A human body movement health monitoring system and method

Abstract

The present invention discloses a human motion health monitoring system and method thereof, which relate to the technical field of motion health monitoring, and include a perception module, wherein the perception module is used to collect a user's motion and physiological data and environmental data; a behavior analysis module, wherein the behavior analysis module includes an analysis unit and a personalized guidance unit, wherein the analysis unit is used to analyze the user's daily behavior pattern according to the information of the perception module, and then identify the user's motion habits and health trends; the personalized guidance unit is used to formulate a motion strategy according to the result of the analysis unit; the optimization processing module is used to optimize the result of the behavior analysis module according to the information of the perception module; customized health and motion suggestions can be provided according to the user's motion habits and health data, thereby improving the applicability and effect of the suggestions; and intervention measures can be provided in advance according to the user's historical motion trends and health risks to prevent potential health problems.

Description

Technical Field

[0001] The present invention relates to the technical field of sports health monitoring, and more specifically, to a human sports health monitoring system and method thereof. Background Art

[0002] Sports health monitoring system is a device that uses various sensors and data processing technologies to monitor and analyze human movement and health conditions. It can help users understand their exercise habits, health conditions, and potential health risks. It is mainly composed of various sensors, such as accelerometers: measuring the acceleration of movement, often used to detect the number of steps and movement types; gyroscopes: measuring rotational movement, assisting in identifying movement direction and posture; heart rate sensors: monitoring heart rate, assessing exercise intensity and cardiovascular health; skin resistance sensors: monitoring changes in skin resistance, which may be related to stress levels; environmental sensors: such as temperature and humidity sensors, monitoring external environmental conditions; GPS: used to locate and track movement paths; microcontrollers: processing sensor data and executing algorithms; storage units: storing data for analysis; Bluetooth for connecting or implementing data transmission; user interfaces and analysis software.

[0003] By collecting users' exercise and physiological data in real time, such as steps, heart rate, exercise type, etc., the system calculates users' exercise habits, health status and potential health risks, helping them manage their health status.

[0004] However, in actual use, users have different exercise habits and health needs, making it difficult to provide personalized advice and guidance, and it is also difficult to accurately predict users' future exercise trends and health risks as needed in order to intervene in a timely manner. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a human body movement health monitoring system and method.

[0006] The present invention provides a human body movement health monitoring system and method thereof, comprising:

[0007] A perception module, the perception module is used to collect the user's motion and physiological data and environmental data;

[0008] The behavior analysis module includes an analysis unit and a personalized guidance unit. The analysis unit is used to analyze the user's daily behavior pattern according to the information of the perception module, and then identify the user's exercise habits and health trends, specifically:

[0009] Obtain the user's exercise habit index information and health index information for the previous month of the current time period;

[0010] All indicators are standardized to obtain a data set of exercise habit history values ​​[Q1, Q2, ..., Q δ ], and a dataset of health history values ​​[W1, W2, …, W δ ];

[0011] According to the formula Calculate and obtain the user's exercise habit score T for the month before the current time period, where q is the number of data in the data set of exercise habit history values, that is, the number of exercise habit indicators, ω δ is the weight coefficient of the δth exercise habit history value;

[0012] According to the formula Calculate and obtain the user's health score T for the previous month of the current time period, where y is the number of data in the health history data set, that is, the number of health indicators, μ δ is the weight coefficient of the δth exercise habit history value;

[0013] According to the formula R = β*T + (1-β)*Y, the user's comprehensive health score R of the previous month is calculated, where β is the evaluation coefficient set in advance;

[0014] Transmitting the user's comprehensive health score R of the previous month to the personalized guidance unit;

[0015] The personalized guidance unit is used to formulate a movement strategy according to the result of the analysis unit;

[0016] An optimization processing module, wherein the optimization processing module is used to optimize the results of the behavior analysis module according to the information of the perception module.

