Supercharge Your Innovation With Domain-Expert AI Agents!

Text picture processing system and method based on association algorithm

A technology of text image and processing system, applied in the field of text image processing system based on association algorithm, which can solve the problems of long time for manual labeling of medical terms and poor accuracy of general thesaurus

Inactive Publication Date: 2021-09-10
ZHEJIANG UNIV OF WATER RESOURCES & ELECTRIC POWER
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problems of poor accuracy of the general lexicon of medical terms and the long time for manually labeling medical terms, etc., and provides a system and method for processing text and pictures based on an association algorithm. A common lexicon of medical terms is trained in the lexicon

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
  • Text picture processing system and method based on association algorithm
  • Text picture processing system and method based on association algorithm
  • Text picture processing system and method based on association algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0048] Embodiment, text image processing system and method based on association algorithm, see figure 1 As shown, the implementation process of the text image processing system and method based on the association algorithm is as follows:

[0049] In the first step, the frequency of single word or double word appears in the statistical bill corpus, and the relevant information f of the connected word before and after this single word or this double word is counted;

[0050] The specific algorithm is as follows:

[0051] Definition 1: Let the condition satisfied by a stable word w be E L (w)>K 1 , and E R (w)>K 1 ,in

[0052]

[0053]

[0054] E. L (w) is the left entropy value of word w, E R(w) is the right entropy value of word w, K 1 is the threshold;

[0055] P(aw|w) refers to the combination probability of the word w and the connectin...

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 text picture processing system and method based on an association algorithm, and belongs to the field of algorithm computation.The implementation process of the text picture processing system and method based on an association algorithm comprises the following steps of: 1, conducting statistics on the frequency that single characters or double characters appear in a bill corpus, and conducting statistics on related information of characters connected with the single characters or the double characters in front and back; 2, using mutual trust entropy for single characters and double characters in a word segmentation word bank, and selecting the double characters greater than a threshold K1 = 10.8 to be added into an initial word bank; and 3, segmenting the bill corpus by using forward maximum matching in the presence of the initial word library, outputting segmented word strings according to a frequency sequence, and recording the number of the word strings.

Description

technical field [0001] The invention relates to the technical field of text image processing, in particular to a text image processing system and method based on an association algorithm. Background technique [0002] Bill structuring refers to the extraction of various semantic elements from clinical medical records, inspection records, and laboratory test sheets stored in text form, serving application scenarios such as drug clinical trials and medical scientific research analysis. Simply put, it is to extract patient information, symptom information, medication information, diagnosis information and many other knowledge points from medical records. [0003] Bill structuring is one of the core technologies for the application of artificial intelligence in the medical field. For example, phase IV clinical trials and real-world trials of pharmaceutical companies usually require analysis of tens of thousands of medical records, and clinical research in hospitals usually requ...

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): G06F16/33G06F16/338
CPCG06F16/3346G06F16/338
Inventor 孙欣欣
Owner ZHEJIANG UNIV OF WATER RESOURCES & ELECTRIC POWER
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com