Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-language inter-translation method and system based on convolutional neural network

A convolutional neural network and multilingual technology, applied in the field of multilingual translation, can solve the problem of low recognition rate of two-dimensional data, achieve high recognition rate, reduce complexity, and avoid overfitting

Inactive Publication Date: 2020-02-14
东营职业学院
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a multilingual intertranslation method and system based on convolutional neural networks to solve the problems in the prior art presented in the above-mentioned background technology. The current development of convolutional neural networks recognizes two-dimensional data such as images, languages, and texts. low rate problem

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
  • Multi-language inter-translation method and system based on convolutional neural network
  • Multi-language inter-translation method and system based on convolutional neural network
  • Multi-language inter-translation method and system based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0081] This embodiment: as figure 1 As shown, a multilingual translation method based on convolutional neural network, including:

[0082] Feature extraction S101: Input the local receptive field of the previous layer into the local neuron set of the convolution layer, and extract the convolution layer through the convolution operation function of the convolution filter after inputting the local neuron set of the convolution layer local features;

[0083] The convolution operation function is:

[0084]

[0085] The Xi is a local neuron set Xi (i=1, 2, 3...nxn) of the convolutional layer;

[0086] The Wi is the value corresponding to the convolution filter of nxn;

[0087] The b is a fixed offset of the convolution filter;

[0088] The y is a local feature formed by the convolution layer locally through a convolution operation function;

[0089] Feature mapping S102: mapping local features into normalized values ​​through an activation function;

[0090] The activation...

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 belongs to the technical field of multilingual inter-translation, and especially relates to a multi-language inter-translation method based on a convolutional neural network. The invention further provides a multi-language inter-translation system based on the convolutional neural network. The method is characterized by inputting the local receiving domain of the previous layer intothe local neuron set of the convolution layer; extracting the convolution layer local features of the input convolution layer local neuron set through a convolution operation function of a convolutionfilter. According to the method, the problem that the recognition rate of convolutional neural network development on two-dimensional data such as images, languages and texts is low in the prior artis solved, and the method has the beneficial technical effects of being high in recognition rate, avoiding overfitting, reducing vector complexity and being suitable for a multilingual inter-translation underlying algorithm.

Description

technical field [0001] The invention belongs to the technical field of multilingual mutual translation, and in particular relates to a multilingual mutual translation method based on a convolutional neural network. The invention also provides a multilingual mutual translation system based on a convolutional neural network. Background technique [0002] Currently, in machine learning, Convolutional Neural Network is a deep feedforward artificial neural network that has been successfully applied to image recognition, Convolutional Neural Network, is a unary feedforward neural network, artificial neural to respond to surrounding units, Large image processing is possible. The convolutional neural network includes a convolutional layer and a pooling layer. In the prior art, there is a problem that the current development of the convolutional neural network has a low recognition rate for two-dimensional data such as images, languages, and texts. Contents of the invention [000...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/58G06N3/04
CPCG06N3/045
Inventor 李金凤
Owner 东营职业学院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com