核心专利集筛选及专利技术主题识别影响
|
摘要
领域重要的技术特征词在技术主题网络中具有关键核心作用,研究对比从核心专利数据集中抽取的技术特征词相对于全数据集的效率,进而探讨基于引文网络的核心专利集筛选策略对技术主题识别所产生的影响。本文借鉴了专利引用强度指标和引用滞后性特征对核心专利集进行两步筛选,研究对比核心专利集与全数据集抽取的主题特征词在词云规模、词频覆盖率、阈值选择以及技术主题划分的差异。实证分析发现,利用核心专利集抽取技术特征词有助于提升技术主题识别的效率和准确性,且基于核心专利集聚类生成的技术主题网络与领域全集的主题覆盖率较大,能够有效简化技术网络中的技术主题,更加便于专家对技术主题进行归纳与总结。
Technical feature words are considered to play a key role in technology networks. This study compares the efficiency of technical feature words extracted from the core patent dataset with those of the whole dataset and discusses the impact of core patent screening on the identification of technology features based on citation networks. This study applies the patent citation intensity indicator and citation time lag into patent screening of core patent documents in two steps. Furthermore, the differences between core documents and whole documents were identified in terms of word cloud,word frequency coverage, threshold selection, and division of technical topics. An empirical analysis on the biomedicine applications of graphene indicates that the feature words extracted from the core patent dataset help increase recognition efficiency and accuracy, and the technology co-classification network generated from the core dataset is more focused than the one generated from the whole network; this effectively simplifies data cleaning and also aids topic identification and expert interpretation.
Technical feature words are considered to play a key role in technology networks. This study compares the efficiency of technical feature words extracted from the core patent dataset with those of the whole dataset and discusses the impact of core patent screening on the identification of technology features based on citation networks. This study applies the patent citation intensity indicator and citation time lag into patent screening of core patent documents in two steps. Furthermore, the differences between core documents and whole documents were identified in terms of word cloud,word frequency coverage, threshold selection, and division of technical topics. An empirical analysis on the biomedicine applications of graphene indicates that the feature words extracted from the core patent dataset help increase recognition efficiency and accuracy, and the technology co-classification network generated from the core dataset is more focused than the one generated from the whole network; this effectively simplifies data cleaning and also aids topic identification and expert interpretation.
引文
[1]沈君.知识网络视角的专利技术主题结构分析——以第三代移动通信技术为例[D].大连:大连理工大学,2012.
[2]杨超,朱东华,汪雪锋,等.专利技术主题分析:基于SAO结构的LDA主题模型方法[J].图书情报工作,2017,3(61):86-96.
[3]许海云,王振蒙,胡正银,等.利用专利文本分析识别技术主题的关键技术研究综述[J].情报理论与实践,2016,11(39):131-137.
[4]屈鹏,王惠临.专利文本分类的基础问题研究[J].现代图书情报技术,2013(3):38-40.
[5]Choi J,Hwang Y S.Patent key network anlayisis for improving technology development efficiency[J].Technological Forecasting&Social Change,2014,83:170-182.
[6]Hu P,Huang M L,Xu P,et al.Finding nuggets in IP portfolios core patent mining through textual temporal analysis[C]//Pro-ceedings of the 21st ACM International Conference on Informa-tion and Knowledge Management.New York:ACM Press,2012:1819-1823.
[7]穆秀秀,郭德斌,刘伟,等.基于核心专利群的专利规避范围界定方法研究[J],工程设计学报,2015,22(2):116-122.
[8]祁延莉,刘西琴.核心专利识别方法研究[J].情报理论与实践,2016,39(11):5-9.
[9]Choi C,Park Y.Monitoring the organic structure of technology based on the patent development path[J].Technology Forecasting&Social Change,2009,76(6):754-768.
[10]Barbera T D,Jimenez S F,Castello M L.Mapping the importance of the real world:the validity of connectivity analysis of patent ci-tation network[J].Research Policy,2011,40(3):473-486.
[11]Yang C,Zhu D H,Wang X F,et al.Requirement-oriented core technological components’identification based on SAO analysis[J].Scientometrics,2017,112:1229-1248.
[12]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.
[13]Harhoff D,Narin F,Scherer F M,et al.Citation frequency and the value of patented invention[J].Review of Economics and Sta-tistics,1999,81(3):511-515.
[14]彭爱东.基于同被引分析的专利分类方法及相关问题探讨[J].情报科学,2008,26(11):1676-1684.
[15]Ha S H,Liu W N,Cho Hune,et al.Technological advances in the fuel cell vehicle:Patent Portfolio management[J].Technological Forecasting&Social Change,2015,100:277-289.
[16]Mane K K,B?rner K.Mapping topics and topic bursts in PNAS[J].Proceedings of the National Academy of Sciences of the Unit-ed States of America,2004,101:5287-5290.
[17]侯婷,吕学强,李卓,等.面向专利技术主题分析的技术主题获取[J].情报理论与实践,2015,38(5):126-140.
[2]杨超,朱东华,汪雪锋,等.专利技术主题分析:基于SAO结构的LDA主题模型方法[J].图书情报工作,2017,3(61):86-96.
[3]许海云,王振蒙,胡正银,等.利用专利文本分析识别技术主题的关键技术研究综述[J].情报理论与实践,2016,11(39):131-137.
[4]屈鹏,王惠临.专利文本分类的基础问题研究[J].现代图书情报技术,2013(3):38-40.
[5]Choi J,Hwang Y S.Patent key network anlayisis for improving technology development efficiency[J].Technological Forecasting&Social Change,2014,83:170-182.
[6]Hu P,Huang M L,Xu P,et al.Finding nuggets in IP portfolios core patent mining through textual temporal analysis[C]//Pro-ceedings of the 21st ACM International Conference on Informa-tion and Knowledge Management.New York:ACM Press,2012:1819-1823.
[7]穆秀秀,郭德斌,刘伟,等.基于核心专利群的专利规避范围界定方法研究[J],工程设计学报,2015,22(2):116-122.
[8]祁延莉,刘西琴.核心专利识别方法研究[J].情报理论与实践,2016,39(11):5-9.
[9]Choi C,Park Y.Monitoring the organic structure of technology based on the patent development path[J].Technology Forecasting&Social Change,2009,76(6):754-768.
[10]Barbera T D,Jimenez S F,Castello M L.Mapping the importance of the real world:the validity of connectivity analysis of patent ci-tation network[J].Research Policy,2011,40(3):473-486.
[11]Yang C,Zhu D H,Wang X F,et al.Requirement-oriented core technological components’identification based on SAO analysis[J].Scientometrics,2017,112:1229-1248.
[12]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.
[13]Harhoff D,Narin F,Scherer F M,et al.Citation frequency and the value of patented invention[J].Review of Economics and Sta-tistics,1999,81(3):511-515.
[14]彭爱东.基于同被引分析的专利分类方法及相关问题探讨[J].情报科学,2008,26(11):1676-1684.
[15]Ha S H,Liu W N,Cho Hune,et al.Technological advances in the fuel cell vehicle:Patent Portfolio management[J].Technological Forecasting&Social Change,2015,100:277-289.
[16]Mane K K,B?rner K.Mapping topics and topic bursts in PNAS[J].Proceedings of the National Academy of Sciences of the Unit-ed States of America,2004,101:5287-5290.
[17]侯婷,吕学强,李卓,等.面向专利技术主题分析的技术主题获取[J].情报理论与实践,2015,38(5):126-140.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |