83 results about "Clinical knowledge" patented technology

The invention discloses a multi-modal medical image data intelligent processing system, relates to the field of medical image analysis, and is applied to multi-modal medical image whole-process analysis of CT, MRI, PET, ultrasound and the like. According to the system, different modal image features are extracted and fused through a cross-modal manifold fusion network; a semantic guidance dynamic registration engine optimizes registration parameters to ensure that the registration error is less than or equal to 1.5 mm; the multi-task collaborative diagnosis network realizes multiple tasks such as disease classification; the clinical knowledge embedding and interpretable module generates a structured report and is in butt joint with an HIS system. Meanwhile, the model is optimized through a federated learning architecture, the adaptability of newly added data is improved by more than or equal to 20%, and intelligent processing and analysis of multi-modal medical images are realized.

The invention relates to the technical field of medical information, in particular to a medical data conjoint analysis system based on medical knowledge graph driving. The system comprises a medical knowledge graph construction module, a medical data quality evaluation module, a medical feature engineering module and a medical knowledge driven analysis module, and heterogeneous knowledge graph modeling can be performed by integrating medical clinical guidelines, biomedical literatures, a drug database and historical medical data so as to generate a medical heterogeneous knowledge graph; obtaining new medical clinical test information and carrying out delayed contradictory learning update to generate a medical dynamic update knowledge graph; the method comprises the following steps: obtaining multi-modal medical data, carrying out quality verification evaluation and medical feature engineering analysis, carrying out knowledge path joint driving analysis at the same time, generating a decision support reasoning path corresponding to medical clinical knowledge, and outputting a corresponding medical knowledge path confidence coefficient. According to the method, fusion reasoning among cross-source data can be realized by constructing the multi-modal medical knowledge graph.

The invention provides a clinical thinking examination question generation and step-by-step analysis construction method and system based on a large language model, and relates to the technical field of large language models. The method comprises the steps of analyzing a teaching outline and real questions over the years, constructing a multi-level clinical knowledge graph, intercepting a knowledge sub-graph according to target difficulty, and generating case question stems, candidate options and a preliminary reasoning path covering the sub-graph; the reasoning path consistency is verified through a logic engine, a simulation answer sample is constructed, item reaction modeling is executed, and the question difficulty is estimated; if the difficulty does not accord with the target difficulty, parameters are automatically fine-tuned and re-generated, and iteration is carried out until the standard is reached; performing error selection rate driven optimization on the interference options to form a final question version; and collecting student answering data feedback atlas weight and difficulty, and writing the content into the versioned question bank. According to the invention, the accuracy of examination question generation, the teaching suitability and the continuous updating ability are improved, and the intelligent evaluation of clinical thinking ability is realized.

The invention discloses a chronic disease intervention safety detection system and method based on large model multi-agent cooperation, and relates to the technical field of natural language processing and multi-agent cooperation in the medical health field. A standardized interface and an adaptive cleaning algorithm are adopted to realize data desensitization, missing value filling and format unification, and a dynamically updated patient health portrait is constructed; complex tasks are decomposed based on a chain reasoning technology, special tools such as a drug interaction detection tool and a nutrition gap calculation engine are developed, and a clinical knowledge base is integrated for parallel analysis; suggestion conflicts are eliminated through a multi-agent debate mechanism, the priority is calculated in combination with a weight rule, manual auditing is triggered to process low-confidence disputes, and finally a structured health report containing medication adjustment, diet optimization and behavior intervention is generated. The limitation of a traditional method in data integration, cross-domain reasoning and conflict resolution is solved.

The invention relates to the technical field of medical monitoring and early warning, in particular to a tumor intervention postoperative intelligent nursing monitoring system, which comprises an individualized data acquisition module for outputting a standardized data packet and a historical feature index table; the dynamic feature processing module generates three-dimensional feature tensors of coding time, physiological features and pathological mark dimensions; the individual self-adaptive modeling module generates an individual risk prediction model embedded with a genetic and pathological response function; the dynamic threshold optimization module encodes a historical baseline fluctuation range into chromosome gene loci, and iteratively corrects an abnormal judgment boundary in combination with a genetic algorithm; the intelligent early warning decision module calls a clinical knowledge graph to generate a three-level early warning instruction, and constructs a double-closed-loop feedback channel: a first closed loop calibrates and judges boundary parameters through a false alarm feedback signal, and a second closed loop converts disposal effectiveness into weight correction vector optimization model parameters; and full-link closed-loop management of individual dynamic physiological variation from feature fusion and model adaptation to decision optimization is realized.

The invention discloses a knowledge graph construction method and device based on multi-modal clinical data, equipment, a medium and a product, and relates to the field of knowledge graph construction, and the method comprises the steps: constructing a medical knowledge type knowledge graph; based on the dynamic event data of the patient and the doctor-patient dialogue data, constructing a medical event type knowledge graph; fusing the medical knowledge type knowledge graph and the medical event type knowledge graph to obtain a fused medical knowledge graph; collecting multi-modal data in the diagnosis process of the patient, and fusing the multi-modal data with the fused medical knowledge graph to obtain a finally constructed knowledge graph; the multi-modal data comprises text data, image data, voice data and physiological signal data. The problems that clinical knowledge is fragmented, deep mining is difficult, data cannot be associated in a unified mode, and doctor-patient communication knowledge is fragmented can be solved.

The invention discloses a multi-agent brain signal autonomous understanding method based on large language model driving, and the method comprises the steps: constructing a hierarchical cooperation architecture comprising a central supervisor agent and a specialized sub-agent, and carrying out the autonomous understanding of a brain signal on the basis of reducing the technical threshold of brain signal analysis; the problems that a traditional normal form process is rigid and long-time-history complex tasks are difficult to process are solved. According to the method, a central supervisor agent is used for analyzing a natural language intention of a user and dynamically decomposing a task, and a specialized sub-agent is combined with a global sharing state and a context isolation mechanism to execute domain-specific full-link dynamic planning and accurate tool calling; a comprehensive analysis report with cross-domain causal logic is generated by integrating quantitative calculation results and qualitative clinical knowledge through hierarchical resource allocation and retrieval enhancement generation mechanism, then a three-layer difficulty assessment reference system is established to verify framework performance, and finally autonomy, flexibility and clinical interpretability of a brain signal understanding process are achieved.

The invention discloses a medical diagnosis-oriented multi-modal credible dialogue type retrieval enhancement generation system, and relates to the field of artificial intelligence, in the system, a multi-modal image analysis module generates a structured image feature data packet based on a multi-modal large model according to an original medical image; the knowledge database construction module is used for constructing a multi-center collaborative medical knowledge database; the image knowledge retrieval module is used for obtaining image feature associated knowledge; the clinical knowledge retrieval module is used for obtaining a candidate knowledge set; a multi-dimensional weighting reordering module obtains a knowledge list; the medical inquiry generation module is used for generating structured preliminary diagnosis based on the user questions, the image abstract and the knowledge list; the credibility verification module is used for verifying the structured preliminary diagnosis to obtain a final diagnosis report; according to the method, the medical knowledge retrieval precision can be improved, the image information fusion capability is enhanced, and high-credibility and traceable intelligent diagnosis and treatment auxiliary service oriented to doctor-patient scenes is realized.

The invention discloses a critical patient physiological parameter monitoring and intelligent early warning system, which relates to the technical field of intelligent medical treatment, and is provided with a multi-modal data collection module for collecting multi-modal physiological parameter data of a critical patient through a sensor array of flexible electronic skin, and a signal alignment module for aligning the multi-modal physiological parameter data of the critical patient. Aligning signal sequences with different sampling rates in the multi-modal physiological parameter data, setting a physiological theoretical range updating module, constructing a transfer learning model according to historical medical records of a patient, updating a physiological theoretical range of a heart rate variation coefficient in real time, setting a grading early warning module, and triggering a Bayesian network composite event detection model. Generating a graded early warning signal, setting a decision support module, dynamically loading a clinical knowledge graph through a micro-service architecture, and pushing decision support information containing rescue priority labels to a monitoring terminal; and the precision and efficiency of intensive care are obviously improved.

The invention discloses a full-process automatic voice-driven electronic medical record generation system, and belongs to the technical field of medical information. The invention aims to solve the problems of insufficient medical term precision, low medical record structuring efficiency, lack of clinical knowledge support, data security risk and the like of voice recognition in the prior art. According to the system, a full-automatic process from voice input to structured medical record output is realized by integrating medical level voice acquisition, term enhanced voice recognition, intelligent medical record generation based on a large language model and a knowledge base, multi-modal interaction and system integration and a full-process safety compliance system adopting edge computing and block chain technologies. According to the method, the medical record writing efficiency can be remarkably improved, manual errors are reduced, medical safety and data privacy are guaranteed, and the method has wide clinical application value.

The invention discloses a structured information extraction system for a mental disorder electronic medical record based on a knowledge graph and a natural language, and belongs to the technical field of medical information processing. According to the system, firstly, core concepts such as diseases, symptoms and drugs are extracted from an authoritative guide to construct a mental disorder knowledge graph, and a standardized clinical knowledge base is established; then pre-training and fine-tuning the deep learning model on a large number of biomedical texts and desensitized medical records to enable the deep learning model to have a medical language understanding ability; performing preprocessing, named entity recognition and entity linking on the electronic medical record text, and mapping spoken expressions to standard medical terms; inference is carried out by utilizing a relation extraction model and combining with a knowledge graph to complement implicit clinical information; and finally, structured data output meeting the standards of FHIR and the like is generated. According to the method, through deep fusion of knowledge driving and data driving, the problems of insufficient semantic understanding and weak generalization ability of a traditional method are effectively solved, and the accuracy and clinical value of electronic medical record structured information extraction are remarkably improved.

The invention relates to the technical field of electric digital data processing, and discloses an intelligent data processing method for clinical research. The method comprises the following steps: constructing a basic clinical knowledge graph fused with an international medical ontology; the method comprises the following steps: performing deep learning driven entity recognition and knowledge graph linking on original data from heterogeneous sources such as an electronic medical record and an inspection system; executing cross-source entity alignment and knowledge fusion based on the graph attention network; performing automatic data quality verification and restoration according to clinical logic rules embedded in the atlas; and finally, extracting and generating a standardized analysis ready data set from the enhanced atlas according to research requirements. According to the technical scheme, high-quality, automatic and semantic integration and flexible delivery of clinical research data are realized, and the data processing efficiency and research reliability are improved.

The invention discloses an acute myocardial infarction diagnosis method based on interpretable hybrid ensemble learning. The specific implementation process is as follows: performing data preprocessing on collected original chest pain data; the adaptability of a single basic algorithm is enhanced through nested iterative optimization and global hyper-parameter tuning; dynamic multi-strategy integration is utilized to select an optimal integration strategy, and layered feature abstraction, probability calibration fusion and a consensus decision mechanism are included; in order to improve clinical transparency, a game theory marginal contribution analysis framework is constructed, and SHAP values of global and local feature contributions are quantified; collaboratively optimizing data-driven feature dimension reduction and clinical knowledge verification on the basis of SHAP value ranking, screening out six key clinical features, and constructing a hybrid integrated learning model; the method is further used for STEMI, NSTEMI and non-AMI diagnosis, and the complex diagnosis adaptability of the method is verified. According to the method, algorithm diversity and clinical transparency are integrated, and effective acute myocardial infarction diagnosis is realized.

The invention provides a medical image visualization analysis system based on deep learning, and relates to the field of artificial intelligence. The objective of the invention is to overcome the defects of an existing system in the aspects of deep learning model interpretability, clinical interactivity and multi-modal data fusion. The system comprises an image data acquisition and standardization module, a deep feature extraction and representation learning module, a multi-task intelligent analysis module, an interpretability analysis module, a multi-dimensional visualization and interaction module, a clinical knowledge fusion and feedback learning module and a system management and integration module. Through the system, the diagnosis efficiency and accuracy can be improved, the trust of doctors is enhanced, the obstacle of a traditional black box model is overcome, and a new man-machine cooperation intelligent diagnosis normal form is constructed.

The invention relates to an old inpatient intestinal preparation failure risk prediction method and system, and the method comprises the steps: collecting the multi-dimensional electronic medical data of a patient from a hospital information system (HIS), a laboratory information system (LIS) and a pharmacy information system (PIS), carrying out the cleaning, missing value filling and standardization preprocessing of the original data, so as to construct a high-quality data set, and carrying out the prediction of the intestinal preparation failure risk of the old inpatient. Generating three core risk characteristics based on clinical knowledge: an age-weighted complication index, a specific drug use mark and a key physiological index anomaly mark; inputting the features into a preset rule engine, performing weighted calculation according to a fixed weight coefficient to obtain a comprehensive risk score, finally dividing patients into low, medium and high risk levels according to a risk threshold value determined by historical data, and outputting a result and storing the result into a database for clinical retrieval and early warning. The method can effectively evaluate the intestinal preparation failure risk of the elderly patient, and provides an objective basis for clinical intervention.

The invention discloses an intelligent generation method and system for a medication guidance sheet based on multi-source heterogeneous medicine data, and belongs to the field of intelligent generation of medication guidance sheets, and the method comprises the following steps: S1, carrying out the standardization and real-time fusion of the multi-source heterogeneous medicine data; s2, integrating the standardized multi-source heterogeneous data and multi-source clinical knowledge, and constructing a knowledge graph; s3, constructing a medication guidance sheet intelligent generation model, and training the medication guidance sheet intelligent generation model; s4, inputting the real-time data of the patient into the trained medication instruction sheet intelligent generation model and the knowledge graph, and generating a medication instruction sheet; and S5, iteratively optimizing the medication guidance sheet intelligent generation model and the knowledge graph. By the adoption of the intelligent generation method and system for the medication guidance list based on the multi-source heterogeneous medicine data, precise, personalized and real-time generation of the medication guidance list is achieved, and the defects of multi-source data integration, dynamic updating, personalization and content quality control in the prior art are overcome.

The invention provides a clinical traditional Chinese medicine knowledge graph construction method based on a multi-modal graph attention network. The method comprises the following steps: acquiring multi-modal data in a traditional Chinese medicine clinical environment; generating a corresponding type label; all modal vectors in the multi-modal semantic representation set are corresponding to nodes, and an initial traditional Chinese medicine clinical knowledge graph is constructed; based on attention enhancement of a graph neural mechanism, generating a graph after structure enhancement; obtaining a standard role set of the traditional Chinese medicine knowledge base, performing semantic role recognition, and generating a node set with role tags; calculating an edge importance score according to the normalized map, and screening out a final edge structure based on the edge importance score to generate a standardized map structure; and importing the standardized map structure into a map database to realize clinical knowledge calling. According to the method, a complete closed-loop process from original clinical data to deployment output is realized through multi-modal modeling, structure generation, graph optimization, role modeling and semantic feedback self-evolution.

The invention discloses a cerebrovascular disease health monitoring method based on an intelligent agent. The method comprises the following steps: step 1, acquiring multi-modal data in real time and preprocessing the multi-modal data; 2, converting the preprocessed multi-modal data into structured health status characterization, and identifying potential cerebrovascular risks; 3, analyzing through a cerebral apoplexy AI model, and outputting a risk level; 4, performing personalized early warning strategy planning based on the risk level; 5, converting an instruction of personalized early warning strategy planning into a cross-platform executable action; and 6, aggregating the desensitization data of the global cerebral apoplexy AI model at the cloud through federal learning, and updating the clinical knowledge graph rule base. According to the method, the health state of the patient is monitored by fusing the multi-modal data, the cerebral apoplexy AI model and the clinical mapping knowledge domain, patients with high-risk and medium-risk cerebrovascular diseases are screened out in time, and medical response is provided in time.

The invention relates to a reasoning enhanced vision-language large model training and image processing method, and the training method comprises the following steps: obtaining an ultra-wide-angle fundus image as an input image, and taking the manual annotation DR classification, the manual annotation lesion type and the clinical background of the ultra-wide-angle fundus image as cue words; utilizing a vision-language model with reasoning ability to generate reasoning enhanced image description and DR classification and lesion types obtained through reasoning; and taking the generated image description and the DR classification and lesion type obtained by reasoning as instructions, constructing a reasoning enhancement instruction data set in combination with the ultra-wide-angle fundus image, and finely adjusting the reasoning enhancement type vision-language large model. Compared with the prior art, the method has the advantages of being capable of effectively integrating clinical knowledge, high in recognition accuracy, high in interpretability and the like.

The invention relates to the technical field of physician cultivation, in particular to a matching method for layered progressive cultivation targets of resident physicians. Comprising the following steps: 1, constructing a physician-based dynamic ability diagram model; 2, cultivating target networked modeling; 3, constructing a heterogeneous data integration platform; 4, reinforcing a learning engine; by constructing a physician-based dynamic ability diagram model and a heterogeneous data integration platform, multi-source data are automatically collected and fused from each information system of a hospital, the system not only analyzes theoretical results, but also introduces 360-degree agile feedback, performs quantitative evaluation from multiple dimensions such as clinical knowledge, skill proficiency, occupational attainment and the like, normalizes and dynamically weights all indexes, and improves the accuracy and reliability of the system. And finally, a personal ability thermodynamic diagram which can be updated in a real-time rolling manner is generated, so that objective, comprehensive and fine description of the ability state of a physician and with the times is realized, and a reliable data foundation is laid for accurate cultivation.

