Check patentability & draft patents in minutes with Patsnap Eureka AI!

Natural language processing method based on neural network and electronic equipment

A technology of natural language processing and neural network, applied in the field of natural language processing methods based on neural network and electronic equipment, can solve problems such as waste of computing resources and time, reduce the amount of calculation, reduce waste of computing resources and time, improve Effect of recognition processing precision

Inactive Publication Date: 2020-12-11
ECARX (HUBEI) TECHCO LTD
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the field of natural language processing, the length of the user sentence (that is, the content of the user's speech) as input data is not fixed, and is usually much smaller than the set maximum value. In this case, if still according to the set maximum value to perform convolution calculation, which will cause a waste of computing resources and time

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
  • Natural language processing method based on neural network and electronic equipment
  • Natural language processing method based on neural network and electronic equipment
  • Natural language processing method based on neural network and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049]Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0050] Convolutions are widely used in neural networks. Convolution calculation is essentially a process of multiplying and accumulating. 2D matrix convolution is the most widely used convolution in machine learning. Its calculation formula is as follows: output=W*input+bias, where output is the output data of convolution, input is the input data of convolution, and W is convolution Product kernel, bias is the preset bias value. T...

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 a natural language processing method based on a neural network and electronic equipment. According to the natural language processing method, length information of an input statement reflecting the actual length of the input statement is mainly introduced, and multiplication operation between a word vector matrix and a convolution kernel is executed for corresponding times according to the length information of the input statement in convolution calculation; The fixed-length convolution based on the fixed preset sentence length in the prior art is converted into the variable-length convolution based on the actual length of the input sentence, so that the calculation amount is greatly reduced, the calculation speed is remarkably increased, and the waste of calculationresources and time is reduced.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a neural network-based natural language processing method and electronic equipment. Background technique [0002] Neural networks (especially convolutional neural networks) have been widely used in the field of natural language processing. The essence of convolution is the process of using a kernel function to extract features from input data, and the output of convolution is the extracted features (represented by a mapping matrix). The input data for convolution can be in NHWC format, namely [batch, in_height, in_width, in_channels], including batch (batch), height (height), width (width), channels (channels) four dimensions, where the height dimension represents The length of the input data. [0003] In the prior art, during the inference and training process of the convolutional neural network, the height, width and number of input channels of the convolution...

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): G06F40/35G06F16/35G06F16/31G06N3/04
CPCG06F40/35G06F16/353G06F16/316G06N3/045
Inventor 黄海荣李林峰王靖宇
Owner ECARX (HUBEI) TECHCO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com