DOI QR코드

DOI QR Code

Keyword Network Analysis for Technology Forecasting

기술예측을 위한 특허 키워드 네트워크 분석

  • Choi, Jin-Ho (School of Business, Sejong University) ;
  • Kim, Hee-Su (School of Business, Sejong University) ;
  • Im, Nam-Gyu (Department of Computer Engineering, Sejong univeristy)
  • 최진호 (세종대학교 경영학과) ;
  • 김희수 (세종대학교 경영학과) ;
  • 임남규 (세종대학교 전자정보공학대학 컴퓨터공학과)
  • Received : 2011.11.18
  • Accepted : 2011.12.19
  • Published : 2011.12.31

Abstract

New concepts and ideas often result from extensive recombination of existing concepts or ideas. Both researchers and developers build on existing concepts and ideas in published papers or registered patents to develop new theories and technologies that in turn serve as a basis for further development. As the importance of patent increases, so does that of patent analysis. Patent analysis is largely divided into network-based and keyword-based analyses. The former lacks its ability to analyze information technology in details while the letter is unable to identify the relationship between such technologies. In order to overcome the limitations of network-based and keyword-based analyses, this study, which blends those two methods, suggests the keyword network based analysis methodology. In this study, we collected significant technology information in each patent that is related to Light Emitting Diode (LED) through text mining, built a keyword network, and then executed a community network analysis on the collected data. The results of analysis are as the following. First, the patent keyword network indicated very low density and exceptionally high clustering coefficient. Technically, density is obtained by dividing the number of ties in a network by the number of all possible ties. The value ranges between 0 and 1, with higher values indicating denser networks and lower values indicating sparser networks. In real-world networks, the density varies depending on the size of a network; increasing the size of a network generally leads to a decrease in the density. The clustering coefficient is a network-level measure that illustrates the tendency of nodes to cluster in densely interconnected modules. This measure is to show the small-world property in which a network can be highly clustered even though it has a small average distance between nodes in spite of the large number of nodes. Therefore, high density in patent keyword network means that nodes in the patent keyword network are connected sporadically, and high clustering coefficient shows that nodes in the network are closely connected one another. Second, the cumulative degree distribution of the patent keyword network, as any other knowledge network like citation network or collaboration network, followed a clear power-law distribution. A well-known mechanism of this pattern is the preferential attachment mechanism, whereby a node with more links is likely to attain further new links in the evolution of the corresponding network. Unlike general normal distributions, the power-law distribution does not have a representative scale. This means that one cannot pick a representative or an average because there is always a considerable probability of finding much larger values. Networks with power-law distributions are therefore often referred to as scale-free networks. The presence of heavy-tailed scale-free distribution represents the fundamental signature of an emergent collective behavior of the actors who contribute to forming the network. In our context, the more frequently a patent keyword is used, the more often it is selected by researchers and is associated with other keywords or concepts to constitute and convey new patents or technologies. The evidence of power-law distribution implies that the preferential attachment mechanism suggests the origin of heavy-tailed distributions in a wide range of growing patent keyword network. Third, we found that among keywords that flew into a particular field, the vast majority of keywords with new links join existing keywords in the associated community in forming the concept of a new patent. This finding resulted in the same outcomes for both the short-term period (4-year) and long-term period (10-year) analyses. Furthermore, using the keyword combination information that was derived from the methodology suggested by our study enables one to forecast which concepts combine to form a new patent dimension and refer to those concepts when developing a new patent.

특허의 중요성이 커짐에 따라 특허분석의 중요성 또한 점점 커지고 있다. 특허분석은 네트워크 기반 방법과 키워드 기반 방법으로 나눠지는데 네트워크 기반은 특허 내부에 존재하는 세부 기술정보에 대한 분석이 불가능하다는 단점이 있고 키워드 기반은 기술정보간의 상호관계를 규명하지 못한다는 단점이 있다. 기존에 제시된 네트워크 기반 특허 분석과 키워드 기반 분석의 한계를 극복하기 위해서 두 방법을 혼합한 방법으로서 본 연구에서는 특허 키워드 네트워크 기반 분석 방법론을 제시하였다. 본 연구에서는 LED 분야의 특허들을 대상으로 텍스트 마이닝을 통해 중요한 기술정보를 추출한 다음, 키워드 네트워크를 구축하고, 이를 대상으로 커뮤니티 네트워크 분석을 수행하였다. 분석 결과는 다음과 같다. 첫째, 특허 키워드 네트워크는 매우 낮은 밀도와 매우 높은 클러스터링 지수를 나타내었다. 밀도가 높다는 것은 LED 분야내 특허 키워드 네트워크 내 노드(키워드)들이 산발적으로 연결되어 있다는 것을 의미하며, 클러스터링 지수가 높다는 것은 해당 키워드 네트워크 내 노드, 즉 키워드들이 각각의 커뮤니티로 매우 긴밀하게 연결되어 있음을 나타낸다. 둘째, 특허 키워드 네트워크도 다른 지식네트워크와 마찬가지로 명확한 멱함수 분포를 따른다는 사실을 알 수 있었다. 이는 기존에 활발히 연구, 활용되어 많은 연결고리를 갖고 있는 특허개념(키워드)수록 지속적으로 다른 연구자들에 의해 선택되고 이 키워드를 바탕으로 새로운 키워드들이 연결되어서 이들 키워드간의 조합으로 새로운 기술이 발명된다는 것이다. 셋째, 특허가 개발될 때 특정 분야에 유입된 키워드 중 새로운 링크가 생긴 키워드의 대부분이 기존에 연결되어 있던 커뮤니티 내의 키워드들과 결합되어 새로운 특허 개념을 구성한다는 사실을 발견하였다. 이러한 사실은 단기(4년) 장기(10년) 두 기간 모두 동일하게 나타났다. 나아가 본 연구에서 제시한 방법론을 통해 도출된 특허 키워드 조합 정보를 활용하면 미래에 어떤 개념들이 합쳐져서 새로운 특허 단위로 만들어 질지 가늠해볼 수 있고, 새로운 특허를 개발할 때 참고할 수 있는 유용한 정보로 활용할 수 있다.

