摘要
【目的/意义】随着网络信息技术的发展及国家对技术转移的政策支持,大量的在线技术交易需求产生。在线技术转移服务平台作为技术供需交易的媒介,供需双方可以在平台上发布大量的技术供需文本信息,提高技术供需文本匹配效率,有助于提高技术交易成功率,促进技术转移。【方法/过程】在分析传统文本匹配方法的基础上,从基于关键词的匹配方法、基于句法分析和文本结构的匹配方法、基于深度学习的匹配方法和基于多维度视角的匹配方法四个方向对目前在线技术供需文本匹配方法现状进行梳理。【结果/结论】大多数研究都融合了多种匹配方法,从多维度视角进行匹配是研究发展趋势。在技术供需文本匹配未来研究中,除了继续将深度学习方法融合到已有的各种方法中,还应该从多维度、跨模态和可解释性方向来提高技术供需文本匹配效率。【创新/局限】本文将技术文本匹配方法进行归纳总结,能对技术文本的匹配方法提供参考,但现实中技术匹配还应该考虑其他影响技术转移的因素。
【Purpose/significance】With the development of network information technology and national policy support for technologytransfer, a large number of online technology transaction needs arise. As the intermediary of technology supply and demand transac-tion, a large number of text information of technology supply and demand can be released on the platform. Improving the efficiency oftext matching of technology supply and demand is helpful to improve the success rate of technology transaction and promote technolo-gy transfer.【Method/process】Based on the analysis of traditional text matching methods, this paper combs the current situation of on-line technology supply and demand text matching methods from four directions: keyword based matching method, syntactic analysisand text structure based matching method, deep learning based matching method and multi-dimensional perspective based matchingmethod.【Result/conclusion】The results show that most of the studies have integrated a variety of matching methods, and matchingfrom a multi-dimensional perspective is the research trend. In the future research of technology supply and demand text matching, inaddition to continuing to integrate deep learning methods into existing methods, researchers should also improve the efficiency of tech-nology supply and demand text matching from the directions of multi-dimensional, cross modal and interpretable.【Innovation/limita-tion】This paper summarizes the technology text matching method, which can provide reference for the technology text matching meth-od, but technology matching should also consider other factors affecting technology transfer in reality.
作者
余辉
梁镇涛
谢豪
YU Hui;LIAGN Zhen-tao;XIE Hao(Center for Studies of Information Resources,Wuhan University,Wuhan 430012,China)
出处
《情报科学》
CSSCI
北大核心
2021年第7期177-185,共9页
Information Science
基金
国家重点研发计划项目“长江中游城市群综合科技服务平台研发与应用示范”(2018YFB1404300)
国家自然科学基金重大课题“国家安全大数据综合信息集成与分析方法”(71790612)
“大数据环境下基于特征本体学习的无监督文本分类方法研究”(71571064)。
关键词
技术转移
技术供需文本
文本表示
供需匹配
技术推荐
technology transfer
technological text for supply and demand
textrepresentation
supply and demand matching
bag of words
technical recommendation
