Health management system and method based on data analysis

Abstract

The present invention relates to a health management system based on data analysis, which belongs to the field of health management. The system includes: a concentration prediction device, which is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment; a reporting execution device, which is used to execute abnormal blood lipid reporting processing when health deviation data appears in the reference blood lipid concentration. The present invention also relates to a health management method based on data analysis. Through the present invention, in view of the technical problem that blood lipid measurements in the future are difficult to predict and still require cumbersome and complicated blood drawing and blood testing processes, a customized AI prediction model can be designed for each hyperlipidemia patient to provide a non-measurement prediction mechanism for blood lipid data in the future, thereby solving the above technical problems.

Description

Technical Field

[0001] The present invention relates to the field of health management, and in particular to a health management system and method based on data analysis. Background Art

[0002] The core content of health management is that medical insurance institutions and medical service institutions carry out systematic health management on their medical insurance customers (including patients or high-risk groups) or medical service customers to effectively control the occurrence or development of diseases, significantly reduce the probability of accidents and actual medical expenses, and thus reduce the purpose of medical insurance compensation losses. With the continuous enrichment and development of actual business content, health management has gradually developed into a set of specialized system solutions and operating businesses, and professional health management institutions that are different from traditional medical institutions such as hospitals have begun to emerge. They collaborate with medical insurance institutions or directly meet individual needs to provide systematic and professional health management services. Health management in a relatively narrow sense refers to establishing exclusive health files based on health examination results, providing health status assessments, and proposing personalized health management plans in a targeted manner.

[0003] For example, a method for constructing a dyslipidemia assessment model, a dietary therapy and a health management system proposed in the Chinese invention patent publication CN117116481A includes: S1: preparing a data set; S2: dividing a feature set; S3: feature screening: filtering the training set using a filtering feature selection method, calculating the correlation between each feature and the target variable using a univariate logistic regression method, and selecting features that meet the preset conditions as input features of the dyslipidemia assessment model; S4: model construction: fitting the training set using a multifactor logistic regression model and constructing a dyslipidemia assessment model; S5: model optimization; S6: model evaluation and verification; S7: model application. Based on the data of patients with dyslipidemia, the present invention fits the training set through a multifactor logistic regression model and constructs a dyslipidemia assessment model, so that the optimized and trained dyslipidemia assessment model can be used to predict the risk of cardiovascular events in patients with dyslipidemia in the future.

[0004] For example, Chinese invention patent publication CN115469087A proposes an intelligent blood lipid detection device for health management with data recording and analysis, the device comprising an upper shell and a lower shell, the upper shell is snap-connected to the upper end of the lower shell, a display screen is provided on the left side of the upper end of the upper shell, and an operation key is provided in the middle of the upper end of the upper shell, a slot is provided in the middle of the right side of the upper end of the upper shell, and a detection part is provided on the bottom wall of the slot; a protective mechanism is slidably connected to the interior of the slot, the protective mechanism comprises a slide plate slidably connected to the interior of the slot, and a sealing plate is fixedly connected to the right side of the slide plate, a storage groove is provided on the upper left wall of the slot, which can realize the closure of the detector slot to prevent dirt from entering the slot and affecting the detection, and at the same time, the protective mechanism for closing the slot will not affect the detection operation, and can also disinfect the slot after detection.

[0005] However, the above-mentioned existing technologies, whether they involve the prediction of the risk of cardiovascular events occurring again in patients with dyslipidemia in the future, or the specific structure of blood lipid detection equipment, are unable to reliably predict the blood lipid data of patients with dyslipidemia in future time periods. It is still necessary to obtain the high blood lipid data of the future time period through a tedious and complicated blood drawing and blood testing process when the future time period arrives. Unlike physiological parameters such as blood pressure, heart rate, body temperature and blood oxygen saturation, which can be measured in a portable manner, it can be seen that the existing technology is still unable to adopt a simple mode to directly obtain blood lipid data for future time periods, resulting in the inability to carry out targeted advance configuration of blood lipid health management strategies for patients with dyslipidemia in the future. Summary of the invention

[0006] In order to solve the technical problems in the prior art, the present invention provides a health management system and method based on data analysis, which can design an AI prediction model with a customized structure for each patient with hyperlipidemia, and provide a non-measurement prediction mechanism for the blood lipid reference information of patients with hyperlipidemia in future time segments, thereby obtaining effective predicted blood lipid data without having to perform tedious and complicated blood drawing and blood testing processes in future time segments, providing key information for the formulation of subsequent blood lipid health management strategies including initiating physical examinations, and improving the intelligence level of blood lipid health management.

[0007] According to a first aspect of the present invention, there is provided a health management system based on data analysis, the system comprising:

[0008] A time-sharing capture device is used to obtain health reference data corresponding to each time segment before the current time segment for the target hyperlipidemia patient, and the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment;

[0009] An information collection device, used to obtain various individual physiological information of a target hyperlipidemia patient, wherein the various individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information, and duration of hyperlipidemia of the target hyperlipidemia patient;

[0010] A sequential training device is used to construct an AI prediction model for performing numerical prediction of blood lipid concentration in future time segments for target hyperlipidemia patients, wherein the AI ​​prediction model is a deep neural network that completes sequential training and the number of trainings is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient;

[0011] A concentration prediction device, connected to the time-sharing capture device, the information collection device and the successive training device, respectively, for intelligently predicting the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment using the AI ​​prediction model based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient and various health reference data corresponding to each time segment before the current time segment;

[0012] A reporting execution device, connected to the concentration prediction device, for executing a reporting process of abnormal blood lipid concentration information when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value interval;

[0013] Wherein, when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value interval, the reporting process of abnormal blood lipid concentration information includes: the reporting execution device has a built-in wireless communication interface for wirelessly connecting to a remote health management server, so as to wirelessly transmit abnormal blood lipid concentration information to the health management server when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value interval;

