Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Knowledge graph-based patient medical record similarity evaluation method and system

A technology of knowledge graph and similarity, which is applied in the field of text data processing, can solve the problems of error propagation, time-consuming and labor-intensive, triple information loss, etc., and achieve the effect of improving recognition accuracy, reducing tedious work, and avoiding error propagation

Pending Publication Date: 2021-02-12
SHANDONG UNIV
View PDF10 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The inventors of the present invention found that the knowledge map has not been widely used in medical treatment, mainly due to the difficulties in the two aspects of unstructured text extraction and knowledge map drawing; the realization of text information extraction in two sub-tasks will cause non-negligible error propagation, Existing supervised learning is time-consuming and labor-intensive, resulting in missing, inaccurate, and unsmooth triplet information for information extraction.

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
  • Knowledge graph-based patient medical record similarity evaluation method and system
  • Knowledge graph-based patient medical record similarity evaluation method and system
  • Knowledge graph-based patient medical record similarity evaluation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1 As shown, Embodiment 1 of the present invention provides a method for evaluating the similarity of patient medical records based on knowledge graphs, including the following steps:

[0039] First, a bidirectional LSTM network (BI-LSTM-CRF) with a conditional random field layer is used for entity recognition, and the obtained medical entity type is represented by a knowledge vector;

[0040] Then, the attention mechanism (Att-BiLSTM) is added to the BI-LSTM-CRF network, and a joint knowledge extraction network (JKENet) is constructed to extract the relationship while recognizing the entity, which is used in the knowledge map. Rapid construction of triples, represented by joint knowledge vectors;

[0041] Finally, the knowledge vectors are merged into the same semantic space by using joint vectors, and the similarity discrimination is realized by calculating the semantic distance between entities.

[0042] In detail, include the following:

[0043] In ...

Embodiment 2

[0088] Embodiment 2 of the present invention provides a patient medical record similarity evaluation system based on a knowledge map, including:

[0089] The data acquisition module is configured to: acquire the text data of the patient's medical record and perform preprocessing;

[0090] The information extraction module is configured to: use a joint information extraction model based on weakly supervised learning to perform entity recognition and entity relationship extraction on the preprocessed data, and represent the obtained medical entity type with a knowledge vector;

[0091] The triplet building module is configured to: construct triplets in the knowledge map according to the obtained entity relationship, and use a joint knowledge vector to represent it;

[0092] The similarity discrimination module is configured to: use the joint vector to merge the knowledge vectors into the same semantic space, and perform similarity discrimination by calculating the semantic dista...

Embodiment 3

[0095] Embodiment 3 of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the method for evaluating the similarity of patient medical records based on knowledge graphs as described in Embodiment 1 of the present invention is implemented. steps, the steps are:

[0096] Obtain the text data of the patient's medical record and perform preprocessing;

[0097] The joint information extraction model based on weakly supervised learning is used to perform entity recognition and entity relationship extraction on the preprocessed data, and the obtained medical entity types are represented by knowledge vectors;

[0098] According to the obtained entity relationship, the triples in the knowledge map are constructed, and the joint knowledge vector is used to represent it;

[0099] The knowledge vectors are merged into the same semantic space by using joint vectors, and the similarity of medical recor...

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 knowledge graph-based patient medical record similarity evaluation method and system. The method comprises the steps of obtaining and preprocessing patient medical record textdata; carrying out entity identification and entity relationship extraction on the preprocessed data by adopting a joint information extraction model based on weak supervised learning, and expressingan obtained medical entity type by using a knowledge vector; constructing triples in the knowledge graph according to the obtained entity relationship, and representing the triples by using a joint knowledge vector; combining the knowledge vectors into the same semantic space by utilizing the joint vector, and judging the similarity by calculating the semantic distance between entities; accordingto the method, important knowledge in the electronic medical record is mined and extracted by using the bidirectional recurrent neural network for multiple times, the subject domain knowledge graph concept is expanded to the medical field, entity identification and relationship extraction are performed under the current situation that the medical entity type is relatively limited, and the accuracy of similarity evaluation is improved.

Description

technical field [0001] The invention relates to the technical field of text data processing, in particular to a method and system for evaluating similarity of patient medical records based on a knowledge map. Background technique [0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art. [0003] Electronic medical record (EMR) refers to digital electronic information such as text symbols, charts, graphics, data, etc. generated by medical personnel using the information system of medical institutions in the process of treating patients. It has the functions of storage, management, transmission and reproduction. The role of medical records. With the continuous development of smart medical care and informatization, electronic medical records have gradually replaced paper medical records and become the main carrier for recording personal medical information and health information. Relevan...

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): G06F16/36G06F40/295G06F40/30G06N3/04G06N3/08G16H10/60
CPCG06F16/367G06F40/295G06F40/30G06N3/084G06N3/049G16H10/60G06N3/044
Inventor 郭伟宋贤鹿旭东孔兰菊崔立真
Owner SHANDONG UNIV
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
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