Title:
TRADITIONAL CHINESE MEDICINE INGREDIENT ANALYSIS METHOD AND SYSTEM BASED ON SPECTRAL CLUSTERING
Document Type and Number:
WIPO Patent Application WO/2023/207453
Kind Code:
A1
Abstract:
Disclosed in the present disclosure are a traditional Chinese medicine ingredient analysis method and system based on spectral clustering. A specific process for acquiring a trained traditional Chinese medicine ingredient analysis model is: acquiring near-infrared spectrum samples of traditional Chinese medicine ingredients; dividing the near-infrared spectrum samples of the traditional Chinese medicine ingredients into an original sample set and a new sample set; dividing the original sample set into a correction set and a verification set, and constructing a traditional Chinese medicine ingredient analysis model by using the correction set and the verification set; performing clustering analysis on the new sample set to obtain different sample categories; selecting a sample closest to the center of each category as a candidate sample; and adding the candidate samples into the correction set divided from the original sample set so as to form a new correction set, taking the remaining samples in the new sample set except the candidate samples as a test set, and using the new correction set and the test set to train the traditional Chinese medicine ingredient analysis model so as to obtain a trained traditional Chinese medicine ingredient analysis model. By using the trained traditional Chinese medicine ingredient analysis model for performing traditional Chinese medicine ingredient analysis, the prediction precision of the model is improved.
Inventors:
NIE LEI (CN)
ZHUANG XIAOQI (CN)
ZANG HENGCHANG (CN)
ZHANG ZHONGHU (CN)
JIN PIAN (CN)
YANG XINYA (CN)
LI LIAN (CN)
JIANG HONG (CN)
ZHU YOU (CN)
ZHUANG XIAOQI (CN)
ZANG HENGCHANG (CN)
ZHANG ZHONGHU (CN)
JIN PIAN (CN)
YANG XINYA (CN)
LI LIAN (CN)
JIANG HONG (CN)
ZHU YOU (CN)
Application Number:
PCT/CN2023/083467
Publication Date:
November 02, 2023
Filing Date:
March 23, 2023
Export Citation:
Assignee:
UNIV SHANDONG (CN)
International Classes:
G01N21/359; G16C20/20; G06N3/08; G06N20/00; G06N20/10; G16C20/70
Domestic Patent References:
| WO2019192433A1 | 2019-10-10 |
Foreign References:
| CN114783539A | 2022-07-22 | |||
| CN110220866A | 2019-09-10 | |||
| CN107563448A | 2018-01-09 | |||
| CN109540836A | 2019-03-29 | |||
| US20210404952A1 | 2021-12-30 |
Attorney, Agent or Firm:
JINAN SHENGDA INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: