A sports pace recommendation method suitable for sports wristbands

Abstract

The present application provides a method for recommending exercise pace suitable for a sports bracelet. The method provides exercise suggestions based on the user's exercise route by calculating the air quality through accessing AQI data, and prompts the user of slippery sections by calculating the ground slippery index through accessing terrain and air temperature and humidity data. During exercise, the ground slippery index predicts the user's heart rate based on the collected real-time heart rate, exercise duration, and slope of the exercise route. The present application can provide pace suggestions based on the wearer's physical signs to avoid sports injuries.

Description

Technical Field

[0001] The present application relates to the technical field of data recognition and feedback, and in particular to a method for recommending exercise pace suitable for a sports bracelet. Background Art

[0002] Scientifically and rationally selecting sports scenes can enhance the user's sports experience and reduce the probability of injury. At present, sports bracelets still mainly use sports monitoring as their main function, that is, they judge the wearer's sports performance by monitoring indicators such as heart rate, breathing rate, and exercise distance during exercise.

[0003] A good habit cannot offset a bad habit. Keeping exercising is a good habit, while smoking, fatigue, and excessive drinking are bad habits. Many users believe that by keeping exercising, they can offset the adverse effects of smoking and other behaviors. In fact, under the subtle influence of bad living habits, the physical condition has gradually become unsuitable for continuing to exercise. Therefore, if you only judge the sports performance without evaluating your own physical condition or the sports environment, exercise will become a high-risk behavior with greater risks. For example, the cardiac arrest of amateur marathon runners during the competition is caused by the lack of physical assessment; for professional cross-country marathon runners, environmental conditions are more likely to become a "murderer" that endangers life. Summary of the invention

[0004] The present application provides a method for recommending exercise pace for a sports bracelet, which can provide exercise pace recommendations based on the wearer's physical signs and exercise routes.

[0005] The technical solution of this application is as follows:

[0006] A method for recommending exercise pace for a sports wristband, comprising the following steps:

[0007] S1) Before the exercise time starts:

[0008] Generate a movement route based on the movement time and waypoints input by the user;

[0009] Obtain the AQI value of the area where the exercise route is located during the exercise time, and determine whether it is suitable for exercise based on the classification of the AQI value;

[0010] Obtain the precipitation and air humidity data of the area where the sports route is located, and calculate the ground slippery index based on the precipitation and air humidity data;

[0011] S2) During exercise:

[0012] Get the user's location in real time, set a reminder point before the road section where the slippery index exceeds the set threshold, and remind the user when the user reaches the reminder point;

[0013] The average heart rate from the start of the exercise to the current exercise, the real-time heart rate at the current exercise, and the average pace are collected at a fixed frequency and input into the heart rate prediction model to calculate the predicted heart rate for a 3-minute period along the exercise route at the average pace:

[0014] The heart rate prediction model is as follows:

[0015] ;

[0016] In the formula, express t Predict your heart rate at all times; Indicates the real-time heart rate at the current moment; Indicates the heart rate change caused by slope; Indicates the heart rate change value caused by the average pace from the start of the exercise to the current moment; Indicates the heart rate change value caused by exercise duration; Indicates the heart rate change value caused by the slippery ground index during the predicted exercise route;

[0017] in,

[0018] ;

[0019] In the formula, and Respectively, the slope s and length of slope section d The heart rate variation coefficient caused by the heart rate variation coefficient is obtained through data training;

[0020] ;

[0021] In the formula, Indicated by the average pace v Caused by heart rate variability coefficient;

[0022] ;

[0023] In the formula, represents the duration of the movement t Caused by heart rate variability coefficient;

[0024] ;

[0025] In the formula, the slippery index is represented by the ground slippery index SSI Caused by heart rate variability coefficient;

[0026] S3) During exercise:

[0027] Based on the predicted heart rate within 3 minutes, the high heart rate interval is extracted and the predicted average heart rate is calculated, wherein the high heart rate interval is defined as the heart rate interval where the heart rate reaches more than 90% of the limit heart rate;

[0028] S4) When the user's heart rate remains in the high heart rate range for more than 1 minute or the predicted average heart rate is in the high heart rate range:

[0029] A healthy heart rate is defined based on a percentage of the limit heart rate, the healthy heart rate and the exercise route in the next 2 minutes are input as known quantities into a heart rate prediction model, an average pace is calculated and the average pace is recorded as an improved average pace;

[0030] With the goal of improving the average pace, a suggested pace is calculated based on the current average pace and displayed to the user.

[0031] Furthermore, the formula of the ground slippery index in step S1) is as follows:

[0032] SSI =0.7 P +0.3 H ;

[0033] In the formula, SSI Indicates the slippery ground index; P It represents the cumulative precipitation 3 hours before the start of the exercise, in mm; H Indicates the air humidity percentage.

[0034] Furthermore, when calculating the slippery surface index:

[0035] Obtain the elevation data of the movement route, and calculate the slope of the movement route based on the elevation data. When the absolute value of the slope is greater than or equal to 6%, correct the SSI value. The formula is as follows:

[0036] SSI i =0.7 P +0.3 H +2 S ;

[0037] In the formula, SSI i Indicates the corrected SSI value, S Indicates the absolute value of the slope.

[0038] Furthermore, in step S2), the threshold of the ground slippery index is set to 50.

[0039] Furthermore, in step S2), the heart rate prediction model uses the observed real-time heart rate at the current moment as the dependent variable, and uses the slope, slope section length, average pace, exercise duration, and ground slippery index as independent variables to construct a linear regression model to estimate the coefficients of each variable:

[0040] ;

[0041] In the formula, It is the real-time observation value of heart rate; is the error term, which represents the difference between the observed value and the model predicted value;

[0042] Use the least squares method to estimate , , , , , , minimize the sum of squares of error terms.

[0043] Further, in step S4), the healthy heart rate is 83% of the limit heart rate, and the limit heart rate is defined as the difference between the value 220 and the age.

[0044] Further, step S5 is also included):

[0045] Based on the real-time position, the map software is called to obtain the road elevation data within 300 meters of the current position, and the route with a slope less than the next slope in the exercise route is selected as the candidate route. The candidate route is input into the heart rate prediction model to output the calculation result, and the recommended pace of the candidate route is calculated based on the calculation result. If the recommended pace of the candidate route is faster than the recommended pace of the exercise route, it is displayed to the user, otherwise it is not displayed.

[0046] Due to the adoption of the above technical solution, the beneficial effects of this application are as follows:

[0047] 1. This application can give exercise suggestions based on weather pollution conditions and the degree of slippery environment. This application determines weather pollution conditions based on AQI classification, and determines the slippery degree of the exercise route based on humidity and rainfall, which helps users understand the exercise route in advance. The slipperiness of the ground is a key factor that causes people to get injured. Muscle fatigue during running will cause the user's perception of ground friction to decrease, and the controllability of muscles after fatigue will decrease, and the uniformity of force will deteriorate. Excessive pushing on the ground on slippery ground can easily lead to body imbalance and sports injuries such as sprains and strains. This application promptly reminds sections with SSI greater than 50, which helps to improve users' safety awareness.

[0048] 2. This application establishes a heart rate prediction model based on environmental conditions and one's own physical condition. In the heart rate model, the real-time heart rate is the predicted starting heart rate, and the predicted heart rate is obtained by superimposing the heart rate influence values ​​of various factors on the starting heart rate. The heart rate model comprehensively considers multiple aspects:

[0049] 1) The user's exercise status, that is, the real-time heart rate and exercise duration. In a fatigued state, the heart rate increases, and it is not easy to bear too much exercise load. The real-time heart rate is used as the starting point. When it is too high, the range between it and the high heart rate is compressed to represent the degree of exercise load.

[0050] 2) The difficulty of the route, that is, the uphill section. The length and gradient of the slope will affect the heart rate. When the slope is too steep, the athlete may be in an anaerobic state, which increases the heart load. Different athletes have different tolerance to anaerobic state. The heart rate model fully considers the difficulty of the route and effectively reminds users to avoid sports injuries caused by excessive persistence.

[0051] 3) Environmental conditions, i.e. the slippery index of the ground. When the ground friction is low, sprains or slips are more likely to occur. At the same time, being alert to slippery sections of the road will also cause the brain to become excited and increase the heart rate. The heart rate prediction model takes into account the increase in heart rate caused by environmental factors and psychological factors.

[0052] 4) The heart rate model uses average pace as the main indicator for adjusting heart rate to provide exercise recommendations that are healthier and more reasonable for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0054] Figure 1 A flow chart of a method for recommending exercise pace for a sports bracelet provided in this application. DETAILED DESCRIPTION

[0055] Example:

[0056] It should be noted that the bracelet communicates via Bluetooth and can connect to the mobile phone to call the API of each application to obtain data such as air quality, elevation data, and maps.

[0057] This embodiment provides a method for recommending exercise pace applicable to a sports wristband, comprising the following steps:

[0058] S1) Before the exercise time starts:

[0059] Generate a movement route based on the movement time and waypoints input by the user;

[0060] Using Bluetooth technology, after the bracelet is connected to the smartphone, the air quality index (AQI), temperature and humidity data are obtained by calling the Moji Weather API of the mobile phone application; the Amap API is called to obtain GPS positioning and terrain elevation data to obtain external data and obtain the AQI value of the area where the exercise route is located during the exercise time.

[0061] The data obtained by the wristband through the API is initially processed and then sent to the wristband via Bluetooth. During this process, the wristband receives and stores the data and determines whether it is suitable for exercise based on the AQI value classification;

[0062] The precipitation and air humidity data of the area where the movement route is located are obtained, and the ground slippery index is calculated based on the precipitation and air humidity data.

[0063] Call the Moji Weather API to obtain air quality, temperature, and humidity data, and call the Amap API to obtain GPS and terrain elevation data. The data is processed and transmitted to the bracelet.

[0064] The user selects the exercise time and multiple points along the way to form his exercise route, and then requests various data on the exercise route through the network. AQI is generally divided into levels 1 to 6, with level 1 being the best level, suitable for exercise, and level 6 being severely polluted and unsuitable for exercise. The user can choose whether to go out for exercise, and the bracelet only displays the AQI to the user.

[0065] The formula for the slippery surface index is as follows:

[0066] SSI =0.7 P +0.3 H ;

[0067] In the formula, SSI Indicates the slippery ground index; P It represents the cumulative precipitation 3 hours before the start of the exercise, in mm; H Indicates the air humidity percentage.

[0068] Cumulative precipitation is directly used mm Substitute the value of air humidity into the calculation.

[0069] When calculating the slippery surface index:

[0070] Get the elevation data of the movement route, calculate the slope of the movement route based on the elevation data, and when the absolute value of the slope is greater than or equal to 6%, SSI The value is corrected, the formula is as follows:

[0071] SSI i =0.7 P +0.3 H +2 S ;

[0072] In the formula, SSI i Indicates the corrected SSI value, S Indicates the absolute value of the slope.

[0073] The slope will directly change the movement force. SSI When the value is too high, the user should be reminded. SSI Too high means a higher risk of injury, increased user alertness, and brain excitement, which can also lead to an increased heart rate.

[0074] S2) During exercise:

[0075] Get the user's location in real time, set a reminder point before the road section where the slippery index exceeds the set threshold, and remind the user when the user reaches the reminder point;

[0076] The algorithm integrated in the bracelet is based on the received environmental data (such as the slippery ground index) and the user's physiological data (such as heart rate). It collects the average heart rate from the start of the exercise to the current exercise time, the real-time heart rate at the current exercise time, and the average pace at a fixed frequency, and inputs them into the heart rate prediction model to calculate the predicted heart rate for a 3-minute period along the exercise route at the average pace:

[0077] The heart rate prediction model is as follows:

[0078] ;

[0079] In the formula, express t Predict your heart rate at all times; Indicates the real-time heart rate at the current moment; Indicates the heart rate change caused by slope; Indicates the heart rate change value caused by the average pace from the start of the exercise to the current moment; Indicates the heart rate change value caused by exercise duration; Indicates the heart rate change value caused by the slippery ground index during the predicted exercise route;

[0080] in,

[0081] ;

[0082] In the formula, and Respectively, the slope s and length of slope section d The heart rate variation coefficient caused by the heart rate variation coefficient is obtained through data training;

[0083] ;

[0084] In the formula, Indicated by the average pace v Caused by heart rate variability coefficient;

[0085] ;

[0086] In the formula, Indicated by the duration of the movement t Caused by heart rate variability coefficient;

[0087] ;

[0088] In the formula, Indicated by the slippery index SSI Caused by heart rate variation coefficient.

[0089] In one embodiment, the threshold value of the slippery ground index is 50, and the distance from the prompt point is SSI The change section is 50m. The fixed collection frequency can be determined by the user according to the complexity of the section. For example, 30s can be taken as a fixed frequency to predict the heart rate in the next 3 minutes. When the user travels to the last predicted exercise route, the heart rate prediction is re-performed and the prediction result 30s ago is replaced.

[0090] The model calculation takes into account multiple factors, including slope, slippery degree, and heart rate. After combining these data, it predicts the heart rate changes in the next few minutes and recommends a suitable exercise pace accordingly. For the heart rate prediction model, the real-time heart rate at the current moment is observed as the dependent variable, and the slope, slope section length, average pace, exercise duration, and ground slippery index are used as independent variables. After normalizing the data, a linear regression model is constructed to estimate the coefficients of each variable:

[0091] ;

[0092] In the formula, It is the real-time observation value of heart rate; is the error term, which represents the difference between the observed value and the model predicted value;

[0093] Use the least squares method to estimate , , , , , , so that the sum of squares of error terms is minimized.

[0094] For the constructed linear regression model: calculate the coefficient of determination or observe the residual distribution to determine the degree of match between the model and the data; use cross-validation to test the predictive ability and stability of the model to prevent overfitting during training.

[0095] Several aspects are taken into consideration in the heart rate model:

[0096] 1) The user's exercise status, that is, the real-time heart rate and exercise duration. In a fatigued state, the heart rate increases, and it is not easy to bear too much exercise load. The real-time heart rate is used as the starting point. When it is too high, the range between it and the high heart rate is compressed to represent the degree of exercise load.

[0097] 2) The difficulty of the route, that is, the uphill section. The length and gradient of the slope will affect the heart rate. When the slope is too steep, the athlete may be in an anaerobic state, which increases the heart load. Different athletes have different tolerance to anaerobic state. The heart rate model fully considers the difficulty of the route and effectively reminds users to avoid sports injuries caused by excessive persistence.

[0098] 3) Environmental conditions, i.e. the slippery index of the ground. When the ground friction is low, sprains or slips are more likely to occur. At the same time, being alert to slippery sections of the road will also cause the brain to become excited and increase the heart rate. The heart rate prediction model takes into account the increase in heart rate caused by environmental factors and psychological factors.

[0099] 4) The heart rate model uses average pace as the main indicator for adjusting heart rate to provide exercise recommendations that are healthier and more reasonable for users.

[0100] When the bracelet calculates that the user is about to enter a high-risk area (such as a high heart rate or a slippery road), the user can be reminded by flashing the screen, vibrating the bracelet, playing voice, etc. to indicate various instructions, thereby enhancing the user's safety awareness and avoiding sports injuries.

[0101] S3) During exercise:

[0102] Based on the predicted heart rate within 3 minutes, the high heart rate interval is extracted and the predicted average heart rate is calculated, where the high heart rate interval is defined as a heart rate interval where the heart rate reaches more than 90% of the limit heart rate.

[0103] The result of the heart rate prediction model output is the heart rate matrix of the future moment, and different moments correspond to different heart rates. In the heart rate matrix, extract the number of high heart rates and calculate the duration according to the time interval of heart rate prediction. The average heart rate is obtained by weighting all heart rates. When calculating the average heart rate, all collected heart rates can be added up and weighted, or the heart rate per second can be calculated separately and weighted. The former is suitable for complex sections with more terrain changes, while the latter is relatively less complex. The former is more accurate, and the latter requires less data.

[0104] There are many medical indicators for the limit heart rate, and different limit heart rates can be used. In this embodiment, the widely used method of (220-age) is used to calculate the limit heart rate.

[0105] S4) When the user's heart rate remains in the high heart rate range for more than 1 minute or the predicted average heart rate is in the high heart rate range:

[0106] A healthy heart rate is defined based on a percentage of the limit heart rate, and the healthy heart rate and the exercise route in the next 2 minutes are input as known quantities into the heart rate prediction model to calculate the average pace and record the average pace as the improved average pace.

[0107] A high heart rate should not last too long, so this embodiment will give user feedback by limiting the duration of the high heart rate and the average heart rate interval. The duration of the high heart rate is also calculated using the heart rate matrix and the sampling interval. When the average heart rate is in the high heart rate interval, it means that the user's heart rate changes greatly during this process, and the user may be experiencing a difficult section that exceeds the body's tolerance range, which also increases the risk of sports injuries.

[0108] With the goal of improving the average pace, a suggested pace is calculated based on the current average pace and displayed to the user.

[0109] The average pace given by the heart rate model is calculated from the start of the exercise. The longer the exercise time, the more stable the average pace. Therefore, when a healthy heart rate is given, the output is still the average pace that includes the duration of the exercise, that is, the improved average pace, so the improved average pace is more accurate and real-time. However, the improved average pace is only the target pace. In order to reach the improved average pace from the average pace, the current pace, that is, the recommended pace should be reduced to below the improved average pace. The recommended pace needs to be determined based on the total distance and total time of the exercise. In this embodiment, the healthy heart rate is defined as 83% of the limit heart rate.

[0110] As an improved embodiment of this embodiment, when obtaining the recommended pace, the heart rate may also be changed by changing the exercise route, including step S5):

[0111] Based on the real-time location, the map software is called to obtain the road elevation data within 300 meters of the current location, and the route with a slope less than the next slope in the exercise route is selected as the candidate route. The candidate route is input into the heart rate prediction model to output the calculation result, and the recommended pace of the candidate route is calculated based on the calculation result. If the recommended pace of the candidate route is faster than the recommended pace of the exercise route, it will be displayed to the user, otherwise it will not be displayed. The candidate route can help the user maintain a more stable and healthy exercise state. If the recommended pace of the candidate route is not faster than the recommended pace of the current exercise route, the system will not recommend a route change to the user to avoid increasing the user's heart rate and exercise risks. This method helps optimize the user's exercise plan and reduce potential health problems caused by improper route selection.

[0112] Users' exercise data can be continuously uploaded to the mobile application, which will store the data and conduct more in-depth analysis, such as trend analysis and health recommendations, to help users better understand their exercise habits and health status.

[0113] It should be noted that the heart rate collection and exercise prompts involved in the above embodiments can be realized by existing electronic modules. Relevant calculations can be performed after the data is collected and transmitted to the mobile phone for calculation.

[0114] Anything not described in this application can be achieved by adopting or drawing on existing technologies.

[0115] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for recommending exercise pace for a sports wristband, characterized in that: The following steps are involved: S1) Before the exercise time starts: Generate a movement route based on the movement time and waypoints input by the user; Obtain the AQI value of the area where the exercise route is located during the exercise time, and determine whether it is suitable for exercise based on the classification of the AQI value; Obtain the precipitation and air humidity data of the area where the sports route is located, and calculate the ground slippery index based on the precipitation and air humidity data; S2) During exercise: Get the user's location in real time, set a reminder point before the road section where the slippery index exceeds the set threshold, and remind the user when the user reaches the reminder point; The average heart rate from the start of the exercise to the current exercise, the real-time heart rate at the current exercise, and the average pace are collected at a fixed frequency and input into the heart rate prediction model to calculate the predicted heart rate for a 3-minute period along the exercise route at the average pace: The heart rate prediction model is as follows: ； In the formula, express t Predict your heart rate at all times; Indicates the real-time heart rate at the current moment; Indicates the heart rate change caused by slope; Indicates the heart rate change value caused by the average pace from the start of the exercise to the current moment; Indicates the heart rate change value caused by exercise duration; Indicates the heart rate change value caused by the slippery ground index during the predicted exercise route; in, ； In the formula, and Respectively, the slope s and slope section length d The heart rate variation coefficient caused by the heart rate variation coefficient is obtained through data training; ； In the formula, Mean pace v Caused by heart rate variability coefficient; ； In the formula, Indicated by the duration of the movement t Caused by heart rate variability coefficient; ； In the formula, Indicated by the slippery index SSI Caused by heart rate variability coefficient; S3) During exercise: Based on the predicted heart rate within 3 minutes, the high heart rate interval is extracted and the predicted average heart rate is calculated, wherein the high heart rate interval is defined as the heart rate interval where the heart rate reaches more than 90% of the limit heart rate; S4) When the user's heart rate remains in the high heart rate range for more than 1 minute or the predicted average heart rate is in the high heart rate range: A healthy heart rate is defined based on a percentage of the limit heart rate, the healthy heart rate and the exercise route in the next 2 minutes are input as known quantities into a heart rate prediction model, an average pace is calculated and the average pace is recorded as an improved average pace; With the goal of improving the average pace, a suggested pace is calculated based on the current average pace and displayed to the user.

2. A method for recommending exercise pace for a sports wristband according to claim 1, characterized in that: The formula of the ground slippery index in step S1) is as follows: SSI =0.7 P +0.3 H ； In the formula, SSI Indicates the slippery ground index; P It represents the cumulative precipitation 3 hours before the start of the exercise, in mm; H Indicates the air humidity percentage.

3. A method for recommending exercise pace for a sports wristband according to claim 2, characterized in that: When calculating the slippery surface index: Obtain the elevation data of the movement route, and calculate the slope of the movement route based on the elevation data. When the absolute value of the slope is greater than or equal to 6%, correct the SSI value. The formula is as follows: SSI i =0.7 P +0.3 H +2 S ； In the formula, SSI i Indicates the corrected SSI value, S Indicates the absolute value of the slope.

4. The method for recommending exercise pace for a sports wristband according to claim 3, characterized in that: In step S2), the threshold of the ground slippery index is set to 50.

5. A method for recommending exercise pace for a sports wristband according to claim 4, characterized in that: In step S2), the heart rate prediction model uses the observed real-time heart rate at the current moment as the dependent variable, and uses the slope, slope section length, average pace, exercise duration, and ground slippery index as independent variables to construct a linear regression model to estimate the coefficients of each variable: ； In the formula, It is the real-time observation value of heart rate; To predict the heart rate at the start time; is the error term, which represents the difference between the observed value and the model predicted value; Use the least squares method to estimate , , , , , , so that the sum of squares of error terms is minimized.

6. A method for recommending exercise pace for a sports wristband according to claim 5, characterized in that: In step S4), the healthy heart rate is 83% of the limit heart rate, and the limit heart rate is defined as the difference between the value 220 and the age.

7. The method for recommending exercise pace for a sports wristband according to claim 5, characterized in that: Also includes step S5): Based on the real-time position, the map software is called to obtain the road elevation data within 300 meters of the current position, and the route with a slope less than the next slope in the exercise route is selected as the candidate route. The candidate route is input into the heart rate prediction model to output the calculation result, and the recommended pace of the candidate route is calculated based on the calculation result. If the recommended pace of the candidate route is faster than the recommended pace of the exercise route, it is displayed to the user, otherwise it is not displayed.

Images