中医典籍知识图谱

本产品通过先进的文本挖掘和自然语言处理技术，对1100多部中医古籍中记载的有效个案进行病证理法方药靶的条文分类、实体的识别和概念术语的归一化处理。建立了中药成分、靶点、药物、疾病之间的相互关系，并与TCMID2、TCMSP、DrugBank、HERB、MedDra等公开数据库概念映射。基于知识图谱实现了经典古方智能检索和推荐系统，提高专科专病验方、有效成分、副作用等的挖掘和筛选效率。This product leverages advanced text mining and natural language processing technologies to classify text passages related to syndrome and disease differentiation, pathogenesis, treatment principles, formulas and therapeutic targets from over 1,100 effective clinical cases recorded in ancient Chinese medical classics, identify relevant entities, and perform normalization processing for conceptual terms. It establishes interrelationships among traditional Chinese medicine (TCM) ingredients, therapeutic targets, medicinals and diseases, and conducts concept mapping with publicly available databases including TCMID2, TCMSP, DrugBank, HERB and MedDra. Based on the constructed knowledge graph, an intelligent retrieval and recommendation system for classic ancient formulas has been developed, which improves the efficiency of mining and screening targeted prescriptions for specific specialties and diseases, active ingredients, adverse reactions and other related contents.