细粒度可循证医药学文档知识融合表示和推理  

Representation and Reasoning for Fine-Grained and Evidence-Based Medical and Pharmaceutical Document Knowledge

作　　者：高峰 龚珊珊[1,2,3,4] 顾进广 徐芳芳[1,2,3,4] GAO Feng;GONG Shanshan;GU Jinguang;XU Fangfang(School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,Hubei,China;Big Data Science and Engineering Research Institute,Wuhan University of Science and Technology,Wuhan 430065,Hubei,China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial,Wuhan University of Science and Technology,Wuhan 430065,Hubei,China;Key Laboratory of Rich-Media Knowledge Organization and Service of Digital Publishing Content,National Press and Publication Administration,Beijing 100038,China)

机构地区：[1]武汉科技大学计算机科学与技术学院,湖北武汉430065 [2]武汉科技大学大数据科学与工程研究院,湖北武汉430065 [3]武汉科技大学湖北省智能信息处理与实时工业系统重点实验室,湖北武汉430065 [4]国家新闻出版署富媒体数字出版内容组织与知识服务重点实验室,北京100038

出　　处：《武汉大学学报（理学版）》2023年第6期796-808,共13页Journal of Wuhan University:Natural Science Edition

基　　金：国家自然科学基金(U1836118);富媒体数字出版内容组织与知识服务重点实验室开放基金(ZD2020/09-01);湖北省教育厅科学研究计划指导项目(B2019009)。

摘　　要：知识图谱开放灵活、互操作性强,对于表达医学知识具有重要价值,但现有医学知识本体模型存在过于关注概念体系构建、深层次医学知识及关联缺失、无法循证和难以跨病种和学科等不足,为解决以上问题,提出了一种支持全文内容与结构细粒度知识和知识论证与循证关系表示的医药学融合知识表示模型及其推理机制,构建了一个面向高血压专病的医药知识图谱来验证这一方法。结果表明,该模型能全面、一致地表达医药学文献、文档中的细粒度知识,同时支持可循证查询和推理。The knowledge graph has become essential for representing medical knowledge due to its openness,flexibility,and interoperability.However,the existing medical ontology excessively focuses on the constructing of conceptual hierarchy instead of capturing complete and fine-grained knowledge pertained in medical documents.Moreover,evidence-based medical knowledge representation and reasoning support are also limited.In addition to the shortcomings of being non-evidence-based,challenging to cross-patients,and difficult to extend cross-disciplines.This paper addresses these issues by introducing a novel knowledge representation framework for medical and pharmaceutical documents.This framework supports fine-grained and evidence-based knowledge representation and reasoning.In addition,hypertension-oriented medical knowledge is established using relevant medical guidelines and drug instruction documents to evaluate the method.

关 键 词：知识图谱 医学知识 细粒度 可循证 推理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]