|
|
|
| Potential High-Value Patent Identify Based on a Time-Series Graph Neural Network |
| Zhou Xiao, Wang Bo, Hu Yulin, Wei Chuchu |
| School of Economics and Management, Xidian University, Xi’an 710126 |
|
|
|
|
Abstract High-value patents are primary resources in constructing the current “dual circulation” development pattern at both domestic and international levels. They also play a pivotal role in positioning China at a strategic high ground in the new international economic order and comprehensively advancing technological self-reliance and self-strengthening. Precisely identifying potential high-value patents is a crucial step for nurturing their value and promoting technological transfer. Based on an in-depth analysis of the characteristics of patents that have won the China Patent Award, this study combines the use of Patent-BERT (bidirectional encoder representations from transformers for patent) and graph deep learning algorithms. By integrating patent evaluation indicators and textual features, we propose a potential high-value patent identification model based on graph convolutional networks (GCNs) and long short-term memory (LSTM) networks. The two main innovative aspects of this research are as follows: (1) Addressing the shortcomings of previous studies that only focused on “quantitative” features such as patent growth rate and collaboration potential and lacked deep semantic understanding of the text. We build a patent value representation model from both textual semantics and patent metrics dimensions. (2) Considering the temporal variability of patent value, we explore the evolutionary rules of patent value from a dynamic perspective, providing a new research approach for patent value mining and assessment. Finally, we compare the performance of various models, including node2vec, doc2vec, GCN, and multilayer perceptron (MLP). The results indicate that our model outperforms the control models across multiple indicators, thereby effectively validating the efficiency and robustness of our research approach.
|
|
Received: 14 August 2023
|
|
|
|
1 陈劲, 阳镇, 朱子钦. “十四五”时期“卡脖子”技术的破解: 识别框架、战略转向与突破路径[J]. 改革, 2020(12): 5-15.
2 国家知识产权局. 国家知识产权局2022年度报告[R/OL]. (2023-06-05). https://www.cnipa.gov.cn/module/download/down.jsp?i_ID=185538&colID=3249.
3 Shane S. Technological opportunities and new firm creation[J]. Management Science, 2001, 47(2): 205-220.
4 侯剑华, 郑碧丽, 张洋. 科学知识扩散研究: 概念界定、理论基础与体系重构[J]. 现代情报, 2020, 40(9): 117-126.
5 韩啸. 大国竞争下美国国防部推动新技术转化的价值链分析[J]. 情报杂志, 2021, 40(6): 17-25.
6 Song H Y, Hou J H, Zhang Y. The measurements and determinants of patent technological value: lifetime, strength, breadth, and dispersion from the technology diffusion perspective[J]. Journal of Informetrics, 2023, 17(1): 101370.
7 Albert M B, Avery D, Narin F, et al. Direct validation of citation counts as indicators of industrially important patents[J]. Research Policy, 1991, 20(3): 251-259.
8 Grimaldi M, Cricelli L, Di Giovanni M, et al. The patent portfolio value analysis: a new framework to leverage patent information for strategic technology planning[J]. Technological Forecasting and Social Change, 2015, 94: 286-302.
9 Martínez C. Patent families: when do different definitions really matter?[J]. Scientometrics, 2011, 86(1): 39-63.
10 魏明珠, 郑荣, 高志豪, 等. 融合知识图谱和深度神经网络的产业新兴技术预测模型研究[J]. 情报学报, 2022, 41(11): 1134-1148.
11 任培民, 赵树然, 姜文远. 基于结构方程-组套索的复杂专利组合测度研究[J]. 科研管理, 2022, 43(9): 159-168.
12 宋艳, 常菊, 陈琳. 专利质量对企业绩效的影响研究——技术创新类型的调节作用[J]. 科学学研究, 2021, 39(8): 1459-1466.
13 Verhoeven D, Bakker J, Veugelers R. Measuring technological novelty with patent-based indicators[J]. Research Policy, 2016, 45(3): 707-723.
