[Purpose/Significance] Building a high-value patent recommendation model in universities from the perspective of university-enterprise cooperation, based on the recognition of high-value patents in universities, accurately focusing on enterprise technology needs, recommending high-value patents that are in line with their technological development direction to the enterprises, in order to improve the efficiency of high-value patent transformation of universities and further promote the coordinated development of universities and enterprises. [Method/Process] Firstly, focusing on four dimensions of patent technology, legal, market, and strategic dimensions, download the patents in the field of “new energy vehicles” of universities and enterprises from the Incopat patent database; then, identify high-value patents of universities through the combination of mutation series method and machine learning; finally, merge the independent claims of high-value patents of universities with those of enterprises, and construct the high-value patent recommendation model of universities through natural language processing and topic modeling. [Result/Conclusion] The high-value patent recommendation model of universities constructed in this study has well achieved the functions of recognizing and recommending high-value patents of universities, providing a method reference for improving the efficiency of university patent transfer and deepening the level of university-enterprise cooperation.
[1] 国家知识产权局-统计报告查询[EB/OL].[2023-02-04]. https://www.cnipa.gov.cn/col/col61/index.html#mark.
[2] 2021年高等学校科技统计资料汇编[EB/OL].[2023-02-01]. http://www.moe.gov.cn/s78/A16/A16_tjdc/202205/W020220527541531257082.pdf.
[3] 宋凯,冉从敬.企业视角下校企知识产权合作主题推荐模型研究[J].现代情报, 2022, 42(3):66-76.
[4] 宋凯,冉从敬.基于企业画像的高校专利个性化推荐[J].图书馆论坛, 2022, 42(9):123-131.
[5] ZEEBROECK N V. The puzzle of patent value indicators[J]. Economic of innovation and new technology, 2011, 20(1):33-62.
[6] LANJOUW J O, SCHANKERMAN M. Characteristics of patent litigation:a window on competition[J]. Rand journal of economics, 2001, 32(1):129-151.
[7] HARHOFF D, SCHERER F M, VOPEL K. Citations, family size, opposition and the value of patent rights[J]. Research policy, 2003, 32(8):1343-1363.
[8] KO N, JEONG B, SEO W, et al. A transferability evaluation model for intellectual property[J]. Computers & industrial engineering, 2019, 131:344-355.
[9] 吕晓蓉.专利价值评估指标体系与专利技术质量评价实证研究[J].科技进步与对策, 2014, 31(20):113-116.
[10] 万小丽,朱雪忠.专利价值的评估指标体系及模糊综合评价[J].科研管理, 2008(2):185-191.
[11] 吕航,林小爱."军转民"专利价值评估指标体系构建及实证研究[J].中国发明与专利, 2019, 16(6):22-26, 32.
[12] 刘妍.专利价值评估研究综述与趋势展望[J].图书情报工作,2022, 66(15):127-139.
[13] LONGSTAFF F A, SCHWARTZ E S. Valuing American options by simulation:a simple least-squares approach[J]. The review of financial studies, 2001, 14(1):113-147.
[14] TRAPPEY A J, TRAPPEY C V, WU C Y, et al. A patent quality analysis for innovative technology and product development[J]. Advanced engineering informatics, 2012, 26(1):26-34.
[15] 张金柱,韩永亮.基于多特征的技术融合关系预测及其价值评估[J].数据分析与知识发现, 2022, 6(S1):33-44.
[16] LAI Y H, CHE H C. Modeling patent legal value by extension neural network[J]. Expert systems with applications, 2009, 36(7):10520-10528.
[17] 吴洁,桂亮,刘鹏.基于图卷积网络的高质量专利自动识别方案研究[J].情报杂志, 2022, 41(1):88-95, 124.
[18] RESNICK P, VARIAN H R. Recommender systems[J]. Communications of the ACM, 1997, 40(3):56-58.
[19] PARK Y, PARK S, JUNG W, et al. Reversed CF:a fast collaborative filtering algorithm using a k-nearest neighbor graph[J]. Expert systems with applications, 2015, 42(8):4022-4028.
[20] JIANG Z F, YANG J, E H H, et al. A content-based recommendation algorithm with social tagging[J]. Computer engineering & software, 2015, 36(1):1-5.
[21] 冉从敬,宋凯.基于混合方法的高校专利个性化推荐模型构建[J].情报理论与实践, 2020, 43(10):93-98.
[22] ILHAMI M, SUHARJITO S. Film recommendation systems using matrix factorization and collaborative filtering[EB/OL].[2023-02-09]. https://ieeexplore.ieee.org/document/7048228/.
[23] 侯梦薇,卫荣,樊林,等.推荐系统在医疗领域的处理模型及应用研究[J].中国数字医学, 2019, 14(1):80-82.
[24] 梁孟华.基于用户兴趣图谱的数字档案资源交互推送服务研究[J].档案学研究, 2019(2):81-87.
[25] QIN J, ZHENG Q, TIAN F, et al. An emotion-oriented music recommendation algorithm fusing rating and trust[J]. International journal of computational intelligence systems, 2014, 7(2):371-381.
[26] TRAPPEY A, TRAPPEY C V, HSIEH A. An intelligent patent recommender adopting machine learning approach for natural language processing:a case study for smart machinery technology mining[J]. Technological forecasting and social change, 2021, 164:120511.
[27] CHUNG J, KO N, YOON J. Inventor group identification approach for selecting university-industry collaboration partners[J]. Technological forecasting and social change, 2021, 171:120988.
[28] 辛阳,文益民,曾德森,等.一种专利智能推荐算法设计与软件实现[J].计算机系统应用, 2013, 22(1):70-73.
[29] 何喜军,吴爽爽,武玉英,等.基于属性异构网络表示学习的专利交易推荐[J].情报学报, 2022, 41(11):1214-1228.
[30] 陈浩,张梦毅,程秀峰.融合主题模型与决策树的跨地区专利合作关系发现与推荐——以广东省和武汉市高校专利库为例[J].数据分析与知识发现, 2021, 5(10):37-50.
[31] ABRAHAM A, NATH B. Hybrid intelligent systems design:a review of adecade of research[R]. Melbourne:Monash University, 2000.
[32] WU Z H, PAN G, ZHENG N. Cyborg intelligence[J]. IEEE intelligent systems, 2013, 28(5):31-33.
[33] 吴朝晖,郑能干.混合智能:人工智能的新方向[J].中国计算机学会通讯, 2012, 8(1):59-64.
[34] HU Y, BIAN Y, WANG Y. Opening the black box of pharmaceutical patent value:an empirical analysis[J]. Drug information journal, 2008, 42(6):561-568.
[35] NI J Y, RONG S, CAROLINA O L U, et al. Valuation of pharmaceutical patents:a comprehensive analytical framework based on technological, commercial, and legal factors[J]. Journal of pharmaceutical innovation, 2015, 10(3):281-285.
[36] 文豪,胡晓阳.基于质量评价模型的专利质押价值评估体系修正研究[J].科技管理研究, 2022, 42(21):168-175.
[37] 张彪,吴红,高道斌.融合多维特征的高校专利价值分级方法及其实证研究[J].图书馆论坛, 2022, 42(11):42-49.
[38] 冉从敬,李旺.高校专利价值评估模型构建[J].情报杂志,2022, 41(7):65-70.
[39] 宋凯,冉从敬.高校专利许可/转让价值评估模型构建——从价值识别到价格预估[J/OL].图书馆论坛[2023-02-04]. http://kns.cnki.net/kcms/detail/44.1306.g2.20210830.1703.004.html.
[40] 宋凯.高校专利技术转移价值评估研究——基于熵权TOPSIS模型和梯度提升树算法[J].情报杂志, 2021, 40(7):52-57.
[41] 宋凯,冉从敬.基于指标计算与内容分析的高校专利价值评估方法研究[J].情报理论与实践, 2023, 46(2):136-144.
[42] 谢宗仁,吕建伟,林华.基于突变级数法的舰船作战能力综合评价[J].中国舰船研究, 2016, 11(3):5-10.
[43] Autogluon可自动执行机器学习的整个过程,有助于实现高精度算法[EB/OL].[2022-09-28]. https://www.xianjichina.com/special/detail_456616.html.
[44] AutoGluon:AutoML for text, image, and tabular data[EB/OL].[2022-08-01]. https://auto.gluon.ai/stable/index.html.
