Intellectual search for analogous patents based on graph representations of the invention's structure

The relevance of this work stems from the fact that traditional patent search systems, which are based on relational databases and keywords, are unable to effectively capture the rich context and complex semantic relationships inherent in patent data. The method of intellectual search for patent-analogs based on subgraph isomorphism in a graph database storing component structures of devices described in inventions is proposed. Intelligence manifests itself in the ability of the system to "understand" the structural essence of the invention, to abstract from the text description and to find technically close solutions even in the case of non-matching keywords. The component structure of the devices was obtained by analyzing patent texts using a previously developed neural network model. A patent is represented as a graph, where nodes represent the elements of the invention and edges represent their relationships, enabling the use of graph algorithms to identify relevant patents. Algorithms have been developed for: parsing a JSON file describing the component structure and loading the information into a graph database; comparing graph representations of the invention's component structure; and editing the graph representation of the invention's component structure. The practical significance lies in the developed patent similarity search module, which is based on graph representations of an invention's component structure. This module can be useful during the stages of filing a patent application by the applicant and conducting a patent examination by a patent office examiner. The software module is implemented in Python using the Neo4j graph DBMS.

1. Fomenkov S.A., Korobkin D.M., Korobkina V.S. Search for patent analogues based on a comparison of key phrases. Engineering Journal of Don. 2024;(11). (In Russ.). URL: http://www.ivdon.ru/en/magazine/archive/n11y2024/9604

2. Bobunov A.V., Korobkin D.M., Fomenkov S.A., Vasiliev S.S. Development of a software module for searching for patent analogues. Engineering Journal of Don. 2022;(11). (In Russ.). URL: http://www.ivdon.ru/en/magazine/archive/n11y2022/8018

3. Baeza-Yates R., Ribeiro-Neto B. Modern Information Retrieval: The Concepts and Technology Behind Search. Addison-Wesley; 2011. 913 p.

4. Liu B. Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data. Berlin, Heidelberg: Springer; 2011. 624 p. https://doi.org/10.1007/978-3-642-19460-3

5. Kim W.Ch., Mauborgne R. Blue Ocean Strategy: How to Create Uncontested Market Space and Make Competition Irrelevant. Boston: Harvard Business School Press; 2005. 240 p.

6. Robinson I., Webber J., Eifrem E. Graph Databases: New Opportunities for Connected Data. Sebastopol: O'Reilly Media; 2015. 238 p.

7. Hogan A., Blomqvist E., Cochez M., et al. Knowledge Graphs. ACM Computing Surveys. 2021;54(4). https://doi.org/10.1145/3447772

8. Sarica S., Song B., Low E., Luo J. Engineering Knowledge Graph for Keyword Discovery in Patent Search. Proceedings of the Design Society: International Conference on Engineering Design. 2019;1(1):2249–2258. https://doi.org/10.1017/dsi.2019.231

9. Haveliwala T.H. Topic-Sensitive PageRank. In: WWW '02: Proceedings of the 11th International Conference on World Wide Web, 07–11 May 2002, Honolulu, HI, USA. New York: ACM; 2002. P. 517–526. https://doi.org/10.1145/511446.511513

10. McColl R.C., Ediger D., Poovey J., Campbell D., Bader D.A. A performance evaluation of open source graph databases. In: PPAA '14: Proceedings of the first workshop on Parallel programming for analytics applications, 16 February 2014, Orlando, FL, USA. New York: ACM; 2014. P. 11–18. https://doi.org/10.1145/2567634.2567638

11. Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv. URL: https://arxiv.org/abs/1810.04805 [Accessed 9th September 2025].

12. Reimers N., Gurevych I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv. URL: https://arxiv.org/abs/1908.10084 [Accessed 9th September 2025].

13. Yang Y., Cui X. Bert-Enhanced Text Graph Neural Network for Classification. Entropy. 2021;23(11). https://doi.org/10.3390/e23111536

14. Zuo H., Yin Y., Childs P. Patent-KG: Patent Knowledge Graph Extraction for Engineering Design. Proceedings of the Design Society. 2022;2:821–830. https://doi.org/10.1017/pds.2022.84

15. Korobkin D., Vasiliev S., Fomenkov S., Kravets A. The Deep Learning Method for Information Extracting about the Components of Patented Devices and their Relationships. In: 2024 6th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), 13–15 November 2024, Lipetsk, Russia. IEEE; 2024. P. 437–442. http://doi.org/10.1109/SUMMA64428.2024.10803690