A big data-based intelligent medical interaction method and system

Abstract

The present application relates to the technical field of data interaction, and provides a smart medical interaction method and system based on big data, in particular to the method, which comprises the following steps: creating a physiological knowledge data model, a user registers by inputting personal attributes through a terminal, and different permissions are given according to the personal attributes; the user inputs relevant health data through the terminal, and collects physiological data of the patient; the relevant health data is analyzed, and a weight value is given to real-time physiological parameters; the weight value is calibrated; the real-time physiological parameters are input into a disease state simulation model for simulation; the simulation result is input into the disease state simulation physiological knowledge data model, a corresponding doctor is found according to the simulation result to provide an answer, and the answer process is stored. The system comprises a health data acquisition module, a health data calling module and an interactive health data module. The present application improves the quality and efficiency of medical services, and provides a precise, convenient and personalized health management scheme for patients.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data interaction, and particularly relates to a smart medical interaction method and system based on big data. BACKGROUND

[0002] Smart medical interaction refers to the use of modern information technology and artificial intelligence technology to build an information-based and intelligent medical environment, enabling interaction between patients, medical staff, medical institutions, and medical equipment, optimizing the medical process, and improving the quality and efficiency of medical services. The design scheme of smart medical interaction usually includes intelligent reservation systems, intelligent diagnosis systems, intelligent triage systems, intelligent follow-up systems, voice interaction technologies, mobile applications, and intelligent data analysis. In smart medical interaction, the application of digital human technology significantly improves the convenience and intelligence level of hospital services. For example, the Moke AI digital human interaction all-in-one machine helps patients quickly find their destination in the hospital through voice interaction and provides functions such as registration, doctor query, and patient question answering, thereby improving the medical experience. In addition, the cloud voice company has comprehensively upgraded the intelligent level of various products in the medical business line based on the Shanhai large model, realizing the transition from an assistant to an expert. Smart medical interaction also involves various forms of intelligent communication, such as intelligent inquiry, intelligent treatment, and intelligent follow-up, which improve patient experience by simplifying processes, improving efficiency, and strengthening doctor-patient communication. Video consultation in telemedicine is an important scenario for promoting doctor-patient communication, and with the help of 5G and artificial intelligence information technology, patients can enjoy real-time consultation services at home. However, smart medical interaction also faces challenges such as data security and privacy protection. Therefore, the relevant departments of the state have issued a series of policies to promote the development of smart medical care, and through continuous innovation, they have promoted the interconnection and sharing of health information. In the future, the development of smart medical care requires the cooperation of multiple parties, including the government, hospitals, colleges and universities, equipment manufacturers, and information technology companies, to participate in production, teaching, and research cooperation, establish unified standards, continuously integrate and utilize cutting-edge innovative technologies, and promote the digitalization process of the entire medical industry. Through the application of modern information technology and artificial intelligence technology, smart medical interaction not only improves the quality and efficiency of medical services, but also improves the patient's medical experience and promotes the transition from the traditional "doctor-centered" communication mode to the new "patient-centered" communication mode. With the continuous progress of technology, smart medical interaction will play an even greater role in the future, providing patients with more high-quality and convenient medical service experiences.

[0003] Prior art one, China patent, application number: 202410809501.8 discloses a health medical data authentication and privacy protection method in smart medical treatment, comprising the following steps: one, the gateway device calls the key generation algorithm based on the security parameter to output the public key for verifying the signature and the private key for signing; two, the gateway device calls the signature algorithm based on the private key generated by the key generation algorithm and the health medical data collected by the gateway device to output the signature of the health medical data. Although the health medical data authentication and privacy protection method in smart medical treatment not only improves the flexibility of data sharing, but also prevents excessive editing of data, enhances the security and availability of shared health medical data, and provides more efficient security protection for the sharing of health medical data in the smart medical system; however, the real-time response and processing capacity are insufficient, which leads to the inability to process in time.

[0004] Prior art two, China patent, application number: 202410168178.0 discloses an internet big data smart medical system based on remote wireless communication, relating to wireless communication technology field. When the system runs, the login user is verified through the client module, and the related information is filled in through the discomfort information module, including fill-in items and selection items, wherein the sequence information of the selection items is the first data set, the user's fill-in information is processed through the data processing module, the related discomfort characteristic data is counted as the second data set, and the matching index Ppzs is obtained by comparing with the large amount of patient health data stored in the cloud service storage module. Through the information calculation module, the matching index Ppzs and the first data set, and the second data set are calculated to obtain the suggestion index Jyzs, the grade suggestion scheme is obtained by comparing with the preset threshold, and the suggestion document guide is formed according to the scheme content. Although it provides a clear action plan for patients so that they can better manage their health status; however, the data sharing and integration are difficult, which leads to low service efficiency.

[0005] The prior art three, Chinese patent, application number: 202410149558.X discloses a kind of intelligent medical system based on artificial intelligence, the operation method of system includes the following steps: step one: data acquisition and integration of medical equipment are realized by sensor;Step two: establish anomaly detection model, and realize fault prediction;Step three: user interface and remote support;Step four: predictive resource management, the data acquisition and integration module is used to collect medical equipment data and carry out data format integration;The anomaly detection and fault prediction module is used to detect the anomaly of medical equipment and realize abnormal fault prediction;The maintenance suggestion and optimization strategy module is used to give the maintenance suggestion and optimization scheme of equipment by system, the anomaly detection module is used to discover the abnormal situation of equipment in time;Data integration and cleaning module is used to ensure the consistency and comparability of data.Although, with the characteristics of medical equipment fault prediction accurate and effective to improve maintenance efficiency;However, real-time response and processing capacity are insufficient, so that it cannot be handled in time.

[0006] At present, prior art one, prior art two and prior art three have the problems of insufficient real-time response and processing capacity and difficult data sharing and integration.Therefore, the present application provides a kind of intelligent medical interactive method and system based on big data. SUMMARY

[0007] To achieve the above object, the technical scheme is as follows:

[0008] In one aspect of the present application, an intelligent medical interactive method based on big data is provided, comprising the following steps:

[0009] A physiological knowledge data model is created based on a historical physiological knowledge database. Users register by inputting personal attributes through a terminal and are given different permissions according to their personal attributes. Users input relevant health data through the terminal, collect physiological data of patients, and transmit the collected physiological data of patients to the physiological knowledge data model.

[0010] The relevant health data is analyzed, and the real-time physiological parameters are given weight values according to the analysis results. The physiological knowledge data model is calibrated according to the weight values. If the calibration is successful, it is directly called. If the calibration fails, a personal data set is formed. The personal data set is divided into a training set, a validation set and a test set.

[0011] A disease state simulation model is constructed based on a patient physiological database. The disease state simulation model is trained using the training set. The real-time physiological parameters are input into the disease state simulation model for simulation. The simulation results are input into the disease state simulation physiological knowledge data model. According to the simulation results, the corresponding physician is found to answer, and the answer process is stored.

[0012] In an alternative embodiment, the process of collecting physiological data of the patient comprises the following steps:

[0013] Based on the historical physiological knowledge database, a physiological knowledge data model is created to identify and connect various health data sources related to the research; historical data is obtained from selected data sources; different historical data is integrated into different physiological knowledge sub-data sets, and different physiological knowledge sub-data sets are combined into a physiological knowledge data set;

[0014] The user inputs personal attributes through the terminal to register and is given different permissions according to the personal attributes; the user inputs relevant health data through the terminal to collect physiological data of the patient, and the collected physiological data of the patient is transmitted to the physiological knowledge data model;

[0015] The physiological data of the patient is preprocessed, including cleaning, conversion and formatting, processing missing values and abnormal values, etc.; the preprocessed physiological data of the patient is input into the physiological knowledge data model for screening.

[0016] In an alternative embodiment, the process of calibrating the physiological knowledge data model according to the weight value comprises the following steps:

[0017] The relevant health data and the user's historical data are compared and analyzed to obtain the patient's health condition; a weight value is assigned based on the patient's health condition, and the data retrieval strategy and the target retrieval database of the physiological knowledge data model are retrieved according to the weight value;

[0018] The database strategy of the target retrieval database is determined; the target retrieval data is retrieved in the target retrieval database based on the data retrieval strategy and the database strategy; and the target retrieval data is output to the user terminal;

[0019] If the retrieval fails, it is determined that the calibration fails; the relevant health data and the historical data and the comparison and analysis results are integrated to form a personal data set.

[0020] In an alternative embodiment, the process of obtaining the patient's health condition comprises the following steps:

[0021] The user's historical state data is retrieved, and the relevant health data is difference calculated to obtain a state change value; if the state change value is positive, it is judged as a recovery state; if the state change value is negative, it is judged as a deterioration state; if the state change value is zero, it is judged as a stable state;

[0022] The state change value and the personal attribute value are summed up to obtain the patient's health condition; the patient's health state is analyzed to obtain a patient risk value; and a weight value is assigned to the relevant health data according to the patient risk value;

[0023] The data retrieval strategy and the target retrieval strategy are retrieved based on the weight value.

[0024] In an optional embodiment, the process of retrieving the target retrieval data in the target retrieval database comprises the following steps:

[0025] If the data retrieval strategy is determined to be the paging retrieval strategy, it is determined whether the first call statement contains a location statement; if the first call statement contains a limit condition statement, it is determined whether the number of data return rows in the limit condition statement is greater than a preset threshold value;

[0026] If the number of data return rows is greater than the preset threshold value, the target application is determined according to the application information, and the target retrieval data of the target application is retrieved in the target retrieval database according to the target application and the database strategy; if the data retrieval strategy is determined to be the non-paging retrieval strategy, the retrieval data of the target application is retrieved in the target retrieval database according to the data query amount of the target application;

[0027] If the first call statement does not contain a limit condition statement, a preset limit statement is added to the first call statement to obtain an updated second call statement; the target database of the target application is retrieved in the target retrieval database, and the retrieved data is input to the user terminal.

[0028] In an optional embodiment, the process of forming a personal data set comprises the following steps:

[0029] It is determined whether the target application can be matched in the preset application whitelist of the target database; if the target application can be matched in the preset application whitelist, the maximum return row number of the preset application whitelist is determined; and the target retrieval data of the target application is retrieved in the target retrieval database according to the maximum return row number;

[0030] If the retrieval fails, it is determined that the calibration fails; the relevant health data, the historical relevant data, and the comparative analysis result are integrated to form a personal data set;

[0031] The personal data set is subjected to preprocessing operations such as removal of abnormal values, balancing of data distribution, classification variable conversion, and numerical variable standardization; and the personal data set is divided into a training set, a validation set, and a test set.

[0032] In an optional embodiment, the process of inputting the simulation result into the physiological knowledge data model of the diseased state simulation comprises the following steps:

[0033] Based on the personal data set, historical disease data in the patient physiological database is retrieved; the training set in the personal data set is used to train the disease state model; during the training process, the personal data set and the historical disease data of the user are analyzed to obtain the disease data trend;

[0034] The disease data is actually learned, and recursive variable screening is performed; based on the training result of the disease state model each time, variables less than a preset value are gradually eliminated, and according to the simulation result of the finally trained disease state model, the variable with the largest contribution to the simulation result of the disease state is extracted;

[0035] The real-time physiological parameters are input into the disease state simulation model for simulation; the simulation result is input into the physiological knowledge data model; the physiological knowledge data model outputs the simulation result to the user terminal; and according to the simulation result, the corresponding doctor is found to answer, and the answer result is stored.

[0036] In an optional implementation, the process of extracting the variable with the largest contribution to the simulation result of the disease state includes the following steps:

[0037] The node set of the training set in the personal data set and the historical disease data of the user is collected, the output data and the characteristics of the output data of each node in the node set are analyzed, and the dependency relationship between the nodes is analyzed according to the analysis result of the node input data and the output data characteristics;

[0038] According to the dependency relationship, a dependency matrix between nodes is constructed, the similarity value between the output data of the historical disease node and the output data of the real-time health data node is calculated, and the dependency relationship between the output data of the historical disease node and the data of the real-time health data node is judged according to the threshold value between the similarity values;

[0039] According to the dependency relationship, the optimal node configuration information, the potential parallel execution set and the sequential execution set between the nodes are identified; and according to the identified parallel execution set and sequential execution set, the execution order of the optimized analysis dependency relationship configuration is reordered.

[0040] In an optional implementation, the process of outputting the simulation result to the user terminal includes the following steps:

[0041] Based on the training result of the disease state simulation model each time, variables less than a threshold value are gradually eliminated, and according to the simulation result of the finally trained disease state, the variable with the largest contribution to the simulation result is extracted; and the final disease state simulation model is obtained;

[0042] The real-time physiological parameters are input into the disease state simulation model, the real-time physiological parameters are simulated, and the health data change of the user is obtained; the health data change of the user is compared with the preset health data change;

[0043] The evaluation result is input into the physiological knowledge data model, and the evaluation result is output to the user terminal, and a corresponding doctor is found according to the evaluation result to answer, and the answering process is stored.

[0044] In another aspect of the present application, a big data-based intelligent medical interaction system is provided, comprising:

[0045] The health data acquisition module is used to create a physiological knowledge data model based on a historical physiological knowledge database, and the user inputs personal attributes through the terminal to register, and different permissions are given according to the personal attributes; the user inputs relevant health data through the terminal, collects physiological data of the patient, and transmits the collected physiological data of the patient to the physiological knowledge data model;

[0046] The health data acquisition module is used to create a physiological knowledge data model based on a historical physiological knowledge database, and the user inputs personal attributes through the terminal to register, and different permissions are given according to the personal attributes; the user inputs relevant health data through the terminal, collects physiological data of the patient, and transmits the collected physiological data of the patient to the physiological knowledge data model;

[0047] The interactive health data module is used to construct a disease state simulation model based on the patient physiological database, and the disease state simulation model is trained using the training set; the real-time physiological parameters are input into the disease state simulation model for simulation; the simulation result is input into the disease state simulation physiological knowledge data model, a corresponding doctor is found according to the simulation result to answer, and the answering process is stored.

