法医学杂志2026，Vol.42Issue(2)：102-111,10.DOI:10.12116/j.issn.1004-5619.2025.451106
法医病理多模态数据库构建与模型增强式检索的实现
Construction of a Multimodal Forensic Pathology Database and Implementation of Model-Augmented Retrieval
摘要
Abstract
Objective To construct a multimodal forensic pathology database based on artificial intelli-gence(AI)technology and explore methods for integrating pre-trained models into multimodal data-bases.Methods A hybrid storage architecture consisting of MySQL,Redis and OSS was employed to manage desensitized multimodal data.Data entry was optimized using optical character recognition(OCR)and natural language processing(NLP)technologies.OCR performance was evaluated and opti-mized using cosine distance,character error rate(CER),and word error rate(WER)to meet practical operational requirements.An intelligent retrieval model was developed using the ChatGLM3-6B model and retrieval-augmented generation(RAG)technology.Model performance was evaluated using ranking metrics including Precision@K,Recall@K,discounted cumulative gain(DCG),and normalized dis-counted cumulative gain(NDCG).Results The database demonstrated satisfactory baseline performance.The response times were maintained within 150 ms for single-query condition and within 2 s for multiple-query conditions.The average disk read throughput reached 950 MB/s.In concurrent performance tests,the database achieved a maximum throughput of 1 200 queries per second(QPS),meeting multimodal data management demands.OCR evaluation showed high recognition accuracy;for high-quality docu-ments,the cosine distance,CER,and WER achieved 0.02,1.5%,and 3.2%,respectively.Intelligent re-trieval results indicated that Precision@K remained consistently high(0.69-1.00),while NDCG values remained above 0.87 for all evaluations.When K=100,the NDCG surpassed 0.95 for all queries,meeting expected performance requirements.Conclusion The multimodal forensic pathology database constructed in this study demonstrates good stability and operational efficiency and can meet the requirements of routine forensic practice for multimodal data storage,management,and analysis.The intelligent re-trieval capabilities,based on pre-trained large language models(LLMs),can be applied to conversa-tional information retrieval from forensic reports and related documents,providing a novel approach to the management and analysis of multimodal databases.关键词
法医病理学/多模态数据/数据库/人工智能/大语言模型/信息检索Key words
forensic pathology/multimodal data/database/artificial intelligence(AI)/large language model(LLM)/information retrieval分类
医药卫生引用本文复制引用
秦豪杰,付恩浩,杨永超,刘雅雯,贾明珠,田志岭,郑哲,郭思云,刘宁国..法医病理多模态数据库构建与模型增强式检索的实现[J].法医学杂志,2026,42(2):102-111,10.基金项目
广东省证据材料司法鉴定(南天)工程技术研究中心2025年度开放课题基金项目(ETRC202502) （南天）
中央级公益性科研院所专项(GY2024D-1,GY2024Z-1) （GY2024D-1,GY2024Z-1）
上海市法医学重点实验室资助项目(21DZ2270800) （21DZ2270800）
河南省自然科学基金项目(252300420591) （252300420591）
