</surname><given-names>M. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Супотницкий Михаил Васильевич. Главный специалист Центра, канд. биол. наук, ст. науч. сотр.</p></bio><bio xml:lang="en"><p>Mikhail V. Supotnitskiy. Senior Researcher. Chief Specialist. Cand. Sci. (Biol.).</p></bio><email xlink:type="simple">27nc_1@mil.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Федеральное государственное бюджетное учреждение «27 Научный центр имени академика Н.Д. Зелинского» Министерства обороны Российской Федерации&#13;
111024, г. Москва, проезд Энтузиастов, д. 19</institution><country>Россия</country></aff><aff xml:lang="en"><institution>27 Scientific Centre Named after Academician N.D. Zelinsky of the Ministry of Defence of the Russian Federation</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>05</day><month>05</month><year>2026</year></pub-date><volume>10</volume><issue>1</issue><fpage>78</fpage><lpage>92</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Супотницкий М.В., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Супотницкий М.В.</copyright-holder><copyright-holder xml:lang="en">Supotnitskiy M.V.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://www.nbsprot.ru/jour/article/view/442">https://www.nbsprot.ru/jour/article/view/442</self-uri><abstract><p>Основные моменты Разработана методология выявления патентоспособных решений в научных статьях, реализованная методами промпт-инжиниринга с использованием большой языковой модели DeepSeek-V3.2. Созданы типовые матрицы для составления патентных заявок на три типа объектов (способ, устройство, вещество), интегрирующие требования российского патентного законодательства и систематизированные ошибки заявителей. Сформулированы 6 научных принципов использования ИИ для трансформации научных результатов в объекты интеллектуальной собственности. Актуальность. Значительная часть научных экспериментальных публикаций содержит патентоспособные технические решения, не выявленные авторами. Большинство статей опубликованы более 12 месяцев назад, что приводит к пропуску срока авторской льготы и создает препятствия для патентования.   Цель – разработать методологию выявления патентоспособных решений в научных статьях с использованием ИИ, позволяющую преобразовывать опубликованные результаты в патентные заявки. Материалы и методы. Исследование базировалось на анализе запросов ФИПС по экспертизе заявок на изобретения. Разработаны чек-лист первичной оценки (10 критериев) и типовые матрицы для составления заявок на способ, устройство и вещество. Для обработки статей использовалась языковая модель DeepSeek-V3.2. Результаты. Из шести статей пять содержали патентоспособные решения. На их основе составлено 9 патентных заявок с 15 независимыми пунктами. Разработаны подходы к выявлению изобретений в публикациях с истекшим сроком авторской льготы на новизну. Англоязычный кейс подтвердил языковую независимость методологии. На генерацию одной заявки уходит 3–7 минут, что соответствует обработке 5–10 тыс. токенов. Заключение. Разработанная методология обеспечивает выявление изобретений в научных публикациях. Методология передается через промпты, загрузку матриц на типовые объекты и информации о типовых ошибках заявителей, и воспроизводится в новом чате. Ключевым фактором является наличие в публикации количественных экспериментальных данных. Предложенная методология также открывает перспективу для выявления патентоспособных объектов спустя годы после их опубликования при условии обнаружения в статье постановки задачи, но без раскрытия конкретного технического решения. Практическая значимость работы. Разработанные система промпт-инжиниринга, чек-лист и типовые матрицы могут использоваться патентными службами и изобретателями ВС РФ для выявления и оформления права на отечественные разработки, что будет способствовать технологическому суверенитету России.</p></abstract><trans-abstract xml:lang="en"><p>Highlights A methodology for identifying patentable solutions in scientific articles, implemented through prompt engineering methods using the large language model DeepSeek-V3.2, has been developed. Standard matrices for drafting patent applications for three types of objects (method, device, substance) have been created, integrating the requirements of Russian patent legislation and systematized applicant errors. Six scientific principles for using AI to transform scientific results into intellectual property objects have been formulated. Relevance. A significant portion of scientific experimental publications contains patentable technical solutions that have not been identified by the authors. Most