图书情报工作

图书情报工作 >

2025 , Vol. 69 >Issue 19: 108 - 123

DOI: https://doi.org/10.13266/j.issn.0252-3116.2025.19.010

研究论文

专利数据异常检测与颠覆性技术预测——以无人机技术为例

  • 肖君超 ,
  • 巫林辉 ,
  • 钟福利 ,
  • 张金玲
展开
  • 1 广东工业大学图书馆 广州 510006;
    2 广东工业大学计算机学院 广州 510006;
    3 中山大学系统科学与工程学院 广州 510275;
    4 桂林电子科技大学数学与计算科学学院 桂林 541004
肖君超，馆员，博士，E-mail：chao8003@sina.com；巫林辉，本科生；钟福利，博士后；张金玲，馆员，硕士。

收稿日期: 2024-10-21

  修回日期: 2025-03-12

  网络出版日期: 2025-09-12

基金资助

本文系国家自然科学基金青年项目“面向服务韧性提升的空间网络系统评估及群智能优化方法研究”（项目编号：62102466）研究成果之一。

收起

Patent Data Anomaly Detection and Disruptive Technology Prediction: A Case Study on Drone Technology

  • Xiao Junchao ,
  • Wu Linhui ,
  • Zhong Fuli ,
  • Zhang Jinling
Expand
  • 1 Guangdong University of Technology Library, Guangzhou 510006;
    2 School of Computer Science, Guangdong University of Technology, Guangzhou 510006;
    3 School of Systems Science and Engineering, Sun Yat-Sen University, Guangzhou 510275;
    4 School of Mathematics and Computing Science, Guilin University of Electronic Technology, Guilin 541004
Xiao Junchao, Librarian, PhD, E-mail: chao8003@sina.com; Wu Linhui, Undergraduate; Zhong Fuli, Postdoc; Zhang Jinling, Librarian, Master’s Degree.

Received date: 2024-10-21

  Revised date: 2025-03-12

  Online published: 2025-09-12

Supported by

This work is supported by the youth project of National Natural Science Foundation of China, titled “Service-Oriented Space Information Network Resilience Assessment and Swarm Intelligence Optimization Approach for Resilience Enhancement” (Grant No. 62102466).

Fold

摘要

[目的/意义] 颠覆性技术能引领领域技术和产业发展，促进企业长足进步，及早预测和部署颠覆性技术对于企业创新和加强其市场地位至关重要。以技术应用和颠覆性技术识别为研究对象，提出一种颠覆性技术预测方法。[方法/过程] 首先，基于每项专利的标题、摘要和国际专利分类号（IPC），构建名词共现图和IPC共现图；其次，利用图异常检测算法在名词共现图和IPC共现图中检测异常名词和IPC编号，并将检测结果与孤立森林中检测到的异常专利相结合，构建异常专利数据集；随后，通过深入分析，提取以异常专利形式出现的颠覆性专利的核心特征，并利用其构建有效的衡量指标体系；最后利用机器学习模型拟合专利指标与颠覆性专利标签之间的相关性，从大量异常技术专利、IPC、名词中预测出潜在的颠覆性技术，并以“无人机技术”为例验证所提方法。[结果/结论] 对无人机技术的实证研究表明，该方法可获得合理的预测结果，并为颠覆性技术预测与专利价值测度分析提供新的视角。

关键词： 颠覆性技术预测; 图异常检测; 名词共现图; IPC共现图

本文引用格式

肖君超 , 巫林辉 , 钟福利 , 张金玲 . 专利数据异常检测与颠覆性技术预测——以无人机技术为例[J]. 图书情报工作, 2025 , 69(19) : 108 -123 . DOI: 10.13266/j.issn.0252-3116.2025.19.010

Abstract

[Purpose/Significance] Disruptive technologies can lead the development of technology and industry and enable enterprises to make great progress. Early prediction and deployment of disruptive technologies are crucial for enterprises to innovate and strengthen their market position. This paper takes technology application and disruptive technology identification as the research objects and proposes a disruptive technology prediction method. [Method/Process] First, based on the title, abstract and international patent classification (IPC) code of each patent, a noun co-occurrence graph and an IPC co-occurrence graph were constructed. Secondly, the graph anomaly detection algorithm was used to detect abnormal nouns and IPC numbers in the noun co-occurrence graph and IPC co-occurrence graph, and the detection results were combined with the abnormal patents detected in the isolation forest to construct an abnormal patent dataset. Then, through in-depth analysis, the core features of disruptive patents that appeared in the form of abnormal patents were extracted, and an effective measurement indicator system was constructed using them. Finally, the correlation between patent indicators and disruptive patent labels was fitted by a machine learning model, and potential disruptive technologies were predicted from a large number of abnormal technology patents, IPCs, and nouns. The proposed method was verified by taking “drone technology” as an example. [Result/Conclusion] The empirical study on drone technology shows that the method obtains reasonable prediction results and provides a new perspective for disruptive technology prediction and patent value measurement analysis.