Keywords

References

  1. Agami, N. M. E., A. M. A. Omran, M. M. Saleh, and H. E. E. E. Shishiny, "An enhanced approach for Trend Impact Analysis", Technological Forecasting and Social Change, Vol.75, No.9(2008), 1439-1450. https://doi.org/10.1016/j.techfore.2008.03.006
  2. Albert, R., I. Albert, and G. L. Nakarado, "Structural vulnerability of the North American power grid", Physical Review E, Vol.58, No.2 (2004).
  3. Bagler, G., "Analysis of the airport network of India as a complex weighted network", Physica A:Statistical Mechanics and its Applications, Vol.387, No.12(2008), 2972-2980. https://doi.org/10.1016/j.physa.2008.01.077
  4. Bengisu, M. and R. Nekhili, "Forecasting emerging technologies with the aid of science and technology databases", Technological Forecasting and Social Change, Vol.73, No.7(2006), 835-844. https://doi.org/10.1016/j.techfore.2005.09.001
  5. Börner, K., J. T. Maru, and R. L. Goldstone, "The simultaneous evolution of author and paper networks", Proceedings of the National Academy of Sciences of the United State of America, Vol.101, No.1(2004), 5266-5273. https://doi.org/10.1073/pnas.0307625100
  6. Buchanan, M., "Nexus:small worlds and the groundbreaking theory of networks", Local : Norton, 2002.
  7. Campbell, R. S., "Patent trends as a technological Forecasting Tool", World Patent Information, Vol.5, No.3(1983), 137-143. https://doi.org/10.1016/0172-2190(83)90134-5
  8. Cancho, R. F. and V. S. Richard, "The small world of human language", Proceedings of the royal society, Vol.268, No.1482(2001), 2261-2265. https://doi.org/10.1098/rspb.2001.1800
  9. Frantzi, K., S. Ananiadou, and H. Mima, "Automatic recognition of multi-word terms", International J ournal of Digital Libraries, Vol.3, No.2(2002), 117-132.
  10. Girvan, M. and M. E. J. Newman, "Community structure in social and biological networks", Proceedings of the National Academy of Sciences of the United states of America, Vol.99, No.12(2002), 7821-7826. https://doi.org/10.1073/pnas.122653799
  11. Jeong, H., Z. Neda, and A. L. Barabasi, "Measuring preferential attachment for evolving networks", Europhysics Letters, Vol.61, No. 4(2003), 1-4. https://doi.org/10.1209/epl/i2003-00260-6
  12. Lee, S. J., B. G. Yoon, and Y. T. Park, "An approach to discovering new technology opportunities: Keyword-based patent map approach", Technovation, Vol.29, No.6/7(2009), 481-497. https://doi.org/10.1016/j.technovation.2008.10.006
  13. Lee, S. J., S. H. Lee, H. J. Seol, and Y. T. Park, "Using patent information for designing new product and technology:keyword based technology roadmapping", R&D Management, Vol.38, No.2(2008), 169-188. https://doi.org/10.1111/j.1467-9310.2008.00509.x
  14. Li, M., Y. Fana, J. Chena, L. Gaoa, Z. Dia, and J. Wua, "Weighted networks of scientific communication : the measurement and topological role of weight", Physica A : Statistical Mechanics and its Applications, Vol.350, No.2/4(2005), 643-656. https://doi.org/10.1016/j.physa.2004.11.039
  15. Li, X., H. Chen, Z. Huang, and M. C. Roco, "Patent citation network in nanotechnology (1976-2004)", Journal of Nanoparticle Research, Vol.9(2007), 337-352. https://doi.org/10.1007/s11051-006-9194-2
  16. Narin, F., "Patent bibliometrics", Scientometrics, Vol.30, No.1(1994), 147-155 https://doi.org/10.1007/BF02017219
  17. Raghavan, U. N., R. Albert, and S. Kumara, "Near linear time algorithm to detect community structures in large-scale networks", Physical Review E, Vol.76, No.5(2007).
  18. Tseng, Y. H. and C. J. Lin, "Text mining techniques for patent analysis", Information Processing and Management, Vol.43, No.4(2007), 1216-1247. https://doi.org/10.1016/j.ipm.2006.11.011
  19. Vandewalle, N., F. Brisbois, and X. Tordoir, "Non-random topology of stock markets", Quantitative Finance, Vol.1, No.3(2001), 372 -374. https://doi.org/10.1088/1469-7688/1/3/308
  20. Wanga, M. and G. D. Yua, "Measuring the preferential attachment mechanism in citation networks", Physica A:Statistical Mechanics and its Applications, Vol.387, No.18(2008), 4692-4698. https://doi.org/10.1016/j.physa.2008.03.017
  21. Wartburg, I. V., T. Teichert, and K. Rost, "Inventive progress measured by multi-stage patent citation analysis", Research Policy, Vol.34, No.10(2005), 1591-1607. https://doi.org/10.1016/j.respol.2005.08.001
  22. Weaver, W. T., "The Delphi forecasting method," The Phi Delta Kappan, Vol.52, No.5 (1971), 267-271.
  23. Yoon, B. G. and Y. T. Park, "A text-mining- based patent network:Analytical tool for high-technology trend", Journal of High Technology Management Research, Vol.15, No.1(2004), 37-50. https://doi.org/10.1016/j.hitech.2003.09.003
  24. Yoon, B. G. and Y. T. Park, "Development of new technology forecasting algorithm:hybrid approach for morphology analysis and conjoint analysis of patent information", IEEE Transactions on Engineering Management, Vol.54, No.3(2007), 588-599. https://doi.org/10.1109/TEM.2007.900796
  25. Yoon, B. U., C. B. Yoon, and Y. T. Park, "On the development and application of a self-organizing feature map-based patent map", R&D Management, Vol.32, No.4(2002), 29 1-300. https://doi.org/10.1111/1467-9310.00261