[0014] Wherein, when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, the abnormal blood lipid concentration information reporting process further includes: the abnormal blood lipid concentration information includes the reference blood lipid concentration of the target hyperlipidemia patient, the location information of the target hyperlipidemia patient, the communication information of the target hyperlipidemia patient and various individual physiological information of the target hyperlipidemia patient;

[0015] Among them, based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment, including: the intelligently predicted reference blood lipid concentration of the target hyperlipidemia patient in the current time segment includes the total cholesterol concentration reference value, triglyceride concentration reference value, low-density lipoprotein cholesterol concentration reference value and high-density lipoprotein cholesterol concentration reference value of the target hyperlipidemia patient in the current time segment;

[0016] Among them, for the target hyperlipidemia patients, the health reference data corresponding to each time segment before the current time segment are obtained, including: the current time segment takes the current moment as the starting moment, the current moment segment and each time segment before the current time segment have the same duration and together constitute a complete time interval.

[0017] According to a second aspect of the present invention, a health management method based on data analysis is provided, the method comprising the following steps:

[0018] For the target hyperlipidemia patient, obtain the health reference data corresponding to each time segment before the current time segment, and the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment;

[0019] Acquire various individual physiological information of the target hyperlipidemia patient, wherein the various individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information and duration of hyperlipidemia of the target hyperlipidemia patient;

[0020] Construct an AI prediction model for predicting blood lipid concentration values ​​in future time segments for target hyperlipidemia patients, wherein the AI ​​prediction model is a deep neural network that completes successive training and the number of trainings is proportional to the duration of hyperlipidemia in the target hyperlipidemia patients;

[0021] Based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment;

[0022] When the reference blood lipid concentration of the target hyperlipidemia patient in the received current time segment is not within the set concentration value range, performing a reporting process of abnormal blood lipid concentration information;

[0023] Wherein, when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value interval, the reporting process of abnormal blood lipid concentration information includes: the reporting execution device has a built-in wireless communication interface for wirelessly connecting to a remote health management server, so as to wirelessly transmit abnormal blood lipid concentration information to the health management server when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value interval;

[0024] Wherein, when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, the abnormal blood lipid concentration information reporting process further includes: the abnormal blood lipid concentration information includes the reference blood lipid concentration of the target hyperlipidemia patient, the location information of the target hyperlipidemia patient, the communication information of the target hyperlipidemia patient and various individual physiological information of the target hyperlipidemia patient;

[0025] Among them, based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment, including: the intelligently predicted reference blood lipid concentration of the target hyperlipidemia patient in the current time segment includes the total cholesterol concentration reference value, triglyceride concentration reference value, low-density lipoprotein cholesterol concentration reference value and high-density lipoprotein cholesterol concentration reference value of the target hyperlipidemia patient in the current time segment;

[0026] Among them, for the target hyperlipidemia patients, the health reference data corresponding to each time segment before the current time segment are obtained, including: the current time segment takes the current moment as the starting moment, the current moment segment and each time segment before the current time segment have the same duration and together constitute a complete time interval.

[0027] It can be seen that the present invention has at least the following significant technical advances:

[0028] Technological progress A: The measurement of hyperlipidemia data requires a tedious and complicated blood drawing and blood test process. Unlike physiological parameters such as blood pressure, heart rate, body temperature and blood oxygen saturation, which can be measured in a portable manner, a customized AI prediction model is designed for each target hyperlipidemia patient to provide a prediction mechanism for the target hyperlipidemia patient's blood lipid reference information in the future time segment, reducing the tedious and complicated blood drawing and blood test process, and providing valuable reference data for the customization of subsequent response strategies including initiating physical examinations;

[0029] Technological progress B: The customized structure of the AI ​​prediction model for blood lipid prediction is reflected in the fact that the AI ​​prediction model is a deep neural network that completes successive training, and its various basic data are targeted for screening and customized design of its training mechanism. The targeted basic data include the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before the current time segment. The current time segment takes the current moment as the start moment, that is, the current time segment is used as the future time segment. At the same time, the number of trainings is proportional to the duration of hyperlipidemia of the target hyperlipidemia patient, so that different AI prediction models are designed for different hyperlipidemia patients, ensuring the effectiveness and stability of the prediction results.

[0030] Technical Progress C: A specific learning mechanism for single-time learning is customized for the AI ​​prediction model that performs blood lipid prediction. In each training of the deep neural network, the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before a certain past time segment are used as multiple input contents of the deep neural network. The total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration, and high-density lipoprotein cholesterol concentration measured for the target hyperlipidemia patient at the middle moment in the certain past time segment are listed as the reference blood lipid concentration of the certain past time segment as the output content of the deep neural network to complete this training, thereby ensuring the training effect of each training, wherein each training performed on the deep neural network corresponds to each past time segment;

[0031] Technological progress D: When the reference blood lipid concentration of the target hyperlipidemia patient is not within the set concentration value range within the current time segment of the intelligent prediction, the reporting processing of abnormal blood lipid concentration information is performed, and the abnormal blood lipid concentration information includes the reference blood lipid concentration of the target hyperlipidemia patient, the positioning information of the target hyperlipidemia patient, the communication information of the target hyperlipidemia patient and various individual physiological information of the target hyperlipidemia patient, thereby realizing non-measurement centralized management of the future blood lipid status of hyperlipidemia patients in various locations. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0033] Figure 1 It is a technical flow chart of the health management system and method based on data analysis according to the present invention.

[0034] Figure 2 The figure is a schematic diagram of the structure of a health management system based on data analysis according to the first embodiment of the present invention.

[0035] Figure 3It is a structural diagram of a health management system based on data analysis according to the second embodiment of the present invention.

[0036] Figure 4 It is a structural diagram of a health management system based on data analysis according to the third embodiment of the present invention.

[0037] Figure 5 It is a structural diagram of a health management system based on data analysis according to the fourth embodiment of the present invention.

[0038] Figure 6 It is a structural diagram of a health management system based on data analysis according to the fifth embodiment of the present invention.

[0039] Figure 7 The figure is a flowchart of the steps of a health management method based on data analysis according to the sixth embodiment of the present invention. DETAILED DESCRIPTION

[0040] like Figure 1 As shown, a technical flow chart of a health management system and method based on data analysis according to the present invention is given.

[0041] like Figure 1 As shown, the specific technical process of the present invention is as follows:

[0042] Step 1: In order to improve the reliability and effectiveness of the blood lipid reference information prediction of the target hyperlipidemia patients in the current time segment that has not yet arrived, multiple targeted basic data are screened;

[0043] Specifically, the multiple targeted basic data include the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment;

[0044] More specifically, the individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information and duration of hyperlipidemia of the target hyperlipidemia patient, and the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment;

[0045] Step 2: Use a customized AI prediction model to perform prediction of specific blood lipid reference information. The AI ​​prediction model is a deep neural network that completes successive training, and the number of training times is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient, thereby establishing AI prediction models with different specific structures for different hyperlipidemia patients;

[0046] Step 3: Introduce a targeted single learning mechanism for the AI ​​prediction model to ensure the effect of each learning, thereby ensuring the stability and reliability of the blood lipid prediction results of the AI ​​prediction model;

[0047] Specifically, in each training of the deep neural network, the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before a certain past time segment are used as multiple input contents of the deep neural network, and the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration and high-density lipoprotein cholesterol concentration measured for the target hyperlipidemia patient at the middle moment in the certain past time segment are listed as the reference blood lipid concentration of the certain past time segment as the output content of the deep neural network to complete this training, thereby ensuring the training effect of each training, wherein each training performed on the deep neural network corresponds to each past time segment;

[0048] Step 4: When the reference blood lipid concentration of the target hyperlipidemia patient is not within the set concentration value range in the current time segment of the intelligent prediction, the abnormal blood lipid concentration information is reported, thereby realizing the non-measurement centralized management of the future blood lipid status of hyperlipidemia patients in various locations;

[0049] Specifically, the abnormal blood lipid concentration information includes the reference blood lipid concentration of the target hyperlipidemia patient, the location information of the target hyperlipidemia patient, the communication information of the target hyperlipidemia patient, and various individual physiological information of the target hyperlipidemia patient;

[0050] It can be seen that through the above steps, effective prediction of future blood lipid data of patients with hyperlipidemia in various places can be achieved, avoiding the tedious and complicated process of blood drawing and blood testing, and providing valuable reference data for the customization of subsequent response strategies including initiating physical examinations.

[0051] The key points of the present invention are: targeted screening of multiple basic data for blood lipid reference information prediction, structural customization mechanism of AI prediction models with different specific structures of different hyperlipidemia patients, targeted single learning mechanism and non-measurement centralized management of future blood lipid status of hyperlipidemia patients in various locations.

[0052] The data analysis-based health management system and method of the present invention will be specifically described below in the form of embodiments.

[0053] Embodiment 1

[0054] Figure 2 The figure is a schematic diagram of the structure of a health management system based on data analysis according to the first embodiment of the present invention.

[0055] like Figure 2 As shown, the health management system based on data analysis includes the following components:

[0056] A time-sharing capture device is used to obtain health reference data corresponding to each time segment before the current time segment for the target hyperlipidemia patient, and the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment;

[0057] For example, different portable physiological parameter acquisition devices can be selected to respectively acquire the blood pressure value, heart rate value, body temperature value and blood oxygen saturation value of the same hyperlipidemia patient at the same time. The measurement of the blood lipid concentration of the hyperlipidemia patient in the past time segment needs to be obtained through a cumbersome and complicated blood drawing and blood testing process. The present invention is implemented precisely to prevent the need for a cumbersome and complicated blood drawing and blood testing process in the future time segment.

[0058] An information collection device, used to obtain various individual physiological information of a target hyperlipidemia patient, wherein the various individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information, and duration of hyperlipidemia of the target hyperlipidemia patient;

[0059] For example, obtaining various individual physiological information of a target hyperlipidemia patient, wherein the individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information and duration of hyperlipidemia of the target hyperlipidemia patient, including: the duration of hyperlipidemia is expressed in days;

[0060] A sequential training device is used to construct an AI prediction model for performing numerical prediction of blood lipid concentration in future time segments for target hyperlipidemia patients, wherein the AI ​​prediction model is a deep neural network that completes sequential training and the number of trainings is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient;

[0061] Specifically, a numerical conversion formula can be selected to represent a numerical conversion relationship in which a deep neural network that has completed successive training and the number of training times is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient;

[0062] For example, the numerical conversion formula can be selected to represent the completion of the training of the deep neural network, and the numerical conversion relationship in which the number of trainings is proportional to the duration of hyperlipidemia of the target hyperlipidemia patient includes: the duration of hyperlipidemia of the target hyperlipidemia patient is 50 days, the number of trainings is 100 times, the duration of hyperlipidemia of the target hyperlipidemia patient is 80 days, the number of trainings is 160 times, the duration of hyperlipidemia of the target hyperlipidemia patient is 120 days, the number of trainings is 240 times, the duration of hyperlipidemia of the target hyperlipidemia patient is 150 days, the number of trainings is 300 times, and so on;

[0063] A concentration prediction device, connected to the time-sharing capture device, the information collection device and the successive training device, respectively, for intelligently predicting the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment using the AI ​​prediction model based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient and various health reference data corresponding to each time segment before the current time segment;

[0064] Specifically, the MATLAB toolbox can be selected to simulate the data processing process of using the AI ​​prediction model to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment based on the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before the current time segment;

[0065] A reporting execution device, connected to the concentration prediction device, for executing a reporting process of abnormal blood lipid concentration information when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value interval;

[0066] Wherein, when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value interval, the reporting process of abnormal blood lipid concentration information includes: the reporting execution device has a built-in wireless communication interface for wirelessly connecting to a remote health management server, so as to wirelessly transmit abnormal blood lipid concentration information to the health management server when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value interval;

[0067] For example, a time division duplex communication link or a frequency division duplex communication link may be selected to wirelessly transmit abnormal blood lipid concentration information to the health management server when the reference blood lipid concentration of the target hyperlipidemia patient is not within the set concentration value interval within the received current time segment;

[0068] Wherein, when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, the abnormal blood lipid concentration information reporting process further includes: the abnormal blood lipid concentration information includes the reference blood lipid concentration of the target hyperlipidemia patient, the location information of the target hyperlipidemia patient, the communication information of the target hyperlipidemia patient and various individual physiological information of the target hyperlipidemia patient;

[0069] Among them, based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment, including: the intelligently predicted reference blood lipid concentration of the target hyperlipidemia patient in the current time segment includes the total cholesterol concentration reference value, triglyceride concentration reference value, low-density lipoprotein cholesterol concentration reference value and high-density lipoprotein cholesterol concentration reference value of the target hyperlipidemia patient in the current time segment;

[0070] Among them, obtaining the health reference data corresponding to each time segment before the current time segment for the target hyperlipidemia patient includes: the current time segment takes the current moment as the starting moment, and the duration of each time segment before the current time segment is equal to that of each time segment and together constitutes a complete time interval;

[0071] For example, the current time segment takes the current moment as the starting moment, the current moment segment and each time segment before the current time segment have the same duration and together form a complete time interval including: the duration of each time segment is 1 day, and the number of each time segment before the current time segment is monotonically positively correlated with the duration of hyperlipidemia of the target hyperlipidemia patient;

[0072] Among them, an AI prediction model for performing numerical prediction of blood lipid concentration in future time segments is constructed for the target hyperlipidemia patient, and the AI ​​prediction model is a deep neural network that completes successive training, and the number of trainings is proportional to the duration of hyperlipidemia of the target hyperlipidemia patient, including: in each training of the deep neural network, the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before a certain past time segment are used as multiple input contents of the deep neural network, and the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration and high-density lipoprotein cholesterol concentration measured for the target hyperlipidemia patient at the middle moment in the certain past time segment are listed as the reference blood lipid concentration of the certain past time segment as the output content of the deep neural network to complete this training;

[0073] Among them, an AI prediction model for performing blood lipid concentration numerical prediction for future time segments is constructed for the target hyperlipidemia patient, and the AI ​​prediction model is a deep neural network that completes successive training and the number of trainings is proportional to the duration of hyperlipidemia of the target hyperlipidemia patient, and also includes: each training performed on the deep neural network corresponds to each past time segment;

[0074] The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, including: the measured blood lipid concentration of the target hyperlipidemia patient in the time segment is the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration and high-density lipoprotein cholesterol concentration measured for the target hyperlipidemia patient at the middle moment in the time segment;

[0075] And wherein, the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and also includes: the average blood pressure value of the target hyperlipidemia patient in the time segment is the arithmetic mean of each blood pressure value measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment.

[0076] Embodiment 2

[0077] Figure 3 It is a structural diagram of a health management system based on data analysis according to the second embodiment of the present invention.

[0078] like Figure 3 As shown, Figure 2 Different from the embodiment in, the health management system based on data analysis also includes the following components:

[0079] A health management server is arranged at a remote end of the reporting execution device and is wirelessly connected to the reporting execution device, and is used to receive each piece of abnormal blood lipid concentration information reported by each reporting execution device corresponding to each hyperlipidemia patient through a wireless communication link;

[0080] For example, a blockchain server, a cloud computing server or a big data server can be selected to implement the health management server, which is set at the remote end of the reporting execution device and wirelessly connected to the reporting execution device, and is used to receive each piece of abnormal blood lipid concentration information reported by each reporting execution device corresponding to each hyperlipidemia patient through a wireless communication link.

[0081] Embodiment 3

[0082] Figure 4 It is a structural diagram of a health management system based on data analysis according to the third embodiment of the present invention.

[0083] like Figure 4 As shown, Figure 3 Different from the embodiment in, the health management system based on data analysis also includes the following components:

[0084] A model storage device, connected to the successive training device, used to receive the AI ​​prediction model sent by the successive training device and store the model;

[0085] For example, a TF storage chip, an MMC storage chip or a CF storage chip may be selected to implement the model storage device, connected to the successive training device, for receiving the AI ​​prediction model sent by the successive training device and storing the model;

[0086] Among them, receiving the AI ​​prediction model sent by the successive training device and storing the model includes: storing various model parameters of the AI ​​prediction model.

[0087] Embodiment 4

[0088] Figure 5 It is a structural diagram of a health management system based on data analysis according to the fourth embodiment of the present invention.

[0089] like Figure 5 As shown, Figure 3 Different from the embodiment in, the health management system based on data analysis also includes the following components:

[0090] A real-time positioning device is arranged in the wearing mechanism of the target hyperlipidemia patient, and is used to locate the target hyperlipidemia patient in real time to obtain positioning information of the location of the target hyperlipidemia patient;

[0091] Specifically, the real-time positioning device can be a GPS positioning device, a Big Dipper positioning device or a Galileo positioning device, which is arranged in the wearing mechanism of the target hyperlipidemia patient and is used to perform real-time positioning of the target hyperlipidemia patient to obtain positioning information of the location of the target hyperlipidemia patient;

[0092] Wherein, the real-time positioning device is connected to the reporting execution device, and is used to send the positioning information of the location of the target hyperlipidemia patient to the reporting execution device.

