TCM LLM · Patents
TCM LLM patents
Invention patents on TCM LLMs, knowledge graphs, RAG, intelligent inquiry, and prescription recommendation—not a dump of herbal-formula patents.
基于生成式模拟医案构建的定制化中医处方推荐大模型
A rule engine enumerates structured TCM features, an LLM turns them into simulated cases, and those cases fine-tune a customized prescription model (published, not granted).
一种面向中医药知识图谱的综合质量评估方法
Sends a small sample to a TCM-tuned large model for a preliminary quality check of a TCM knowledge graph (published, not granted).
TCM dialogue generation with a large language model and long-term memory
Generates personalized TCM dialogue from a long-term memory bank and user portrait (published, not granted).
一种融合时空特征的针灸推理模型构建方法、系统及设备
Aligns four-examination and course features, retrieves past acupuncture plans, and uses a fine-tuned LLM with chain-of-thought for an explainable plan (published, not granted).
基于知识图谱与大语言模型的脾胃学派理法方药分析系统
Combines a spleen-stomach school knowledge graph, vector retrieval, and an LLM for formula selection, safety checks, and prescription writing (published, not granted).
一种基于大语言模型的中医古籍症状标准化处理方法
An LLM finds candidate symptom spans in sliced classical TCM texts and maps them into a standard symptom semantic field (published, not granted).
Digital inheritance and analysis of Zhang Xichun's theory, method, formula, and herbs
Rule engine plus three-way retrieval and an LLM for Zhang Xichun school analysis (published, not granted).
一种面向中医方剂推荐的知识图谱大模型问答方法及系统
Encodes a case with a Chinese instruction LLM, fuses it with a dynamic TCM knowledge graph, and returns formula recommendations as answers (published, not granted).
基于大语言模型的中医智能问诊方法及系统
Intent is parsed from multimodal inquiry data, then dual-path retrieval over TCM knowledge produces the consultation result (published, not granted).
基于多模态中医大语言模型的数据分析方法、系统、终端及介质
Trains a multimodal TCM large model on tongue images, speech, and inquiry text, then outputs a preliminary TCM analysis (granted June 2026).
辅助诊断结果和参考处方生成方法、装置、介质及计算机设备
Recalls similar records and treatment rationales on four paths, then a large model drafts TCM diagnosis, syndrome pattern, and a reference prescription (published, not granted).
一种基于图注意力网络与大语言模型的中药处方生成方法
Herbal prescription generation is cast as multi-label classification, with graph attention and an LLM modeling drug synergy and contraindications (published, not granted).
基于多模态大模型的中医舌诊药饮推荐方法
A multimodal model turns a tongue image into a condition description and a medicinal-drink recommendation (granted May 2026).
Causal contrastive learning and LLM graph attention for TCM prescription recommendation
Heterogeneous and homogeneous symptom-herb graphs plus an LLM-enhanced causal mechanism (published, not granted).
Multi-task joint optimization for TCM prescription generation
A pretrained LLM predicts herb sequences and herb sets jointly, with extra weight on rare herbs (published, not granted).
LLM-based intelligent acupuncture diagnosis agent
Acupuncture knowledge bases, graph, vector search and reranking, with an LLM agent that classifies questions and asks follow-ups (published, not granted).
TCM diagnosis-and-treatment platform combining an LLM with dual-channel retrieval
LLM plus TCM knowledge-graph dual-channel retrieval for inheriting master-physician experience and generating formulas (published, not granted).
Knowledge-graph and LLM system for TCM syndrome-differentiation QA
Chunks classics and cases, extracts a graph, then retrieves local and global keywords for syndrome-differentiation answers (published, not granted).
一种基于视觉语言模型的中医舌诊智能分析方法
Fine-tunes Qwen-VL with tongue-diagnosis prompts so a tongue image yields structured color and coating labels plus a natural-language reading (published, not granted).
Structured evidence-subgraph RAG for TCM herb recommendation
Multi-hop evidence subgraphs plus Hopfield associative retrieval for herb recommendation, with graph constraints against hallucination (published, not granted).
Knowledge-enhanced generation of TCM case commentaries
Retrieves knowledge-graph subgraphs, then writes case notes along etiology, treatment principles, formulas, and prognosis (published, not granted).
一种心血管疾病的基于针灸诊疗知识图谱的智能问答系统
Builds a cardiovascular acupuncture knowledge graph and sends hits to a cloud LLM for wording; if retrieval fails, the LLM answers with a caution (published, not granted).
一种基于人工智能的方剂配制方法、系统、介质和设备
An LLM maps case entities to disease and syndrome, drafts a formula, scores it, and regenerates from structured advice until the score passes (published, not granted).
一种基于动态语义分块、知识图谱与多跳路径规划的中医大语言模型AI题库智能生成方法及系统
Chunks TCM text, plans multi-hop paths on a knowledge graph, and trains a large model to generate a TCM question bank (published, not granted).
一种基于中医语言大模型的中医智能分析方法及系统
LoRA-tunes a TCM language model that maps syndrome and chief complaint to a formula (published, not granted).
Knowledge-distillation and RL for oncology TCM prescription recommendation
Distills GPT-4o into a Qwen student, then DPO, for interpretable oncology TCM prescriptions (published, not granted).
一种融合舌象、心率及文本的多模态健康状态评估方法
Takes tongue image as the main signal, adds heart rate and self-reported text, and prompts DeepSeek to write a health-status assessment (published, not granted).
基于大语言模型的经络辨证与针灸方案生成方法及系统
Multi-source clinical data are quantified and cleaned, then a meridian-syndrome knowledge base and an LLM generate acupuncture plans (published, not granted).
Multimodal knowledge-graph construction from TCM texts and records
An LLM extracts triples from TCM texts, then fuses a real-world case layer into a multimodal graph (published, not granted).
一种基于大语言模型的人-信息-物理三元数据融合中药制造知识图谱构建系统、电子设备及存储介质
An LLM extracts triples from manufacturing text under TCM term and relation constraints, then a human-cyber-physical ontology assembles a manufacturing knowledge graph (published, not granted).
基于检索增强生成的针灸大模型构建方法、系统及装置
An acupuncture LLM answers questions from vector-retrieved knowledge snippets and, for diagnosis requests, retrieves treatment entries from an acupuncture-plan library (published, not granted).
一种基于多模态大语言模型的中医临床辅助决策系统和方法
Tongue-image features are fused with clinical text, similar cases are retrieved, and a multimodal LLM drafts syndrome, diagnosis, herbal prescription, and reasoning (published, not granted).
Knowledge-graph recommendation of classic TCM formulas
Maps colloquial symptoms to terms, filters by constitution, and recommends classic formulas (granted).
大小模型协同中药方剂优化方法、系统、终端及存储介质
A formula-optimization LLM proposes a macro revision, a smaller pharmacologic model traces constituent herbs, and the two are merged into a final formula (published, not granted).
融合动态知识图谱的针灸大模型辨证方法及调理优化系统
A dynamically updated acupuncture knowledge graph is combined with time-series clinical features, graph attention, and reinforcement learning to differentiate syndromes and draft acupuncture plans (published, not granted).
中医药多模态LLM训练方法及其应用
Extracts tongue-coating and pulse features, fuses them with text by cross-modal attention, and trains a multimodal TCM large language model (granted).
基于大语言模型的中医五音疗疾个性化音乐生成系统及其构建方法
An LLM first performs TCM syndrome differentiation, then generates personalized five-tone therapy music under tonal constraints (published, not granted).
针灸穴位推荐方法及其模型获取方法、装置、设备及介质
Trains a language model on medical records so symptoms map to acupuncture points, then applies parameter tuning and policy optimization (published, not granted).
一种基于大模型的中药分类方法
Entities from multi-source herbal data are mapped to modern pharmacological indicators, then a pretrained large model is adaptively fine-tuned to classify herbs (published, not granted).
一种基于大模型智能体协作规划的中医诊断场景模拟方法
Turns unstructured case records into structured knowledge, then large-model agents collaborate to simulate a TCM diagnostic encounter (published, not granted).
基于大语言模型的中药药物警戒问答系统的构建方法
A Chinese-materia-medica knowledge base trains the pharmacovigilance RAG model PV-RAG to answer natural-language safety questions (published, not granted).
基于胸肺科中医问诊报告大语言模型的中医方剂推荐方法和系统
Shared knowledge domains fine-tune a chest-and-lung TCM inquiry LLM that outputs constitution and symptom parameters and recommends food-medicine formulas (published, not granted).
一种基于大模型的心血管疾病医疗决策支持方法
A pretrained large model fuses TCM syndrome knowledge with a Western pathology graph to propose cardiovascular decisions that include Chinese herbal formulas (published, not granted).
Knowledge-graph and case-enhanced RAG for intelligent TCM inquiry
Leiden subgraph search plus hybrid global/local recall, then a single LLM response (published, not granted).
