科技文献个性化服务系统在高校中的应用  

Application of individualized service system for scientific and technological documents in colleges and universities

作　　者：蒋晓玲 吴卫成 Jiang Xiaoling;Wu Weicheng(Collge of Computer and Software Engineering,Huaiyin Institute of Technology,Huaian 223001,China)

机构地区：[1]淮阴工学院计算机与软件工程学院,江苏淮安223001

出　　处：《江苏科技信息》2019年第8期47-49,共3页Jiangsu Science and Technology Information

基　　金：2018年度江苏省建设系统科技项目;项目编号:2018ZD269;2018年度淮阴工学院课堂教学改革实践专项课题;项目编号:2018021

摘　　要：为了提高文献推送的准确率,文章设计了一种基于Word2Vec的高校师生科技文献个性化服务系统,通过爬虫挖取以及基于Lucene的全文检索方案对数据进行检索,通过Word Embedding技术计算相似度,在一定程度上解决了系统数据稀疏性与冷启动问题。在120万篇文献中,实验取得了科技文献82%的推荐准确率,满足高校师生对文献检索的效率需求。In order to improve the accuracy of document push,this paper designs a Word2Vec-based personalized service system for scientific and technological documents of teachers and students in colleges and universities.Through crawler digging and full-text retrieval based on Lucene,the similarity degree is calculated by Word Embedding technology,which solves the problem of system data sparsity and cold start to some extent.In 1.2 million articles,the experiment has acquired science and technology.The literature recommendation accuracy is 82%,which meets the demands of the teachers and students for the efficiency of document retrieval.

关 键 词：个性化推荐 信息过载 用户建模 

分 类 号：G255[文化科学—图书馆学]