Patent Dokümanlarının Anlamsal Benzerliğinin Tespiti Üzerine Bir İnceleme

Öz

Teknik anlamda en güncel bilgileri barındıran, yüksek hacmiyle bilgi keşfi açısından müthiş bir potansiyele sahip olan ve teknoloji yönetimi alanında kilit bir rol üstlenen patent verisinin işlenmesinde patent madenciliği çalışmaları giderek önem kazanmaktadır. Patent verisi içerisinde bulunan yapısal veya yapısal olmayan verilerin hepsi önemli olsa da, patent madenciliği çalışmalarının en kritik hedefi patent dokümanlarının anlamsal benzerliğini tespit edebilmektir. Patentlerin anlamsal benzerlik tespiti ile patent başvuru sürecinin en zor ve en çok vakit alan safhası olan patentlenebilirlik kriterlerinin tespitinin otomatik olarak yapılabilmesi mümkün olacaktır. Patent metinlerinin, metin madenciliği yöntemleri ile yapısal hale getirilerek birbirine ne kadar benzediklerini tespit etmek için küme teorisi yaklaşımları, vektör uzay modeli yaklaşımları veya ontoloji vb. bilgi kaynaklarından faydalanılan yaklaşımlar mevcuttur. Ancak patent metinlerinin karmaşık yapısı ve kendine has terminolojisi sebebiyle bu yöntemlerden hedeflenen verim alınamamaktadır. Bu eksikliği gidermek için kullanıldığı her alanda büyük başarılar ortaya koyan derin öğrenme yöntemlerinden, patent metinlerinin anlamsal olarak karşılaştırılmasında da faydalanılması gerekmektedir. Bu alanda çalışmalar yapılmasına rağmen etkin bir şekilde patentlenebilirlik tespiti yapabilen modeller henüz başlangıç aşamasındadır. Nitelikli bir model geliştirilerek patentlenebilirlik tespiti yapıldıktan sonra patent araştırma raporunun otomatik olarak hazırlanması teknoloji yönetimi alanındaki büyük ihtiyacın karşılanabilmesi adına önemli bir adım olacaktır.

Anahtar Kelimeler

• patent
• patent madenciliği
• metin madenciliği
• anlamsal benzerlik
• patentlenebilirlik
• derin öğrenme

A Review on the Determination of Semantic Similarity of Patent Documents

Öz

Patent mining studies are gaining importance in the processing of patent data, which contains the most up-to-date technical information, has a great potential in terms of information discovery with its high volume, and plays a key role in the field of technology management. Although all the structured or unstructured data in the patent data are important, the most critical goal of patent mining studies is to determine the semantic similarity of patent documents. With the semantic similarity detection of patents, it will be possible to automatically determine the patentability criteria, which is the most difficult and time-consuming phase of the patent application process. Set theory approaches, vector space model approaches or ontology etc. are used to determine how similar patent texts are to each other by structuralizing them with text mining methods. There are approaches that make use of information sources. However, due to the complex structure and unique terminology of patent texts, the targeted efficiency cannot be obtained from these methods. In order to overcome this deficiency, deep learning methods, which have shown great success in every field they are used, should also be utilized in the semantic comparison of patent texts. Although studies have been carried out in this area, models that can effectively detect patentability are still in their infancy. After a qualified model is developed and patentability is determined, the automatic preparation of the patent search report will be an important step in meeting the great need in the field of technology management.

Anahtar Kelimeler

• patent
• patent mining
• text mining
• semantic similarity
• patentability
• deep learning

Kaynakça

1. [1] Bonino D., Ciaramella A., and Corno F., "Review of the state-of-the-art in patent information and forthcoming evolutions in intelligent patent informatics", World Patent Information , 32(1): 30-38, (2010).
2. [2] Schwander P. "An evaluation of patent searching resources: comparing the professional and free on-line databases", World Patent Information, 22: 147-165, (2000).
3. [3] Madani F. and Weber C., "The evolution of patent mining: Applying bibliometrics analysis and keyword network analysis", World Patent Information, 46: 32-48, (2016).
4. [4] Kayakökü A. and Akay D., "Patent Madenciliği", Journal of Polytechnic, 24(2): 745-753, (2021).
5. [5] Kayakökü A. and Demirbaş Ş., "Patent Arama Motorlarının Kullanımı Üzerine Bir İnceleme", Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarim Ve Teknoloji, 5(3):149-165, (2017).
6. [6] Chandrasekaran D. and Mago V., "Evolution of Semantic Similarity--A Survey", ACM Computing Surveys, 54(2): 1-37, (2021).
7. [7] Krishna A.M., Jin Y., Foster C., Gabel G., Hanley B. and Youssef A., “Query Expansion for Patent Searching using Word Embedding and Professional Crowdsourcing”, ArXiv, (2019).
8. [8] Walter L. Radauer A. and Moehrle M.G., “The beauty of brimstone butterfly, novelty of patents identified by near environment analysis based on text mining”, Scientometrics, 111: 103-115, (2017).

9. [9] Arts S., Cassiman B., and Gomez J.C., “Text matching to measure patent similarity”, Strategic Manage J, 39(1): 62-84, (2018).
10. [10] Moehrle M.G., “Measures for textual patent similarities: A guided way to select appropriate approaches”, Scientometrics, 85(1): 95-109, (2010).
11. [11] Moehrle M.G. and Gerken J.M., “Measuring textual patent similarity on the basis of combined concepts: Design decisions and their consequences”, Scientometrics, 91(3): 805-826, (2012).
12. [12] An X., Li J., Xu S., Chen L. and Sun W., “An improved patent similarity measurement based on entities and semantic relations”, Journal Informetrics, 15,(2): 101-135, (2021).
13. [13] Wang X.F., Ren H.C., Chen Y., Liu Y.Q., Qiao Y.L., and Huang Y., “Measuring patent similarity with SAO semantic analysis”, Scientometrics, 121(1): 1-23, (2019)
14. [14] Bergmann I., Butzke D., Walter L., Fuerste J.P., Moehrle M.G., and Erdmann V.A., “Evaluating the risk of patent infringement by means of semantic patent analysis: the case of DNA chips”, R&D Management, 38(5): 550-562, (2008).
15. [15] Ontañón S., “An overview of distance and similarity functions for structured data”, Artificial Intelligence Review, 53(7): 5309-5351, (2020).
16. [16] Batyrshin I., Cross V., Kreinovich V., and Rifqi M., “Towards a general theory of similarity and association measures: Similarity, dissimilarity and correlation functions”, Journal of Intelligent & Fuzzy Systems, 36(4): 2977-3004, (2019).
17. [17] Park H., Yoon J., and Kim K., “Identifying patent infringement using SAO based semantic technological similarities”, Scientometrics, 90(2): 515-529, (2012).
18. [18] Shahmirzadi O., Lugowski A., and Younge K., “Text Similarity in Vector Space Models: A Comparative Study”, Book Text Similarity in Vector Space Models: A Comparative Study, (2019) .
19. [19] Wang J. and Chen Y.J., “A novelty detection patent mining approach for analyzing technological opportunities”, Advanced Engineering Informatics, 42: 100941, (2019).
20. [20] Moehrle M.G., “Similarity measurement in times of topic modelling”, World Patent Information, 59: 101934, (2019).
21. [21] Cvitanić T., Lee B., Song H.I., Fu K.K. and Rosen D.W., "LDA v. LSA: A Comparison of Two Computational Text Analysis Tools for the Functional Categorization of Patents", ICCBR Workshops, (2016).
22. [22] Sánchez D., Batet M., Isern D. and Valls A., “Ontology-based semantic similarity: A new feature-based approach”, Expert Systems with Applications, 39(9): 7718-7728, (2012).
23. [23] Sarica S., Luo J. and Wood K.L., “TechNet: Technology semantic network based on patent data”, Expert Systems with Applications, 142: 112995, (2020).
24. [24] Jang H., Jeong Y., and Yoon B. “TechWord: Development of a technology lexical database for structuring textual technology information based on natural language processing”, Expert Systems with Applications, 164, (2021).
25. [25] Cross V. and Youbo W., “Semantic Relatedness Measures in Ontologies Using Information Content and Fuzzy Set Theory”, The 14th IEEE International Conference on Fuzzy Systems, (2005) .
26. [26] Gan M., Dou X. and Jiang R., “From ontology to semantic similarity: Calculation of ontology-based semantic similarity”, The Scientific Word Journal, (2013).
27. [27] AIndukuri K.V., Ambekar A.A. and Sureka A., “Similarity Analysis of Patent Claims Using Natural Language Processing Techniques”, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007), 169-175, (2007).
28. [28] Sharma P., Tripathi R., Singh V.K. and Tripathi R.C., “Automated patents search through semantic similarity”, 2015 International Conference on Computer, Communication and Control (IC4), Indore, 1-5, (2015).
29. [29] Sharma P., Tripathi R., and Tripathi R.C., “Finding Similar Patents through Semantic Expansion”, 2016 International Conference on Computer Communication and Informatics, India, (2016).
30. [30] Villa A.M. and Wirz M., “A sequential patent search approach combining semantics and artificial intelligence to identify initial State-of-the-Art documents”, World Patent Information, 68, (2022).
31. [31] Aristodemou L. and Tietze F., “The state-of-the-art on Intellectual Property Analytics (IPA): A literature review on artificial intelligence, machine learning and deep learning methods for analysing intellectual property (IP) data”, World Patent Information, 55: 37-51, (2018).
32. [32] Genin B.L. and Zolkin D.S., “Similarity search in patents databases. The evaluations of the search quality”, World Patent Information, 64, (2021).
33. [33] Setchi R., Spasić I., Morgan J., Harrison C., and Corken R., “Artificial intelligence for patent prior art searching”, World Patent Information, 64, (2021).
34. [34] Hafner A., Damij N. and Modic D., “Augmented intelligence for state-of-the-art patent search”, 2022 IEEE Technology and Engineering Management Conference, Turkey, (2022).
35. [35] Vaish K., Rawat P., Kathuria S., Singh R., Joshi K. and Verma A., “Artificial Intelligence Reducing the Intricacies of Patent Prior Art Search”, 2023 International Conference on Computational Intelligence and Sustainable Engineering Solutions, India, (2023).
36. [36] Schellekens M., “Artificial Intelligence and the re-imagination of inventive step”, Journal of Intellectual Property, Information Technology and E-Commerce Law, 13(2): 89-98, (2022).
37. [37] Krestel R., Chikkamath R., Hewel C., and Risch J., “A survey on deep learning for patent analysis”, World Patent Information, 65, (2021).
38. [38] Whalen R., Lungeanu A., Dechurch L. and Contractor N., “Patent Similarity Data and Innovation Metrics”, Journal of Empirical Legal Studies, 17(3): 615-639, (2020).
39. [39] Helmers L., Horn F., Biegler F., Oppermann T., and Müller K.R., “Automating the search for a patent”s prior art with a full text similarity search”, Plos One, 14(3), (2019).
40. [40] Kim S., Park I. and Yoon B., “SAO2Vec: Development of an algorithm for embedding the subject–action–object (SAO) structure using Doc2Vec”, Plos One, , 15(2), (2020).
41. [41] Jeon D., Ahn J.M., Kim J. and Lee C., “A doc2vec and local outlier factor approach to measuring the novelty of patents”, Technol Forecast Soc, 174, (2022).
42. [42] Aras H., Türker R., Geiss D., Milbradt M, and Sack H., “Get your hands dirty: Evaluating word2vec models for patent data”, Proceedings of the Posters and Demos Track of the International Conference on Semantic Systems (SEMPDF), 1-4, (2018).
43. [43] Lu Y., Xiong X., Zhang W., Liu J., and Zhao R., “Research on classification and similarity of patent citation based on deep learning”, Scientometrics, 123(2): 813-839, 2020.
44. [44] Kim J., Yoon J., Park E., and Choi S., “Patent document clustering with deep embeddings”, Scientometrics, 123(2): 563-577, (2020).
45. [45] Lei L., Q, J. and Zheng K., "Patent Analytics Based on Feature Vector Space Model: A Case of IoT" IEEE Access, 7, 45705-45715. (2019).
46. [46] Chung P. and Sohn S.Y., “Early detection of valuable patents using a deep learning model: Case of semiconductor industry”, Technological Forecasting and Social Change, 158: 120-146, (2020).
47. [47] Chen L., Xu S., Zhu L., Zhang J., Lei X., and Yang G., “A deep learning based method for extracting semantic information from patent documents”, Scientometrics, 125(1): 289-312, (2020).
48. [48] Choi J., Lee J., Yoon J., Jang S., Kim J., and Choi S., “A two-stage deep learning-based system for patent citation recommendation”, Scientometrics, (2022).
49. [49] Lee J.-S., “PatentTransformer: A Framework for Personalized Patent Claim Generation”, The 32nd International Conference on Legal Knowledge and Information Systems, Spain, (2019).
50. [50] Lee J.-S., and Hsiang J., “Prior Art Search and Reranking for Generated Patent Text”, ArXiv, (2020).
51. [51] Stamatis V., “End to End Neural Retrieval for Patent Prior Art Search”, 44th European Conference on IR Research, Norway, (2022).
52. [52] Li R., Yu W., Huang Q. and Liu Y., “Patent Text Classification based on Deep Learning and Vocabulary Network”, International Journal of Advanced Computer Science and Applications, 14(1), (2023).
53. [53] Choi S., Lee H., Park E. and Choi S., “Deep learning for patent landscaping using transformer and graph embedding”, Technological Forecasting and Social Change, 175: 121-413, (2022).
54. [54] Nemani P. and Vollala S., “A Cognitive Study on Semantic Similarity Analysis of Large Corpora: A Transformer-based Approach”, 2022 IEEE 19th India Council International Conference, India, (2022).
55. [55] Lo H.-C. and Chu J.-M., “Pre-trained Transformer-based Classification for Automated Patentability Examination”, 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, Australia, (2021).