Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic text classification method

An automatic classification and text technology, applied in neural learning methods, special data processing applications, instruments, etc., can solve problems such as weak feature extraction ability and poor noise processing ability, and achieve the effect of improving accuracy and anti-noise ability.

Inactive Publication Date: 2018-01-19
UNIV OF SCI & TECH BEIJING
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide an automatic text classification method to solve the problems of poor noise processing ability and weak feature extraction ability existing in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic text classification method
  • Automatic text classification method
  • Automatic text classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.

[0038] Aiming at the existing problems of poor noise processing ability and weak feature extraction ability, the invention provides an automatic text classification method.

[0039] Such as figure 1 As shown, the automatic text classification method provided by the embodiment of the present invention includes:

[0040] S101, acquiring text to be classified;

[0041] S102, using a denoising auto encoder (Denoising Auto Encoder, DAE) and a restricted Boltzmann machine (Restricted Boltzmann Machine, RBM), constructing a denoising deep neural network model (Denoising DeepNeural Network, DDNN);

[0042] S103, using the constructed noise reduction deep neural network model to perform feature extraction on the acquired text to be classified;

[0043] S104, a...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an automatic text classification method, and aims at improving the correctness and anti-noise capacity of text classification. The method comprises the following steps of: obtaining a to-be-classified text; constructing a denoising deep neural network model by adoption of a denoising automatic encoder and a restricted Boltzmann machine; carrying out feature extraction on theobtained to-be-classified text by utilizing the constructed denoising deep neural network model; and carrying out automatic classification by utilizing a Softmax regression algorithm according to thefeature extraction result. The method relates to the field of text classification.

Description

technical field [0001] The invention relates to the field of text classification, in particular to an automatic text classification method. Background technique [0002] In network information, text occupies an important position as the main information bearing way. Text classification (Text Classification, TC) is to use computers to automatically classify and mark text sets or other entities and objects according to certain classification systems or standards. At present, deep learning has been successfully applied to a variety of pattern classification problems. Using deep learning-based methods can better mine the complex semantic relationships contained in text. [0003] However, in the prior art, a single method is generally used to classify texts, which has weak feature extraction ability and poor processing ability for noise data, resulting in low accuracy of classification results. Contents of the invention [0004] The technical problem to be solved by the prese...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/30G06F17/27G06N3/08
CPCG06N3/088G06N3/047G06N3/044G06N3/045
Inventor 张媛钰阿孜古丽谢永红张德政栗辉李春苗
Owner UNIV OF SCI & TECH BEIJING