[Objective] This paper proposes a new method for evaluating and classifying patent values. [Methods] With the help of value indicators, we designed a patent value analysis and classification system based on self-organizing maps (SOM) and support vector machine (SVM) techniques. We used the SOM to determine value categories, and then applied the random forest (RF) algorithm to rank value indictors based on their significance. Finally, we improved classification performance with the wrapped feature reduction method. [Results] The value tags determined by SOM effectively represented the patent values. Meanwhile, the value indictors were reduced from 14 to 10, and the classification accuracy was increased from 76.28% to 86.89%. [Limitations] Further refinement of patent values in each category is needed, which might reduce the patent value indicators. [Conclusions] The proposed SOM-RF-SVM method could support research and development activities as well as reduce the dependence on human factors.
周成,魏红芹. 专利价值评估与分类研究*——基于自组织映射支持向量机[J]. 数据分析与知识发现, 2019, 3(5): 117-124.
Cheng Zhou,Hongqin Wei. Evaluating and Classifying Patent Values Based on Self-Organizing Maps and Support Vector Machine. Data Analysis and Knowledge Discovery, DOI：10.11925/infotech.2096-3467.2018.0674.
(Zhang Yaotian, Du Weichun, Jia Mingshun, et al.Research on the Evaluation of Enterprise Patents Quality Based on the Adaptive Analytic Hierarchy Process[J]. Library and Information Service, 2016, 60(7): 110-115.)
[3]
Dereli T, Durmu?o?lu A.Classifying Technology Patents to Identify Trends: Applying a Fuzzy-Based Clustering Approach in the Turkish Textile Industry[J]. Technology in Society, 2009, 31(3): 263-272.
(Qiu Yihui, Zhang Chiyu, Chen Shuixuan.Research of Patent-Value Assessment Indictor System Based on Classification and Regression Tree Algorithm[J]. Journal of Xiamen University: Natural Science, 2017, 56(2): 244-251.)
[7]
Archontopoulos E.Prior Art Search Tools on the Internet and Legal Status of the Results: A European Patent Office Perspective[J]. World Patent Information, 2004, 26(2): 113-121.
[8]
Dang J, Motohashi K.Patent Statistics: A Good Indicator for Innovation in China? Patent Subsidy Program Impacts on Patent Quality[J]. China Economic Review, 2015, 35: 137-155.
[9]
Chen Y S, Chang K C.The Relationship Between a Firm’s Patent Quality and Its Market Value—The Case of US Pharmaceutical Industry[J]. Technological Forecasting & Social Change, 2010, 77(1): 20-33.
[10]
Frietsch R, Neuh?usler P, Jung T, et al.Patent Indicators for Macroeconomic Growth—The Value of Patents Estimated by Export Volume[J]. Technovation, 2014, 34(9): 546-558.
[11]
Harhoff D, Scherer F M, Vopel K. Citations, Family Size, Opposition and the Value of Patent Rights[J]. Research Policy, 2003, 32(8): 1343-1363.
(Zheng Suli, Song Mingshun.Review on the Determinants of Patent Value: An Integrate Framework[J]. Studies in Science of Science, 2012, 30(9): 1316-1323.)
[13]
Marco A C.The Dynamics of Patent Citations[J]. Economics Letters, 2006, 94(2): 290-296.
[14]
苏健美. 基于收益法的专利权价值评估研究[D]. 昆明:云南大学, 2014.
[14]
(Su Jianmei.Research on Patent Value Evaluation Based on Income Law[D]. Kunming: Yunnan University, 2014.)
(Yang Guancan, Liu Tong, Li Gang, et al.Research on Patent Value Evaluation Based on Comprehensive Citation Network[J]. Journal of the China Society for Scientific and Technical Information, 2013, 32(12): 1265-1277.)
(Lv Lucheng, Liu Ya, Yang Guancan.Research on the Influencing Factors of Patent Citation Based on Decision Tree Method[J]. Information Studies: Theory & Application, 2015, 38(2): 28-32.)
[18]
Chiu C Y, Huang P T.Application of the Honeybee Mating Optimization Algorithm to Patent Document Classification in Combination with the Support Vector Machine[J]. International Journal of Automation and Smart Technology, 2013, 3(3): 179-191.
[19]
Wu C H, Ken Y, Huang T.Patent Classification System Using a New Hybrid Genetic Algorithm Support Vector Machine[J]. Applied Soft Computing, 2010, 10(4): 1164-1177.
(Yao Dengju, Yang Jing, Zhan Xiaojuan.Feature Selection Algorithm Based on Random Forest[J]. Journal of Jilin University: Engineering and Technology Edition, 2014, 44(1): 137-141.)
[22]
Strobl C, Boulesteix A L, Kneib T, et al.Conditional Variable Importance for Random Forests[J]. BMC Bioinformatics, 2008, 9: 307.
(Pei Yunlong, Cai Hong, Wang Xiaonan.How Does Domestic and Foreign Scientific Literature Affect Technology Innovation Quality of High-tech Industries in China: An Analysis Based on Patent Citations Scientific Publications[J]. Journalof the China Society for Scientific and Technical Information, 2013, 32(12): 1333-1344.)
(Zhou Cheng, Wei Hongqin.Identifying Crowd Participants with Modified Random Forests Algorithm[J]. Data Analysis and Knowledge Discovery, 2018, 2(7): 46-54)
(Xu Qingfu, Kang Xudong, Yang Zhongkai, et al.Research on the Characteristics of Inter-Provincial Technology Transfer in China Based on Patent Right Transfer[J]. Journal of Intelligence, 2017, 36(7): 66-72.)
[27]
Wu J L, Chang P C, Tsao C C, et al.A Patent Quality Analysis and Classification System Using Self-Organizing Maps with Support Vector Machine[J]. Applied Soft Computing, 2016, 41: 305-316.
(Sun Yutao, Luan Qian.A ‘Three Stages-Two Dimensions’ Model of Patent Quality Measuring and Its Empirical Study: A Case Study of C9 League[J]. Science of Science and Management of S.& T., 2016, 37(6): 23-32.)
(Qiao Yongzhong, Tan Wanlin.Empirical Studies of the Relationship of the Claims Number and the Maintenance Time of Patents: Based on the Data of Patents Granted by China and Japan[J]. Science of Science and Management of S.& T., 2017, 38(2): 77-86.)
