Health risk assessment system based on multi-source data fusion analysis of smart wearable devices

Abstract

The present invention provides a health risk assessment system based on multi-source data fusion analysis of smart wearable devices, and relates to the technical field of health risk assessment. The present invention obtains motion data, physiological data and surrounding environment data of a wearer through a smart wearable device; analyzes the motion data to obtain motion health indicators, and analyzes the physiological data to obtain physiological health indicators; judges a target state as a rest state, a normal state and a motion state according to the surrounding environment data and an activity intensity index; generates a motion health assessment coefficient and a physiological health assessment coefficient according to the motion health indicators and the physiological health indicators; generates a target health state assessment coefficient according to the motion health assessment coefficient and the physiological health assessment coefficient, and completes a health assessment of each target state according to the target health state assessment coefficient; the present invention takes into account the differences in target states and completes an accurate and scientific assessment of the target state from an operational and physiological perspective.

Description

Technical Field

[0001] The present invention relates to the technical field of health risk assessment, and in particular to a health risk assessment system based on multi-source data fusion analysis of smart wearable devices. Background Art

[0002] In modern society, health issues are increasingly attracting people's attention, especially with the change of lifestyle, the incidence of insufficient exercise and chronic diseases is increasing year by year. Traditional health monitoring methods generally rely on regular physical examinations in hospitals, which often cannot meet the needs of individualized and real-time monitoring. This method not only has the problems of time lag and incomplete information, but also easily causes users to ignore their own health status. In addition, many existing wearable devices can only monitor exercise or physiological parameters individually, lack of comprehensive analysis of data from multiple sources, resulting in insufficient accuracy and effectiveness of health assessment. Therefore, how to reasonably integrate data from different sources to form a systematic health risk assessment is a technical problem that needs to be solved urgently.

[0003] With the rapid development of smart wearable technology, more and more devices are able to monitor the user's motion status, physiological parameters and surrounding environment information in real time. However, existing technologies are often limited to the analysis of a single data source and lack the deep integration and intelligent analysis of multi-source data. At the same time, the scientificity and rationality of the evaluation method also need to be strengthened to ensure that the evaluation results can truly reflect the user's health status. This makes the establishment of a scientific health risk assessment system that can integrate multi-faceted data an important and urgent research direction.

[0004] In the prior art, the publication number CN118940212A discloses a health risk assessment method and system based on multi-source data fusion analysis, which collects user behavior data and body data to evaluate changes in user body data; According to changes in body data, the user behavior is analyzed by support vector machine SVM, and health risk scores are scored and user health risks are judged through user behavior analysis; User behavior is predicted based on user body data, and user behavior time is counted, and the recommended exercise time is calculated with reference to the user health risk, and a comprehensive risk assessment is performed based on user behavior; Data is securely transmitted to the cloud through wireless transmission, and a report is generated. The prior art can accurately monitor the health status of users through multi-dimensional data collection and analysis, and provide real-time dynamic health risk assessment for users with cerebrovascular diseases through scoring and calculation of user health risks. However, the prior art still has shortcomings. First, the prior art only evaluates the target health status and ignores the differences between target states, which may lead to inaccurate and unreasonable evaluation results. For example, dividing the target state into rest, normal and exercise states, and using the same set of standards for health assessment for these three states does not conform to the actual situation. This approach ignores the significant differences in individual physiological and behavioral characteristics under different conditions, which may lead to misjudgment of health status. Secondly, when evaluating the impact of target activities on health, existing technologies consider too few factors and only focus on the single indicator of step count. This one-sided evaluation method ignores many other important health-influencing factors, resulting in an incomplete understanding of individual health status.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a health risk assessment system based on multi-source data fusion analysis of smart wearable devices to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A health risk assessment system based on multi-source data fusion analysis of smart wearable devices, the specific steps include:

[0009] A data acquisition module is used to obtain the wearer's motion data, physiological data and surrounding environment data through the smart wearable device;

[0010] A feature analysis module, used to analyze the motion data to obtain motion health indicators, and to analyze the physiological data to obtain physiological health indicators; the motion health indicators include: activity intensity index, gait balance index and calorie consumption index; the physiological health indicators include heart rate variability, blood pressure volatility and hypoxemia index;

[0011] A state judgment module is used to judge the target state according to the surrounding environment data and the activity intensity index, and the target state is a resting state, a normal state or a moving state;

[0012] A health assessment module is used to generate a sports health assessment coefficient and a physiological health assessment coefficient according to the sports health index and the physiological health index; generate a target health state assessment coefficient according to the sports health assessment coefficient and the physiological health assessment coefficient, and complete the health assessment of each target state according to the target health state assessment coefficient;

[0013] Furthermore, the motion data includes the target's three-axis acceleration, three-axis angular velocity, heat conversion coefficient and number of steps in the monitoring time period; the physiological data includes the target's adjacent heartbeat intervals, blood pressure, and blood oxygen value in the same monitoring time period; the surrounding environment data includes the ultraviolet intensity and wind speed at the location of the smart wearable device; the three-axis acceleration, three-axis angular velocity, number of steps, ultraviolet intensity and wind speed at the location of the smart wearable device are all collected by sensors in the smart wearable device; the three-axis takes the horizontal direction in front of the target's movement as Axis direction, The axis is 90 degrees to the left horizontally. Axis direction, vertically downward direction; the adjacent heartbeat intervals, blood pressure and blood oxygen values ​​are collected by medical instruments in the smart wearable device; the thermal conversion coefficient is 0.05 kcal / step.

[0014] Furthermore, the specific formula for obtaining the activity intensity index is:

[0015] ;

[0016] in, is the activity intensity index, For the Target time The acceleration in the axial direction, For the Target time The acceleration in the axial direction, For the Target time The acceleration in the axial direction, For the Target time Angular acceleration along the axis, For the Target time Angular acceleration along the axis, For the Target time Angular acceleration in the direction of the axis; is the index of the acceleration sampling time within the monitoring period, and , is the total number of acceleration sampling moments during the monitoring period, and the acceleration and angular acceleration are sampled simultaneously during the monitoring period; the specific formula for generating the gait balance index is:

[0017] ;

[0018] in, is the gait balance index, During the monitoring period, the target The variance of the acceleration in the axis direction, During the monitoring period, the target The mean value of the acceleration in the axial direction;

[0019] The specific formula used to generate the calorie expenditure index is:

[0020] ;

[0021] in, is the calorie consumption index, is the heat transfer coefficient, is the number of steps taken by the target during the monitoring period;

[0022] The specific formula used to generate heart rate variability is:

[0023] ;

[0024] in, is the heart rate variability, is the total number of heartbeats of the target during the monitoring period. For the The heartbeat and The interval between adjacent heartbeats, is the index of the heartbeat, and ;

[0025] The specific formula upon which blood pressure volatility is generated is:

[0026] ;

[0027] in, For blood pressure fluctuations, The total number of blood pressure tests during the monitoring period. For the The blood pressure value of the test, is the mean blood pressure of the target during the monitoring period, is the index of the number of blood pressure tests, and ;

[0028] The specific formula used to generate the hypoxemia index is:

[0029] ;

[0030] in, is the hypoxemia index, The total number of blood oxygen tests of the target during the monitoring period. For the The blood oxygen value of the test, is the index of the number of blood oxygen tests, and .

[0031] Furthermore, the specific logic for determining the target state is as follows: the ultraviolet intensity threshold at the location of the preset smart wearable device , wind speed threshold at the location of the smart wearable device and , , Activity Intensity Index gear , and , , if the ultraviolet intensity at the location of the smart wearable device is , wind speed at the location of the smart wearable device and activity intensity index , then the target is judged to be in a resting state. If the wind speed at the location of the smart wearable device is , activity intensity index , then the target is judged to be in motion; if the target is neither in rest nor in motion, then the target is judged to be in normal state.

[0032] Furthermore, the formula for generating the sports health assessment coefficient is:

[0033] ;

[0034] in, is the sports health assessment coefficient, is the activity intensity index, is the gait balance index, is the calorie consumption index, is the excessive activity intensity threshold;

[0035] The specific logic for generating the physiological health assessment coefficient is as follows:

[0036] ;

[0037] in, is the physiological health assessment coefficient, is the heart rate variability, For blood pressure fluctuations, It is the hypoxemia index.

[0038] Furthermore, the specific logic for generating the target health status evaluation coefficient is: generating the sports health evaluation coefficient and the physiological health evaluation coefficient according to the sports health index and the physiological health index, and the specific formula for generating the target health status evaluation coefficient is:

[0039] ;

[0040] actually, is the target health status assessment coefficient, is the sports health assessment coefficient, is the physiological health assessment coefficient, is the weight coefficient, which is set according to the target state. If the target is in a resting state, , , if the target is in normal state, then , If the target is in motion, , .

[0041] Furthermore, the specific logic for health assessment of each state of the target is as follows: preset target health state assessment threshold ,like , then the target is judged to be unhealthy. The target is judged as sub-healthy. , then the target is judged to be healthy.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention can significantly improve the accuracy of health assessment by setting different weight coefficients for the target's sports health coefficient and physiological health coefficient according to different target states (rest, normal and exercise), and formulate special assessment standards. It can reduce misjudgment caused by state differences, thus making health assessment more practical.

[0044] The present invention also takes into account calorie consumption, gait balance and activity intensity to generate an exercise health assessment coefficient that can comprehensively assess an individual's exercise health status; through this assessment coefficient, an important basis can be provided for the target's health status, thereby more effectively guiding health management and improving exercise effects.

[0045] The present invention specifically evaluates the target's sports health and physiological health separately and generates corresponding evaluation indicators. By independently analyzing these two aspects, the individual's health status can be understood more accurately. This effectively improves the overall health level. Based on this comprehensive two aspects, a comprehensive evaluation of the target's health status is performed. This evaluation method not only enhances the scientific nature of the evaluation, but also provides more targeted suggestions for health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0047] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0048] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0049] Example:

[0050] See also Figure 1 , the present invention provides a technical solution:

[0051] A health risk assessment system based on multi-source data fusion analysis of smart wearable devices, the specific steps include:

[0052] A data acquisition module is used to obtain the wearer's motion data, physiological data and surrounding environment data through the smart wearable device;

[0053] The motion data includes the target's three-axis acceleration, three-axis angular velocity, heat conversion coefficient and number of steps in the monitoring time period; the physiological data includes the target's adjacent heartbeat intervals, blood pressure, and blood oxygen value in the same monitoring time period; the surrounding environment data includes the ultraviolet intensity and wind speed at the location of the smart wearable device; the three-axis acceleration, three-axis angular velocity, number of steps, ultraviolet intensity and wind speed at the location of the smart wearable device are all collected by sensors in the smart wearable device; the three-axis horizontal direction in front of the target's movement is taken as Axis direction, The axis is 90 degrees to the left horizontally. Axis direction, vertically downward direction; the adjacent heartbeat intervals, blood pressure and blood oxygen values ​​are collected by medical instruments in the smart wearable device; the thermal conversion coefficient is 0.05 kcal / step.

[0054] A feature analysis module, used to analyze the motion data to obtain motion health indicators, and to analyze the physiological data to obtain physiological health indicators; the motion health indicators include: activity intensity index, gait balance index and calorie consumption index; the physiological health indicators include heart rate variability, blood pressure volatility and hypoxemia index;

[0055] The specific formula for obtaining the activity intensity index is:

[0056] ;

[0057] in, is the activity intensity index, For the Target time The acceleration in the axial direction, For the Target time The acceleration in the axial direction, For the Target time The acceleration in the axial direction, For the Target time Angular acceleration along the axis, For the Target time Angular acceleration along the axis, For the Target time Angular acceleration in the direction of the axis; is the index of the acceleration sampling time within the monitoring period, and , is the total number of acceleration sampling moments during the monitoring period, and the acceleration and angular acceleration are sampled simultaneously during the monitoring period;

[0058] The activity intensity index reflects the average activity intensity in a given time period. The larger the value, the higher the average activity intensity in a given time period. Reflects the total acceleration of the target in three-dimensional space. The larger the value, the greater the total acceleration of the target in three-dimensional space, the stronger the target activity, and the greater the activity intensity index; It represents the rotation intensity of an object in three-dimensional space. The larger the value, the higher the rotation intensity of the object in three-dimensional space, the stronger the target activity, and the greater the activity intensity index. This formula can help quantify and analyze an individual's exercise intensity, so as to better understand their exercise behavior and health level.

[0059] The specific formula used to generate the gait balance index is:

[0060] ;

[0061] in, is the gait balance index, During the monitoring period, the target The variance of the acceleration in the axis direction, During the monitoring period, the target The average value of the acceleration in the axial direction; the gait balance index reflects the degree of balance of the individual in gait. The closer the value is to 1, the more balanced the gait is. In gait analysis, The axis represents vertical movement (such as jumping up and down or the up and down movement when walking). Indicates the vertical acceleration during gait. The larger the value, the more powerful the gait. The variance of the acceleration in the axial direction can reflect the individual's balance ability when walking. If the acceleration in the axis direction changes greatly (for example, it fluctuates violently up and down), then the target The variance of the acceleration in the axial direction will be large, which indicates a lack of stability and coordination when walking.

[0062] The specific formula used to generate the calorie expenditure index is:

[0063] ;

[0064] in, is the calorie consumption index, is the heat transfer coefficient, is the number of steps taken by the target during the monitoring period;

[0065] The calorie consumption index reflects the target's calorie consumption during the monitoring period. The larger the value, the more calories the target consumes during the monitoring period; the heat conversion coefficient is 0.05 kcal / step, and the activity intensity index reflects the average activity intensity during a given period of time. The larger the value, the more calories the target consumes, and the greater the activity intensity index.

[0066] The specific formula used to generate heart rate variability is:

[0067] ;

[0068] in, is the heart rate variability, is the total number of heartbeats of the target during the monitoring period. For the The heartbeat and The interval between adjacent heartbeats, is the index of the heartbeat, and ;

[0069] Heart rate variability reflects the ability of the autonomic nervous system to regulate the cardiovascular system. The value has a direct impact on physical health. The larger the value, the stronger the ability of the autonomic nervous system to regulate the cardiovascular system. It can be used as an indicator of various physiological health conditions.

[0070] The specific formula upon which blood pressure volatility is generated is:

[0071] ;

[0072] in, For blood pressure fluctuations, The total number of blood pressure tests during the monitoring period. For the The blood pressure value of the test, is the mean blood pressure of the target during the monitoring period, is the index of the number of blood pressure tests, and ;

[0073] Blood pressure volatility refers to the degree of change in blood pressure values ​​during the monitoring period, usually expressed as the square root of the variance. The larger the value, the greater the change in blood pressure values ​​during the monitoring period.

[0074] The specific formula used to generate the hypoxemia index is:

[0075] ;

[0076] in, is the hypoxemia index, The total number of blood oxygen tests of the target during the monitoring period. For the The blood oxygen value of the test, is the index of the number of blood oxygen tests, and The hypoxemia index indicates the degree to which the blood oxygen level is below the normal range in a specific period of time. The higher the index, the greater the degree to which the blood oxygen level is below the normal range, which may have a negative impact on physical health; the blood oxygen value is usually expressed as a percentage.

[0077] A state judgment module is used to judge the target state according to the surrounding environment data and the activity intensity index, and the target state is a resting state, a normal state or a moving state;

[0078] Preset UV intensity threshold for smart wearable device location , wind speed threshold at the location of the smart wearable device and , , Activity Intensity Index gear , and , ,in, and The value is set relatively small, mainly used to identify rest. and The value of is set relatively large to identify the motion state. The value is set very high. Appropriate activities are good for health, but if the range of motion is too large, it will cause damage to the body. It is to identify whether the body is in a state of excessive exercise;

[0079] When people are resting, their activity intensity is usually low, and they are in relatively dim and closed places. The surrounding ultraviolet intensity and wind speed are usually relatively low. Therefore, if the ultraviolet intensity of the location of the smart wearable device is met at the same time , wind speed at the location of the smart wearable device and activity intensity index , then the target is judged to be in a resting state, which specifically refers to sleeping. When people are exercising, their movements are large, so the activity intensity index and the wind speed at the location of the smart wearable device will also be large. Considering that many people choose to exercise at night, the ultraviolet intensity is not considered. Therefore, if the wind speed at the location of the smart wearable device is satisfied at the same time , activity intensity index , then the target is judged to be in motion; if the target is neither in rest nor in motion, then the target is judged to be in normal state.

[0080] A health assessment module is used to generate a sports health assessment coefficient and a physiological health assessment coefficient according to the sports health index and the physiological health index; generate a target health state assessment coefficient according to the sports health assessment coefficient and the physiological health assessment coefficient, and complete the health assessment of each target state according to the target health state assessment coefficient;

[0081] The formula for generating the sports health assessment coefficient is:

[0082] ;

[0083] in, is the sports health assessment coefficient, is the activity intensity index, is the gait balance index, is the calorie consumption index, It is the threshold of excessive activity intensity; the sports health assessment coefficient is designed to comprehensively assess the individual's sports health status, including calorie consumption, gait balance and activity intensity. The larger the value, the healthier the target's current condition; it can provide an important basis for the target's health assessment; the calorie consumption index indicates the energy consumption of an individual during exercise. Higher calorie consumption generally indicates higher exercise intensity and more active exercise habits, which have a positive effect on physical health, so the sports health assessment coefficient will be higher. The gait balance index reflects the importance of gait and coordination during exercise. A higher gait balance index indicates that an individual has better balance ability during activities, which can effectively reduce the risk of injury, thereby promoting safer and more effective exercise, so the sports health assessment coefficient will be higher. The gait balance index reflects the importance of gait and coordination during exercise. A higher gait balance index indicates that an individual has better balance ability during activities, which can effectively reduce the risk of injury, thereby promoting safer and more effective exercise. Therefore, the sports health assessment coefficient will be higher, Reflects the positive or negative impact of activity intensity on physical health. When the activity intensity is within a safe range, the activity intensity index value will increase, reflecting healthy exercise habits. Therefore, the exercise health assessment coefficient will be higher. , the activity at this point has reached excessive activity, and continuing to increase the intensity of the activity may bring potential risks. The excessive activity intensity threshold is considered to be the upper limit of safe and effective activity intensity. Activities exceeding this threshold may cause excessive fatigue or injury to the body.

[0084] The specific logic for generating the physiological health assessment coefficient is as follows:

[0085] ;

[0086] in, is the physiological health assessment coefficient, is the heart rate variability, For blood pressure fluctuations, = is the hypoxemia index. The Physiological Health Assessment Index takes into account heart rate variability, blood pressure volatility and blood oxygen level, and reflects the individual's physiological health status. The root mean square difference of the heartbeat interval, heart rate variability reflects the variability of heart rate and the regulatory ability of the autonomic nervous system. Higher heart rate variability values ​​mean that the individual's heart health and autonomic nervous system regulation ability are better, which is usually associated with better physiological adaptability and lower stress levels. An increase in heart rate variability will lead to an increase in the Physiological Health Assessment Index value, indicating good physiological health. Blood pressure volatility refers to the degree of change in blood pressure over a certain period of time. When blood pressure volatility increases, the individual's physiological health status may be poor, and the Physiological Health Assessment Index value will decrease accordingly, reflecting a higher health risk. The hypoxemia index reflects the individual's blood oxygen level. When the blood oxygen level is low, the individual's Physiological Health Assessment Index will decrease, reflecting potential health risks, and the Physiological Health Assessment Index will decrease.

[0087] The specific logic for generating the target health status assessment coefficient is as follows: the sports health assessment coefficient and the physiological health assessment coefficient are generated according to the sports health index and the physiological health index. The specific formula for generating the target health status assessment coefficient is as follows:

[0088] ;

[0089] actually, is the target health status assessment coefficient, is the sports health assessment coefficient, is the physiological health assessment coefficient, is the weight coefficient, which is set according to the target state. If the target is in a resting state, , , if the target is in normal state, then , If the target is in motion, , . The target health status assessment coefficient reflects the overall health status of an individual. The larger the value, the better the individual's overall health status. The sports health assessment coefficient provides important information about the individual's sports health status. A higher sports health assessment coefficient value indicates good exercise habits, appropriate exercise intensity, and better overall exercise ability. These factors all contribute to improving physical health and reducing the risk of chronic diseases; therefore, the target health status assessment coefficient will be higher. The physiological health assessment coefficient reflects the individual's physiological health status, including heart health, autonomic nervous system function, and blood oxygen levels. A higher physiological health assessment coefficient value indicates good physiological adaptability and lower health risks; therefore, the target health status assessment coefficient will be higher;

[0090] In the resting state, individuals have less physical activity and their bodies are mainly in a state of recovery and rest. In this case, physiological health assessment is particularly important because physiological indicators (such as heart rate, blood pressure, blood oxygen, etc.) reflect an individual's physical function and recovery ability. Setting it to 0 means that the sports health assessment is not considered in this state, and all the focus is on physiological health. This helps monitor the individual's physiological condition at rest, such as whether they have enough rest and whether there are potential health problems.

[0091] Under normal conditions, individuals have a balanced lifestyle, with moderate exercise and a certain amount of rest. At this time, both sports health and physical health are important, but physical health is slightly more dominant. Therefore, the weight of the physical health assessment coefficient is higher than the sports health assessment coefficient; reflecting that the health status of an individual is to some extent affected by the combined influence of exercise and physical status in daily life. Maintaining good physical health is still the key, but moderate exercise also begins to play a role.

[0092] In the exercise state, the individual's physical activity increases significantly, and the influence of sports health increases significantly. At this time, the relative importance of sports health and physiological health is balanced, because a good exercise state affects physiological health, and good physiological health can support more effective sports performance. and The setting of equal values ​​emphasizes the interaction between the two at this stage. Exercise can improve physiological health (e.g., improving heart rate variability, lowering blood pressure, etc.), and a good physiological state can enhance exercise performance.

[0093] The specific logic for health assessment of each target state is as follows: preset target health state assessment threshold ,like , then the target is judged to be unhealthy. The target is judged as sub-healthy. , then the target is judged to be healthy.

[0094] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0095] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A health risk assessment system based on multi-source data fusion analysis of smart wearable devices, characterized in that: The specific steps include: A data acquisition module, which is used to obtain the wearer's motion data, physiological data, and surrounding environment data through intelligent wearable devices; A feature analysis module, which is used to analyze the motion data to obtain motion health indicators and analyze the physiological data to obtain physiological health indicators; the motion health indicators include: activity intensity index, gait balance index, and calorie consumption index; the physiological health indicators include heart rate variability, blood pressure volatility, and oxygen deficiency index; A state judgment module, which is used to judge the target state according to the surrounding environment data and activity intensity index, and the target state is a rest state, a normal state, or a motion state; A health assessment module, which is used to generate a motion health assessment coefficient and a physiological health assessment coefficient according to the motion health indicators and physiological health indicators; generate a target health state assessment coefficient according to the motion health assessment coefficient and the physiological health assessment coefficient, and complete the health assessment of each target state according to the target health state assessment coefficient; The specific formula for obtaining the activity intensity index is: Among them, AII is the activity intensity index, a ix is the acceleration of the target along the x-axis at the ith moment, a iy is the acceleration of the target along the y-axis at the i-th moment, a iz is the acceleration of the target along the z-axis at the ith moment, ω ix is the angular acceleration of the target along the x-axis at the ith moment, ω iy is the angular acceleration of the target along the y-axis at the i-th moment, ω iz is the angular acceleration of the target along the z-axis at the i-th moment; i is the index of the acceleration sampling moment in the monitoring time period, and i∈[1,I], I is the total number of acceleration sampling moments in the monitoring time period, and the acceleration and angular acceleration are sampled simultaneously in the monitoring time period; The specific formula for generating the gait balance index is: Among them, GBI is the gait balance index, is the variance of the acceleration of the target along the z-axis during the monitoring period, is the average value of the acceleration of the target along the z-axis during the monitoring period; The specific formula for generating the calorie consumption index is: CBE = K * ST * AII Where, CBE is the calorie consumption index, K is the heat conversion coefficient, and ST is the number of steps of the target within the monitoring time period; The specific formula for generating heart rate variability is: Among them, RMSSD is the heart rate variability, N is the total number of heartbeats of the target during the monitoring period, and RR v is the interval between the vth heartbeat and the v+1th heartbeat, v is the index of the heartbeat, and v∈[1,N]; The specific formula for generating blood pressure volatility is: Among them, VPB is blood pressure volatility, M is the total number of blood pressure tests of the target during the monitoring period, and BP j is the blood pressure value of the jth test, μ BP is the mean blood pressure of the target during the monitoring period, j is the index of the number of blood pressure tests, and j∈[1,M]; The specific formula for generating the oxygen deficiency index is: Among them, OR is the hypoxemia index, L is the total number of blood oxygen tests of the target during the monitoring period, and SPO l is the blood oxygen value of the lth test, l is the index of the number of blood oxygen tests, and l∈[1,L]; The specific logic for judging the target state is: preset the ultraviolet intensity threshold I0 at the location of the intelligent wearable device, the wind speed thresholds V0 and V1 at the location of the intelligent wearable device, V0 < V1, activity intensity index gears ALL0, ALL1, and ALL2, ALL0 < ALL1 < ALL2. If it simultaneously meets that the ultraviolet intensity I at the location of the intelligent wearable device is < I0, the wind speed V at the location of the intelligent wearable device is < V0, and the activity intensity index ALL0 < ALL, then it is judged that the target is in a rest state. If it simultaneously meets that the wind speed V at the location of the intelligent wearable device is > V1 and the activity intensity index ALL > ALL1, then it is judged that the target is in a motion state. If the target is neither in a rest state nor in a motion state, then it is judged that the target is in a normal state; The formula for generating the motion health assessment coefficient is: Where, AHI is the motion health assessment coefficient, AII is the activity intensity index, GBI is the gait balance index, CBE is the calorie consumption index, and ALL2 is the excessive activity intensity threshold; The specific logic for generating the physiological health assessment coefficient is: Where, PHI is the physiological health assessment coefficient, RMSSD is the heart rate variability, VOB is the blood pressure volatility, and OR is the oxygen deficiency index; The specific logic for generating the target health state assessment coefficient is: generate a motion health assessment coefficient and a physiological health assessment coefficient according to the motion health indicators and physiological health indicators. The specific formula for generating the target health state assessment coefficient is: HPI = α * AHI + β * PHI In fact, HPI is the target health status evaluation coefficient, AHI is the exercise health evaluation coefficient, PHI is the physiological health evaluation coefficient, and α and β are weight coefficients, which are specifically set according to the target state. If the target is in the rest state, then α = 0 and β = 1. If the target is in the normal state, then α = 0.25 and β = 0.

75. If the target is in the exercise state, then α = 0.5 and β = 0.

5.

2. A health risk assessment system based on multi-source data fusion analysis of smart wearable devices according to claim 1, characterized in that: The exercise data includes the three-axis acceleration, three-axis angular velocity, heat conversion coefficient, and number of steps of the target during the monitoring period; the physiological data includes the adjacent heart rate intervals, blood pressure, and blood oxygen values of the target during the same monitoring period; the surrounding environment data includes the ultraviolet intensity and wind speed at the location of the smart wearable device; the three-axis acceleration, three-axis angular velocity, number of steps, ultraviolet intensity, and wind speed at the location of the smart wearable device are all collected by sensors in the smart wearable device; for the three axes, the horizontal direction directly in front of the target's movement is taken as the x-axis direction, the direction 90 degrees to the left horizontally from the x-axis is the y-axis direction, and the vertical downward direction is the z-direction; the adjacent heart rate intervals, blood pressure, and blood oxygen values are collected by medical instruments in the smart wearable device; the heat conversion coefficient is taken as 0.05 kcal / step.

3. The health risk assessment system based on multi-source data fusion analysis of smart wearable devices according to claim 1 is characterized by: The specific logic for health evaluation of each target state is as follows: a preset target health status evaluation threshold HPI0 is set. If HPI < HPI0, the target is determined to be unhealthy. If HPI0 ≤ HPI < 2HPI0, the target is determined to be sub-healthy. If HPI ≥ 2HPI0, the target is determined to be healthy.

Images