智慧图书馆图书分类模型技术研究综述  

Summary of Research on Book Classification Model Technology in Smart Library

作　　者：沈雅婷 邵莹 卞恺 SHEN Ya-ting;SHAO Ying;BIAN Kai(Nanjing University of Science and Technology ZiJin College,Nanjing 210023,Jiangsu)

机构地区：[1]南京理工大学紫金学院计算机学院,江苏南京210023

出　　处：《电脑与电信》2021年第12期9-13,共5页Computer & Telecommunication

基　　金：江苏省高等学校基础科学(自然科学)研究项目资助,项目编号:21KJB520009;江苏高校哲学社会科学研究项目资助,项目编号:2021SJA2253;全国高等院校计算机基础教育研究会计算机基础教育教学研究项目资助,项目编号:2021-AFCEC-332;南京理工大学紫金学院科学研究项目资助,项目编号:2021ZRKX0401004;江苏省大学生创新创业项目资助,项目编号:202113654020Y。

摘　　要：比较分析近年来三种图书分类研究模型:基于集成学习的分类模型、基于双向LSTM的分类模型和基于向量空模型的分类模型。在相同数据集上测试,后两者分类模型的准确率相近,它们相较于第一种模型的准确率高出约2%~8%,其中基于向量空模型的分类模型用时短;而基于双向LSTM的分类模型的准确率有提升空间,会随训练次数的增加而逐步上升,但所耗时间也会增加。这几种模型对后期智慧图书馆图书分类起着不可忽视的启示作用,学者们可以根据需要选择使用上述模型,对于不同分类算法的研究,有机会对分类的准确度、速度实现突破。This paper compares and analyzes three research models of book classification in recent years, which are the classification model based on ensemble learning, the classification model based on bidirectional LSTM and the classification model based on vector space model. Tested on the same data set, the accuracy of the latter two classification models is similar, and their accuracy is about 2% ~ 7% higher than that of the first model, in which the classification model based on vector space model takes less time.The accuracy of the classification model based on bidirectional LSTM can be improved, which will gradually increase with the increasing of training times, but the time will also increase. These models play an important role in the book classification of the later Smart Library. Scholars can choose to use the above models according to their needs. For the research of different classification algorithms, they have the opportunity to make a breakthrough in the accuracy and speed of classification.

关 键 词：图书分类 特征提取 集成学习 双向LSTM模型 向量空模型 

分 类 号：G254.3[文化科学—图书馆学] TP181[自动化与计算机技术—控制理论与控制工程]