Yao, MingyuanMingyuanYaoSun, HaoranHaoranSunLiang, ShengbinShengbinLiangShen, YanqingYanqingShenYukie, NikiNikiYukie2024-04-022024-04-022023978-3-031-12127-2https://dspace.usj.edu.mo/handle/123456789/5636Medical classification is affected by many factors, and the traditional medical classification is usually restricted by factors such as too long text, numerous categories and so on. In order to solve these problems, this paper uses word vector and word vector to mine the text deeply, considering the problem of scattered key features of medical text, introducing long-term and short-term memory network to effectively retain the features of historical information in long text sequence, and using the structure of CNN to extract local features of text, through attention mechanism to obtain key features, considering the problems of many diseases, by using hierarchical classification. To stratify the disease. Combined with the above ideas, a deep DLCF model suitable for long text and multi-classification is designed. This model has obvious advantages in CMDD and other datasets. Compared with the baseline models, this model is superior to the baseline model in accuracy, recall and other indicators.enBook Section