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

Automatic interpretation method, system and device for hospital inspection report

A technology for inspection reports and hospitals, applied in the field of medical diagnosis, can solve problems such as wrong recognition results, lack of application scenarios and business realization

Inactive Publication Date: 2019-03-26
XINBO ZHUOCHANG TECH BEIJING
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This paper mainly compares and studies some algorithms for OCR recognition and error correction. It lacks specific application scenarios and business implementation. Interpreting OCR recognition for hospital inspection reports is only the first step. Of course, the higher the accuracy rate, the better. However, due to image quality and other reasons, errors in the recognition results are inevitable, and it is not enough to correct only for the OCR algorithm, and it is necessary to combine the error correction with the business

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
  • Automatic interpretation method, system and device for hospital inspection report
  • Automatic interpretation method, system and device for hospital inspection report
  • Automatic interpretation method, system and device for hospital inspection report

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 As shown, step 100 is executed, and the user uploads the hospital examination report. The user uploads the hospital inspection report to the system by taking pictures with mobile phones, scanning and uploading, taking pictures after scanning the QR code, etc. The photos taken must ensure a certain brightness and clarity to avoid problems during OCR recognition. Step 110 is executed, the system performs OCR recognition, and records the words, numbers, letters and special symbols on the hospital examination report into the recognition file. Step 120 is executed to capture index keywords. Extract the Chinese name and English name from the recognition file, and match them with the indicator names in the expert knowledge base. The text similarity algorithm is used to calculate the similarity between the Chinese and English names in the identification file and the index names in the expert knowledge base, and those whose similarity exceeds the similarity t...

Embodiment 2

[0050] Such as figure 2 As shown, an automatic interpretation system for hospital inspection reports includes an identification module 200 , a capture module 210 , a generation module 220 , a recommendation module 230 , an interpretation module 240 and an expert knowledge base 250 .

[0051]The identification module 200 is an identification module for performing OCR identification on the hospital examination report uploaded by the user. The user uploads the hospital inspection report to the identification module 200 by taking pictures with the mobile phone, scanning and uploading, taking pictures after scanning the QR code, and the like.

[0052] The capture module 210 is used to capture abnormal indicator information. The capture module includes a keyword sub-module 211 , a judgment sub-module 212 , and a confirmation sub-module 213 . The keyword sub-module 211 is used for index keyword capture, matches the index keyword from the OCR recognition result according to the ind...

Embodiment 3

[0058] The present invention provides a convenient and authoritative automatic report interpretation method for ordinary users, uses the automatic index extraction rules to interpret the information in the report based on OCR identification and authoritative knowledge base, and gives users corresponding explanations and health guidance.

[0059] First, the user takes a photo and uploads the report that needs to be interpreted. The first thing to facilitate the user to input information is to upload the photo, and the second is to ensure the integrity and correctness of the information.

[0060] Then perform OCR recognition on the pictures uploaded by users to extract basic information. There is a certain accuracy problem in OCR recognition. It is necessary to apply machine learning methods to continuously train the lexicon to improve the dictionary and achieve a certain accuracy.

[0061] According to the recognition result of OCR, the abnormal index information is captured. ...

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 provides an automatic interpretation method, system and device for a hospital inspection report, and the method comprises the step: performing OCR identification of a hospital inspectionreport file uploaded by a user, and further comprises the steps: capturing the anomaly index information; generating electronic inspection report information; combining with a knowledge base to automatically generate recommendation information; and generating an interpretation file of the hospital inspection report according to the recommendation information. The invention provides the automaticinterpretation method, system and device for the hospital inspection report, and the method and system use the automatic extraction rule to interpret the information in the report based on the OCR recognition and the authoritative knowledge base, and give the user corresponding explanation and health guidance.

Description

technical field [0001] The invention relates to the technical field of medical diagnosis, in particular to a method and system for automatically interpreting hospital examination reports. Background technique [0002] With the continuous improvement of people's health awareness, more and more people begin to pay attention to their physical condition. It is difficult for ordinary people to understand the inspection and laboratory report as the standard of health judgment. Due to the serious imbalance in the ratio of doctors to patients in China, it is impossible for doctors to explain the detailed information of the report to each patient in detail. Although with the popularization of the Internet, people have more and more sources of knowledge, but the above are so mixed that it is impossible for ordinary people to distinguish true from false. [0003] Taoke Baba published a master's degree thesis titled "Research on OCR Technology-Based Laboratory Sheet Recognition Method...

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): G16H15/00G16H70/00G06F17/27G06K9/00G06K9/20
CPCG16H15/00G16H70/00G06F40/279G06V30/40G06V10/22
Inventor 吕军震于国方胥洪锋李长松赵长磊郭二中武佳
Owner XINBO ZHUOCHANG TECH BEIJING
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