33 results about "Diagnostic reasoning" patented technology

The invention discloses an electric power system equipment image anomaly detection and quality diagnosis method based on a multi-modal visual language model. The method comprises the following steps: constructing a large-scale multi-modal data set comprising an electrical equipment image, an object detection annotation, a pairing question and answer knowledge base and an official supervision document, constructing a basic diagnosis model based on a visual language model, and carrying out instruction tuning; carrying out post-training on the model by adopting group relative strategy optimized reinforcement learning, and generating an interpretable step-by-step diagnostic reasoning chain; in the reasoning process, related knowledge is dynamically retrieved based on a retrieval enhancement generation technology of a graph structure, and the accuracy and compliance of a diagnosis decision are enhanced; and finally, generating a diagnosis report containing the exception type, the root cause and the decision suggestion. Compared with a traditional method, the method solves the three problems of data scarcity, opaque reasoning and knowledge isolation in the field of electric power detection, and has the remarkable advantages that the diagnosis process can be explained, complex multi-step reasoning is supported, and domain knowledge can be dynamically integrated.

The invention relates to the technical field of medical report generation, and discloses a medical image automatic annotation and report generation system which comprises a preprocessing module, a hierarchical feature extraction module, a semantic annotation module, a guide generation module, a diagnosis reasoning module and a man-machine cooperation interface. According to the method, through standardized preprocessing, hierarchical feature extraction and automatic generation of the annotation and the report, the processing efficiency is greatly improved, and the manual load is reduced; secondly, on the basis of hierarchical feature extraction and semantic and visual embedding alignment, feature support and semantic mapping precision of annotation and reporting are enhanced, and result accuracy and cross-scene consistency are improved; meanwhile, multi-modal alignment processing and multi-dimensional information fusion enhance the adaptability of the system to different image types, generate a structured report conforming to the clinical process and improve the clinical applicability; in addition, a man-machine cooperation feedback mechanism forms a parameter optimization closed loop, so that the system dynamically adapts to new scenes and specifications, and continuous improvement of generalization ability is realized.

The invention provides a medical diagnosis reasoning method and system based on multi-agent coevolution, and the method comprises the steps: driving a large-scale language model to decompose a medical problem through a problem decomposition agent, and determining a to-be-retrieved sub-problem through a self-adaptive retrieval agent, and selecting a proper knowledge base and a proper retrieval algorithm to obtain multi-source retrieval data, and verifying that the intelligent agent performs de-reforming synthesis on the data to obtain an integrated abstract. The expert recruitment agent builds an expert team according to the abstract, the expert agent diagnoses and reasones to build a dynamic reasoning library, the reasoning library is iteratively optimized through judgment, cross reasoning and the auto-reflection physician agent, the dynamic convergence controller monitors the reasoning library, iteration is terminated when conditions are met, and a final diagnosis decision is output. According to the method, information is directionally obtained from a plurality of authoritative and professional medical knowledge bases through problem multi-granularity retrieval and population evolutionary reasoning, and reasoning efficiency can be improved while reasoning correctness is guaranteed.

The invention provides a dynamic knowledge graph construction and diagnosis reasoning method oriented to intelligent inquiry, and relates to the technical field of knowledge graphs, comprising the following steps: acquiring multi-source medical data, performing entity recognition and semantic annotation, establishing a causal probability graph based on a structured entity set, and establishing a dynamic knowledge graph; and selecting an optimal questioning problem according to the information gain in the inquiry process, dynamically updating the causal probability by using the Bayesian rule, and finally propagating the conditional probability along the causal path to generate a diagnosis conclusion. According to the invention, personalized inquiry decision and accurate diagnosis reasoning are realized, and the diagnosis accuracy and efficiency of the intelligent inquiry system are improved.

The invention discloses an automatic triage and accurate diagnosis method fusing multi-modal medical data, and relates to the technical field of automatic triage, and the method comprises multi-modal medical data acquisition, preprocessing and representation vector construction, and realizes department recommendation, priority determination and disease probability analysis through a triage decision network and a diagnosis inference engine. Generating an interpretable path; according to the method, multi-modal data such as texts, numerical values, images, time sequences and voices are fused, technologies such as a cross-modal attention fusion network and a medical knowledge graph are adopted, accurate triage and diagnosis are achieved, meanwhile, a structured report is generated through a confidence degree evaluation and grading processing flow, data feedback and model updating are supported, image-text report reminding is provided for a patient, and the accuracy of triage and diagnosis is improved. The medical efficiency and the diagnosis accuracy are improved.