articles were published more than 12 months ago, which leads to missing the novelty grace period and creates obstacles for patenting. Purpose of the study is to develop a methodology for identifying patentable solutions in scientific articles using AI, enabling the transformation of published results into patent applications. Materials and Methods. The study was based on an analysis of FIPS (Federal Institute of Industrial Property) inquiries regarding the examination of invention applications. The DeepSeek-V3.2 language model was used for processing the articles. A primary assessment checklist (10 criteria) and standard matrices for drafting applications for methods, devices, and substances were developed. Approbation was carried out on six articles of various topics, including an English-language publication. Results. Of the six articles, five (83.3%) contained patentable solutions. Based on these, 9 patent applications with 15 independent claims were drafted. Publications with an expired novelty grace period (up to 7 years) were successfully circumvented by introducing new essential features. The English-language case confirmed the language independence of the methodology. Six scientific principles for using AI to identify inventions were formulated. Conclusion. The developed methodology enables the identification of inventions in scientific publications. The methodology is conveyed through prompts and can be reproduced in a new chat session. The key success factor is the presence of quantitative experimental data in the publication. The proposed strategy for circumventing prior publications allows for patenting solutions years after publication, provided the article states the problem without disclosing a specific solution. Practical significance of the work. The developed prompt engineering system, checklist, and standard matrices can be used by patent services and inventors of the Armed Forces of the Russian Federation to identify and secure rights to domestic developments, thereby contributing to Russia's technological sovereignty.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>DeepSeek</kwd><kwd>авторская льгота на новизну</kwd><kwd>изобретение</kwd><kwd>искусственный интеллект</kwd><kwd>научная статья</kwd><kwd>патентная заявка</kwd><kwd>патентование</kwd><kwd>промпт-инжиниринг</kwd><kwd>существенные признаки</kwd><kwd>техническое решение</kwd><kwd>технологический суверенитет</kwd><kwd>чек-лист</kwd></kwd-group><kwd-group xml:lang="en"><kwd>artificial intelligence</kwd><kwd>checklist</kwd><kwd>DeepSeek</kwd><kwd>essential features</kwd><kwd>grace period for novelty</kwd><kwd>invention</kwd><kwd>patent application</kwd><kwd>patenting</kwd><kwd>prompt engineering</kwd><kwd>scientific article</kwd><kwd>technical solution</kwd><kwd>technological sovereignty</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Супотницкий М.В. Типичные ошибки в формуле и описании изобретений, создаваемых в войсках РХБ защиты ВС РФ. Вестник войск РХБ защиты. 2023;7(1):73–81. EDN: untpoj. https://doi.org/10.35825/2587-5728-2023-7-1-73-81</mixed-citation><mixed-citation xml:lang="en">Supotnitskiy MV. Typical Mistakes in Claims and Specifications of the Inventions in the NBC Protection Corps. Journal of NBC Protection Corps. 2023;7(1):73–81. (In Russ.). EDN: untpoj. https://doi.org/10.35825/2587-5728-2023-7-1-73-81</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Guo D, Yang D, Zhang H, Song J, Wang P, Zhu Q, et al. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature. 2025;645:633–638. https://doi.org/10.1038/s41586-025-09422-z</mixed-citation><mixed-citation xml:lang="en">Guo D, Yang D, Zhang H, Song J, Wang P, Zhu Q, et al. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature. 2025;645:633–638. https://doi.org/10.1038/s41586-025-09422-z</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Hoyt RE, Bajwa M. Measuring the Accuracy and Reproducibility of DeepSeek R1, Claude 3.5 Sonnet, and GPT-4.1 on Complex Clinical Scenarios. Appl Clin Inform. 2026;17(1):64–72. https://doi.org/10.1055/a-2807-4256</mixed-citation><mixed-citation xml:lang="en">Hoyt RE, Bajwa M. Measuring the Accuracy and Reproducibility of DeepSeek R1, Claude 3.5 Sonnet, and GPT-4.1 on Complex Clinical Scenarios. Appl Clin Inform. 