Enterprise industry secondary industry multi-label classifier based on deep learning algorithm

Abstract

The invention discloses an enterprise industry secondary industry multi-label classifier based on a deep learning algorithm, which is composed of an acquisition module, a preprocessing module, a management module, a model establishment module, a training verification module, an input module and a display module. The acquisition module is used for acquiring enterprise operation scope information. The preprocessing module is used for preprocessing the enterprise operation scope information. The management module is used for manually indexing the enterprise operation scope information and making a training set, a verification set and a test set for multi-label classification training. The model establishment module is used for establishing an Albert + TextCNN model by using the training set. The training verification module is used for training the established Albert + TextCNN model and verifying an accuracy rate. The method has the beneficial effects that the multi-label classification of the secondary industry of the enterprise is realized, and the problem that the training time required by an existing method is too long is improved; and through modular design, single-label classification can be carried out, and the accuracy is greatly improved compared with that of the existing method.

Description

technical field [0001] The invention belongs to the technical field of NLP natural language processing, and in particular relates to a multi-label classifier for enterprise industry secondary industries based on a deep learning algorithm. Background technique [0002] NLP Natural Language Processing refers to developing applications or services that can understand human language. [0003] Existing technologies are mainly divided into three categories, namely unsupervised and semi-supervised learning methods, traditional machine learning methods and deep learning methods; among them: unsupervised learning methods and semi-supervised learning methods are usually artificially formulated standards and Extract features, such as using term frequency (TF), inverse document frequency (IDF), logistic regression (Logistic Regression), decision tree (Decision Tree), mutual information (Mutual Information), k-adjacent value (K-adjacent value), adaptive Enhancement (AdaBoost) and multi-...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an enterprise industry secondary industry multi-label classifier based on a deep learning algorithm to solve the problem that the existing technology proposed in the above background technology does not support the enterprise secondary industry classification and multi-label classification. The accuracy rate of the method used in the existing technology is not high, it is difficult to complete the multi-label classification task in the existing technology, and the existing technology is cumbersome, complicated, troublesome and difficult to maintain

Images