图书情报工作

图书情报工作 >

2024 , Vol. 68 >Issue 9: 65 - 75

DOI: https://doi.org/10.13266/j.issn.0252-3116.2024.09.007

情报研究

基于超网络的核心技术识别方法

  • 陈文杰 ,
  • 曲建升 ,
  • 黄珂敏
展开
  • 1 中国科学院成都文献情报中心 成都 610299;
    2 中国科学院大学经济与管理学院信息资源管理系 北京 100190
陈文杰,馆员,博士研究生;黄珂敏,博士研究生。

收稿日期: 2023-09-27

  修回日期: 2024-01-15

  网络出版日期: 2024-05-16

基金资助

本文系国家重点研发计划项目“从生物医学和流行病学研究数据中自动生成因果图的系列工具研发”(项目编号:2022YFF0712000)，中国科学院文献情报能力建设专项“证据知识图谱支撑的循证决策与推演研究”(项目编号:E2C0003007)和“实验方法自动抽取与建模研究”(项目编号:E2C0003008)研究成果之一。

收起

Research on Core Technology Identification Based on Hypernetwork

  • Chen Wenjie ,
  • Qu Jiansheng ,
  • Huang Kemin
Expand
  • 1 National Science Library (Chengdu), Chinese Academy of Sciences, Chengdu 610299;
    2 University of Chinese Academy of Sciences, Beijing 100190

Received date: 2023-09-27

  Revised date: 2024-01-15

  Online published: 2024-05-16

Supported by

This work is supported by the National Key Research and Development Program of China titled“Research and Development of a Series of Tools for Automatically Generating Cause and Effect Diagrams from Biomedical and Epidemiological Research Data”(Grant No.2022YFF0712000), the special project for the Construction of Literature and Information Capacity of the Chinese Academy of Sciences titled“The Research of Evidence Based Decision-making and Deduction Supported by Evidence Knowledge Graph”(Grant No.E2C0003007) and“Research on Automatic Extraction and Modeling of Experimental Methods”(Grant No.E2C0003008).

Fold

摘要

[目的/意义] 对特定技术领域的核心技术进行识别与分析,可以全面了解该领域的研究现状与发展趋势,为前沿技术研发和抢占科技制高点提供参考与建议。[方法/过程] 引入超网络结构表征技术实体间的多元共现关系,利用超网络嵌入技术自动生成融合结构特征和属性特征的技术节点向量并通过模糊聚类得到技术集群,构建基于超网络结构的局部中心性、半局部中心性和全局中心性等度量指标,以识别每个技术集群中的核心技术节点。[结果/结论] 以碳捕集、利用和封存技术领域为例,验证此方法的有效性和科学性,结果显示化学吸收、膜分离、固体吸附和低温分离等技术是该领域的核心技术,有助于我国合理配置资源、加大核心技术的研发力度以获取竞争优势。

关键词： 核心技术识别; 技术共现超网络; 超网络嵌入; 中心性度量

本文引用格式

陈文杰 , 曲建升 , 黄珂敏 . 基于超网络的核心技术识别方法[J]. 图书情报工作, 2024 , 68(9) : 65 -75 . DOI: 10.13266/j.issn.0252-3116.2024.09.007

Abstract

[Purpose/Significance] Identifying and analyzing the core technology in a specific technical field can provide a comprehensive understanding of the research status and development in that field, and give suggestions for the cutting-edge technology research and acquisition.[Method/Process] It introduced a hypernetwork structure to characterize the multiple co-occurrence relationships between entities, automatically generated technology node vectors that integrate structural and attribute features with hypernetwork embedding, and obtained technology clusters through fuzzy clustering. It constructed some measures such as local neutrality, semi local centrality, and global centrality based on the hypernetwork structure to identify the core technology nodes in each technology cluster.[Result/Conclusion] Taking the field of carbon capture, utilization, and storage technology as an example, it verifies the effectiveness and scientificity of the method proposed in this article. The results show that chemical absorption, membrane separation, solid adsorption, and low-temperature separation are the core technologies in this field, which help allocate resources reasonably and improve the research of core technologies to gain competitive advantages in China.

Key words： identification of core technologies; technology co-occurrence hypernetwork; hypernetwork embedding; centrality measurement

