Cycling calorie consumption calculation method and system

Abstract

The present invention provides a cycling calorie consumption calculation method and system, the method comprising: obtaining a connected external device through a code table; obtaining basic information of cycling users, and dividing users into corresponding population groups through big data analysis based on physiological characteristics of the population; obtaining a relationship coefficient corresponding to the same calorie estimation scheme in the corresponding population group according to the population group to which the user belongs; the relationship coefficient is a relationship coefficient obtained by calibrating the coefficient of the second highest precision calorie estimation scheme through a high precision calorie estimation result based on machine learning; collecting data based on the relationship coefficient and the external device, calculating the calories consumed by cycling in real time; if the code table has no connected external device, calculating the calories consumed by cycling based on the relationship coefficient and the principle of physics. The scheme realizes accurate calculation of cycling calorie consumption and reduces estimation errors.

Description

Technical Field

[0001] The invention belongs to the technical field of bicycle computers, and in particular relates to a cycling calorie consumption calculation method and system. Background Art

[0002] Cycling is a sport with a wide range of users, and has many uses, such as transportation, exercise and fitness, and sports competitions. When riding, cyclists continuously pedal to drive the bicycle forward, which consumes calories. Generally, kilocalories are used as the unit of measurement for calorie consumption. During the riding process, real-time calculation of the calories consumed by the user is important for evaluating the user's exercise effect and guiding the user's training.

[0003] If you want to accurately calculate the calorie consumption of cycling, you can usually only measure it in a laboratory or with professional equipment. This method is expensive and cannot be used in daily life. It is only used for scientific research, athlete training, etc. In practice, research has found that other data indicators can be used to estimate calories, which can be close to the actual value to a certain extent. At present, common estimation methods include using bicycle power meters, maximum oxygen uptake, heart rate, physical principles, or empirical formulas, etc., combined with corresponding algorithms, to obtain calorie estimates, and the estimation accuracy decreases in turn. The parameters used in these methods are fixed, ignoring the individual differences of each rider. In addition, due to the influence of factors such as the vehicle itself, road sections, and weather, the actual estimated calorie consumption value is not accurate. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a cycling calorie consumption calculation method and system, which are used to solve the problem of low accuracy in cycling calorie consumption calculation.

[0005] In a first aspect of an embodiment of the present invention, a method for calculating calorie consumption during cycling is provided, comprising:

[0006] Obtaining a connected external device through a code table, wherein the external device is one of a power meter, a sports wearable device for measuring maximum oxygen uptake and heart rate, and a heart rate belt;

[0007] Obtain basic information of cycling users and classify them into corresponding groups based on their physiological characteristics through big data analysis;

[0008] According to the population group to which the user belongs, obtaining the relationship coefficient corresponding to the same calorie estimation scheme in the corresponding population group;

[0009] Wherein, the relationship coefficient is a relationship coefficient obtained by calibrating the coefficient of the second-highest precision calorie estimation scheme through the high-precision calorie estimation result based on machine learning;

[0010] Calculate the calories consumed by cycling in real time according to the relationship coefficient and data collected by external devices;

[0011] If the cycling computer has no external device connected, the calories consumed by cycling are calculated according to the relationship coefficient and the principle of physics.

[0012] In a second aspect of an embodiment of the present invention, a cycling calorie consumption calculation system is provided, comprising:

[0013] Obtaining a connected external device through a code table, wherein the external device is one of a power meter, a sports wearable device for measuring maximum oxygen uptake and heart rate, and a heart rate belt;

[0014] Obtain basic information of cycling users and classify them into corresponding groups based on their physiological characteristics through big data analysis;

[0015] According to the population group to which the user belongs, obtaining the relationship coefficient corresponding to the same calorie estimation scheme in the corresponding population group;

[0016] Wherein, the relationship coefficient is a relationship coefficient obtained by calibrating the coefficient of the second-highest precision calorie estimation scheme through the high-precision calorie estimation result based on machine learning;

[0017] Calculate the calories consumed by cycling in real time according to the relationship coefficient and data collected by external devices;

[0018] If the cycling computer has no external device connected, the calories consumed by cycling are calculated according to the relationship coefficient and the principle of physics.

[0019] In a third aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect of the embodiment of the present invention when executing the computer program.

[0020] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiment of the present invention are implemented.

[0021] In the embodiment of the present invention, based on big data and machine learning technology, different population groups are divided and the relationship coefficients of different population groups are optimized and calibrated, so as to provide personalized relationship coefficients for different population groups to calculate calorie consumption, thereby improving the accuracy of cycling calorie estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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 or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic diagram of a flow chart of a cycling calorie consumption calculation method provided by an embodiment of the present invention;

[0024] Figure 2 Another schematic diagram of a flow chart of a cycling calorie consumption calculation method provided by an embodiment of the present invention;

[0025] Figure 3 A schematic diagram of the structure of a cycling calorie consumption calculation system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, 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 embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be understood that the term "including" and other similar expressions in the specification or claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, such as a process, method, system, or device including a series of steps or units is not limited to the listed steps or units. In addition, "first" and "second" are used to distinguish different objects, not to describe a specific order.

[0028] It should be noted that known calorie estimation methods include calculation based on a bicycle power meter, calculation based on maximum oxygen uptake, calculation based on heart rate, calculation based on principles of physics, and calculation based on empirical formulas. The estimation accuracy of each scheme decreases in turn, among which the estimation accuracy based on a bicycle power meter is the highest.