[0093] Embodiment 5

[0094] Figure 6 It is a structural diagram of a health management system based on data analysis according to the fifth embodiment of the present invention.

[0095] like Figure 6 As shown, Figure 5 Different from the embodiment in, the health management system based on data analysis also includes the following components:

[0096] An on-site display device, connected to the concentration prediction device, for receiving the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment intelligently predicted by the AI ​​prediction model;

[0097] Specifically, the on-site display device can be selected as a liquid crystal display device, an LED display device or an LCD display device, which is connected to the concentration prediction device to receive the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment intelligently predicted by the AI ​​prediction model.

[0098] Next, various embodiments of the present invention will be described in detail.

[0099] In a health management system based on data analysis according to various embodiments of the present invention:

[0100] Acquiring various individual physiological information of the target hyperlipidemia patient, wherein the various individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information and duration of hyperlipidemia of the target hyperlipidemia patient, including: the BMI index of the target hyperlipidemia patient is the square of the value obtained by dividing the weight of the target hyperlipidemia patient in kilograms by the height of the target hyperlipidemia patient in meters;

[0101] Wherein, when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, the reporting process of abnormal blood lipid concentration information is performed, including: when the total cholesterol concentration reference value of the target hyperlipidemia patient received in the current time segment exceeds the preset total cholesterol concentration threshold, when the triglyceride concentration reference value exceeds the preset triglyceride concentration threshold, when the low-density lipoprotein cholesterol concentration reference value exceeds the preset low-density lipoprotein cholesterol concentration threshold and / or when the high-density lipoprotein cholesterol concentration reference value is lower than or equal to the preset high-density lipoprotein cholesterol concentration threshold, the reporting process of abnormal blood lipid concentration information is performed;

[0102] For example, when the total cholesterol concentration reference value of the target hyperlipidemia patient in the received current time segment exceeds the preset total cholesterol concentration threshold, the triglyceride concentration reference value exceeds the preset triglyceride concentration threshold, the low-density lipoprotein cholesterol concentration reference value exceeds the preset low-density lipoprotein cholesterol concentration threshold and / or the high-density lipoprotein cholesterol concentration reference value is less than or equal to the preset high-density lipoprotein cholesterol concentration threshold, the reporting process of abnormal blood lipid concentration information includes: the specific value selected for the preset total cholesterol concentration threshold is 5.2 mmol per liter, the specific value selected for the preset triglyceride concentration threshold is 1.7 mmol per liter, the specific value selected for the preset high-density lipoprotein cholesterol concentration threshold is 3.4 mmol per liter, and the specific value selected for the preset high-density lipoprotein cholesterol concentration threshold is 1.0 mmol per liter.

[0103] And in the health management system based on data analysis according to various embodiments of the present invention:

[0104] Based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment, including: synchronously inputting the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment into the AI ​​prediction model;

[0105] Among them, based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, using the AI ​​prediction model to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment also includes: running the AI ​​prediction model to obtain the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment output by the AI ​​prediction model;

[0106] The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and also includes: the average heart rate value of the target hyperlipidemia patient in the time segment is the arithmetic mean of the heart rate values ​​measured for the target hyperlipidemia patient at each evenly spaced time in the time segment;

[0107] The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and also includes: the average body temperature value of the target hyperlipidemia patient in the time segment is the arithmetic mean of the body temperature values ​​measured for the target hyperlipidemia patient at each uniformly spaced time in the time segment;

[0108] And wherein, the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and also includes: the average blood oxygen saturation value of the target hyperlipidemia patient in the time segment is the arithmetic mean of each blood oxygen saturation value measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment.

[0109] Embodiment 6

[0110] Figure 7 The figure is a flowchart of the steps of a health management method based on data analysis according to the sixth embodiment of the present invention.

[0111] like Figure 7 As shown, the health management method based on data analysis according to the sixth embodiment of the present invention specifically includes the following steps:

[0112] For the target hyperlipidemia patient, obtain the health reference data corresponding to each time segment before the current time segment, and the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment;

[0113] For example, different portable physiological parameter acquisition devices can be selected to respectively acquire the blood pressure value, heart rate value, body temperature value and blood oxygen saturation value of the same hyperlipidemia patient at the same time. The measurement of the blood lipid concentration of the hyperlipidemia patient in the past time segment needs to be obtained through a cumbersome and complicated blood drawing and blood testing process. The present invention is implemented precisely to prevent the need for a cumbersome and complicated blood drawing and blood testing process in the future time segment.

[0114] Acquire various individual physiological information of the target hyperlipidemia patient, wherein the various individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information and duration of hyperlipidemia of the target hyperlipidemia patient;

[0115] For example, obtaining various individual physiological information of a target hyperlipidemia patient, wherein the individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information and duration of hyperlipidemia of the target hyperlipidemia patient, including: the duration of hyperlipidemia is expressed in days;

[0116] Construct an AI prediction model for predicting blood lipid concentration values ​​in future time segments for target hyperlipidemia patients, wherein the AI ​​prediction model is a deep neural network that completes successive training and the number of trainings is proportional to the duration of hyperlipidemia in the target hyperlipidemia patients;

[0117] Specifically, a numerical conversion formula can be selected to represent a numerical conversion relationship in which a deep neural network that has completed successive training and the number of training times is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient;

[0118] For example, the numerical conversion formula can be selected to represent the completion of the training of the deep neural network, and the numerical conversion relationship in which the number of trainings is proportional to the duration of hyperlipidemia of the target hyperlipidemia patient includes: the duration of hyperlipidemia of the target hyperlipidemia patient is 50 days, the number of trainings is 100 times, the duration of hyperlipidemia of the target hyperlipidemia patient is 80 days, the number of trainings is 160 times, the duration of hyperlipidemia of the target hyperlipidemia patient is 120 days, the number of trainings is 240 times, the duration of hyperlipidemia of the target hyperlipidemia patient is 150 days, the number of trainings is 300 times, and so on;

