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

Text classification method based on LSTM neural network model

A neural network model and text classification technology, applied in the field of text classification based on the LSTM neural network model, can solve the problems of gradient disappearance and gradient explosion, and achieve the effect of reducing difficulty, high accuracy, and solving the problems of gradient disappearance and gradient explosion.

Pending Publication Date: 2020-07-14
SHANGHAI MUNICIPAL ELECTRIC POWER CO
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention classifies the text through the LSTM neural network model, which can solve the problems of gradient disappearance and gradient explosion in the traditional network, and has high accuracy

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
  • Text classification method based on LSTM neural network model
  • Text classification method based on LSTM neural network model
  • Text classification method based on LSTM neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] A text classification method based on the LSTM neural network model proposed by the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Advantages and features of the present invention will be apparent from the following description and claims. It should be noted that the drawings are all in a very simplified form and use imprecise ratios, which are only used to facilitate and clearly assist the purpose of illustrating the embodiments of the present invention.

[0027] The present invention proposes a kind of text classification method based on LSTM neural network model, comprises the following steps:

[0028] S1. Model the text in the document collection through the vector space model to obtain the vector space of the text in the document collection;

[0029] The Chinese lexical analysis system is used to preprocess the text in the document collection and convert it into a form that can be...

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 discloses a text classification method based on an LSTM neural network model, and the method comprises the following steps: S1, carrying out the modeling of texts in a document set through a vector space model, and obtaining the vector space of the texts in the document set; S2, extracting features of vector spaces of texts in the document set through a mutual information algorithm to obtain feature vectors of the texts in the document set; S3, training the LSTM neural network model through the feature vector of the text of the known text category; and S4, taking the feature vector of the text to be detected as the input of the LSTM neural network model to obtain the classification result of the text. The text is classified through the LSTM neural network model, the problemsof gradient disappearance and gradient explosion existing in a traditional network can be solved, and high accuracy is achieved.

Description

technical field [0001] The invention relates to data processing technology, in particular to a text classification method based on an LSTM neural network model. Background technique [0002] Today, with the rapid development of the power Internet of Things, there are a large number of electronic texts in the power grid system, such as power grid customer information, power grid business data, etc. However, due to the chaotic management of current power grid information and the lack of a unified data model, the same information may have textual differences due to different business formats, and there is no unified standard, which will seriously affect the efficiency and cost of various businesses in the power grid system. Therefore, it is very meaningful to search and extract information from the massive electronic texts in the power grid system, and then further classify them. [0003] Text classification (Text Classification) is one of the main research problems in Natural...

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): G06F16/33G06F16/35G06K9/62G06N3/04G06N3/08
CPCG06F16/35G06F16/3344G06N3/084G06N3/044G06N3/045G06F18/241
Inventor 陈琰陈晓露俞睿默陆正嘉刘逸逸邱继芸周晓鹂黄静韬
Owner SHANGHAI MUNICIPAL ELECTRIC POWER CO