参考文献

[1] 赵建,梁爽.关键核心技术识别方法研究进展[J/OL].情报杂志:1-10[2024-01-12]. http://kns.cnki.net/kcms/detail/61.1167. G3.20231113.1025.004.html.(ZHAO J, LIANG S. Research progress on identification methods of key core technologies[J]. Journal of intelligence:1-10[2024-01-12]. http://kns.cnki.net/kcms/detail/61.1167.G3.20231113.1025.004.html.)
[2] 徐霞,吴福象,王兵.基于国际专利分类的关键核心技术识别研究[J].情报杂志, 2022, 41(10):74-81.(XU X, WU F X, WANG B. Research on identification of key core technology based on international patent classification[J]. Journal of intelligence, 2022, 41(10):74-81.)
[3] 马涛,索琪.基于超图的超网络研究综述[J].运筹与管理, 2021, 30(2):232-239.(MA T, SUO Q. Review of hypernetwork based on hypergraph[J]. Operations research and management science, 2021, 30(2):232-239.)
[4] FENG Y, YOU H, ZHANG Z, et al. Hypergraph neural networks[C]//AAAI conference on artificial intelligence. Hawaii:AAAI, 2019:3558-3565.
[5] TU K, CUI P, WANG X, et al. Structural deep embedding for hyper-networks[C]//AAAI conference on artificial intelligence. New Orleans:AAAI, 2018:110-125.
[6] ZHANG R, ZOU Y, MA J. Hyper-SAGNN:a self-attention based graph neural network for hypergraphs[C]//International conference on learning representations. Zoom:ICLR, 2020:2230-2243.
[7] 胡秉德,王新根,王新宇,等.超图学习综述:算法分类与应用分析[J].软件学报, 2022, 33(2):498-523.(HU B D, WANG X G, WANG X Y, et al. Survey on hypergraph learning:algorithm classification and application analysis[J]. Journal of software, 2022, 33(2):498-523.)
[8] 李纲,巴志超.科研合作超网络下的知识扩散演化模型研究[J].情报学报, 2017, 36(3):274-284.(LI G, BA Z C. Research on evolutionary dynamics of knowledge diffusion based on collaboration hypernetwork[J]. Journal of the China Society for Scientific and Technical Information, 2017, 36(3):274-284.)
[9] 高晨晖,姜晓睿,叶政君,等.基于异质学术超网的文献评价[J].情报学报, 2016, 35(8):826-837.(GAO C H, JIANG X R, YE Z J, et al. Ranking scientific articles over heterogeneous academic hypernetwork[J]. Journal of the China Society for Scientific and Technical Information, 2016, 35(8):826-837.)
[10] 王雨,郭进利.超网络视角下的科研合作网络节点重要性评估[J].图书馆杂志, 2018, 37(10):89-100.(WANG Y, GUO J L. The evaluation of node importance within the scientific collaboration network from hypernetwork perspective[J]. Library journal, 2018, 37(10):89-100.)
[11] 孙海生.基于超网络模型的研究热点探测与聚类主题描述[J].情报杂志, 2017, 36(6):93-98.(SUN H S. Research on hot topics detection and clustering results description based on super network model[J]. Journal of intelligence, 2017, 36(6):93-98.)
[12] 曾荣燊,李弼程,陈刚,等.基于线上-线下超网络模型的舆论演化仿真分析[J].计算机应用研究, 2024, 41(2):507-514.(ZENG R S, LI B C, CHEN G, et al. Analysis of public opinion evolution based on online-offline supernetwork model[J]. Application research of computers, 2024, 41(2):507-514.)
[13] 刘盼盼,王丽.关系网络视角下新兴技术识别研究进展[J].图书情报工作, 2022, 66(11):139-150.(LIU P P, WANG L. Research progress of emerging technology identification from the perspective of relational network[J]. Library and information service, 2022, 66(11):139-150.)
[14] KAJIKAWA Y, YOSHIKAWA J, TAKEDA Y, et al. Tracking emerging technologies in energy research:toward a roadmap for sustainable energy[J]. Technological forecasting&social change, 2008, 75(6):771-782.
[15] CHO T S, SHIH H Y. Patent citation network analysis of core and emerging technologies in Taiwan:1997-2008[J]. Scientometrics, 2011, 89(3):795-811.
[16] 戚筠,唐恒,石俊国.基于小世界网络特性的核心技术识别研究——以石墨烯为例[J].情报杂志, 2020, 39(2):50-55.(QI Y, TANG H, SHI J G. Research on core technology identification based on small world network characteristics:a case study of graphene[J]. Journal of intelligence, 2020, 39(2):50-55.)
[17] 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. 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.)
[18] SONG K, KIM K, LEE S, et al. 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(3):118-132.
[19] 武川,王宏起,王珊珊.前沿技术识别与预测方法研究——基于专利主题相似网络与技术进化法则[J].中国科技论坛, 2023(4):34-42.(WU C, WANG H Q, WANG S S. Research on the identification and prediction methods of frontier technologies:based on the patent topic similarity network and technology evolution[J]. Forum on science and technology in China, 2023(4):34-42.)
[20] 黄璐,朱一鹤,张嶷.基于加权网络链路预测的新兴技术主题识别研究[J].情报学报, 2019, 38(4):335-341.(HUANG L, ZHU Y H, ZHANG Y. Research on identification of emerging topics based on link prediction with weighted networks[J]. Journal of the China Society for Scientific and Technical Information, 2019, 38(4):335-341.)
[21] 罗吉利,李孟军,姜江,等.基于证据推理的核心技术识别方法研究[J].情报杂志, 2017, 34(1):38-43, 31.(LUO J L, LI M J, JIANG J, et al. On recognition of the core technology using evidential reasoning[J]. Journal of intelligence, 2017, 34(1):38-43, 31.)
[22] DOTSIKA F, WATKINS A. Identifying potentially disruptive trends by means of keyword network analysis[J]. Technological forecasting&social change, 2017, 119(6):114-127.
[23] 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.)
[24] 楼旭明,张程锦,唐影.基于专利分析和TRIZ理论的无人机技术态势研究[J].情报杂志, 2020, 39(2):56-62.(LOU X M, ZHANG C J, TANG Y. Research on the development status and trend of UAV technology based on patent analysis and TRIZ theory[J]. Journal of intelligence, 2020, 39(2):56-62.)
[25] 李维思,谭力铭,章国亮,等.基于多源信息融合的产业链关键核心技术主题识别研究:以人工智能领域为例[J].信息资源管理学报, 2022, 12(1):116-126.(LI W S, TAN L M, ZHANG G L, et al. Research on topic recognition of key core technology in industrial chain based on multi-source information fusion:taking AI as an example[J]. Journal of information resources management, 2022, 12(1):116-126.)
[26] 王秀红,高敏.基于BERT-LDA的关键技术识别方法及其实证研究——以农业机器人为例[J].图书情报工作, 2021, 65(22):114-125.(WANG X H, GAO M. The key technology identification method based on BERT-LDA and its empirical research:a case study of agricultural robots[J]. Library and information service, 2021, 65(22):114-125.)
[27] LIN W G, LIU X D, XIAO R B. Research on product core component acquisition based on patent semantic network[J]. Entropy, 2022, 24(4):1-20.
[28] 任海英,李真.基于输入输出型SAO网络的核心技术链识别方法研究——以量子计算领域为例[J].图书情报工作, 2021, 65(19):117-129.(REN H Y, LI Z. Research on identification method of core technology chain based on an input-output SAO network:a case of quantum computing technologies[J]. Library and information service, 2021, 65(19):117-129.)
[29] 陈育新,李健,韩毅.核心-边缘理论视角下的颠覆性技术识别研究[J].情报理论与实践, 2022, 45(8):121-129.(CHEN Y X, LI J, HAN Y. Research on a method to identify disruptive technologies in the view of core-periphery theory[J]. Information studies:theory&application, 2022, 45(8):121-129.)
[30] 李慧,庞经纬,孟玮.基于专利知识流网络和图表示学习的技术机会链路预测研究[J].情报理论与实践, 2023, 46(7):107-114, 149.(LI H, PANG J W, MENG W. Research on technology opportunity link prediction based on patent knowledge flow network and graph representation learning[J]. Information studies:theory&application, 2023, 46(7):107-114, 149.)
[31] 江屏,王川,孙建广,等. IPC聚类分析与TRIZ相结合的专利群规避设计方法与应用[J].机械工程学报, 2015, 51(7):144-154.(JIANG P, WANG C, SUN J G. Method and application of patented design around by combination of IPC cluster analysis and TRIZ[J]. Journal of mechanical engineering, 2015, 51(7):144-154.)
[32] FENG Y, YOU H, ZHANG Z, et al. Hypergraph neural networks[C]//Proceedings of the AAAI conference on artificial intelligence. Honolulu:AAAI, 2019:3558-3565.
[33] 阮逸润,老松杨,王竣德,等.基于领域相似度的复杂网络节点重要度评估算法[J].物理学报, 2017, 66(3):371-379.(RUAN Y R, LAO S Y, WANG J D, et al. Node importance measurement based on neighborhood similarity in complex network[J]. Acta physica sinica, 2017, 66(3):371-379.)
[34] 阳平坚,彭栓,王静,等.碳捕集、利用和封存(CCUS)技术发展现状及应用展望[J].中国环境科学, 2024, 44(1):404-416.(YANG P J, PENG S, WANG J, et al. Carbon Capture, Utilization and Storage (CCUS) technology development status and application prospects[J]. China environmental science, 2024, 44(1):404-416)
[35] DHG[EB/OL].[2024-01-12]. https://deephypergraph.readthedocs.io/en/latest/index.html.
[36] Optuna[EB/OL].[2024-01-12]. https://optuna.org/.
[37] LAURENS V D M, HINTON G. Visualizing data using t-SNE[J]. Journal of machine learning research, 2008, 9(2605):2579-2605.
[38] 温翯,韩伟,车春霞,等.燃烧后二氧化碳捕集技术与应用进展[J].精细化工, 2022, 39(8):1584-1595, 1632.(WEN H, HAN W, CHE C X, et al. Progress of post-combustion carbon dioxide capture technology development and applications[J]. Fine chemicals, 2022, 39(8):1584-1595, 1632.)
Options
文章导航

/

〈 〉