The invention discloses a veterinary clinical first-aid decision support method and system based on a knowledge graph, and relates to the technical field of veterinary clinical first-aid decision support. Dynamic nature and accuracy of veterinary first-aid decision support are remarkably improved by constructing a static and dynamic combined knowledge graph and a two-way parallel reasoning mechanism; individual dynamic evolution of the knowledge graph is achieved, the actual effect feedback of field measures is fused into the graph through a state change weight algorithm, knowledge representation can adapt to the current case in real time, and the adaptability of the model is enhanced. In combination with forward diagnosis reasoning and backward traceability reasoning, treatment suggestions are deduced from symptoms, effectiveness of implemented measures can be evaluated, diagnosis hypotheses can be reversely corrected, a decision closed loop is formed, and reasoning reliability is improved; through conflict resolution and fusion of decision paths, a structured dynamic report is generated, the misdiagnosis risk is effectively reduced, and the disposal process is optimized.

The invention discloses a self-adaptive diagnosis model training method and system for OCT images. The system comprises an image data preprocessing module, a feature self-adaptive extraction module, a diagnosis model self-adaptive training module, a model performance dynamic evaluation module, a diagnosis reasoning and feedback module and a model iterative optimization module. According to the method, accurate adaptation of OCT images with different qualities and different equipment sources is realized through a hierarchical preprocessing and dynamic feature fusion mechanism, and heterogeneity interference of the images is effectively eliminated; based on hierarchical training of lesion complexity and dynamic loss function design, the model can focus on samples difficult to recognize and minority classes of lesions, and the diagnosis balance is improved.

The invention discloses a diagnostic reasoning RAG system for resisting retrieval noise based on a self-generated knowledge base, and the system comprises a knowledge retrieval module which carries out the retrieval from an external knowledge base according to a user question to obtain a plurality of target text blocks; the evaluation generation module is used for independently evaluating each target text block through an evaluation model so as to identify retrieval noise, generating a correlation judgment result and a noise degree judgment result of each target text block, and generating internal memory information as a self-generated knowledge base based on a user question; and the diagnosis reasoning module is used for integrating the user question, each target text block, the corresponding correlation judgment result, the noise degree judgment result and the internal memory information into enhanced prompt information and inputting the enhanced prompt information into a large language model to generate a diagnosis reasoning answer. According to the method, retrieval noise interference can be effectively resisted, model knowledge support is strengthened by means of the self-generated knowledge base, the precision and timeliness of medical diagnosis reasoning are improved, and the requirements of the medical field for high-precision and strong-timeliness clinical decision making are met.

The invention discloses a medical question and answer method and system based on a knowledge graph and an intelligent agent, and relates to the technical field of natural language processing. The method comprises the following steps: firstly, identifying a core entity related to patient description information from a medical knowledge graph, and obtaining an optimized entity set; performing association reasoning path and neighbor path exploration on entities in the optimized entity set to obtain an association reasoning path set and a second-order neighbor reasoning path set; then, paths in the associated reasoning path set and the second-order neighbor reasoning path set are converted into natural language description information based on prompt words of natural language conversion, and the natural language description information forms a knowledge text set; and finally, performing diagnosis reasoning on the patient description information and the information in the knowledge text set according to reasoning prompts, and outputting a diagnosis result. The method has remarkable advantages in the aspects of fact accuracy, disease diagnosis accuracy and drug recommendation accuracy.

The invention discloses a novel equivalence device structure closing and single-step repairing method and system in medical diagnosis, drug discovery and physiological status modeling, belongs to the field of medical diagnosis analysis, biological information processing and model verification, and ensures the reliability and traceability of the process through structural equivalence device detection and receipt track recording. The method monitors sequential equivalents (ABBA rectangles for checking consistency of operational orders) and conservation equivalents (triangles for checking information conservation and energy balance) during operation to find anomalies in diagnostic inference chains, drug action pathways, or physiological closed loops (such as predictor deviations, energy conservation imbalances, or model inconsistencies). When a non-equivalence condition is detected, the system selects a unique repair adapter from a geometric layer, a frame layer and a field layer for correction according to a preset priority, and the deviation metric mu is strictly reduced by one (delta mu = 1) during each repair, and is gradually converged to an equivalence closed state.

