<?xml version="1.1" encoding="utf-8"?>
<article xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><front><journal-meta><journal-id journal-id-type="publisher-id">EDTR</journal-id><journal-title-group><journal-title>Educational Theory Observation</journal-title></journal-title-group><issn>2995-5017</issn><eissn>2995-5025</eissn><publisher><publisher-name>Art and Technology</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.61369/EDTR.2026090040</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>融合分层知识图谱与加权图嵌入的中草药可解释处方推荐研究</title><url>https://artdesignp.com/journal/EDTR/4/9/10.61369/EDTR.2026090040</url><author>王鑫鑫</author><pub-date pub-type="publication-year"><year>2026</year></pub-date><volume>4</volume><issue>9</issue><history><date date-type="pub"><published-time>2026-09-20</published-time></date></history><abstract>针对现有中草药处方推荐模型存在中医理论约束缺失、模型黑盒不可解释、小样本医案泛化能力弱、君臣佐使配伍逻辑建模不足等问题，本文构建分层式中草药知识图谱，提出面向方剂配伍的分层加权图嵌入算法，并搭建融合辨证论治、君臣佐使规则的知识增强推荐框架。对比实验结果表明，相较主流基线模型，本文模型 Top5召回率提升10.27%，方剂君臣佐使结构合规率提升16.53%，在罕见证候小样本场景下识别稳定性显著优于对比方法。</abstract><keywords>中草药, 知识图谱, 图嵌入, 君臣佐使, 可解释推荐, 小样本学习</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[1]WANG W Y, ZHOU H, WANG Y F, et al. Current policies and measures on the development of traditional Chinese medicine in China [J]. Pharmacological Research, 2021,163: 105187.
[2]YAO L, ZHANG Y, WEI B. A Topic Modeling Approach for Traditional Chinese Medicine Prescriptions [J]. IEEE Transactions on Knowledge and Data Engineering, 2018,30 (6): 1007-1021.
[3]王斌，刘涛，王广志 . 支持新型冠状病毒肺炎的中医智能处方推荐和知识库系统 [J]. 中国数字医学，2020, 15 (5):25-27.
[4]LI W, YANG Z. Exploration on Generating Traditional Chinese Medicine Prescriptions from Symptoms with an End-to-End Approach [C]//NLP-CC, 2019.
[5]LI C, LIU D, YANG K. Herb-Know: Knowledge Enhanced Prescription Generation for Traditional Chinese Medicine [C]//2020 IEEE International Conference on Bioinformatics and Biomedicine, 2020.
[6]WANG X, LIU S. LLM-GCN Fusion Model for Traditional Chinese Medicine Prescription Recommendation [C]//2023 IEEE International Conference on Bioinformatics and Biomedicine, 2023.
[7]ZHUANG Y, LI M. TCM-PG: GAT and LLM Integrated Intelligent Prescription Generation Model with Dual Compatibility Constraints [J]. KSII Transactions on Internet and Information Systems, 2024,20 (5):2368-2389.
[8]WEN Z H, DONG Y C, PENG L H, et al. PRDAGE: Prescription Recommendation Framework Based on Multi-Graph Embedding and Medical Record Augmentation [J]. PeerJ Computer Science, 2025, 11:e2974.
[9]WANG W Y, ZHOU H, WANG Y F, et al. Current policies and measures on the development of traditional Chinese medicine in China [J]. Pharmacological Research, 2021,163: 105187.</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