Key words： disruptive technology prediction; graph anomaly detection; noun co-occurrence graph; IPC co-occurrence graph

参考文献

[1] AN X, LI J, XU S, et al. An improved patent similarity measurement based on entities and semantic relations[J]. Journal of informetrics, 2021, 15(2):101135.
[2] LEE C, JEON D, AHN J M, et al. Navigating a product landscape for technology opportunity analysis:a Word2Vec approach using an integrated patent-product database[J]. Technovation, 2020, 96-97:102140.
[3] CAPPONI G, MARTINELLI A, NUVOLARI A. Breakthrough innovations and where to find them[J]. Research policy, 2022, 51(1):104376.
[4] 许佳琪,汪雪锋,雷鸣,等.从突破性创新到颠覆性创新:内涵、特征与演化[J].科研管理, 2023, 44(2):1-13.(XU J Q, WANG X F, LEI M, et al. From breakthrough innovation to disruptive innovation:their connotations, characteristics and evolution[J]. Science research management, 2023, 44(2):1-13.)
[5] ARTHUR W B. The nature of technology:what it is and how it evolves[M]. New York:Simon & Schuster, 2009.
[6] 王政媛,靳军宝,郑玉荣,等.基于弱信号感知的颠覆性技术早期识别特征研究进展[J].情报理论与实践, 2025, 48(4):174-181, 201.(WANG Z Y, JIN J B, ZHENG Y R, et al. Advances in early recognition characterization of disruptive technologies based on weak signal sensing[J]. Information studies:theory & application, 2025, 48(4):174-181, 201.)
[7] 胡泽文,王梦雅,韩雅蓉.基于LDA2Vec-BERT的新兴技术主题多维指标识别与演化分析研究——以颠覆性技术领域:区块链为例[J].现代情报, 2024, 44(9):42-58.(HU Z W, WANG M Y, HAN Y R. Multidimensional indicator identification and evolution analysis of emerging technology topics based on LDA2Vec-BERT:a case study of blockchain technology in the field of disruptive technology[J]. Journal of modern information, 2024, 44(9):42-58.)
[8] 王宏,刘沁莹,胡玉峰,等.基于多源数据融合的新兴技术识别方法研究[J].科技进步与对策, 2025, 42(5):21-31.(WANG H, LIU Q Y, HU Y F, et al. An approach for identifying emerging technologies by fusing Multi-Source data[J]. Science & technology progress and policy, 2025, 42(5):21-31.)
[9] ARTS S, APPIO F P, LOOY B. Inventions shaping technological trajectories:do existing patent indicators provide a comprehensive picture?[J]. Scientometrics, 2013, 97(2):397-419.
[10] BOWER J L, CHRISTENSEN C M. Disruptive technologies:catching the wave[J]. Harvard business review, 1995, 73(1):43-53.
[11] 王康,陈悦.基于异质性专利的颠覆性技术早期识别研究[J].科学学研究, 2023, 41(8):1364-1375.(WANG K, CHEN Y. Research on early identification of disruptive technologies based on heterogeneous patents[J]. Studies in science of science, 2023, 41(8):1364-1375.)
[12] 王丹,周潇,赵捧未,等.基于离群点视角的颠覆性专利预测研究[J].图书情报工作, 2024, 68(5):74-86.(WANG D, ZHOU X, ZHAO P W, et al. Research on disruptive patent prediction based on outlier perspective[J]. Library and information service, 2024, 68(5):74-86.)
[13] DOTSIKA F, WATKINS A. Identifying potentially disruptive trends by means of keyword network analysis[J]. Technological forecasting & social change, 2017, 119:114-127.
[14] MOMENI A, ROST K. Identification and monitoring of possible disruptive technologies by patent-development paths and topic modeling[J]. Technological forecasting and social change, 2016, 104:16-29.
[15] WANG X, LIANG W, YE X, et al. Disruptive development path measurement for emerging technologies based on the patent citation network[J]. Journal of informetrics, 2024, 18(1):101493.
[16] ZAMANI M, YALCIN H, NAEINI A B, et al. Developing metrics for emerging technologies:identification and assessment[J]. Technological forecasting and social change, 2022, 176:121456.
[17] BHATT P C, LAI K K, DRAVE V A, et al. Patent analysis based technology innovation assessment with the lens of disruptive innovation theory:a case of blockchain technological trajectories[J]. Technological forecasting and social change, 2023, 196:122864.
[18] PUCCETTI G, GIORDANO V, SPADA I, et al. Technology identification from patent texts:a novel named entity recognition method[J]. Technological forecasting and social change, 2023, 186:122160.
