目的 :研究中成药牛黄解毒片的质量评价方法。方法 :应用反向传播神经网络 (BP神经网络 )模型。结果 :该分类结果与其它经典方法一致 ,识别准确率为 10 0 %。结论 :该方法具有较强的容错能力和较快的识别速度 ,简单易行 ,便于大规模的数据处理 ,也可用于其它中成药的质量评价。 Objective : To study the quality evaluation method of Niuhuang Jiedu Tablets. Methods : Application of back propagation neural network (BP neural network) model. Results : This classification result is consistent with other classical methods and the recognition accuracy is 10%. Conclusion: This method has strong fault tolerance and fast recognition speed, is simple and easy to implement, and is convenient for large-scale data processing. It can also be used for quality evaluation of other proprietary Chinese medicines.