Maximum oxygen uptake estimation method, estimation system and estimation interaction system

Abstract

The invention discloses a maximum oxygen uptake estimation method and system and an estimation interaction system, and the estimation method comprises the steps: obtaining heart rate data, power data and / or speed data from a historical motion data sequence of a motion user, and forming a fit file; based on the fit file, extracting the maximum average power and / or the maximum average speed and the average heart rate corresponding to the maximum average power and / or the maximum average speed; acquiring real-time oxygen uptake in the corresponding motion mode based on a preset model, the maximum average speed and / or the maximum average power in different motion modes; acquiring a heart rate correction coefficient based on the maximum heart rate, the average heart rate and the resting heart rate of the exercise user; and estimating the maximum oxygen uptake in different exercise modes based on the height, weight and heart rate correction coefficient of the exercise user and the real-time oxygen uptake in different exercise modes. According to the method, the maximum oxygen uptake of the exercise user can be reliably and accurately obtained by using the historical exercise data.

Description

Technical Field

[0001] The present invention relates to the field of sports health technology, and in particular to a maximum oxygen uptake estimation method, an estimation system and an estimation interactive system. Background Art

[0002] Maximum oxygen uptake is an important sports health indicator. Its physiological significance is the respiratory oxygen uptake level corresponding to the maximum heart rate, and the unit is ml / kg / min. Generally, to obtain the maximum oxygen uptake, you need to wear a respiratory monitoring device to perform an indoor exercise test. At the same time, this test requires the tester to make the heart rate close to the maximum heart rate through high-intensity exercise.

[0003] This testing method requires external respiratory monitoring equipment and has high exercise intensity, so it is not suitable for everyone (for example, users with heart health problems), and extreme sports can easily cause safety hazards.

[0004] Therefore, there is an urgent need for a method that can obtain maximum oxygen uptake without the need for extreme exercise or external respiratory monitoring equipment, while ensuring that the maximum oxygen uptake is obtained and avoiding excessive exercise intensity. Summary of the invention

[0005] To solve the above technical problems, the present invention provides a maximum oxygen uptake estimation method, which estimates the maximum oxygen uptake in different exercise modes based on the exercise user's own physiological information, as well as the exercise user's heart rate data, power data in a cycling exercise mode, and / or speed data in a running or walking exercise mode.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions:

[0007] The present application relates to a method for estimating maximum oxygen uptake, comprising:

[0008] Acquire heart rate data, power data and / or speed data from a historical sports data sequence of a sports user to form a fit file, wherein speed data is acquired in a running or walking sports mode, and power data is acquired in a cycling sports mode;

[0009] Extracting the maximum average power and / or the maximum average speed, and the average heart rate corresponding to the maximum average power and / or the maximum average speed based on the fit file;

[0010] In the running sports mode, based on the first preset model between the maximum average speed and the real-time oxygen uptake in the running sports mode, the real-time oxygen uptake corresponding to the extracted maximum average speed is obtained; in the walking sports mode, based on the second preset model between the maximum average speed and the real-time oxygen uptake in the walking sports mode, the real-time oxygen uptake corresponding to the extracted maximum average speed is obtained; in the cycling sports mode, based on the third preset model between the maximum average power and the real-time oxygen uptake in the cycling sports mode, the real-time oxygen uptake corresponding to the extracted maximum average power is obtained;

[0011] Obtaining a heart rate correction coefficient α based on the maximum heart rate, average heart rate and resting heart rate of the exercise user;

[0012] Based on the user's height h, weight m, heart rate correction factor α, and real-time oxygen uptake in different exercise modes, the maximum oxygen uptake in different exercise modes is estimated.

[0013] In some embodiments of the present application, based on the fit file, the maximum average power and / or the maximum average speed, and the average heart rate corresponding to the maximum average power and / or the maximum average speed are extracted, specifically:

[0014] A sliding window method is used to slide and sample the average power or average speed in each window. After the entire fit file is slid, the maximum average power and / or maximum average speed in each window is extracted, and the average heart rate in the window corresponding to the maximum average power and / or maximum average speed is simultaneously extracted.

[0015] In some embodiments of the present application, the sliding window is 5 minutes in length and is sampled in 1 second steps.

[0016] In some embodiments of the present application, the first preset model is:

[0017] vo2_1=a11·v_mean_max 2 -a12·v_mean_max+a13;

[0018] The second preset model is:

[0019] vo2_2=b11·v_mean_max+b12;

[0020] The third preset model is:

[0021] vo2_3=(c11·power_mean_max+c12) / m;

[0022] Among them, vo2_1 represents the real-time oxygen uptake obtained in the running sports mode, vo2_2 represents the real-time oxygen uptake obtained in the walking sports mode, vo2_3 represents the real-time oxygen uptake obtained in the cycling sports mode, a11, a12, a13, b11, b12, c11 and c12 are experimental coefficients, v_mean_max represents the maximum average speed, and power_mean_max represents the maximum average power.

