Certificate classification model training method, certificate classification method, certificate classification device and medium

A classification model and certificate technology, applied to computer parts, character and pattern recognition, instruments, etc., can solve the problems of poor classification accuracy of machine learning models, inability to obtain large data volume electronic certificate samples, and small data volume of electronic certificate samples

Pending Publication Date: 2022-03-18
ONE CONNECT SMART TECH CO LTD SHENZHEN
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the electronic document classification scenario, some related technologies use machine learning models for classification, but the inventor found that: before using electronic document samples to train machine learning models, it is necessary to perform data enhancement processing on electronic document samples, but the existing The dat

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
  • Certificate classification model training method, certificate classification method, certificate classification device and medium
  • Certificate classification model training method, certificate classification method, certificate classification device and medium
  • Certificate classification model training method, certificate classification method, certificate classification device and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025]The present invention provides a training method for a certificate classification model, which pre-divides N types of data enhancement algorithm sets and sets the order of use of these data enhancement algorithm sets, and then determines from the N types of data enhancement algorithm sets according to the order of use. The data enhancement algorithm set for data enhancement processing is performed on the certificate sample, and the data enhancement processing is performed on the certificate sample according to each determined data enhancement algorithm set to obtain the target certificate sample, and the above data enhancement operations are performed on multiple certificate samples to make the final Obtaining target document samples has complex and diverse features, so when training the document classification model based on these target document samples, different types of features can be obtained based on a small amount of data, so that the document classification model...

Embodiment 2

[0065] figure 2 Shows a flow chart of the certificate classification method provided by Embodiment 2 of the present invention, as figure 2 As shown, the method includes step M1 to step M5, wherein:

[0066] Step M1, obtaining the certificate to be classified.

[0067] The certificate to be classified can be an electronic certificate obtained directly by taking a photo, or the electronic certificate obtained by taking a photo can be used as a certificate sample and then executed as a target certificate sample obtained through steps S1 to S3, or it can be taken by taking a photo through an existing data enhancement method Obtained electronic certificates are obtained after performing data enhancement processing.

[0068] Step M2, extracting the features of the documents to be classified through m convolutional layers of the document classification model, and obtaining m second feature vectors, wherein m is a positive integer greater than or equal to 2, and the document class...

Embodiment 3

[0083] Embodiment 3 of the present invention also provides a training device for a certificate classification model. The training device for a certificate classification model corresponds to the training method for a certificate classification model provided in Embodiment 1 above. The corresponding technical features and technical effects are described in this paper. The details will not be described in the embodiment, and the relevant part can refer to the first embodiment above. specifically, image 3 A block diagram of a training device for a certificate classification model provided by Embodiment 3 of the present invention is shown. Such as image 3 As shown, the training device 300 of the certificate classification model includes an acquisition sample module 301, an acquisition data set module 302, an enhancement processing module 303 and a model training module 304, wherein:

[0084] Obtaining a sample module 301, configured to obtain a certificate sample set, and extr...

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 relates to the technical field of artificial intelligence, and particularly discloses a training method for a certificate classification model, and the method comprises the steps: obtaining a certificate sample set, and extracting a certificate sample from the certificate sample set; obtaining preset N data enhancement algorithm sets and a use sequence of the N data enhancement algorithm sets; determining a data enhancement algorithm set for performing data enhancement processing on the certificate sample from the N data enhancement algorithm sets according to the use sequence, and performing data enhancement processing on the certificate sample according to the determined data enhancement algorithm set to obtain a target certificate sample; and training a certificate classification model for carrying out certificate classification according to the plurality of target certificate samples.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a training method of a certificate classification model, a certificate classification method, a device and a computer-readable storage medium. Background technique [0002] As there are more and more types of user certificates, the government or enterprises have an increasing demand for the classification of electronic certificates. In the electronic document classification scenario, some related technologies use machine learning models for classification, but the inventor found that: before using electronic document samples to train machine learning models, it is necessary to perform data enhancement processing on electronic document samples, but the existing The data enhancement processing method is only applicable to scenarios with a large amount of data in electronic certificate samples; The data enhancement processing method performs data enhancement process...

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): G06V10/764G06K9/62
CPCG06F18/214G06F18/24
Inventor 蔡壮壮林大权徐亮
Owner ONE CONNECT SMART TECH CO LTD SHENZHEN
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap