Selection of Innovative Technologies in Greenhouse Systems: A Multi-Criteria Approach Based on Patent Data

Öz

The ever-increasing pace of technological development has led to shorter lifecycles for technological projects, making it crucial for researchers and technology companies to carefully consider when, where, and how much to invest. Moreover, the current trend of technological research and innovation transitioning from within a single sector to a more interdisciplinary and collaborative framework involving multiple companies and groups heightens the necessity for businesses to gather information to identify collaboration areas and potential partners. In this context, for an organization working in a certain field and aiming to innovate, the question of which technologies it should invest in to take its work forward is among the most important problems of innovation today. This study proposes an innovative and objective method for selecting technologies by leveraging patent data, data mining algorithms, and Multi-Criteria Decision-Making (MCDM) techniques. The research focuses on greenhouse technologies, a vital area within agricultural innovation, and uses patent data to identify promising technological directions. Patent records from the European Patent Office (EPO) were collected using a custom software tool that queries patents within the CPC classification Y02A40/25 (Greenhouse Technologies). After cleaning the data, the FP-Growth algorithm was applied to identify frequently co-occurring technology classifications. Five key criteria were used to evaluate these technology pairs: support value (frequency), average patent age, average forward citations, average backward citations, and the average patent strength of leading applicant companies. Using the Entropy Weight method, objective weights were assigned to each criterion. The TOPSIS method was then applied to rank the identified technology pairs in terms of their overall suitability for investment and innovation. The results indicated that greenhouse cultivation (A01G9), hydroponic farming (A01G31), plant processing (A01G7), agriculture-related technologies (Y02P60), and business-specific software systems (G06Q50) are the most strategic areas for innovation. Notably, the inclusion of G06Q50 underscores the growing importance of software and digital infrastructure in greenhouse innovation. This suggests that companies aiming to advance in this field should not only enhance their core greenhouse technologies but also invest in complementary software and algorithmic solutions. In conclusion, the study presents a novel framework for technology selection that can guide R&D investment decisions using patent data, especially in sectors where innovation plays a critical role.

Anahtar Kelimeler

• Technology selection
• Greenhouse technologies
• Patent analysis
• Multi-Criteria Decision Making
• FP-Growth
• Entropy weight

Sera Sistemlerinde Yenilikçi Teknoloji Seçimi: Patent Verilerine Dayalı Çok Kriterli Bir Yaklaşım

Öz

Teknolojik gelişmelerin artan hızı, teknolojik projelerin yaşam döngülerini kısaltmış ve bu durum, araştırmacılar ile teknoloji şirketlerinin ne zaman, nerede ve hangi ölçüde yatırım yapacaklarını titizlikle planlamalarını zorunlu kılmıştır. Teknolojik araştırma ve inovasyonun disiplinler arası ve çok paydaşlı bir yapıya yönelmesi, işletmelerin iş birliği alanlarını ve potansiyel ortaklarını belirlemek amacıyla kapsamlı veri toplama ihtiyacını artırmaktadır. Bu bağlamda, belirli bir alanda çalışan ve yenilik yapmayı hedefleyen bir organizasyon için, çalışmalarını ileriye taşımada, hangi teknolojilere yatırım yapması gerektiği sorusu, günümüz inovasyonunun en önemli sorunları arasındadır. Bu çalışma, patent verileri, veri madenciliği algoritmaları ve çok kriterli karar verme (ÇKKV) tekniklerinden yararlanarak teknolojilerin seçilmesi için yenilikçi ve nesnel bir yöntem önermektedir. Araştırma, tarımsal inovasyon içinde hayati bir alan olan sera teknolojilerine odaklanmakta ve gelecek vaat eden teknolojileri belirlemek için patent verilerini kullanmaktadır. Patent verileri, özel bir yazılım aracı kullanılarak Avrupa Patent Ofisi'nden (EPO) alınmıştır. CPC sınıflandırması Y02A40/25 (Sera Teknolojileri) içindeki patentler sorgulanmıştır. Veriler temizlendikten sonra, sıklıkla birlikte görülen teknoloji sınıflandırmalarını belirlemek için FP-Büyüme algoritması uygulanmıştır. Bu teknoloji çiftlerini değerlendirmek için beş temel ölçüt: destek değeri (frekans), ortalama patent yaşı, ortalama ileri atıflar, ortalama geri atıflar ve önde gelen başvuru şirketlerinin ortalama patent gücü kullanılmıştır. Entropi Ağırlığı yöntemi kullanılarak, her ölçüte nesnel ağırlıklar atanmıştır. Belirlenen teknoloji çiftleri, yatırım ve inovasyon için genel uygunlukları açısından TOPSIS yöntemi ile sıralanmıştır. Sonuçlar, sera yetiştiriciliğinin (A01G9), hidroponik çiftçiliğin (A01G31), bitki işlemenin (A01G7), tarımla ilgili teknolojilerin (Y02P60) ve işletmeye özgü yazılım sistemlerinin (G06Q50) inovasyon için en stratejik alanlar olduğunu göstermiştir. Özellikle, G06Q50'nin dahil edilmesi, sera inovasyonunda yazılım ve dijital altyapının artan önemini vurgulamaktadır. Bu, alanda ilerlemeyi hedefleyen şirketlerin yalnızca temel sera teknolojilerini geliştirmekle kalmayıp aynı zamanda tamamlayıcı yazılım ve algoritmik çözümlere de yatırım yapmaları gerektiğini göstermektedir. Sonuç olarak, çalışma, özellikle inovasyonun kritik bir rol oynadığı sektörlerde, patent verilerini kullanarak Ar-Ge yatırım kararlarına rehberlik edebilecek teknoloji seçimi için yeni bir çerçeve sunmaktadır.

