Traditional Chinese medicine short text multi-classification method based on LD and ANN-SoftMax Regressor

A multi-category, short-text technology, applied in text database clustering/classification, neural learning methods, unstructured text data retrieval, etc., can solve problems such as insufficient mining of semantic relationships

Active Publication Date: 2019-11-05
HUAIYIN INSTITUTE OF TECHNOLOGY
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the semantic relationship between diseases and drugs has not been fully exploited and incorporated into the recommendation

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
  • Traditional Chinese medicine short text multi-classification method based on LD and ANN-SoftMax Regressor
  • Traditional Chinese medicine short text multi-classification method based on LD and ANN-SoftMax Regressor
  • Traditional Chinese medicine short text multi-classification method based on LD and ANN-SoftMax Regressor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0118] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0119] Such as Figure 1~5 Shown, a kind of Chinese medicine short text multiple classification method based on LD and ANN-SoftMax Regressor of the present invention, comprises the steps:

[0120] Step 1: Preprocess the text data to obtain the artificial entity annotation text label dataset T1, text dataset T2, and jieba word segmentation to process the text dataset T2 to obtain the text dataset T3; the specific method is:

[0121] Step 1.1: Define Text as a text information set, Name as a single...

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 traditional Chinese medicine short text multi-classification method based on an LD and ANN-SoftMax Regressor. The method is mainly based on constructed text label data labeled by an artificial entity to process data on the traditional Chinese medicine short text data. Firstly, a jaeba word segmentation tool is adopted for word segmentation, and then a Bag-of-Words model is adopted for processing. A symptom synonym dictionary is established in an LD mode to perform dimension reduction processing on text onehot vectorization representation after word bag construction byutilizing SVD and PCA, and then ANN-SoftMax Regressor multi-classification training is performed to finally obtain the traditional Chinese medicine short text multi-classification method. The methodis suitable for the field of traditional Chinese medicine and short text classification, and can effectively enable fuzzy symptom classification of diseases to be more accurate.

Description

technical field [0001] The invention belongs to the technical field of classification of traditional Chinese medicine and short texts, and in particular relates to a multi-classification method for short texts of traditional Chinese medicine based on LD and ANN-SoftMaxRegressor. Background technique [0002] When faced with the problem of short text classification, researchers will choose to integrate similarity models, neural networks, etc. into short text classification to study the relationship between texts in order to improve the accuracy of text classification. [0003] Zhang Hui, Zhu Quanyin and others’ existing research foundations include: Bai Qiuchan, Jin Chunxia, ​​Zhang Hui, Zhou Haiyan. Word co-occurrence text topic clustering algorithm[J].Computer Engineering and Science,2013,35(07):164- 168.; Liu Pengfei, Zhang Baoyu, Yuan Zhinan, Zhang Hui. Research and development of drug traceability system based on blockchain [J]. Information Communication, 2019(04): 162-1...

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): G06F16/35G06F17/27G06N3/08
CPCG06F16/353G06N3/084Y02A90/10
Inventor 章慧张发朱全银俞扬信
Owner HUAIYIN INSTITUTE OF TECHNOLOGY
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