中医电子病历命名实体识别研究进展

打开文本图片集

中图分类号：TP391 文献标识码：A 文章编号：2096-4706（2025）15-0078-09

Abstract：Asaproductintegrating Traditional Chinese Medicine （TCM） theorywith moderninformationtechnologyTCM ElectronicMedicalRecords（TCM-EMRs）contain vastamountsofsemi-structuredorunstructuredclinical information，and their effcientutlizationreliesonNamed EntityRecognition （NER）inNaturalLanguage Processing.This papersystematically reviews theresearch progressofTCM-NERtechniques，clarifyingitscoretaskofidentifying keymedicalentities （e.g.，diseases， symptoms，and drugs）from textsand transforming them into structured data to support applications such as knowledge graph construction，intellgentdiagnosisndtreatment，andelationextraction.ItprovidesadetailedintroductiontoNERmethos basedondictionaries，rules，MachineLearning，andDeepLearning，summarizes themainchalengescurrentlyfaced byTCMEMRNER，andproposesfutureresearchdirections.Bysynthesizingtechnologicaladvancementsandexistingisues，thispaper offers theoretical references and practical pathways for subsequent research.

Keywords： Natural Language Processing; Traditional Chinese Medicine electronic medical record; Named Entity Recognition; Deep Learming

0 引言

中医是以中国古代哲学和自然观为基础，通过长期实践形成的独特的医学体系。（剩余21389字）