•  
  •  
 

Scientific Information Research

Keywords

LDA; random forest model; patent invalidation; word2vec model; explainable machine learning

Abstract

[Purpose/significance]Taking patent infringement as the starting point, this paper explores the influence mechanism of different factors on the tendency of patent infringement declaration, then compares and analyzes the differences in the influencing factors of invalid declaration under different infringement themes in the same field.[Method/process]Firstly, this paper uses the LDA topic model to subdivide the infringement topics in the selected emerging industry field, and understands the different infringement topics and infringement keywords of the infringement patents in this field;Secondly, the statistical correlation model is used to calculate various data indicators under different infringement classification topics and comparatively analyze the correlation between invalid declaration tendencies. Finally,by constructing a multi-feature fusion random forest model, the patents under different infringement classification topics are identified and trained for invalid declaration classification, and the LIME model in machine learning can be explained. Explain the degree of influence of the measurement index features in the model.[Result/conclusion]According to the correlation analysis after topic classification, it is found that under different topic classifications, the selected feature indicators not only have different overall influence on the determination of invalidity after infringement, but also have different influencing factors and influence degree rankings in different classification results. There existed significant differences in the classification rules and classification indicators relied on by different classification topics.

First Page

75

Reference

[1] 国家知识产权局战略规划司.2021年中国知识产权统计年报[EB/OL].(2022-08-10)[2022-11-28].https://www.cnipa.gov.cn/tjxx/jianbao/year2021/indexy.html.
[2] 张红娟,刘希萌,张俊艳,等.中国企业在美专利侵权诉讼研究[J].中国发明与专利,2022,19(10):33-41.
[3] HENKEL J.The Licensing of Standard-Essential Patents in the IoT-A Value Chain Perspective on the Market for Technology[J].SSRN Electronic Journal,2022.
[4] 石友华.专利侵权认定标准研究[D].北京:首都经济贸易大学,2013.
[5] 李莹,周胜生.基于大数据视角的专利侵权风险预警模式研究[J].中国发明与专利,2021,18(03):11-17.
[6] 付振康,柳炳祥,鄢春根,等.专利文献视角下专利寿命影响因素研究:一项Meta分析[J].科学与管理,2023,43(03):66-78.
[7] 王桐,王伟,张世玉,等.基于专利组合的中药企业专利威胁预警分析[J].中华医学图书情报杂志,2018,27(09):15-19.
[8] 蒋启蒙,朱雪忠.专利侵权诉讼中无效宣告倾向的影响因素研究[J].科学学研究,2022,40(07):1224-1233.
[9] STERLACCHINI A.Trends and determinants of energy innovations:Patents,environmental policies and oil prices[J].Journal of Economic Policy Reform,2019,23(02):1-18.
[10] CHIEN S,CUNNINGHAM D,KHAN K S.Inguinal hernia repair:A systematic analysis of online patient information using the Modified Ensuring Quality Information for Patients tool[J/OL].British Journal of Surgery,2021.https://www.researchgate.net/publication/349465635.DOI: 10.13140/RG.2.2.22512.58885.
[11] LANJOUW J O,SCHANKERMAN L M.Characteristics of Patent Litigation:A Windowon Competition[J].Rand Journal of Economics,2001,32(01):129-151.
[12] HALL B,HARHOFF D.Post-grant reviews in the U.S.patent system-design,choices and expected impact[J].Berkeley Technology Law Journal,2004,19(01):989-1015.
[13] 刘立春,漆苏.专利特征对药品专利法律质量评估的实证研究[J].科研管理,2015,36(06):119-127.
[14] 张晓月,安秋凡,甄伟军.转化视角下的高校专利价值研究:基于“一流大学”建设高校发明授权专利的数据[J].中国高校科技,2019(03):69-73.
[15] 梁正,尹志锋.专利行政诉讼审判结果及其影响因素分析:基于2004—2013年中国专利行政诉讼数据的实证研究[J].知识产权,2016(10):83-88,93.
[16] 李建霖,李兰琪.基于机器学习的高校可转化专利识别模型构建与应用[J].数字技术与应用,2022,40(06):11-17.
[17] HARHOFF D,REITZIG M.Determinants of Opposition Against EPO Patent Grants:The Case of Biotechnology and Pharmaceuticals[J].International Journal of Industrial Organization,2004,22(04):443-480.
[18] STERLACCHINI A.Trends and determinants of energy innovations:Patents,environmental policies and oil prices[J].Journal of Economic Policy Reform,2020,23(01):49-66.
[19] TRAJTENBERG M,SHIFF G,MELAMED R.The“Names Game”::Harnessing Inventors,Patent Data for Economic Research[J].Annals of Economics and Statistics,2009(93-94):67-77.
[20] RYSMAN M,SIMCOE T.Patents and the Performance of Voluntary Standard-Setting Organizations[J].Management Science,2008(11):1920-1934.
[21] 冯君,周静珍,杜芸.单件专利质量评价指标体系研究[J].科技管理研究,2012,32(23):166-170.
[22] 刘亚杰,陈朝晖,谢薇.高校专利运营风险指标体系构建研究[J].中国发明与专利,2018,15(01):20-24.
[23] 国家知识产权局专利管理司,中国技术交易所组织编著.专利价值分析指标体系操作手册[M].北京:知识产权出版社,2012.
[24] LERNER J,SERU A.The Use and Misuse of Patent Data:Issues for Finance and Beyond[J].The Review of Financial Studies,2022,35(06):2667-2704.
[25] 张娴,方曙.专利引用网络主路径方法研究述评与展望[J].图书情报工作,2016,60(20):140-148.
[26] 李春燕,石荣.专利质量指标评价探索[J].现代情报,2008(02):146-149.
[27] 冯仁涛.基于专利文献的专利维持时间影响因素分析[J].情报杂志,2020,39(07):202-207.
[28] 杨秀财,林波,王园.专利家族学术影响力的影响因素研究[J].科技与经济,2020,33(03):46-50.
[29] 张杰,孙超,翟东升,等.基于诉讼专利的专利质量评价方法研究[J].科研管理,2018,39(05):138-146.
[30] 郭青,戚湧,高盼军.基于技术、法律和经济三位一体的专利质量评价及应用研究[J].中国发明与专利,2021,18(01):21-29.
[31] 刘强,马欢军.协同创新战略背景下的专利转让纠纷法律适用:以经济学分析为视角[J].大理大学学报,2018,3(03):82-91.
[32] 袁晓东,侯帆.专利丛林:内涵、测量与解决机制[J].知识产权,2019(06):58-65.
[33] 付振康,柳炳祥,周子钰.基于集成学习的专利质量分析与分类预测研究[J].情报杂志,2022,41(10):89-96.
[34] 陈咏梅,伍聪聪.欧盟《通用数据保护条例》域外适用条件之解构[J].德国研究,2022,37(02):85-101,123-124.
[35] 国务院.国务院关于加快培育和发展战略性新兴产业的决定[EB/OL].(2010-10-10)[2022-11-28].https://www.gov.cn/zwgk/2010-10/18/content_1724848.htm.
[36] 王宏起,郭雨,武建龙.战略性新兴企业专利风险评价研究[J].科技管理研究,2016,36(01):56-60.
[37] 新华社.中华人民共和国国民经济和社会发展第十四个五年规划和2035年远景目标纲要[EB/OL].(2021-03-13)[2022-11-28].https://www.gov.cn/xinwen/2021-03/13/content_5592681.htm.

Share

COinS