基于技术互补性的“创新-成熟”型技术机会识别研究

doi:10.13998/j.cnki.issn1002-1248.25-0395

摘要/Abstract

摘要：

[目的/意义] 从技术互补性的视角出发，对创新型离群专利和市场成熟型热点专利进行互补研究，发现“创新-成熟”型技术机会，对技术机会识别的研究有重要意义。 [方法/过程] 首先，利用关联规则算法和离群值检测算法对专利分类号进行处理，得到关联性弱、分布边缘化的分类号代表的离群专利以及关联性强、分布中心化的分类号所代表的热点专利。其次，构建时间加权指数和关键词独特性指数来筛选符合双高指数的离群专利作为创新型离群专利；基于专利所处技术生命周期阶段和专利市场价值测度，筛选热点专利作为市场成熟型热点专利。最后，利用两种类型专利的技术关键词构建二维矩阵，通过生成式拓扑映射算法得到技术空白点，将关键词同时来源于两种类型专利的技术空白点作为最终的“创新-成熟”型技术机会。 [结果/结论] 以新能源汽车电池为例进行实证研究，共发现10项技术机会。经与相关政策文件进行内容比对可知，识别结果与该领域的技术现状和发展规划具有较高的一致性，验证了本研究提出的技术机会识别方法的有效性和科学性。

关键词: 技术互补, 关联规则, 离群值检测算法, 文本挖掘, 生成式拓扑映射

Abstract:

[Purpose/Significance] Starting from the perspective of technological complementarity, this paper proposes a new approach for identifying technological opportunities by comprehensively using outlier patents and hot patents. The fusion analysis of innovative outlier patents and market mature hot patents is carried out to identify "innovation maturity" technological opportunities that combine innovation and maturity, which is of great significance for enriching the theory and methods of technological opportunity identification. [Method/Process] First, based on the "association distribution" characteristics of patent classification numbers, a two-stage method was adopted to screen patents. In the first stage, we used the association rule algorithms to find classification numbers with weak and strong associations, and obtained initial outlier patents and initial hotspot patents. In the second stage, outlier detection algorithms were used to obtain the marginalization classification numbers of the two types of patents in the first stage. Patents containing marginalization classification numbers were selected as the final outlier patents, while patents containing such classification numbers were removed as the final hotspot patents. Second, different methods were adopted for patent screening based on the differences in innovation and maturity of patent content. Using structured and unstructured data from patent databases, we constructed time weighted indicators and keyword uniqueness indicators as the screening indicators for innovative outlier patents. We constructed a technology lifecycle stage discrimination function and patent market value measurement indicators as the screening criteria for mature hot patents in the market. The screened patents were classified into technical fields based on the major categories in the International Patent Classification. Finally, we identified technological opportunities based on technological complementarity. By using the generative topology mapping algorithm to obtain a technical blank point map, the top K keywords in each blank point were obtained, and the sources of the keywords were marked to ensure that new technological opportunities have both good innovation capabilities and mature market prospects. In the future, keyword combinations derived from different types of patents were regarded as "innovation mature" technological opportunities. [Results/Conclusions] Taking the field of new energy vehicle batteries as an example, empirical analysis was conducted to obtain a total of 10 technical opportunities in 5 sub technical fields. Through content comparison with relevant policy texts, 7 technical opportunities showed high consistency. It was found that the identification results were highly consistent with the current technological layout and development direction of the field, indicating that this method has good effectiveness and scientificity in technology opportunity identification, and can provide support for technology prediction and innovation decision-making.

Key words: complementary technology, association rules, outlier detection algorithm, text mining, generative topological mapping

中图分类号: G353.1

侯艳辉, 王紫瑄, 王家坤. 基于技术互补性的“创新-成熟”型技术机会识别研究[J/OL]. 农业图书情报学报. https://doi.org/10.13998/j.cnki.issn1002-1248.25-0395.

HOU Yanhui, WANG Zixuan, WANG Jiakun. "Innovation-aturity" Technology Opportunity Identification Based on Technological Complementarity[J/OL]. Journal of library and information science in agriculture. https://doi.org/10.13998/j.cnki.issn1002-1248.25-0395.

图/表 18

表1

图1

图2

表2

图3

表3

图4

图5

图6

图7

图8

表4

表5

表6

表7

表8

表9

表10

参考文献 44

[1]	陈亮, 陈利利, 许海云, 等. 国内外专利挖掘研究进展与前瞻[J]. 图书情报工作, 2024, 68(2): 110-133.
	CHEN L, CHEN L L, XU H Y, et al. A global literature review in recent advancement of patent mining[J]. Library and information service, 2024, 68(2): 110-133.
[2]	祝娜, 尹俊华, 翟羽佳. 一种专利共类与深度学习模型结合的技术融合预测方法研究[J]. 情报理论与实践, 2024, 47(1): 145-153.
	ZHU N, YIN J H, ZHAI Y J. Research on a technology fusion prediction method combining patent commonality with deep learning model[J]. Information studies: Theory & application, 2024, 47(1): 145-153.
[3]	黄鲁成, 李晓宇, 李晋. 基于专利的ABOD-RFM技术机会识别方法研究[J]. 情报理论与实践, 2020, 43(9): 144-149.
	HUANG L C, LI X Y, LI J. Research on technology opportunity identification method of ABOD-RFM based on patent[J]. Information studies: Theory & application, 2020, 43(9): 144-149.
[4]	JEON D, AHN J M, KIM J, et al. A doc2vec and local outlier factor approach to measuring the novelty of patents[J]. Technological forecasting and social change, 2022, 174: 121294.
[5]	康宇航. 基于“耦合-共引”混合网络的技术机会分析[J]. 情报学报, 2017, 36(2): 170-179.
	KANG Y H. Analysis of technology opportunity based on "coupling and co-citation" hybrid network[J]. Journal of the China society for scientific and technical information, 2017, 36(2): 170-179.
[6]	SONG K, KIM K, LEE S. Identifying promising technologies using patents: A retrospective feature analysis and a prospective needs analysis on outlier patents[J]. Technological forecasting and social change, 2018, 128: 118-132.
[7]	李慧, 孟玮. 专利视角下的美国空军核心技术演化分析[J]. 情报理论与实践, 2021, 44(2): 41-49.
	LI H, MENG W. An analysis of the evolution of core technologies in the U.S.Air force from a patent perspective[J]. Information studies: Theory & application, 2021, 44(2): 41-49.
[8]	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.
	KONG D J, DONG F, CHEN Z J, et al. Prediction of emerging technologies from the perspective of outlier patents: Based on bert model and deep neural networks[J]. Library and information service, 2021, 65(17): 131-141.
[9]	ZHU C, MOTOHASHI K. Identifying the technology convergence using patent text information: A graph convolutional networks (GCN)-based approach[J]. Technological forecasting and social change, 2022, 176: 121477.
[10]	李宜展,孔晔晗,李泽霞.可拓理论在技术演化与预测中的应用潜力[J].现代情报,2024,44(10):86-102.
	LI Y Z, KONG Y H, LI Z X. Potential application of extenics in technology evolution and forecasting[J]. Journal of modern information, 2024,44(10):86-102.
[11]	张硕, 李荣荣, 乔亚丽. 技术组合进化视角下的产品创新机会识别研究[J]. 情报理论与实践, 2024, 47(12): 133-142.
	ZHANG S, LI R R, QIAO Y L. Research on identifying product innovation opportunities from the perspective of technology portfolio evolution[J]. Information studies: Theory & application, 2024, 47(12): 133-142.
[12]	郭俊芳, 汪雪锋, 李乾瑞, 等. 一种新型的技术形态识别方法: 基于SAO语义挖掘方法[J]. 科学学研究, 2016, 34(1): 13-21.
	GUO J F, WANG X F, LI Q R, et al. A new method to identify technology morphology: SAO-based semantic analysis approach[J]. Studies in science of science, 2016, 34(1): 13-21.
[13]	张振刚, 罗泰晔. 基于知识组合理论的技术机会发现[J]. 科研管理, 2020, 41(8): 220-228.
	ZHANG Z G, LUO T Y. Technology opportunity discovery based on knowledge combination theory[J]. Science research management, 2020, 41(8): 220-228.
[14]	桂美增, 许学国. 基于深度学习的技术机会预测研究: 以新能源汽车为例[J]. 图书情报工作, 2021, 65(19): 130-141.
	GUI M Z, XU X G. Approach to technology opportunity prediction based on deep learning: Taking the case of new energy vehicles[J]. Library and information service, 2021, 65(19): 130-141.
[15]	SON C, SUH Y, JEON J, et al. Development of a GTM-based patent map for identifying patent vacuums[J]. Expert systems with applications, 2012, 39(3): 2489-2500.
[16]	吴菲菲, 米兰, 黄鲁成. 以技术标准为导向的企业研发方向识别与评估[J]. 科学学研究, 2018, 36(10): 1837-1847.
	WU F F, MI L, HUANG L C. Identification and evaluation of R & D direction oriented by technical standards[J]. Studies in science of science, 2018, 36(10): 1837-1847.
[17]	YOON B, PARK I, YUN D, et al. Exploring promising vacant technology areas in a technology-oriented company based on bibliometric analysis and visualisation[J]. Technology analysis & strategic management, 2019, 31(4): 388-405.
[18]	YU J, HWANG J G, HWANG J, et al. Identification of vacant and emerging technologies in smart mobility through the GTM-based patent map development[J]. Sustainability, 2020, 12(22): 9310.
[19]	冯家琪, 王海燕, 吴菲菲, 等. 基于标准和专利数据的企业技术研发方向识别研究[J]. 情报杂志, 2024, 43(3): 106-112, 149.
	FENG J Q, WANG H Y, WU F F, et al. Research on enterprise technology R & D direction identification based on standard and patent data[J]. Journal of intelligence, 2024, 43(3): 106-112, 149.
[20]	COLOMBELLI A, KRAFFT J, QUATRARO F. Properties of knowledge base and firm survival: Evidence from a sample of French manufacturing firms[J]. Technological forecasting and social change, 2013, 80(8): 1469-1483.
[21]	曾德明, 周涛. 企业知识基础结构与技术创新绩效关系研究: 知识元素间关系维度新视角[J]. 科学学与科学技术管理, 2015, 36(10): 80-88.
	ZENG D M, ZHOU T. The relationship between knowledge base and innovative performance: A new relational perspective of knowledge elements[J]. Science of science and management of S & T, 2015, 36(10): 80-88.
[22]	赵展一, 李贞贞, 钟永恒, 等. 融合专利类别与语义信息的企业潜在技术关系测算方法研究[J]. 情报理论与实践, 2023, 46(3): 200-208.
	ZHAO Z Y, LI Z Z, ZHONG Y H, et al. Research on the measuring method of enterprise potential technology relationship based on patent category and semantic information[J]. Information studies: Theory & application, 2023, 46(3): 200-208.
[23]	LI R R, WANG X F, LIU Y Q, et al. Improved technology similarity measurement in the medical field based on subject-action-object semantic structure: A case study of Alzheimer’s disease[J]. IEEE transactions on engineering management, 2023, 70(1): 280-293.
[24]	张娴, 许海云, 方曙, 等. 专利技术组合机会与合作潜力研究[J]. 情报杂志, 2015, 34(7): 39-46.
	ZHANG X, XU H Y, FANG S, et al. Exploring potential patent portfolios: An integrated approach based on topic identification and correlation analysis[J]. Journal of intelligence, 2015, 34(7): 39-46.
[25]	颜雪松, 蔡之华. 一种基于Apriori的高效关联规则挖掘算法的研究[J]. 计算机工程与应用, 2002, 38(10): 209-211.
	YAN X S, CAI Z H. Research on a high-efficient algorithm of mining association rule based on apriori[J]. Computer engineering and applications, 2002, 38(10): 209-211.
[26]	ABUZAID A H. Identifying density-based local outliers in medical multivariate circular data[J]. Statistics in medicine, 2020, 39(21): 2793-2798.
[27]	龙小宁, 王禹诺, 张美扬. 专利前向引用的价值: 基于中国上市公司发明专利数据的经验分析[J]. 山东大学学报(哲学社会科学版), 2024(5): 47-58.
	LONG X N, WANG Y N, ZHANG M Y. The value of forward citations of patents: An empirical analysis based on invention patent data of Chinese listed companies[J]. Journal of Shandong University (philosophy and social sciences), 2024(5): 47-58.
[28]	宋凯, 冉从敬. 基于主题挖掘与专利评估的技术机会识别研究: 以智慧农业为例[J]. 图书情报工作, 2023, 67(3): 61-71.
	SONG K, RAN C J. Research on technology opportunity identification based on topic mining and patent evaluation: A case study of smart agriculture[J]. Library and information service, 2023, 67(3): 61-71.
[29]	潘威, 胡元佳, 王一涛. 针灸技术创新的国际化: 基于美国针灸专利的定量分析[J]. 中国针灸, 2011, 31(8): 749-752.
	PAN W, HU Y J, WANG Y T. Globalization of acupuncture technology innovation: A quantitative analysis based on acupuncture patents in the U.S.A[J]. Chinese acupuncture & moxibustion, 2011, 31(8): 749-752.
[30]	麻天, 余本国, 张静, 等. 基于混合聚类与融合用户兴趣的协同过滤推荐算法[J]. 电子技术应用, 2022, 48(4): 29-33.
	MA T, YU B G, ZHANG J, et al. Collaborative filtering recommendation algorithm based on hybrid clustering and user preferences fusion[J]. Application of electronic technique, 2022, 48(4): 29-33.
[31]	UDDIN S, KHAN A. The impact of author-selected keywords on citation counts[J]. Journal of informetrics, 2016, 10(4): 1166-1177.
[32]	张倩. 生命周期视角下的高新技术企业价值评估[J]. 市场周刊, 2022, 35(1): 44-46.
	ZHANG Q. Value evaluation of high-tech enterprises from the perspective of life cycle[J]. Market weekly, 2022, 35(1): 44-46.
[33]	ADAMUTHE A C, THAMPI G T. Technology forecasting: A case study of computational technologies[J]. Technological forecasting and social change, 2019, 143: 181-189.
[34]	何丽娜, 高建刚. 中国5G专利技术的申请特性和生命周期研究[J]. 科技和产业, 2024, 24(11): 150-155.
	HE L N, GAO J G. Research on application characteristics and life cycle of 5G patent technology in China[J]. Science technology and industry, 2024, 24(11): 150-155.
[35]	卢志平, 玉晓晶. 专利价值评估的理论研究: 基于技术、法律、市场三维视角的分析[J]. 价格理论与实践, 2024(7): 126-130, 222.
	LU Z P, YU X J. Theoretical Research on Patent Value Evaluation: Analysis based on the three-dimensional perspectives of technology, law, and market[J]. Price: theory & practice, 2024(7): 126-130, 222.
[36]	PUTNAM J. The value of international patent rights[M]. New Haven: Yale University, 1996.
[37]	李奎元, 曲永昶, 崔遵康, 等. 生物育种领域核心专利识别与分析[J]. 中国农业文摘-农业工程, 2025, 37(1): 14-22.
	LI K Y, QU Y C, CUI Z K, et al. Identification and analysis of core patents in the field of biological breeding[J]. China agricultural abstracts - Agricultural engineering, 2025, 37(1): 14-22.
[38]	LEE Y G, LEE J D, SONG Y I, et al. An in-depth empirical analysis of patent citation counts using zero-inflated count data model: The case of KIST[J]. Scientometrics, 2007, 70(1): 27-39.
[39]	刘婷, 赵亚娟. 技术机会识别研究综述与展望[J]. 农业图书情报学报, 2023, 35(7): 4-17.
	LIU T, ZHAO Y J. Review and prospect of reesearch on technology opportunity identification[J]. Journal of library and information science in agriculture, 2023, 35(7): 4-17.
[40]	李娟, 李保安, 方晗, 等. 基于AHP-熵权法的发明专利价值评估: 以丰田开放专利为例[J]. 情报杂志, 2020, 39(5): 59-63.
	LI J, LI B A, FANG H, et al. Evaluation of invention patent value based on AHP-entropy weight method: Taking Toyota's open-source patent as an example[J]. Journal of intelligence, 2020, 39(5): 59-63.
[41]	REITZIG M. Improving patent valuations for management purposes: Validating new indicators by analyzing application rationales[J]. Research policy, 2004, 33(6/7): 939-957.
[42]	田涛. 非专利文献检索初探[J]. 技术与市场, 2015, 22(8): 350.
	TIAN T. A preliminary study on non-patent literature retrieval[J]. Technology and market, 2015, 22(8): 350.
[43]	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.
	CHAO R, LONG M, HUANG X L. Research on characteristics and patent value of Chinese patent gold award[J]. Journal of Zhongnan University of economics and law, 2020(5): 73-81.
[44]	MAKRI M, HITT M A, LANE P J. Complementary technologies, knowledge relatedness, and invention outcomes in high technology mergers and acquisitions[J]. Strategic management journal, 2010, 31(6): 602-628.

技术机会类型	含义	特点
新兴技术	指处于早期发展阶段、具有显著创新性，且可能对社会、经济或特定领域产生深远影响的技术	“0~N”的颠覆性创新
融合技术	指通过整合不同学科、领域或技术的核心优势，形成具有协同效应的技术体系，是技术进化和创新的主要方式和根本体现	“1+1>2”的协同创新
空白技术	在某一领域中尚未出现，但具有较大发展潜力，通过创新填补技术或市场缺口的技术	从0到1的突破性创新

一级指标	二级指标	具体解释
市场影响力X	布局国家或地域数C1	布局国家或地域数越多，说明注重在全球范围内保护自己的知识产权，有利于专利所属企业在国际市场上布局^[36]
	专利许可次数C2	专利许可次数越多，说明该专利在市场上的应用范围越广，企业能够从专利许可中获得更多的市场收益^[37]
	专利转让次数C3	专利的转让数量越多，说明该专利的技术方案在市场上得到了广泛的认可，市场影响力较强^[38]
市场多样性Y	IPC分类号数量C4	分类号越多，说明该专利涵盖了更广泛的技术领域，体现了专利技术在进入市场上的多样性和广度^[39]
市场多样性Y	说明书页数C5	说明书页数较多通常意味着技术细节详尽、创新点密集或解决方案复杂，体现专利覆盖更广泛的技术分支，从而支撑更多样化的市场应用^[40]
市场竞争力Z	发明人数量C6	较多的发明人数量可能意味着更广泛的研发团队，拥有着更强的技术整合能力，从而提升专利质量和竞争力^[41]
	引用非专利文献数C7	引用非专利文献数越多，意味着专利在学术界或行业内受到广泛关注，与其他专利相比更具市场认可^[42]
	专利简单同族个数C8	同族专利越多，说明该专利在多个市场上受到保护和广泛布局，具有较强的市场竞争力^[43]

算法	TP	FP	精确率（Precision）/%	准确率（Accuracy）/%	F1分数
Apriori	215	609	26.09	64.85	0.320
LOF	208	1 515	12.12	29.77	0.186
Apriori+LOF	194	433	30.84	70.81	0.339

H01领域技术机会	关键词来源构成
TO-1	充电Z、加热Z、固定板Z、含氮A、接线柱A
TO-2	电极Z、控制器Z、锂电池A、脱氮A、制备A

技术领域	技术关键词
H02	轻量化、充电、薄膜电池、太阳能、光伏
	充电、交换开关、轻量化、光伏、房车
	薄膜电池、交换开关、快速拆卸、供电、轻量化
B60	电机、智能控制、充电站、控制器、即时充电
G06	自主运行、无线通信接口、车辆动力、燃料电池、充电站
G01	可用容量、通信装置、监测、诊断装置、电池