中医诊疗复杂巨系统的人工神经网络建模原理  

Modeling principle of artificial neural network for complex giant system of traditional Chinese medicine diagnosis and treatment

作　　者：孙肇阳 吕桂娇 郭义[1,2] 陈波 陈勇 马铭泽 SUN Zhao-yang;LYU Gui-jiao;GUO Yi;CHEN Bo;CHEN Yong;MA Ming-ze(School of Traditional Chinese Medicine,Tianjin University of Traditional Chinese Medicine,Tianjin 301617,China;National Clinical Research Center for Chinese Medicine Acupuncture and Moxibustion,Tianjin 301617,China)

机构地区：[1]天津中医药大学中医学院,天津301617 [2]国家中医针灸临床医学研究中心,天津301617

出　　处：《中华中医药杂志》2022年第10期5841-5844,共4页China Journal of Traditional Chinese Medicine and Pharmacy

基　　金：中国工程院2019年重大咨询项目(No.2019-ZD-6-03);天津市级大学生创新创业项目(No.202110063018)。

摘　　要：基于中医诊疗复杂巨系统原型抽象要素层级、联系方式与系统功能,构建中医诊疗复杂巨系统逻辑模型,并阐明其复杂性特征。解释人工神经网络的算法机制,指出其内核遵循复杂性科学的方法论原则,与中医诊疗复杂巨系统的运作模式具有相似性,因此可以很好地模拟系统复杂性特征及功能。本研究为人工神经网络在中医诊疗系统建模领域的应用提供理论依据,亦为具体模型的可解释性研究奠定基础。The element hierarchy, contact and system function of the complex giant system of traditional Chinese medicine(TCM) diagnosis and treatment are abstracted, the logic model is constructed, and its complexity characteristics are clarified. The article explains the algorithm mechanism of artificial neural network(ANN) and proves that it has the similarity with the operation mode of complex giant system of TCM diagnosis and treatment, so it can simulate system complexity characteristics and functions well. This study provides a theoretical basis for the application of ANN in the field of TCM diagnosis and treatment system modeling and lay the foundation for interpretable research on specific models.

关 键 词：人工神经网络 中医诊疗复杂巨系统 建模原理 证素 人工智能 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] R2-03[自动化与计算机技术—控制科学与工程]