2026;17(1):64–72. https://doi.org/10.1055/a-2807-4256</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Xu P, Wu Y, Jin K, Chen X, He M, Shi D. DeepSeek-R1 outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in bilingual complex ophthalmology reasoning. Adv Ophthalmol Pract Res. 2025;5(3):189–95. https://doi.org/10.1016/j.aopr.2025.05.001</mixed-citation><mixed-citation xml:lang="en">Xu P, Wu Y, Jin K, Chen X, He M, Shi D. DeepSeek-R1 outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in bilingual complex ophthalmology reasoning. Adv Ophthalmol Pract Res. 2025;5(3):189–95. https://doi.org/10.1016/j.aopr.2025.05.001</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Debnath T, Siddiky MNA, Rahman ME, Das P, Guha AK, Rahman RH, et al. A Comprehensive Survey of Prompt Engineering Techniques in Large Language Models. TechRxiv. 2025. https://doi.org/10.36227/techrxiv.174140719.96375390/v2</mixed-citation><mixed-citation xml:lang="en">Debnath T, Siddiky MNA, Rahman ME, Das P, Guha AK, Rahman RH, et al. A Comprehensive Survey of Prompt Engineering Techniques in Large Language Models. TechRxiv. 2025. https://doi.org/10.36227/techrxiv.174140719.96375390/v2</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Wang H, Kim J, Lee S, Park C. A Comprehensive Survey of Automatic Prompt Optimization: Taxonomies, Frameworks, and Future Directions. arXiv [preprint]. 2025. arXiv:2506.15147</mixed-citation><mixed-citation xml:lang="en">Wang H, Kim J, Lee S, Park C. A Comprehensive Survey of Automatic Prompt Optimization: Taxonomies, Frameworks, and Future Directions. arXiv [preprint]. 2025. arXiv:2506.15147</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Kim D, Lee S, Park J, Choi Y. Theoretical Foundations of Prompt Engineering: From Heuristics to Expressivity. arXiv [preprint]. 2026 Jan 13. arXiv:2512.12688v2 https://doi.org/10.48550/arXiv.2512.12688</mixed-citation><mixed-citation xml:lang="en">Kim D, Lee S, Park J, Choi Y. Theoretical Foundations of Prompt Engineering: From Heuristics to Expressivity. arXiv [preprint]. 2026 Jan 13. arXiv:2512.12688v2 https://doi.org/10.48550/arXiv.2512.12688</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Ari U. 5C Prompt Contracts: A Minimalist, Creative-Friendly, Token-Efficient Design Framework for Individual and SME LLM Usage. arXiv [preprint]. 2025 Aug 5. arXiv:2507.07045 https://doi.org/10.48550/arXiv.2507.07045</mixed-citation><mixed-citation xml:lang="en">Ari U. 5C Prompt Contracts: A Minimalist, Creative-Friendly, Token-Efficient Design Framework for Individual and SME LLM Usage. arXiv [preprint]. 2025 Aug 5. arXiv:2507.07045 https://doi.org/10.48550/arXiv.2507.07045</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Freeman B, Kicklighter A, Erdman M, Gordon Z. Toward Epistemic Stability: Engineering Consistent Procedures for Industrial LLM Hallucination Reduction. arXiv [preprint]. 2026 Mar 8. arXiv:2603.10047v1</mixed-citation><mixed-citation xml:lang="en">Freeman B, Kicklighter A, Erdman M, Gordon Z. Toward Epistemic Stability: Engineering Consistent Procedures for Industrial LLM Hallucination Reduction. arXiv [preprint]. 2026 Mar 8. arXiv:2603.10047v1</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Huang K, Chen J, Li M, Zhang Y. Prompt Engineering for Requirements Engineering: A Literature Review and Roadmap. arXiv [preprint]. 2025 Jul 10. arXiv:2507.07682 https://doi.org/10.48550/arXiv.2507.07682</mixed-citation><mixed-citation xml:lang="en">Huang K, Chen J, Li M, Zhang Y. Prompt Engineering for Requirements Engineering: A Literature Review and Roadmap. arXiv [preprint]. 2025 Jul 10. arXiv:2507.07682 https://doi.org/10.48550/arXiv.2507.07682</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Morishige M, Koshihara R. Ensuring Reproducibility in Generative AI Systems for General Use Cases: A Framework for Regression Testing and Open Datasets. arXiv [preprint]. 2025. arXiv:2505.02854 https://doi.org/10.48550/arXiv.2505.02854</mixed-citation><mixed-citation xml:lang="en">Morishige M, Koshihara R. Ensuring Reproducibility in Generative AI Systems for General Use Cases: A Framework for Regression Testing and Open Datasets. arXiv [preprint]. 2025. arXiv:2505.02854 https://doi.org/10.48550/arXiv.2505.02854</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Zeng Q, Jin C, Wang X, Zheng Y, Li Q. AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science. In: Findings of the Association for Computational Linguistics: EMNLP 2025. Suzhou, China: Association for Computational Linguistics; 2025. P. 10170–201.</mixed-citation><mixed-citation xml:lang="en">Zeng Q, Jin C, Wang X, Zheng Y, Li Q. AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science. In: Findings of the Association for Computational Linguistics: EMNLP 2025. Suzhou, China: Association for Computational Linguistics; 2025. P. 10170–201.