Medical Text Generation Method Based on Generative Adversarial Network Technology

A network technology and generative technology, applied in the field of data mining of medical texts, can solve the problems of patient privacy and security, lack of medical texts, etc.

Active Publication Date: 2020-06-02
北京未来云服科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to provide a medical text generation method based on generative confrontation network technology, which generates new medical texts by disrupting data and simulating them for training, learning and testing in machine learning, data mining, artificial intelligence and other methods Use, solve the patient privacy security issues that may be involved in medical texts, and solve the problem of lack of medical texts

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
  • Medical Text Generation Method Based on Generative Adversarial Network Technology
  • Medical Text Generation Method Based on Generative Adversarial Network Technology
  • Medical Text Generation Method Based on Generative Adversarial Network Technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0084] Below in conjunction with principle of the present invention, accompanying drawing and embodiment the present invention is further described

[0085] see figure 1 with figure 2 , as shown in the legend, a medical text generation method based on generative confrontation network technology, including the following steps:

[0086] (1) Download multiple medical documents in a certain subject area to form a medical document set PD_SET to be preprocessed;

[0087] (2) Set the number n of medical documents to be generated;

[0088] (3) The medical text set GD_SET generated by initialization is empty;

[0089] (4) Initialize the input data set INPUT_SET to be empty;

[0090] (5) Determine whether the medical document set PD_SET to be preprocessed has unprocessed documents, if so, randomly read one of the medical documents D, and turn to step (6); if not, turn to step (10);

[0091] (6) Medical document D is removed from the medical document set PD_SET to be preprocessed; ...

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 method for generating medical text based on generative confrontation network technology, comprising the following steps: downloading multiple medical documents in a certain field; using word vectors to represent each word in each medical document; Classify the text of each medical document and keep the required medical documents; obtain the best output sequence annotation of each required medical document; obtain the index of the keyword set of each required medical document, and randomly shuffle the index, Obtain new medical documents and their corresponding sequence annotations; use generative confrontation network-based generative model training to generate medical texts; output the generated medical texts; obtain the BLEU parameters of the generated medical texts; evaluate the generated medical texts, and finally Get target medical text. The invention generates new medical texts by disrupting data, so as to solve the problems of patients' privacy security and less medical texts.

Description

technical field [0001] The invention relates to the field of data mining of medical texts, in particular to a method for generating medical texts based on generative confrontation network technology. Background technique [0002] At present, researchers have applied new methods such as artificial intelligence and machine learning to medical text data, and while obtaining some good results, they have also encountered some problems, such as: [0003] (1) Lack of data. The data of medical texts, especially the data of some rare diseases and severe diseases is seriously insufficient, which will cause the failure of machine learning and other methods in the training and learning stage, and cannot reflect the information of these diseases correctly, truthfully and comprehensively. [0004] (2) Privacy and security. How to protect privacy and security has always been a hot spot of concern. For example, a former mayor of Indiana was suddenly found to be infected with a vicious in...

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 Patents(China)
IPC IPC(8): G06F16/35G16H50/70G06F21/62
CPCG16H50/70G06F21/6254G06F40/00G06F40/216G06F40/30G06F40/284G06F40/56G06N3/088G06N3/047G06N3/048G06N3/044G06N3/045
Inventor 朱斐叶飞伏玉琛陈冬火
Owner 北京未来云服科技有限公司
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