14 Huang L, Liu F Y, Zhang Y. Overlapping community discovery for identifying key research themes[J]. IEEE Transactions on Engineering Management, 2021, 68(5): 1321-1333.
15 王萧萧, 朱桂龙. 产学合作提升专利质量了吗?[J]. 科学学研究, 2019, 37(8): 1461-1470, 1516.
16 严晓宁, 孙沛霖, 林光彬. 市场法在知识产权评估中的运用挑战与设想[J]. 中国资产评估, 2021(5): 4-7, 28.
17 Bakker J, Verhoeven D, Zhang L, et al. Patent citation indicators: one size fits all?[J]. Scientometrics, 2016, 106(1): 187-211.
18 苗红, 张惠钊, 林昭颍, 等. 基于专利文本语义距离的跨领域关键共性技术识别方法研究[J]. 情报杂志, 2023, 42(8): 90-95.
19 冯立杰, 周炜, 王金凤, 等. 基于SAO语义分析的多维技术演化路径与技术创新机会识别研究[J]. 情报学报, 2022, 41(11): 1149-1160.
20 孔德婧, 董放, 陈子婧, 等. 离群专利视角下的新兴技术预测——基于BERT模型和深度神经网络[J]. 图书情报工作, 2021, 65(17): 131-141.
21 张金柱, 韩永亮. 基于多特征的技术融合关系预测及其价值评估[J]. 数据分析与知识发现, 2022, 6(2/3): 33-44.
22 Liu W D, Qiao W B, Wang Y, et al. Patent transformation opportunity to realize patent value: discussion about the conditions to be used or exchanged[J]. Information Processing & Management, 2021, 58(4): 102582.
23 岳丽欣, 刘自强, 刘春江, 等. 融合引用和文本特征的技术创新路径识别研究[J]. 图书情报工作, 2023, 67(3): 49-60.
24 Qi J J, Lei L, Zheng K, et al. Patent analytic citation-based VSM: challenges and applications[J]. IEEE Access, 2020, 8: 17464-17476.
25 Lanjouw J O. Patent protection in the shadow of infringement: simulation estimations of patent value[J]. The Review of Economic Studies, 1998, 65(4): 671-710.
26 晁蓉, 龙敏, 黄筱玲. 发明专利特征与专利价值——基于中国专利金奖的经验分析[J]. 中南财经政法大学学报, 2020(5): 73-81.
27 刘洋. 高价值专利指标探讨——基于中国金奖专利的实证分析[J]. 中国高校科技, 2021(8): 80-84.
28 Grimaldi M, Cricelli L. Indexes of patent value: a systematic literature review and classification[J]. Knowledge Management Research & Practice, 2020, 18(2): 214-233.
29 Lee N. Exclusion and coordination in collaborative innovation and patent law[J]. International Journal of Intellectual Property Management, 2009, 3(1): 79-93.
30 Suzuki J. Structural modeling of the value of patent[J]. Research Policy, 2011, 40(7): 986-1000.
31 郭状, 余翔. 基于我国人工智能专利数据的专利价值影响因素分析[J]. 情报杂志, 2020, 39(9): 88-94.
32 Lanjouw J O, Schankerman M. Patent quality and research productivity: measuring innovation with multiple indicators[J]. The Economic Journal, 2004, 114(495): 441-465.
33 Fischer T, Leidinger J. Testing patent value indicators on directly observed patent value—an empirical analysis of Ocean Tomo patent auctions[J]. Research Policy, 2014, 43(3): 519-529.
34 Pakes A. Patents as options: some estimates of the value of holding European patent stocks[J]. Econometrica, 1986, 54(4): 755-784.
35 Marco A C, Sarnoff J D, deGrazia C A W. Patent claims and patent scope[J]. Research Policy, 2019, 48(9): 103790.
36 Park Y, Park G. A new method for technology valuation in monetary value: procedure and application[J]. Technovation, 2004, 24(5): 387-394.
37 国家知识产权局专利管理司, 中国技术交易所. 专利价值分析指标体系操作手册[M]. 北京: 知识产权出版社, 2012.