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Tao X, Tula A, Chen X. From prompt design to iterative generation: Leveraging LLMs in PSE applications. Computers &amp; Chemical Engineering. 2025. https://doi.org/10.1016/j.compchemeng.2025.108284</mixed-citation><mixed-citation xml:lang="en">Tao X, Tula A, Chen X. From prompt design to iterative generation: Leveraging LLMs in PSE applications. Computers &amp; Chemical Engineering. 2025. https://doi.org/10.1016/j.compchemeng.2025.108284</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Zhou Y, Muresanu AI, Han Z, et al. Large Language Models Are Human-Level Prompt Engineers. arXiv [preprint]. 2022. arXiv:2211.01910 https://doi.org/10.48550/arXiv.2211.01910</mixed-citation><mixed-citation xml:lang="en">Zhou Y, Muresanu AI, Han Z, et al. Large Language Models Are Human-Level Prompt Engineers. arXiv [preprint]. 2022. arXiv:2211.01910 https://doi.org/10.48550/arXiv.2211.01910</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Vilakati S. Prompt engineering for accurate statistical reasoning with large language models in medical research. Frontiers in Artificial Intelligence. 2025;8:1658316. https://doi.org/10.3389/frai.2025.1658316</mixed-citation><mixed-citation xml:lang="en">Vilakati S. Prompt engineering for accurate statistical reasoning with large language models in medical research. Frontiers in Artificial Intelligence. 2025;8:1658316. https://doi.org/10.3389/frai.2025.1658316</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Li Z, Wang X, Yang Y, Yao Z, Xiong H, Du M. Adaptive Prompting in the Metaverse: An Iterative Prompt Optimization Framework for Enhancing LLM Performance Across Diverse Tasks. In: 2025 IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom); 2025. P. 245–52. https://doi.org/10.1109/MetaCom63298.2025.00045</mixed-citation><mixed-citation xml:lang="en">Li Z, Wang X, Yang Y, Yao Z, Xiong H, Du M. Adaptive Prompting in the Metaverse: An Iterative Prompt Optimization Framework for Enhancing LLM Performance Across Diverse Tasks. In: 2025 IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom); 2025. P. 245–52. https://doi.org/10.1109/MetaCom63298.2025.00045</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Kargaran AH, Modarressi A, Nikeghbal N, Diesner J, Yvon F, Schütze H, et al. MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment. In: Findings of the Association for Computational Linguistics: ACL 2025. Vienna, Austria: Association for Computational Linguistics; 2025. P. 27001–23. https://doi.org/10.48550/arXiv.2410.05873</mixed-citation><mixed-citation xml:lang="en">Kargaran AH, Modarressi A, Nikeghbal N, Diesner J, Yvon F, Schütze H, et al. MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment. In: Findings of the Association for Computational Linguistics: ACL 2025. Vienna, Austria: Association for Computational Linguistics; 2025. P. 27001–23. https://doi.org/10.48550/arXiv.2410.05873</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Doddapaneni S, Khan MSUR, Venkatesh D, Dabre R, Kunchukuttan A, Khapra MM, et al. Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs. In: Proceedings of the 63rd Annual Meeting of the Association forComputational Linguistics (Volume 1: Long Papers). Vienna, Austria: Association for Computational Linguistics; 2025. P. 29297–329. https://doi.org/10.48550/arXiv.2410.13394</mixed-citation><mixed-citation xml:lang="en">Doddapaneni S, Khan MSUR, Venkatesh D, Dabre R, Kunchukuttan A, Khapra MM, et al. Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs. In: Proceedings of the 63rd Annual Meeting of the Association forComputational Linguistics (Volume 1: Long Papers). Vienna, Austria: Association for Computational Linguistics; 2025. P. 29297–329. https://doi.org/10.48550/arXiv.2410.13394</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Джермакян В.Ю. Патентное право по Гражданскому кодексу Российской Федерации: постатейный комментарий, практика применения, размышления. 3-е изд., перераб. и доп. М.: 2014.</mixed-citation><mixed-citation xml:lang="en">Dzhermakyan VYu. Patent law under the Civil Code of the Russian Federation: article-by-article commentary, application practice, reflections. 3rd ed., revised and enlarged. Moscow; 2014. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Панда П, Сычева А. ChatGPT. Мастер подсказок, или как создавать сильные прмпты для нейросети. СПб: Питер; 2024. 224 с.</mixed-citation><mixed-citation xml:lang="en">Panda P, Sycheva A. ChatGPT. Master podskazok, ili kak sozdavat' sil'nye prompty dlya neyroseti. Saint Petersburg: Piter; 2024. 224 p. (In Russ.).</mixed-citation></citation-alternatives></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>
