69 results about "Symptom profiles" patented technology

The invention discloses an AI-based traditional Chinese medicine dialectical auxiliary diagnosis method and system and a medium thereof, and relates to the technical field of intelligent auxiliary diagnosis, and the method comprises the steps: collecting physiological monitoring data, tongue condition data and pulse condition signals of a patient, obtaining patient symptom information, mapping the patient symptom information to a preset traditional Chinese medicine pathogenesis classification model, and generating an initial symptom feature vector; calling a knowledge base containing traditional Chinese medicine prescription rules and compatibility medication taboo, performing data space-time alignment processing and dynamic combination calculation on the initial symptom feature vector, and generating a personalized candidate prescription set conforming to the traditional Chinese medicine compatibility taboo; according to dynamic combination calculation, a solution algorithm based on a constraint satisfaction problem is adopted, and multi-dimensional association rule matching is carried out in combination with the mapping relation between syndromes and modern medical symptoms; and outputting a prescription medication recommendation scheme containing traditional Chinese medicine compatibility, dosage and decoction methods based on the candidate prescription set. The method supports the formulation of an accurate personalized diagnosis and treatment scheme, and meets the requirements of high-quality traditional Chinese medicine personalized auxiliary diagnosis and treatment.

The present invention relates to an early monitoring system for pancreatic cancer based on big data, including a data acquisition module, a feature extraction module, a risk assessment module and an early warning trigger module. The data acquisition module is used to obtain the user's laboratory test data, imaging test data and clinical symptom data. The feature extraction module is connected to the data acquisition module, and constructs a comprehensive feature vector by extracting biochemical indicator features, imaging features and symptom features. The risk assessment module uses a pre-trained deep learning model to analyze the feature vector and generate a pancreatic cancer risk probability. The early warning trigger module compares the risk probability with a preset threshold, generates an early warning signal when the risk probability exceeds the threshold, and pushes it to a medical service terminal to suggest further diagnosis. The present invention combines multimodal data and deep learning technology to achieve accurate early monitoring of pancreatic cancer and improve diagnostic efficiency and accuracy.

The invention discloses an intelligent remote follow-up visit method and system for tumor patients, and relates to the technical field of medical intellectualization, and the method comprises the steps: collecting follow-up visit data through a remote medical terminal, carrying out the processing of the follow-up visit data, obtaining a physical sign index sequence and a symptom feature vector, and generating a dynamic follow-up visit evaluation score through a time sequence prediction model; performing semantic analysis on the electronic medical record data of the patient based on the medical knowledge map, extracting tumor stage classification data, chemoradiotherapy measurement data, weight nutrition indexes and laboratory inspection data, determining a basic risk coefficient, a cumulative dose ratio and a body state score, and generating a baseline follow-up assessment score through a prediction model; and according to the dynamic follow-up evaluation score and the baseline follow-up evaluation score, calculating a comprehensive follow-up grade and generating a next follow-up plan. According to the invention, the accuracy of patient state evaluation is improved, accurate configuration of medical resources is realized, and the quality and efficiency of remote follow-up visit are effectively improved.

The invention discloses a traditional Chinese medicine recommendation method based on knowledge driving and a residual attention network, and the method comprises the following steps: S1, a data collection and cleaning module: obtaining prescription text data, executing a standardized process for symptoms and traditional Chinese medicine terms in the prescription text data, and dividing a data set after the standardized process is executed into a training set, a verification set and a test set; s2, an entity pre-training module: extracting symptom semantic features by using a Word2vec training model to extract the features of symptom entities in the prescription and obtain overall context semantic representation, constructing a traditional Chinese medicine attribute knowledge graph, and fusing the natural attribute features of the traditional Chinese medicine as external knowledge into a recommendation model; s3, a multi-graph construction and entity feature learning module: according to a co-occurrence relationship between the symptoms and the traditional Chinese medicines, constructing a symptom-traditional Chinese medicine isomerism graph (SHHG), a symptom-symptom isomerism graph (SSIG) and a traditional Chinese medicine-traditional Chinese medicine isomerism graph (HHIG); respectively extracting symptom features, traditional Chinese medicine features and interaction features from a symptom-traditional Chinese medicine isomeric graph (SHHG), a symptom-symptom isocomposition (SSIG) and a traditional Chinese medicine-traditional Chinese medicine isocomposition (HHIG) by using a graph attention neural network, and enhancing entity features by using a residual structure; the feature fusion and traditional Chinese medicine recommendation module is used for fusing symptom features and traditional Chinese medicine features extracted from a symptom-traditional Chinese medicine isomerism graph (SHHG), a symptom-symptom isomerism graph (SSIG) and a traditional Chinese medicine-traditional Chinese medicine isomerism graph (HHIG) to obtain final symptom features and traditional Chinese medicine features, and expressing the symptom features by using MLP to obtain a traditional Chinese medicine recommendation result. And finally recommending a proper traditional Chinese medicine set according to the given symptom set.

The invention provides a common mental disease intelligent diagnosis method and system based on multiple agents, and relates to the field of medical artificial intelligence. The method comprises the following steps: S1, extracting diagnosis standards and symptom characteristics of common mental disorders, and constructing a similar patient knowledge base after verification and evaluation of the similar patient knowledge base and expert calibration; s2, acquiring clinical data from a hospital information system, and performing large medical record structuring, clinical scale simplification and scale score analysis on the clinical data to form a similar patient database; and S3, performing symptom matching and scale performance analysis on the input clinical data, constructing a multi-agent mental disease diagnosis framework, and performing multi-agent diagnosis debate based on the multi-agent mental disease diagnosis framework. The technical problems of symptom overlapping and diagnosis subjectivity among common mental diseases are solved by constructing a multi-agent cooperative diagnosis framework, introducing particle size symptom analysis and dynamically integrating structured authoritative medical diagnosis standards.

The invention relates to the technical field of medical assistant systems, and discloses a comprehensive intelligent medical assistant system, which comprises an information acquisition unit used for acquiring user state information; the user state information comprises user static data, dynamic data and feedback data; the model construction unit is used for performing feature extraction according to the user state information and establishing data association indexes of physiology, environment and behaviors; the information processing unit is used for automatically capturing symptom characteristic information and carrying out diagnostic analysis on the input information in combination with user state information; the pushing unit is used for performing local decision processing on the analysis result, forming a diagnosis path diagram and pushing the diagnosis path diagram to a user side; and the learning optimization unit is used for optimizing a recommendation strategy according to the feedback data and integrating long-term health features to carry out optimization suggestions. According to the invention, the service mode of medical health is remodeled, the unique health characteristics of each user can be more accurately understood, the service quality and credibility of a medical assistant system are improved, and the occupancy rate of medical resources is reduced.

The invention belongs to the technical field of traditional Chinese medicine syndrome type classification, and discloses a traditional Chinese medicine syndrome type library construction method and system based on a convolutional neural network, and the method comprises the steps: constructing a corpus for mapping traditional Chinese medicine semantics and a dynamic semantic analysis framework, and carrying out the data enhancement preprocessing of the corpus; the method comprises the following steps: acquiring data, cleaning the acquired data, and removing repeated, missing or abnormal data; constructing a convolutional neural network, and processing and outputting the input data; and constructing a traditional Chinese medicine syndrome type library based on the output syndrome types, and deploying the trained convolutional neural network in an online diagnosis and treatment system for automatic classification and storage. Key features can be automatically extracted from traditional Chinese medicine clinical data, the traditional Chinese medicine symptoms are classified into the corresponding traditional Chinese medicine syndromes by constructing the mapping relation between the traditional Chinese medicine symptoms and the syndromes and utilizing the convolutional neural network to learn the symptom features, a perfect traditional Chinese medicine syndrome knowledge base is formed, and scientific and efficient auxiliary decision support is provided for traditional Chinese medicine clinical diagnosis and treatment.

The invention relates to the technical field of artificial intelligence, and discloses an interpretable depression detection method and system, and the method comprises the steps: retrieving a post related to a depressive symptom from a user social media history; on the basis of the post text corresponding to the symptom problem, a problem perception text representation is generated through fusion of a Longform encoder and an attention mechanism, and an optimal reasoning strategy is selected from a predefined reasoning strategy pool through a hybrid expert network; based on an inference strategy of question perception text representation and selection, selecting a most adaptive large language model from a predefined large language model pool through a hybrid expert network; deducing the severity of each depression symptom of the user according to an inference strategy and a large language model, and calculating the overall depression symptom severity of the user; according to the method, the reasoning strategy and the large language model are dynamically selected through the hybrid expert network, the optimal processing combination is adaptively matched for different symptom features and post contents, and the limitation of a fixed reasoning mode is overcome.

The invention provides a mood disorder assessment system based on multi-level feature fusion, and the system comprises a data collection unit which is used for collecting electroencephalogram signals of a plurality of brain regions of a to-be-assessed patient; the electroencephalogram feature extraction unit is used for extracting electroencephalogram features corresponding to the electroencephalogram signals of the brain regions; the multi-level feature extraction unit is constructed on the basis of the symptom features of the multiple testees and the corresponding electroencephalogram features, and is used for performing multi-level electroencephalogram feature latent variable extraction on the electroencephalogram features of the brain regions of the patient to be evaluated to obtain multi-level electroencephalogram feature latent variables; and the feature fusion and classification unit is used for carrying out classification prediction based on the electroencephalogram feature latent variables to obtain a mood disorder assessment result of the patient to be assessed. The method solves the problem that a mood disorder assessment system in the prior art adopts a single feature extraction and learning strategy and has no constraint of symptom information, so that the recognition capability of a model for mood disorders of different functional abnormality types is limited.

The invention relates to a clinical symptom nursing strategy intelligent recommendation system and method based on artificial intelligence, and the method combines historical clinical symptoms and nursing big data to construct a corresponding nursing strategy intelligent recommendation model, thereby enabling the nursing strategy intelligent recommendation model to recognize the feature relationship between different symptom features and corresponding nursing strategies. And enabling the model to recognize the symptom characteristics of a clinical patient and intelligently recommend a corresponding nursing strategy. The system can also combine model output and nurse feedback, fuse and recommend a clinical symptom nursing strategy most related to patient symptoms, so that nurses can make preliminary assessment and deal with the appearing symptoms to confirm nursing problems, sort critical and urgent conditions, develop nursing measures, highlight nursing key points and improve the nursing efficiency. And potential complications can be prevented or treated in time. In clinical nursing work, clinical nurses can be effectively guided to perform judgment thinking and carry out predictive nursing, so that the nursing work is homogenized, and the nursing quality and safety are improved.

The invention relates to a diagnosis and treatment result prediction method fusing a time sequence and traditional Chinese medicine multi-stage diagnosis and treatment, belongs to the technical field of traditional Chinese medicine diagnosis and treatment prediction, and solves the problem of lack of accurate whole-process prediction in the prior art. The method comprises the following steps: acquiring the current doctor-seeing symptom and historical doctor-seeing time sequence data of a to-be-predicted patient; the historical treatment time sequence data comprises symptom, syndrome, therapy and prescription data of each time step; constructing a graph structure corresponding to each time step of the historical doctor-seeing time sequence data; extracting a symptom feature sequence, a syndrome feature sequence, a therapy feature sequence and a prescription feature sequence by adopting a trained graph neural network model based on the graph structure and the current treatment symptom; and based on the symptom feature sequence, the syndrome feature sequence, the therapy feature sequence and the prescription feature sequence, performing multi-stage diagnosis and treatment result prediction by adopting a trained recurrent neural network model to obtain the prediction results of the syndrome, the therapy and the prescription of the current doctor seeing of the to-be-predicted patient. And accurate whole-process prediction is realized.

The invention relates to the technical field of triage devices, in particular to a voice triage device, which comprises a voice acquisition module used for acquiring oral symptom information of a patient; converting the symptom information into audio data; the voice recognition module is in communication connection with the voice acquisition module; the symptom analysis module is in communication connection with the voice recognition module and generates symptom feature vectors based on the symptom keywords; the intelligent triage module is in communication connection with the symptom analysis module and receives the symptom feature vector; calculating the similarity between the symptom feature vector and each disease based on a preset disease symptom database; according to the similarity, generating a preliminary diagnosis result and a recommended doctor seeing department; the output module is in communication connection with the intelligent triage module and is used for receiving the preliminary diagnosis result and a recommended treatment department; the preliminary diagnosis result and the recommended diagnosis department are output in a text or voice form, and a comprehensive and efficient voice triage system is constructed by combining advanced technologies such as voice recognition, natural language processing, machine learning and the like.

The invention provides a special disease first-aid full-process auxiliary decision-making method based on multi-modal perception and AI, and relates to the technical field of medical first aid, and the method comprises the steps: obtaining first-aid field multi-modal data, constructing a feature dependence graph, and recognizing the type and symptom features of a special disease; indexing special disease diagnosis and treatment data based on the symptom feature vector, and determining a reference case and a treatment path; the action space is constructed in combination with clinical specifications, the expected income is predicted by applying Monte Carlo search, and the optimal treatment scheme is generated, so that the first-aid special disease recognition accuracy can be improved, the treatment decision time can be shortened, and the first-aid intervention effect can be improved.

The invention discloses a traditional Chinese medicine physiotherapy management system based on big data and artificial intelligence, and relates to the technical field of physiotherapy management, and the system comprises a data input module, a data management module, a retrieval module, a database, a dialectical analysis module, and a medication evaluation module. Wherein the data input module is used for collecting patient data; the data management module can perform symptom feature extraction on the information received by the data input module; syndrome differentiation and treatment reference examples are stored in the database, and each syndrome differentiation and treatment reference example corresponds to a group of reference features and at least one group of reference treatment schemes; the retrieval module performs retrieval according to all symptom characteristics of the patient to select a conforming syndrome differentiation and treatment reference example; the dialectical analysis module performs dialectical analysis based on patient data and traditional Chinese medicine knowledge; the technical effects of improving the efficiency of screening information related to traditional Chinese medicine syndrome differentiation treatment by doctors and reducing the screening time and workload are achieved.

The invention discloses a traditional Chinese medicine prescription diagnosis decision method and system, and relates to the technical field of decision diagnosis, and the method comprises the steps: collecting the symptom description data, geographic position data and seasonal climate data of a patient, carrying out the standardization processing of the symptom description data, and generating a symptom feature vector; performing time sequence analysis on the symptom feature vector by using a recurrent neural network, extracting a symptom evolution feature matrix, calculating an environmental influence weight based on geographic position data and seasonal climate data, and performing feature fusion on the symptom evolution feature matrix and an environmental influence weight vector to obtain a comprehensive feature vector; inputting the comprehensive feature vector into a pre-trained BERT model to obtain a semantic feature vector, and calculating a syndrome matching degree; and calculating the prescription probability according to the symptom evolution vector, the environmental influence weight and the syndrome matching degree, and outputting the probability distribution of each prescription to obtain a prescription decision result. The accuracy and objectivity of diagnosis decision are improved, and standardization and intelligence of the traditional Chinese medicine diagnosis and treatment process are further achieved.

The invention relates to the technical field of knowledge maps, in particular to a veterinary treatment big data knowledge map construction method, which comprises the following steps of: acquiring animal case symptom characteristics, physical indexes, medical history records and intervention stage data, normalizing the symptom characteristics and encoding medical history to generate a case characteristic vector set; mapping symptoms and medicine nodes to establish a semantic relationship to calculate association strength, embedding physique and medical history to update node confidence to generate a personalized knowledge graph model, dynamically correcting edge weights in combination with feedback and medicine response, and extracting an effective intervention path to construct an association index to generate a veterinary treatment big data knowledge graph. According to the method, through normalization and sequential processing of multi-source case data, feature quantification and tracking are achieved, dynamic association is established based on semantic mapping and graph attention, confidence attenuation and an attribute weighting mechanism are fused, a node relation is optimized and self-adaptive evolution is carried out, individual difference and drug response capture is enhanced, and the updating performance of diagnosis and treatment knowledge is improved; and accurate and intelligent diagnosis and treatment analysis is promoted.

The invention discloses an intelligent prescription recommendation method based on shared expression fusion, a medium and equipment, and the method comprises the steps: firstly obtaining original symptom text data of a patient, and generating a potential embedded expression through a pre-training model; global and local relation graphs are constructed through full connection, nearest neighbor and farthest neighbor composition modes, and global and local features with the same dimension are extracted through a graph convolutional neural network; and utilizing the shared encoder, the global decoder and the local decoder to reconstruct features, optimizing parameters of the shared encoder, and obtaining fusion symptom feature representation. And initializing the prescription embedding vector and extracting the characteristics of the prescription embedding vector, calculating a correlation score matrix fusing the symptom characteristics and the prescription characteristics, and outputting a preset number of prescriptions with the highest score as a recommendation result. According to the method, the complex relationship between symptoms can be effectively mined, and the accuracy and stability of prescription recommendation are improved.

Embodiments of the present application disclose an information recommendation method, device, equipment, system and storage medium. In the method, first, medical text materials of a target object are acquired. Then, symptom entities in the medical text materials are determined. Next, based on the medical text materials, symptom entity feature information and context feature information corresponding to the symptom entities are extracted. Then, the symptom entity feature information and the context feature information are fused to obtain fusion features corresponding to the symptom entities. Finally, information is recommended based on the fusion features corresponding to the symptom entities in the medical text materials. By extracting the symptom entity feature information and the context feature information corresponding to the symptom entities from the medical text materials, richer symptom-related semantics is used as the basis for the recommended information. Compared with the prior art, the technical solution of the present application enriches the basis category of the recommended information, improves the utilization rate of information in the medical text materials, and thus makes the recommended information more accurate.

The application provides a syndrome type classification method and device based on syndrome element decomposition, equipment and medium. The method analyzes the syndrome type name and syndrome type description of the to-be-classified syndrome type through a syndrome element prediction model, splits and predicts the main syndrome element and the secondary syndrome element of the to-be-classified syndrome type as the symptom characteristics of the to-be-classified syndrome type. The target feature vector of the to-be-classified syndrome type is subjected to similarity matching through the retrieval of the known feature vector of the known syndrome type, so that the known syndrome type similar to the feature of the to-be-classified syndrome type is searched in the known syndrome type library to complete the classification of the to-be-classified syndrome type. The application relates to the technical field of model prediction. The feature vector of the to-be-classified syndrome type is obtained through the syndrome element decomposition of the syndrome type, and the vector matching is performed with the known syndrome type, so that the matching between the syndrome types with different standard names and the same symptoms can be realized, the accuracy of the syndrome type matching is improved, and the classification accuracy between the syndrome types with different standards is improved.

The present invention discloses a system for determining a venous thromboembolism prevention plan based on diagnosis and treatment information, and relates to the field of data processing technology. The system for determining a venous thromboembolism prevention plan includes: a feature matching module, which is used to establish a symptom matching model based on the symptom characteristics of venous thromboembolism, and collect the real-time diagnosis and treatment characteristics of the target object and input them into the symptom matching model for feature matching; a risk assessment and grading module, which is used to predict the risk probability of venous thromboembolism in the target object according to the feature matching results; and a personalized plan formulation module, which is used to formulate personalized venous thromboembolism prevention plans for target objects of different risk levels in combination with the preference characteristics of the target object. The present invention can accurately capture multiple factors such as the target object's treatment preference, drug selection preference, and risk tolerance preference through the preference analysis module, and then further optimize the prevention plan based on these personalized data.

The application discloses a kind of based on knowledge graph's simulation clinical experiment environment interaction method, specifically related to medical artificial intelligence and clinical simulation technical field;Initial disease entity node and its corresponding symptom feature set are acquired, and initial pathological state graph with time factor is constructed;Based on user interaction behavior extraction operation feature vector, utilize graph neural inference model to carry out multi-hop semantic path inference, generate post-interaction state graph;Further calculate the semantic shift degree caused by user operation, dynamically adjust graph inference weight;Extract relevant etiological entity and generate pathological evolution chain, calculate response difference degree in combination with user subsequent behavior, dynamically adjust virtual patient feedback, trigger path rollback operation if necessary;The application can realize the precise modeling and response control based on knowledge graph in clinical simulation environment, improve the interaction intelligence, explainability and stability of system, applicable to medical teaching, virtual diagnosis training and the like scene.

The application discloses a farm veterinarian question and answer and auxiliary diagnosis method and system based on a large language model, which comprises the following steps: standardizing a colloquial query to obtain structured query information; based on the information, mixed retrieval is carried out from a hierarchical veterinarian knowledge base to obtain a candidate disease list and a multi-source evidence set; a preliminary diagnosis answer is generated according to the multi-source evidence set, semantic and evidence alignment evaluation is carried out, and evidence sufficiency scores are generated; the differential diagnosis attributes of each disease in the candidate disease list are compared to identify key differences, and information missing items are identified by comparison with standard symptom profiles; based on the scores, key differences and information missing items, a multi-round diagnosis enhanced retrieval framework and user interaction are adopted, the candidate disease list and the multi-source evidence set are updated, and a diagnosis report is generated in combination with veterinary drug compliance rules. The application integrates hierarchical knowledge graphs, multi-evidence alignment and multi-round diagnosis logic, improves the accuracy of veterinarian question and answer, reduces knowledge illusion, and ensures drug compliance.

A method comprising receiving a record of historical epileptic seizure events in a patient, including, for each recorded historical epileptic seizure event, seizure characterisation data characterising duration, symptom profile, and / or severity of the seizure event; dividing the recorded seizure events of the record of historical epileptic seizure events into a plurality of seizure sets based on the seizure characterisation data; for at least one seizure set individually, using the record of historical epileptic seizures to generate a set-specific temporal probability model, wherein the set-specific temporal probability model projects variability over time of likelihood of occurrence of a seizure event fitting the seizure characterisation data for the respective individual seizure set into a future time period.

The invention discloses a time sequence classification method and system based on a multi-relation atlas, and the method comprises the steps: obtaining multivariable time sequence data through the sampling of a sensor, and defining the state of the sensor; related symptoms of each sensor state are mined through a large language model, and a sensor state relation graph is constructed for each symptom; a multi-graph gating network is constructed and trained, the multi-graph gating network is composed of a plurality of GNNs, a gating network and an MLP network, each GNN is learned by using a sensor state relation graph of one symptom, multivariable time sequence data is learned through the plurality of GNNs to obtain time sequence characteristics of the sensor state relation graph of each symptom, and the time sequence characteristics of the sensor state relation graph of each symptom are obtained; and aggregating into a total symptom feature through a gating network, and finally obtaining final classification output through an MLP network. The invention relates to the technical field of natural language processing, can combine a multi-relationship graph with multivariable time sequence data training, enables the construction of the relationship graph to be flexible, and effectively improves the classification accuracy.

The present invention provides a complication risk warning method, including: extracting all symptom features of the target organism to determine a symptom feature vector combination; inputting the symptom feature vector combination into a complication risk warning model to obtain the warning level of all complications corresponding to the symptom feature vector combination; the symptom feature vector combination is a combination of quantized representations of all symptom feature vectors; the complication risk warning model is obtained based on multiple feature vector combination samples and complication warning level label training corresponding to each feature vector combination sample. The present invention enables practitioners to be free from the constraints of professional knowledge level, and is widely used in intelligent risk warning assistance for various organisms, saving the time cost of combing decision rules one by one, so it can shorten the calculation feedback time of complication risk warning, making the organism complication risk warning model easier to promote among grassroots breeders.

The application discloses a pediatric emergency department hierarchical treatment guidance method based on symptom analysis and an electronic device, which comprises the following steps: acquiring age information of a target patient and detecting interaction data, wherein the interaction data comprises chief complaints and accompanying symptoms; based on the age information, a hierarchical evaluation rule library matched with the age information is called, and the interaction data is calculated by level through a preset logical judgment path in the hierarchical evaluation rule library, and a target pre-examination hierarchical result is output; the target pre-examination hierarchical result and the interaction data are combined, a preset pediatric clinical diagnosis and treatment mapping rule library is called for joint matching, a target examination item corresponding to the target pre-examination hierarchical result and the symptom characteristics is screened out, and a to-be-executed examination list is generated. In this way, the pre-examination hierarchical classification can be quickly and accurately performed, and the children and their families can be guided to efficiently complete the subsequent examination and treatment.

The invention relates to the technical field of artificial intelligence, in particular to a traditional Chinese medicine auxiliary diagnosis large model training method and device and electronic equipment. And in combination with symptom feature information of abnormal items in the traditional Chinese medicine theory as a mark, performing fine tuning training on the pre-trained multi-modal large model. In the process, multi-modal image data and traditional Chinese medicine theoretical knowledge are effectively fused, so that a second multi-modal large model special for traditional Chinese medicine auxiliary diagnosis is generated. According to the model, abnormal item identification can be carried out by accurately applying the traditional Chinese medicine theory based on the face, tongue and face infrared images of the user, so that the intelligent level and accuracy of traditional Chinese medicine identification in online inquiry are remarkably improved, the problems of information transmission limitation and non-uniform doctor resource distribution in the online traditional Chinese medicine inquiry are effectively solved, and the user experience is improved. And the online inquiry efficiency and the medical experience of the patient are improved.

The application provides a disease-specific emergency whole-process auxiliary decision-making method based on multi-modal perception and AI, relates to the technical field of medical emergency, and comprises the following steps: acquiring multi-modal data of an emergency scene, constructing a feature dependency graph, and identifying disease types and symptom characteristics; indexing disease diagnosis and treatment data based on a symptom characteristic vector, determining reference cases and treatment paths; combining clinical norms to construct an action space, applying Monte Carlo search to predict expected returns, and generating an optimal treatment plan, which can improve the accuracy of emergency disease identification, shorten the treatment decision-making time, and improve the emergency intervention effect.

The invention discloses an LLM triage decision-making method based on animal injury, and the method comprises the steps: obtaining the related structural input information of animal injury, including animal types, exposure levels, basic information of patients and symptom description, and standardizing the symptom features through a natural language processing technology; multi-modal fusion is carried out on the large language model and directed acyclic medical logic map embedded features constructed according to diagnosis and treatment specifications, a Prompt input sequence containing medical logic constraints is generated, and the large language model is explicitly guided to carry out reasoning according to a medical decision path; according to the method, the path validity is dynamically tracked in the reasoning process, a structured log is generated, and finally the triage level and the processing suggestion conforming to the diagnosis and treatment specification are output, so that the standardization, the consistency and the traceability of the triage decision are improved, and the medical compliance and the clinical application value of the intelligent triage system are effectively enhanced.

The application discloses a traditional Chinese medicine prescription efficacy prediction method based on a prescription-symptom heterogeneous graph, first, the characteristics of traditional Chinese medicines are counted, the traditional Chinese medicine characteristics are initialized, the traditional Chinese medicine characteristics are aggregated based on a multiple attention mechanism, the prescription characteristics are initialized, the symptom characteristics are initialized based on a known prescription-symptom correlation matrix, and the dimensionality of the symptom characteristics is reduced through an encoder, then, a prescription-symptom heterogeneous network is constructed, feature learning is performed in the heterogeneous network by using a graph convolution, and finally, the efficacy is predicted by using the finally learned prescription and symptom characteristics. The method of the application uses a multiple attention mechanism, the feature representation of the prescription is more reasonable, the dimensionality of the symptom characteristics is reduced by using an encoder, the training and learning efficiency is improved, a prescription-symptom heterogeneous network is constructed, feature learning is performed by using a graph convolution, the efficacy of the prescription can be more intuitively and efficiently predicted, and the prescription efficacy prediction precision is improved.