Health monitoring method and system based on data analysis

Abstract

The invention relates to the field of health monitoring, in particular to a health monitoring method and system based on data analysis, and the method comprises the steps: collecting health data of an individual user according to sensor equipment, building a health assessment neural network model, obtaining a real-time health assessment result of the individual user, and carrying out the grading of the health of the individual user; according to an output result of the health assessment neural network model and the body health related data information, calculating a health monitoring prompt information sending frequency adjustment coefficient; according to the average motion frequency, whether the sending frequency of the health monitoring prompt information is optimized or not is judged; and in combination with the optimized sending frequency of the health monitoring prompt information, establishing a health intelligent tracking model according to the feedback information of the individual, and monitoring and evaluating the health condition of the individual.

Description

Technical Field

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

[0002] With the continuous improvement of people's attention to health, health monitoring has become an important part of daily life. Traditional health monitoring methods mainly rely on manual records and regular physical examinations. This method has problems such as untimely, inaccurate, and incomplete data, and cannot reflect an individual's health status in real time. In recent years, with the development of sensor technology, Internet of Things technology, and big data analysis technology, health monitoring methods based on data analysis have gradually emerged.

[0003] However, existing health monitoring methods based on data analysis still have some deficiencies. For example, the accuracy and integrity of data collection need to be improved, the accuracy and efficiency of data analysis algorithms are low, and there is a lack of personalized health assessment and warning mechanisms. Most importantly, the frequency of sending messages to remind individual users to pay attention to their physical health is not targeted, resulting in too high or too low a sending frequency, making it impossible for users to effectively pay attention to their own physical health problems or causing certain interference to users' lives.

[0004] Therefore, a health monitoring method and system based on data analysis are needed. Summary of the Invention

[0005] A health monitoring method and system based on data analysis provided by the present invention aim to intelligently help users monitor their health status in real time, prevent diseases, optimize health behaviors, achieve personalized health management, and continuously improve the individual's health level and quality of life by analyzing users' health data.

[0006] The technical solution of the present invention is as follows: A health monitoring method based on data analysis includes the following steps: Step S1. Collect the health data of individual users according to sensor devices, establish a health assessment neural network model, obtain the real-time health assessment results of individual users, and classify the health conditions of individual users; Step S2. Calculate the adjustment coefficient of the sending frequency of health monitoring reminder information according to the output result of the health assessment neural network model and the data information related to physical health; Step S3. Combine the obtained average exercise frequency to determine whether to optimize the sending frequency of health monitoring reminder information; Step S4. Through the optimized sending frequency of health monitoring reminder information, and at the same time according to the feedback information, establish a health intelligent tracking model to monitor and evaluate the health status of individuals.

[0007] Step S1 specifically includes: The health assessment neural network model includes an input layer, an intelligent analysis layer, an evaluation layer, and an output layer; in the intelligent analysis layer, the input health index feature data information is analyzed, and the output result is transmitted to the evaluation layer, where the output result of the intelligent analysis layer is optimized and the final analysis result is output by the output layer.

[0008] In step S1, the individual's health condition is classified into levels, and at the same time, the sending frequency of the health monitoring prompt information is preset; the health levels are set to three levels, , including level one, that is, the healthy state, level two, that is, the sub-healthy state, and level three, that is, the unhealthy state; the probability distribution function of the health assessment results under different health levels, where: represents the prior probability of the health level ; represents the index of the health level; the health level with the largest posterior probability is selected as the individual's health level, .

[0009] Step S1 specifically includes: The predefined basic health monitoring prompt information sending frequency is , the lowest health monitoring prompt information sending frequency is , and the highest health monitoring prompt information sending frequency is ; When , the first health monitoring prompt information sending frequency is set to , then , represents the adjustment coefficient when in the healthy state; When , the first health monitoring prompt information sending frequency is set to , then , represents the adjustment coefficient when in the sub-healthy state; When , the first health monitoring prompt information sending frequency is set to , then , represents the adjustment coefficient when in the unhealthy state.

[0010] Step S2 specifically includes: According to the health monitoring prompt information sending frequency adjustment coefficient ​Adjust the sending frequency of the health monitoring prompt information according to the comparison result with the comparison parameter of the preset health monitoring prompt information sending frequency adjustment coefficient, and obtain the adjusted second health monitoring prompt information sending frequency 。

[0011] In step S2, the comprehensive exercise health score is mapped through the activation function to obtain the health monitoring prompt information sending frequency adjustment coefficient , and the specific process is as follows: Among them, represents the constant adjustment coefficient; represents the interference coefficient that affects the health monitoring prompt information.

[0012] Step S3 specifically includes: Preset the average exercise frequency , and compare the average exercise frequency with the preset average exercise frequency ; If , then adjust it to the third health monitoring prompt information sending frequency , ; If , then adjust it to the third health monitoring prompt information sending frequency , that is, the third health monitoring prompt information sending frequency, ; If , then adjust it to the third health monitoring prompt information sending frequency , that is, the third health monitoring prompt information sending frequency, ; Among them, represents the first regulation coefficient; represents the second regulation coefficient.

[0013] Step S4 specifically includes: Among them, represents the updated result; represents the optimized health monitoring prompt information sending frequency; represents the update coefficient; represents the th current situation of the body movement related indicators; represents the update function of the user's body movement related indicator situation; represents the probability that the ideal sleep duration situation meets the standard; represents the probability that the actual sleep duration situation meets the standard; Indicates the obstructive characteristics of external work pressure.

[0014] A health monitoring system based on data analysis, including the following: An individual user data acquisition module, a user health assessment module, a health level classification module, a transmission frequency adjustment parameter determination module, a transmission frequency adjustment module, and a health intelligent tracking module; The individual user data acquisition module is responsible for acquiring and collecting health-related data of individual users through sensor devices. The user health assessment module evaluates and analyzes the health data of individual users to generate health assessment results for individual users. The health level classification module divides the health status of individual users into different health levels according to the output results of the user health assessment module. The transmission frequency adjustment parameter determination module calculates the adjustment coefficient of the transmission frequency of health monitoring prompt information according to the output results of the health assessment neural network model and the information on physical health-related data. The transmission frequency adjustment module is responsible for adjusting the transmission frequency of health monitoring prompt information to ensure that the information transmission frequency is suitable for the user's health status and needs. The health intelligent tracking module establishes a health intelligent tracking model according to the feedback information through the optimized transmission frequency of health monitoring prompt information.

[0015] The frequency adjustment module includes a first adjustment unit, a second adjustment unit, and a third adjustment unit. The first adjustment unit determines the initial transmission frequency of health monitoring prompt information according to the user's health assessment results and health level classification. The second adjustment unit adjusts the transmission frequency of health monitoring prompt information according to the comparison result between the adjustment coefficient of the transmission frequency of health monitoring prompt information and the comparison parameter of the preset transmission frequency of health monitoring prompt information. The third adjustment unit compares the average exercise frequency with the preset average exercise frequency and determines whether to optimize the transmission frequency of health monitoring prompt information according to the comparison result.

[0016] Beneficial effects: 1. Through the health assessment neural network model, the present invention can achieve personalized health assessment based on the specific health data of each individual, taking into account the physiological characteristics and health history of each person, and accurately assessing the health status of the individual; by analyzing the health data of individual users based on the neural network model, the health conditions of users can be classified into levels, so as to more intuitively understand the overall health status of individuals and provide corresponding suggestions and management plans for different levels; moreover, by regularly sending health monitoring reminder messages at a preset frequency, it can timely remind users to pay attention to their own health status, encourage users to take positive health behaviors, and timely intervene in potential health problems.

[0017] 2. The present invention calculates the adjustment coefficient according to the real-time health assessment results and physical health data information, realizes the adjustment of the sending frequency of dynamic health reminder messages, timely reflects the changes in the health status of individual users, meets the health monitoring needs of users, improves the user experience, enhances user participation and enthusiasm; at the same time, improves the early warning effect, helps users better cope with health problems, timely take necessary actions, and prevent the occurrence of diseases.

[0018] 3. The present invention adjusts the sending frequency of reminder messages according to the average exercise frequency, which can help users develop healthier living habits, make the health reminder messages more targeted and effective, improve user participation and enthusiasm for health management; optimizing the sending frequency of health monitoring reminder messages can increase users' attention to health problems and help them better manage their health status.

[0019] 4. Based on the optimized sending frequency of reminder messages and feedback information, the health intelligent tracking model established by the present invention provides more personalized health management services, adjusts the health monitoring plan according to the actual needs and feedback of individuals; combined with feedback information, the health intelligent tracking model can achieve more real-time health monitoring, timely discover health problems and adjust health management strategies, and improve the effect of health management; by deeply analyzing the health data of individuals with the help of the health intelligent tracking model, potential health problems and trends are discovered, and more targeted health management suggestions are provided for individuals. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flowchart of a health monitoring method based on data analysis according to the present invention; Figure 2 is a module diagram of a health monitoring system based on data analysis according to the present invention; Figure 3 is a schematic diagram of the sending frequency adjustment module according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0021] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners. At the same time, it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0022] Referring to the attached Figure 1 , this embodiment provides a health monitoring method based on data analysis, including the following steps: S1. Collect the health data of individual users according to the sensor device, establish a health assessment neural network model, obtain the real-time health assessment results of individual users, classify the health assessment results of individual users, and preset the sending frequency of health monitoring prompt information.

[0023] Collect the health data of individual users through a variety of sensor devices. The sensor devices include but are not limited to wearable devices, such as smart bracelets and smart watches; medical devices, such as sphygmomanometers and blood glucose meters; environmental sensors, such as temperature and humidity sensors, air quality sensors, etc. The health data includes physiological data, such as heart rate, blood pressure, blood glucose, body temperature, etc.; exercise data, such as number of steps, exercise distance, exercise intensity, etc.; sleep data, such as sleep time, sleep quality, etc. and environmental data, such as temperature, humidity, air quality, etc. Clean and preprocess the collected original health data, remove noise data, abnormal data and missing data, and standardize the data for subsequent data analysis and processing.

[0024] In the embodiment of the present invention, a health assessment neural network model is established according to the obtained health data information of individual users, the real-time health assessment results of individual users are obtained, the health assessment results of individual users are classified, and the sending frequency of health monitoring prompt information is preset. The health monitoring prompt information is received through smart wearable devices or communication devices associated with personal information, etc., to remind the monitored personnel to timely master the individual physical state, take active health management measures, and promote health and prevent diseases.

[0025] Establish a health assessment neural network model through deep learning, use the obtained individual health data as training samples, and use it as the input of the health assessment neural network model, denoted as , Denote The health index feature data information of , where any one of the health index feature data information is represented by . The health assessment neural network model includes an input layer, an intelligent analysis layer, an evaluation layer, and an output layer.

[0026] The input layer transfers To the analysis layer, the transfer process is as follows: Among them, represents the input of the analysis layer; represents the connection weight between the input layer and the evaluation layer; represents the output of the input layer; represents the bias of the evaluation layer.

[0027] In the intelligent analysis layer, the input health index feature data information is analyzed, and the specific process is as follows: Among them, represents the output of the intelligent analysis layer; represents the body data feature fusion parameter; represents the blood pressure and pulse index, which is the ratio of pulse pressure to mean arterial pressure; represents the normal heart rate range of the human body; represents at; represents the recording time period; represents the heart rate fluctuation change coefficient; represents the deep sleep duration; represents recording the th cycle of sleep quality; represents the influence function of the surrounding environment on human health; represents the stability factor of the intelligent analysis process; represents the influence coefficient of environmental factors; The intelligent analysis layer transmits the output result to the evaluation layer, and in the evaluation layer, the output result of the intelligent analysis layer is optimized, and the specific process is as follows: Among them, represents the output of the evaluation layer; represents the learning factor; represents the connection weight between the intelligent analysis layer and the evaluation layer; represents the bias of the enhancement layer.

