粗糙集理论是处理海量不完备信息系统的有力工具，可很好的运用到方剂数据分析中。本文对变精度粗糙集模型进行改进，结合相容关系，提出加权变精度容差关系模型，并将属性重要度和信息熵相结合作为启发式信息，给出基于属性敏感度的约简算法。在此基础上，将方剂各组成药物映射为粗糙集属性，对其进行重要度评价，并结合临床疗效，进行属性约简，探讨方-药-症-证对应关系。实验证明，将本文算法应用到方剂数据分析中，能准确地揭示方剂配伍规律和方证相应关系，指导临床遣方用药。

Rough set theory is a powerful tool to deal with incomplete information system, which can be applied to prescription data analysis. In this paper, we suggested an improved rough set model called WVP-T model. The model combined the variable precision model with the tolerance relation model. It can overcome the shortcoming of classical model. Furthermore, attribute importance and entropy of information were combined as heuristic information. Medicine was mapped to rough set attribute in order to value its importance. Then, combined with curative effect, attribute reduction was used to investigate the relationship between prescription and medicine and the relationship between symptom and syndrome. The experimental results showed that algorithm proposed in this paper can be used in prescription data analysis and can accurately reveal the compatibility rules to guide the clinical medication.

江苏省科技厅自然科学基金青年项目（SBK2014042320）：多数据挖掘方法集成的方剂配伍规律挖掘模式设计与系统实现，负责人：佘侃侃；南京中医药大学青年自然科学基金项目（13XZR36）：基于数据挖掘的方剂配伍与临床疗效相关性研究，负责人：佘侃侃。