南方科技大学知识苑(SUSTech KC): 一种基于数据增强的中药道地性判别方法及装置

Title	一种基于数据增强的中药道地性判别方法及装置
Alternative Title	Traditional Chinese medicine genuine nature discrimination method and device based on data enhancement
Author	胡清; 吕广丰
First Inventor	胡清
Original applicant	南方科技大学
First applicant	南方科技大学
Address of First applicant	518000 广东省深圳市南山区桃源街道学苑大道1088号
Current applicant	南方科技大学
Address of Current applicant	518000 广东省深圳市南山区桃源街道学苑大道1088号 (广东,深圳,南山区)
First Current Applicant	南方科技大学
Address of First Current Applicant	518000 广东省深圳市南山区桃源街道学苑大道1088号 (广东,深圳,南山区)
Application Number	CN202211205120.6
Application Date	2022-09-29
Open (Notice) Number	CN115423042A
Date Available	2022-12-02
Status of Patent	实质审查
Legal Date	2022-12-20
Subtype	发明申请
SUSTech Authorship	First
Abstract	本发明涉及一种基于数据增强的中药道地性判别方法及装置，道地性判别方法包括：查找预先采集的中药材自身元素数据，按设定规则进行预处理，获得各中药材处理后的第一数据；采用分桶策略对第一数据进行数据映射处理；基于数据增强方式，对映射后的第一数据中正负样本数量不平衡的数据进行数据增强，并对数据增强处理后的数据重新按照分桶区间进行映射，获取正负样本数量平衡的第二数据；对预先建立的分类模型进行训练，以获取训练后的用于对中药材的道地性进行判别的分类模型；本发明仅需要对现有采集的中药材自身元素数据进行操作并结合深度机器学习方法就能对中药道地性进行准确高效的判别。
Other Abstract	The invention relates to a traditional Chinese medicine geology discrimination method and device based on data enhancement, and the method comprises the steps: searching pre-collected element data of traditional Chinese medicinal materials, carrying out the preprocessing according to a set rule, and obtaining the first data of each traditional Chinese medicinal material after the processing; performing data mapping processing on the first data by adopting a bucket dividing strategy; based on a data enhancement mode, performing data enhancement on data with unbalanced positive and negative sample numbers in the mapped first data, and mapping the data subjected to data enhancement processing according to the bucket interval again to obtain second data with balanced positive and negative sample numbers; training a pre-established classification model to obtain a trained classification model for judging the geology of the traditional Chinese medicinal materials; according to the method, the geology of the traditional Chinese medicine can be accurately and efficiently judged only by operating the currently collected element data of the traditional Chinese medicine and combining the deep machine learning method.
IPC Classification Number	G06K9/62 ; G16H70/40
INPADOC Legal Status	（ENTRY INTO FORCE OF REQUEST FOR SUBSTANTIVE EXAMINATION）[2022-12-20][CN]
INPADOC Patent Family Count	1
Extended Patent Family Count	1
Priority date	2022-09-29
Patent Agent	齐胜杰
Agency	北京易捷胜知识产权代理有限公司
URL	[Source Record]
Data Source	PatSnap
Document Type	Patent
Identifier	http://kc.sustech.edu.cn/handle/2SGJ60CL/533188
Department	School of Environmental Science and Engineering
Recommended Citation GB/T 7714	胡清,吕广丰. 一种基于数据增强的中药道地性判别方法及装置.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation Sequential No:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh