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

Model correction method and correction system

A model correction and model technology, applied in character and pattern recognition, instrument, character recognition, etc., can solve problems such as lack of error correction mechanism, and achieve the effect of improving recognition accuracy and recognition rate

Inactive Publication Date: 2019-10-15
SUNING CLOUD COMPUTING CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If it is necessary to improve the recognition success rate, a large number of samples are required for marking training, and there is a lack of an error correction mechanism based on the entire pipeline of the business system to improve the overall recognition rate

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
  • Model correction method and correction system
  • Model correction method and correction system
  • Model correction method and correction system

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0053] "ocrName": "totleMoney",

[0054] "ocrValue": "198.00",

[0055] "businessFlag": "1",

[0056] "ocrReusltDet": false,

[0057] "businessValue": "300.00"

[0058] In Example 1, the amount is wrongly recognized, the business data is 300, and the model recognition is 198. Therefore, the marker model identifies errors.

example 2

[0060] "ocrName": "ticketsMoney",

[0061] "ocrValue": "192.23",

[0062] "businessFlag": "1",

[0063] "ocrReusltDet": true,

[0064] "businessValue": "192.23"

[0065] In example 2, identify the amount, the business data is 192.23, and the model identification is 192.23. Therefore, the marker model is identified correctly.

[0066] After the field information is generated from the data information, the system can easily find the model data information marked as wrong from the field information. For example, in the above two examples, the field information of "ocrReusltDet": false is searched directly. When the model data information marked as error is found, the corresponding error data information is obtained. Finally, according to the model data information marked as error, the general character recognition result with coordinates is restored. Such as image 3 As shown, the wrong model data information on the right side of the figure is restored to the general text...

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 discloses a model correction method and correction system, which can improve the recognition rate of a model. The model correction method comprises the steps that data information is collected from a picture, and the data information comprises correct data information that service data and model identification data are consistent and error data information that the service data and the model identification data are inconsistent; judging whether the error data information is a model identification error or not, and if so, entering the next step; and performing model antisense according to the error data information, automatically marking, and training a model.

Description

technical field [0001] The invention belongs to the field of model correction, and in particular relates to a model correction method and a correction system. Background technique [0002] At present, most of the invoice reimbursement, scanning, and review in the financial shared office field still adopt manual review. Financial personnel are faced with the process of receiving, sorting, scanning, reviewing, and replying to physical invoices every day. The entire process line is boring, and there are a lot of repetitive manual operations, especially the bill review. It is necessary to repeatedly compare whether the reimbursement process information reported by employees is consistent with the bill information, which is time-consuming and laborious. [0003] The traditional ocr recognition is based on the attention_ocr technology to complete the general recognition model. Through the continuous marking training of the marking platform, the text recognition results from left ...

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): G06K9/32G06K9/62G06K9/72
CPCG06V20/63G06V10/768G06V30/10G06F18/241
Inventor 陆俊龙王宇赵娟郭近之高兴宇
Owner SUNING CLOUD COMPUTING 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