[0023] In some embodiments of the present application, the heart rate correction coefficient is obtained based on the maximum heart rate, average heart rate and resting heart rate of the sports user, specifically, the heart rate correction coefficient α is calculated using the following formula:

[0024]

[0025] Among them, hr_max represents the maximum heart rate, hr_mean represents the average heart rate, hr_rest represents the resting heart rate, and k1 represents the ratio of the lactate threshold heart rate to the maximum heart rate of the exercise user.

[0026] In some embodiments of the present application, the maximum heart rate hr_max can be calculated using the physiological information of the exercise user, specifically:

[0027]

[0028] In some embodiments of the present application, when the sports user is in cycling sports mode, the maximum heart rate hr_max can be estimated by the following steps:

[0029] Filter out power cache sequences and heart rate cache sequences from historical cycling data of sports users;

[0030] The screened power buffer sequence and heart rate buffer sequence are used to fit the functional relationship between the maximum heart rate and the maximum power;

[0031] Based on a preset model, the corresponding maximum aerobic power Map is estimated using the weight, height and power threshold FTP of the exercise user;

[0032] Based on the functional relationship and the maximum aerobic power Map, obtaining a corresponding heart rate as the estimated maximum heart rate;

[0033] Wherein, the power threshold FTP is updated based on the physical fitness change of the sports user;

[0034] The preset model describes the relationship between the maximum aerobic power of the exercise user and his / her weight, height and power threshold.

[0035] In some embodiments of the present application, the power cache sequence and the heart rate cache sequence are screened out from the historical riding data of the sports user, specifically:

[0036] Acquire the power data and heart rate data of the exercise user in the historical riding data to form a fit file;

[0037] From the fit file, filter and extract the power data whose size reaches the product of the first preset value and the power threshold FTP, and synchronously record the heart rate data at the corresponding moment;

[0038] The sliding window method is adopted to slide and sample the average power and average heart rate in each window. After the fit file sliding is completed, the average power under each window forms the power cache sequence, and the average heart rate under each window forms the heart rate cache sequence.

[0039] In some embodiments of the present application, the following formula is specifically used to estimate the maximum oxygen uptake in different exercise modes:

[0040] vo2_max(i)=vo2_i·α·(1-|pm / h 2 |), where i = 1, 2, 3;

[0041] Wherein, vo2_max(1) represents the maximum oxygen uptake estimated in the running exercise mode, vo2_max(2) represents the maximum oxygen uptake estimated in the walking exercise mode, vo2_max(3) represents the maximum oxygen uptake estimated in the cycling exercise mode, and p is the experimental coefficient.

[0042] The maximum oxygen uptake estimation method involved in some embodiments provided in this application has the following advantages and beneficial effects:

[0043] (1) Estimating the maximum oxygen uptake based on the heart rate data, power data and / or speed data in the historical exercise data sequence of the exercise user, without the need to wear external respiratory equipment or extreme exercise, thus avoiding health risks caused by high-intensity exercise;

[0044] (2) It can meet the estimation of maximum oxygen uptake in running, walking and cycling exercise modes, and has strong adaptability.

[0045] Some embodiments of the present application also relate to a maximum heart rate estimation system, including:

[0046] A data acquisition module, which acquires heart rate data, power data and / or speed data from a historical exercise data sequence of an exercise user to form a fit file, wherein speed data is acquired in a running or walking exercise mode, and power data is acquired in a cycling exercise mode;

[0047] A data extraction module, which extracts the maximum average power and / or the maximum average speed, and the average heart rate corresponding to the maximum average power and / or the maximum average speed based on the fit file;

[0048] an oxygen uptake acquisition module, which, in a running sports mode, acquires the real-time oxygen uptake corresponding to the extracted maximum average speed based on a first preset model between the maximum average speed in the running sports mode and the real-time oxygen uptake; in a walking sports mode, acquires the real-time oxygen uptake corresponding to the extracted maximum average speed based on a second preset model between the maximum average speed in the walking sports mode and the real-time oxygen uptake; in a cycling sports mode, acquires the real-time oxygen uptake corresponding to the extracted maximum average power based on a third preset model between the maximum average power in the cycling sports mode and the real-time oxygen uptake;

[0049] A heart rate information correction module, which obtains a heart rate correction coefficient α based on the maximum heart rate, average heart rate and resting heart rate of the exercise user;

[0050] The maximum oxygen uptake estimation module estimates the maximum oxygen uptake in different exercise modes based on the height h, weight m, heart rate correction coefficient α, and real-time oxygen uptake in different exercise modes of the exercise user.

[0051] Some embodiments of the present application also relate to a maximum oxygen uptake estimation interactive system, including:

[0052] A heart rate collection device is used to collect the heart rate data of the exercise user and form the heart rate data in the historical exercise data sequence;

[0053] A power collection device, which is used to collect power data of the sports user in the cycling sports mode to form power data in the historical sports data sequence;

[0054] A speed collection device, which is used to collect speed data of the sports user in a running or walking sports mode to form speed data in the historical sports data sequence;

[0055] A terminal, which receives the historical exercise data sequence and is used to execute the maximum oxygen uptake estimation method according to any one of claims 1 to 8, and displays the estimated maximum oxygen uptake at the front end of the terminal.