[0017] Preferably, the specific working mode of the personalized guidance unit is as follows:

[0018] Set a comprehensive health score threshold in advance;

[0019] Obtain the difference ΔR between the user's comprehensive health score R last month and the comprehensive health score threshold;

[0020] Divide the difference ΔR by 2 to get the difference in exercise habits. and health difference

[0021] Exercise habit difference Divide by the weight coefficient of the number of steps in the exercise habit score to obtain the step difference K1;

[0022] Difference based on exercise habits Divide by the weight coefficient of exercise time in exercise habit score to get the exercise time gap K2;

[0023] The step difference K1 and exercise time difference K2 are transmitted to the user's mobile terminal through signals, and a new step difference and new exercise time for the day are set for the user. The new step difference is the current step number plus the step difference K1, and the new exercise time is the current exercise time plus the exercise time difference.

[0024] Preferably, the personalized guidance unit is further used to provide sleep advice to the user according to the result of the analysis unit, specifically:

[0025] The health difference Divide by the weight coefficient of sleep quality in the health score to get the sleep quality gap K3;

[0026] Determine whether the current sleep quality gap K3 is a positive number or a negative number. If a positive value indicates that the user's sleep time is below the target level, a negative value indicates that the user's sleep time exceeds the target level.

[0027] If the user's sleep time is lower than the target level, information suggesting increasing sleep is generated and transmitted to the user. If it is a negative value, the user may be sleeping too much, and the user is suggested to reduce sleep time or improve sleep efficiency.

[0028] Preferably, the personalized guidance unit is also used to predict the user's future movement trends and health risks and intervene in advance, specifically:

[0029] According to the formula Get the user's expected comprehensive health score R n , where K represents the size of the moving average window, that is, the number of past time points considered, and R t-f represents the comprehensive health score at time point tf, where f, ranges from 1 to k;

[0030] A threshold of expected comprehensive health score is set in advance. If the user's expected comprehensive health score R n If the score is less than the expected comprehensive health score threshold, an alarm signal is generated and transmitted to the user's mobile terminal.

[0031] Preferably, the specific working mode of the optimization processing module is as follows:

[0032] Get the deviation P1 of the temperature value one month before the current time period;

[0033] Obtain the deviation P2 of the humidity value one month before the current time period;

[0034] Obtain the deviation P3 of the air quality index (AQI) one month before the current time period;

[0035] Obtain the deviation P4 of the ultraviolet index (UVI) one month before the current time period;

[0036] Obtain the deviation P5 of the wind speed one month before the current time period;

[0037] Get the maximum deviation of the temperature value, humidity value, air quality index, ultraviolet index and wind speed in the current time period, which are marked as Pmax1, Pmax2, Pmax3, Pmax4 and Pmax5 respectively;

[0038] According to the formula Calculate and obtain comprehensive environmental impact factors;

[0039] According to the formula LA=LE+M, the comprehensive impact factor LA is calculated, where M is the weather impact factor;

[0040] The comprehensive influencing factor LA is brought into the behavior analysis module for adjustment.

[0041] Preferably, the optimization processing module is also used to optimize the prediction result of the personalized guidance unit, specifically:

[0042] Obtain the uncertainty U of the user's historical indicators;

[0043] According to the formula X = e -θ*U , calculate and obtain the influencing factor X of the user's expected comprehensive health score;

[0044] According to the formula R X =R n *X, calculate and obtain the optimized expected comprehensive health score R X ;

[0045] The optimized expected comprehensive health score R X Transmitted to the personalized guidance unit for further judgment.

[0046] Preferably, the uncertainty U of the user's historical indicator is obtained as follows:

[0047] Get the average values ​​of the user's historical step count, heart rate, and exercise frequency, marked as μ1, μ2, and μ3 respectively;

[0048] The standard deviations of the user's historical steps, heart rate, and exercise frequency are obtained and marked as μ4, μ5, and μ6 respectively;

[0049] According to the formula The uncertainty U of the user's historical indicators is obtained, where τ is an integer exponent used to control the impact of different indicators on the uncertainty of the user's historical indicators.

[0050] Preferably, the value of τ is determined as follows:

[0051] In the initial case, that is, if all indicators are equally important for the final uncertainty index U, τ is equal to 1, so that the geometric mean becomes the arithmetic mean;

[0052] When there are range differences among the number of steps, heart rate, and exercise frequency, τ is adjusted accordingly.