[0119] Based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment;

[0120] Specifically, the MATLAB toolbox can be selected to simulate the data processing process of using the AI ​​prediction model to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment based on the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before the current time segment;

[0121] When the reference blood lipid concentration of the target hyperlipidemia patient in the received current time segment is not within the set concentration value range, performing a reporting process of abnormal blood lipid concentration information;

[0122] Wherein, when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value interval, the reporting process of abnormal blood lipid concentration information includes: the reporting execution device has a built-in wireless communication interface for wirelessly connecting to a remote health management server, so as to wirelessly transmit abnormal blood lipid concentration information to the health management server when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value interval;

[0123] For example, a time division duplex communication link or a frequency division duplex communication link may be selected to wirelessly transmit abnormal blood lipid concentration information to the health management server when the reference blood lipid concentration of the target hyperlipidemia patient is not within the set concentration value interval within the received current time segment;

[0124] Wherein, when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, the abnormal blood lipid concentration information reporting process further includes: the abnormal blood lipid concentration information includes the reference blood lipid concentration of the target hyperlipidemia patient, the location information of the target hyperlipidemia patient, the communication information of the target hyperlipidemia patient and various individual physiological information of the target hyperlipidemia patient;

[0125] Among them, based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment, including: the intelligently predicted reference blood lipid concentration of the target hyperlipidemia patient in the current time segment includes the total cholesterol concentration reference value, triglyceride concentration reference value, low-density lipoprotein cholesterol concentration reference value and high-density lipoprotein cholesterol concentration reference value of the target hyperlipidemia patient in the current time segment;

[0126] Among them, obtaining the health reference data corresponding to each time segment before the current time segment for the target hyperlipidemia patient includes: the current time segment takes the current moment as the starting moment, and the duration of each time segment before the current time segment is equal to that of each time segment and together constitutes a complete time interval;

[0127] For example, the current time segment takes the current moment as the starting moment, the current moment segment and each time segment before the current time segment have the same duration and together form a complete time interval including: the duration of each time segment is 1 day, and the number of each time segment before the current time segment is monotonically positively correlated with the duration of hyperlipidemia of the target hyperlipidemia patient;

[0128] Among them, an AI prediction model for performing numerical prediction of blood lipid concentration in future time segments is constructed for the target hyperlipidemia patient, and the AI ​​prediction model is a deep neural network that completes successive training, and the number of trainings is proportional to the duration of hyperlipidemia of the target hyperlipidemia patient, including: in each training of the deep neural network, the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before a certain past time segment are used as multiple input contents of the deep neural network, and the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration and high-density lipoprotein cholesterol concentration measured for the target hyperlipidemia patient at the middle moment in the certain past time segment are listed as the reference blood lipid concentration of the certain past time segment as the output content of the deep neural network to complete this training;

[0129] Among them, an AI prediction model for performing blood lipid concentration numerical prediction for future time segments is constructed for the target hyperlipidemia patient, and the AI ​​prediction model is a deep neural network that completes successive training and the number of trainings is proportional to the duration of hyperlipidemia of the target hyperlipidemia patient, and also includes: each training performed on the deep neural network corresponds to each past time segment;

[0130] The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, including: the measured blood lipid concentration of the target hyperlipidemia patient in the time segment is the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration and high-density lipoprotein cholesterol concentration measured for the target hyperlipidemia patient at the middle moment in the time segment;

[0131] And wherein, the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and also includes: the average blood pressure value of the target hyperlipidemia patient in the time segment is the arithmetic mean of each blood pressure value measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment.

[0132] In addition, the present invention may also cite the following technical contents to further demonstrate the outstanding essential features of the present invention:

[0133] The average heart rate value of the target hyperlipidemia patient in the time segment is the arithmetic mean of the heart rate values ​​measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment, including: performing arithmetic mean operation on the remaining multiple heart rate values ​​obtained by removing the maximum value and the minimum value of the heart rate values ​​measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment, so as to obtain the arithmetic mean of the heart rate values ​​measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment;

[0134] For example, performing arithmetic mean operation on the remaining plurality of heart rate values ​​obtained after removing the maximum value and the minimum value of each heart rate value measured for the target hyperlipidemia patient at each evenly spaced time in the time segment to obtain the arithmetic mean of each heart rate value measured for the target hyperlipidemia patient at each evenly spaced time in the time segment includes: a numerical conversion process of selecting a numerical conversion function to represent each heart rate value to the arithmetic mean of each heart rate value;

[0135] Among them, based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, using the AI ​​prediction model to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment also includes: converting the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment into hexadecimal values ​​and then synchronously inputting them into the AI ​​prediction model;

[0136] Among them, based on the duration of each time segment, the individual physiological information of the target hyperlipidemia patient and the health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment, which also includes: the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment output by the AI ​​prediction model is a numerical representation mode of a hexadecimal value.