[0028] Finally, the output layer outputs the final analysis result, , among which, represents the output result of the output layer, represents the connection weight between the evaluation layer and the output layer, represents the bias of the output layer.

[0029] The individual health assessment results are classified, and at the same time, the preset health monitoring prompt information sending frequency .

[0030] Set the health level There are three levels, including level one, which is the healthy state; level two, which is the sub-healthy state; and level three, which is the unhealthy state. Level one, the healthy state, indicates that all physical indicators are within the normal range, there are no obvious diseases or discomfort symptoms, the body functions well, and it has strong immunity and adaptability. Level two, the sub-healthy state, indicates a state between health and disease. Although there is no clear disease diagnosis, there are some discomfort symptoms or mild abnormalities in certain indicators. Level three, the unhealthy state, indicates that there are obvious diseases or pathological conditions in the body, and medical intervention and treatment are required.

[0031] Probability distribution function of health assessment results at different health levels of , where ; Determine the posterior probability that an individual belongs to different health levels , and the calculation process is as follows: where represents the prior probability of health level ; represents the index of the health level, which is used to traverse all possible health levels. The prior probability is obtained by using known statistical techniques based on existing authoritative medical reports and a large amount of historical data or survey reports.

[0032] Select the health level with the maximum posterior probability as the individual's health level, as follows: where represents the maximum value of the obtained posterior probability.

[0033] In the first adjustment unit, the basic health monitoring prompt information sending frequency is predefined as , the lowest health monitoring prompt information sending frequency is , and the highest health monitoring prompt information sending frequency is ; When an individual's physical health is in the healthy state, that is, , set the first health monitoring prompt information sending frequency to , then , represents the adjustment coefficient when in the healthy state; When an individual's physical health is in the sub-healthy state, that is, , set the first health monitoring prompt information sending frequency to , then , represents the adjustment coefficient when in the sub-healthy state; When an individual's physical health is in the unhealthy state, that is, , set the first health monitoring prompt information sending frequency to , then , represents the adjustment coefficient when in an unhealthy state.

[0034] Through the health assessment neural network model of the present invention, personalized health assessment can be achieved according to the specific health data of each individual. Considering the physiological characteristics and health history of each person, the health status of the individual can be accurately evaluated. Based on the analysis of the health data of individual users by the neural network model, the health conditions of the users can be classified into levels, so as to more intuitively understand the overall health status of the individual and provide corresponding suggestions and management plans for different levels. Moreover, by regularly sending health monitoring reminder messages at a preset frequency, users can be timely reminded to pay attention to their own health status, prompting users to take positive health behaviors and timely intervene in potential health problems.

[0035] S2. Calculate the adjustment coefficient of the health monitoring reminder message sending frequency according to the output result of the health assessment neural network model and the physical health-related data information ; Adjust the health monitoring reminder message sending frequency according to the comparison result between the adjustment coefficient of the health monitoring reminder message sending frequency and the comparison parameter of the preset health monitoring reminder message sending frequency adjustment coefficient.

[0036] In the embodiment of the present invention, according to the output result of the health assessment neural network model and the body movement-related data information, feature information is extracted and multi-dimensionally fused using the existing technology to calculate the comprehensive exercise health score , define represents the th body movement-related index situation, including steps, calorie consumption, exercise distance, etc., represents the number of indexes, represents the weight corresponding to each body movement-related index, and the process is as follows: Among them, , respectively represent the output results of the health assessment network after fusion processing , the body movement-related index situation corresponding relevant weights.

[0037] Map the comprehensive exercise health score through the activation function to obtain the adjustment coefficient of the health monitoring reminder message sending frequency , and the specific process is as follows: Among them, represents the constant adjustment coefficient; The interference coefficient that affects the health monitoring prompt information.

[0038] In the second adjustment unit, adjust the coefficient according to the sending frequency of the health monitoring prompt information The comparison parameter with the first preset health monitoring prompt information sending frequency adjustment coefficient And the comparison parameter of the second preset health monitoring prompt information sending frequency adjustment coefficient Adjust the sending frequency of the health monitoring prompt information according to the comparison result, , and the specific process is as follows: If , then adjust the sending frequency of the health monitoring prompt information to , that is, the second health monitoring prompt information sending frequency, ; If , then adjust the sending frequency of the health monitoring prompt information to , that is, the second health monitoring prompt information sending frequency, ; If , then adjust the sending frequency of the health monitoring prompt information to , that is, the second health monitoring prompt information sending frequency, .

[0039] The present invention calculates the adjustment coefficient according to the real-time health assessment result and the physical health data information, realizes the dynamic adjustment of the health prompt information sending frequency, timely reflects the change of the health status of individual users, meets the health monitoring needs of users, improves the user experience, enhances the user participation and enthusiasm; at the same time, improves the early warning effect, helps users better cope with health problems, takes necessary actions in time, and prevents the occurrence of diseases.

[0040] S3. According to the average exercise frequency , judge whether to optimize the sending frequency of the health monitoring prompt information.

[0041] In the embodiment of the present invention, define the observation period as , the average exercise frequency represents the average number of exercises per day within the observation period ; at the same time, preset the average exercise frequency , compare the average exercise frequency with the preset average exercise frequency , and judge whether to optimize the sending frequency of the health monitoring prompt information according to the comparison result; In the third adjustment unit, if , it indicates that the current exercise frequency does not meet the preset standard, and it is necessary to optimize the sending frequency of the health monitoring prompt information to remind the user to pay more attention to their physical condition; then the sending frequency of the health monitoring prompt information is adjusted to , that is, the sending frequency of the third health monitoring prompt information, ; If , it indicates that the current exercise frequency meets the preset standard, and the current sending frequency of the health monitoring prompt information remains unchanged; then the sending frequency of the health monitoring prompt information is adjusted to , that is, the sending frequency of the third health monitoring prompt information, ; If , it indicates that the user's exercise condition is good and exceeds the preset standard, and it is necessary to optimize the sending frequency of the health monitoring prompt information to avoid excessive interruption to the user; then the sending frequency of the health monitoring prompt information is adjusted to , that is, the sending frequency of the third health monitoring prompt information, ; Among them, represents the first regulation coefficient; represents the second regulation coefficient.

[0042] The present invention adjusts the sending frequency of the prompt information according to the average exercise frequency, which can help users develop healthier living habits, make the health prompt information more targeted and effective, and improve the user's participation and enthusiasm for health management; optimizing the sending frequency of the health monitoring prompt information can improve the user's attention to health problems and help them better manage their health conditions.

[0043] S4. Combine the optimized sending frequency of the health monitoring prompt information , and at the same time, according to the individual's feedback information, establish a health intelligent tracking model to monitor and evaluate the individual's health status, provide early warnings, and effectively prevent chronic diseases and sudden diseases, etc.

[0044] In the embodiment of the present invention, the process of establishing the health intelligent tracking model is as follows:

[0045] Among them, represents the updated result; represents the optimized sending frequency of the health monitoring prompt information; represents the update coefficient; represents the current situation of the th body movement-related index; Indicates the probability that the ideal sleep duration situation meets the standard; Indicates the probability that the actual sleep duration situation meets the standard; Indicates the obstructive characteristics of external work pressure.

[0046] Based on the optimized sending frequency of prompt information and feedback information, the health intelligent tracking model established by the present invention provides a more personalized health management service, adjusts the health monitoring plan according to the actual needs and feedback of individuals; combined with the feedback information, the health intelligent tracking model can achieve more real-time health monitoring, timely discover health problems and adjust health management strategies, and improve the effect of health management; by deeply analyzing the health data of individuals with the help of the health intelligent tracking model, potential health problems and trends are discovered, and more targeted health management suggestions are provided for individuals.

[0047] Refer to the appendix Figure 2 , this embodiment provides a health monitoring system based on data analysis, including the following: Individual user data acquisition module, user health assessment module, health level classification module, sending frequency adjustment parameter determination module, sending frequency adjustment module, health intelligent tracking module; The individual user data acquisition module is responsible for acquiring and collecting the health-related data of individual users through sensor devices, health application programs or manual input methods, etc., including physiological indicators, exercise data, diet records, sleep conditions, etc.; The user health assessment module evaluates and analyzes the health data of individual users, generates the health assessment results of individual users, and helps users understand their own health conditions; The health level classification module divides the health conditions of individual users into different health levels according to the output results of the user health assessment module; The sending frequency adjustment parameter determination module calculates the sending frequency adjustment coefficient of health monitoring prompt information according to the output results of the health assessment neural network model and the health-related data information of the body; The sending frequency adjustment module is responsible for adjusting the sending frequency of health monitoring prompt information to ensure that the information sending frequency is suitable for the user's health condition and needs; The health intelligent tracking module monitors the health conditions of individuals by establishing a health intelligent tracking model according to the feedback information through the optimized sending frequency of health monitoring prompt information; Refer to the appendix Figure 3 , the sending frequency adjustment module includes a first adjustment unit, a second adjustment unit, and a third adjustment unit; The first adjustment unit determines the initial sending frequency of health monitoring prompt information according to the user's health assessment results and health level classification; The second adjustment unit adjusts the sending frequency of the health monitoring prompt information according to the comparison result of the comparison parameter between the sending frequency adjustment coefficient of the health monitoring prompt information and the preset sending frequency adjustment coefficient of the health monitoring prompt information; The third adjustment unit compares the average exercise frequency with the preset average exercise frequency, and determines whether to optimize the sending frequency of the health monitoring prompt information according to the comparison result.

[0048] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a machine for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0049] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0051] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0052] The above content is only for explaining the technical idea of the present invention and cannot be used to limit the protection scope of the present invention. Any modification made on the basis of the technical solution in accordance with the technical idea proposed by the present invention falls within the protection scope of the claims of the present invention.

Claims

1. A health monitoring method based on data analysis, characterized in that: The following steps are involved: Step S1. Collect health data of individual users according to sensor equipment, establish a health assessment neural network model, obtain real-time health assessment results of individual users, and grade the health conditions of individual users; Step S2. Calculate the frequency adjustment coefficient of sending health monitoring prompt information according to the output results of the health assessment neural network model and the health-related data information; Step S3. Based on the average exercise frequency obtained, determine whether to optimize the frequency of sending health monitoring prompt information; Step S4. By optimizing the frequency of sending health monitoring reminder information and based on the feedback information, a health intelligent tracking model is established to monitor and evaluate the health status of the individual.

2. A health monitoring method based on data analysis according to claim 1, characterized in that: The step S1 specifically includes: The health assessment neural network model includes an input layer, an intelligent analysis layer, an evaluation layer, and an output layer; the input health indicator characteristic data information is analyzed in the intelligent analysis layer, and the output results are passed to the evaluation layer, and the output results of the intelligent analysis layer are optimized in the evaluation layer, and the final analysis results are output by the output layer.

3. A health monitoring method based on data analysis according to claim 1, characterized in that: In step S1, the individual health conditions are graded and the frequency of sending health monitoring prompt information is preset; the health grade is set For level three, , including level 1, i.e. healthy state, level 2, i.e. sub-health state, level 3, i.e. unhealthy state; health assessment results at different health levels The probability distribution function of ,in: , Indicates health level The prior probability of Represents the index of health level; the health level with the largest posterior probability is selected as the individual's health level, .

