Text classification method and device, terminal and storage medium

A text classification and training sample technology, applied in the computer field, can solve problems such as inaccurate classification results

Pending Publication Date: 2019-06-28
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a text classification method, device, terminal and computer-readable st

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 and device, terminal and storage medium
  • Text classification method and device, terminal and storage medium
  • Text classification method and device, terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0039] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0040] Please see figure 1 , figure 1It is a schematic diagram of the hardware structure of the terminal provided by the present invention. The terminal may be a server or a computer, including components such as a memory 10 and a processor 20 . In the terminal, the processor 20 is connected to the memory 10, and a computer program is stored in the memory 10, and the computer program is executed by the processor 20 at the same time, so as to implement the steps of the corresponding method in the following embodiments.

[0041] The memory 10 can be used to store software programs and various data. The memory 10 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one function-required application program (such as using an optimize...

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 and device based on a neural network model, a terminal and a storage medium, and the method comprises the steps: searching a learning rate according to the gradient of an optimizer based on a random gradient descent and momentum method in the deep learning training process of the text classification model, and then improving the attenuation ratein the optimizer according to the reduction ratio of the learning rate; Based on the improved attenuation rate, the searched learning rate and the gradient, optimizing the neural network model through an optimizer until the model completes optimization training; And finally, inputting the text word vector corresponding to the target text into the neural network model subjected to optimization training to obtain a text classification result. In the text classification model learning and training process, a neural network model is optimized by combining a momentum method, random gradient descent and dynamic adjustment of the learning rate and the attenuation rate in an optimizer, the convergence speed and the execution effect of the model are helped to be increased, and then the accuracy ofa classification result during text classification is improved.

Description

technical field [0001] The present invention relates to the field of computers, in particular to a neural network model-based text classification method, device, terminal and computer-readable storage medium. Background technique [0002] The current text classification model based on deep learning is to input the word vector into the trained neural network model to obtain the classification result of the word vector. In order to make the classification results more realistic, it is necessary to train the neural network model before text classification, and the most important link in the model training process is to optimize the neural network model through the optimizer. However, at this stage, the optimization method of deep learning models based on text classification mostly adopts the method of SGD (Stochastic Gradient Descent, stochastic gradient descent), which can achieve good accuracy, that is, low error rate, to a certain extent when the model convergence speed is i...

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): G06F16/35G06K9/62
CPCY02T10/40
Inventor 肖京徐亮金戈
Owner PING AN TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products