Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic identification method for test reports

An automatic recognition and report technology, applied in the field of text recognition, can solve the problems of low data recognition accuracy, achieve the effect of improving recognition accuracy and data collection efficiency, and facilitating clinical statistical analysis

Pending Publication Date: 2020-10-20
翰博瑞强(上海)医药科技有限公司
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for automatic identification of laboratory reports in order to solve the problem of low recognition accuracy of data collected directly through OCR technology in laboratory reports

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] A method for automatic identification of laboratory reports, comprising the following steps:

[0023] Step 1: Obtain the test report of the subject.

[0024] Step 2: Use a professional scanner to scan the laboratory report into a standard text in JPEG image format, and at the same time cover the subject's personal information with a unique code corresponding to the subject, which includes the subject number and hospital number information.

[0025] Step 3: Establish a template model based on the text and graphic distribution characteristics of the standard text content, and adjust the corresponding standard text area to be recognized according to the template model matched by the test report.

[0026] Among them, the template model includes pixel area values, pixel accumulation values ​​of different rows and columns, and test report type values. The pixel area value and the cumulative value of pixels in different rows and columns are obtained after scanning the test re...

Embodiment 2

[0032] A method for automatic identification of laboratory reports, comprising the following steps:

[0033] Step 1: Obtain the test report of the subject.

[0034] Step 2: Use adhesive tape to cover the subject's personal information in the test report, and then use a professional scanner to scan the test report into a standard text in PDF format.

[0035]Step 3: Establish a template model based on the text and graphic distribution characteristics of the standard text content, and adjust the corresponding standard text area to be recognized according to the template model matched by the test report.

[0036] Among them, the template model includes pixel area values, pixel accumulation values ​​of different rows and columns, and test report type values. The pixel area value and the cumulative value of pixels in different rows and columns are obtained after scanning the test report. The pixel area value is the maximum area value of the picture after removing the blank areas ar...

Embodiment 3

[0041] A method for automatic identification of laboratory reports, comprising the following steps:

[0042] Step 1: Obtain the test report of the subject.

[0043] Step 2: Use a professional scanner to scan the laboratory report into a standard text in PDF format, and at the same time cover the subject's personal information with the unique code corresponding to the subject, which includes the subject number and hospital number information.

[0044] Step 3: Establish a template model based on the text and graphic distribution characteristics of the standard text content, and adjust the corresponding standard text area to be recognized according to the template model matched by the test report.

[0045] Among them, the template model includes pixel area values, pixel accumulation values ​​of different rows and columns, and test report type values. The pixel area value and the cumulative value of pixels in different rows and columns are obtained after scanning the test report....

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 automatic identification method for a test report and relates to the technical field of text identification. The method comprises the following steps of acquiring the test report of a subject; scanning the test report into a standard text in a PDF or picture format, and covering the personal information of the subject; establishing a template model based on the characterand graph distribution characteristics in the standard text, and adjusting a to-be-identified region of the standard text by utilizing the template model; identifying data in the to-be-identified area by utilizing an OCR technology; and finally, naming the standard text and storing the standard text into a corresponding folder according to the name of the standard text. The method is based on thecharacteristics of the test report, corresponding template models are established for different test reports, the OCR identification area is adjusted by using the template model to accurately identify each item of test report data in different formats, so identification accuracy of the test report is high, collection efficiency of the test report data is further improved, and a problem of low identification accuracy of data acquisition directly through the OCR technology is solved.

Description

technical field [0001] The invention relates to the technical field of text recognition, in particular to an automatic recognition method for a test report. Background technique [0002] In clinical medicine and clinical trials, laboratory reports are an important part of clinical raw data. Especially in many clinical trials, laboratory report data account for 60-80% of the information. In the current laboratory report data collection, the data connection with the hospital information system is a common way, but it also faces many difficulties. In consideration of the confidentiality of subjects' information, almost all clinical trial institutions in China cannot directly share the electronic data of laboratory reports. In the execution of clinical trials, all clinical coordinators CRC need to print out each test report of the subject through the hospital information system, and then write the data in the test report into the relevant files of the corresponding subject. I...

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): G06K9/00G06K9/62G06F21/62G16H15/00
CPCG06F21/6245G16H15/00G06V30/40G06V10/751G06V30/10
Inventor 霍红建孟凡强陈阶
Owner 翰博瑞强(上海)医药科技有限公司