Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Data classification method and device and terminal equipment

A data classification and data technology, applied in the field of deep learning, to achieve the effect of improving accuracy

Active Publication Date: 2019-09-06
SHENZHEN INSTITUTE OF INFORMATION TECHNOLOGY
View PDF12 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a data classification method, device and terminal equipment to solve the problem of how to improve the accuracy of data classification 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
  • Data classification method and device and terminal equipment
  • Data classification method and device and terminal equipment
  • Data classification method and device and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] figure 1 A schematic flow chart of the first data classification method provided by the embodiment of the present application is shown, and the details are as follows:

[0036] In S101, the first data to be tested is input into a neural network based on data augmentation, wherein the neural network based on data augmentation includes a transformation network, a prediction network, and a decision layer, and the transformation network and the prediction network are both Neural Networks with Deep Learning Capabilities.

[0037] The first data to be tested x refers to data to be classified, and the first data to be tested may be image data, voice data, text data, etc. to be classified. The neural network based on data augmentation is specifically an end-to-end deep neural network with sample data augmentation function, which is composed of transformation network, prediction network and decision-making layer, such as figure 2 shown. Among them, both the transformation ne...

Embodiment 2

[0058] Figure 4 It shows a schematic flowchart of the second data classification method provided by the embodiment of the present application, and the details are as follows:

[0059] In S401, original sample data is acquired, wherein the original sample includes first original sample data carrying a first result label and second original sample data carrying a second result label.

[0060] Obtain original sample data. For example, when the first data to be tested for classification is image data, a preset number of target images can be collected as original sample data by means of image acquisition, and the original sample data can be made Carry the corresponding result label. Alternatively, a preset number of original sample data carrying result tags can be obtained by downloading and reading an existing target image database. Among them, carrying the first result label y i The first original sample x i and carry the second result label y j The second original sample x...

Embodiment 3

[0088] Figure 6 It shows a schematic flowchart of the third data classification method provided by the embodiment of the present invention. The data classification method in the embodiment of the present invention is specifically a human skeleton behavior recognition method, and the first data to be tested is specifically the first human body image data to be tested. , the second data to be tested is specifically the second human body image data to be tested, and the classification result is specifically the result of human skeleton behavior recognition, as detailed below:

[0089] In S601, input the first human body image data to be tested into the neural network based on data augmentation, wherein the neural network based on data augmentation includes a transformation network, a prediction network and a decision layer, and the transformation network and the prediction network Both are neural networks with deep learning capabilities.

[0090] The first human body image data...

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 method is suitable for the technical field of deep learning. Provided are a data classification method and device, and terminal equipment, the method comprises steps of inputting first to-be-tested data into a neural network based on data augmentation, the neural network based on data augmentation comprising a transformation network, a prediction network, and a decision layer, the transformation network and the prediction network being neural networks with deep learning capabilities; obtaining second to-be-tested data through the conversion network according to the first to-be-tested data;respectively obtaining a first prediction result corresponding to the first to-be-tested data and a second prediction result corresponding to the second to-be-tested data through the prediction network according to the first to-be-tested data and the second to-be-tested data; and according to the first prediction result and the second prediction result, obtaining a final classification result ofthe first to-be-tested data through the decision layer. According to the embodiment of the invention, the data classification accuracy can be improved.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to a data classification method, device and terminal equipment. Background technique [0002] With the development of deep learning technology, deep neural networks are widely used in various data processing such as image recognition, image segmentation, speech recognition, and gesture recognition. The key to deep neural network processing of these data lies in the detection and classification of the object to be tested. Therefore, whether it is the recognition of data such as images or voices, or image segmentation, it can be collectively referred to as the classification of data by deep neural networks. [0003] Using a deep neural network to classify data often requires collecting and labeling a large amount of sample data in advance. However, the acquisition of a large number of sample data is usually time-consuming and laborious, and sample data is also diffic...

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): G06K9/62
CPCG06F18/25G06F18/241
Inventor 孟凡阳柳伟梁永生杨火祥黄玉成王昌伟
Owner SHENZHEN INSTITUTE OF INFORMATION TECHNOLOGY
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
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