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

Sample screening method and device and computer equipment

A screening method, computer technology, applied in computer parts, computing, neural learning methods, etc., can solve the problem of not being able to automatically and quickly pick out normal samples

Active Publication Date: 2020-10-02
PINGAN INT SMART CITY TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide a sample screening method, aiming to solve the technical problem that normal samples cannot be picked out automatically and quickly

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
  • Sample screening method and device and computer equipment
  • Sample screening method and device and computer equipment
  • Sample screening method and device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0050] refer to figure 1 , the sample screening method of an embodiment of the present application, comprising:

[0051] S1: Input all the samples to be screened into the Yolov3 neural network model;

[0052] S2: Obtain the computer-labeled frame data obtained by identifying each of the samples to be screened by the Yolov3 neural network model, and the manually-labeled frame data corresponding to each of the samples to be screened obtained in advance;

[0053] S3: Calculate the average accuracy corresponding to each of the samples to be screened respectively according to...

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 artificial intelligence and blockchain technologies, and discloses a sample screening method, which comprises the steps of inputting all to-be-screened samples into a Yolov3 neural network model; obtaining computer annotation box data obtained by identifying each to-be-screened sample through a Yolov3 neural network model, and pre-obtained manual annotation box data corresponding to each to-be-screened sample; according to the computer annotation box data and the manual annotation box data corresponding to each to-be-screened sample, calculating average accuracy corresponding to each to-be-screened sample; comparing the size relationship between the average precision corresponding to each to-be-screened sample and a first preset value; dividing the to-be-screened samples of which the average precision is less than or equal to a first preset value into inferior samples, and dividing the to-be-screened samples of which the average precision is greater than the first preset value into normal samples. And the average accuracy of the samples is calculated through the computer labeling box data and the manual labeling box data, so that the samples can be automatically and quickly picked.

Description

technical field [0001] This application relates to the field of artificial intelligence and block chain technology, in particular to sample screening methods, devices and computer equipment. Background technique [0002] Training samples play a vital role in model training. However, due to the subjective factors of human labeling in sample labeling and the large number of training samples, it is impossible to manually filter out parts such as smearing, occlusion, and illegible handwriting. Inferior samples affect the model training effect. Or the scarcity of samples in some scenarios leads to a serious shortage of training samples, resulting in low accuracy of the trained model. The existing technology cannot identify and eliminate inferior samples, and cannot automatically and quickly pick out normal samples. Contents of the invention [0003] The main purpose of this application is to provide a sample screening method, aiming to solve the technical problem that normal ...

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): G06K9/62G06N3/08
CPCG06N3/08G06V2201/07G06F18/214
Inventor 黄哲
Owner PINGAN INT SMART CITY 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