[0056] After reading the specific embodiments of the present invention in conjunction with the accompanying drawings, other features and advantages of the present invention will become more clear. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0058] Figure 1 is a flow chart of an embodiment of the maximum oxygen uptake estimation method proposed in this application;

[0059] Figure 2 is a flow chart of a maximum heart rate estimation method involved in an embodiment of a maximum oxygen uptake estimation method proposed in this application;

[0060] Figure 3 It is the filtered power data and heart rate data involved in the maximum heart rate estimation method;

[0061] Figure 4 It is a flow chart of obtaining maximum aerobic power involved in the maximum heart rate estimation method;

[0062] Figure 5 It is a comparison chart between the maximum heart rate estimated by the maximum heart rate estimation method and the actual maximum heart rate tested;

[0063] Figure 6 is a comparison chart between the maximum oxygen uptake estimated by the maximum oxygen uptake estimation method proposed in the present application and the actual maximum oxygen uptake tested;

[0064] Figure 7 It is a hardware block diagram of an embodiment of the maximum oxygen uptake estimation interactive system proposed in this application.

[0065] Reference numerals:

[0066] 100. Heart rate acquisition device; 200. Power acquisition device; 300. Speed ​​acquisition device; 400. Terminal. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0068] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In the description of the present invention, it should be understood that the orientation or position relationship indicated by the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. is based on the orientation or position relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0069] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0070] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0071] In order to solve the problem of needing extreme exercise and wearing external respiratory monitoring equipment to obtain maximum oxygen uptake, some embodiments of the present application involve a maximum oxygen uptake estimation method, which is based on the historical exercise data sequence of the exercise user, does not require extreme exercise and wearing external respiratory monitoring equipment, and can achieve reliable and accurate estimation of the maximum oxygen uptake, thereby facilitating the measurement of the health status of the exercise user.

[0072] In some embodiments of the present application, a method for estimating maximum oxygen uptake is provided.

[0073] The maximum oxygen uptake estimation method is implemented based on the maximum oxygen uptake estimation system. As follows, the maximum oxygen uptake estimation method will be described in conjunction with the maximum oxygen uptake estimation system.

[0074] Figure 1 A flowchart showing the method for estimating the maximum oxygen uptake is shown, therefore, refer to Figure 1 , the maximum oxygen uptake estimation method is described in detail as follows.

[0075] S1: Acquire heart rate data, power data and / or speed data from a historical exercise data sequence of an exercise user to form a fit file.

[0076] The data acquisition process may be implemented by a data acquisition module (not shown) in the maximum oxygen uptake estimation system.

[0077] When a sports user performs different sports modes, different sports data sequences will be generated within a time period.

[0078] The historical exercise data sequence represents the data generated by the exercise user during exercise, which may include various types of data, including but not limited to heart rate data, power data, and speed data.

[0079] Therefore, as needed, the required data is selected from the historical sports data sequence. For example, when the sports user is in the cycling sports mode, the heart rate data and power data of the sports user are obtained; when the sports user is in the running or walking sports mode, the heart rate data and speed data of the sports user are obtained.

[0080] The data acquisition process may be implemented by a data acquisition module (not shown) in the maximum oxygen uptake estimation system.

[0081] In some embodiments of the present application, for example, a heart rate acquisition device 100 (such as a heart rate belt) can be used to collect heart rate data generated by an athlete during exercise, for example, a power acquisition device 200 (such as a power meter) can be used to collect power data generated by an athlete during cycling, and for example, a speed acquisition device 300 (such as an inertial sensor) can be used to collect the speed of an athlete during running or walking.

[0082] S2: Based on the fit file, extract the maximum average power and / or the maximum average speed, and the average heart rate corresponding to the maximum average power and / or the maximum average speed.

[0083] The data extraction process may be implemented by a data extraction module (not shown) in the maximum oxygen uptake estimation system.

[0084] The maximum oxygen uptake is the breathing oxygen uptake level corresponding to the maximum heart rate. Therefore, in order to improve the accuracy of estimating the maximum oxygen uptake, in the cycling sports mode, the maximum average power and the average heart rate at the corresponding moment of the maximum average power are extracted; in the walking or running sports mode, the maximum average speed and the average heart rate at the corresponding moment of the maximum average speed are extracted.

[0085] In some embodiments of the present application, a sliding window method is used to obtain the maximum average power and / or the maximum average speed.

[0086] In cycling sports mode, obtain the fit file containing heart rate data and power data.

[0087] A sliding window of 5 minutes in length is used, which slides in steps of 1 second. Each time the window slides, the average power in the window is calculated.

[0088] After sliding through the sequence length of the fit file, the maximum average power is extracted from the multiple average powers corresponding to the multiple windows as the maximum average power power_mean_max, see the following formula (1), and the average heart rate hr_mean at the corresponding moment is recorded at the same time.

[0089]

[0090] Wherein, n represents the length of the motion data sequence, k represents the kth movement of the sliding window, i represents the counting point within the sliding window, and power(i) represents the power data.

[0091] In running or cycling sports mode, obtain a fit file containing heart rate data and speed data.

[0092] A sliding window of 5 minutes in length is used, which slides in steps of 1 second. Each time the window slides, the average speed under the window is calculated.

[0093] After sliding through the sequence length of the fit file, the maximum average speed is extracted from the multiple average speeds corresponding to the multiple windows as the maximum average speed v_mean_max, see the following formula (2), and the average heart rate hr_mean at the corresponding moment is recorded at the same time.

[0094]

[0095] Where n represents the length of the motion data sequence, k represents the kth movement of the sliding window, i represents the counting point in the sliding window, and v(i) represents the velocity data.

[0096] S3: Based on the preset models, maximum average speed and / or maximum average power in different sports modes, obtain the real-time oxygen uptake in the corresponding sports mode.

[0097] The process of obtaining the oxygen uptake may be implemented by an oxygen uptake obtaining module (not shown) in the maximum oxygen uptake estimation system.

[0098] In the running / walking / cycling sports mode, speed / power can also reflect the oxygen uptake level in the current state to a certain extent.

[0099] Therefore, in some embodiments of the present application, in the running / walking sports mode, the maximum average speed is used to reflect the oxygen uptake level, and in the cycling sports mode, the maximum average power is used to reflect the oxygen uptake level.

[0100] Therefore, in order to accurately reflect the oxygen uptake level, in the running sports mode, a first preset model between the maximum average speed in the running sports mode and the real-time oxygen uptake is pre-established; in the walking sports mode, a second preset model between the maximum average speed in the walking sports mode and the real-time oxygen uptake is pre-established; in the cycling sports mode, a third preset model between the maximum average power in the cycling sports mode and the real-time oxygen uptake is pre-established.

[0101] In some embodiments of the present application, the first preset model is as follows:

[0102] vo2_1=a11·v_mean_max 2 -a12·v_mean_max+a13 (3)

[0103] Among them, vo2_1 represents the real-time oxygen uptake obtained in the running exercise mode, a11, a12, and a13 are experimental coefficients, and v_mean_max represents the maximum average speed.

[0104] The first preset model as described above is fitted using the maximum oxygen uptake and maximum average speed detected by the breathing monitoring equipment of multiple sports users in the running sports mode, and a11, a12 and a13 are reversely calculated using the obtained maximum oxygen uptake and maximum average speed.

[0105] In some embodiments of the present application, a11 may be 4.3804, a12 may be 0.2996, and a13 may be 7.0928.

[0106] In some embodiments of the present application, the second preset model is as follows:

[0107] vo2_2=b11·v_mean_max+b12 (4)

[0108] Among them, vo2_2 represents the real-time oxygen uptake obtained in the walking exercise mode, b11 and b12 are experimental coefficients, and v_mean_max represents the maximum average speed.

[0109] The second preset model as described above is fitted using the maximum oxygen uptake and maximum average speed detected by the breathing monitoring equipment of multiple exercise users in walking exercise mode, and b11 and b12 are back-calculated using the obtained maximum oxygen uptake and maximum average speed.

[0110] In some embodiments of the present application, b11 may be 11.89, and b12 may be 3.5.

[0111] In some embodiments of the present application, the third preset model is as follows:

[0112] vo2_3=(c11·power_mean_max+c12) / m (5)

[0113] Among them, vo2_3 represents the real-time oxygen uptake obtained in the cycling sports mode, c11 and c12 are experimental coefficients, power_mean_max represents the maximum average power, and m represents the weight of the exercise user.

[0114] The third preset model as described above is fitted using the maximum oxygen uptake and maximum average power detected by the breathing monitoring equipment of multiple sports users in the cycling sports mode, and c11 and c12 are reversed using the obtained maximum oxygen uptake and maximum average power speed.

[0115] In some embodiments of the present application, c11 may be 12.24, and c12 may be 350.

[0116] S4: Obtain a heart rate correction coefficient α based on the maximum heart rate, average heart rate, and resting heart rate of the exercise user.

[0117] The heart rate correction process can be implemented by a heart rate information correction module (not shown) in the maximum oxygen uptake estimation system.

[0118] The heart rate affects the estimated maximum oxygen uptake. Therefore, in order to accurately estimate the maximum oxygen uptake, the heart rate correction coefficient α is obtained by combining the maximum heart rate hr_max, the average heart rate hr_mean and the resting heart rate hr_rest using the following formula (6).

[0119]

[0120] Among them, k1 represents the ratio of the lactate threshold heart rate of the sports user to the maximum heart rate, and different sports users have different k1 values.

[0121] In some embodiments of the present application, for example, k1 may be 0.8273.

[0122] In some embodiments of the present application, the maximum heart rate hr_max can be calculated using the age of the exercise user using the following formula (7).

[0123]

[0124] As mentioned above, the calculation of the maximum heart rate hr_max depends on age. Therefore, there may be a situation where people of similar age have large differences in heart rate. In this case, the maximum heart rate hr_max obtained by using formula (7) is not accurate enough.

[0125] Therefore, in some embodiments of the present application, in the cycling sports mode, the maximum heart rate hr_max can be estimated based on the historical cycling data sequence.

[0126] Figure 2 A flowchart showing the maximum heart rate estimation method is shown in FIG. Figure 2 ,The maximum heart rate estimation method is described in detail as follows.

[0127] S11: Acquire power data and heart rate data of the exercise user from a historical cycling data sequence of the exercise user.

[0128] The historical cycling data sequence of a sports user may include heart rate data, power data, speed data, etc. Therefore, when heart rate data and power data are needed, the historical cycling data sequence may be filtered.

[0129] S12: Filter out a power cache sequence and a heart rate cache sequence based on the acquired power data and heart rate data.

[0130] During cycling, the heart rate will increase with the increase of exercise intensity. When the output power exceeds the power threshold FTP (Functional Threshold Power), the heart rate will further increase until the power value reaches Map (Maximal aerobic power). Then the heart rate will converge to the maximum level. The heart rate in this state is close to the maximum heart rate.

[0131] Since the positive correlation between power and heart rate is relatively strong during the period from moderate-intensity exercise to heart rate convergence, if you want to estimate the maximum heart rate, the power corresponding to the heart rate needs to be screened to avoid the problem of poor accuracy in maximum heart rate estimation caused by the introduction of power data at low power.

[0132] Among them, FTP refers to the average power output of the user when riding as hard as possible for one hour; Map refers to the power value corresponding to the maximum heart rate during exercise.

[0133] In some embodiments of the present application, the filtered power is limited to be greater than the product of the first preset value and FTP to filter out lower power, which helps to accurately achieve the fitting of the following functional relationship.

[0134] As mentioned above, the heart rate data and power data in the historical cycling data sequence can form a fit file. The specific filtering method is as follows.

[0135] (1) Further screening is performed on the fit file to extract power data whose size reaches the product of the first preset value and the power threshold FTP, and the heart rate data at the corresponding time is synchronously sampled.

[0136] The first preset value may be preset as needed. As mentioned above, in order to improve the accuracy of the maximum heart rate estimation, the first preset value may be set between 50% and 70%.

[0137] In some embodiments of the present application, the first preset value may be selected to be 60%.

[0138] That is, the power data having a power value greater than 60%*FTP and the heart rate data of the filtered power data are filtered.

[0139] See also Figure 3 , which shows the filtered power data and heart rate data, from Figure 3 As can be seen from the graph, when maximum aerobic power is reached, the heart rate converges to the maximum heart rate.

[0140] In some embodiments of the present application, since FTP is required, the user is required to provide FTP in advance. If it cannot be provided, the FTP needs to be calculated using the FTP calculation method involved in Patent Publication No. CN117688275A.

[0141] The FTP calculation method involved in CN117688275A is not described in detail here and is incorporated into this article by reference.

[0142] (2) A sliding window method is used to slide and sample the average power and average heart rate in each window. After the entire fit file is slid, the average power in each window forms the power cache sequence power_batch, and the average heart rate in each window forms the heart rate cache sequence heatat_batch.

[0143] The calculation method is shown in the following formula (8).

[0144]

[0145] In some embodiments of the present application, a 30 s sliding window and a 1 s step are used for average sampling.

[0146] As in (8) above, i represents the i-th movement of the sliding window, and k is a counting point, representing 1 to 30 in the sliding window.

[0147] power represents power data, heatat represents heart rate data, power_batch(i) represents the average power of the i-th sliding window, and heatat_batch(i) represents the average heart rate of the i-th sliding window.

[0148] S13: using the screened power buffer sequence and heart rate buffer sequence to fit the functional relationship between the maximum heart rate and the maximum power.

[0149] See also Figure 3 The filtered power data and heart rate data are shown according to Figure 3 From the heart rate data and power data shown in , it can be seen that heart rate and power have a strong positive correlation.

[0150] That is, when the output power is higher, there will also be a correspondingly higher heart rate.

[0151] Therefore, when there are enough data in the power cache sequence and the heart rate cache sequence in S12, the cached heart rate data and power data are used to perform function fitting, and this functional relationship refers to the linear relationship between the maximum power and the maximum heart rate.

[0152] In some embodiments of the present application, the power data power_batch(i) in the power cache sequence power_batch and the heart rate data heatat_batch(i) in the heart rate cache sequence heatat_batch as described above are used to calculate the fitting parameters grad and bias used to fit the functional relationship based on the least squares method, so that the maximum heart rate = grad*maximum power+bias.

[0153] The fitting parameters grad and bias are obtained using the following formula (9).

[0154]

[0155] Where n represents the length of the sliding window, represents the average value of the power buffer sequence, Represents the average value of the heart rate buffer sequence.

[0156] S14: Based on a preset model, the corresponding maximum aerobic power Map is estimated using the weight, height and power threshold FTP of the exercise user.

[0157] As mentioned above, after the power reaches the maximum aerobic power Map, the heart rate will converge to a maximum level close to the maximum heart rate. Therefore, if the fitting function relationship between the heart rate and power is known, the Map can be estimated more accurately, and then the maximum heart rate can be reversely calculated using the function relationship.

[0158] Therefore, a reliable and accurate estimation of the Map helps to reliably and accurately estimate the maximum heart rate.

[0159] Since the Map is related to the FTP and physiological information (including height h and weight m) of the exercise user, a preset model between the Map of the exercise user and his weight, height and power threshold is established in advance.

[0160] The preset model is obtained by fitting the Map output by multiple users through extreme sports, FTP, height and weight, and is an empirical model, as shown in the following formula (10).

[0161]

[0162] Among them, q1, q2 and q3 are fitting coefficients, h is height, and m is weight.

[0163] For example, q1 may be 0.7326, q2 may be 44.13, and q3 may be 22.035.

[0164] See also Figure 4 , which shows a flowchart for estimating the maximum aerobic power Map.

[0165] First, the height h and weight m of the exercise user are obtained from their physiological information.

[0166] Physiological information may include, in addition to height and weight, age, resting heart rate, etc., for example, but in this application, only height and weight are used.

[0167] Secondly, it is determined whether there is an FTP input in advance. If not, the FTP is calculated using the method described in Patent Publication No. CN117688275A as described above.

[0168] After that, after obtaining the height h, weight m and FTP, the Map can be obtained according to formula (10).

[0169] S15: Based on the functional relationship and the maximum aerobic power Map, the corresponding heart rate is obtained as the estimated maximum heart rate.

[0170] As described above, the heart rate corresponding to the maximum aerobic power is considered to be the maximum heart rate. Therefore, based on the functional relationship obtained in S13 and the Map obtained in S14, the maximum heart rate hr_max is obtained.

[0171] hr_max=grad*Map+bias.

[0172] After a sports user rides multiple times, the physical fitness data changes, and the user's FTP also changes. Therefore, when the maximum heart rate hr_max is calculated based on the new FTP, a calculation error will be caused.

[0173] Therefore, the present application updates the power threshold FTP based on the physical fitness changes of the sports user to achieve reliable estimation of the maximum heart rate hr_max.

[0174] In some embodiments of the present application, it is necessary to obtain the speed power of the corresponding riding, update the FTP by estimating the oxygen uptake vo2_power, and the updated FTP is used to filter the data in S12 of the next wheel.

[0175] In some embodiments of the present application, the following formula (11) is used to update FTP.

[0176]

[0177] Among them, power represents the power recorded by the athlete during the cycling process, m represents the weight of the athlete, hr_max and hr_rest represent the maximum heart rate and resting heart rate of the athlete, k1, k2 and k3 are all experimental coefficients, k is the heart rate to oxygen uptake coefficient, this value will change with the user's athletic ability, hr_power is the average heart rate corresponding to the window of maximum average power obtained by sliding window.

[0178] In some embodiments of the present application, a 30s sliding window and a 1s step sliding are used to obtain hr_power.

[0179] After calculating the average power of each window, the maximum average power is obtained, and the average heart rate at the time corresponding to the maximum average power is recorded as hr_power.

[0180] In some embodiments of the present application, for example, k1 may be 12.24, k2 may be 350, and k3 may be 15.024.

[0181] When testing data of different sports users, the experimental coefficient k will also be different.

[0182] See also Figure 5 , which provides a comparison chart between the maximum heart rate estimated by the maximum heart rate estimation method involved in the embodiment of the present application (ie, the estimated value) and the actual measured maximum heart rate (ie, the true value).

[0183] The heart rate measured during extreme exercise is the maximum heart rate, which can be obtained by the user wearing a heart rate collection device (such as a heart rate belt). Figure 5 Shown by the dashed line.

[0184] The maximum heart rate obtained by the maximum heart rate estimation method of this application is shown in Figure 5 Shown by the solid line.

[0185] pass Figure 5 It can be seen that the maximum heart rate estimated by the maximum heart rate estimation method described above is basically similar to the actual maximum heart rate of the exercise user, with high accuracy; and the estimated maximum heart rate does not use age parameters, avoiding the defect of poor maximum heart rate calculation caused by age parameters.

[0186] It should be noted that there is no chronological order between S3 and S4 as described above, and S3 and S4 are shown herein only for the purpose of convenience of description.

[0187] S5: Estimate the maximum oxygen uptake in different exercise modes based on the height h, weight m, heart rate correction factor α, and real-time oxygen uptake in different exercise modes of the exercise user.

[0188] This VO2max estimation process may be implemented by a VO2max estimation module (not shown) in a VO2max estimation system.

[0189] In some embodiments of the present application, the following formula (12) is specifically used to estimate the maximum oxygen uptake under different exercise modes:

[0190] vo2_max(i)=vo2_i·α·(1-|pm / h 2 |) (12)

[0191] Wherein, i=1,2,3, vo2_max(1) represents the maximum oxygen uptake estimated in the running exercise mode, vo2_max(2) represents the maximum oxygen uptake estimated in the walking exercise mode, vo2_max(3) represents the maximum oxygen uptake estimated in the cycling exercise mode, and p is the experimental coefficient.

[0192] In some embodiments of the present application, p may be 22.04.

[0193] See also Figure 6 , which provides a comparison chart between the maximum oxygen uptake estimated by the maximum oxygen uptake estimation method involved in the embodiment of the present application under different exercise modes (i.e., the estimated value) and the actual measured maximum oxygen uptake (i.e., the true value).

[0194] The maximum oxygen uptake measured during extreme exercise can be obtained by wearing a respiratory monitoring device, see Figure 6 As shown in the black filled box.

[0195] The maximum oxygen uptake in walking exercise mode obtained by the maximum oxygen uptake estimation method of this application is shown in Figure 6Indicated by the long dashed line.

[0196] The maximum oxygen uptake in the running exercise mode obtained by the maximum oxygen uptake estimation method of this application is shown in Figure 6 Indicated by short dashed lines.

[0197] The maximum oxygen uptake in cycling mode obtained by the maximum oxygen uptake estimation method of this application is shown in Figure 6 Shown as solid line.

[0198] pass Figure 6 It can be seen that the maximum oxygen uptake estimated by the maximum oxygen uptake estimation method of the embodiment of the present application is basically similar to the actual maximum oxygen uptake of the sports user, and has a high accuracy rate.

[0199] In some embodiments of the present application, see Figure 7 , and also relates to an interactive system for estimating maximum oxygen uptake.

[0200] The maximum oxygen uptake estimation interactive system includes a heart rate acquisition device 100 , a power acquisition device 200 , a speed acquisition device 300 and a terminal 400 .

[0201] The heart rate collection device 100 (eg, a heart rate belt) is used to collect the heart rate data of a sports user and send it to the terminal 400 .

[0202] The power collection device 200 (eg, a power meter) is used to collect power data of a sports user and send the data to the terminal 300 .

[0203] The speed acquisition device 300 (eg, an inertial sensor) is used to collect speed data of a moving user and send the data to the terminal 400 .

[0204] The terminal 400 may be a smart device (eg, a mobile phone, a smart watch, a pad) that is respectively connected to the heart rate acquisition device 100 , the power acquisition device 200 , and the speed acquisition device 300 for communication.

[0205] The maximum oxygen uptake estimation method as described above is integrated in the terminal 400 for performing maximum oxygen uptake estimation.

[0206] The estimated maximum oxygen uptake can be displayed on the front end of the terminal 400 for easy viewing by sports users.

[0207] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for a person skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions claimed to be protected by the present invention.

Claims

1. A method for estimating maximum oxygen uptake, characterized in that: include: Acquire heart rate data, power data and / or speed data from a historical sports data sequence of a sports user to form a fit file, wherein speed data is acquired in a running or walking sports mode, and power data is acquired in a cycling sports mode; Extracting the maximum average power and / or the maximum average speed, and the average heart rate corresponding to the maximum average power and / or the maximum average speed based on the fit file; Based on a first preset model between the maximum average speed and the real-time oxygen uptake in the running sport mode, the real-time oxygen uptake corresponding to the extracted maximum average speed when running is obtained; based on a second preset model between the maximum average speed and the real-time oxygen uptake in the walking sport mode, the real-time oxygen uptake corresponding to the extracted maximum average speed when walking is obtained; based on a third preset model between the maximum average power and the real-time oxygen uptake in the cycling sport mode, the real-time oxygen uptake corresponding to the extracted maximum average power when cycling is obtained; Obtaining a heart rate correction coefficient α based on the maximum heart rate, average heart rate and resting heart rate of the exercise user; Based on the user's height h, weight m, heart rate correction factor α, and real-time oxygen uptake in different exercise modes, the maximum oxygen uptake in different exercise modes is estimated.

2. The method for estimating maximum oxygen uptake according to claim 1, characterized in that: Based on the fit file, the maximum average power and / or the maximum average speed, and the average heart rate corresponding to the maximum average power and / or the maximum average speed are extracted, specifically: A sliding window method is used to slide and sample the average power or average speed in each window. After the entire fit file is slid, the maximum average power and / or maximum average speed in each window is extracted, and the average heart rate in the window corresponding to the maximum average power and / or maximum average speed is simultaneously extracted.

3. The method for estimating maximum oxygen uptake according to claim 1, characterized in that: The first preset model is: vo2_1=a11·v_mean_max 2 -a12·v_mean_max+a13; The second preset model is: vo2_2=b11·v_mean_max+b12; The third preset model is: vo2_3=(c11·power_mean_max+c12) / m; Among them, vo2_1 represents the real-time oxygen uptake obtained in the running sports mode, vo2_2 represents the real-time oxygen uptake obtained in the walking sports mode, vo2_3 represents the real-time oxygen uptake obtained in the cycling sports mode, a11, a12, a13, b11, b12, c11 and c12 are experimental coefficients, v_mean_max represents the maximum average speed, and power_mean_max represents the maximum average power.

4. The method for estimating maximum oxygen uptake according to claim 1, characterized in that: Based on the maximum heart rate, average heart rate and resting heart rate of the exercise user, a heart rate correction coefficient is obtained, specifically, the heart rate correction coefficient α is calculated using the following formula: Among them, hr_max represents the maximum heart rate, hr_mean represents the average heart rate, hr_rest represents the resting heart rate, and k1 represents the ratio of the lactate threshold heart rate to the maximum heart rate of the exercise user.

5. The method for estimating maximum oxygen uptake according to claim 1 or 4, characterized in that: The maximum heart rate hr_max can be calculated using the age of the exercise user, specifically:

6. The method for estimating maximum oxygen uptake according to claim 1 or 4, characterized in that: When the sports user is in cycling sports mode, the maximum heart rate hr_max can be estimated by the following steps: Filter out power cache sequences and heart rate cache sequences from historical cycling data of sports users; The screened power buffer sequence and heart rate buffer sequence are used to fit the functional relationship between the maximum heart rate and the maximum power; Based on a preset model, the corresponding maximum aerobic power Map is estimated using the weight, height and power threshold FTP of the exercise user; Based on the functional relationship and the maximum aerobic power Map, obtaining a corresponding heart rate as the estimated maximum heart rate; Wherein, the power threshold FTP is updated based on the physical fitness change of the sports user; The preset model describes the relationship between the maximum aerobic power of the exercise user and his / her weight, height and power threshold.

7. The method for estimating maximum oxygen uptake according to claim 6, characterized in that: Filter out the power cache sequence and heart rate cache sequence from the historical riding data of the sports user, specifically: Acquire the power data and heart rate data of the exercise user in the historical riding data to form a fit file; From the fit file, filter and extract the power data whose size reaches the product of the first preset value and the power threshold FTP, and synchronously record the heart rate data at the corresponding moment; The sliding window method is adopted to slide and sample the average power and average heart rate in each window. After the fit file sliding is completed, the average power under each window forms the power cache sequence, and the average heart rate under each window forms the heart rate cache sequence.

8. The method for estimating maximum oxygen uptake according to claim 1, characterized in that: The following formula is used to estimate the maximum oxygen uptake in different exercise modes: vo2_max(i)=vo2_i·α·(1-|pm / h 2 |), where i = 1, 2, 3; Wherein, vo2_max(1) represents the maximum oxygen uptake estimated in the running exercise mode, vo2_max(2) represents the maximum oxygen uptake estimated in the walking exercise mode, vo2_max(3) represents the maximum oxygen uptake estimated in the cycling exercise mode, and p is the experimental coefficient.

9. A maximum heart rate estimation system, characterized in that: include: A data acquisition module, which acquires heart rate data, power data and / or speed data from a historical exercise data sequence of an exercise user to form a fit file, wherein speed data is acquired in a running or walking exercise mode, and power data is acquired in a cycling exercise mode; A data extraction module, which extracts the maximum average power and / or the maximum average speed, and the average heart rate corresponding to the maximum average power and / or the maximum average speed based on the fit file; an oxygen uptake acquisition module, which acquires the real-time oxygen uptake corresponding to the extracted maximum average speed when running based on a first preset model between the maximum average speed and the real-time oxygen uptake in the running sports mode; in the walking sports mode, based on a second preset model between the maximum average speed and the real-time oxygen uptake in the walking sports mode, acquires the real-time oxygen uptake corresponding to the extracted maximum average speed; in the cycling sports mode, based on a third preset model between the maximum average power and the real-time oxygen uptake in the cycling sports mode, acquires the real-time oxygen uptake corresponding to the extracted maximum average power; A heart rate information correction module, which obtains a heart rate correction coefficient α based on the maximum heart rate, average heart rate and resting heart rate of the exercise user; The maximum oxygen uptake estimation module estimates the maximum oxygen uptake in different exercise modes based on the height h, weight m, heart rate correction coefficient α, and real-time oxygen uptake in different exercise modes of the exercise user.

10. A maximum oxygen uptake estimation interactive system, characterized in that: include: A heart rate collection device is used to collect the heart rate data of the exercise user and form the heart rate data in the historical exercise data sequence; A power collection device, which is used to collect power data of the sports user in the cycling sports mode to form power data in the historical sports data sequence; A speed collection device, which is used to collect speed data of the sports user in a running or walking sports mode to form speed data in the historical sports data sequence; A terminal, which receives the historical exercise data sequence and is used to execute the maximum oxygen uptake estimation method according to any one of claims 1 to 8, and displays the estimated maximum oxygen uptake at the front end of the terminal.

Images