The invention discloses a path modeling and model optimization method and system for clinical diagnostic reasoning, and the method comprises the steps: obtaining real clinical medical record data, and constructing a diagnostic reasoning data set after preprocessing; performing diagnostic reasoning on samples in the data set by using a pre-trained large language model to obtain an absolute correct reasoning path and a simulated correct reasoning path so as to construct a correct reasoning path set; performing supervision and fine tuning on the large language model based on the correct reasoning path set; reasoning the data set again by using the fine-tuned model, and collecting samples with diagnosis errors and error reasoning paths corresponding to the samples; and constructing a preference sample pair set according to the wrong reasoning path set and the correct reasoning path set, and performing preference optimization training on the fine-tuned model based on the preference sample pair set to obtain an optimized large language model. According to the method, explicit modeling and large language model optimization are performed on the diagnosis reasoning path, so that the stability and interpretability of the model diagnosis reasoning process are improved.

The invention belongs to the technical field of engineering construction, and discloses an engineering machinery diagnosis method and system based on a maintenance project, and the method comprises the steps: obtaining the state data, operation data and fault codes of engineering machinery; constructing a dynamic triggering condition of the maintenance project, and judging whether to trigger maintenance reminding or not based on the state data, the operation data and the fault code; and constructing an expert knowledge base comprising a fault tree, a case base and a rule base, obtaining a fault phenomenon, calling the expert knowledge base, combining the state data, the operation data and the fault code, executing diagnosis reasoning combining forward reasoning and backward reasoning, and obtaining a diagnosis result. According to the invention, on the basis of the real-time state of the equipment, dynamic prediction and maintenance demand reminding, when the fault occurs, the expert knowledge base is utilized to quickly position the fault reason and provide maintenance guidance, so that the maintenance cost is reduced and the attendance rate of the equipment is improved.

This invention relates to the field of medical informatics, providing a medical-assisted reasoning method and system based on a small language model and Monte Carlo tree search. The method includes: standardizing raw patient medical data to obtain an initial training dataset; expanding candidate diagnostic reasoning paths within a Monte Carlo tree search framework based on a small language model to obtain multiple candidate reasoning paths; inputting these multiple candidate reasoning paths into a process reward model, scoring the intermediate reasoning steps of each path to obtain step scores; ranking and filtering the candidate reasoning paths based on the step scores to obtain a set of high-quality reasoning paths; jointly training the policy model and the process reward model to obtain an optimized reasoning model; and generating reasoning results from the optimized reasoning model based on the optimal reasoning path to obtain a comprehensive suggestion set. This invention improves the interpretability of medical-assisted reasoning and enhances the robustness of the diagnostic system.

The invention discloses a traditional Chinese medicine disease diagnosis auxiliary system based on a clinical mapping knowledge domain, and relates to the technical field of traditional Chinese medicine diagnosis. Searching syndrome nodes associated with the symptoms and tongue picture features from a traditional Chinese medicine clinical knowledge map to form an initial syndrome set; calculating a matching degree between the pulse condition waveform data and typical pulse condition features of each syndrome node, and performing sorting and screening to form a focused syndrome set; extracting associated treatment methods and prescriptions to generate a preliminary diagnosis reasoning chain; and performing logic verification and optimization on the reasoning chain through a graph neural network syndrome evolution deduction model, outputting an optimized diagnosis path, and recording related data to a diagnosis and treatment file. The system can assist in traditional Chinese medicine diagnosis, improve diagnosis pertinence and reasoning preciseness, and perfect diagnosis and treatment records.

The invention discloses a human-machine collaborative inquiry visual interaction system and method based on a medical large model. The system comprises a real-time knowledge base module, a data fusion module, a large model reasoning module and a visual interaction module. The real-time knowledge base module is used for acquiring medical literature data in real time and dynamically updating a basic medical knowledge graph; the data fusion module is used for acquiring multi-source medical data of a target patient and constructing a personalized knowledge graph; the large model reasoning module is used for receiving the personalized knowledge graph to perform preliminary diagnosis reasoning, responding to an intervention instruction to perform adjustment and then performing reasoning again to generate a final diagnosis conclusion; the visual interaction module is used for visually displaying the diagnosis information and receiving an intervention operation instruction input by a user; according to the method, the personalized knowledge graph is constructed, the reasoning logic chain is visually displayed, and real-time intervention of doctors is supported, so that transparent man-machine collaborative diagnosis is realized, and the interpretability of diagnostic reasoning and the accuracy of clinical decision are remarkably improved.

