[目的/意义] 高校专利技术转移对象识别对提高专利转移转化率、有效促进科技与经济紧密结合、实现创新驱动发展具有积极意义。[方法/过程] 研究用企业技术需求表征市场需求，首先基于改进的技术树方法构建领域多维信息技术树，然后在对技术需求分类的基础上，分析技术需求文档的文本特征和需求内容特征，确定需求提取规则和需求类型，最后构建不同场景下的需求-技术匹配模型。[结果/结论] 以石墨烯领域专利数据对创建模型的有效性进行实证分析，结果表明基于技术需求去匹配能够满足条件的高校专利，以此来挖掘高校专利运营客户，是有的放矢推销高校专利、促进专利转化的有效手段。
[Purpose/significance] The identification of university patent transfer objects has positive significance for improving patent transfer conversion rate, effectively promoting the close integration of technology and economy, and achieving innovation-driven development.[Method/process] This paper used the technical requirements of enterprises to represent the market demand. Firstly, the domain multi-dimensional information technology tree was constructed based on the improved technology tree method, and then this paper analyzed the text characteristics and requirements content characteristics of the technical requirements document to determine the extraction rules and demand types based on the classification of technical requirements, and finally constructed the demand-technology matching model in different scenarios according to the demand type.[Result/conclusion] The feasibility of the method is verified by the patent data of graphene, and the results show that it is an effective means to strategically market college patents and promote patent conversion by matching the patents of colleges based on technical requirements to search for university patent operation customers.
[1] 中共中央文献研究室. 习近平关于科技创新论述摘编[M]. 北京:中央文献出版社,2016.
[2] 国家知识产权局.高校专利转化现状调查研究[EB/OL].[2019-11-04]. http://www.sipo.gov.cn/gwyzscqzlssgzbjlxkybgs/zlyj_zlbgs/1131773.htm.
[3] 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.
[4] 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, 2017:1-14.
[5] JI I, LIM H, PARK T Y. Exploring potential users of patents for technology transfer:utilizing patent citation data[J]. Procedia computer science, 2016, 91:211-220.
[6] 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.
[7] 罗建,史敏,文意纯,等.基于情报分析的技术转移对象识别方法研究——以重金属污水治理领域为例[J]. 情报工程, 2017, 3(6):14-21.
[8] 顾征, 李文. 创业型大学知识产权管理经典模式——斯坦福OTL四十年经验启示[J]. 高等工程教育研究, 2011(6):54-67.
[9] 国务院办公厅. 国务院办公厅关于推广第二批支持创新相关改革举措的通知.[EB/OL].[2019-11-04]. http://www.gov.cn/zhengce/content/2019-01/08/content_5355837.htm.
[10] 陈海秋. 德国洪堡大学专利战略的特点和启示[J]. 研究与发展管理, 2005, 17(4):94-97.
[11] 赵紫怡, 张悦馨, 王珊珊. 专利商业运营模式研究[J]. 技术与创新管理, 2017,38(6):626-634.
[12] 濮雪莲. 高校专利商业化中的企业需求驱动策略研究[J]. 技术经济与管理研究, 2015(1):41-44.
[13] 李昶, 唐恒, 金玉成, 等. 高校专利转化模式选择影响机制及演化模型[J]. 中国科技论坛, 2016(4):76-82.
[14] 唐恒, 朱伟伟. 基于客户价值导向的高校专利运营研究[J]. 技术经济与管理研究, 2012(12):31-34.
[15] 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):14-24.
[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] CASCINI G, ZINI M. Measuring patent similarity by comparing inventions functional trees[J]. IFIP international federation for information processing. 2008,277:31-42.
[18] HUNT R, LEE S, KANG S, et al. Applying technology road-maps in project selection and planning[J]. International journal of quality & reliability management, 2008, 25(1):39-51.
[19] 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.
[20] BLEI D M, NG A Y, JORDAN MI. Latent dirichlet allocation[J]. Journal of machine learning research, 2003(3):993-1022.
[21] 李平, 田朔. 市场需求对技术创新的门限特征分析[J]. 经济问题探索, 2014(10):18-25.
[22] 赵振霞, 陈红.我国石墨烯技术发展现状及趋势分析——基于专利数据[J]. 纺织导报,2016(9):40-43.
[23] 杨曦, 余翔, 刘鑫. 基于专利情报的石墨烯产业技术竞争态势研究[J]. 情报杂志, 2017,36(12):75-81.
[24] 百度AI开放平台. SDK文档-Python语言[EB/OL].[2019-10-14]. http://ai.baidu.com/docs#/NLP-Python-SDK/top.
