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

Method for establishing model data set and cloud system

A technology of model data and establishment methods, applied in the field of deep learning, can solve the problems of high manpower and time costs, and achieve the effect of improving efficiency and accuracy

Inactive Publication Date: 2018-06-22
CLOUDMINDS BEIJING TECH CO LTD
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention expects to provide a method for establishing a model data set and a cloud system to solve the problem that existing classification methods based on deep learning rely too much on manual labeling, resulting in labor and time costs for manual labeling and verification. higher technical issues

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
  • Method for establishing model data set and cloud system
  • Method for establishing model data set and cloud system
  • Method for establishing model data set and cloud system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] figure 1 It shows the principle diagram of the method for establishing the model data set in the first embodiment of the present application, as figure 1 As shown, the method includes:

[0033] Step 101: cluster the data in the data set according to the selected data features, and classify and mark the data in the data set according to the clustering result.

[0034] Step 102: Train the initialized classification model according to the classified and labeled data set to obtain a trained classification model.

[0035] Step 103: Test the trained classification model, and build a model data set according to the test results.

[0036] During implementation, the execution subject of the above steps may be a cloud server, and the cloud server performs feature extraction on the data in the data set according to the features in the preset feature library, uses a clustering algorithm to cluster the extracted data features, and according to the clustering results Automatically...

Embodiment 2

[0079] Based on the same inventive concept, the embodiment of this application also provides a cloud system for establishing a model data set. Since the problem-solving principle of these devices is similar to a method for establishing a model data set, the implementation of these devices can be found in the method. implementation, the repetition will not be repeated.

[0080] image 3 It shows the cloud system architecture diagram for establishing the model data set in the second embodiment of the present application, as shown in image 3 As shown, the establishment of the model data set cloud system 300 may include:

[0081] The clustering server 301 is configured to cluster the data in the data set according to the selected data characteristics, and classify and mark the data in the data set according to the clustering result;

[0082] The training server 302 is used to train the initialization classification model according to the data set after classification and markin...

Embodiment 3

[0100] Based on the same inventive concept, an electronic device is also provided in the embodiment of the present application. Since its principle is similar to the establishment of a model data set, its implementation can refer to the implementation of the method, and the repetition will not be repeated.

[0101] Figure 4 shows a schematic structural diagram of the electronic device in Embodiment 3 of the present application, as Figure 4 As shown, the electronic device includes: a transceiver device 401, a memory 402, one or more processors 403; and one or more modules, the one or more modules are stored in the memory and are configured to Executed by the one or more processors, the one or more modules include instructions for performing steps in any of the above methods.

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 application provides a method and a cloud system for establishing a model data set, and the said method comprises: carrying out training on an initialization classification model according to theclassified data set to obtain a trained classification model; the trained classification model is tested and the model data set is established according to the test results. The application can utilize the finally determined model data set used for realizing the classification identification, thereby eliminating the labor and time cost consumed by manual annotation and verification, and realizingthe automatic labeling of the model data set, and effectively improving the efficiency and the accuracy of the classified identification.

Description

technical field [0001] This application relates to the field of deep learning technology, in particular to a method for establishing a model data set and a cloud system. Background technique [0002] In recent years, compared with traditional classification methods, classification methods based on deep learning have made significant breakthroughs in classification effects and high classification accuracy. As deep learning networks such as ResNet and DenseNet have been continuously proposed, based on deep learning The classification method has gradually become the main trend of classification applications. [0003] The classification method based on deep learning mainly uses a huge training set to continuously train model parameters through forward transmission and reverse transmission in the classification model to obtain a trained classification model to achieve the ideal classification effect, and the ideal classification effect is mainly Rely on the representativeness of...

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): G06K9/62
CPCG06F18/23G06F18/24G06F18/214
Inventor 梁昊南一冰廉士国
Owner CLOUDMINDS BEIJING TECH CO LTD
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