摘要: 中药数据的不规范,使预处理成为数据挖掘系统中的一个重要过程。该文开发中药特性信息数据挖掘系统,介绍系统结构与挖掘流程,分析中药数据的特征,对数据进行预处理,包括过滤噪声数据、中医药术语规范化、缺损数据处理、剂量单位规范化、作用度规一化、功效量化等。
关键词:
数据挖掘,
中药,
方剂,
数据预处理
Abstract: The description of Traditional Chinese Medicine(TCM) information is not uniform, so data preprocessing is a key process in data mining system. This paper develops data mining system for TCM prescription information, introduces the system architecture and the mining process are described, analyzes the characteristic of data in TCM, and preprocess data such as filtering noisy data, jargon of TCM uniform, absent data processing, measurement units of dose uniform, measurement of effect for medicine, quantity of effect and so on.
Key words:
data mining,
Traditional Chinese Medicine(TCM),
prescription,
data preprocessing
中图分类号:
胡建军;. 中药特性信息数据挖掘系统中的预处理设计[J]. 计算机工程, 2008, 34(21): 284-封三.
HU Jian-jun;. Design of Preprocessing in Data Mining System for Traditional Chinese Medicine Prescriptions Information[J]. Computer Engineering, 2008, 34(21): 284-封三.