38 results about "Symptom profiles" patented technology

The invention discloses a medical triage method. The method comprises the following steps: receiving symptom description information; extracting a plurality of symptom features from the symptom description information; matching the plurality of symptom features with a preset medical knowledge graph to obtain target department information, wherein the medical knowledge graph comprises a mapping relationship between symptom characteristics and target department information; and outputting the target department information to prompt a user to see a doctor according to the target department information. The invention further discloses a medical triage device and a storage medium. Through intelligent medical triage, the treatment efficiency of the patient is improved.

The invention relates to an emergency patient clinic health monitoring system. The system is characterized by at least comprising an information acquisition module, a grading evaluation module and anearly warning evaluation module, wherein the information acquisition module acquires at least one physiological information data of a patient in a contact manner and is associated with two-dimensionalcode information of the patient; the grading evaluation module evaluates a first danger grade of the patient under the condition that at least one kind of physiological information data are abnormalon the basis of an abnormal physiological data change curve containing abnormal data in a preset time interval and a grade list associated with the abnormal physiological data change curve; the earlywarning evaluation module selects at least one terminal equipment associated with an emergency department as an alternative early warning terminal and evaluates the early warning priority order on thebasis of the danger level and/or symptom characteristics; and early warning is carried out according to the priority sequence under the condition that the abnormal physiological data change curve and/or the abnormal frequency trigger an early warning condition.

The invention relates to the field of natural language processing, and discloses a symptom data processing method and device, computer equipment and a storage medium. The method includes obtaining symptom data; processing the symptom data into a representation vector through a preset BERT encoder, wherein the representation vector is generated based on symptom feature data in the symptom data, wherein the symptom feature data comprises symptom names and symptom attributes, wherein the preset BERT encoder is obtained after training of a pre-training task, and wherein the pre-training task is used for determining an association relationship between the representation vector and the symptom name and the symptom attribute; and inputting the representation vector into a preset TextCNN model, and obtaining a classification result output by the preset TextCNN model. The accuracy of the triage result can be improved, and the quality of the triage result is improved. The invention can also be applied to construction of smart cities.

The invention discloses a disease auxiliary diagnosis system and device based on clustering and a storage medium. The system comprises a disease library module used for establishing an oral salty disease library; a vectorization module used for vectorization representation to obtain feature vectors of various disease symptoms; a disease clustering module used for clustering various diseases in thesalty disease library by adopting a k-means clustering method optimized based on a grey wolf-seagull algorithm; a first classification module used for establishing a to-be-identified case symptom feature vector and clustering the to-be-identified case symptom feature vector to obtain a first classification result; and a second classification module used for re-classifying the to-be-identified cases by calculating the intra-class semantic similarity according to the first classification result. According to the method, disease categories are clustered by adopting an optimized K-means clustering algorithm, so that the operand is greatly reduced, and the disease diagnosis rate and accuracy are improved.

The invention provides a venereal disease diagnosis system based on clinical symptom features, which comprises a features preprocessing unit, a classification and clustering unit, a model constructionunit and a venereal disease prediction unit, wherein the features preprocessing unit is used for marking and preprocessing the collected various venereal disease clinical symptom features of a patient; the classification and clustering unit is used for classifying and clustering the various venereal disease clinical symptom features through a classification algorithm and a clustering algorithm, setting the weight of each venereal disease clinical symptom feature acting on each venereal disease, and constructing a training set based on the venereal disease clinical symptom features and the venereal diseases; the model construction unit is used for training the training set through deep learning and a neural network model and obtaining a venereal disease diagnosis model based on the deep learning and the neural network; and the venereal disease prediction unit is used for outputting a diagnosis result according to the clinical symptom features of the to-be-identified crowd input into the venereal disease diagnosis model. According to the invention, the diagnosis accuracy can be greatly improved, the risk of missed diagnosis and misdiagnosis is reduced to the maximum extent, and unnecessary medical processes are reduced.

The invention relates to the technical field of artificial intelligence, and discloses a triage data processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring patient symptom information of a patient; performing human body system identification on the patient symptom information through an upper-layer learning model in the hierarchical reinforcement learning model, and identifying a first human body system category; obtaining a lower-layer reinforcement learning model associated with the first human body system category from thehierarchical reinforcement learning model; predicting the symptom information of the patient through the obtained lower-layer reinforcement learning model and obtaining an action result; and when theaction result is the recommended department action, performing symptom feature identification on the patient symptom information through the department triage model, and identifying a triage result corresponding to the patient. According to the invention, the related symptoms of the patient are inquired through the hierarchical reinforcement learning model, and the clinic department of the patientcan be quickly and accurately determined. The method is suitable for the field of smart medical treatment, and can further promote the construction of smart cities.

