[目的/意义] 专利转移对象识别对高校有的放矢推送专利、提升专利转移效率、实现科技创新驱动经济发展具有重要意义。[方法/过程] 对高校专利信息和企业多源信息进行语义抽取，构建能够体现企业产品/技术纵向延伸需求的领域技术树，最后建立高校与企业间的技术-需求匹配模型，依其匹配程度进行高校专利转移客户识别。[结果/结论] 以我国气凝胶领域的高校专利为例对识别方法进行实证，结果表明该方法可准确识别出具有产品/技术纵向延伸需求的高校专利转移对象，应对供求信息不对称问题，是促进高校专利转移、实现科技创新与市场需求精准对接的有效手段。
[Purpose/significance] It is of great significance to identify the object of patent technology transfer for colleges and universities to push patents, improve the conversion rate of patents, and realize the economic development driven by scientific and technological innovation. [Method/process] This paper studied the semantic extraction of university patent information and enterprise multi-source information, constructed the domain technology tree that can reflect the vertical extension demand of enterprise products / technologies, and finally established the technology demand matching model between universities and enterprises, and carried out the customer identification of university patent transfer. [Result/conclusion] Taking the university patent in aerogel field as an example, the method of identification was verified. The results showed that the method can accurately identify the patent transfer objects with the product / technology vertical extension demand, and deal with the asymmetric information of supply and demand. It is an effective means to promote the transfer of patents in colleges and universities and achieve the precise docking of scientific and technological innovation with market demand.
[1] 陈立新. 2019年国家发明专利数据统计分析的结论与讨论之四——高校专利较强企业较弱[EB/OL].[2020-03-02]. http://wap.sciencenet.cn/blog-681765-1221354.html?mobile=1.
[2] 国家知识产权局. 2019年中国专利调查报告[EB/OL].[2020-03-20]. http://www.cnipa.gov.cn/zscqgz/1146807.htm.
[3] 张洁音.区域性知识市场网络化中介能力研究——以浙江技术市场为例[J].科技进步与对策,2015,32(13):42-46.
[4] ZHU X Z, KAI H U. The design of patent transaction confirmation system based on online technology marketplaces[J]. Journal of library and information science, 2019,4(8):35-43.
[5] WANG X, WANG Z, HUANG Y, et al. Identifying R&D partners through subject-action-object semantic analysis in a problem & solution pattern[J]. Technology analysis and strategic management, 2017,29(10):1-14.
[6] 张娴,许海云,方曙,等.专利技术组合机会与合作潜力研究[J].情报杂志,2015,34(7):39-46.
[7] PARK I, JEONG Y, YOON B, et al. Exploring potential R&D collaboration partners through patent analysis based on bibliographic coupling and latent semantic analysis[J]. Technology analysis & strategic management, 2015,27(7):759-781.
[8] 许海云,王超,董坤,等.基于创新链中知识溢出效应的产学研R&D合作对象识别方法研究[J].情报学报,2017,36(7):682-694.
[9] SEO W, YOON J, PARK H, et al. Product opportunity identification based on internal capabilities using text mining and association rule mining[J]. Technological forecasting & social change, 2016,105:94-104.
[10] 伊惠芳,吴红.多级需求分析视域下高校专利转移对象识别研究——以石墨烯为例[J].图书情报工作, 2020,64(12):118-126.
[11] 杨公朴,夏大慰.现代产业经济学[M].上海:上海财经大学出版社,2002:50-80.
[12] 李万立.旅游产业链与中国旅游业竞争力[J].经济师,2005(3):123-124.
[13] 王秋菊.产业链内涵及结构分析[J].物流科技,2012,35(5):89-91.
[14] 丰米宁,魏凤,李健,等.产业链视角下的主题识别与技术演化研究——以3D打印领域为例[J].情报杂志,2020,39(8):46-52,62.
[15] 李昌,吴红,伊惠芳,等.基于改进LDA主题模型的中日美氢能产业链技术布局研究[J].情报杂志,2019,38(7):78-84,110.
[16] 翟东升,夏军,张杰,等.基于专利特征抽取的技术树构建方法研究[J].情报学报,2015,34(7):717-724.
[17] YOON B, PHAAL R, PROBERT D. Morphology analysis for technology road mapping:application of text mining[J].R&D management, 2008,38(1):51-68.
[18] CHOI S, PARK H, KANG D, et al. An SAO-based text mining approach to building a technology tree for technology planning[J]. Expert systems with applications, 2012,39(13):11443-11455.
[19] 翟东升,郭程,张杰,等.基于专利的企业潜在研发伙伴推荐方法研究[J].数据分析与知识发现,2017,1(3):10-20.
[20] FANTONI G, APREDA R, DELL'ORLETTA F, et al. Automatic extraction of function-behaviour-state information from patents[J].Advanced engineering informatics,2013,27(3):317-334.
[21] 姜春涛.运用图示法自动提取中文专利文本的语义信息[J].图书情报工作,2015,59(21):115-122.
[22] DONGHWA K, DEOKSEONG S, SUHYOUN C, et al. Multi-co-training for document classification using various document representations:TF-IDF, LDA, and Doc2Vec[J]. Information sciences,2018,477:15-29.
[23] AI-ANZI F S, ABUZEINA D. Towards an enhanced arabic text classification using cosine similarity and latent semantic indexing[J]. Journal of king saud university computer & information sciences, 2017,29(2):189-195.
