A method, system and interactive system for estimating cycling power

Abstract

This invention discloses a method, system, and interactive system for estimating cycling power. The estimation method includes: obtaining the user's maximum heart rate; obtaining the user's real-time oxygen uptake based on the maximum heart rate, average heart rate, and resting heart rate; back-estimating cycling power based on the real-time oxygen uptake, the user's weight, and the bicycle's weight; calculating bias corrections for different exercise states based on the user's heart rate gradients under different exercise states; and using the bias corrections for different exercise states to correct the estimated cycling power, thereby obtaining the user's cycling power under different exercise states. This invention eliminates the need for power monitoring equipment, estimating cycling power under different exercise states based on the user's physiological information, bicycle weight, and heart rate data.

Description

Technical Field

[0001] This invention relates to the field of sports and health technology, and in particular to a method, system and interactive system for estimating cycling power. Background Technology

[0002] Power output is a crucial parameter in cycling and an important indicator of cycling ability. Normally, power measurement requires an external power measurement device (e.g., a power meter). However, many users who don't use power meters also have a need for this metric.

[0003] Therefore, there is an urgent need for a method to obtain cycling power without wearing a power meter.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background technology of this application, and therefore may include prior art that is not known to those skilled in the art. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method for estimating cycling power, which estimates cycling power under different exercise conditions based on the exercise user's physiological information, bicycle weight, and heart rate data.

[0006] To achieve the above-mentioned objectives, the present invention employs the following technical solution:

[0007] This application relates to a method for estimating cycling power, including:

[0008] Get the maximum heart rate hr_max of the user who is exercising;

[0009] The real-time oxygen uptake of the exercise user is obtained based on the maximum heart rate hr_max, average heart rate, and resting heart rate hr_rest. vo2 ;

[0010] Based on the real-time oxygen uptake vo2 The user's weight m_body and the bicycle weight m_bake are used to estimate the cycling power p_dummy.

[0011] Based on the heart rate gradient of the exercise user under different exercise states, the bias correction under different exercise states is calculated;

[0012] The bias correction under different exercise states is used to correct the estimated cycling power, so as to obtain the cycling power of the exercise user under different exercise states.

[0013] Different exercise states include exercise states with gradual changes in heart rate, exercise states with rapid increases in heart rate, and exercise states with slow decreases in heart rate.

[0014] In some embodiments of this application, the maximum heart rate hr_max of the exercising user is obtained as follows:

[0015] ;

[0016] Calculate the maximum heart rate hr_max1 using the age of the exercise user;

[0017] The maximum heart rate hr_max is initialized using the maximum heart rate hr_max1;

[0018] A sliding window approach is used to obtain the real-time heart rate of the latest active user entering the window.

[0019] The real-time heart rate is compared with the maximum heart rate hr_max. If the real-time heart rate is greater than or equal to the maximum heart rate hr_max, the maximum heart rate hr_max is updated using the real-time heart rate. If the real-time heart rate is less than the maximum heart rate hr_max, the maximum heart rate hr_max is not updated.

[0020] In some embodiments of this application, the cycling power estimation method further includes: identifying different exercise states based on the heart rate gradient of the exercise user, specifically:

[0021] The window's core frequency gradient is obtained in real time using a sliding window approach. grad , as the heart rate gradient of the exercise user;

[0022] When the heart rate gradient is greater than the preset gradient value d0, it indicates that the exercise user is in a state of rapid heart rate increase. Otherwise, it is determined whether the heart rate gradient is less than 0. If it is, it indicates that the exercise user is in a state of slow heart rate decrease. Otherwise, it indicates that the exercise user is in a state of stable heart rate change.

[0023] Wherein, the preset gradient value d0 is greater than 0.5 and less than or equal to 1.

[0024] In some embodiments of this application, the window's inner frequency gradient grad Specifically:

[0025] ;

[0026] in, n Indicates the length of the sliding window. i This represents the count points within the sliding window; hr(i) Represented as the first in the sliding window i Heart rate values.

[0027] In some embodiments of this application, bias corrections are calculated based on the heart rate gradients of the exercise user under different exercise states. bias Specifically:

[0028] ;

[0029] Where k0, b0, c0, k1, and b1 are experimental coefficients.

[0030] In some embodiments of this application, the real-time oxygen uptake of the exercise user is obtained based on the maximum heart rate hr_max, average heart rate, and resting heart rate hr_rest. vo2 Specifically:

[0031] The average heart rate of the user during exercise is obtained in real time using a sliding window method.

[0032] Using formula Obtain real-time oxygen uptake vo2 ;

[0033] Where α is the experimental coefficient characterizing the conversion of oxygen uptake heart rate.

[0034] In some embodiments of this application, based on the real-time oxygen uptake vo2 The user's weight m_body and the bicycle's weight m_bake are used to inversely estimate the cycling power p_dummy.

[0035] p_dummy =vo2*( m_body+m_bake)-a / b;

[0036] Where a and b are the empirical values ​​for bias correction and coefficient correction, respectively.

[0037] In some embodiments of this application, bias correction under different motion states bias Used for estimating riding power p_dummy The following corrections have been made:

[0038] p_dummy = p_dummy + bias.

[0039] The cycling power estimation methods provided in this application have the following advantages and beneficial effects:

[0040] (1) Based on the heart rate data of the exercise user, the weight of the exercise user and the weight of the bicycle, the cycling power is estimated without the need to wear a power meter, thus meeting the power needs of the user without a power meter;

[0041] (2) The power estimation method requires low-cost hardware and can provide more cycling feedback data for novice users;

[0042] (3) Considering the relationship between heart rate and power, the cycling power is corrected by utilizing the trend of heart rate changes of exercise users under different exercise states, which broadens the applicable scenarios of the power estimation method and improves the accuracy of power estimation of exercise users under different exercise states.

[0043] This application relates to a cycling power estimation system, comprising:

[0044] The heart rate acquisition module is used to obtain the maximum heart rate of the exercise user. hr_max ;

[0045] Oxygen uptake acquisition module, which is used to acquire oxygen based on maximum heart rate hr_max Average heart rate and resting heart rate hr_rest Obtain the real-time oxygen uptake of the exercise user. vo2 ;

[0046] A power estimation module, used to estimate power based on the real-time oxygen uptake. vo2 The weight of the exercise user m_body and bicycle weight m_bake Reverse estimation of cycling power p_dummy ;

[0047] The bias correction calculation module is used to calculate the bias correction for different exercise states based on the heart rate gradient of the exercise user under different exercise states.

[0048] The power correction module uses bias correction under different exercise conditions to correct the estimated cycling power, so as to obtain the cycling power of the exercise user under different exercise conditions.

[0049] Different exercise states include exercise states with gradual changes in heart rate, exercise states with rapid increases in heart rate, and exercise states with slow decreases in heart rate.

[0050] This application also relates to an interactive system for estimating cycling power, including:

[0051] Heart rate monitoring devices are used to collect heart rate data from exercise users.

[0052] The terminal receives the heart rate data, the physiological information of the exercise user, and the weight of the bicycle, and performs the cycling power estimation method as described above, and displays the cycling power on the front end of the terminal.

[0053] Other features and advantages of the present invention will become clearer after reading the detailed embodiments of the invention in conjunction with the accompanying drawings. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a flowchart of an embodiment of the cycling power estimation method proposed in this application;

[0056] Figure 2 This is a flowchart illustrating the bias correction under different motion states in an embodiment of the cycling power estimation method proposed in this application;

[0057] Figure 3 This is a comparison chart between the cycling power estimated by the cycling power estimation method proposed in this application and the actual cycling power tested.

[0058] Figure 4 This is a graph of the cumulative absolute error function of the cycling power estimated by the cycling power estimation method proposed in this application;

[0059] Figure 5 This is a graph of the cumulative error function of the cycling power estimated by the cycling power estimation method proposed in this application;

[0060] Figure 6 This is a hardware block diagram of an embodiment of the cycling power estimation interactive system proposed in this application.

[0061] Figure label:

[0062] 100. Heart rate acquisition equipment; 200. Terminal. Detailed Implementation

[0063] The technical solutions in the embodiments of the present invention will be clearly and completely described 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.

[0064] Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention. In the description of this invention, it should be understood that the terms "center," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0065] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0066] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0067] To address the issue of users needing to wear power monitoring devices to obtain cycling power during cycling, some embodiments of this application involve cycling power estimation methods. These methods are based on the user's heart rate data, bicycle weight, and user's body weight, eliminating the need for power monitoring devices. This allows for reliable and accurate estimation of cycling power, facilitating the assessment of the user's health status and providing rich cycling feedback data for beginners.

[0068] Some embodiments of this application relate to a method for estimating cycling power.

[0069] The cycling power estimation method is based on a cycling power estimation system. The cycling power estimation method will be described below in conjunction with the cycling power estimation system.

[0070] Figure 1 A flowchart illustrating the cycling power estimation method is shown; therefore, refer to... Figure 1 The method for estimating cycling power is described in detail below.

[0071] S1: Get the maximum heart rate hr_max of the user who is exercising.

[0072] Heart rate data can be obtained through the heart rate acquisition module (not shown) of the cycling power estimation system.

[0073] Before starting the ride, it is necessary to obtain the user's physiological information and the bicycle's weight. m_bake .

[0074] This physiological information includes: height h、 weight m_body Age, resting heart rate hr_rest Maximum heart rate hr_max, etc. 。

[0075] In some embodiments of this application, maximum heart rate hr_max The age of the sports user can be estimated using the following formula (1) to obtain... hr_max=hr_max1 .

[0076] (1).

[0077] Maximum heart rate as above hr_max1 The calculation relies on age, therefore, there may be cases where people of similar age have significantly different heart rates. In such cases, the maximum heart rate obtained using formula (1) is used. hr_max That is not accurate enough.

[0078] In some embodiments of this application, the accuracy of obtaining the maximum heart rate is improved by acquiring it in real time.

[0079] A heart rate monitoring device 100 (e.g., a heart rate belt) is used to acquire the heart rate of the exercise user in real time during cycling.

[0080] The result obtained using the formula (1) above hr_max1 Initialize maximum heart rate hr_max , that is, hr_max=hr_ max1.

[0081] A sliding window method is used to obtain the real-time heart rate of the latest active user entering the window.

[0082] The real-time heart rate is compared with the maximum heart rate hr_max. If the real-time heart rate is greater than or equal to the maximum heart rate hr_max, the real-time heart rate is used to update the maximum heart rate hr_max, that is, the real-time heart rate is assigned to hr_max. If the real-time heart rate is less than the maximum heart rate hr_max, the maximum heart rate hr_max is not updated, that is, hr_max is kept.

[0083] The sliding window has an entry length of 11 and a step size of 1. Of course, other sizes and step sizes of sliding windows can also be selected.

[0084] A smaller entry length for the sliding window results in a smaller computation delay. For example, when the entry length of the sliding window is 11 and the step size is 1, the computation delay is less than 10 seconds.

[0085] S2: Obtain the real-time oxygen uptake of the exercise user based on the maximum heart rate hr_max, average heart rate, and resting heart rate hr_rest. vo2 .

[0086] This real-time oxygen uptake acquisition process can be achieved through the oxygen uptake acquisition module (not shown) in the cycling power estimation system.

[0087] During exercise, the body provides energy according to the intensity of the exercise. As a metabolic marker, heart rate can reflect the amount of oxygen taken up to a certain extent. In other words, heart rate is related to the level of oxygen intake during respiration.

[0088] In some embodiments of this application, the average heart rate within a sliding window is used to improve the accuracy of oxygen uptake. hr_mean Calculate oxygen uptake based on maximum heart rate and hr_rest. vo2 See formula (2).

[0089] (2)

[0090] Where α is the experimental coefficient characterizing the conversion of oxygen uptake to heart rate, which can be obtained by fitting user physiological information; for example, it can be set to 15.3, representing oxygen uptake. vo2 It can reflect the rate at which a user consumes energy during their current exercise state.

[0091] As described above, the average heart rate is obtained by using a sliding window. Each time the window is slid, a calculation is performed. The sliding window can be selected with an entry length of 11 and a step size of 1.

[0092] The average heart rate within the sliding window can be calculated using formula (3).

