动态不确定因果图在中医智能辅助辨证中的应用研究

Research on the Application of Dynamical Uncertainty Causality Graph in Intelligent Assisted Syndrome Differentiation of Traditional Chinese Medicine

以郁病辨证为例,开展动态不确定因果图在中医智能辅助辨证中的应用研究,提高中医智能辅助辨证模型中辨证知识的可视化程度和辨证推理过程的可解释性。对郁病权威文档进行整理分析、获取郁病辨证知识,采集郁病医案并进行筛选和数据预处理,构建郁病智能辅助辨证DUCG知识库,在知识库中表示症状知识和证型知识以及二者之间的关系,结合DUCG推理机进行辨证推理测试和分析。构建了包含19个子图的郁病智能辅助辨证DUCG知识库和包含6个子图的郁病智能辅助辨证DUCG核心知识库,辨证推理测试获得的初步准确率可达72.92%、按证型分组统计的准确率最高可达100%,可根据DUCG化简图对辨证结果进行详细解释。将动态不确定因果图理论应用于中医智能辅助辨证研究,有助于提高辨证模型中辨证知识的可视化程度和辨证推理过程的可解释性。

Taking the syndrome differentiation of depression as an example,this paper carries out research on the application of DUCG in intelligent assisted syndrome differentiation of TCM,and improves the visualization degree of syndrome differentiation knowledge in the syndrome differentiation model and the interpretability of syndrome differentiation reasoning process in the intelligent assisted syndrome differentiation model of TCM.It organizes and analyzes authoritative documents on depression,acquires knowledge on syndrome differentiation of depression,and collects,screens and preprocesses medical records of depression.A DUCG knowledge base for depression intelligent assisted syndrome differentiation is constructed,in which the symptom knowledge,syndrome type knowledge and the relationship between them are expressed,and it combines DUCG inference machine to conduct testing and analysis of syndrome differentiation reasoning.It constructs a DUCG knowledge base for depression intelligent assisted syndrome differentiation containing 19 subgraphs and a DUCG core knowledge base for depression intelligent assisted syndrome differentiation containing 6 subgraphs.The preliminary accuracy obtained through testing of syndrome differentiation reasoning can reach 72.92%,and the highest accuracy achieved by grouping statistics according to syndrome types can reach 100%.The syndrome differentiation results can be explained in detail according to the DUCG diagram.Applying DUCG theory to the research of intelligent assisted syndrome differentiation of TCM can help improve the visualization of syndrome differentiation knowledge and the interpretability of syndrome differentiation reasoning process in syndrome differentiation models.