Document classification method of multi-scale image convolutional neural network, electronic equipment and storage medium

• Main Authors: LIU JIAOYANG, XU YAOQUN, WANG YUEMAO, YAN LIUQIAN, ZHANG YUHANG, ZHANG YU
• Format: Patent
• Language: Chinese; English
• Published: 22.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a document classification method of a multi-scale graph convolutional neural network, electronic equipment and a storage medium, and belongs to the technical field of document classification. In order to improve the document classification efficiency, documents of file types are collected, keyword extraction is carried out, the strong and weak relation between keyword nodes is calculated through logic and operation, and a data set is established; data cleaning and data preprocessing are carried out, and then a processed data set is divided into a training set, a verification set and a test set; constructing a multi-scale image convolutional neural network document classification model fused with an attention mechanism; training the multi-scale image convolutional neural network document classification model of the fusion attention mechanism by using the training set to obtain a trained multi-scale image convolutional neural network document classification model of the fusion attention