38 Capponi G, Martinelli A, Nuvolari A. Breakthrough innovations and where to find them[J]. Research Policy, 2022, 51(1): 104376.
39 李睿, 王双玲, 康心寓. 优质专利识别目标下的无效宣告胜出专利特征研究[J]. 图书情报工作, 2022, 66(23): 72-81.
40 Trappey A J C, Trappey C V, Govindarajan U H, et al. Patent value analysis using deep learning models—the case of IoT technology mining for the manufacturing industry[J]. IEEE Transactions on Engineering Management, 2021, 68(5): 1334-1346.
41 Iazzolino G, Migliano G. The valuation of a patent through the real options approach: a tutorial[J]. Journal of Business Valuation and Economic Loss Analysis, 2015, 10(1): 99-116.
42 Devlin J, Chang M W, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference on the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2019: 4171-4186.
43 赵雪峰, 胡瑾瑾, 吴德林, 等. 一种基于特征拼接、标签迁移及深度学习组合的专利价值评估方法[J]. 情报学报, 2023, 42(6): 663-680.
44 Park H, Noh J, Ham B. Learning memory-guided normality for anomaly detection[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 14360-14369.
45 Zhang Q J, Jin D H, Wang Y W, et al. Semantic clone detection based on code feature fusion learning[J]. International Journal of Software Engineering and Knowledge Engineering, 2023, 33(7): 1039-1062.
46 何琦, 艾蔚, 潘宁利. 数字转型背景下的创新扩散: 理论演化、研究热点、创新方法研究——基于知识图谱视角[J]. 科学学与科学技术管理, 2022, 43(6): 17-50.
47 Czarnitzki D, Toole A A. Patent protection, market uncertainty, and R&D investment[J]. The Review of Economics and Statistics, 2011, 93(1): 147-159.
48 Kurosawa T, Takama Y. Predicting researchers’ future activities using visualization system for co-authorship networks[C]// Proceedings of the 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology. Piscataway: IEEE, 2011: 332-339.
49 Zhu Y J, Quan L H, Chen P Y, et al. Predicting coauthorship using bibliographic network embedding[J]. Journal of the Association for Information Science and Technology, 2023, 74(4): 388-401.
50 周莉, 刘苗, 周蕊格, 等. 基于专利文本挖掘的科技文化产业技术发展趋势研究[J]. 科技进步与对策, 2019, 36(23): 69-75.
51 Kwon S, Liu X Y, Porter A L, et al. Research addressing emerging technological ideas has greater scientific impact[J]. Research Policy, 2019, 48(9): 103834.
52 工业和信息化部关于印发“十四五”信息通信行业发展规划的通知[EB/OL]. (2021-11-01) [2023-06-17]. https://www.gov.cn/zhengce/zhengceku/2021-11/16/content_5651262.htm.
53 战略性新兴产业分类(2018)(国家统计局令第23号)[EB/OL]. (2018-11-26) [2023-06-17]. https://www.gov.cn/zhengce/zhengceku/2018-12/31/content_5433037.htm.
54 中国信息通信研究院. 中国5G发展和经济社会影响白皮书(2022年)[R]. 北京: 中国信息通信研究院, 2023: 12-16.
55 中国信息通信研究院, 中国通信企业协会. 5G消息发展报告(2022年)[R]. 北京: 中国信息通信研究院, 2022: 11-18.
56 中国信息通信研究院. 中国信息消费发展态势报告(2022年)[R]. 北京: 中国信息通信研究院, 2022: 1-11.
57 CSIS. Accelerating 5G in the United States[R]. Washington, DC: Center for Strategic and International Studies, 2021: 19-25.
58 U.S. Congress. Endless Frontier Act[EB/OL]. (2020-05-21) [2023-06-18]. https://www.congress.gov/bill/116th-congress/senate-bill/3832?q=%7B%22search%22%3A%22Endless+Frontier+Act%22%7D&r=25&s=1.
59 张伟伦. “数字中国”顶层规划为产业新浪潮夯基布局[N]. 中国贸易报, 2023-03-07(001). |
|
|
|