[0093] (3)

[0094] Where n represents the length of the sliding window (i.e., 11). i This represents the count points within the sliding window; hr(i) Represented as the first in the sliding window i Heart rate value, hr_mean This represents the average heart rate within the sliding window.

[0095] Therefore, the average heart rate is calculated each time the sliding window is slid, and a maximum heart rate is also obtained. The real-time oxygen uptake is then calculated using the average heart rate, maximum heart rate, and resting heart rate. vo2.

[0096] S3: Based on real-time oxygen uptake vo2 The user's weight m_body and the bicycle's weight m_bake are used to inversely estimate the cycling power p_dummy.

[0097] The estimation of cycling power can be achieved through the power estimation module (not shown) in the cycling power estimation system.

[0098] Real-time oxygen uptake is measured by heart rate. vo2 After estimation, based on real-time oxygen uptake vo2、 Weight of sports users m_ body and bicycle weight m_bake Using formula (4), cycling power p_dummy Perform inverse estimation 。

[0099] p_dummy =vo2*( m_body+m_bake)-a / b (4)

[0100] Where a and b are the empirical values ​​for bias correction and coefficient correction, respectively, for example, a It can be set to 350. b It can be set to 9.5 。

[0101] S4: Calculate the bias correction for different exercise states based on the heart rate gradient of the exercise user under different exercise states.

[0102] In some embodiments of this application, different exercise states include an exercise state with a gradual change in heart rate (referred to as exercise state I), an exercise state with a rapid increase in heart rate (referred to as exercise state II), and an exercise state with a slow decrease in heart rate (referred to as exercise state III).

[0103] The calculation of this bias correction can be performed by the bias correction calculation module (not shown) in the cycling power estimation system.

[0104] In order to improve the accuracy of cycling power estimation, in some embodiments of this application, the cycling power obtained by formula (4) is corrected according to the heart rate gradient.

[0105] During a short burst of sprinting exercise, the heart rate rises rapidly, and the heart rate gradient increases. During a pause in cycling, the heart rate drops rapidly, and the heart rate gradient decreases. In a steady state of exercise, the heart rate remains relatively stable, and the heart rate gradient fluctuates within a small range. Therefore, cycling power is adjusted according to the different heart rate gradients.

[0106] Based on the heart rate gradient, the exercise state of the user is determined, and then the corresponding bias correction is obtained based on the heart rate gradient corresponding to the exercise state. bias .

[0107] First, the exercise status of the user is determined based on the heart rate gradient.

[0108] (1) Using a sliding window, the window's central velocity gradient is obtained in real time using formula (5). grad This serves as the heart rate gradient for exercise users.

[0109] (5)

[0110] in, n Indicates the length of the sliding window. i This represents the count points within the sliding window; hr(i) Represented as the first in the sliding window i Heart rate values.

[0111] The heart rate gradient is calculated once every time the window is slid. grad.

[0112] (2) Determine the heart rate gradient grad and The preset gradient value d0 is greater than 0.5 and less than or equal to 1.

[0113] Heart rate gradient grad When the heart rate is greater than the preset gradient value d0, it indicates that the user is in a state of rapid heart rate increase (i.e., exercise state II); otherwise, the heart rate gradient is determined. grad If the value is less than 0, it indicates that the user is in a state of slow heart rate decrease (i.e., exercise state III); otherwise, it indicates that the user is in a state of stable heart rate change (i.e., exercise state I).

[0114] Then, see Figure 2 Formula (6) is used to obtain the corresponding bias correction based on the corresponding heart rate gradient under the corresponding exercise state. bias .

[0115] (6)

[0116] Where k0, b0, c0, k1, and b1 are experimental coefficients, and d0 can be 1; k1 will be assigned a larger value than k0, for example, k1 can be in the range of 5 to 10.

[0117] k0, b0, c0, k1, and b1 are all generalized empirical values ​​obtained by fitting heart rate and power data from multiple user samples.

[0118] In some embodiments of this application, cycling power is compensated for under different motion conditions.

[0119] S5: Bias correction using different motion states bias It is used to correct the estimated cycling power to obtain the cycling power of the sports user under different sports conditions.

[0120] This power correction process can be implemented by the power correction module (not shown) in the cycling power estimation system.

[0121] p_dummy = p_dummy + bias.

[0122] As mentioned above, there are three motion states for the user. See Figure 2 Different film corrections were given, and then different bias corrections were used to adjust the riding power.

[0123] Under a state of exercise with a gradual change in heart rate (i.e., exercise state I), bias Zero, p_dummy Formula (4) is used for calculation.

[0124] During exercise with a rapid increase in heart rate (i.e., exercise state II), bias for grad(k 0 *grad+b 0 +c 0 ) ,use grad(k 0 *grad+b 0 +c 0 ) The correction is made using formula (4) p_dummy ,Right now, p_dummy = p_dummy + grad(k) 0 * grad+b 0 +c 0 ) .

[0125] During exercise in a state where the heart rate decreases slowly (i.e., exercise state III), bias For k1* grad+b 1 Using k1* grad+b 1 The correction is made using formula (4) p_dummy ,Right now, p_dummy=p_dummy+ k1* grad+b 1 .

[0126] See Figure 3 It provides a comparison chart between the cycling power estimated by the cycling power estimation method involved in the embodiments of this application (i.e., the estimated value) and the actual measured cycling power (i.e., the true value).

[0127] Cycling power can be obtained by the user wearing a power monitoring device (such as a power meter), see [link to relevant documentation]. Figure 3 As shown by the dashed line.

[0128] The cycling power obtained using the cycling power estimation method of this application can be found in [reference]. Figure 3 As shown by the solid line in the middle.

[0129] pass Figure 3 It can be seen that the trend of cycling power estimated by the cycling power estimation method described above is basically the same as the trend of the actual cycling power of the exercise user, and the estimated cycling power is basically similar to the actual cycling power.

[0130] See Figure 4 It provides a curve of the cumulative absolute error function relative to the confidence level, based on the mean absolute error between the estimated cycling power (i.e., the estimated value) and the actual measured cycling power (i.e., the true value); see [link to relevant documentation]. Figure 5 It gives the curve of the cumulative relative error function of the average relative error between the estimated power and the actual power and the relative confidence level.

[0131] In the absolute error cumulative function, the horizontal axis represents 0 to the maximum average absolute error, and the vertical axis represents the confidence level. In the relative error cumulative function, the horizontal axis represents 0 to the maximum average relative error, and the vertical axis represents the confidence level.

[0132] See Figure 4 It can be seen that the confidence level for a mean absolute error of less than 30W is over 80%; see [link / reference]. Figure 5 It can be seen that the confidence level of the mean relative error being less than 0.3W reaches about 90%.

[0133] Therefore, this cycling power estimation method has a high accuracy rate in estimating cycling power and does not require wearing power monitoring equipment, thus reducing cost investment.

[0134] In some embodiments of this application, see Figure 6It also involves an interactive system for estimating cycling power.

[0135] The cycling power estimation interactive system includes a heart rate acquisition device 100 and a terminal 200.

[0136] The heart rate acquisition device 100 is used to collect the heart rate data of the exercise user and send it to the terminal 200.

[0137] The terminal 200 can communicate with a stopwatch or smart device (e.g., mobile phone, smartwatch, tablet) that is connected to the heart rate acquisition device 100.

[0138] The cycling power estimation method described above is integrated into the terminal 200 for performing cycling power estimation.

[0139] The estimated cycling power can be displayed on the front end of the terminal 200 for easy viewing by the user.

[0140] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions claimed by the present invention.

