基于深度学习的数字图书馆文本分类研究

Text Classification of Digital Library Based on Deep Learning

【目的/意义】引入人工智能领域中的深度学习方法来解决数字图书馆中传统文本分类的缺陷,这既是人工智能领域研究的重点,也是图书馆领域关注的热点问题。【方法/过程】在对数字图书馆传统文本分类进行系统梳理的基础上,提出基于深度学习的数字图书馆文本分类模型,利用词向量的方法对文本特征进行表示,采用深度学习模型中的卷积神经网络提取文本信息的本质特征,并进行了实验验证。【结果/结论】实验测试表明,基于深度学习的文本分类模型可以有效地提高数字图书馆文本分类的准确率和召回率,不仅可以提高数字图书馆内部业务的智能化程度,还可以提高数字图书馆信息服务的效率和质量。

【Purpose/significance】This paper introduces deep learning methods in the field of artificial intelligence to solve the defects of traditional text classification in digital libraries.This is not only the focus of research in the field of artificial intelligence,but also a hot issue in the library field.【Method/process】On the basis of the systematic summarization of the traditional text classification in digital libraries,this paper puts forward a digital library text classification model based on deep learning,it uses the word embedding method to represent text features,and it uses the convolutional neural network in the deep learning model to extract the essential features of the text and it has been experimentally verified it.【Result/conclusion】Experimental tests show that the text classification model based on deep learning can effectively improve the accuracy and recall of text classification in digital libraries.It can not only improve the intelligence of the digital library internal business,but also improve the efficiency and quality of digital library information services.