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

OCR (Optical Character Recognition) method

A recognition method and text information technology, applied in the field of OCR recognition, can solve problems such as structuring of medical reports

Active Publication Date: 2022-03-25
BEIJING MORE HEALTH TECH GRP CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] This technical solution mainly solves the problem of the structure of the medical examination report. The unstructured medical examination report is mainly stored in the form of image, pdf and url, and the data is received Afterwards, the data processing is initially processed and finally structured through the system

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
  • OCR (Optical Character Recognition) method
  • OCR (Optical Character Recognition) method
  • OCR (Optical Character Recognition) method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. One embodiment of the present application realizes OCR recognition through intelligent segmentation of key and value of physical examination items. This technology solves the problem that the physical examination item key and value are identified as one element because the coordinates are too close together. The intelligent segmentation algorithm, such as figure 1 As shown, key=name, value=*** is segmented, and then key and value are extracted, the algorithm is as follows: based on the standard dictionary library of separators to retrieve whether there are separators in the recognition results, such as:, -=, etc.; The delimi...

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 an OCR (Optical Character Recognition) method, which is characterized by comprising the following steps of: 1, collecting a text in an unstructured form; 2, extracting character information and coordinate information from the text in the unstructured form; step 3, aligning the character information according to the coordinate information; and step 4, formatting and outputting the aligned character information formed in the step 3.

Description

technical field [0001] The invention relates to the field of OCR recognition, in particular to an OCR recognition method. Background technique [0002] The current OCR recognition is mainly for digital conversion of unstructured texts such as PDF format and jpg format. Many hidden dangers will be buried, especially in the medical field where there are a large number and sensitive information needs to solve the above problems. Contents of the invention [0003] This technical solution mainly solves the problem of structured medical examination reports. Unstructured medical examination reports are mainly stored in the form of images, pdfs, and urls. change. The ocr prompt identification method mainly includes two sets of mechanisms. First, the received request is forwarded. After forwarding, it is used to identify the text part of the medical examination report. The returned information includes the text and its coordinates. Then, the returned information is processed. Th...

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): G06V30/24
Inventor 李栋栋刘邦长常德杰赵红文谷书锋赵进罗晓斌庄博然张平
Owner BEIJING MORE HEALTH TECH GRP 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