The invention discloses a radiotherapy plan automatic optimization method and device based on a large language model and RAG, and the device comprises an initial plan generation module which is used for generating an initial scheme based on a fixed weight; the data construction module is used for establishing a clinical knowledge base and completing semantic segmentation and vector indexing; the retrieval module is used for matching the query vector with a knowledge base, and obtaining a weighted knowledge set through similarity screening and reordering; the enhancement prompt generation module is used for generating an enhancement prompt; the large language model evaluation module is used for evaluating a scheme and outputting a weight adjustment suggestion; the iterative optimization module is used for updating parameters and generating a new scheme until convergence; and the comprehensive evaluation module analyzes the candidate schemes and outputs an optimal radiotherapy plan. According to the method, the large language model and the RAG are combined, clinical knowledge dynamic introduction and weight adaptive optimization are realized, manual intervention is reduced, target coverage and endangered organ protection are both considered, and radiotherapy plan intelligence and clinical value are improved.

The application provides an unsupervised liver tumor CT image segmentation method based on manual features, relates to the technical field of deep learning, and first collects normal liver CT images as a data set, and selects a tumor position in combination with clinical knowledge. A texture similar to real imaging is generated through three-dimensional simple noise binary mask, and histological features are used for morphological modeling. Then, the tumor texture is superimposed with the liver CT image at the selected position to synthesize a new liver tumor CT image. A segmentation model is trained by using the CT image with annotations, and the synthesized image is used for medical image segmentation. Finally, the segmentation results are evaluated by using the Dice coefficient, the Hausdorff distance, the standardized surface distance and the surface distance index. The application is helpful for artificially synthesizing tumor lesion images and generating voxel-level annotations, and provides a new perspective for solving the medical image annotation challenge and promoting liver tumor diagnosis and treatment.

The invention provides an illness state tracking and early warning system based on a knowledge database, and the system comprises a data module which is responsible for collecting and integrating clinical knowledge and patient data information in the cardiovascular field; the survival rate prediction analysis module is used for extracting pathological features from the patient model, performing survival rate prediction analysis by using a deep learning algorithm and a neural network model, and displaying a prediction result to a physician in a visual report form; and the illness state auxiliary tracking, studying and judging module monitors the illness state change of the patient in real time, analyzes the illness state development trend and risk factors in combination with a knowledge graph and a patient model, and provides treatment scheme recommendation and early warning notification functions. Through the beneficial effects of integrating medical resources, improving data security, accurately predicting the survival rate of a patient, monitoring and early warning in real time, widely applying a knowledge graph, being friendly to user interaction, feedback circulation and continuous optimization and the like, powerful support is provided for prevention, diagnosis and treatment of cardiovascular diseases.

The application provides a medical image segmentation method and system based on concept guidance and cross-modal alignment, and belongs to the field of medical image processing. The method comprises the following steps: obtaining a medical image to be segmented and its corresponding clinical text description; generating clinical knowledge concepts related to the target disease by using a large language model, and constructing a concept set through clinical review; inputting the medical image, the clinical text description and the concept set into a trained concept-guided segmentation model to extract visual features, text features and concept labels; generating concept features aligned with the visual features through a concept-visual alignment module; dynamically adjusting the normalization process of the visual features through a concept modulation decoder, combining the features through multi-head cross attention, and outputting the final image segmentation result by using a segmentation head. The application effectively solves the problems of lack of effective clinical prior guidance in existing medical image segmentation, poor cross-modal feature alignment, and insufficient lesion segmentation accuracy.

The application relates to the technical field of sales support, and discloses a medicine sales data analysis method, which comprises the following steps: constructing a cognitive map model; performing clinical path complexity grading; applying a clinical path complexity grading algorithm to analyze clinical decision process data of a medical institution, and calculating a clinical path complexity index; implementing cognitive-clinical path matching; adopting a cognitive-clinical path matching algorithm to process sales representative cognitive state data and clinical path complexity data, and calculating a matching degree score; performing hierarchical progressive information presentation; based on a hierarchical progressive information presentation algorithm, processing the matching degree score and the clinical path data, dividing information into different priority levels, and outputting an optimized information presentation sequence; and providing personalized clinical knowledge navigation; the application significantly improves the accuracy and effectiveness of professional information transmission by intelligently adapting the cognitive ability of a sales representative to the complexity of a clinical path.

This invention relates to the field of data processing technology and specifically discloses a method for constructing a clinical terminology knowledge graph. The method includes: acquiring multi-source clinical data and medical domain dictionary data; determining the clinical entity set and data block dictionary set for each clinical data block of each medical clinical data from each data source; determining multiple business domain clustering data for each business domain label and the clustered medical entity set for each business domain clustering data; calculating the statistical entity relationship set and graph entity relationship set between every two medical entities in the clustered medical entity set of each business domain label; and constructing a clinical knowledge graph. This method enables deep collaboration between multi-source clinical data and medical dictionaries, improving the professionalism and reliability of medical entity associations, balancing the independence of business domain knowledge with the interoperability of global knowledge, and providing high-quality core support for intelligent medical assistance, medical research, and clinical knowledge transmission.

The invention provides an after-myocardial infarction brain injury risk prediction method and system based on multi-modal data fusion, and relates to the technical field of medical information processing, and the method comprises the steps: firstly obtaining a heart image, a brain image and a brain tissue microwave echo signal of a patient; generating waveform data based on the phase difference and the amplitude difference of the echo signals; taking the heart feature data, the brain feature data and the waveform data as nodes respectively, and establishing connection edges among the nodes according to a preset clinical knowledge base to form a heterogeneous graph; processing the graph by using a graph neural network to obtain associated features; and finally, inputting the associated features into a multi-task learning model, and outputting a future brain injury risk probability and a self-regulation function damage degree result. The accuracy and comprehensiveness of myocardial infarction after-brain injury risk prediction are improved.

This invention relates to the interdisciplinary field of smart healthcare and digital twin technology, specifically to a dynamic medical twin system and interactive prediction method based on a physiological double helix driven and four-dimensional linkage modalities. The system continuously collects and fuses multi-source biophysical data through a physical entity helix, while a digital virtual helix solves a network of physiological equations coupled with metabolic and stress fields in real time. Both systems achieve endogenous synchronous mapping of gene loci and expressed proteins through a built-in base pairing engine. The four modalities of mirroring, deduction, intervention, and knowledge are responsible for high-fidelity real-time presentation, disease progression prediction, virtual intervention deduction, and clinical knowledge accumulation, respectively, forming a complete closed loop of "observation-deduction-intervention-learning." This invention elevates the system architecture from a static hierarchical stack to a dynamic life-body metaphor, supporting users to perform virtual operations on the twin and receive real-time feedback on multi-scale physiological responses across the entire system, achieving a leap from "morphological simulation" to "life mechanism simulation."

This invention relates to the field of medical data technology and discloses an AI-based method for managing cardiovascular chronic disease data. The method constructs a cardiovascular data pool containing patients' historical medical records and real-time physiological signals; establishes a dynamic ontology in the cardiovascular data pool based on a clinical knowledge graph, which defines the semantic relationships between different data entities; maps and generates data evolution trajectories on the dynamic ontology according to a preset treatment target path; activates an intelligent agent configured to traverse the dynamic ontology along the data evolution trajectory, resolving causal constraints between data entities based on the semantic relationships encountered during the traversal; the intelligent agent adaptively reorganizes new data flowing into the cardiovascular data pool in real time according to the resolved causal constraints, generating data slices with temporal correlation; inputs the data slices into a pre-trained deep learning network for feature fusion, outputting a dynamic profile of the patient's cardiovascular health status.

The invention discloses a medical history collection system supporting clinical thinking path recognition, and belongs to the technical field of medical information. The system comprises a hypothesis agent cluster management module used for initializing an agent cluster composed of a plurality of hypothesis agents based on a clinical knowledge graph, each hypothesis agent corresponding to a candidate disease and comprising static knowledge related to the candidate disease; the doctor-patient interaction interface module is used for receiving the initial clinical evidence and analyzing the initial clinical evidence into an initial clinical evidence state vector; the dynamic evidence processing and state evolution engine is used for iteratively driving the state evolution of the agent cluster; and the thinking path generation and visualization module is used for generating a clinical thinking path according to the state evolution process of the agent cluster. The technical problem that the dynamic and nonlinear diagnosis thinking process of clinicians cannot be effectively captured and restored in the prior art is solved.