Heart failure text classification method and system based on TextCNN model and storage medium

• Main Author: LI DENG'AO
• Format: Patent
• Language: Chinese; English
• Published: 28.12.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention relates to the field of heart failure text classification methods, and discloses a heart failure text classification method and a system based on a TextCNN model and a storage medium, and the method comprises the steps: S1, collecting medical text data; S2, preprocessing the medical text data; S3, processing the preprocessed text data again through a Word2vec model and an LDA model, and obtaining and splicing word vectors; S4, putting the word vectors spliced in the S3 into a convolutional neural network TextCNN model for training; and S5, outputting a training result. According to the method, a convolutional neural network TextCNN model is used for heart failure text classification, firstly, obtained text data of heart failure and other diseases are preprocessed, then the preprocessed data are converted into vectors through a Word2vec model, meanwhile, a subject term vector set is obtained through the LDA model, is spliced with a vector processed by the Wor2vec model in the early stage, and fin