[0048] The present application can provide personalized health management solutions for different users through user registration and input of personal attributes; the collected health data can update the physiological knowledge data model in real time, improving the accuracy and timeliness of health monitoring. Through real-time data analysis and weight assignment, the system can dynamically adjust the physiological knowledge data model, improving the adaptability and accuracy of the model; dividing the personal data set into a training set, a validation set and a test set can help improve the training effect and generalization ability of the model. Through the disease state simulation model, the system can more accurately predict the disease state of the patient, improving the accuracy of diagnosis; the system can automatically find a corresponding doctor to answer according to the simulation result, providing intelligent medical services; storing the answering process can help accumulate knowledge and optimize future service processes. BRIEF DESCRIPTION OF DRAWINGS

[0049] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, and are used to explain the present application together with embodiments of the present application, and do not constitute a limitation of the present application. In the drawings:

[0050] Figure 1A step flow chart of the method for providing a big data-based smart medical interaction in embodiment 1 of the present application is provided as follows:

[0051] Figure 2 A step flow chart of the step of collecting physiological data of a patient in the method for providing a big data-based smart medical interaction in embodiment 2 of the present application is provided as follows:

[0052] Figure 3 A step flow chart of the step of calibrating a physiological knowledge data model according to a weight value in the method for providing a big data-based smart medical interaction in embodiment 3 of the present application is provided as follows:

[0053] Figure 4 A step flow chart of the step of obtaining a health condition of a patient in the method for providing a big data-based smart medical interaction in embodiment 4 of the present application is provided as follows:

[0054] Figure 5 A step flow chart of the step of obtaining a target calling data from a target calling database in the method for providing a big data-based smart medical interaction in embodiment 5 of the present application is provided as follows:

[0055] Figure 6 A step flow chart of the step of forming a personal data set in the method for providing a big data-based smart medical interaction in embodiment 6 of the present application is provided as follows:

[0056] Figure 7 A step flow chart of the step of inputting a simulation result to a physiological knowledge data model simulating a disease state in the method for providing a big data-based smart medical interaction in embodiment 7 of the present application is provided as follows:

[0057] Figure 8 A step flow chart of the step of extracting a variable having the largest contribution to a simulation result of a disease state in the method for providing a big data-based smart medical interaction in embodiment 8 of the present application is provided as follows:

[0058] Figure 9 A step flow chart of the step of outputting a simulation result to a user terminal in the method for providing a big data-based smart medical interaction in embodiment 9 of the present application is provided as follows:

[0059] Figure 10 A functional module diagram of the system for providing a big data-based smart medical interaction in embodiment 10 of the present application is provided as follows:

[0060] Figure 11 A block diagram of an electronic device provided in embodiment 11 of the present application is provided as follows:

[0061] Figure 12 A block diagram of a computer readable storage medium provided in embodiment 12 of the present application is provided as follows: DETAILED DESCRIPTION

[0062] Clearly, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments.

[0063] Hereinafter, the terms "first", "second", and the like are used only for the convenience of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second", and the like can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0064] In the present application, unless otherwise explicitly specified and limited, the term "connection" should be understood broadly, for example, "connection" can be a fixed mechanical connection, or a detachable mechanical connection, or integrated; or "connection" can be direct connection, or indirect connection through intermediate media. In addition, unless otherwise explicitly specified and limited, the term "coupling" should be understood broadly, for example, "coupling" can be direct electrical connection, for example, physical contact and electrical conduction between two components, or can be understood as electrical connection between different components through solid lines such as copper foil or wire of printed circuit board (PCB) in circuit structure, to transmit electrical signals; or "coupling" can be indirect electrical connection between two components through intermediate media; or "coupling" can be electrical connection between two components through space / non-contact, for example, capacitive coupling between two components, to transmit electrical signals.

[0065] In the embodiments of the present application, the orientation terms such as "up", "down", "left", "right", etc. can include but not limited to the orientation defined by the relative position of the components in the drawings. It should be understood that these directional terms can be relative concepts, which are used for relative description and clarification, and can be changed accordingly according to the change of the position of the components in the drawings.

[0066] The embodiments of the present application can be used in smart hospital and ward, remote medical treatment and remote monitoring, medical resource optimization and management, smart medical platform and cloud service, and mobile medical treatment and wearable devices.

[0067] The key technical features of the embodiments of the present application are as follows: the embodiments of the present application input personal attributes and health data by the user, the system can assign different permissions to different users, and construct a personalized physiological knowledge data model according to the personal data; the system can collect the physiological data (such as heart rate, blood pressure, blood sugar level, etc.) of the patient in real time, and analyze these data in real time. By assigning a weight value to the physiological parameter and calibrating the physiological knowledge data model, the system can dynamically adjust the model parameters; the disease state simulation model constructed based on the patient physiological database can learn through the training set and simulate real-time physiological parameters to predict the patient's disease state; the system supports different users to open different clinical data access permissions; through role management and system log recording, the user operation can be effectively managed to prevent data leakage and abuse; the system can find the corresponding doctor for answering according to the simulation results, and store the answering process; the system can integrate physiological data from different devices and sensors, analyze and mine through big data processing technology, find the potential rules and trends behind the data, and provide valuable health information and suggestions for the user; the system can predict the future changes of health indicators according to the real-time physiological index data, and generate corresponding dynamic labels. Combined with the user portrait information, the system can recommend personalized health knowledge to help the user better manage his health.

[0068] Embodiment 1

[0069] As shown in Figure 1 , the embodiments of the present application provide a smart medical interaction method based on big data, comprising the following steps:

[0070] Step S100: creating a physiological knowledge data model based on a historical physiological knowledge database, a user inputs personal attributes through a terminal to register, and different permissions are assigned according to the personal attributes; the user inputs related health data through the terminal, collects the physiological data of the patient, and transmits the collected physiological data of the patient to the physiological knowledge data model;

[0071] Among them, different permissions include patient permissions, doctor permissions and management permissions, etc.

[0072] The expression of the physiological knowledge data model is:

[0073]

[0074] The activation function calculation formula is:

[0075]

[0076] The permission coefficient calculation formula is:

[0077]

[0078] Trend coefficient calculation formula:

[0079]

[0080] where n represents the number of data sources, i.e., how many different health data sources are integrated into the model; D i′ represents the i'th data source, such as heart rate, blood pressure, blood glucose level, or primary care practice, laboratory data, insurance data, etc.; W i′ represents the importance or contribution of the i'th data source in the model, different data sources may have different effects on the model, so different weights need to be given; U represents the user's personal attributes, such as age, gender, medical history, etc., which will affect the analysis results of the model; P represents the permissions given to the user according to their attributes, the permission coefficient will affect the range and depth of data that the user can access or use; m represents the number of time series, i.e., how many time series data are used in the model; T j represents the j'th time series data, such as heart rate over time, blood pressure over time, etc.; TC j represents the trend coefficient of the j'th time series data, which is used to capture the trend of time series data; p represents the number of neural network layers, i.e., how many layers of neural networks are included in the model; L k represents the k'th layer of neural network, which is used for nonlinear transformation and feature extraction of data; AF k represents the activation function of the k'th layer of neural network, such as Sigmoid function, which is used to introduce nonlinear characteristics; q represents the number of data fusion, i.e., how many different data fusion methods are used in the model; F l represents the l'th data fusion method, such as weighted average, principal component analysis, etc., which is used to fuse data from different sources; FW l represents the weight of the l'th data fusion method, which is used to adjust the contribution of different data fusion methods in the model; e represents the natural constant, approximately equal to 2.71828; r represents the total number of user attributes; A u represents the weight of the u'th user attribute, which represents the influence degree of the attribute on the permission; C u represents the contribution value of the u'th user attribute, which represents the specific value or importance of the attribute; t represents the index of time point, s represents the total number of time points of time series data; T j (t) represents the value of the j'th time series at time point t, such as heart rate, blood pressure, etc. changing with time; G(t) represents the weight or importance of time point t, which is used to adjust the influence of different time points on the trend;

[0081] Step S200: analyze the relevant health data, and assign a weight value to the real-time physiological parameters according to the analysis result; the physiological knowledge data model is calibrated according to the weight value, if the calibration is successful, it is directly called; if the calibration fails, a personal data set is formed; the personal data set is divided into a training set, a validation set and a test set;

[0082] The physiological data includes heart rate, blood pressure, blood sugar level and drug intake, etc.

[0083] Step S300: based on the patient physiological database, a disease state simulation model is constructed, the disease state simulation model is trained using the training set; the real-time physiological parameters are input into the disease state simulation model for simulation; the simulation result is input into the disease state simulation physiological knowledge data model, the corresponding doctor is found according to the simulation result to answer, and the answering process is stored.

[0084] In the above embodiment, in step S100 of the present embodiment, based on the historical physiological knowledge database, a data model reflecting the relationship between physiological parameters and health status is constructed; the user inputs personal attributes through the terminal to register, and the system assigns different permissions (patient permission, doctor permission, management permission, etc.) according to these attributes; the user inputs relevant health data through the terminal, which is collected and transmitted to the physiological knowledge data model; through user registration and input of personal attributes, the system can provide personalized health management solutions for different users; the collected health data can update the physiological knowledge data model in real time, improving the accuracy and timeliness of health monitoring. In step S200, the collected health data is analyzed, and a weight value is assigned to the real-time physiological parameters according to the analysis result; the physiological knowledge data model is calibrated according to the weight value, if the calibration is successful, it is directly called; if the calibration fails, a personal data set is formed, and the personal data set is divided into a training set, a validation set and a test set; through real-time data analysis and weight assignment, the system can dynamically adjust the physiological knowledge data model, improving the adaptability and accuracy of the model; dividing the personal data set into a training set, a validation set and a test set helps to improve the training effect and generalization ability of the model. In step S300, a disease state simulation model is constructed based on the patient physiological database; the disease state simulation model is trained using the training set, the real-time physiological parameters are input into the disease state simulation model for simulation; the simulation result is input into the disease state simulation physiological knowledge data model, the corresponding doctor is found according to the simulation result to answer, and the answering process is stored; through the disease state simulation model, the system can more accurately predict the disease state of the patient, improving the accuracy of diagnosis; the system can automatically find the corresponding doctor to answer according to the simulation result, providing intelligent medical services; storing the answering process helps to accumulate knowledge and optimize future service processes.

[0085] Embodiment 2:

[0086] As Figure 2 shown in FIG. 1, based on the embodiment 1, the process of collecting physiological data of the patient in step S100 provided by the embodiment of the present application comprises the following steps:

[0087] Step S101: creating a physiological knowledge data model based on a historical physiological knowledge database, identifying and connecting various health data sources related to the research; obtaining historical data from selected data sources; integrating different historical data into different physiological knowledge sub-data sets, and combining different physiological knowledge sub-data sets into a physiological knowledge data set;

[0088] Among them, various health data sources include primary care practices, laboratory data, and insurance data; selected data sources include physiological parameters such as heart rate, blood pressure, and blood glucose level;

[0089] Step S102: the user inputs personal attributes through the terminal for registration, and gives different permissions according to the personal attributes; the user inputs related health data through the terminal, collects physiological data of the patient, and transmits the collected physiological data of the patient to the physiological knowledge data model;

[0090] Step S103: performing preprocessing operations such as cleaning, conversion and formatting, processing missing values and abnormal values on the physiological data of the patient; inputting the preprocessed physiological data of the patient into the physiological knowledge data model for screening.

[0091] In the above embodiments, step S101 in this embodiment constructs a data model based on a historical physiological knowledge database, capable of identifying and connecting various health data sources. These sources include primary healthcare practices, laboratory data, and insurance data. Physiological parameters such as heart rate, blood pressure, and blood glucose levels are selected as data sources. Historical data is obtained from the selected data sources. Different historical data are integrated into different physiological knowledge subsets, and these subsets are then merged into a complete physiological knowledge dataset. This embodiment improves data integrity and usability by integrating data from different sources to form a comprehensive physiological knowledge dataset. It ensures that data from different sources have the same format and structure, facilitating subsequent data processing and analysis. The constructed data model effectively identifies and connects various health data sources, providing a solid foundation for subsequent data analysis. Through integration and standardization, data quality is improved, and the possibility of data inconsistency and errors is reduced. In step S103, the user registers by inputting personal attributes through the terminal, and different permissions are granted according to these attributes. The user inputs relevant health data through the terminal to collect patient physiological data. The collected patient physiological data is then transmitted to the physiological knowledge data model. This embodiment ensures data security and privacy through user registration and permission management; it enables real-time collection of patient physiological data, improving data timeliness and accuracy; and it ensures that data can be transmitted to the data model in a timely manner, providing support for subsequent data processing and analysis. In step S103, the patient physiological data is cleaned, removing duplicate data, filling in missing data, and correcting erroneous data. The data is transformed, including data normalization and data segmentation. The data is formatted to ensure consistency and readability. Missing values ​​and outliers are processed to improve data quality. The preprocessed patient physiological data is then input into the physiological knowledge data model for filtering. This embodiment improves data quality and reduces the impact of noise and errors through data cleaning and preprocessing; it ensures data consistency and readability through data transformation and formatting, facilitating subsequent data analysis; it improves data reliability and accuracy by handling missing and outlier values; and it ensures that only high-quality data is input into the data model through screening, thereby improving the model's performance and accuracy.

[0092] Example 3:

[0093] like Figure 3 As shown, based on Example 1, the process of calibrating the physiological knowledge data model according to weight values ​​in step S200 of this embodiment of the invention includes the following steps:

[0094] Step S201: comparing and analyzing the related health data and the user history related data to obtain a patient health condition; assigning a weight value based on the patient health condition, and calling a data calling strategy and a target calling database of a physiological knowledge data model according to the weight value;

[0095] Step S202: determining a database strategy of the target calling database; calling target calling data in the target calling database based on the data calling strategy and the database strategy; and outputting the target calling data to a user terminal;

[0096] Step S203: if the calling fails, determining calibration failure; integrating the related health data, the history related data and the comparison and analysis result to form a personal data set; and dividing the personal data set into a training set, a verification set and a test set.

[0097] In the above embodiments, step S201 in this embodiment identifies the patient's health trends and potential problems by comparing and analyzing current health data with historical data. This step utilizes data mining and machine learning techniques, such as feature selection and feature extraction, to identify key features related to the patient's health status. Based on the analysis results, weight values ​​are assigned to each feature or data point, which typically involves feature importance assessment and parameter adjustment during model training. Based on the weight values, appropriate physiological knowledge data models and target databases are selected to ensure that the retrieved data can effectively support subsequent health analysis and decision-making. This embodiment, through comparative analysis and weight assignment, can more accurately identify the patient's health status and reduce the risk of misdiagnosis and missed diagnosis. Selecting appropriate data models and databases based on weight values ​​can improve the efficiency and accuracy of data retrieval and avoid unnecessary resource waste. In step S202, a suitable database access strategy is formulated based on the data retrieval strategy to ensure data integrity and consistency; data retrieval operations are performed in the target database, which typically involves technologies such as SQL queries and data interface calls; the retrieved data is output to the user terminal, which may involve technologies such as data format conversion and data visualization; this embodiment, by optimizing the database strategy and retrieval process, can quickly respond to the user's data needs and improve the user experience; it ensures that the data retrieved from the database is consistent with the data displayed on the user terminal, avoiding information loss or errors. If data retrieval fails in step S203, calibration is deemed a failure, and corresponding error handling measures are taken. Relevant health data is integrated with historical data to form a complete personal dataset. The preprocessed dataset is divided into training, validation, and test sets to facilitate subsequent model training and evaluation. This embodiment improves data quality and reliability through data cleaning and preprocessing, providing a solid foundation for subsequent modeling and analysis. Reasonable dataset division effectively evaluates model performance and prevents overfitting. Integrating and preprocessing personal health data better supports the development and implementation of personalized health management plans.

[0098] Example 4:

[0099] like Figure 4 As shown, based on Example 3, the process of determining the patient's health status in step S201 of this embodiment of the invention includes the following steps:

[0100] Step S2011: Retrieve the user's historical status data and calculate the difference with the relevant health data to obtain the status change value. If the status change value is positive, it is judged as a recovery state; if the status change value is negative, it is judged as a deterioration state; if the status change value is zero, it is judged as a stable state.

[0101] Step S2012: summing the state change value and the personal attribute value to calculate the health status of the patient; analyzing the health status of the patient to obtain the risk value of the patient; and assigning a weight value to the relevant health data according to the risk value of the patient;

[0102] Step S2013: based on the weight value, the data retrieval strategy and the target retrieval strategy of the physiological knowledge model are retrieved; the data retrieval strategy is determined to be a paging retrieval strategy or a non-paging retrieval strategy, and the corresponding target application is determined.

[0103] In the above embodiment, in step S2011 of the present embodiment, the historical state data of the user is retrieved, and the state change value is obtained by difference calculation with the current health data. This method is similar to the feature extraction technology commonly used in medical data analysis, such as extracting health index features from historical data. According to the positive, negative and zero of the state change value, the health status of the user is judged, which is similar to the classification method in health status evaluation. The health status change of the user is monitored in real time, and the recovery, deterioration or stable state is found in time. In the present embodiment, through the judgment of the state change value, the user can be provided with early warning information to help the user take timely measures. In step S2012, the state change value and the personal attribute value are summed to obtain the health status of the patient. This method is similar to the comprehensive scoring method in health evaluation. The health status of the patient is analyzed to obtain the risk value of the patient, which is similar to the risk score in the health risk evaluation model. According to the risk value of the patient, a weight value is assigned to the relevant health data, which is similar to the feature weighting in data mining. In the present embodiment, the combination of the personal attribute value and the state change value provides personalized health evaluation, which is similar to the health management based on individual differences. Through the calculation of the risk value, personalized health advice and early warning can be provided for the patient to help the user better manage health. In step S2013, the data retrieval strategy and the target retrieval strategy of the physiological knowledge model are retrieved based on the weight value. The data retrieval strategy is determined to be a paging retrieval strategy or a non-paging retrieval strategy. In the present embodiment, the data retrieval strategy driven by the weight value can more efficiently manage a large amount of health data, reduce the burden on the server, and improve the data query efficiency. According to different data retrieval strategies, different target applications are supported to improve the flexibility and applicability of the system.

[0104] Embodiment 5

[0105] As shown in Figure 5 the process of retrieving target retrieval data in the target retrieval database in step S202 provided by the present embodiment on the basis of embodiment 3, comprising the following steps:

[0106] Step S2021: if it is determined that the data retrieval strategy is a paging retrieval strategy, it is determined whether there is a location statement in the first call statement; if it is determined that the first call statement has a limit condition statement, it is determined whether the number of data return rows in the limit condition statement is greater than a preset threshold value;

[0107] Step S2022: If the value is greater than the preset threshold, the target application is determined based on the application information, and the target application's data is retrieved from the target retrieval database according to the target application and the database strategy; if the data retrieval strategy is determined to be a non-pagination retrieval strategy, the target application's retrieval data is retrieved from the target retrieval database according to the target application's data query volume.

[0108] Step S2023: If it is determined that the first call statement does not have a restrictive condition language, a preset restrictive statement is added to the first call statement to obtain the updated second call statement; the target database of the target application is retrieved from the target call database, and the retrieved data is input to the user terminal.

[0109] In the above embodiments, step S2021 determines whether the data retrieval strategy is a pagination retrieval strategy. It checks whether an address selection statement exists in the first call statement. If a limiting condition statement exists, it further checks whether the number of returned data rows exceeds a preset threshold. This embodiment effectively controls the scale of data queries by checking the number of returned data rows in the limiting condition statement, avoiding performance issues caused by returning too much data. Pagination strategies can significantly improve performance when handling large amounts of data, especially when the data volume is large, the pagination method of the database service layer performs even better. Step S2022 determines the target application based on the application information. If it is a pagination retrieval strategy and the number of returned rows exceeds the threshold, the data of the target application is retrieved from the target retrieval database. If it is a non-pagination retrieval strategy, data is retrieved according to the data query volume of the target application. This embodiment optimizes the data query process according to actual needs by dynamically adjusting the data retrieval strategy, improving the system's response speed and resource utilization. Pagination strategies can effectively reduce the amount of data in a single query, thereby reducing the server load and improving query efficiency. In step S2023, if the first call statement does not have a limiting condition statement, a preset limiting condition statement is added to it; the updated second call statement is used to retrieve data from the target call database and input the result to the user terminal; adding a limiting condition statement can better control the amount of data returned, avoid unnecessary data transmission, and thus improve system performance.

[0110] Example 6:

[0111] like Figure 6 As shown, based on Example 3, the process of forming a personal dataset in step S203 of this embodiment of the invention includes the following steps:

[0112] Step S2031: Determine whether the preset application white list in the target database can match the target application; if the preset application white list can match the target application, determine the maximum return row number of the preset application white list; and according to the maximum return row number, call the target application data in the target database.

[0113] Step S2032: If the calling fails, determine that the calibration fails; integrate the relevant health data, historical relevant data and comparative analysis results to form a personal data set.

[0114] Step S2033: Perform preprocessing operations such as removing outliers, balancing data distribution, categorical variable conversion, and numerical variable standardization on the personal data set; and divide the personal data set into a training set, a validation set, and a test set.

[0115] In the above embodiment, in step S2031, the preset application white list in the target database is called to check whether the target application can be matched; if the target application can be matched, the maximum return row number of the preset application white list is determined; and according to the maximum return row number, the target application data in the target database is called; in this embodiment, through the matching of the preset application white list, only the application data that meets the conditions is called, and the interference of irrelevant data is reduced; by determining the maximum return row number, the range and efficiency of data calling can be effectively controlled, and unnecessary data processing is avoided. In step S2032, if the target application data fails, it is determined that the calibration fails; the relevant health data, historical relevant data and comparative analysis results are integrated to form a personal data set; in this embodiment, through the determination of the calling failure, the problems in the data acquisition process are identified and processed in time, and the interruption of the process is avoided; multiple source data are integrated to construct a more comprehensive personal data set, providing more abundant information for data analysis and model training. In step S2033, the personal data set is preprocessed by removing outliers, balancing data distribution, converting categorical variables, and standardizing numerical variables; and the personal data set is divided into a training set, a validation set, and a test set; in this embodiment, by removing outliers and balancing data distribution, the quality and consistency of the data are improved, the noise influence in model training is reduced, the model training optimization is performed through categorical variable conversion and numerical variable standardization, the consistency of the data format is ensured, and the efficiency and accuracy of the model training are improved; by dividing the training set, the validation set and the test set, the performance and generalization ability of the model can be effectively evaluated, and the problems of overfitting or underfitting are avoided.

[0116] Embodiment 7:

[0117] As Figure 7As shown, on the basis of Embodiment 1, the process of inputting the simulation result into the physiological knowledge data model of the disease state simulation in step S300 provided by the present embodiment comprises the following steps:

[0118] Step S301: based on the personal data set, the historical disease data in the patient physiological database is retrieved; the training set in the personal data set is used to train the disease state model; during the training process, the personal data set and the historical disease data of the user are analyzed to obtain the disease data trend;

[0119] Step S302: learning the disease data, using recursion to select variables; based on the training result of the disease state model each time, the variables less than the preset value are gradually eliminated, and according to the simulation result of the final training disease state model, the variable with the largest contribution to the disease state simulation result is extracted;

[0120] Step S303: inputting the real-time physiological parameters into the disease state simulation model for simulation; inputting the simulation result into the physiological knowledge data model; the physiological knowledge data model outputs the simulation result to the user terminal; and according to the simulation result, the corresponding doctor is found to answer, and the answer result is stored.