AI-LLM method and system for intelligent TCM inquiry
Multimodal inquiry fusing face/body/tongue images, speech prosody, and a disease library (granted).
Multimodal knowledge-graph and LLM system for TCM rehabilitation diagnosis
Aligns tongue, pulse, and inquiry features with knowledge-graph embeddings before a rehabilitation expert LLM (published, not granted).
基于多源特征融合的中医方剂智能推荐方法、介质和设备
Blends content-based recommendation, collaborative filtering, and an LLM reading of symptom text to rank personalized formulas (published, not granted).
一种基于OCR识别和大模型的中药方数据解析方法及装置
Handwritten herbal prescriptions are OCR'd into prompts on incompatibility, dosage, and administration, which a large model scores into an overall judgment (granted 20 June 2025; application published 11 April 2025).
应用大语言模型的泌尿科中医问诊结果预测方法和系统
An LLM predicts core lesion keywords from urological TCM inquiry text and adjusts its parameters from recorded feedback (granted 6 March 2026; application published 11 April 2025).
一种用于智能中医系统的大语言模型的构建方法
Labeled tongue images and historical records train a tongue-inquiry model used to construct an LLM for an intelligent TCM system (granted).
LLM-based Chinese-medicine prescription recommendation with soft prompts
Soft prompts and cross-attention feed patient text into an LLM for controllable herb recommendations (published, not granted).
一种基于大语言模型的中医问答系统及方法
A dataset built from TCM literature trains an LLM that takes a user's medical question and returns a dialogue answer (published, not granted).
一种基于大语言模型的中医知识图谱生成方法及系统
A model trained on herbal and consultation data visualizes treatment options for a patient and is updated from outcome ratings (published, not granted).
LLM method for learning famous-physician TCM formulas
Aligns classical-Chinese case terms with vernacular text using models such as Qwen (published, not granted).
利用AI大模型进行舌象分析的方法及装置
Uses a large model to read tongue images by constitution, symptoms, and an overall interpretation (published, not granted).
LLM and knowledge-graph method for TCM formula compatibility
Pairs a TCM LLM with a knowledge graph for formula compatibility (published, not granted).
LLM-based Chinese-materia-medica question answering
Chinese-materia-medica QA fine-tuned from Baichuan2-7B-Chat (granted February 2025).
一种基于多模态大模型的中医舌诊分析系统及方法
Tongue- and face-image instructions fine-tune a general LLM such as LLaMA into TongueLMM for tongue interpretation, multi-turn QA, and constitution reasoning (published, not granted).
基于AI大模型智能人体域网的中医六经辨证智能对话健康管理系统
A six-meridian TCM dialogue system over a body-area network and a large model (published; deemed withdrawn on 6 February 2026).
基于AI大模型的中医元气充盈智能健康管理系统
Converts wearable signals into TCM terms and passes them to a TCM large model (published; deemed withdrawn on 6 February 2026).
Building a TCM QA system from a large language model and a knowledge graph
Closed loop of LLM generation and knowledge-graph completion for TCM QA (published, not granted).
以大语言模型为先验的智能中医系统
An LLM rewrites patient diagnostic text, which is then semantically interpreted to predict TCM syndromes and causes and to suggest treatment (granted).
一种基于大语言模型的中医知识深度挖掘方法
Retrieval augmentation and model fine-tuning are trained together so the system can explain TCM terms and syndromes and suggest treatment from a patient query (published, not granted).
一种基于计算视觉与大语言模型辅助中医诊疗的系统
An LLM handles spoken inquiry while computer vision converts patient images into findings that are retrieved and fed back to the LLM for TCM decision support (published, not granted).
Long-document retrieval-augmented generation for TCM question answering
Long-document RAG (expansion, recall, reranking, source citations) for TCM QA (granted July 2024).
AI-large-model system for intelligent TCM prescription recommendation
Trains an AI large model on medical records to recommend personalized TCM prescriptions, wired into a hospital IS (published, not granted).
一种基于大语言模型的针灸辅助诊疗和模型评价的方法
ChatGLM3-6B is fine-tuned on labeled symptoms, points, and operations to propose acupuncture plans, which are scored by sentence similarity (published, not granted).
一种基于大语言模型的中医客服回复系统
Synonym-augmented TCM text trains a Transformer LLM that is fine-tuned to parse customer requests and draft replies; the application was granted as CN118070907B on 2024-07-09.
一种基于大语言模型的中医知识图谱构建方法
An LLM extracts named entities and relations from TCM text, merges similar entities, and builds a TCM knowledge graph (published, not granted).