The application discloses a kind of based on dynamic retrieval and chain reasoning's auxiliary diagnosis method, device and medium of dermatosis.It is described as follows:The method includes: obtaining skin disease image and user description text;First visual language model is input to target sample, and medical entity feature is extracted and primary diagnosis hypothesis is generated;According to the clinical diagnosis sequence of mechanism inference from feature perception, generate reasoning node sequence;Based on current node and reasoning context, construct retrieval query, retrieve reference information in skin disease knowledge base and integrate with reasoning node, form image-knowledge-reasoning chain triple knowledge structure;The integration result of the reasoning node sequence and the triple knowledge structure is input into second language model, and auxiliary diagnosis report containing diagnosis reasoning process and diagnosis conclusion is generated and output.No skin disease image-diagnosis report pairing training data can improve the explainability and reliability of zero sample diagnosis.The application also provides the corresponding diagnostic device and computer readable medium.

The invention relates to the technical field of natural language processing, and discloses a method and system for evaluating the influence of social attributes on a large model diagnostic reasoning process. The method comprises the following steps: standardizing an original medical record data set, removing samples associated with population attributes, and arranging the samples into a hierarchical standard format to obtain a standardized data set; the standardized data set is neutralized, population attribute information is replaced, and complete neutrality is ensured through backstepping verification; for various social attributes, attribute texts are generated based on multiple sub-dimensions, corresponding fields of medical records in the neutral data set are embedded through semantic fusion, and a fusion data set is constructed; obtaining a diagnosis result by using a large language model; and calculating a performance index and a reasoning style change index based on the diagnosis result, and evaluating the influence of social attributes on the big language model diagnosis reasoning process. According to the method, the real effects of different social attributes on diagnostic reasoning can be comprehensively measured.

The invention provides a crack diagnosis reasoning method and system based on an engineering inspection agent in the technical field of engineering detection and artificial intelligence crossing. The method comprises the steps that S1, a mobile terminal collects multi-modal data and uploads the multi-modal data to a server; s2, the server inputs the multi-modal data into a crack recognition model to obtain crack masks and geometric features, physical scale parameters of cracks are calculated in combination with scale calibration information, and crack fact data are generated; s3, taking the crack fact data as input, performing two-stage retrieval in the engineering knowledge graph to construct an evidence sub-graph, and performing coding and reasoning on the evidence sub-graph by using a graph neural network to generate a sub-graph context vector; and S4, the crack fact data and the sub-graph context vectors are fused to obtain fusion features, the fusion features are input into the large language model, and a diagnosis conclusion is generated. The method has the advantages that the precision, the efficiency, the interpretability, the environmental adaptability and the generalization ability of crack diagnosis are greatly improved.

The invention discloses an embedded path evolution tracking system and an implementation method thereof, and aims to solve the technical problems of incomplete path record, difficulty in problem positioning and insufficient experience inheritance in innovation process management. The system is embedded in innovation platforms such as DIKWP-TRIZ and comprises a path data acquisition module, a log storage module, an organization visualization module, a path analysis module, an improvement suggestion module and a learning optimization module. Key events such as cognitive engine reasoning jump, TRIZ principle application and user decision are intercepted in real time, standardized path units are generated and stored according to a time sequence, and a multi-level evolution path chain and a visual network diagram are constructed. The path analysis module can diagnose and infer breaking points and unresolved contradictions, the improvement suggestion module prompts introduction of new knowledge or adjustment strategies according to the contradictions, and the learning optimization module dynamically optimizes a scheduling algorithm based on a historical data training model. According to the method, full-path transparent recording and intelligent analysis of the innovation process are achieved, efficient redisk, accurate problem positioning and strategy optimization are supported, the innovation success rate and knowledge management efficiency are remarkably improved, and the method is suitable for the fields of research and development management, patent mining and the like.

The application discloses a food old product health diagnosis method and system based on a category rigidity rule engine and a computer readable storage medium. The method forms a food old product diagnosis closed loop through a food vertical field knowledge base, isolated storage of enterprise private data, irreversible encryption and interval desensitization, a category rigidity rule engine, a fixed weight scoring model and desensitization aggregation statistics. The application limits diagnosis reasoning within structured rules, industry baseline and compliance threshold, and outputs traceable results through rule hit logs, deduction details and desensitization aggregation field, which can reduce the risk of enterprise plaintext operation data leakage, improve the consistency, reviewability and data security of food old product health diagnosis.

The application discloses a large language model-based cutting and winding integrated machine fault diagnosis method and system, relates to the technical field of equipment fault diagnosis, and comprises a table data intelligent processing module, a knowledge base construction module, a diagnosis reasoning module and a user interaction module; the table data intelligent processing module performs automatic fault mode labeling and description standardization on a cutting and winding integrated machine fault diagnosis case base provided by a user; a domain knowledge graph construction module integrates a standardized table database and automatically constructs a domain knowledge graph; a diagnosis reasoning module performs fault diagnosis reasoning based on a large language model and the knowledge graph; and a user interaction module provides a multi-modal user interaction interface and supports visual presentation of fault diagnosis. Therefore, the large language model-based cutting and winding integrated machine fault diagnosis method and system can improve the intelligent level of fault diagnosis, reduce the cost of knowledge base construction and expansion, and enhance the ease of use and maintainability of the system.

The application discloses a medical question and answer method and system based on a knowledge graph and an intelligent agent, and relates to the technical field of natural language processing.The application first identifies core entities related to patient description information from a medical knowledge graph, and obtains an optimized entity set; then respectively performs associated reasoning path and neighbor path exploration on the entities in the optimized entity set, and obtains an associated reasoning path set and a second-order neighbor reasoning path set; then converts the paths in the associated reasoning path set and the second-order neighbor reasoning path set into natural language description information based on a prompt statement of natural language conversion, and the natural language description information constitutes a knowledge text set; finally, according to reasoning prompts, performs diagnostic reasoning on the information in the patient description information and the knowledge text set, and outputs a diagnostic result.The method disclosed by the application can achieve significant advantages in terms of factual accuracy, disease diagnosis accuracy and drug recommendation accuracy.

The invention discloses a pathological section AI auxiliary diagnosis model based on a soft-pass intelligent computing platform and an implementation method, belongs to the technical field of auxiliary diagnosis, and aims to solve the problems that AI auxiliary diagnosis is high in data dependence, high in computing resource demand, poor in platform adaptability and lack of a feedback iteration mechanism. The pathological section AI auxiliary diagnosis model based on the soft-communication intelligent computing platform comprises the soft-communication intelligent computing platform, a pathological section preprocessing module, an AI auxiliary diagnosis model module and a diagnosis result output and feedback module, the pathological section AI auxiliary diagnosis implementation method based on the soft-pass intelligent computing platform comprises the steps of soft-pass intelligent computing platform initialization, pathological section data acquisition and preprocessing, AI auxiliary diagnosis model training, pathological section AI auxiliary diagnosis and diagnosis result feedback and model iteration. The diagnosis reasoning response time is shortened, and in a clinical test, a doctor combines an auxiliary diagnosis result of the method, so that the diagnosis efficiency is remarkably improved.

The invention discloses a comprehensive evaluation method for gas consumption safety behavior capability of catering industry personnel based on fuzzy Bayesian network construction, and the method comprises the steps: determining an evaluation index system, building the evaluation index system based on the statistics and rule analysis of catering gas accidents in 2019-2023, and the cause analysis of the Bayesian network, and employing a plan behavior theory, a factor set source serving as a model construction basis; a model structure construction system is determined, basic factor sets are determined according to the evaluation index system, Bayesian network nodes are determined according to the relation between the factor sets, and an evaluation model is constructed; a data processing system is determined, a questionnaire survey data result is subjected to evaluation level establishment, natural language variable corresponding triangular fuzzy number, equalization and ambiguity resolution processing to obtain a prior probability, and a conditional probability is obtained by applying a Noisy-or Gate model and serves as a data source to be input into a constructed evaluation model; determining a model evaluation system, formulating a gas use safety behavior capability evaluation level of a catering practitioner, obtaining a gas use safety behavior capability evaluation result of a certain place or a person through predictive reasoning, reversely verifying the reasonable feasibility of the model by applying diagnostic reasoning, and obtaining a mutual influence relationship among nodes through support reasoning.

