Abnormity inspection report automatic recognition method based on keyword network correlation analysis

A technology of keyword network and correlation analysis, which is applied in the field of automatic identification of abnormal inspection reports, and can solve problems such as the inability of computers to identify

Active Publication Date: 2017-01-04
依据数据(湖南)科技有限公司
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for text reports, manual interpretation is still the main method, and computers cannot recognize them.

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
  • Abnormity inspection report automatic recognition method based on keyword network correlation analysis
  • Abnormity inspection report automatic recognition method based on keyword network correlation analysis
  • Abnormity inspection report automatic recognition method based on keyword network correlation analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] The abnormal examination results R are included in the database: mass shadows are seen in the left lower lung field, and calcification shadows are seen in the aorta. The keyword pairs are: (lower left lung field, mass), (aorta, calcification).

[0077] There is a patient, the test result R 1 : The lung field is clear, and the lung markings are not thickened or disordered. The size and shape of the heart were normal. The double diaphragm is smooth, the costophrenic angle is sharp, and the aorta is calcified

[0078] First clause, get S 1 : clear lung field, S 2 : Lung markings without thickening or disorder, S 3 : Normal heart size and shape, S 4 : Double diaphragm smooth, S 5 : Costophrenic angle sharp, S 6 : Aortic calcification

[0079] Subsequently, the keywords of each sentence are extracted to form keyword pairs: (lung field, clear), (lung texture, no thickening), (lung texture, disorder), (heart size, normal), (heart shape, normal) , (double diaphragm, s...

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 abnormity inspection report automatic recognition method based on keyword network correlation analysis. Sentence and word segmentation is performed on a conclusion in a report, keywords are extracted, a keyword network is built, the keyword network is compared with a keyword network in a historical abnormity report database, the relevance is calculated, and therefore whether the report is normal or not is judged automatically. The multi-aspect inspection result can be effectively considered, and whether the inspection report of the text type has the abnormity inspection result or not is automatically and efficiently recognized.

Description

technical field [0001] The invention relates to an automatic identification method for anomaly inspection reports based on keyword network correlation analysis. Background technique [0002] The inspection report generally includes two parts: inspection findings and inspection conclusions. The inspection findings are descriptions and explanations of various phenomena and findings reflected in the inspection of human organs through medical equipment; inspection conclusions (opinions) are subjective judgments of doctors, generally literal. At present, the inspection report mainly judges whether it is normal based on the doctor's experience. For the image report, there are some studies that analyze the image to judge whether it is normal. However, for text reports, manual interpretation is still the main method, and computers cannot recognize them. Clinical medical staff can generally know whether it is normal when they see it, so as to identify abnormal inspection reports. ...

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): G06F17/30G06F19/00
CPCG06F16/3344G06F16/367G16H50/20
Inventor 王亚南
Owner 依据数据(湖南)科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap