Method and device for establishing text information recognition model and terminal equipment

A text information and recognition model technology, applied in the computer field, can solve the problem of unable to obtain the entity recognition model of text information information in the health industry, etc.

Active Publication Date: 2021-02-09
新奥新智科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides a method, device and terminal equipment for establishing a text information recognition model to solve the problem that it is objectively difficult to obtain the required number of samples in the prior art to train the text information entity recognition model of the health industry, so that The problem that the ideal text information information entity recognition model of the health industry cannot be obtained in practice

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
  • Method and device for establishing text information recognition model and terminal equipment
  • Method and device for establishing text information recognition model and terminal equipment
  • Method and device for establishing text information recognition model and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0057] figure 1 It is a flowchart of a method for establishing a text information recognition model provided in an embodiment of the present invention.

[0058] like figure 1 As shown, the method for establishing the text information recognition model includes steps S110-S150:

[0059] S110: Obtain a data set of Chinese text information.

[0060] In this embodiment, the data set of Chinese text information is a converted Chinese document vector data set. Please refer to the specific conversion steps figure 2 , figure 2 It is an implementation diagram of the process of obtaining a data set of Chinese text information provided in an embodiment of the present invention.

[0061] like figure 2 As shown, obtaining a data set of Chinese text information may specifically include the following steps S210-S220:

[0062] S210, acquiring Chinese text.

[0063] In this embodiment, the Chinese text is a marked Chinese corpus, and the Chinese corpus belongs to recognizable entity...

no. 2 example

[0118] Based on the same inventive concept as the method in the first embodiment, correspondingly, this embodiment also provides a device for establishing a text information recognition model.

[0119] Figure 8 It is a schematic diagram of the implementation flow of the device for establishing a text information recognition model provided by the embodiment of the present invention.

[0120] like Figure 8 As shown, the shown device includes 81 Chinese data set acquisition module, 82 health data set acquisition module, 83 migration data set generation module, 84 extended data set generation module and 85 text information recognition model establishment module.

[0121] Among them, the 81 Chinese data set acquisition module is configured as a data set for acquiring Chinese text information;

[0122] 82. The health data set acquisition module is configured to acquire a data set of text information of the health industry;

[0123] 83 The migration data set generating module is...

no. 3 example

[0147] The above method and device can be applied to terminal devices such as desktop computers, notebooks, palmtop computers and cloud servers.

[0148] Figure 9 It is a schematic diagram of a terminal device that can apply the above method and device provided in an embodiment of the present invention. As shown in the figure, the device 9 includes a memory 91, a processor 90, and is stored in the memory 91 and can be stored in the memory 91. The computer program 92 running on the processor 90, when the processor 90 executes the computer program 92, implements the steps of the method for establishing the text information recognition model. E.g Figure 8 The functions of modules 81 to 85 are shown.

[0149] The device 9 may be a computing device such as a cloud server. The terminal device may include, but not limited to, a processor 90 and the memory 91 . Those skilled in the art can understand that, Figure 9 It is only an example of the device 9 and does not constitute ...

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 is applicable to the field of computers, and provides a method and device for establishing a text information recognition model and terminal equipment, and the method comprises the steps: obtaining a data set of Chinese text information; obtaining a data set of text information of the health industry; based on the data set of the text information of the health industry, classifying the data set of the Chinese text information by adopting a K-nearest neighbor algorithm to obtain a migration data set; adding a data set of text information of the health industry into the migration data set to generate an extended data set; and training a known named entity recognition model by utilizing the extended data set to obtain a recognition model of text information of the health industry. The method and device well solve the problem that in the prior art, it is difficult to objectively obtain the number of samples meeting the requirements to train the text information entity recognition model of the health industry, so that an ideal text information entity recognition model of the health industry cannot be obtained in practice.

Description

technical field [0001] The invention belongs to the field of computers, and in particular relates to a method, device and terminal equipment for establishing a text information recognition model. Background technique [0002] In recent years, people's living standards have gradually improved, and citizens have begun to pay more and more attention to their own health, so the demand for medical health is also increasing. With the advent of the intelligent age, people are not satisfied with seeking medical advice offline, but hope to obtain useful medical information through the Internet. It is hoped that useful information can be obtained through necessary processing of existing medical and health information, especially text information, such as consultation records, doctor's orders, and electronic medical records. A key step in natural language processing of text in the medical domain is to recognize medical entities such as diseases, symptoms, body parts, etc. However, si...

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): G06F16/35G06K9/62
CPCG06F16/35G06F18/214G06F18/2413Y02A90/10
Inventor 赵蕾王玥黄信宋英豪
Owner 新奥新智科技有限公司
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