556results about "Medical references" patented technology

The invention provides a medical text big data intelligent labeling and knowledge graph construction method and system, and relates to the technical field of medical text processing, and the method comprises the steps: recognizing entities in a medical text through a pre-trained deep bidirectional coding model and a multi-level entity recognition network, and carrying out the normalization processing in combination with a medical knowledge base, according to the method, the semantic association degree between entities is calculated, a relation extraction result is optimized based on comparative learning, comprehensive relation representation is obtained through fusion of multi-granularity coding and a gating mechanism, the entity relation is determined in combination with an inference rule network, a medical knowledge graph is constructed based on an initial knowledge graph, and the accuracy of medical text entities and relation labeling can be effectively improved. And a more perfect medical knowledge graph is constructed, which is helpful for assisting medical diagnosis and decision making.

The invention discloses a medical information multi-agent expert thinking chain collaborative reasoning method and system, and the method comprises the steps: constructing a sub-expert agent and a summarizer agent based on a large language model, processing the medical information, and outputting a processing conclusion of the medical information; and secondly, constructing an evaluator agent, performing medical information conflict evaluation on the output of the sub-expert agent and the summarizer agent, activating a multi-agent debate mechanism when the conclusion output of the summarizer agent exceeds a medical conflict threshold, and outputting whether a processing conclusion is credible or not. Then constructing a coordinator agent, selecting called sub-expert agents and summarizer agents, and generating a plurality of forward reasoning thinking chains; and finally, the evaluator agent evaluates whether the output of the forward reasoning thinking chain exceeds a medical conflict threshold, and iteratively updates an output processing conclusion. According to the method, complex problems in medical information processing problems can be analyzed, and reasoning accuracy and interpretability are remarkably improved.

The invention provides a disease science popularization error correction method and system based on artificial intelligence. According to the method, the disease knowledge query content input by the user and the associated science popularization text data source are obtained, the semantic focus is dynamically recognized by utilizing the pre-trained language model, and the context-associated semantic focus distribution graph is generated. On the basis of cross-modal correlation analysis of a map and multi-source heterogeneous medical representation, a potential cognitive deviation region is positioned, and an error correction priority queue is constructed in combination with authority weight differences of medical knowledge nodes. Incremental correction is further carried out on the error expression according to the queue priority, and an error correction feedback result containing medical traceability information is generated while the original semantic intention of the user is reserved; according to the technical scheme provided by the invention, high-precision error correction of disease science popularization content and closed-loop feedback of medical traceability information are realized, and user cognition accuracy and knowledge credibility are improved.

The invention relates to the technical field of computers, and discloses an integrated information system for clinical test archives and a data processing method thereof, and the method comprises the steps: constructing a standardized data model covering a whole process; multi-source data dynamic structured intake and integrity verification are carried out; performing multi-dimensional semantic association analysis based on a Bayesian network and a correlation coefficient; block chain type version tracing and difference comparison are carried out; performing role-sensitivity-operation-context four-dimensional access control; and task-driven collaborative sharing and auditing log records. The system comprises a unified modeling module, a data intake module, a semantic analysis module, a version tracing module, an access control module and a collaborative auditing module. The problems of data islands, semantic segmentation, poor dynamic adaptability, weak safety protection and the like in the prior art are solved, intelligent management, semantic interconnection, safety controllability and efficient collaboration of the whole life cycle of clinical test files are achieved, and data quality, audit compliance and multi-role collaboration efficiency are remarkably improved.

A system for the dynamic normalization of clinical terms and entity linking using a modular natural language processing (NLP) pipeline, consisting of: a preprocessing module configured to receive unstructured clinical text and perform operations such as de-identification, spelling correction, abbreviation expansion, and sentence segmentation; a tokenization and embedding processing unit configured to segment the preprocessed text into sub-word units and generate context-related embeddings using transformer-based biomedical language models; a processing unit for dynamic vocabulary expansion configured to update a specialized dictionary in real time by monitoring new abbreviations, acronyms, or institution-specific terms from incoming clinical data streams and feedback from clinical staff; a candidate concept generator configured to retrieve potential ontology mappings by performing an approximate nearest neighbor search via an embedding index linked to medical knowledge bases; a semantic disambiguation controller configured to evaluate candidate concepts using a graph neural network model that takes into account the local linguistic context, patient-specific metadata, and temporal relationships between entities; an ontology linking interface configured to map disambiguated entities to standardized concepts in one or more controlled vocabularies; and a feedback learning module configured to incorporate clinician corrections into the model parameters through reinforcement-based updates, thus enabling continuous self-improvement of entity normalization.