Claims

1. A method for estimating cycling power, characterized in that, include: Get the maximum heart rate hr_max of the user who is exercising; Based on the maximum heart rate hr_max, average heart rate, and resting heart rate hr_rest, the real-time oxygen uptake (VO2) of the exercise user is obtained: A sliding window method is used to obtain the average heart rate within the window in real time, which is used as the average heart rate hr_mean of the exercise user. Based on the maximum heart rate hr_max, hr_mean, and resting heart rate hr_rest, the formula is used... The real-time oxygen uptake (vo2) of the exercise user is obtained, where α is an experimental coefficient characterizing the conversion of oxygen uptake heart rate. Based on the real-time oxygen uptake vo2, the weight of the exercise user m_body, and the weight of the bicycle m_bake, the cycling power p_dummy is estimated in reverse: p_dummy=vo2*( m_body+m_bake)-a / b where a and b are the bias correction empirical value and the coefficient correction empirical value, respectively. A sliding window approach is used to obtain the window's central velocity gradient (grad) in real time. Where n represents the length of the sliding window, i represents the counting point within the sliding window; hr(i) represents the i-th heart rate value within the sliding window. When the heart rate gradient is greater than the preset gradient value d0, it indicates that the exercise user is in a state of rapid heart rate increase. Otherwise, it is determined whether the heart rate gradient is less than 0. If it is, it indicates that the exercise user is in a state of slow heart rate decrease. Otherwise, it indicates that the exercise user is in a state of stable heart rate change. Based on the heart rate gradient of the exercise user under different exercise states, the bias correction for different exercise states is calculated, specifically as follows: ； Among them, d0 is greater than 0.5 and less than or equal to 1, and k0, b0, c0, k1, and b1 are all obtained by fitting heart rate and power data from multiple user samples; The bias correction under different exercise states is used to correct the estimated cycling power, so as to obtain the cycling power of the exercise user under different exercise states: p_dummy = p_dummy + bias.

2. The cycling power estimation method according to claim 1, characterized in that, To obtain the maximum heart rate hr_max of a user during exercise, the specific steps are as follows: Calculate the maximum heart rate hr_max1 using the age of the exercise user; ； The maximum heart rate hr_max is initialized using the maximum heart rate hr_max1; A sliding window approach is used to obtain the real-time heart rate of the latest active user entering the window. The real-time heart rate is compared with the maximum heart rate hr_max. If the real-time heart rate is greater than or equal to the maximum heart rate hr_max, the maximum heart rate hr_max is updated using the real-time heart rate. If the real-time heart rate is less than the maximum heart rate hr_max, the maximum heart rate hr_max is not updated.

3. A cycling power estimation system, characterized in that, include: The heart rate acquisition module is used to obtain the maximum heart rate hr_max of the exercise user; The oxygen uptake acquisition module uses a sliding window approach to acquire the average heart rate within the window in real time, which is used as the average heart rate hr_mean of the exercise user. The oxygen uptake acquisition module is based on the maximum heart rate hr_max, hr_mean, and resting heart rate hr_rest, using a formula... The real-time oxygen uptake (vo2) of the exercise user is obtained, where α is an experimental coefficient characterizing the conversion of oxygen uptake heart rate. The power estimation module is used to estimate the cycling power p_dummy in reverse based on the real-time oxygen uptake vo2, the weight of the exercise user m_body and the weight of the bicycle m_bake: p_dummy = vo2*( m_body+m_bake)-a / b, where a and b are the bias correction empirical value and the coefficient correction empirical value, respectively. The bias correction calculation module uses a sliding window approach to obtain the window's incenter gradient (grad) in real time. Where n represents the length of the sliding window, i represents the counting point within the sliding window; hr(i) represents the i-th heart rate value within the sliding window. When the heart rate gradient is greater than the preset gradient value d0, it indicates that the exercise user is in a state of rapid heart rate increase; otherwise, it determines whether the heart rate gradient is less than 0. If it is, it indicates that the exercise user is in a state of slow heart rate decrease; otherwise, it indicates that the exercise user is in a state of stable heart rate change. The bias correction calculation module is used to calculate the bias correction bias under different exercise states based on the heart rate gradient of the exercise user under different exercise states, specifically: ； Among them, d0 is greater than 0.5 and less than or equal to 1, and k0, b0, c0, k1, and b1 are all obtained by fitting heart rate and power data from multiple user samples; The power correction module uses bias correction bias under different exercise states to correct the estimated cycling power, so as to obtain the cycling power of the exercise user under different exercise states: p_dummy = p_dummy + bias.

4. A cycling power estimation interactive system, characterized in that, include: Heart rate monitoring devices are used to collect heart rate data from exercise users. The terminal receives the heart rate data, the physiological information of the exercise user, and the weight of the bicycle, and executes the cycling power estimation method as described in claim 1 or 2, and displays the cycling power on the front end of the terminal.

Images