构建中医目诊智能系统的问题与建议  

Problems and suggestion of constructing an intelligent system for visual diagnosis in traditional Chinese medicine

作　　者：高远 李丹阳 张仕娜 晏峻峰[1,2,3] 彭清华 GAO Yuan;LI Danyang;ZHANG Shina;YAN Junfeng;PENG Qinghua(Hunan University of Chinese Medicine,Changsha 410208,China;Institute of TCM Diagnostics,Hunan University of Chinese Medicine,Changsha 410208,China;School of Informatics,Hunan University of Chinese Medicine,Changsha 410208,China)

机构地区：[1]湖南中医药大学,长沙410208 [2]湖南中医药大学中医诊断研究所,长沙410208 [3]湖南中医药大学信息科学与工程学院,长沙410208

出　　处：《中华中医药杂志》2023年第10期4535-4539,共5页China Journal of Traditional Chinese Medicine and Pharmacy

基　　金：湖南省研究生科研创新项目(No.QL20220183,No.QL20220184,No.CX20210716);湖南省教育厅重点项目(No.21A0250);湖南中医药大学中医学一流学科开放基金项目(No.2022ZYX08,No.2021ZYX31);湖南中医药大学研究生创新课题(No.2022CX02)。

摘　　要：目诊是通过观察目来判断全身病证的诊断方法,中医目诊智能系统还有许多问题尚未得到有效解决。现通过方法论、数字化、逻辑性3个方面探讨构建中医目诊智能系统的问题,并提出解决建议。首先,目诊智能系统的构建过程中缺乏方法论指导,需要以复杂系统科学作为方法论指导。其次,数字化问题包括信息采集问题、中医计量诊断问题和数理模型问题,需通过制定目诊规范化采集和计量诊断标准,建立适合的数理模型。再次,多源信息分析问题、诊断信息权重问题和解释性问题这3个逻辑性问题,需要运用融合智能算法和层次分析法,以及多学科研究团队“多次迭代,逐步近似”构建目诊智能系统的解释体系。The visual diagnosis is a diagnostic method to judge systemic diseases by observing the eyes.There are still many problems that have not been effectively solved for an intelligent system for visual diagnosis in traditional Chinese medicine(TCM).The three aspects of methodology,digitization,and logic are used to discuss the problems of constructing an intelligent system for visual diagnosis in TCM and to propose solutions.Firstly,the construction process of visual diagnostic intelligent system lacks methodological guidance and needs to be guided by complex system science as the methodology.Secondly,the digital problems include information collection problem,TCM metrological diagnosis problem and mathematical model problem,which need to establish suitable mathematical model by developing standardized collection and metrological diagnosis standards for visual diagnosis.Next then,the three logical problems of multi-source information analysis,diagnostic information weight and explanatory problems require the use of fusion intelligent algorithms and analytic hierarchy methods,as well as the multidisciplinary research teams'multiple iterations and gradual approximation'to construct an explanation system for visual diagnosis intelligent systems.

关 键 词：目诊 人工智能 复杂系统 方法论 数理模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] R241[自动化与计算机技术—控制科学与工程]