Anahtar Kelimeler

• Teknoloji seçimi
• Sera teknolojileri
• Patent analizi
• Çok kriterli karar verme
• FP-Büyüme algoritması
• Entropi ağırlığı

Kaynakça

1. Abbas, A., Zhang, L. and Khan, S.U. (2014). A literature review on the state-of-the-art in patent analysis, World Patent Information, 37: 3-13.
2. Al-Chalabi, M. (2015). Overview of hydroponic and aeroponic systems for urban agriculture. Journal of Agricultural Science, 7(5): 1–10.
3. Altuntaş, S. and Sezer, M. (2021). A novel technology intelligence tool based on utility mining. IEEE Transactions on Engineering Management, 70(7): 2480-2492.
4. An, J., Kim, K., Mortara, L. and Lee, S. (2018). Deriving technology intelligence from patents: Preposition-based semantic analysis. Journal of Informetrics, 12(1): 217-236.
5. Aznar-Sánchez, J. A., Velasco-Muñoz, J. F., López-Felices, B. and Román-Sánchez, I. M. (2020). An analysis of global research trends on greenhouse technology: Towards a sustainable agriculture. International Journal of Environmental Research and Public Health, 17(2): 4.
6. Cano, P. B., Carcedo, A. J. P., Hernández, C. M. and García, C. M. (2025). Trends in agricultural technology: A review of US patents. Precision Agriculture, 26(59): 1-17.
7. Cascini, G. and Zini, M. (2008). Measuring patent similarity by comparing inventions functional trees. IFIP International Federation for Information Processing, 277: 31–42.
8. Chan, F. T. S., Chan, M. H. and Tang, N. K. H. (2000). Evaluation methodologies for technology selection. Journal of Materials Processing Technology, 107(1–3): 330–337.

9. Choi, Y., Park, S. and Lee, S. (2021). Identifying emerging technologies to envision a future innovation ecosystem: A machine learning approach to patent data. Scientometrics, 126(7):5431-5476.
10. Cocis, A.-D., Batrancea, L. and Tulai, H. (2021). The link between corporate reputation and financial performance and equilibrium within the airline industry. Mathematics, 9(17): 2150.
11. Crosby, M. (2000). Patents, innovation and growth. Economic Record, 76(234): 255-262.
12. Çinkılıç, L., Varış, S. and Kubaş, A. (2014). Greenhouse vegetable growing and its problems in Thrace Regio. Journal of Tekirdag Agricultural Faculty, 11(2): 1-10. (In Turkish)
13. Ernst, H. (1997a). The use of patent data for technological forecasting: the diffusion of CNC-technology in the machine tool industry. Small Business Economics, 9(4): 361-381.
14. Ernst, H. (1997b). The Patent Portfolio for Strategic R&D Planning. Innovation in Technology Management - The Key to Global Leadership, PICMET 1997: Portland International Conference on Management and Technology, 31 July, P. 491-496, Portland, OR, USA.
15. Ernst, H. (2003). Patent information for strategic technology management. World Patent Information, 25(3): 233-242.
16. European Patent Office. Legal event data. https://www.epo.org/en/searching-for-patents/helpful-resources/first-time-here/legal-event-data (Accessed Date: 13.05.2025).
17. European Patent Office. (2022). EPO worldwide legal event data (INPADOC). Bulk Data Sets. https://www.epo.org/en/searching-for-patents/data/bulk-data-sets/inpadoc (Accessed Date: 13.05.2025).
18. Griliches, Z. (1998). Patent Statistics as Economic Indicators: A Survey. In: R&D and Productivity: The Econometric Evidence Z., Ed(s): Griliches, University of Chicago Press.
19. Han, J., Pei, J. and Yin, Y. (2004). Mining frequent patterns without candidate generation: A frequent-pattern tree approach. Data Mining and Knowledge Discovery, 8(1): 53-87.
20. Hwang, C.L. and Yoon, K. (1981). Methods for Multiple Attribute Decision Making–Methods and Applications: A State-of-the-art Survey. Springer, Berlin/Heidelberg, Germany.
21. Jun, S. (2011). IPC Code Analysis of Patent Documents Using Association Rules and Maps – Patent Analysis of Database Technology. International Conference on Bio-Science and Bio-Technology (ICBB). 11-12 October, P. 21-30, Yogyakarta, Indonesia.
22. Kim, G. and Bae, J. (2017). A novel approach to forecast promising technology through patent analysis. Technological Forecasting and Social Change, 117: 228-237.
23. Kim, Y. G., Suh, J. H. and Park, S. C. (2008). Visualization of patent analysis for emerging technology. Expert Systems with Applications, 34(3): 1804-1812.
24. Kim, G. J., Park, S. S. and Jang, D. S. (2015). Technology forecasting using topic-based patent analysis. Journal of Scientific and Industrial Research, 74(5): 265-270.
25. Lee, S. and Park, Y. (2005). Customization of technology roadmaps according to roadmapping purposes: Overall process and detailed modules. Technological Forecasting and Social Change, 72(5): 567-583.
26. Lee, S., Yoon, B., Lee, C. and Park, J. (2009a). Business planning based on technological capabilities: Patent analysis for technology-driven roadmapping. Technological Forecasting and Social Change, 76(6): 769-786.
27. Lee, S., Yoon, B. and Park, Y. (2009b). An approach to discovering new technology opportunities: Keyword-based patent map approach. Technovation, 29(6–7): 481-497.
28. Lingua, D. G. (2005). INPADOC: 30 years of endeavours yet unmapped territories remain. World Patent Information, 27(2): 105-111.
29. Mohammadian, A., Dahooie, J. H. and Qorbani, A. R. (2020). Prioritizing the applications of internet of things in the agriculture by using sustainable development indicators. Iranian Journal of Agricultural Economics and Development Research, 51(4):745-759.
30. Oztaysi, B. (2014). A decision model for information technology selection using AHP integrated TOPSIS-Grey: The case of content management systems. Knowledge-Based Systems, 70: 44-54.
31. Paci, R., Sassu, A. and Usai, S. (1997). International patenting and national technological specialization. Technovation, 17(1): 25-38.
32. Park, I., Jeong, Y., Yoon, B. and Mortara, L. (2014). Exploring potential R&D collaboration partners through patent analysis based on bibliographic coupling and latent semantic analysis. Technology Analysis & Strategic Management, 27(7): 759-781.
33. Park, S., Lee, S. J. and Jun, S. (2015). A network analysis model for selecting sustainable technology. Sustainability, 7(10): 13126-13141.
34. Pérez-Alonso, J., García-Martínez, A., and López, M. (2020). Energy efficiency and resource management in modern greenhouses. Renewable Energy, 148: 1116-1127.
35. Resh, H. M. (2022). Hydroponic Food Production: A Definitive Guidebook for the Advanced Home Gardener and the Commercial Hydroponic Grower. CRC Press, Boca Raton, USA.
36. Salvadó, L.L., Villeneuve, E., Masson, D., Abi Akle, A. and Bur, N. (2022). Decision Support System for technology selection based on multi-criteria ranking: Application to NZEB refurbishment. Building and Environment, 212.
37. Shen, Y.-C., Chang, S.-H., Lin, G. T. R., and Yu, H.-C. (2010). A hybrid selection model for emerging technology. Technological Forecasting and Social Change, 77(1): 151-166.
38. Sivri, M. and Çanakcı, M. (2024). Determination of spraying properties of nozzle plates in greenhouse sprayers in use. Journal of Tekirdag Agricultural Faculty, 21(3): 648-665. (In Turkish).
39. Song, K. and Ran, C. (2023). Research on technology opportunity identification based on topic mining and patent evaluation: A case study of smart agriculture. Library and Information Service, 67(3): 61-71.
40. Torkkeli, M. and Tuominen, M. (2002). The contribution of technology selection to core competencies. International Journal of Production Economics, 77(3): 271-284.
41. Van Straten, G., van Willigenburg, L. and van Henten, E. (2019). Robotics and automation in greenhouse crop production. Biosystems Engineering, 187: 1-14.
42. Wang, Y. L. (2012). Research on technology selection for enterprises with tools of patent analysis. International Conference on Management Science and Engineering-Annual Conference Proceedings, 1: 1651-1657.
43. Yoon, B., Phaal, R. and Probert, D. (2008). Morphology analysis for technology roadmapping: Application of text mining. R and D Management, 38(1): 51-68.
44. Zhu, Y., Tian, D., and Yan, F. (2020). Effectiveness of entropy weight method in decision-making. Mathematical Problems in Engineering, 2020: 1-5.