[19] XIANG M, FU D, LV K. Identifying and predicting trends of disruptive technologies:an empirical study based on text mining and time series forecasting[J]. Sustainability, 2023, 15(6):5412.
[20] KIM T S, SOHN S Y. Machine-learning-based deep semantic analysis approach for forecasting new technology convergence[J]. Technological forecasting and social change, 2020, 157:120095.
[21] 窦永香,开庆,王佳敏.一种基于图表示学习的潜在颠覆性技术识别方法[J].情报学报, 2023, 42(6):637-648.(DOU Y X, KAI Q, WANG J M. Potential disruptive technology identification method based on graph representation learning[J]. Journal of the China Society for Scientific and Technical Information, 2023, 42(6):637-648.)
[22] 宋博文,栾春娟,梁丹妮.机器学习视域下新兴技术主题识别研究——基于技术特征相似性[J].现代情报, 2022, 42(9):49-57.(SONG B W, LUAN C J, LIANG D N. Recognition model of emerging technology topic from machine learning perspective:based on similarity of technical characteristics[J]. Journal of modern information, 2022, 42(9):49-57.)
[23] 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.
[24] XU Z, HUANG X, ZHAO Y, et al. Contrastive attributed network anomaly detection with data augmentation[C]//PacificAsia conference on knowledge discovery and data mining. Cham:Springer, 2022:444-457.
[25] LIU F T, TING K M, ZHOU Z H. Isolation Forest[C]//2008 eighth IEEE international conference on data mining. Pisa:IEEE, 2008:413-422.
[26] KWON S, LIU X, PORTER A L, et al. Research addressing emerging technological ideas has greater scientific impact[J]. Research policy, 2019, 48(9):103834.
[27] LIANG Z, MAO J, LU K, et al. Combining deep neural network and bibliometric indicator for emerging research topic prediction[J]. Information processing & management, 2021, 58(5):102611.
[28] HIGHAM K, DE RASSENFOSSE G, JAFFE A B. Patent quality:towards a systematic framework for analysis and measurement[J]. Research policy, 2021, 50(4):104215.
[29] BELENZON S. Cumulative innovation and market value:evidence from patent citations[J]. The economic journal, 2012, 122(559):265-285.
[30] 梁镇涛,毛进,李纲.融合"科学-技术"知识关联的高颠覆性专利预测方法[J].情报学报, 2023, 42(6):649-662.(LIANG Z T, MAO J, LI G. Integrating science-technology knowledge linkage to predict disruptive patents[J]. Journal of the China Society for Scientific and Technical Information, 2023, 42(6):649-662.)
[31] 唐恒,张星星,汪满容.基于内容理解与指标融合的高价值专利识别[J].情报杂志, 2024, 43(4):168-174, 127.(TANG H, ZHANG X X, WANG M R. High-value patent recognition based on content understanding and indicators integration[J]. Journal of intelligence, 2024, 43(4):168-174, 127.)
[32] 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.)
[33] 周潇,王博,胡玉琳,等.基于时序图神经网络的潜在高价值专利识别研究[J].情报学报, 2024, 43(6):697-711.(ZHOU X, WANG B, HU Y L, et al. Potential high-value patent identify based on a time-series graph neural network[J]. Journal of the China Society for Scientific and Technical Information, 2024, 43(6):697-711.)
[34] 衣春波,赵文华,邓璐芗,等.基于专利信息的技术创新策源评价指标体系构建与应用[J].情报杂志, 2021, 40(2):55-62.(YI C B, ZHAO W H, DENG L X, et al. Construction and application of evaluation index system of technology innovation cradle based on patent information[J]. Journal of intelligence, 2021, 40(2):55-62.)
[35] 罗素平,寇翠翠,金金,等.基于离群专利的颠覆性技术预测——以中药专利为例[J].情报理论与实践, 2019, 42(7):165-170.(LUO S P, KOU C C, JIN J, et al. Disruptive technology prediction based on outlier patents:traditional Chinese medicine patents as an example[J]. Information studies:theory & application, 2019, 42(7):165-170.)
[36] HAMBLING D. Change in the air:disruptive developments in armed UAV technology[EB/OL].[2025-05-26]. https://unidir. org/files/publication/pdfs/-en-726.pdf.
[37] BOLING B, BOUDREAUX B, BLANC A A, et al. Emerging technology beyond 2035:scenario-based technology assessment for future military contingencies[EB/OL].[2025-05-26]. https://www.rand.org/content/dam/rand/pubs/research_reports/RRA1500/RRA1564-1/RAND_RRA1564-1.synopsis.pdf.
[38] FAN B, LI Y, ZHANG R, et al. Review on the technological development and application of UAV systems[J]. Chinese journal of electronics, 2020, 29(2):199-207.
Options
文章导航

/

〈 〉