Cited by

  1. 텍스트 마이닝을 활용한 신문사에 따른 내용 및 논조 차이점 분석 vol.18, pp.3, 2012, https://doi.org/10.13088/jiis.2012.18.3.053
  2. 특허 인용 네트워크 분석을 통한 기술지식의 확산 경로 분석: 정보통신기술을 중심으로 vol.10, pp.1, 2011, https://doi.org/10.16972/apjbve.10.1.201502.143
  3. 기록관리학 분야 국내 학술지의 연구동향에 관한 연구: 「한국기록관리학회」와 「기록학연구」를 중심으로 vol.33, pp.1, 2011, https://doi.org/10.3743/kosim.2016.33.1.085
  4. An Analysis of the “One Belt, One Road” Research Trend Using Social Network Analysis vol.32, pp.2, 2011, https://doi.org/10.37059/tjosal.2016.32.2.387
  5. Analyzing the Change of Discourse about Adolescent Problems Based on the Foucault’s Governmentality vol.18, pp.2, 2011, https://doi.org/10.15703/kjc.18.2.201704.223
  6. 조달청 OPEN API 빅데이터를 활용한 공공 소프트웨어 산업의 SNA 패턴 분석 vol.24, pp.3, 2011, https://doi.org/10.22693/niaip.2017.24.3.042
  7. 소셜 네트워크 분석(SNA)을 이용한 실과(기술·가정)교육 분야 연구 동향 분석 vol.56, pp.6, 2018, https://doi.org/10.6115/fer.2018.043
  8. A Study on Foresight the Promising Technology in IoT-based U-Health Industry vol.3, pp.4, 2011, https://doi.org/10.33443/tm.2018.3.4.99
  9. A Study on the Deduction and Diffusion of Promising Artificial Intelligence Technology for Sustainable Industrial Development vol.12, pp.14, 2011, https://doi.org/10.3390/su12145609
  10. 한중일 사물인터넷(IoT) 관련 특허의 IPC 코드 기반 기술융복합 분석 : PCT 국제출원을 중심으로 vol.24, pp.7, 2011, https://doi.org/10.6109/jkiice.2020.24.7.949
  11. 키워드 네트워크 분석을 이용한 공공데이터 수요 예측 vol.27, pp.4, 2020, https://doi.org/10.22693/niaip.2020.27.4.024
  12. Introducing Patents with Indirect Connection (PIC) for Establishing Patent Strategies vol.13, pp.2, 2011, https://doi.org/10.3390/su13020820
  13. Tracing the evolution of physics with a keyword co-occurrence network vol.78, pp.3, 2011, https://doi.org/10.1007/s40042-020-00051-5
  14. 5개국 바이오헬스 산업의 기술융합과 트렌드 분석 : 특허 동시분류분석과 텍스트마이닝을 활용하여 vol.12, pp.4, 2011, https://doi.org/10.15207/jkcs.2021.12.4.009