[0053] Preferably, the optimization processing module is also used to measure the delay impact of data processing, specifically:

[0054] Obtain the calculation delay reduction value σ1, the data processing efficiency value σ2, the network delay improvement σ3 and the segment delay σ4;

[0055] According to the formula Ln=(σ1*∈1)+(σ2*∈2)+(σ3*∈3)+(σ4*∈4), the data impact factor Ln is obtained, and the data impact factor Ln is multiplied by the optimized expected comprehensive health score R X The further adjusted expected comprehensive health score is obtained and transmitted to the personalized guidance unit for judgment.

[0056] Preferably, ∈1, ∈2, ∈3 and ∈4 are preset weights, and the specific value determination method is:

[0057] The variances of the computational delay reduction value, the data processing efficiency value, the network delay improvement, and the segment delay are obtained, and the standardized value of the variance of each indicator is calculated, and the standardized value of the variance is used as a weight.

[0058] Beneficial effects: Customized health and exercise recommendations can be provided based on the user's exercise habits and health data to improve the applicability and effectiveness of the recommendations. Intervention measures can also be provided in advance to prevent potential health problems based on the user's historical exercise trends and health risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flow chart of the monitoring system of the present invention. DETAILED DESCRIPTION

[0060] like Figure 1As shown: A human motion health monitoring system and method thereof, including: It should be noted that it is a device that uses various sensors and data processing technologies to monitor and analyze human motion and health conditions, which can help users understand their exercise habits, health conditions and potential health risks; it is mainly composed of various sensors, such as accelerometers: measuring the acceleration of motion, often used to detect the number of steps and motion types; gyroscopes: measuring rotational motion, assisting in identifying the direction and posture of motion; heart rate sensors: monitoring heart rate, assessing exercise intensity and cardiovascular health; skin resistance sensors: monitoring skin resistance changes, which may be related to stress levels; environmental sensors: such as temperature and humidity sensors, monitoring external environmental conditions; GPS: used to locate and track motion paths; microcontrollers: processing sensor data and executing algorithms; storage units: storing data for analysis; Bluetooth for connecting or implementing data transmission; user interfaces and analysis software;

[0061] By collecting users' exercise and physiological data in real time, such as steps, heart rate, exercise type, etc., the system calculates users' exercise habits, health status and potential health risks, helping them manage their health status.

[0062] However, in actual use, users have different exercise habits and health needs, making it difficult to provide personalized advice and guidance, and it is difficult to accurately predict users' future exercise trends and health risks as needed, so as to intervene in a timely manner;

[0063] This technical solution can provide customized health and exercise suggestions based on the user's exercise habits and health data, improving the applicability and effectiveness of the suggestions; and can provide intervention measures in advance to prevent potential health problems based on the user's historical exercise trends and health risks;

[0064] A sensing module, which is used to collect the user's motion and physiological data and environmental data; it should be noted that the motion data includes the number of steps, heart rate, sleep quality, etc., the environmental data includes temperature and humidity, etc., and the user's physiological data includes the user's blood pressure and BMI index (height-to-weight ratio), etc.;

[0065] The behavior analysis module includes an analysis unit and a personalized guidance unit. The analysis unit is used to analyze the user's daily behavior pattern according to the information of the perception module, and then identify the user's exercise habits and health trends, specifically:

[0066] Obtain the user's exercise habit index information and health index information for the previous month of the current time period; it should be noted that, in this embodiment, the exercise habit index information may be the number of steps, exercise time and exercise frequency, and the health index information may be the user's heart rate, sleep quality, blood pressure and BMI index, specifically a data set of each index recorded in days, a month is 30 days, so each index information is a data set consisting of 30 data;

[0067] It should also be noted that the frequency of exercise can be obtained by dividing the number of exercise days by the total number of days, and the quality of sleep can be obtained by dividing the sleep duration by the recommended sleep duration;

[0068] All indicators are standardized to obtain a data set of exercise habit history values ​​[Q1, Q2, ..., Q δ ], and a dataset of health history values ​​[W1, W2, …, W δ ]; It should be noted that standardization can eliminate the influence of different dimensions;

[0069] It should also be noted that the standardization process can be:

[0070] According to the formula Calculate the standard value of the j-th day of the δ-th exercise habit index information in the month before the current time period of the user; where δX i is the i-th value in the δ-th exercise habit index information data set, min(δX i ) represents the minimum value in the δth exercise habit index information data set, max(δX i ) represents the maximum value in the δth exercise habit index information data set. In this embodiment, δX represents the δth exercise habit index information. There are three exercise habit index information, so 1X represents the number of steps, 2X represents the exercise time, and 3X represents the exercise frequency;

[0071] For example, if the number of steps taken by the user on the first day of the month before the current time period is 5000, then 1X1 is the first indicator information data set, that is, the first value in the step indicator data set. The maximum number of steps taken by the user on one day in the month before the current time period is 10000, and the minimum number of steps taken on one day is 3000. Then min(1X1) is 3000, and max(1X1) is 10000.

[0072] Then according to the formula Calculate and obtain the δth exercise habit history value Q δ , where n is 30, which is the number of data in the dataset;

[0073] Similarly, the health history values ​​[W1, W2, …, W δ ];

[0074] According to the formula Calculate and obtain the user's exercise habit score T for the month before the current time period, where q is the number of data in the data set of exercise habit history values, that is, the number of exercise habit indicators, ω δ is the weight coefficient of the δth exercise habit history value; it should be noted that, in this embodiment, the number of q is three, Q1 is the step history value, Q2 is the exercise time history value, and Q3 is the exercise frequency history value; it should also be noted that, in this embodiment, the corresponding weight coefficients are ω1, ω2 and ω3, and the specific values ​​are obtained according to the evaluation of the staff. Statistical methods (such as principal component analysis PCA) can be used to analyze the correlation between different indicators and reduce the influence of multicollinearity to determine. In this embodiment, the values ​​of ω1, ω2 and ω3 can be 0.283, 0.398 and 0.319;

[0075] According to the formula Calculate and obtain the user's health score T for the previous month of the current time period, where y is the number of data in the health history data set, that is, the number of health indicators, μ δ is the weight coefficient of the δth exercise habit history value; it should be noted that, in this embodiment, the number of y is four, of which W1 is the heart rate history value, W2 is the sleep quality history value, W3 is the blood pressure history value, and W4 is the BMI index history value; it should also be noted that, in this embodiment, the corresponding weight coefficients are μ1, μ2, μ3 and μ4, and the specific values ​​are obtained according to the evaluation of the staff. Statistical methods (such as principal component analysis PCA) can be used to analyze the correlation between different indicators and reduce the influence of multicollinearity to determine. In this embodiment, the values ​​of μ1, μ2, μ3 and μ4 can be 0.279, 0.323, 0.105 and 0.293;

[0076] According to the formula R=β*T+(1-β)*Y, the comprehensive health score R of the user last month is calculated, where β is a pre-set evaluation coefficient; it should be noted that in this embodiment, the value of β is between 0 and 1. In the initial case, β is the system recommended value set by the staff, and the value can be 0.582;

[0077] It should also be noted that this calculation method can reflect the user's behavior and health trends over a period of time, rather than just based on short-term performance, and reduce the impact of single-day fluctuations on the score, providing a more stable score that is suitable for health conditions that require long-term effects. It is updated monthly to reflect the user's latest changes, which can help provide continuous motivation in the subsequent process of encouraging users to form long-term behavioral changes;

[0078] Transmitting the user's comprehensive health score R of the previous month to the personalized guidance unit;

[0079] The personalized guidance unit is used to formulate an exercise strategy according to the results of the analysis unit; it should be noted that customized exercise and health suggestions are provided by deeply analyzing user behavior;

[0080] The optimization processing module is used to optimize the results of the behavior analysis module according to the information of the perception module. It should be noted that the speed and accuracy of the data processing of the behavior analysis module can be improved, and errors and misjudgments can be reduced.

[0081] As an optional embodiment: the specific working mode of the personalized guidance unit is as follows:

[0082] A comprehensive health score threshold is set in advance; it should be noted that the comprehensive health score threshold is obtained by calculating the average value of all users of the appropriate age;

[0083] Obtain the difference ΔR between the user's comprehensive health score R last month and the comprehensive health score threshold;

[0084] Divide the difference ΔR by 2 to get the difference in exercise habits. and health difference It should be noted that in this embodiment, the purpose is to improve the user's exercise habits and health status in equal proportion, so the difference ΔR is divided by 2 when taking the value. Other equal divisions can also be performed during actual use;

[0085] Exercise habit difference Divide by the weight coefficient of the number of steps in the exercise habit score to obtain the step difference K1; it should be noted that, in this embodiment, the weight coefficient of the number of steps in the exercise habit score is ω1, and the value can be 0.283;

[0086] Difference based on exercise habits Divide by the weight coefficient of the exercise time in the exercise habit score to obtain the exercise time difference K2; it should be noted that, in this embodiment, the weight coefficient of the number of steps in the exercise habit score is ω2, which can be 0.398;

[0087] The step difference K1 and the exercise time difference K2 are transmitted to the user's mobile phone terminal through a signal, and a new step difference and a new exercise time for the day are set for the user. The new step difference is the current step plus the step difference K1, and the new exercise time is the current exercise time plus the exercise time difference. It should be noted that the exercise strategy can be adjusted according to the results of the analysis unit to better help the user achieve a healthy state.

[0088] As an optional embodiment: the personalized guidance unit is further used to provide sleep suggestions to the user according to the result of the analysis unit, specifically:

[0089] The health difference Divide by the weight coefficient of sleep quality in the health score to obtain the sleep quality gap K3; it should be noted that the weight coefficient of sleep quality in the health score is μ2, which can be 0.323;

[0090] Determine whether the current sleep quality gap K3 is a positive number or a negative number. If a positive value indicates that the user's sleep time is below the target level, a negative value indicates that the user's sleep time exceeds the target level.

[0091] If the user's sleep time is lower than the target level, a message suggesting increasing sleep is generated and transmitted to the user. If it is a negative value, the user may sleep too much, and the user is suggested to reduce sleep time or improve sleep efficiency. It should be noted that personalized sleep adjustment suggestions can be made for the user based on the difference in their sleep quality.

[0092] As an optional embodiment: the personalized guidance unit is also used to predict the user's future movement trends and health risks and intervene in advance, specifically:

[0093] According to the formula Get the user's expected comprehensive health score R n , where K represents the size of the moving average window, that is, the number of past time points considered, and R t-f represents the comprehensive health score at time point tf, where f ranges from 1 to k; it should be noted that by calculating the average value, this formula can smooth short-term fluctuations, reduce the impact of outliers, and show long-term trends more clearly. It can be used as a predictor of future health scores, assuming that future trends will continue the average performance of the past k time points;

[0094] A threshold of expected comprehensive health score is set in advance. If the user's expected comprehensive health score R n If the score is less than the expected comprehensive health score threshold, an alarm signal is generated and transmitted to the user's mobile terminal.

[0095] As an optional embodiment: the specific working mode of the optimization processing module is as follows:

[0096] Get the deviation P1 of the temperature value one month before the current time period;

[0097] Obtain the deviation P2 of the humidity value one month before the current time period;

[0098] Obtain the deviation P3 of the air quality index (AQI) one month before the current time period;

[0099] Obtain the deviation P4 of the ultraviolet index (UVI) one month before the current time period;

[0100] The deviation P5 of the wind speed in the previous month of the current time period is obtained; it should be noted that the above deviations are calculated by subtracting the absolute value of the corresponding ideal threshold from the average index in the previous month of the current time period. For example, the deviation P1 is the average temperature value in the previous month of the current time period minus the absolute value of the temperature threshold;

[0101] Get the maximum deviation of the temperature value, humidity value, air quality index, ultraviolet index and wind speed in the current time period, which are marked as Pmax1, Pmax2, Pmax3, Pmax4 and Pmax5 respectively;

[0102] According to the formula The comprehensive environmental impact factor is obtained by calculation; it should be noted that the calculation method based on actual deviation and historical data reduces the influence of subjective judgment and improves the objectivity of the assessment. The IEF can be dynamically updated according to real-time environmental data to reflect the current environmental conditions in a timely manner;

[0103] According to the formula LA=LE+M, the comprehensive impact factor LA is calculated, where M is the weather impact factor;

[0104] The comprehensive influencing factor LA is brought into the behavior analysis module for adjustment. It should be noted that the influencing factor can be dynamically adjusted in combination with the environment and weather monitoring data, timely suggestions and warnings can be provided, and the impact of the environment and weather on the user's sports performance and health status can be more objectively evaluated.

[0105] As an optional embodiment: the optimization processing module is further used to optimize the prediction result of the personalized guidance unit, specifically: it should be noted that although the personalized guidance unit can make predictions based on historical data, in actual use, user behavior may be uncertain and difficult to accurately predict;

[0106] Obtain the uncertainty U of the user's historical index; it should be noted that, in this embodiment, a nonlinear combination method can be considered to integrate different uncertainty indicators to form a comprehensive uncertainty index;

[0107] According to the formula X = e -θ*U , calculate and obtain the influencing factor X of the user's expected comprehensive health score; it should be noted that e is the base of the natural logarithm, and θ is an adjustment parameter used to control the degree of influence of uncertainty on the influencing factor. In this embodiment, the value of θ can be 1.023;

[0108] According to the formula RX =R n *X, calculate and obtain the optimized expected comprehensive health score R X ;

[0109] The optimized expected comprehensive health score R X Transmitted to the personalized guidance unit for further judgment. It should be noted that the contribution of different indicators to the uncertainty of user behavior can be comprehensively considered to optimize the user's expected comprehensive health score. When the importance of each indicator is difficult to quantify and compare, a method for balancing the impact of each indicator is provided.

[0110] As an optional embodiment: the uncertainty U of the user's historical indicator is obtained as follows:

[0111] Get the average values ​​of the user's historical step count, heart rate, and exercise frequency, marked as μ1, μ2, and μ3 respectively;

[0112] The standard deviations of the user's historical steps, heart rate, and exercise frequency are obtained and marked as μ4, μ5, and μ6 respectively;

[0113] According to the formula The uncertainty U of the user's historical indicators is obtained, where τ is an integer exponent used to control the impact of different indicators on the uncertainty of the user's historical indicators.

[0114] As an optional embodiment: the value of τ is determined as follows:

[0115] In the initial case, that is, if all indicators are equally important for the final uncertainty index U, τ is equal to 1, so that the geometric mean becomes the arithmetic mean;

[0116] When there are range differences in the number of steps, heart rate, and exercise frequency, τ is adjusted accordingly. It should be noted that if the variability of some indicators is large, a smaller τ value may be needed to reduce the impact of these indicators on the geometric mean. The range of indicators: For indicators with large range differences, τ may need to be adjusted to balance their contribution to the comprehensive index; the scale of indicators: If the scales of different indicators vary greatly, τ can be adjusted to reduce the impact of indicators with larger scales; experience or expert opinion: τ is selected based on experience or expert opinion. In this embodiment, τ is 1.023.

[0117] As an optional embodiment: the optimization processing module is also used to measure the delay impact of data processing, specifically:

[0118] The calculation delay reduction value σ1, data processing efficiency value σ2, network delay improvement σ3 and segment delay σ4 are obtained; it should be noted that the delay reduction value σ1 is obtained by calculating the delay reduction ratio before and after the introduction of edge computing, which can reflect the effect of edge computing on delay improvement. The data processing efficiency value σ2 is obtained by calculating the data processing efficiency of the edge node relative to the central server. The network delay improvement σ3 measures the impact of edge computing on network delay by calculating the network delay improvement. The segment delay σ4 is obtained by measuring the total time required from data generation to data processing completion through end-to-end delay.

[0119] According to the formula Ln=(σ1*∈1)+(σ2*∈2)+(σ3*∈3)+(σ4*∈4), the data impact factor Ln is obtained, and the data impact factor Ln is multiplied by the optimized expected comprehensive health score R X The further adjusted expected comprehensive health score is obtained and transmitted to the personalized guidance unit for judgment. It should be noted that by evaluating the effect of edge computing technology on reducing data transmission delay, it is helpful to further optimize system performance.

[0120] As an optional embodiment: ∈1, ∈2, ∈3 and ∈4 are preset weights, and the specific value selection method is:

[0121] The variances of the computational delay reduction value, the data processing efficiency value, the network delay improvement, and the segment delay are obtained, and the standardized value of the variance of each indicator is calculated, and the standardized value of the variance is used as the weight. It should be noted that the method for calculating the standardized value of the variance of each indicator can be to divide the variance of a single indicator by the sum of the variances of all indicators.

[0122] How it works

[0123] It can provide customized health and exercise recommendations based on the user's exercise habits and health data to improve the applicability and effectiveness of the recommendations; and it can provide intervention measures in advance to prevent potential health problems based on the user's historical exercise trends and health risks.

[0124] The above are only preferred implementations of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical staff in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of this template.

Claims

1. A human body movement health monitoring system, characterized in that: include: A perception module, the perception module is used to collect the user's motion and physiological data and environmental data; The behavior analysis module includes an analysis unit and a personalized guidance unit. The analysis unit is used to analyze the user's daily behavior pattern according to the information of the perception module, and then identify the user's exercise habits and health trends, specifically: Obtain the user's exercise habit index information and health index information for the previous month of the current time period; All indicators are standardized to obtain a data set of exercise habit history values ​​[Q1, Q2, ..., Q δ ], and a dataset of health history values ​​[W1, W2, …, W δ ]; According to the formula Calculate and obtain the user's exercise habit score T for the month before the current time period, where q is the number of data in the data set of exercise habit history values, that is, the number of exercise habit indicators, ω δ is the weight coefficient of the δth exercise habit history value; According to the formula Calculate and obtain the user's health score T for the previous month of the current time period, where y is the number of data in the health history data set, that is, the number of health indicators, μ δ is the weight coefficient of the δth health history value; According to the formula R = β*T + (1-β)*Y, the user's comprehensive health score R of the previous month is calculated, where β is the evaluation coefficient set in advance; Transmitting the user's comprehensive health score R of the previous month to the personalized guidance unit; The personalized guidance unit is used to formulate a movement strategy according to the result of the analysis unit; An optimization processing module, the optimization processing module is used to optimize the result of the behavior analysis module according to the information of the perception module; The specific working mode of the optimization processing module is as follows: Get the deviation P1 of the temperature value one month before the current time period; Obtain the deviation P2 of the humidity value one month before the current time period; Obtain the deviation P3 of the air quality index (AQI) one month before the current time period; Obtain the deviation P4 of the ultraviolet index (UVI) one month before the current time period; Obtain the deviation P5 of the wind speed one month before the current time period; Get the maximum deviation of the temperature value, humidity value, air quality index, ultraviolet index and wind speed in the current time period, which are marked as Pmax1, Pmax2, Pmax3, Pmax4 and Pmax5 respectively; According to the formula Calculate and obtain comprehensive environmental impact factors; According to the formula LA=LE+M, the comprehensive impact factor LA is calculated, where M is the weather impact factor; The comprehensive influencing factor LA is brought into the behavior analysis module for adjustment.

2. A human body movement health monitoring system according to claim 1, characterized in that: The specific working mode of the personalized guidance unit is as follows: Set a comprehensive health score threshold in advance; Obtain the difference ΔR between the user's comprehensive health score R last month and the comprehensive health score threshold; Divide the difference ΔR by 2 to get the difference in exercise habits. and health difference Exercise habit difference Divide by the weight coefficient of the number of steps in the exercise habit score to obtain the step difference K1; Difference based on exercise habits Divide by the weight coefficient of exercise time in exercise habit score to get the exercise time gap K2; The step difference K1 and the exercise time difference K2 are transmitted to the user's mobile terminal through signals, and a new step number and new exercise time for the day are set for the user. The new step number is the current step number plus the step difference K1, and the new exercise time is the current exercise time plus the exercise time difference.

3. A human body movement health monitoring system according to claim 2, characterized in that: The personalized guidance unit is further used to provide sleep suggestions to the user according to the result of the analysis unit, specifically: The health difference Divide by the weight coefficient of sleep quality in the health score to get the sleep quality gap K3; Determine whether the current sleep quality gap K3 is a positive number or a negative number. If a positive value indicates that the user's sleep time is below the target level, a negative value indicates that the user's sleep time exceeds the target level. If the user's sleep time is lower than the target level, information suggesting increasing sleep is generated and transmitted to the user. If it is a negative value, the user may be sleeping too much, and the user is suggested to reduce sleep time or improve sleep efficiency.

4. A human body movement health monitoring system according to claim 3, characterized in that: The personalized guidance unit is also used to predict the user's future movement trends and health risks and intervene in advance, specifically: According to the formula Get the user's expected comprehensive health score R n , where K represents the size of the moving average window, that is, the number of past time points considered, and R t-f represents the comprehensive health score at time point tf, where f, ranges from 1 to k; A threshold of expected comprehensive health score is set in advance. If the user's expected comprehensive health score R n If the score is less than the expected comprehensive health score threshold, an alarm signal is generated and transmitted to the user's mobile terminal.

5. A human body movement health monitoring system according to claim 4, characterized in that: The optimization processing module is also used to optimize the prediction result of the personalized guidance unit, specifically: Obtain the uncertainty U of the user's historical indicators; According to the formula X = e -θ*U , calculate and obtain the influencing factor X of the user's expected comprehensive health score, e is the base of the natural logarithm, and θ is an adjustment parameter used to control the degree of influence of uncertainty on the influencing factor; According to the formula R X =R n *X, calculate and obtain the optimized expected comprehensive health score R X ; The optimized expected comprehensive health score R X Transmitted to the personalized guidance unit for further judgment.

6. A human body movement health monitoring system according to claim 5, characterized in that: The uncertainty U of the user's historical indicator is obtained as follows: Get the average values ​​of the user's historical step count, heart rate, and exercise frequency, marked as μ1, μ2, and μ3 respectively; The standard deviations of the user's historical steps, heart rate, and exercise frequency are obtained and marked as μ4, μ5, and μ6 respectively; According to the formula The uncertainty U of the user's historical indicators is obtained, where τ is an integer exponent used to control the impact of different indicators on the uncertainty of the user's historical indicators.

7. A human body movement health monitoring system according to claim 6, characterized in that: The value of τ is determined as follows: In the initial case, that is, if all indicators are equally important for the final uncertainty index U, τ is equal to 1, so that the geometric mean becomes the arithmetic mean; When there are range differences among the number of steps, heart rate, and exercise frequency, τ is adjusted accordingly.

8. A human body movement health monitoring system according to claim 5, characterized in that: The optimization processing module is also used to measure the delay impact of data processing, specifically: Obtain the calculation delay reduction value σ1, the data processing efficiency value σ2, the network delay improvement σ3 and the segment delay σ4; According to the formula Ln=(σ1*∈1)+(σ2*∈2)+(σ3*∈3)+(σ4*∈4), the data impact factor Ln is obtained, and the data impact factor Ln is multiplied by the optimized expected comprehensive health score R X Obtaining a further adjusted expected comprehensive health score, and transmitting the score to the personalized guidance unit for judgment; The ∈1, ∈2, ∈3 and ∈4 are preset weights, and the specific value selection method is: The variances of the computational delay reduction value, the data processing efficiency value, the network delay improvement, and the segment delay are obtained, and the standardized value of the variance of each indicator is calculated, and the standardized value of the variance is used as a weight.

Images