The embodiment of the invention provides a standard symptom extraction method and device, electronic equipment and a storage medium. The method comprises the steps of determining a medical record textof a to-be-extracted standard symptom; extracting medical record symptom region characteristics of the medical record text, and performing standard symptom extraction based on the medical record symptom region characteristics of the medical record text and the standard symptom characteristics of each standard symptom to obtain a standard symptom extraction result corresponding to the medical record text, wherein the standard symptom characteristics of each standard symptom are determined based on a knowledge graph. According to the standard symptom extraction method and device, the electronicequipment and the storage medium provided by the embodiment of the invention, the accuracy of standard symptom extraction is improved, and meanwhile, the spectrum departure rate of a standard symptomextraction result is also reduced.

The invention discloses a traditional Chinese medicine auxiliary diagnosis and treatment method and system for a chronic obstructive pulmonary disease. The method comprises the steps: collecting symptom information of a patient with the chronic obstructive pulmonary disease; preprocessing the symptom information to obtain a traditional Chinese medicine symptom type result corresponding to the symptom feature vector; according to the traditional Chinese medicine syndrome type result, acquiring recommended drugs through judgment; then performing, by the user, corresponding intervention correction according to the traditional Chinese medicine syndrome type result and the recommended medicine; and recording the treatment process of the chronic obstructive pulmonary disease patient and ending the treatment. According to the method provided by the invention, the traditional Chinese medicine auxiliary diagnosis and treatment process of the chronic obstructive pulmonary disease is decomposed into two links of syndrome type judgment and drug recommendation, and the relevance among symptoms, syndrome types and drugs in a traditional Chinese medicine diagnosis and treatment data set of the chronic obstructive pulmonary disease is fully utilized in the construction process of the syndrome type judgment model and the drug recommendation model. Therefore, the auxiliary diagnosis and treatment information with a relatively good auxiliary effect is obtained.

Embodiments of the invention provide a search method and apparatus, and a storage medium. The method comprises the steps of obtaining search information; obtaining at least one symptom feature based on the search information; according to the semantic association degree of the symptom features and the symptoms, weights are set for the symptom features respectively; obtaining a target similarity between each symptom feature with the set weight and at least one preset symptom entity; and determining a target symptom entity from the at least one preset symptom entity according to the target similarity and outputting the target symptom entity. Through the scheme, the accuracy of symptom entities can be identified, and similar symptoms and non-similar symptoms can be effectively distinguished.

The invention discloses a drug recommendation method and system for chronic obstructive pulmonary disease, and belongs to the field of medical data processing. The method comprises the steps: converting each symptom into a vector by using a knowledge graph which takes symptoms and syndromes as entities and takes the relationship between the symptoms and between the syndromes as the relationship between the entities, constructing a symptom matrix, after inputting a drug recommendation model, obtaining drug vectors containing drug recommendation scores, and taking part of drugs with the highest scores as recommended drugs. The model comprises a feature extraction network used for performing feature extraction on the symptom matrix to obtain a symptom feature matrix; a first vector reshaping layer, which is used for reshaping the symptom feature matrix into a symptom feature vector; a recurrent neural network, which is used for decoding a tag vector from the symptom feature vector; and a scoring network, which is used for mapping the tag vector into a drug vector. According to the method, the influence of syndrome type prediction errors can be avoided while the relevance among symptoms, syndrome types and drugs is utilized, and the recommendation accuracy is improved.

The invention provides a disease cognition system based on main symptom and accompanying symptom words. The system comprises a data acquisition module used for acquiring disease feature information and corresponding symptom feature information and establishing a disease knowledge database, a feature extraction module which is used for obtaining to-be-recognized clinical symptom feature informationand obtaining feature words, a matching module which is used for matching the disease feature words to be recognized with the disease feature information and searching symptom feature information corresponding to the disease feature information from a disease knowledge database according to the matching similarity, and a cognition module which is used for establishing a Jaccard coefficient similarity algorithm, calculating the similarity between the symptom feature words to be identified and the symptom feature information and generating a corresponding cognition report. According to the method, a combined cognitive model is constructed through the keyword matching method and the Jaccard coefficient similarity theorem, the to-be-recognized disease is accurately recognized through the combined cognitive model, recognition accuracy of the system is improved, and user experience is improved.

The invention provides a medical record information processing method and device, electronic equipment and a storage medium. The method comprises the steps that target medical record information is acquired; extracting target symptom features in the target medical record information; determining the similarity between the target symptom feature and a preset symptom feature of each preset reference crowd, wherein the preset reference crowds are crowds with the same kind of disease types; based on each similarity and a first preset similarity condition, searching a target reference crowd matched with the target symptom feature in all preset reference crowds; and determining a diagnosis result according to the disease type corresponding to the target reference population. According to the embodiment of the invention, the disease prediction speed can be improved.

The invention discloses a disease prediction set processing method and device, electronic equipment and a storage medium. The method comprises the steps: obtaining a disease prediction set of a to-be-detected sample, wherein the disease prediction set comprises at least two disease types subjected to confidence degree sorting, and the to-be-detected sample comprises at least one symptom feature; based on the confusion degree of the at least one symptom feature, scoring the to-be-detected sample to judge whether the to-be-detected sample is an error-prone sample; and if the to-be-detected sample is an error-prone sample, adjusting the confidence degree sequence in the disease prediction set of the to-be-detected sample. In this way, the prediction accuracy of the disease prediction set can be improved.

The invention discloses a medical record processing method, a computer readable storage medium and computer equipment. The method comprises the following steps: acquiring a target medical record; extracting a target symptom word set from the target medical record; based on the target symptom word set, extracting a target symptom feature word set from the target medical record; obtaining a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease; and determining a target disease corresponding to the target medical record based on the first weight of the target symptom word in the predetermined disease included in the target symptom word set and the second weight of the target symptom feature word in the predetermined disease included in the target symptom feature word set. The technical problems of low efficiency and high error rate when the corresponding disease is determined according to the medical record of the patient in the related technology are solved.

The invention provides a disease correlation prediction method based on a twin network, which solves the technical problem of small disease correlation calculation range in the prior art, and comprises the following implementation steps of: (1) acquiring a disease data set; (2) constructing a training sample set and a test sample set; (3) constructing symptom features and classification features of the disease; (4) constructing a disease correlation prediction model based on a twin network; (5) carrying out iterative training on the twin network-based disease correlation prediction model C; and (6) obtaining a disease correlation prediction result. According to the method, the calculation range of disease correlation is remarkably expanded, and the method can be used for guiding classification of diseases, inferring pathogenesis of the diseases, repositioning of drugs and research and development of new drugs.

The invention relates to the field of electronic medical records, and discloses an electronic medical record data-based symptom complexity calculation method. The method comprises the following steps: a, establishing symptom characteristics: acquiring symptoms, duration and identifiers (ID) of patients from a database, and enabling the symptoms and the duration to correspond to the corresponding patients according to the identifiers (ID) of the patients; b, symptom preprocessing: performing statistics on symptoms, establishing a symptom matrix of the patient, and outputting the symptom matrix after preprocessing; c, symptom complexity calculation: calculating a symptom probability in the preprocessed symptom matrix and a duration probability corresponding to the symptom, and constructing a symptom complexity calculation formula of the patient according to the symptom probability and the duration probability. According to the method, on the basis of a whole disease research all-crowd queue, the relationship between symptoms and duration is proposed, the current symptoms are converted into vectors on the basis of expressions of all symptoms of crowds in the current queue, and the complexity and severity of the symptoms are obtained.

The invention discloses a physique recognition method and device based on a knowledge graph, equipment and a storage medium, and can be widely applied to the technical field of artificial intelligence. The method comprises the following steps: acquiring symptom text data; extracting symptom feature data from the symptom text data; inputting the symptom characteristic data into a knowledge graph to obtain strong correlation symptom data and/or weak correlation symptom data corresponding to the symptom characteristic data; according to the knowledge graph and the strong correlation symptom data and/or weak correlation symptom data corresponding to the symptom feature data, obtaining score data of the symptom feature data corresponding to a plurality of preset physique category data; according to the score data of the symptom feature data corresponding to a plurality of preset physique category data, determining the physique category data corresponding to the symptom feature data, the preset physique category data including the physique category data, the physique recognition accuracy can be effectively improved, and the diagnosis effect is ensured.

The invention provides a self-service medical registration interaction method and device, a storage medium and a self-service registration machine, and the method comprises the steps: collecting feature identification information of a target user, and recognizing identity information of the target user based on the feature identification information; acquiring symptom feature information of the target user, and searching a target department and a target doctor matched with the symptom feature information in a hospital to which the self-service registration machine belongs; generating registration information of the target user according to the identity information, the target department and the target doctor. According to the invention, when the user needs self-service registration, after identity authentication and symptom description information of the user are completed by obtaining the feature identification information of the user, the corresponding department can be automatically matched, automatic registration can be completed, so that the user operation process can be simplified and intellectualization of self-service registration can be achieved.

The invention provides a carotid artery calcification index evaluation method, and relates to the technical field of medical treatment. According to the carotid artery calcification index evaluation method, a medical service platform, a patient terminal, an expert terminal and a medical institution system are included, and the patient terminal, the expert terminal and the medical institution system all establish data communication with the medical service platform; the medical service platform collects symptom features related to carotid artery calcification from the expert terminal and the medical institution system which establish communication, classifies the symptom features according to the types of the symptom features, and corresponds to the numerical value of the frequency after symptom classification according to the occurrence frequency of the symptom. By constructing a framework of a medical service platform, a patient terminal, an expert terminal and a medical institution system, convenience is provided for daily examination of people, people can judge the current state of the body carotid artery according to the finally obtained carotid artery calcification index by depending on the method, the operation process is very simple, special examination is not needed, and the efficiency is high. And the safety of the carotid artery can be ensured.

The invention belongs to the technical field of pet disease diagnosis, and particularly discloses a pet disease probability diagnosis method and system, and the method comprises the steps: calculating the weight of each part of pet disease probability calculation through the types, symptom features, physiological features, past experiences and auxiliary inspection results of pets; calculating the probability that the pet suffers from the disease according to a pet disease diagnosis rule standard, wherein the disease probability is equal to the sum of the weight percentages representing all symptoms * the symptom credibility * the first coefficient * the second coefficient * the third coefficient. The pet disease probability diagnosis method and system are high in practicability, can help a user to remarkably improve the accuracy of pet disease diagnosis, reduce the misdiagnosis rate and death rate of pets, and solve the problem that pet disease diagnosis is inaccurate.

The invention provides a clinical somatic symptom classification diagnosis system, and relates to the field of medical diagnosis. The system is composed of a user side and a background cloud server side. The user side is used for inputting patient body symptom characteristic data and checking results; the background cloud server comprises a cloud storage platform, a big data computing platform and an intelligent analysis platform; a clinical somatic symptom classification diagnosis scale is stored in the cloud storage platform, the big data calculation platform is used for calculating somatic symptom characteristic data of a patient, and the intelligent analysis platform is used for analyzing a diagnosis result. All operations of the clinical somatic symptom classification diagnosis system can be completed through the mobile terminal device, and the system is simple, efficient and convenient. The data is centrally stored in a back-end cloud platform database, support is provided for future research and analysis, efficient utilization of data resources is achieved, and a foundation is laid for AI artificial intelligence to achieve intelligent diagnosis.

The embodiment of the invention discloses a method, device and equipment for realizing feature selection. The method comprises the steps: acquiring a current symptom feature set of a user, and determining a first symptom feature and a feature value of the first symptom feature; acquiring the conditional probability of the first symptom feature under each disease condition and the conditional probability of a second symptom feature under each disease condition from the medical knowledge graph, calculating the global importance of the second symptom feature, and/or calculating the identification importance of the second symptom feature; and finally, according to the global importance and/or identification importance of the second symptom features, determining the importance of the second symptom features, sorting the second symptom features, and selecting the second symptom features meeting a preset condition from a sorting result as candidate symptom features. Therefore, the correlation degree between the symptom features of the inquiry can be enhanced, the calculation complexity of determining the second symptom feature is reduced, the inquiry times required for determining the predicted disease are reduced, and the inquiry efficiency of the symptom features is improved.

The invention provides a traditional Chinese medicine prescription recommendation method based on symptom term mapping and deep learning, and belongs to the technical field of traditional Chinese medicine prescription recommendation. All symptom words of a patient are subjected to symptom term mapping, network embedding representation, symptom feature fusion, convolutional neural network learning, full-connection network training and activation layer activation; obtaining a prediction probability of each candidate traditional Chinese medicine; the prediction probability of each traditional Chinese medicine is arranged in a descending order, and the corresponding traditional Chinese medicine sequence after descending is used as the final recommendation sequence. According to the invention, traditional Chinese medicine prescription recommendation is carried out based on symptom term mapping and deep learning, the'out-of-word 'problem of clinical symptoms is relieved through symptom term mapping, prescription recommendation is carried out in combination with deep learning, and an attention-based prescription recommendation feature contribution degree evaluation module is established. A feature fusion-based symptom term representation and patient clinical feature fusion strategy is established, and the reliability of prescription recommendation is improved.