上海交通大学学报

上海交通大学学报 >

2020 , Vol. 54 >Issue 7: 705 - 717

DOI: https://doi.org/10.16183/j.cnki.jsjtu.2020.99.007

学报（中文）

采用机器学习算法的技术机会挖掘模型及应用

展开
  • 西北工业大学 管理学院， 西安 710129

网络出版日期: 2020-07-31

基金资助

国家自然科学基金资助项目(71971170)

收起

Model of Technology Opportunity Mining Using Machine Learning Algorithm and Its Application

Expand
  • School of Management, Northwestern Polytechnical University, Xi’an 710129, China

Online published: 2020-07-31

Fold

摘要

现有技术机会挖掘结果的应用性较低，究其原因，一是样本量较小，二是挖掘过程缺乏对技术应用前景的评估.为解决这一问题，以提升挖掘结果的应用性为目标，以海量专利为样本，在现有研究的基础上，加入对技术应用前景的评估，提出三维的专利预测模型.采用机器学习下的PLSA算法，结合Hadoop平台下的MapReduce计算框架，运用专利文本挖掘，构建专利预测模型的技术维和功效维；采用熵权和TOPSIS法构建专利预测模型的价值维；基于MapReduce计算框架填充专利预测模型的单元项.并以DII数据库中钛领域1999～2018年 133508 例专利文本为样本应用了专利预测模型.结果显示，该模型在钛领域内共挖掘出了3个优先级和2个次级的技术机会，可以按优先顺序对技术机会进行开发.该模型丰富了技术机会挖掘的方法，为创新主体指明了更为准确和前景化的技术研发方向.

关键词： 机器学习算法; 专利文本挖掘; 技术机会; 钛

本文引用格式

包清临, 柴华奇, 赵嵩正, 王吉林 . 采用机器学习算法的技术机会挖掘模型及应用[J]. 上海交通大学学报, 2020 , 54(7) : 705 -717 . DOI: 10.16183/j.cnki.jsjtu.2020.99.007

Abstract

The applicability of the existing technology opportunity mining results is relatively low owing to the small sample size and the lack of evaluation on the technology application prospects in the mining process. In order to solve this problem, with the goal of improving the applicability of mining results, based on the existing research, this paper proposes a three-dimensional patent prediction model by taking into account a large number of patents and adding an assessment of the prospects for technology applications. Using the PLSA algorithm in machine learning and combining with the MapReduce computing framework under Hadoop, it uses patent text mining to construct the technology and function dimensions of the patent prediction model, adopts entropy weight and TOPSIS method to construct the value dimension of the patent prediction model, and fills the element items in the patent forecasting model based on the MapReduce computing framework. Then, it applies a patent prediction model to 133508 patent texts in the titanium field in the DII database from 1999 to 2018. The results show that the model has identified a total of 3 priority and 2 secondary technology opportunities in the titanium field, and these technology opportunities can be developed in order of priority. This model enriches the method for technology opportunity mining and provides a more accurate and prospective technology research and development direction for innovation subjects.

Key words： machine learning algorithms; patent text mining; technology opportunity; titanium

参考文献

［1］TRAPPEY A J C, TRAPPEY C V, CHANG A C, et al. Deriving competitive foresight using an ontology-based patent roadmap and valuation analysis［J］. International Journal on Semantic Web and Information Systems, 2019, 15(2): 68-91. ［2］FRISHAMMAR J, RICHTNR A, BRATTSTRM A, et al. Opportunities and challenges in the new innovation landscape: Implications for innovation auditing and innovation management［J］. European Management Journal, 2019, 37(2): 151-164. ［3］BERG C, ALEXANDER A T. The openness of open innovation in ecosystems: Integrating innovation and management literature on knowledge linkages［J］. Journal of Innovation & Knowledge, 2019, 4(4): 211-218. ［4］KARIA N. Knowledge resources, technology resources and competitive advantage of logistics service providers［J］. Knowledge Management Research & Practice, 2018, 16(3): 414-426. ［5］KUNCORO W, SURIANI W O. Achieving sustainable competitive advantage through product innovation and market driving［J］. Asia Pacific Management Review, 2018, 23(3): 186-192. ［6］CHEN C. Searching for intellectual turning points: Progressive knowledge domain visualization［J］. PNAS, 2004, 101(Sup.1): 5303-5310. ［7］GRAFSTRM J. International knowledge spillovers in the wind power industry: Evidence from the European Union［J］. Economics of Innovation and New Technology, 2018, 27(3): 205-224. ［8］江屏, 张瑞红, 孙建广, 等. 基于TRIZ的专利规避设计方法与应用［J］. 计算机集成制造系统, 2015, 21(4): 914-923. JIANG Ping, ZHANG Ruihong, SUN Jianguang, et al. Method and application of patent design around based on TRIZ［J］. Computer Integrated Manufacturing Systems, 2015, 21(4): 914-923. ［9］WANG M Y, FANG S C, CHANG Y H. Exploring technological opportunities by mining the gaps between science and technology: Microalgal biofuels［J］. Technological Forecasting and Social Change, 2015, 92: 182-195. ［10］JIA L Z, WU C L, ZHU X H, et al. Design by analogy: Achieving more patentable ideas from one creative design［J］. Chinese Journal of Mechanical Engineering, 2018, 31: 37. ［11］CHENG T Y. A new method of creating technology/function matrix for systematic innovation without expert［J］. Journal of Technology Management & Innovation, 2012, 7(1): 118-127. ［12］JIN G, JEONG Y, YOON B. Technology-driven roadmaps for identifying new product/market opportunities: Use of text mining and quality function deployment［J］. Advanced Engineering Informatics, 2015, 29(1): 126-138. ［13］JOUNG J, KIM K. Monitoring emerging technologies for technology planning using technical keyword based analysis from patent data［J］. Technological Forecasting and Social Change, 2017, 114: 281-292. ［14］李凡, 鲁明羽, 陆玉昌. 关于文本特征抽取新方法的研究［J］. 清华大学学报(自然科学版), 2001, 41(7): 98-101. LI Fan, LU Mingyu, LU Yuchang. Research about new methods of text feature extraction［J］. Journal of Tsinghua University (Science and Technology), 2001, 41(7): 98-101. ［15］宋晓雷, 王素格, 李红霞, 等.基于概率潜在语义分析的词汇情感倾向判别［J］. 中文信息学报, 2011, 25(2): 89-93. SONG Xiaolei, WANG Suge, LI Hongxia, et al. Word sentiment orientation discrimination based on PLSA［J］. Journal of Chinese Information Processing, 2011, 25(2): 89-93. ［16］DEERWESTER S, DUMAIS S T, FURNAS G W, et al. Indexing by latent semantic analysis［J］. Journal of the American Society for Information Science, 1990, 41(6): 391-407. ［17］HOFMANN T. Probabilistic latent semantic analysis［DB/OL］. (2013-01-23).http:∥arxiv.org/abs/1301.6705. ［18］李宁, 罗文娟, 庄福振, 等.基于MapReduce的并行PLSA算法及在文本挖掘中的应用［J］. 