The invention discloses a diversified epiphyseal development map generation method and device based on a potential diffusion model. The method comprises the following steps: making a data set, covering and collecting an original X-ray film image, preprocessing data, labeling a skeleton maturity level and desensitizing the image; an original image is encoded to a potential space by using a variational auto-encoder, and the image detail generation capability is improved by optimizing a loss function; a fuzzy learning module is introduced in the de-noising stage of the diffusion model, and the diversity of generated skeleton features is enhanced through operations such as batch normalization and random disturbance; a progressive alignment strategy is adopted, skeleton basic structure learning is emphasized in the initial stage, a skeleton grade evaluation network is introduced in the later stage, and skeleton detail features are emphasized; optimizing the generation model by using the skeleton recognition model; and inputting development levels, ages and genders of 14 skeletons, and generating a corresponding left-hand skeleton X-ray film image. According to the method, diversified and high-quality skeletal development images are generated through a potential diffusion model framework in combination with VAE optimization, an FLM module and a progressive alignment strategy, skeletal development features are truly reflected, the problems of detail loss and insufficient diversity in the prior art are solved, the method is particularly excellent in performance when sparse data and long-tail distribution are processed, and the method is suitable for large-scale popularization and application. And the authenticity of the generated image and the practicability of medical diagnosis are improved.

The invention provides an intelligent medical information system based on multi-system integration, a data security management method and device, electronic equipment and a storage medium, and is applied to the technical field of medical data processing. According to the method, three types of information including core security elements, multi-system heterogeneous adaptation (including HIS / LIS / EMR interface specifications and the like) and full-process auditing (including operation logs and the like) are obtained. Normalizing the core security elements by using technologies such as AI multi-mode privacy identification and the like to generate a standardized security baseline file; heterogeneous adaptation information is processed through a lightweight API connector and the like, and a multi-system security access scheme is formed. Associating the baseline file with the access scheme, and generating a full-life-cycle protection strategy in a zero-trust architecture; and processing the audit information to generate a dynamic security audit report. And finally, based on a security-adaptation linkage decision engine and compliance verification, outputting a cross-system data security sharing scheme and a privacy disclosure emergency response instruction, and realizing a medical data security management closed loop.

The invention relates to a patient examination item recommendation method based on a medical knowledge graph. The method comprises the steps that firstly, historical data in the medical field is acquired, key information is extracted from the historical data to generate an entity relation triple, and then a medical knowledge graph is constructed; then, generating a patient state sub-graph based on patient input information, processing the medical knowledge graph by adopting an improved TransD model, and determining unique representation of an entity-relationship pair; mapping the patient state sub-map to a unique representation space, obtaining vector representation of a patient and an examination item related entity, and calculating a similarity value between vectors to obtain a similarity value matrix; and finally, performing priority ranking on the inspection items according to the matrix, and generating a final recommendation list through threshold screening and combination with graph neural network verification, optimization and adjustment of priorities. By adopting the method, examination items can be accurately recommended for patients, doctors are assisted to improve the treatment efficiency, the queuing time of the patients is shortened, and the medical experience of the patients is remarkably improved.

The invention discloses an accurate structured representation and semantic comparison method for traditional Chinese medicine situational information. The method comprises the following steps: constructing a situational dimension semantic rich network; key dimension information is extracted from a traditional Chinese medicine situation text through a thinking chain structuring module and is converted into a structured situation text, and then multi-level dimension features are extracted through a situation information coding module; then, in-layer context information and inter-layer multi-dimensional information are captured through an in-layer context information enriching module and an inter-layer information intersection module in sequence to obtain semantic-rich context semantic features; training the context dimension semantic rich network and carrying out context semantic comparison; according to the method, the traditional Chinese medicine semantic understanding ability of a general Chinese large language model is mined in combination with a thinking chain prompt tuning method, traditional Chinese medicine situation information is accurately extracted, meanwhile, multi-level traditional Chinese medicine situation dimension information is fused to obtain situation semantic features with rich semantics, the accuracy of traditional Chinese medicine situation semantic comparison is improved, and the traditional Chinese medicine situation semantic comparison efficiency is improved. And valuable reference situations are provided for traditional Chinese medicine clinicians.

The invention discloses a chronic disease risk prediction method and system fusing a knowledge graph and a large language model, and the method comprises the following steps: obtaining a natural language problem related to a chronic disease, and carrying out the semantic analysis; according to the analysis content, hypothetical questions and answers related to chronic diseases are generated through a large language model, and key entities are extracted; mapping the key entities to corresponding nodes in a medical knowledge graph, exploring a semantic path and a causal relationship between the key entities, and constructing an inference chain pointing to potential disease risks from acquired information; introducing a fragment granularity sensing mechanism, performing fine granularity analysis on each fragment in the reasoning chain, and rearranging and optimizing a link sequence; and based on the optimized inference chain, converting the question and answer result into a structured diagnosis result for visual display. According to the method, the whole process from question asking to answer generation of the patient is optimized, the efficiency and accuracy of chronic disease risk prediction are effectively improved, and meanwhile, personalized health management service is provided for the patient.

The invention relates to the technical field of intelligent medical treatment, in particular to a household intelligent health management system and a method thereof.The system collects household environment parameters and user physiological indexes through a data collection subsystem, constructs a medical knowledge graph of a three-layer structure through a knowledge graph driving subsystem, and dynamically updates the medical knowledge graph; the multi-target health intervention subsystem generates a candidate intervention scheme set based on a knowledge graph, the digital twinborn verification subsystem predicts and selects a scheme with a health improvement index higher than a target by establishing a user, environment and interactive twinborn model, and the adaptive interaction subsystem pushes the verified scheme to a user in a personalized manner and collects feedback information. Meanwhile, the digital twinborn verification subsystem transmits the feedback information to the knowledge graph driving subsystem to trigger dynamic updating of the knowledge graph, the system comprehensively collects health influence factors, comprehensive data support is provided for health risk assessment, and personalized health management is achieved.

A computer-implemented system and computer instructions stored on non-transitory computer readable medium for bilingual medical inquiry in both Arabic and English, including multiple-choice question answering, open-ended question answering, and multi-turn question answering. The system and instructions use a mixture of experts large language model (MOE LLM) having a router network connected to multiple expert networks. The MOE LLM is trained with medical domain data and is used to receive the input bilingual text in a format for a medical inquiry, and output text in a format of a response to the medical inquiry, in sequence. The system and instructions incorporate an English-to-Arabic translation pipeline having a language translation model to generate Arabic language medical instruction sets from English language medical instructions, for large scale use in Arabic and English medical inquiry.

The invention discloses a cognitive disorder early screening and diagnosis system based on multi-modal data, and the system comprises the following modules: (1) a multi-modal data collection module which is used for obtaining image data, gene data, behavior data and clinical narrative information; the clinical narrative information comprises at least two of a patient chief complaint text, an interference factor hooking option and a symptom time axis; the causal purification module is used for filtering pseudo-correlation among the multi-modal data through clinical narrative anchoring and reverse intervention deduction, and comprises a narrative anchoring unit which is used for identifying data conflicts through a structured clinical narrative field based on a preset causal conflict rule base, and triggering freezing or weight descending operation; the intervention deduction unit is used for generating a reverse intervention verification packet containing a low-cost intervention measure and a review plan, and updating a causal rule base based on review data; according to the method, the statistical association limitation of the traditional technology is broken through, and the diagnosis and treatment normal form upgrading from correlation to causality is realized.

The invention discloses a medical document slicing and retrieval method and device, equipment and a storage medium, and the method comprises the steps: generating a high-fidelity semantic summary text and a child node of a structured keyword set through a father node containing an original complete paragraph text, and storing the child node to a vector database; storing the semantic summary text and the structured keyword set into a keyword database; and when a user query instruction is received, performing dual-channel retrieval through the vector database and the keyword database, obtaining related target child nodes, extracting target original contents of a target father node from the target child nodes, transmitting the target original contents to the large language model, generating a final answer, and sending the final answer to the user. According to the method, the relevance and accuracy of retrieval results can be remarkably improved, instant and accurate decision support basis is provided for doctors, semantic integrity can be reserved, efficient multi-modal retrieval can be achieved, and the speed and efficiency of medical document slicing and retrieval are improved.

The invention provides a medical information retrieval enhancement method and device based on a large model and related equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: in response to a medical information query request, executing double-path joint retrieval of keywords and semantics in a pre-constructed medical knowledge base to obtain a candidate data set containing at least one medical information query result, the medical knowledge base is a database which analyzes the multi-modal medical data based on a multi-modal medical data deep analysis large model and is constructed according to the analyzed medical text data; and adopting a plurality of sorting tools to resort the medical information query results in the candidate data set, and performing fusion processing on a plurality of resorting results obtained by resorting to obtain a medical information query result after retrieval enhancement. According to the method and the device, the precision improvement and response efficiency optimization of medical knowledge retrieval can be realized, a high-credibility knowledge enhancement service is provided for a clinical decision support system, and the method and the device have important application value.

The invention provides a personalized precise nutrition recipe recommendation method and system based on a genetic algorithm, and the method comprises the steps: inputting various personal information, including gender, age, weight, height, and nutrition risk information (lack of nutrients, risk genes or risk SNP ID), all the personal information being dynamically linked together, and quantitative nutrient demands are generated for specific individuals according to the resident dietary nutrient reference intake and a pre-constructed nutrient-gene interaction database. A food nutrient composition database is pre-constructed on the system and comprises various foods from four different countries and nutritional ingredients of the foods. And then, according to individual quantitative nutrient requirements, selecting and combining food by writing a genetic algorithm, iteratively perfecting the combination of food types and food amounts, and finally outputting an accurate nutrition recipe meeting individual nutrition requirements.

The application discloses a kind of cognitive impairment early screening and diagnosis system based on multi-modal data, including following module: (1) multi-modal data acquisition module, for obtaining image data, gene data, behavior data and clinical narrative information;The clinical narrative information includes at least two kinds of patient complaint text, interference factor hook item, symptom time axis;(2) causal purification module, for filtering the pseudo-correlation between multi-modal data by clinical narrative anchoring and reverse intervention deduction, including: narrative anchoring unit: based on preset causal conflict rule base, through structured clinical narrative field identification data conflict, trigger freezing or weight reduction operation;Intervention deduction unit: generate the reverse intervention verification package containing low-cost intervention measures and review plan, and update causal rule base based on review data;The application breaks through the statistical correlation limitation of traditional technology, realizes the upgrade of diagnosis and treatment paradigm from "correlation" to "causality".

The invention discloses a chronic disease high-risk population health management system, and the system comprises a task management module which is used for creating a target task and distributing the task to a basic medical institution; the task management module is used for collecting information of risk personnel for the first time and dividing the risk personnel to corresponding risk levels; the intervention management module is used for periodically collecting various behavior data and health data of the risk personnel and feeding back intervention suggestions in real time according to the collected data, and meanwhile, the intervention management module is used for combining and comparing the data in various stages and dynamically evaluating the intervention suggestions so as to continuously optimize the guidance suggestion library; and the follow-up management module is used for periodically reminding risk personnel to fill corresponding data and reminding personnel with different risk levels to perform offline follow-up with different frequencies so as to further provide personalized intervention suggestions. Management of the system can help risk personnel to gradually change bad living habits and behavior modes, and therefore the purpose of preventing or delaying development of chronic diseases is achieved.

The invention belongs to the technical field of artificial intelligence, and aims to provide a knowledge question answering method and system, electronic equipment and a computer program product. The method comprises the following steps: receiving user input information of a target user, and sequentially performing feature extraction processing and intention retrieval processing on the user input information to obtain a user intention tag; obtaining a target agent matched with the target user and an anthropomorphic instruction, carrying out intention matching processing on the user intention label and the target agent by adopting a preset routing module, and if the user intention label hits skilled intention information of the target agent, carrying out question-answer matching processing on the user intention label and pre-stored question-answer template data, and target answer data is obtained, the target answer data and the personification instruction are sent to a preset base large model reasoning module for rewriting processing, and a question and answer output result is obtained. According to the method, the real-time reasoning cost can be reduced, the reasoning delay is reduced, and the anthropomorphism of the question and answer output result can be improved.

The invention provides a multi-agent medical examination recommendation system and method, and relates to the technical field of medical intellectualization. Comprising a medical examination recommendation data set building module used for extracting key medical entities and personal information of patients from electronic medical records of an intensive care medical information database, and generating enhanced patient sequence data by using the key medical entities and a preprocessing mode; the medical knowledge graph building module is used for building a medical knowledge graph according to the disease and the triple generation module based on the large language model; and the medical examination recommendation module is used for processing the enhanced patient sequence data and personal information by utilizing a plurality of intelligent agents and a medical knowledge graph to obtain a target medical examination item. In this way, structured medical examination data can be provided, and the quality of a data set is high; multiple agents are introduced, so that the flexibility and adaptability of the recommended target medical examination items are improved; and the reasonability of the recommendation result is improved by utilizing the established medical knowledge graph.

A system determines a finding item template based on a current report's characteristics. The system parses and categorizes text from prior reports into finding items using the template's criteria, displaying categorized phrases in a user interface. This enhances consistency and speed of reporting, allowing users to edit finding items and apply AI feature detection to images.

The invention relates to the field of intelligent medical treatment, in particular to a traditional Chinese and western medicine multi-modal data association network construction method and device and a program product. Comprising the steps of S1, acquiring a traditional Chinese medicine inquiry data set and a western medicine clinical data set of a patient; s2, performing first feature extraction on the traditional Chinese medicine inquiry data set to obtain N time sequence traditional Chinese medicine features X1, wherein N is the number of doctor seeing times; s3, performing second feature extraction on the western medicine clinical data set to obtain N time sequence western medicine features Y1; s4, the correlation between the Mth time sequence traditional Chinese medicine feature and the Mth time sequence western medicine feature is calculated to obtain a traditional Chinese medicine related feature X2 and a western medicine related feature Y2 which have an incidence relation, M is smaller than or equal to N, Y2 is smaller than or equal to Y1, and X2 is smaller than or equal to X1; and S5, taking the Western medicine related features as labels, obtaining the traditional Chinese medicine related features corresponding to each Western medicine related feature based on the association relationship, and generating an N * Y2 Western medicine related feature-traditional Chinese medicine related feature association network. The application has good clinical value.

The invention discloses a medical question-answering system based on a large language model, belongs to the field of large language models in artificial intelligence in the field of computers, and particularly relates to the medical question-answering system based on the large language model. The objective of the invention is to solve the problems of low answering accuracy and poor medical problem solving ability of a general large language model in the medical field. The system comprises a large language base module used for selecting an open source large language model of a general field as a base model; the knowledge instance sampling module is used for sampling knowledge instances from the knowledge graph; the question-answer data generation module is used for generating question-answer data according to the knowledge instances by using a large language base model; the large language base model fine tuning module is used for performing fine tuning on the large language base model by using the generated question and answer data to obtain a fine-tuned large language base model; and the reply generation module is used for answering the to-be-processed medical knowledge question based on the fine-tuned large language base model.

The invention provides an auxiliary system for a rheumatoid arthritis medication scheme. The auxiliary system is used for matching similar historical medication schemes, related medication costs and treatment results used for treating historical rheumatoid arthritis patients and judging whether transaminase abnormity occurs or not based on the treatment conditions of current patients, analyzing each historical medication scheme, and determining whether the transaminase abnormity occurs or not according to the analyzed historical medication schemes and the analyzed transaminase abnormity. And obtaining scores or grades of three dimensions of safety, effectiveness and economy of each historical medication scheme. And based on the requirements or tendencies of the patient on the medication schemes in three dimensions of safety, effectiveness and economy, screening out corresponding candidate medication schemes from the historical medication schemes and recommending the candidate medication schemes. According to the technical scheme, by means of the computer technology, the corresponding medication scheme is automatically recommended based on the medication tendency of the rheumatoid arthritis patient, decision assistance is provided, the time for adapting the medication scheme for the patient is saved, and the satisfaction degree of the rheumatoid arthritis patient to the medication scheme is improved.

The invention discloses a robot-assisted operation error detection method based on cooperative agent reasoning. The method comprises the following steps: constructing a multi-classification operation error system and a clinical informed knowledge base; based on a multi-classification operation error system and a knowledge base, a chain type reasoning prompt base is constructed according to different professional levels and analysis perspectives; for an input operation video clip, by calculating a composite risk score of a technical complexity score and a clinical influence score, allocating error instances of different risk scores to corresponding professional level reasoning paths; and deploying a time analysis agent, a space analysis agent and a process analysis agent for each professional level reasoning path, calling a corresponding chain reasoning prompt by each agent to analyze the operation video clip, and outputting a final error detection result based on an optimization threshold value by weighting and fusing analysis results of each agent. According to the invention, accurate detection of various surgical errors can be realized, and detection efficiency and clinical suitability are considered at the same time.

The invention relates to pattern recognition and anomaly detection in the technical field of computers, and discloses a laying hen disease early-stage AI early warning method and a laying hen disease early-stage AI early warning system. The method comprises the following steps: obtaining a laying hen behavior video stream, an excrement image and body temperature data, and carrying out preprocessing such as timestamp alignment and equipment number mapping to generate a training and reasoning input structure; then target tracking, key point coding, region segmentation, contour feature coding and body temperature fragment statistical coding are executed to extract a multi-source feature sequence; performing time window alignment, scale normalization, pattern recognition and anomaly detection processing on the multi-source features to realize disease type recognition; and finally, generating an early warning event based on rule triggering and threshold judgment, and forming closed-loop disposal through prevention and treatment scheme retrieval and instruction arrangement. According to the method, collaborative analysis and early abnormity early warning of multi-source heterogeneous data are realized, and the disease recognition accuracy and early warning timeliness are remarkably improved.

The application relates to the technical field of computers and discloses an integrated information system for clinical trial archives and a data processing method thereof, the method comprising the following steps: constructing a standardized data model covering the whole process; dynamically structuring and inputting multi-source data and checking the integrity; performing multi-dimensional semantic correlation analysis based on a Bayesian network and a correlation coefficient; performing block chain version tracing and difference comparison; performing four-dimensional access control of roles-sensitivity-operations-context; and performing task-driven collaborative sharing and audit logging. The system comprises six modules, namely, unified modeling, data input, semantic analysis, version tracing, access control and collaborative audit. The application solves the problems of data islands, semantic fragmentation, poor dynamic adaptability and weak security protection in the prior art, realizes intelligent management, semantic interconnection, safe controllability and efficient collaboration of the whole life cycle of clinical trial archives, and significantly improves data quality, audit compliance and multi-role collaboration efficiency.

The invention relates to the technical field of medical literature translation, in particular to a medical literature translation method based on a large language model and a term library. Comprising the following steps: S1, reading a to-be-translated document to obtain a document object model (DOM); s2, screening out a special format in the document object model; s3, a translation database is constructed, the translation database comprises a term library, a memory library and an abbreviation library, an Aho-Corasick automaton and a vector index technology are used, the document to be translated is matched with the translation database, and a corresponding matching result is obtained for each translation database; s4, using an AI system to provide a matching result in the step S3 for the AI system as a reference, and completing translation of the to-be-translated document to obtain a translated text; s5, in the translated text translated in the step S4, the special format screened out in the step S2 is restored, and the accuracy and specialty of medical literature translation can be improved.

The invention relates to the field of medical artificial intelligence, in particular to a clinical scoring system combining large language model multi-agents and machine learning and a self-evolution method of the clinical scoring system, and provides the clinical scoring system based on the large language model multi-agents and the self-evolution method of the clinical scoring system. The objective of the invention is to overcome the defects of data missing sensitivity, insufficient interpretability, weak dynamic updating capability and the like of an existing clinical scoring system. According to the system, through a multi-agent collaboration architecture, the natural language interaction capability of a large language model (LLM) and the precise prediction capability of a machine learning model are deeply fused, and a self-evolution mechanism is introduced to realize dynamic optimization, so that the reliability, flexibility and transparency of clinical decisions are remarkably improved.

The invention provides a medication guidance system and method based on knowledge graph and vector retrieval fusion, and relates to the technical field of artificial intelligence, and the medication guidance system comprises an application access layer, a service interface layer and a mixed retrieval engine layer; the application access layer is used for receiving external demand information and transmitting the external demand information to the large model platform; the service interface layer is used for receiving a query instruction of a large model platform, transmitting the query instruction to the mixed retrieval engine layer and transmitting a retrieval result to the large model platform, so that the large model platform outputs the retrieval result; the mixed retrieval engine layer is used for generating a graph database query statement and a query semantic vector according to the query instruction, performing structured query on a graph database according to the graph database query statement, performing semantic similarity retrieval in a vector database based on the query semantic vector, and generating a graph retrieval result and a vector retrieval result to the large model platform. Through the medication guidance system, specialized medication guidance can be realized.