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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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