[0137] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0139] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A health management system based on data analysis, characterized in that: The system comprises: A time-sharing capture device is used to obtain, for a target hyperlipidemia patient, health reference data corresponding to each time segment before the current time segment, wherein the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment; An information collection device for acquiring various individual physiological information of a target hyperlipidemia patient, wherein the individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information, and duration of hyperlipidemia of the target hyperlipidemia patient; A sequential training device is used to construct an AI prediction model for performing future time segment blood lipid concentration numerical prediction for a target hyperlipidemia patient, wherein the AI ​​prediction model is a deep neural network that completes sequential training, and the number of training sessions is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient; a concentration prediction device, connected to the time-sharing capture device, the information collection device, and the successive training device, respectively, for intelligently predicting the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment using the AI ​​prediction model based on the duration of each time segment, individual physiological information of the target hyperlipidemia patient, and health reference data corresponding to each time segment before the current time segment; a reporting execution device connected to the concentration prediction device, configured to execute a reporting process for abnormal blood lipid concentration information when the reference blood lipid concentration of the target hyperlipidemia patient is not within a set concentration value range within the received current time segment; Wherein, when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value range, executing the reporting process of abnormal blood lipid concentration information includes: the reporting execution device has a built-in wireless communication interface for wirelessly connecting to a remote health management server, so as to wirelessly transmit the abnormal blood lipid concentration information to the health management server when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value range; Wherein, when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, performing the reporting process of abnormal blood lipid concentration information further includes: the abnormal blood lipid concentration information includes the reference blood lipid concentration of the target hyperlipidemia patient, the positioning information of the target hyperlipidemia patient, the communication information of the target hyperlipidemia patient, and various individual physiological information of the target hyperlipidemia patient; Among them, based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment, including: the intelligently predicted reference blood lipid concentration of the target hyperlipidemia patient in the current time segment includes the total cholesterol concentration reference value, triglyceride concentration reference value, low-density lipoprotein cholesterol concentration reference value, and high-density lipoprotein cholesterol concentration reference value of the target hyperlipidemia patient in the current time segment; Among them, for the target hyperlipidemia patient, obtaining health reference data corresponding to each time segment before the current time segment includes: the current time segment takes the current moment as the starting moment, and the current moment segment and each time segment before the current time segment have the same duration and together form a complete time interval; Among them, an AI prediction model for performing numerical prediction of blood lipid concentration in future time segments is constructed for the target hyperlipidemia patient. The AI ​​prediction model is a deep neural network that completes successive training, and the number of trainings is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient. The model includes: in each training of the deep neural network, the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before a certain past time segment are used as multiple input contents of the deep neural network, and the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration, and high-density lipoprotein cholesterol concentration measured for the target hyperlipidemia patient at the middle moment of the certain past time segment are listed as the reference blood lipid concentration of the certain past time segment as the output content of the deep neural network to complete this training; Among them, an AI prediction model is constructed for a target hyperlipidemia patient to perform blood lipid concentration numerical prediction for future time segments, wherein the AI ​​prediction model is a deep neural network that completes successive training, and the number of trainings is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient, and further includes: each training of the deep neural network corresponds to each past time segment; The single piece of health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, including: the measured blood lipid concentration of the target hyperlipidemia patient in the time segment is the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration, and high-density lipoprotein cholesterol concentration obtained by measuring the target hyperlipidemia patient at the middle moment in the time segment; The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and further includes: the average blood pressure value of the target hyperlipidemia patient in the time segment is the arithmetic average of the blood pressure values ​​measured for the target hyperlipidemia patient at evenly spaced moments in the time segment; The average heart rate value of the target hyperlipidemia patient in the time segment is the arithmetic mean of the heart rate values ​​respectively measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment, including: performing an arithmetic mean operation on the remaining multiple heart rate values ​​obtained after removing the maximum value and the minimum value of the heart rate values ​​respectively measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment, so as to obtain the arithmetic mean of the heart rate values ​​respectively measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment; Among them, based on the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before the current time segment, using the AI ​​prediction model to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment includes: synchronously inputting the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before the current time segment into the AI ​​prediction model; Among them, using the AI ​​prediction model to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment further includes: running the AI ​​prediction model to obtain the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment output by the AI ​​prediction model; The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and further includes: the average heart rate value of the target hyperlipidemia patient in the time segment is the arithmetic average of the heart rate values ​​measured for the target hyperlipidemia patient at evenly spaced moments in the time segment; The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and further includes: the average body temperature value of the target hyperlipidemia patient in the time segment is the arithmetic average of the body temperature values ​​measured for the target hyperlipidemia patient at each evenly spaced time in the time segment; The individual health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient during the time segment, and further includes: the average blood oxygen saturation value of the target hyperlipidemia patient during the time segment is the arithmetic mean of the blood oxygen saturation values ​​of the target hyperlipidemia patient measured at evenly spaced moments during the time segment; The system further comprises: The health management server is arranged at the remote end of the reporting execution device and is wirelessly connected to the reporting execution device, and is used to receive each piece of abnormal blood lipid concentration information reported by each reporting execution device corresponding to each hyperlipidemia patient through a wireless communication link.

2. The health management system based on data analysis according to claim 1, characterized in that: The system further comprises: A model storage device, connected to the successive training device, for receiving the AI ​​prediction model sent by the successive training device and storing the model; Among them, receiving the AI ​​prediction model sent by the successive training device and storing the model includes: storing various model parameters of the AI ​​prediction model.

3. The health management system based on data analysis according to claim 1, characterized in that: The system further comprises: A real-time positioning device is provided in the wearing mechanism of the target hyperlipidemia patient, and is used to locate the target hyperlipidemia patient in real time to obtain positioning information of the target hyperlipidemia patient; The real-time positioning device is connected to the reporting execution device and is used to send the positioning information of the target hyperlipidemia patient to the reporting execution device.

4. The health management system based on data analysis according to claim 1, characterized in that: The system further comprises: An on-site display device is connected to the concentration prediction device and is used to receive the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment intelligently predicted by the AI ​​prediction model.

5. The data analysis-based health management system according to any one of claims 1 to 4, characterized in that: Acquiring various individual physiological information of a target hyperlipidemia patient, wherein the various individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information, and duration of hyperlipidemia of the target hyperlipidemia patient, including: the BMI index of the target hyperlipidemia patient is the square of the value obtained by dividing the weight of the target hyperlipidemia patient in kilograms by the height of the target hyperlipidemia patient in meters; Among them, when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, the reporting processing of abnormal blood lipid concentration information includes: when the total cholesterol concentration reference value of the target hyperlipidemia patient received in the current time segment exceeds the preset total cholesterol concentration threshold, when the triglyceride concentration reference value exceeds the preset triglyceride concentration threshold, when the low-density lipoprotein cholesterol concentration reference value exceeds the preset low-density lipoprotein cholesterol concentration threshold and / or the high-density lipoprotein cholesterol concentration reference value is lower than or equal to the preset high-density lipoprotein cholesterol concentration threshold, the reporting processing of abnormal blood lipid concentration information is executed.

