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

Medical automatic question answering method and system based on common sense fusion

A technology of automatic question answering and common sense, applied in medical automatic diagnosis, neural learning methods, computer-aided medical procedures, etc., can solve problems such as problem type limitations, and achieve the effect of improving professionalism, improving user experience, and facilitating understanding

Pending Publication Date: 2022-04-22
SHANGHAI JIAO TONG UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the invention has limitations on the type of questions

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 automatic question answering method and system based on common sense fusion
  • Medical automatic question answering method and system based on common sense fusion
  • Medical automatic question answering method and system based on common sense fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] According to a medical automatic question answering method based on common sense fusion provided by the present invention, such as Figure 1-Figure 4 shown, including:

[0083] Step S1: Segment the training sentence, use the word segmentation as a keyword, query the knowledge base and the knowledge base, and obtain entity-relationship triples;

[0084] Step S2: Fusion coding the triples and the training sentences, so that the structured common sense in the library is fused with the training sentences;

[0085] Step S3: Randomly select part of the entity masking of the fused and encoded training sentences, replace the next sentence with other random sentences at a fixed probability, and input the obtained training corpus into the multi-layer partition transformer encoder for training to obtain a preliminary common sense fusion language model ;

[0086] Step S4: Perform word segmentation and entity relationship query on the questions in the question-answer da...

Embodiment 2

[0114] Embodiment 2 is a preferred example of Embodiment 1 to describe the present invention more specifically.

[0115] Those skilled in the art can understand the medical automatic question answering method based on common sense fusion provided by the present invention as a specific implementation of the common sense fusion based medical automatic question answering system, that is, the common knowledge fusion based medical automatic question answering system can be executed by The step flow of the medical automatic question answering method based on common sense fusion is realized.

[0116] A medical automatic question answering system based on common sense fusion provided according to the present invention includes:

[0117] Module M1: Segment the training sentences, use the word segmentation as a keyword, query the knowledge base and the knowledge base, and obtain entity-relationship triples;

[0118] Module M2: Fusion encoding of triples and training sentences...

Embodiment 3

[0148] Embodiment 3 is a preferred example of Embodiment 1 to describe the present invention more specifically.

[0149] A medical automatic question answering method and system based on common sense fusion provided by the present invention comprises the following steps:

[0150] Step S1: Segment the training sentence, use the obtained word segmentation as a keyword, query the knowledge base and the knowledge base, and obtain entity-relationship triples;

[0151] Step S2: Fusion coding the triples and the training sentences, so that the structured common sense can be integrated into the common training sentences;

[0152] Step S3: Randomly select part of the entity mask from the sentence after fusion encoding, replace the next sentence with other random sentences at a fixed probability, input the training corpus obtained in the two ways into the multi-layer partition transformer encoder for training, and obtain a preliminary model ;

[0153] Step S4: According to...

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 a medical automatic question answering method and system based on common sense fusion, and the method comprises the steps: carrying out the word segmentation of a training statement, querying a common sense library and a knowledge library, and obtaining an entity relation triple; fusing and coding the triple and the training statement; randomly selecting part of entities for masking the training statements subjected to fusion coding, replacing the next sentence with other random statements according to a fixed probability, and inputting the obtained training corpus into a multi-layer partition encoder for training; performing word segmentation and entity relationship query on questions in the question and answer data, and fusing codes; taking a common sense fusion coding sequence of the question as model input, and taking an answer as a supervision label for training to obtain a common sense fusion language model; a visual medical automatic question-answering system is built, questions are input into a model through a front end, and output of the model serves as answers to be displayed on an interface. According to the method and the system, the types of the questions of the user are not limited, common knowledge and medical knowledge are fused into the language model, and the specialty is improved while the answer is ensured to conform to grammar rules.

Description

technical field [0001] The present invention relates to the field of medical automatic question answering, in particular to a medical automatic question answering method and system based on common sense fusion. Background technique [0002] The medical automatic question answering system can obtain users' medical related questions and automatically give answers. Traditional search engines require users to extract and identify the query results themselves, while the question answering system can automatically generate answers based on the knowledge base. For example, it can directly give corresponding answers to questions such as diseases, medicines, symptoms, and inspections, which can greatly facilitate users and reduce the pressure on medical staff. [0003] Existing medical question answering systems usually can only answer questions of a given type and generate answers of fixed grammatical types. Specifically, existing medical question answering systems first match the...

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
IPC IPC(8): G06F16/332G06F16/33G06F16/36G06F40/284G06N3/04G06N3/08G16H50/20
CPCG06F16/3329G06F16/367G06F16/3334G06F40/284G06N3/04G06N3/08G16H50/20
Inventor 唐飞龙杨帆唐灿李旭陈龙刘嘉成
Owner SHANGHAI JIAO TONG UNIV
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