Please wait a minute...
Data Analysis and Knowledge Discovery  2023, Vol. 7 Issue (2): 119-128    DOI: 10.11925/infotech.2096-3467.2022.0330
Current Issue | Archive | Adv Search |
Early Identification of Star Inventor Types in the Perspective of Innovation Duality
Liu Xiang(),Liu Xiang,Yu Bowen
School of Information Management, Central China Normal University, Wuhan 430079, China
Download: PDF (1018 KB)   HTML ( 16
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] Identifying the star inventors by the number of patents and patent citations has obvious time lag effects. Therefore, this paper constructs a graph convolutional neural network to find the emerging star inventors effectively. [Methods] This paper defines four types of star inventors: “composite”, “consolidation”, “breakthrough” and “development” which can also be grouped as “continuity innovation” and “breakthrough innovation”. Then, we constructed a model based on graph convolutional neural network combining patent titles and the cooperation relationship to find star inventors. [Results] We examined our model with patent data in the field of molecular biology and microbiology. The overall accuracy of this model in identifying the innovation types of star inventors reached 79.4%, which was about 15% higher than the method using word vectors. [Limitations] The proposed model could not identify “breakthrough star inventors” effectively. [Conclusions] Our new model could reduce the time-lag effect of the existing methods and identify the innovation type of star inventors earlier.

Key wordsStar Inventors      Duality of Innovation      Early Recognition      Breakthrough Innovation      Continuous Innovation      Relations of Cooperation     
Received: 11 April 2022      Published: 28 March 2023
ZTFLH:  G305 TP183  
Fund:National Natural Science Foundation of China(71673106)
Corresponding Authors: Liu Xiang,ORCID:0000-0003-4315-2699,E-mail: xiangliu@mail.ccnu.edu.cn。   

Cite this article:

Liu Xiang, Liu Xiang, Yu Bowen. Early Identification of Star Inventor Types in the Perspective of Innovation Duality. Data Analysis and Knowledge Discovery, 2023, 7(2): 119-128.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2022.0330     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2023/V7/I2/119

Four Types of Innovation by Star Inventors
Models for Early Identification of Star Inventor Types of Innovation
序号 名词 动词 其他
主题词 频次 主题词 频次 主题词 频次
1 method 25 436 produce 5 066 with 3 331
2 cell 8 135 encode 2 749 or 2 580
3 acid 7 081 prepare 2 696 recombinant 1 708
4 protein 5 770 detect 2 456 specific 1 646
5 process 5 327 identify 2 072 basic 1 280
6 nucleic 4 453 determine 2 000 associated 904
7 gene 4 113 contain 1 549 related 839
8 composition 3 877 bind 1 465 non 781
9 production 3 672 modify 1 150 isolated 705
10 detection 3 629 enhance 645 which 572
Examples of Star Inventors’ Features
The Distribution of Continuous Innovation Value and Breakthrough Innovation Value of Star Inventors
序号 发明人 method methods acid process nucleic ……
1 Kenneth W. Kinzler 1 1 1 1 1 ……
2 Bert Vogelstein 1 1 1 0 1 ……
3 Xu Hong 1 1 1 0 1 ……
4 Li Xiaodong 1 1 1 0 1 ……
5 Robert Dicosimo 0 0 1 1 0 ……
Example of Feature Matrix Construction for Star Inventors
序号 Inventor C D Label
1 Kenneth W. Kinzler 0.015 458 0.066 849 D3
2 Bert Vogelstein 0.019 288 0.069 034 D3
3 Xu Hong 0.078 413 0.008 913 D2
4 Li Xiaodong 0.094 061 0.003 644 D2
5 Robert Dicosimo 0.044 878 0.042 104 D2
Example of Star Inventor Innovation Types Tag Annotation
The Influence of the Number of Feature Words on the Recognition Result
Early Identification Model Parameter Tuning Experimental of Star Inventor Innovation Types
预测模型 A c c/% D1(复合型) D2(巩固型) D3(突破型) D4(发展型)
P/% R/% F 1/% P/% R/% F 1/% P/% R/% F 1/% P/% R/% F 1/%
未嵌入合作关系 64.1 65.8 71.4 68.5 66.7 18.2 28.6 44.4 33.3 38.1 66.7 88.3 73.7
词向量+合作关系 79.4 85.3 82.9 84.1 80.0 72.7 76.2 62.5 41.7 50.0 75.0 88.2 81.1
Results of Early Identification Studies on Innovation Types of Star Inventors
[1] 李思宏, 罗瑾琏, 田瑞雪. 科技人才评价与选拔体系构建思路[J]. 科技进步与对策, 2009, 26(14):148-150.
[1] (Li Sihong, Luo Jinlian, Tian Ruixue. The Thought of the Construction of the Evaluation and Selection of Science and Technology Talents[J]. Science & Technology Progress and Policy, 2009, 26(14):148-150.)
[2] 杨璐瑶, 张向前. 我国“十三五”适应创新驱动的科技人才发展机制的制度分析[J]. 科技管理研究, 2016, 36(7):60-65.
[2] (Yang Luyao, Zhang Xiangqian. The Institutional Analysis of 13th Five Year Plan Adapting to the Innovation-driven Technology Professionals Development Mechanism[J]. Science and Technology Management Research, 2016, 36(7):60-65.)
[3] Zucker L G, Darby M R, Armstrong J S. Commercializing Knowledge: University Science, Knowledge Capture, and Firm Performance in Biotechnology[J]. Management Science, 2002, 48(1): 138-153.
doi: 10.1287/mnsc.48.1.138.14274
[4] Coff R W, Kryscynski D. Drilling for Micro-Foundations of Human Capital-based Competitive Advantages[J]. Journal of Management, 2011, 37(5): 1429-1443.
doi: 10.1177/0149206310397772
[5] Narin F, Breitzman A. Inventive Productivity[J]. Research Policy, 1995, 24(4): 507-519.
doi: 10.1016/S0048-7333(94)00780-2
[6] Liu K. Human Capital, Social Collaboration, and Patent Renewal within U.S. Pharmaceutical Firms[J]. Journal of Management, 2014, 40(2): 616-636.
doi: 10.1177/0149206313511117
[7] Ernst H, Leptien C, Vitt J. Inventors are Not Alike: The Distribution of Patenting Output Among Industrial R&D Personnel[J]. IEEE Transactions on Engineering Management, 2000, 47(2): 184-199.
doi: 10.1109/17.846786
[8] Moretti E, Wilson D J. The Effect of State Taxes on the Geographical Location of Top Earners: Evidence from Star Scientists[J]. The American Economic Review, 2017, 107(7): 1858-1903.
doi: 10.1257/aer.20150508
[9] Zacchia P. Benefiting Colleagues but not the City: Localized Effects from the Relocation of Superstar Inventors[J]. Research Policy, 2018, 47(5): 992-1005.
doi: 10.1016/j.respol.2018.03.004
[10] Hohberger J. Does It Pay to Stand on the Shoulders of Giants? An Analysis of the Inventions of Star Inventors in the Biotechnology Sector[J]. Research Policy, 2016, 45(3): 682-698.
doi: 10.1016/j.respol.2015.12.003
[11] Schiffauerova A, Beaudry C. Star Scientists and Their Positions in the Canadian Biotechnology Network[J]. Economics of Innovation and New Technology, 2011, 20(4): 343-366.
doi: 10.1080/10438591003696886
[12] Subramanian A M, Lim K, Soh P H. When Birds of a Feather don’t Flock Together: Different Scientists and the Roles They Play in Biotech R&D Alliances[J]. Research Policy, 2013, 42(3): 595-612.
doi: 10.1016/j.respol.2012.12.002
[13] 贾军, 魏洁云. 新兴产业核心技术早期识别方法与应用研究[J]. 科学学研究, 2018, 36(7):1206-1214.
[13] (Jia Jun, Wei Jieyun. Study on the Method and Application of Early Identification of Core Technology in Emerging Industry[J]. Studies in Science of Science, 2018, 36(7):1206-1214.)
[14] 肖悦珺, 李红莲, 张乐, 等. 特征融合的中文专利文本分类方法研究[J]. 数据分析与知识发现, 2022, 6(4): 49-59.
[14] (Xiao Yuejun, Li Honglian, Zhang Le, et al. Classifying Chinese Patent Texts with Feature Fusion[J]. Data Analysis and Knowledge Discovery, 2022, 6(4): 49-59.)
[15] 贾杉杉, 刘畅, 孙连英, 等. 基于多特征多分类器集成的专利自动分类研究[J]. 数据分析与知识发现, 2017, 1(8):76-84.
[15] (Jia Shanshan, Liu Chang, Sun Lianying, et al. Patent Classification Based on Multi-feature and Multi-classifier Integration[J]. Data Analysis and Knowledge Discovery, 2017, 1(8):76-84.)
[16] Wu L F, Wang D S, Evans J A. Large Teams Develop and Small Teams Disrupt Science and Technology[J]. Nature, 2019, 566(7744): 378-382.
doi: 10.1038/s41586-019-0941-9
[17] 杨雪梅, 王雪, 杜建, 等. 基于论文摘要和引文文本语料的突破性研究特征词识别[J]. 图书情报工作, 2020, 64(11):125-132.
doi: 10.13266/j.issn.0252-3116.2020.11.014
[17] (Yang Xuemei, Wang Xue, Du Jian, et al. Identifying Feature Words Based on Abstracts and Citation Text Corpus of Breakthrough Research[J]. Library and Information Service, 2020, 64(11):125-132.)
doi: 10.13266/j.issn.0252-3116.2020.11.014
[18] 李钰曼, 陈志泊, 许福. 基于KACC模型的文本分类研究[J]. 数据分析与知识发现, 2019, 3(10):89-97.
[18] (Li Yuman, Chen Zhibo, Xu Fu. Classifying Texts with KACC Model[J]. Data Analysis and Knowledge Discovery, 2019, 3(10):89-97.)
[19] 周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6):1229-1251.
[19] (Zhou Feiyan, Jin Linpeng, Dong Jun. Review of Convolutional Neural Network[J]. Chinese Journal of Computers, 2017, 40(6):1229-1251.)
[20] 徐冰冰, 岑科廷, 黄俊杰, 等. 图卷积神经网络综述[J]. 计算机学报, 2020, 43(5):755-780.
[20] (Xu Bingbing, Cen Keting, Huang Junjie, et al. A Survey on Graph Convolutional Neural Network[J]. Chinese Journal of Computers, 2020, 43(5):755-780.)
[21] 雷兵, 刘小, 钟镇. 基于题录信息的领域学术文献细粒度分类方法研究[J]. 图书情报工作, 2021, 65(14):128-137.
doi: 10.13266/j.issn.0252-3116.2021.14.015
[21] (Lei Bing, Liu Xiao, Zhong Zhen. Research on Fine-Grain Classification Method of Academic Literature Based on Bibliographies[J]. Library and Information Service, 2021, 65(14):128-137.)
doi: 10.13266/j.issn.0252-3116.2021.14.015
[22] Kipf T N, Welling M.Semi-supervised Classification with Graph Vonvolutional Networks[OL]. arXiv Preprint, arXiv:1609.02907.
[23] 杨光泽, 欧阳勇, 孙思思, 等. 基于图卷积网络嵌入社交关系的毕业去向预测[J]. 计算机应用研究, 2021, 38(11):3322-3326,3365.
[23] (Yang Guangze, Ouyang Yong, Sun Sisi, et al. Prediction of Graduation Destination Based on Graph Convolutional Network Embedded Social Relations[J]. Application Research of Computers, 2021, 38(11):3322-3326,3365.)
[24] Singh J, Fleming L. Lone Inventors as Sources of Breakthroughs: Myth or Reality?[J]. Management Science, 2010, 56(1): 41-56.
doi: 10.1287/mnsc.1090.1072
[25] 李海林, 徐建宾, 林春培, 等. 合作网络结构特征对创新绩效影响研究[J]. 科学学研究, 2020, 38(8):1498-1508.
[25] (Li Hailin, Xu Jianbin, Lin Chunpei, et al. Structural Features of Cooperative Network Impact on Innovation Performance[J]. Studies in Science of Science, 2020, 38(8):1498-1508.)
[26] 曾德明, 张志东, 赵胜超. 科学合作网络、伙伴动态性与企业创新绩效[J]. 科学学研究, 2022, 40(5):906-914.
[26] (Zeng Deming, Zhang Zhidong, Zhao Shengchao. Scientific Cooperation Network, Partnership Dynamics and Innovation Performance[J]. Studies in Science of Science, 2022, 40(5):906-914.)
[27] 关鹏, 王曰芬, 傅柱, 等. 基于专利合作网络的研发团队识别及创新产出影响研究[J]. 数据分析与知识发现, 2022, 6(5): 99-111.
[27] (Guan Peng, Wang Yuefen, Fu Zhu, et al. Identifying R&D Teams and Innovations with Patent Collaboration Networks[J]. Data Analysis and Knowledge Discovery, 2022, 6(5): 99-111.)
[28] Lavie D, Kang J, Rosenkopf L. Balance Within and Across Domains: The Performance Implications of Exploration and Exploitation in Alliances[J]. Organization Science, 2011, 22(6): 1517-1538.
doi: 10.1287/orsc.1100.0596
[29] Funk R J, Owen-Smith J. A Dynamic Network Measure of Technological Change[J]. Management Science, 2017, 63(3): 791-817.
doi: 10.1287/mnsc.2015.2366
[30] Chen J, Shao D, Fan S. Destabilization and Consolidation: Conceptualizing, Measuring, and Validating the Dual Characteristics of Technology[J]. Research Policy, 2021, 50(1). https://doi.org/10.1016/j.respol.2020.104115.
[31] 宁亚辉, 樊兴华, 吴渝. 基于领域词语本体的短文本分类[J]. 计算机科学, 2009, 36(3):142-145.
[31] (Ning Yahui, Fan Xinghua, Wu Yu. Short Text Classification Based on Domain Word Ontology[J]. Computer Science, 2009, 36(3):142-145.)
[32] 闵超, 步一, 孙建军. 基于专利大数据的中国国际专利技术流动分析[J]. 图书与情报, 2017(5):33-39.
[32] (Min Chao, Bu Yi, Sun Jianjun. Analysis on Technology Mobility of International Patents from China Based on Patent Big Data[J]. Library and Information, 2017(5):33-39.)
[1] Han Fang, Zhang Shengtai, Feng Lingzi, Yuan Junpeng. Identifying Breakthrough Patent Topics by Measuring Technological Convergence——Case Study of Solar PV Domain[J]. 数据分析与知识发现, 2021, 5(12): 137-147.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn