|
|
|
| Patent Evaluation with a Machine Learning Approach |
| Liu Xia1, Huang Can1, Yu Xiaofeng2 |
1.Institute for Intellectual Property Management, School of Management, Zhejiang University, Hangzhou 300058
2.Department of Computer Science & Engineering, The Hong Kong University of Science and Technology, Hong Kong 999077 |
|
|
|
|
Abstract As the number of patent applications in CNIPA (China National Intellectual Property Administration) increases, patent value is of great interest throughout industries, governments, and academies. However, the existing statistic and econometric models cannot take advantage of huge samples of patent data for value prediction. Based on more than 850,000 patent applications field in 2010 and 2011, this paper provides a machine learning approach to predict patent forward citations at an early stage by using multiple patent indicators that can be defined immediately after the relevant patents are public. The developed model could provide a prediction on whether the relevant patent would receive forward citations; however it was weak in differentiating between high and low citations. Moreover, based on the Gini impurity, features of backward citations provide more information for value prediction. In other words, the prior art search process during the patent examination should be focused on. Finally, the paper discusses the limitations of the adopted model, as well as improvement methods for further studies.
|
|
Received: 04 October 2018
|
|
|
|
1 世界知识产权组织(WIPO). 2011年世界知识产权指标[R/OL]. 2011. https://www.wipo.int/publications/en/details.jsp?id=236& plang=EN.
2 ReutersThomson. China s IQ (innovation quotient)-trends in patenting and the globalization of Chinese innovation[R/OL]. 2014. https://www.rouse.com/magazine/news/chinas-iq-innovation- quotient-trends-in-patenting-and-the-globalization-of-chinese- innovation/.
3 裴宏, 吴艳. 实施专利质量提升工程加快建设知识产区强国[N/OL]. 知识产权报, 2017, http://www.sipo.gov.cn/zscqgz/1101209.html.
4 郭俊华, 杨晓颖. 专利资助政策的评估及改进策略研究——以上海市为例[J]. 科学学研究, 2010, 28(1): 17-25.
5 龙小宁, 王俊. 中国专利激增的动因及其质量效应[J]. 世界经济, 2015(6): 115-142.
6 张古鹏, 陈向东, 杜华东. 中国区域创新质量不平等研究[J]. 科学学研究, 2011, 29(11): 1709-1719.
7 宋河发, 穆荣平, 陈芳, 等. 基于中国发明专利数据的专利质量测度研究.[J]. 科研管理, 2014, 35 (11): 68-76.
8 杨思思, 戴磊, 郝屹. 专利经济价值度通用评估方法研究[J]. 情报学报, 2018, 37(1): 52-60.
9 李瑞茜, 陈向东. 基于专利共类的关键技术识别及技术发展模式研究[J]. 情报学报, 2018, 37(5): 495-502.
10 郑贵忠, 刘金兰. 基于生存分析的专利有效模型研究[J]. 科学学研究, 2010, 28(11): 1677-1682.
11 乔永忠. 专利维持时间影响因素研究[J]. 科研管理, 2011, 32(7): 143-149.
12 肖冰. 基于法定保护期的专利维持时间影响因素研究[J]. 科学学研究, 2017, 35(11): 1652-1658.
13 刘佩佩, 袁红梅. 专利权无效宣告结果的影响因素探讨——基于药物专利属性的实证研究[J]. 情报学报, 2017, 36(4): 392-400.
14 李华杰, 史丹, 马丽梅. 基于大数据方法的经济研究: 前沿进展与研究综述[J]. 经济学家, 2018(6): 96-104.
15 国家知识产权局.《2016专利统计年报》[R]. 2016.
16 SquicciariniM, DernisH, CriscuoloC. Measuring patent quality[R]. OECD, 2013.
17 BoeingP, MuellerE. Measuring patent quality in cross-country comparison[J]. Economics Letters, 2016, 149: 145-147.
18 LernerJ. The importance of patent scope: An empirical analysis[J]. The RAND Journal of Economics, 1994, 25(2): 319-333.
19 郑素丽, 宋明顺. 专利质量由何决定?——基于文献综述的整合性框架[J]. 科学学研究, 2012, 30(9): 1316-1323.
20 HarhoffD, NarinF, SchererF M, et al. Citation frequency and the value of patented inventions[J]. Review of Economics and statistics, 1999, 81(3): 511-515.
21 NarinF, HamiltonK S, OlivastroD. The increasing linkage between US technology and public science[J]. Research Policy, 1997, 26(3): 317-330.
22 CassimanB, VeugelersR, ZunigaP. In search of performance effects of (in) direct industry science links[J]. Industrial and Corporate Change, 2008, 17(4): 611-646.
23 HarhoffD, SchererF M, K. CitationsVopel, sizefamily, opposition and the value of patent rights[J]. Research Policy, 2003, 32(8): 1343-1363.
24 Van ZeebroeckN. The puzzle of patent value indicators[J]. Economics of Innovation and New Technology, 2011, 20(1): 33-62.
25 HastieT, TibshiraniR, FriedmanJ. Unsupervised learning[M]// The elements of statistical learning. New York: Springer, 2009.
26 MullainathanS, SpiessJ. Machine learning: an applied econometric approach[J]. Journal of Economic Perspectives, 2017, 31(2): 87-106.
27 WooldridgeJ M. Introductory econometrics: A modern approach[M]. Beijing: Tsinghua University Press, 2014. |
|
|
|