The present application relates to a biliary tract cancer prediction method and system based on iterative self-consistency and large model verification, relating to the field of artificial intelligence, comprising obtaining electronic medical record text data of a patient to be predicted; the present application inputs a prompt word sequence into a current base large language model to generate an independent reasoning path set, adopts a majority voting mechanism to select positive samples and negative samples, constructs candidate data pairs, introduces a verification large language model to verify the medical logic rationality of the positive samples, guarantees the diagnosis quality through a double mechanism, improves the accuracy and reliability of the diagnosis reasoning, supervises and fine-tunes the current base large language model, optimizes a comparison loss function to obtain an updated base large language model, realizes continuous iterative optimization of the diagnosis logic, inputs the structured prompt word sequence of a new patient to be diagnosed into the final base large language model, generates an optimal reasoning path and a diagnosis conclusion, and outputs a thought chain reasoning result containing medical logic.

The invention discloses an enhanced fault diagnosis system based on an equipment testability model, and the system is characterized in that the input of a fault feature extraction module is connected with a real-time monitoring system and a data and knowledge management system, and is used for receiving parameter information, fault information and a special diagnosis extraction rule; the output is connected with the relevance diagnosis reasoning module and the heuristic diagnosis reasoning module and outputs fault features to the two modules; the input of the relevance diagnosis reasoning module is connected with the real-time monitoring system, the data and knowledge management system and the fault feature extraction module, receives the parameter information, the fault information, the structure behavior relevance model and the fault features, and the output of the relevance diagnosis reasoning module is connected with the fault processing module and outputs a relevance diagnosis conclusion to the fault processing module. According to the method, the expert troubleshooting process is simulated, multiple diagnosis methods including heuristic diagnosis and relevance diagnosis are adopted, and combination-level and system-level fault diagnosis is achieved.

The invention discloses a micro-assembly defect interpretability analysis system and method, and belongs to the field of defect analysis, the micro-assembly defect interpretability analysis system comprises a data acquisition subsystem, a feature extraction subsystem, a physical rule knowledge base and a diagnostic reasoning subsystem, the physical rule knowledge base is integrated with a fuzzy logic subsystem and a Bayesian network; the fuzzy logic subsystem processes the process parameter uncertainty corresponding to the defect characteristics and outputs confidence, the Bayesian network performs probabilistic reasoning by taking the defect characteristics as evidence, updates the posterior probability of each process root cause, and determines one or more target process root causes causing defects by integrating the confidence and the posterior probability. According to the method, by integrating the confidence coefficient of fuzzy logic and the posterior probability of the Bayesian network, a quantitative target process root cause with probability statistics support is finally output, so that process adjustment is converted into an accurate and quantitative process parameter adjustment value from qualitative guidance depending on experience, the production line trial and error cost is greatly reduced, and the optimization period is greatly shortened.

This invention provides a method and system for generating intelligent diagnostic reports based on electromyography (EMG) and evoked potential (EVP) data, belonging to the field of medical diagnostic technology. First, it acquires the subject's EMG and EVP data sets, performs difference compensation and association mapping on the two types of data, establishes dynamic association relationships, and obtains a cross-data type association feature set. Then, it calls a multi-round iterative intelligent diagnostic reasoning model to perform symptom association analysis and generate a preliminary diagnostic conclusion. Next, it integrates the preliminary diagnostic conclusion with clinical reference information to obtain an optimized diagnostic conclusion. Finally, it generates a structured intelligent diagnostic report based on the optimized diagnostic conclusion, including an electrophysiological evidence chain, association analysis details, clinical matching results, and phased suggestions. Each part can be viewed through an associated index, improving diagnostic accuracy and efficiency.

The invention discloses an AI hospital guide system based on structured multi-round dialogues, and relates to the technical field of artificial intelligence medical hospital guide. Comprising an initial information standardization module, an ICD-11-based dynamic diagnosis reasoning module, a humanized interaction processing module and a medical resource recommendation module which are sequentially subjected to data interaction. The initial information standardization module converts non-standard symptom expression of a patient into ICD-11 standard structured data through a built-in disease-symptom civil dictionary and large model reasoning; the dynamic diagnosis reasoning module completes disease preliminary screening, probability dynamic calculation and decision optimization through multiple rounds of dialogues on the basis of an ICD-11 extended data set, and outputs a target department set; the user-friendly interaction module extracts emotion features and emergency signals of the patient and generates an adaptive reply; and the medical resource recommendation module combines department strength and doctor authority to adjust a recommendation weight according to an emergency level. The system solves the problem of pain points such as incomplete traditional hospital guide information acquisition, the average interaction round is less than or equal to 2.5, the department recommendation accuracy is greater than or equal to 95%, and accurate and humanized hospital guide is realized.