[0121] In the above embodiments, step S301 retrieves historical disease data from the patient's physiological database and performs preprocessing, including data cleaning, missing value handling, and standardization. The disease state model is trained using the training set in the personal dataset, which typically involves selecting appropriate features, feature extraction, and feature engineering. Trend analysis derives the trend of disease data by analyzing the personal dataset and the user's historical disease data. In this embodiment, by using historical data for training, the model can better capture the patient's health trends. Medical decision support provides personalized health advice and early warning information to patients by analyzing their personal data. Step S302 uses a recursive method to screen variables, gradually eliminating unimportant variables. Based on each training result, the model is progressively optimized to ensure its predictive performance. Finally, the variables that contribute most to the disease state simulation results are extracted, which may involve feature importance ranking and influence factor analysis. This embodiment reduces redundant variables in the model through recursive screening, improving the model's operating efficiency and interpretability; and enhances the model's predictive ability and accuracy by extracting key variables. In step S303, real-time physiological parameters are input into the disease state simulation model for simulation, which may involve real-time monitoring and data acquisition of multiple physiological parameters; the simulation results are input into the physiological knowledge data model and output through the user terminal; the corresponding physician is searched for answers based on the simulation results and the answers are stored; in this embodiment, through real-time data input and simulation, the system can monitor the patient's health status in a timely manner and provide early warning information; and through the expert answer and storage mechanism, the system can help medical institutions optimize resource allocation and improve the level of medical services.

[0122] Example 8:

[0123] like Figure 8 As shown, based on Example 7, the process of extracting the variable that contributes the most to the simulation result of the disease state in step S302 of this embodiment of the invention includes the following steps:

[0124] Step S3021: Collect the node set of the training set of the personal dataset and the user's historical disease data, analyze the output data and characteristics of each node in the node set, and analyze the dependency relationship between nodes based on the feature analysis results of the node input data and output data.

[0125] Step S3022: Construct a dependency matrix between nodes based on the dependency relationship, calculate the similarity value between the output data of historical disease nodes and the output data of real-time health data nodes, and determine the dependency relationship between the output data of historical disease nodes and the data of real-time health data nodes based on the similarity threshold.

[0126] The formula for calculating the similarity value between the output data of historical disease nodes and the output data of real-time health data nodes is as follows: Let S(h,r) be the similarity value between the output data vector h of historical disease nodes and the output data vector r of real-time health data nodes.

[0127]

[0128] In the formula, h represents the output data vector of historical disease nodes, h = [h1, h2, ..., h n ]; r represents the output data vector of the real-time health data node, r = [r1, r2, ..., r n ]; n represents the dimension of the data vector; w i This represents the weight of the i-th data dimension, used to adjust the influence of different dimensions on the similarity value; TF(h i ,r i () represents the word frequency of the i-th dimension, indicating the importance of that dimension in the data;

[0129]

[0130] In the formula, IDF(h) i ,r i ) represents the inverse document frequency of the i-th dimension, indicating the rarity of that dimension in the global data;

[0131]

[0132] In the formula, N is the total number of data sets, and II(h) i =r j ) is an indicator function, when h i =r j The value is 1 if it is true, and 0 otherwise.

[0133] DTW(h i ,r i ) represents the dynamic time warping similarity of the time series in the i-th dimension, used to measure the similarity of time series data;

[0134]

[0135] In the formula, τ is the time warping function, and T is the length of the time series;

[0136] Cov(h i ,r i ) represents the covariance of the i-th dimension, which is used to measure the linear relationship between two data sequences;

[0137]

[0138] In the formula, μ h and μ r They are h i and r i The formula comprehensively considers the word frequency, inverse document frequency, dynamic time warping of the time series, and covariance of the data, and calculates the final similarity value through weighted summation; the weights can be adjusted according to specific application scenarios to adapt to different data characteristics and needs; it can effectively calculate the similarity value between historical disease nodes and real-time health data nodes;

[0139] Step S3023: Identify optimizable node configuration information, as well as potential parallel execution sets and sequential execution sets between nodes, based on the dependencies; reorder and optimize the execution order of the dependency configuration based on the identified parallel execution sets and sequential execution sets.

[0140] In the above embodiments, step S3021 extracts the training set and the user's historical disease data from the personal dataset to form a node set; the output data and features of each node are analyzed in detail to identify the dependencies between nodes; this embodiment determines the dependencies between nodes through feature analysis of input and output data; the identification of dependencies helps to better understand the correlation between data, thereby improving the depth and breadth of data analysis. Step S3022 constructs a dependency matrix based on the dependencies between nodes, and calculates the similarity value of the output data between historical disease nodes and real-time health data nodes; this embodiment can monitor the user's health status in real time and promptly detect potential health problems by calculating similarity; based on the similarity results, health management strategies are dynamically adjusted to improve the pertinence and effectiveness of health management. Step S3033 identifies and optimizes node configuration information to improve the overall performance of the system. It identifies the set of nodes that can be executed in parallel and the set of nodes that need to be executed sequentially. Based on the sets of parallel and sequential execution, it reorders and optimizes the execution order of the dependency configuration. This embodiment can significantly improve the system's operating efficiency and response speed by optimizing node configuration and execution order. The identification of the parallel execution set enables the system to better handle the needs of multi-task parallel processing, enhancing the system's flexibility and scalability.

[0141] Example 9:

[0142] like Figure 9 As shown, based on Example 7, the process of outputting the simulation results to the user terminal in step S303 of this embodiment of the invention includes the following steps:

[0143] Step S3031: based on each training result of the disease state simulation model, gradually eliminate variables less than a threshold, extract the variable value that contributes most to the simulation result according to the final training disease state simulation result, and obtain the final disease state simulation model;

[0144] Step S3032: input the real-time physiological parameters into the disease state simulation model, simulate the real-time physiological parameters, and obtain the user's health data change; compare the user's health data change with the preset health data change;

[0145] Step S3033: evaluate the comparison result, input the evaluation result into the physiological knowledge data model, output the evaluation result to the user terminal, and find the corresponding doctor according to the evaluation result to answer, and store the answering process.

[0146] In the above embodiments, step S3031 of the present embodiment gradually eliminates variables less than a threshold to ensure that only variables that significantly contribute to the simulation result are retained in the model; key features are extracted from the training data, which are essential to the prediction ability of the model; by retaining the variables that contribute most to the simulation result, the model can more accurately reflect the real disease state, thereby improving the prediction accuracy; eliminating irrelevant or less influential variables can reduce the risk of model overfitting, making the model more generalizable to new data. Step S3032 simulates using the latest physiological parameter data to ensure that the health data change output by the model is based on the latest user state; compare the simulation result with the preset health data change to evaluate whether the user's health condition is within the normal range; by real-time simulation and comparative analysis, the system can timely detect the user's health abnormalities and provide early warning and intervention suggestions for the user; according to the user's real-time health data change, the system can provide personalized health management solutions to help users better maintain their health. Step S3033 evaluates the comparison result in detail and feeds back the evaluation result to the physiological knowledge data model for model optimization; the evaluation result is output to the user terminal and the corresponding doctor is found according to the evaluation result to answer, so that the user can obtain professional medical advice in time; by timely feedback and professional answers, users can obtain more comprehensive and accurate health management information, improving user satisfaction and trust in the system; finding the corresponding doctor according to the evaluation result to answer helps to optimize the allocation of medical resources to ensure that users can obtain timely and effective medical services.

[0147] Embodiment 10:

[0148] As shown in Figure 10 Based on embodiments 1-9, the smart medical interaction system based on big data provided by the present embodiment comprises:

[0149] The health data collection module 1 is used to create a physiological knowledge data model based on a historical physiological knowledge database, a user registers by inputting personal attributes through a terminal, and different permissions are given according to the personal attributes; the user inputs relevant health data through the terminal, collects physiological data of the patient, and transmits the collected physiological data of the patient to the physiological knowledge data model;

[0150] Different permissions include patient permissions, doctor permissions, and management permissions, etc.

[0151] The health data retrieval module 2 is used to analyze the relevant health data, and to assign a weight value to the real-time physiological parameters according to the analysis results; the physiological knowledge data model is calibrated according to the weight value, and if the calibration is successful, it is directly retrieved; if the calibration fails, a personal data set is formed; the personal data set is divided into a training set, a validation set, and a test set;

[0152] The physiological data includes heart rate, blood pressure, blood sugar level, and drug intake, etc.

[0153] The interactive health data module 3 is used to construct a disease state simulation model based on the patient physiological database, and to train the disease state simulation model using the training set; the real-time physiological parameters are input into the disease state simulation model for simulation; the simulation results are input into the disease state simulation physiological knowledge data model, a corresponding doctor is found according to the simulation results for answering, and the answering process is stored.

[0154] In the above embodiments, the present embodiment collects health data module users to register by inputting personal attributes through terminals, assigns different permissions according to personal attributes, including patient permissions, doctor permissions, and management permissions, etc. This design ensures the security and privacy of data, while meeting the needs of different roles; users input relevant health data through terminals, such as heart rate, blood pressure, blood sugar level, and drug intake, etc. The data is collected and transmitted to the physiological knowledge data model in real time; according to the user's personal attributes and health data, the system can provide personalized health management suggestions and warning information, thereby improving the user's health management efficiency. The health data module analyzes the relevant health data and assigns weight values to the real-time physiological parameters according to the analysis results. The physiological knowledge data model is calibrated according to the weight values, and if the calibration is successful, it is directly called; if the calibration fails, a personal data set is formed; the personal data set is divided into a training set, a validation set, and a test set, which are used for training and verifying the disease state simulation model; through weight assignment and model calibration, the system can more accurately assess the user's health status and provide personalized health advice and warning information; through data set division and training, the disease state simulation model is continuously optimized, improving the accuracy and reliability of the model; the interactive health data module constructs a disease state simulation model based on the patient physiological database and trains it using the training set; input the real-time physiological parameters into the disease state simulation model for simulation; find the corresponding doctor according to the simulation results and store the answer process; through the disease state simulation, the system can provide more intelligent health management services for users, helping them better understand their health status; storing the answer process makes it easy for users to check and trace at any time, enhancing the transparency and traceability of the system.

[0155] Figure 11 A block diagram of an exemplary electronic device suitable for implementing an embodiment of the present application is shown.

[0156] The electronic device can include a central processor / microprocessor / master control chip, etc. 4; a storage medium 5 coupled to the central processor / microprocessor / master control chip, etc. 4, and storing computer executable instructions therein for performing the steps of various methods of embodiments of the present application when executed by the processor.

[0157] The central processor / microprocessor / master control chip, etc. 4 can include but is not limited to, for example, one or more processors or microprocessors, etc.

[0158] The storage medium 5 can include, but is not limited to, for example, a random access memory (RAM), a read only memory (ROM), a flash memory, an EPROM memory, an EEPROM memory, a register, a computer storage medium (such as a hard disk, a floppy disk, a solid state disk, a removable disk, a CD-ROM, a DVD-ROM, a Blu-ray disk, and the like).

[0159] In addition, the electronic device can further include, but is not limited to, a data bus 6, an input / output bus / external bus / device bus, and the like 7, a display 8, and an input / output device 9 (such as a keyboard, a mouse, a speaker, and the like), and the like.

[0160] The central processing unit / microprocessor / master control chip, and the like 4 can communicate with external devices (8, 9, and the like) via a wired or wireless network (not shown) through the I / O bus 7.

[0161] The storage medium 5 can further store at least one computer executable instruction for performing the steps of the various functions and / or methods in the embodiments described in the present technology when executed by the central processing unit / microprocessor / master control chip, and the like 4.

[0162] In one embodiment, the at least one computer executable instruction can also be compiled or constitute a software product in which one or more computer executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described in the present technology.

[0163] Figure 12 A schematic diagram of a computer readable storage medium according to an embodiment of the present application is shown.

[0164] As Figure 12 shown, a non-transitory computer readable storage medium 11 stores instructions, for example, computer readable instructions 10. When the computer readable instructions 10 are executed by a processor, the various methods described above can be performed. The non-transitory computer readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory can include, for example, a random access memory (RAM) and / or a cache memory, and the like. The non-transitory non-volatile memory can include, for example, a read only memory (ROM), a hard disk, a flash memory, and the like. For example, the non-transitory computer readable storage medium 11 can be connected to a computing device such as a computer, and then, when the computing device executes the computer readable instructions 10 stored on the non-transitory computer readable storage medium 11, the various methods described above can be performed.

[0165] In several embodiments provided by the present application, it should be understood that the disclosed apparatus and method can be implemented in other manners. For example, the division of the units is merely a logical function division, and there can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, can be indirect couplings or communication connections through some interfaces, and can be in electrical, mechanical or other forms.

[0166] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0167] In addition, the functional units in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0168] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for executing all or part of the steps of the embodiments of the present application by a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (English full name: Read-Only Memory, English abbreviation: ROM), a random access memory (English full name: Random Access Memory, English abbreviation: RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0169] The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A big data-based smart medical interaction method, characterized in that, Comprising the following steps: A physiological knowledge data model is created based on a historical physiological knowledge database, a user registers by inputting personal attributes through a terminal, and different permissions are assigned according to personal attributes; the user inputs relevant health data through the terminal, collects physiological data of the patient, and transmits the collected physiological data of the patient to the physiological knowledge data model, and assigns a weight value to the real-time physiological parameter; The physiological knowledge data model is calibrated according to the weight value, and if the calibration is successful, it is directly called; If the calibration fails, a personal data set is formed; The personal data set is divided into a training set, a validation set, and a test set; A disease state simulation model is constructed based on the patient physiological database, and the disease state simulation model is trained using the training set; The real-time physiological parameter is input into the disease state simulation model for simulation; the simulation result is input into the physiological knowledge data model; The physiological knowledge data model outputs the simulation result to the user terminal; And according to the simulation result, find the corresponding doctor for answer, and store the answer result; The simulation result is input into the disease state simulation physiological knowledge data model, the corresponding doctor is found according to the simulation result, the answer process is stored, and the answer process is stored; The process of inputting real-time physiological parameters into the disease state simulation model for simulation includes: Based on the personal data set, historical disease data in the patient physiological database is retrieved; the training set in the personal data set is used to train the disease state model; during the training process, the personal data set and the user's historical disease data are analyzed to obtain the disease data trend; Learn from the disease data trend, use recursion to select variables; based on the training result of the disease state model each time, gradually eliminate variables less than a preset value, extract the variable that contributes most to the disease state simulation result according to the final training disease state model simulation result; collect the node set of the training set in the personal data set and the user's historical disease data, analyze the output data and the characteristics of the output data of each node in the node set, and analyze the dependence relationship between the nodes according to the analysis result of the node input data and the output data characteristics; form a dependence matrix between nodes according to the dependence relationship, calculate the similarity value between the output data of the historical disease node and the output data of the real-time health data node, and judge the dependence relationship between the output data of the historical disease node and the output data of the real-time health data node according to the threshold value between the similarity; According to the dependence relationship, identify the optimal node configuration information, as well as the potential parallel execution set and the sequential execution set between nodes; according to the identified parallel execution set and sequential execution set, reorder the execution order of the optimized analysis dependence relationship configuration; Wherein, the formula for calculating the similarity value between the output data of the historical disease node and the output data of the real-time health data node; The formula considers the word frequency, inverse document frequency, dynamic time warping of time series, and covariance of the data, and calculates the final similarity value by weighted summation; The weight is adjusted according to the specific application scenario to adapt to different data characteristics and needs; it can calculate the similarity value between the historical disease node and the real-time health data node. 2.The big data based smart medical interaction method of claim 1, wherein, The process of collecting patient physiological data includes the following steps: The physiological knowledge data model is created based on a historical physiological knowledge database, various health data sources related to the research are identified and connected, historical data is obtained from selected data sources, different historical data is integrated into different physiological knowledge sub-data sets, and the different physiological knowledge sub-data sets are combined into a physiological knowledge data set; The user inputs personal attributes through a terminal to register, and different permissions are given according to the personal attributes; the user inputs relevant health data through the terminal, collects physiological data of the patient, and transmits the collected physiological data of the patient to the physiological knowledge data model; The patient physiological data is preprocessed by cleaning, converting and formatting, processing missing values and abnormal values; The preprocessed patient physiological data is input into the physiological knowledge data model for screening. 3.The big data based smart medical interaction method of claim 1, wherein, The calibration process of the physiological knowledge data model according to the weight value includes the following steps: The relevant health data and the user historical data are compared and analyzed to obtain the patient health condition; the weight value is assigned based on the patient health condition, and the data retrieval strategy and the target retrieval database of the physiological knowledge data model are retrieved according to the weight value; The database strategy of the target retrieval database is determined; the target retrieval data is retrieved in the target retrieval database based on the data retrieval strategy and the database strategy; The target retrieval data is output to the user terminal; If the retrieval fails, it is determined that the calibration fails; the relevant health data and the historical data and the comparison and analysis results are integrated to form a personal data set. 4.The big data based smart medical interaction method of claim 3, wherein, The process of obtaining the patient health condition includes the following steps: The state change value is obtained by retrieving the user historical state data and performing difference calculation on the relevant health data; if the state change value is positive, it is judged as a recovery state; if the state change value is negative, it is judged as a deterioration state, and if the state change value is zero, it is judged as a stable state; The patient health condition is obtained by summing the state change value and the personal attribute value; the patient risk value is obtained by analyzing the patient health state; The weight value is assigned to the relevant health data according to the patient risk value; The data retrieval strategy and the target retrieval strategy of the physiological knowledge model are retrieved based on the weight value; The data retrieval strategy is determined to be a paging retrieval strategy or a non-paging retrieval strategy, and the corresponding target application is determined. 5.The big data based smart medical interaction method of claim 3, wherein, The process of retrieving the target retrieval data in the target retrieval database includes the following steps: If it is determined that the data retrieval strategy is a paging retrieval strategy, it is determined whether there is a location statement in the first call statement; if the first call statement has a limit condition statement, it is determined whether the number of data return rows in the limit condition statement is greater than a preset threshold; If it is greater than the preset threshold, the target application is determined according to the application information, and the target retrieval data of the target application is retrieved in the target retrieval database according to the target application and the database strategy; If it is determined that the data retrieval strategy is a non-paging retrieval strategy, the retrieval data of the target application is retrieved in the target retrieval database according to the data query amount of the target application; If the first call statement does not have a limit condition language, a preset limit statement is added to the first retrieval statement to obtain an updated second call statement; The target database of the target application is retrieved in the target call database, and the retrieved data is input to the user terminal. 6.The big data based smart medical interaction method of claim 3, wherein, The process of forming a personal data set comprises the following steps: Determine whether the preset application whitelist in the target database can match the target application; determine the maximum number of returned rows in the preset application whitelist if the target application can be matched in the preset application whitelist; According to the maximum number of returned rows, the target application data in the target database is retrieved; If the retrieval fails, it is determined that the calibration fails; Integrate the relevant health data with the historical relevant data and the comparative analysis results to form a personal data set; The personal data set is processed to remove outliers, balance data distribution, convert categorical variables, and standardize numerical variables; the personal data set is divided into a training set, a validation set, and a test set. 7.The big data based smart medical interaction method of claim 1, wherein, The process of outputting the simulation results to the user terminal comprises the following steps: Based on the training results of the disease state simulation model each time, variables less than the threshold value are gradually eliminated, and the variable value that contributes most to the simulation results is extracted according to the final training disease state simulation results; Obtain the final disease state simulation model; Input real-time physiological parameters into the disease state simulation model to simulate the real-time physiological parameters and obtain the user's health data changes; Compare the user's health data changes with the preset health data changes; Evaluate the comparison results and input the evaluation results into the physiological knowledge data model; Output the evaluation results to the user terminal and find the corresponding doctor for answer according to the evaluation results, and store the answer process.

8. A big data-based smart medical interaction system applying the big data-based smart medical interaction method of any one of claims 1 to 7. Comprise: The health data collection module is used to create a physiological knowledge data model based on a historical physiological knowledge database; the user inputs personal attributes through the terminal to register and is given different permissions according to the personal attributes; The user inputs relevant health data through the terminal, collects patient physiological data, and transmits the collected patient physiological data to the physiological knowledge data model; The health data retrieval module is used to analyze the relevant health data and assign weight values to real-time physiological parameters according to the analysis results; The physiological knowledge data model is calibrated according to the weight values, and if the calibration is successful, it is directly retrieved; If the calibration fails, a personal data set is formed; The personal data set is divided into a training set, a validation set, and a test set; The interactive health data module is used to construct a disease state simulation model based on a patient physiological database and train the disease state simulation model using the training set; Input real-time physiological parameters into the disease state simulation model for simulation; input the simulation results into the disease state simulation physiological knowledge data model, and retrieve the historical disease data of the patient physiological database based on the personal data set; Train the disease state model using the training set in the personal data set; During the training process, the personal data set and the user's historical disease data are analyzed to obtain the disease data trend; Learn the disease data trend and use recursion to select variables; According to the training result of the disease state model each time, the variables less than the preset value are gradually eliminated, and according to the simulation result of the final training disease state model, the variables with the greatest contribution to the simulation result of the disease state are extracted; the node set of the training set in the personal data set and the historical disease data of the user is collected, the output data and the characteristics of the output data of each node in the node set are analyzed, the dependence relationship between the nodes is analyzed according to the analysis result of the input data and the output data of the nodes; the dependence matrix between the nodes is constructed according to the dependence relationship, the similarity value between the output data of the historical disease node and the output data of the real-time health data node is calculated, and the dependence relationship between the output data of the historical disease node and the output data of the real-time health data node is judged according to the threshold value between the similarity values; According to the dependence relationship, the node configuration information that can be optimized, and the potential parallel execution set and the sequential execution set between the nodes are identified; according to the identified parallel execution set and sequential execution set, the execution order of the optimized analysis dependence relationship configuration is reordered; The real-time physiological parameters are input into the disease state simulation model for simulation; the simulation result is input into the physiological knowledge data model; The physiological knowledge data model outputs the simulation result to the user terminal; And according to the simulation result, the corresponding doctor is found to answer, and the answer result is stored; The formula for calculating the similarity value between the output data of the historical disease node and the output data of the real-time health data node; The formula comprehensively considers the word frequency, inverse document frequency, dynamic time warping of time series and covariance of the data, and calculates the final similarity value by weighted summation. The weight is adjusted according to the specific application scene to adapt to different data characteristics and needs; the similarity value between the historical disease node and the real-time health data node can be calculated.

Images