2024年 05期

Technology-effect Matrices Constructed by Using Subject-Action-Object Semantic Analysis


摘要(Abstract):

针对准确定义技术、功效主题的关键问题,通过分析技术、功效主题在构建技术功效矩阵中的语义共现性,提出一种基于主体-行为-客体语义分析的技术功效矩阵构建方法;基于目标领域制定检索表达式,在国家知识产权局专利数据库中下载相关专利信息数据,并预处理专利数据,得到目标专利信息文档;利用Python语言编程,采用中文分词工具包语言技术平台提取专利信息文档的主体-行为-客体语义结构,结合目标领域语料库、词频-逆文本频率和余弦相似度计算主题词的语义相似度;利用聚类算法Louvain算法实现社区网络划分,以凝练技术、功效主题,并通过主体-行为-客体语义结构的共现关系构建技术功效矩阵;以海底电缆反应力锥切削技术为例,通过专利实例分析验证所提出方法的有效性。结果表明:在分析大量专利实例以构建技术功效矩阵时,所提出的方法可以有效地实现专利实例中主体-行为-客体语义结构的社区网络划分;通过分析社区网络中节点主题的权重确定社区网络主题,提高了主题凝聚的准确性;在海底电缆反应力锥切削技术的专利实例分析中,利用主体-行为-客体语义结构和Louvain算法凝聚了7个技术主题、 9个功效主题,验证了所提出方法的有效性。

关键词(KeyWords): 主体-行为-客体;语义分析;技术功效矩阵;专利文本;聚类算法

基金项目(Foundation): 山东省自然科学基金项目(ZR2020ME137)

作者(Author): 张瑞年,高常青,时子皓,刘永旭,杨波

DOI: 10.13349/j.cnki.jdxbn.20240024.002

参考文献(References):

[1] 方曙,张娴,肖国华.专利情报分析方法及应用研究[J].图书情报知识,2007(4):64.

[2] KOSTOFF R N,BOYLAN R,SIMONS G R.Disruptive tech-nology roadmaps[J].Technological Forecasting & Social Change,2004,71:141.

[3] 鲁建厦,徐林燕,赵林斌,等.基于文献计量法的RFID研究现状分析[J].计算机集成制造系统,2017,23(11):2518.

[4] 李晓曼,宋红燕.面向专利情报研究的SAO语义结构分析方法述评[J].情报科学,2020,38(10):168.

[5] CHOI S,YOON J,KIM K,et al.SAO network analysis of patents for technology trends identification:a case study of polymer electrolyte membrane technology in proton exchange membrane fuel cells[J].Scientometrics,2011,88(3):865-866.

[6] KIM K,PARK K,LEE S.Investigating technology opportunities:the use of SAOx analysis[J].Scientometrics,2019,118(1):45.

[7] MA T T,ZHOU X,LIU J,et al.Combining topic modeling and SAO semantic analysis to identify technological opportunities of emerging technologies[J].Technological Forecasting & Social Change,2021,173:121159.

[8] 刘鹏,闫煜析,冯立杰,等.用户需求导向下基于三级技术功效矩阵的产品创新机会识别[J].情报理论与实践,2023,46(8):138.

[9] YOON J,KIM K.Identifying rapidly evolving technological trends for R&D planning using SAO-based semantic patent networks[J].Scientometrics,2011,88(1):213.

[10] YANG C,HUANG C,SU J.An improved SAO network-based method for technology trend analysis:a case study of graphene[J].Journal of Informetrics,2018,12(1):271.

[11] 李乾瑞,郭俊芳,朱东华.基于形态分析和模糊一致矩阵识别技术机会[J].科研管理,2020,41(7):33.

[12] 马铭,王超,周勇,等.基于语义信息的核心技术主题识别与演化趋势分析方法研究[J].情报理论与实践,2021,44(9):106.

[13] YOON B,KIM S,KIM S,et al.Doc2vec-based link prediction approach using SAO structures:application to patent network[J].Scientometrics,2022,127(9):5385.

[14] OH M,JANG H,KIM S,et al.Main path analysis for tech-nological development using SAO structure and DEMATEL based on keyword causality[J].Scientometrics,2023,128(4):2079.

[15] PARK H,YOON J,KIM K.Identifying patent infringement using SAO based semantic technological similarities[J].Scientometrics,2012,90(2):515.

[16] WANG X F,REN H C,CHEN Y,et al.Measuring patent similarity with SAO semantic analysis[J].Scientometrics,2019,121(1):1.

[17] HOHERCHAK H,DARCHUK N,KRYVYI S.Representation,analysis,and extraction of knowledge from unstructured natural language texts[J].Cybernetics and Systems Analysis,2021,57(3):481.

[18] 曹国忠,杨雯丹,刘新星.基于主体-行为-客体(SAO)三元结构的专利分析方法研究综述[J].科技管理研究,2021,41(4):159-160.

[19] 张兆锋,张均胜,姚长青.一种基于知识图谱的技术功效图自动构建方法[J].情报理论与实践,2018,41(3):149.

[20] 翟东升,张京先,胡等金.基于SAO结构和词向量的专利技术功效图自动构建研究[J].情报理论与实践,2020,43(3):116.

[21] 段庆锋,蒋保建.基于SAO结构的专利技术功效图构建研究[J].现代情报,2017,37(6):48.

[22] TRAPPEY A J C,TRAPPEY C V,GOVINDARAJAN U H,et al.Construction and validation of an ontology-based technology function matrix:technology mining of cyber physical system patent portfolios[J].World Patent Information,2018,55:19.

[23] JHUANG A C C,SUN J J H,TRAPPEY A J C,et al.Computer supported technology function matrix construction for patent data analytics[C]//2017 IEEE 21st International Conference on Computer Supported Cooperative Work in Design (CSCWD),April 26-28,2017,Wellington,New Zealand.New York:IEEE,2017:457.

[24] ZHOU X,HUANG L,PORTER A,et al.Tracing the system transformations and innovation pathways of an emerging technology:solid lipid nanoparticles[J].Technological Forecasting & Social Change,2019,146:788-789.

[25] HU Z Y,FANG S,WEI L,et al.An SAO-based approach to technology evolution analysis using patent information:case study:graphene sensors[J].Chinese Journal of Library and Information Science,2015,8(3):64-65.

[26] 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.

[27] 龚永罡,郭远南.基于TF-IDF和word2Vec的中文文本自动摘要模型[J].中国新通信,2023,25(2):66-67.

[28] 吴宗卓.文本分类中TF-IDF算法的改进研究[J].计算技术与自动化,2022,41(2):85-86.

[29] BLONDEL V D,GUILLAUME J L,LAMBIOTTE R,et al.Fast unfolding of communities in large networks[J].Journal of Statistical Mechanics:Theory and Experiment,2008,10:2-3.