科技情报研究2026，Vol.8Issue(1)：45-56,12.DOI:10.19809/j.cnki.kjqbyj.2026.01.005
基于知识图谱链路预测的西药药物风险知识发现
Drug Risk Knowledge Discovery for Western Medicines Based on Knowledge Graph Link Prediction
摘要
Abstract
[Purpose/significance]The risk information contained in drug instructions is usually incomplete,and some new adverse reactions can only be discovered in actual clinical use.This paper proposes an information organization and knowledge discovery method for pharmacovigilance,in order to timely and accurately identify missing risk knowl-edge in drug instructions.[Method/process]Drug instructions of 8 152 Western medicines are collected as the research data;On the basis of ontology construction,data annotation,and model training,the UIE model is used to jointly ex-tract entity and relationship triplets from the research data;A new knowledge graph link prediction method Comp-GCN-RotatE,is proposed,and performance comparison experiments are conducted with classical RotatE on multiple datasets;Empirical research is conducted by using the proposed method.[Result/conclusion]Compared to the classical Rotate method,research results show that our method has significant improvements in the three indicators,MRR,Hits@3 and Hits@10,and achieve performance of 58.7％,65.6％and 80.5％respectively on the research data.The method proposed can effectively discover drug risk knowledge that is not mentioned in drug instructions but is actual-ly monitored,providing new ideas for pharmacovigilance in China.关键词
知识图谱/链路预测/知识推理/风险预测/药物警戒Key words
knowledge graph/link prediction/knowledge reasoning/risk prediction/pharmacovigilance分类
社会科学引用本文复制引用
魏建香,马恒远,孙越泓,杜文文,胡乐天..基于知识图谱链路预测的西药药物风险知识发现[J].科技情报研究,2026,8(1):45-56,12.基金项目
国家社会科学基金重点项目"面向药物警戒的领域知识库构建与应用研究"(编号:23ATQ009) （编号:23ATQ009）
江苏省社会科学基金一般项目"基于图谱融合的突发公共卫生事件跨领域影响机制研究"(编号:23TQB007). （编号:23TQB007）
