Unlock instant, AI-driven research and patent intelligence for your innovation.

Medical word meaning identification method and device, computer equipment and storage medium

A technology of medicine and word meaning, applied in the field of data processing, can solve problems such as not being able to hit the correct concept, and achieve the effect of technology sharing, precise medical diagnosis, and improvement of accuracy

Pending Publication Date: 2020-06-30
深圳平安医疗健康科技服务有限公司
View PDF13 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to address the above-mentioned technical problems. This application provides a medical word meaning recognition method, device, computer equipment, and storage medium to solve the problem of not being able to hit the correct concept from thousands of standard concepts in the prior art to accurately Technical issues with locating relevant medical words

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 word meaning identification method and device, computer equipment and storage medium
  • Medical word meaning identification method and device, computer equipment and storage medium
  • Medical word meaning identification method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Example 1, such as figure 2 As shown, a medical word meaning recognition method is provided, which is applied to figure 1 The server in , as an example, includes the following steps:

[0040] Step 202, acquire the sentence to be analyzed, and search out the medical words related to the sentence to be analyzed from the preset medical word list according to the sentence to be analyzed, wherein the number of medical words is at least one.

[0041] The execution subject adopted in this embodiment can be a server or a computer device. This embodiment uses the server as the execution subject to perform medical word meaning recognition for illustration; the above-mentioned sentence to be analyzed can be a sentence input by a patient or a doctor in the terminal, and the above-mentioned medical The word list is a form pre-stored on the server. In this embodiment, the medical semantic segmentation in the SNOMED-CT knowledge base is used, and the medical features of 11 medical c...

Embodiment 2

[0052] Example 2, such as image 3 As shown, before step 202, it also includes:

[0053] Step 302, obtain the first training sample B1 from the case database, and obtain the second training sample B2 from the medical word list. The server can obtain the first training sample B through the platform 1 , Obtain the second training sample B through the medical word list 2 , specifically, the platform can be records of patients' illness conditions recorded by medical associations such as hospitals and clinics.

[0054] Step 304, establishing a similarity label between the first training sample B1 and at least one second training sample B2, wherein the second training sample B2 is a medical word related to the text of the first training sample B1. Through the first training sample B 1 A second training sample B related to a plurality of words related to the first training sample B1 2 Create a similarity label, for example, the first training sample: B1 = "glaucoma filtering ble...

Embodiment 3

[0058] Example 3, such as Figure 4 As shown, based on Embodiment 2, step 202 includes:

[0059] Step 402, identifying the analyzed text in the sentence to be analyzed.

[0060] Step 404, determine the similarity label corresponding to the analyzed text in the medical word list.

[0061] Step 406, according to the similarity labels, obtain medical words that are relevant to the text of the sentence to be analyzed.

[0062] Based on the similarity tags obtained in Example 2, after the server obtains the patient or doctor's sentence to be analyzed from the terminal, it can find the corresponding medical word from the medical word list. Specifically, the server obtains the sentence to be analyzed, then identifies the text of the sentence to be analyzed, and determines the similarity label corresponding to the sentence to be analyzed in the medical word list through comparison. medical word.

[0063] This embodiment can directly obtain the medical words that have a correlation...

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 belongs to the field of data processing, and discloses a medical word meaning identification method and device, computer equipment and a readable storage medium. The method comprises thesteps: acquiring a to-be-analyzed statement, and finding out medical words related to the to-be-analyzed statement from a preset medical word form according to the to-be-analyzed statement; importingthe to-be-analyzed statement and the medical word into the Bilstm model to obtain an original statement vector and a medical word vector; performing pooling analysis on the original statement vectorand the medical word vector to obtain an original feedforward vector and a medical feedforward vector; and importing the original feed-forward vector and the medical feed-forward vector into a cosinesimilarity algorithm to obtain a cosine value between the original feed-forward vector and the medical feed-forward vector, and taking the medical word corresponding to the maximum cosine value as a medical word meaning identification result. By adopting the method, the technical problems that correct concepts cannot be hit from thousands of standard concepts and related medical words cannot be accurately positioned are solved.

Description

technical field [0001] The present application relates to the field of data processing, in particular to a medical word meaning recognition method, device, computer equipment and storage medium. Background technique [0002] With the development of information technology, deep learning models have recently made great progress in the general field of semantic similarity, such as robot recognition of semantics, but there have been no outstanding results in the semantic similarity of Chinese medical clinical data; [0003] At present, the twin network model is used for the clinical semantic recognition of medicine. The traditional twin network model maps a sentence to be analyzed and a medical word initially determined according to the sentence to be analyzed to the analysis space at the same time, so that the sentence to be analyzed and the corresponding The representation of medical words in the space realizes the clinical semantic recognition of medicine through the calculat...

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): G06F40/284G06F40/30
Inventor 施维郭建福张旭
Owner 深圳平安医疗健康科技服务有限公司