6. A health management method based on data analysis, implemented based on the system of claim 1, characterized in that: Obtain, for the target hyperlipidemia patient, health reference data corresponding to each time segment before the current time segment. The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment. Acquiring various individual physiological information of the target hyperlipidemia patient, wherein the individual physiological information of the target hyperlipidemia patient includes the BMI index, age information, gender information, and duration of hyperlipidemia of the target hyperlipidemia patient; Constructing an AI prediction model for target hyperlipidemia patients to perform future time segment blood lipid concentration numerical predictions. The AI ​​prediction model is a deep neural network that completes successive training, and the number of training sessions is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient; Based on the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment; When the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, performing a reporting process for abnormal blood lipid concentration information; Wherein, when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value range, executing the reporting process of abnormal blood lipid concentration information includes: the reporting execution device has a built-in wireless communication interface for wirelessly connecting to a remote health management server, so as to wirelessly transmit the abnormal blood lipid concentration information to the health management server when the received reference blood lipid concentration of the target hyperlipidemia patient in the current time segment is not within the set concentration value range; Wherein, when the reference blood lipid concentration of the target hyperlipidemia patient received in the current time segment is not within the set concentration value range, performing the reporting process of abnormal blood lipid concentration information further includes: the abnormal blood lipid concentration information includes the reference blood lipid concentration of the target hyperlipidemia patient, the positioning information of the target hyperlipidemia patient, the communication information of the target hyperlipidemia patient, and various individual physiological information of the target hyperlipidemia patient; Among them, based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment, the AI ​​prediction model is used to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment, including: the intelligently predicted reference blood lipid concentration of the target hyperlipidemia patient in the current time segment includes the total cholesterol concentration reference value, triglyceride concentration reference value, low-density lipoprotein cholesterol concentration reference value, and high-density lipoprotein cholesterol concentration reference value of the target hyperlipidemia patient in the current time segment; Among them, for the target hyperlipidemia patient, obtaining health reference data corresponding to each time segment before the current time segment includes: the current time segment takes the current moment as the starting moment, and the current moment segment and each time segment before the current time segment have the same duration and together form a complete time interval; Among them, an AI prediction model for performing numerical prediction of blood lipid concentration in future time segments is constructed for the target hyperlipidemia patient. The AI ​​prediction model is a deep neural network that completes successive training, and the number of trainings is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient. The model includes: in each training of the deep neural network, the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before a certain past time segment are used as multiple input contents of the deep neural network, and the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration, and high-density lipoprotein cholesterol concentration measured for the target hyperlipidemia patient at the middle moment of the certain past time segment are listed as the reference blood lipid concentration of the certain past time segment as the output content of the deep neural network to complete this training; Among them, an AI prediction model is constructed for a target hyperlipidemia patient to perform blood lipid concentration numerical prediction for future time segments, wherein the AI ​​prediction model is a deep neural network that completes successive training, and the number of trainings is proportional to the duration of hyperlipidemia in the target hyperlipidemia patient, and further includes: each training of the deep neural network corresponds to each past time segment; The single piece of health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, including: the measured blood lipid concentration of the target hyperlipidemia patient in the time segment is the total cholesterol concentration, triglyceride concentration, low-density lipoprotein cholesterol concentration, and high-density lipoprotein cholesterol concentration obtained by measuring the target hyperlipidemia patient at the middle moment in the time segment; The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and further includes: the average blood pressure value of the target hyperlipidemia patient in the time segment is the arithmetic average of the blood pressure values ​​measured for the target hyperlipidemia patient at evenly spaced moments in the time segment; The average heart rate value of the target hyperlipidemia patient in the time segment is the arithmetic mean of the heart rate values ​​respectively measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment, including: performing an arithmetic mean operation on the remaining multiple heart rate values ​​obtained after removing the maximum value and the minimum value of the heart rate values ​​respectively measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment, so as to obtain the arithmetic mean of the heart rate values ​​respectively measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment; Among them, based on the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before the current time segment, using the AI ​​prediction model to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment includes: synchronously inputting the duration of each time segment, the individual physiological information of the target hyperlipidemia patient, and the health reference data corresponding to each time segment before the current time segment into the AI ​​prediction model; Among them, using the AI ​​prediction model to intelligently predict the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment based on the duration of each time segment, various individual physiological information of the target hyperlipidemia patient, and various health reference data corresponding to each time segment before the current time segment further includes: running the AI ​​prediction model to obtain the reference blood lipid concentration of the target hyperlipidemia patient in the current time segment output by the AI ​​prediction model; The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and further includes: the average heart rate value of the target hyperlipidemia patient in the time segment is the arithmetic average of the heart rate values ​​measured for the target hyperlipidemia patient at evenly spaced moments in the time segment; The single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value, and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and further includes: the average body temperature value of the target hyperlipidemia patient in the time segment is the arithmetic average of the body temperature values ​​measured for the target hyperlipidemia patient at each evenly spaced time in the time segment; Among them, the single health parameter data corresponding to each time segment is the measured blood lipid concentration, average blood pressure value, average heart rate value, average body temperature value and average blood oxygen saturation value of the target hyperlipidemia patient in the time segment, and also includes: the average blood oxygen saturation value of the target hyperlipidemia patient in the time segment is the arithmetic average of each blood oxygen saturation value measured for the target hyperlipidemia patient at each evenly spaced moment in the time segment.

Images