中文信息学报, 2015, 29(2): 79-86. LI Ning, LUO Wenjuan, ZHUANG Fuzhen, et al. MapReduce based parallel probabilistic latent semantic analysis for text mining［J］. Journal of Chinese Information Processing, 2015, 29(2): 79-86. ［19］HUANG J Y, HSU H T. Technology-function matrix based network analysis of cloud computing［J］. Scientometrics, 2017, 113(1): 17-44. ［20］KIM G, BAE J. A novel approach to forecast promising technology through patent analysis［J］. Technological Forecasting and Social Change, 2017, 117: 228-237. ［21］WANG H, CHI Y, HSIN P. Constructing patent maps using text mining to sustainably detect potential technological opportunities［J］. Sustainability, 2018, 10(10): 3729. ［22］LIU K, YEN Y, KUO Y H. A quick approach to get a technology-function matrix for an interested technical topic of patents［J］. International Journal of Arts and Commerce, 2013, 2(6): 85-96. ［23］TRAPPEY A J C, TRAPPEY C V, WANG T M, et al. Ontology-based technology function matrix for patent analysis of additive manufacturing in the dental industry［J］. International Journal of Manufacturing Research, 2017, 12(1): 64-82. ［24］TARP M, FRIIS T, OLSEN P, et al. Automated reduction of statistical errors in the estimated correlation function matrix for operational modal analysis［J］. Mechanical Systems and Signal Processing, 2019, 132: 790-805. ［25］PAKES A, SCHANKERMAN M. The rate of obsolescence of patents, research gestation lags, and the private rate of return to research resources［M］∥R&D, patents, and productivity. Chicago: University of Chicago Press, 1984: 73-88. ［26］REITZIG M. What determines patent value? Insights from the semiconductor industry［J］. Research Policy, 2003, 32(1): 13-26. ［27］BAKKER J. The log-linear relation between patent citations and patent value［J］. Scientometrics, 2017, 110(2): 879-892. ［28］BESSEN J, NEUHUSLER P, TURNER J L, et al. Trends in private patent costs and rents for publicly-traded United States firms［J］. International Review of Law and Economics, 2018, 56: 53-69. ［29］HILLER R S, SAVAGE S J, WALDMAN D M. Using aggregate market data to estimate patent value: An application to United States smartphones 2010 to 2015［J］. International Journal of Industrial Organization, 2018, 60: 1-31. ［30］MA J, PORTER A L. Analyzing patent topical information to identify technology pathways and potential opportunities［J］. Scientometrics, 2015, 102: 811-827. ［31］GINTING G, FADLINA, MESRAN, et al. Technical approach of TOPSIS in decision making［J］. International Journal of Recent Trends in Engineering & Research, 2017, 3(8): 58-64. ［32］HEGDE D, LUO H. Patent publication and the market for ideas［J］. Management Science, 2018, 64(2): 652-672. ［33］HARRIGAN K R, DI GUARDO M C, MARKU E. Patent value and the Tobin’s Q ratio in media services［J］. The Journal of Technology Transfer, 2018, 43(1): 1-19. ［34］VAN RAAN A F J. Patent citations analysis and its value in research evaluation: A review and a new approach to map technology-relevant research［J］. Journal of Data and Information Science, 2017, 2(1): 13-50. ［35］万小丽, 朱雪忠.专利价值的评估指标体系及模糊综合评价［J］. 科研管理, 2008, 29(2): 185-191. WAN Xiaoli, ZHU Xuezhong. The indicator system and fuzzy comprehensive evaluation of patent value［J］. Science Research Management, 2008, 29(2): 185-191. ［36］孙玉艳, 张文德.企业专利量化评估系统的设计与实现［J］. 现代图书情报技术, 2009, 25(11): 64-68. SUN Yuyan, ZHANG Wende. Design and implementation of evaluation system of enterprise patent value［J］. New Technology of Library and Information Service, 2009, 25(11): 64-68. ［37］HWANG C L, YOON K. Methods for multiple attribute decision making［M］∥Multiple attribute decision making. Berlin, Heidelberg: Springer, 1981: 58-191. ［38］CHEN C T. Extensions of the TOPSIS for group decision-making under fuzzy environment［J］. Fuzzy Sets and Systems, 2000, 114(1): 1-9. ［39］JAHANSHAHLOO G R, LOTFI F H, IZADIKHAH M. Extension of the TOPSIS method for decision-making problems with fuzzy data［J］. Applied Mathematics and Computation, 2006, 181(2): 1544-1551. ［40］BISWAS P, PRAMANIK S, GIRI B C. TOPSIS method for multi-attribute group decision-making under single-valued neutrosophic environment［J］. Neural Computing and Applications, 2016, 27(3): 727-737. ［41］Clarivate. Manual code lookup ［EB/OL］. ［2020-03-05］. http:∥ips.clarivate.com/cgi-bin/mc/displaycode.cgi.
Options
文章导航

/

〈 〉