4. A health monitoring method based on data analysis according to claim 3, characterized in that: The step S1 specifically includes: The frequency of sending basic health monitoring reminder information is predefined as , the minimum frequency of sending health monitoring reminder messages is , the maximum frequency of sending health monitoring reminder messages is ; when When the first health monitoring reminder message is sent, set the frequency to ,but , Indicates the adjustment coefficient when in a healthy state; when When the first health monitoring reminder message is sent, set the frequency to ,but , Indicates the adjustment coefficient when in a sub-healthy state; when When the first health monitoring reminder message is sent, set the frequency to ,but , Indicates the adjustment coefficient when it is in an unhealthy state.

5. The health monitoring method based on data analysis according to claim 1, characterized in that: The step S2 specifically includes: Send frequency adjustment coefficient according to health monitoring prompt information The health monitoring prompt information sending frequency adjustment coefficient is compared with the preset health monitoring prompt information sending frequency adjustment coefficient to adjust the health monitoring prompt information sending frequency to obtain the adjusted second health monitoring prompt information sending frequency. .

6. The health monitoring method based on data analysis according to claim 1, characterized in that: In step S2, the comprehensive sports health score Through the activation function Mapping is performed to obtain the frequency adjustment coefficient of sending health monitoring prompt information , the specific process is as follows: in, represents the constant adjustment coefficient; Indicates the interference coefficient that affects the health monitoring prompt information.

7. The health monitoring method based on data analysis according to claim 5, characterized in that: The step S3 specifically includes: Preset average exercise frequency , compare the average motion frequency with the preset average motion frequency Make a comparison; if , then adjust to the third health monitoring reminder information sending frequency , ; if , then adjust to the third health monitoring reminder information sending frequency , that is, the frequency of sending the third health monitoring reminder information, ; if , then adjust to the third health monitoring reminder information sending frequency , that is, the frequency of sending the third health monitoring reminder information, ; in, represents the first control coefficient; Represents the second control coefficient.

8. The health monitoring method based on data analysis according to claim 1, characterized in that: The step S4 specifically includes: in, Indicates the updated result; Indicates the optimized frequency of sending health monitoring reminder information; represents the update coefficient; Indicates The current status of physical activity related indicators; An update function that represents the status of indicators related to the user's body movement; Indicates the probability that the ideal sleep duration meets the standard; Indicates the probability that the actual sleep duration meets the standard; Indicates the hindering characteristics of external work pressure.

9. A health monitoring system based on data analysis, applied to the health monitoring method based on data analysis according to claim 1, characterized in that: Includes the following: Individual user data acquisition module, user health assessment module, health level classification module, transmission frequency adjustment parameter determination module, transmission frequency adjustment module, health intelligent tracking module; The individual user data acquisition module is responsible for acquiring and collecting health-related data of individual users through sensor devices; The user health assessment module assesses and analyzes the health data of individual users and generates health assessment results for individual users; The health level classification module classifies the health status of individual users into different health levels according to the output results of the user health assessment module; The sending frequency adjustment parameter determination module calculates the health monitoring prompt information sending frequency adjustment coefficient according to the output result of the health assessment neural network model and the physical health related data information; The sending frequency adjustment module is responsible for adjusting the sending frequency of the health monitoring prompt information to ensure that the frequency of information sending is suitable for the health status and needs of the user; The health intelligent tracking module establishes a health intelligent tracking model according to the feedback information by optimizing the sending frequency of the health monitoring prompt information.

10. A health monitoring system based on data analysis according to claim 9, characterized in that: Includes the following: The transmission frequency adjustment module includes a first adjustment unit, a second adjustment unit, and a third adjustment unit; A first adjustment unit determines the frequency of sending the initial health monitoring prompt information according to the health assessment result and health level classification of the user; The second adjustment unit adjusts the health monitoring prompt information sending frequency according to a comparison result of the health monitoring prompt information sending frequency adjustment coefficient and a preset health monitoring prompt information sending frequency adjustment coefficient comparison parameter; The third adjustment unit compares the average exercise frequency with the preset average exercise frequency, and determines whether to optimize the frequency of sending the health monitoring prompt information according to the comparison result.

Images