[0029] A bicycle power meter is a device installed on the crank, chainring, pedal, etc. of a bicycle (depending on the specific product) that can calculate the user's cycling power in real time. The general principle is to calculate the force applied by the user based on the deformation of the device, thereby calculating the torque, and then calculating the user's power. Studies have found that the work done by the user during cycling is about 20%~25% of the total heat generated by the human body, and generally the greater the power, the higher the proportion. Therefore, a power meter is used to obtain the user's power, and the power is used to calculate the user's work, and then multiplied by a conversion ratio (4~5) to calculate calories. The power meter method is the most accurate calorie estimation algorithm currently known. However, the conversion ratio is actually a function of power. This function is not the same for different people, and it will change with the improvement of training level, changes in physical condition, etc.

[0030] Maximum oxygen uptake refers to the maximum amount of oxygen that the human body can take in when exercising at the maximum intensity. It is an important indicator of the body's aerobic exercise capacity. The human body generates heat through a series of chemical reactions, and this process consumes oxygen. This process can be regarded as a slow combustion process. Generally speaking, the more oxygen consumed, the more intense the combustion, and therefore the more heat generated. Therefore, calories can be estimated using oxygen consumption. Studies have found that when other factors remain unchanged, there is a linear relationship between calories and maximum oxygen uptake. Generally, sports watches / bracelets are commonly used to measure maximum oxygen uptake. This solution is less accurate than the power meter and more accurate than the heart rate solution. The relationship between calories and maximum oxygen uptake is an empirical formula. The coefficients of this empirical formula vary among different groups of people and change with the improvement of personal training level, physical condition, etc.

[0031] Heart rate refers to the number of heartbeats per minute. Within a certain range, the more intense the exercise, the higher the heart rate and the more calories consumed. At the same time, heart rate is also related to the oxygen intake of the human body. Therefore, heart rate can also be used to estimate calories. Studies have found that when other factors remain unchanged, there is a linear relationship between heart rate and calories. Heart rate is generally measured with a heart rate meter. This scheme is less accurate than the maximum oxygen uptake and slightly better than the physics principle scheme. Similarly, the relationship between calories and heart rate is an empirical formula, and the coefficients of the empirical formula change with different populations, the improvement of personal training level, and changes in physical condition. In addition, heart rate is easily affected by the environment, personal stress, diet, drugs, etc., which has a certain impact on calorie estimation.

[0032] The principle of physics is to estimate the amount of force applied by the user, combined with the known user's cycling speed, the user's cycling power can be calculated according to the formula "power = force × speed", and then the calories can be obtained by referring to the power meter method.

[0033] Specifically, for the estimation of the force applied by the user: the forces applied to the user during riding include friction resistance Fr, air resistance Fa, gravity component Fg when going uphill and downhill, force corresponding to acceleration Facc, and upward elastic force of the vertical road surface when bumpy, etc. Generally, only the first four forces are considered.

[0034] Then F = Fr + Fa + Fg + Facc,

[0035] Where, Fr = Cr * mg, Fa = Ca * v^2 (v^2 represents the square of velocity), Fg = mgsinθ, Facc =ma.

[0036] M is the sum of the human body weight and the bicycle weight, g is the acceleration due to gravity (9.8m / s^2), Cr is the friction coefficient between the tire and the ground, Ca is the air resistance coefficient, v is the amplitude of the vector sum of the riding speed and the wind speed, θ is the angle between the slope and the ground when going up and down the slope (hereinafter referred to as the slope angle), and a is the riding acceleration, only positive acceleration is taken.

[0037] When the slope angle is small, sinθ≈tanθ≈θ, which means that the slope can be used instead of sinθ.

[0038] Compared with the power meter solution, this solution still has the following problems: First, the friction coefficient is difficult to determine, and Cr is affected by many factors, including tire type, tire condition, ground condition and weather. Generally speaking, the friction coefficient of a road bike is smaller than that of a mountain bike on the same road section. The friction coefficient of the same bicycle is different on different road conditions such as cement ground, asphalt road, stone road, sand surface, and muddy ground. Even on the same road section, the friction coefficient is different in different weather conditions such as sunny days, rainy days, and snowy days. Second, the air resistance coefficient is difficult to determine, and Ca is affected by many factors such as the user's body shape, clothing, and bicycle type. Third, it is easily affected by wind force, and wind factors are difficult to measure in real time: general equipment cannot measure wind speed and wind direction. Therefore, if a fixed friction coefficient and air resistance coefficient are used, and the influence of wind factors is ignored, it will have a great impact on the calorie calculation results.

[0039] The empirical formula roughly estimates the user's calorie consumption rate based on the user's personal physiological information such as gender, weight, riding speed, uphill and downhill conditions, etc., and then multiplies it by time to calculate the calories.

[0040] See also Figure 1 , a schematic diagram of a flow chart of a cycling calorie consumption calculation method provided by an embodiment of the present invention, including:

[0041] S101, obtaining a connected external device through a code table, wherein the external device is one of a power meter, a sports wearable device for measuring maximum oxygen uptake and heart rate, and a heart rate belt;

[0042] The code table at least includes GPS, a barometric altimeter, an ANT communication module and a Bluetooth communication module. The code table communicates with the external device based on the ANT or ANT+ protocol, and acquires the external device collection information based on the connection between the code table and the external device.

[0043] The power meter, sports wearable device and heart rate belt are used to collect the riding power, maximum oxygen uptake and heart rate of the riding user respectively. When the meter is connected to any device, the calorie estimation method corresponding to the device is used for estimation. The sports wearable device can be a sports bracelet or a watch.

[0044] It should be understood that the cycling computer also has the function of collecting or calculating the riding speed (including the riding speed relative to the wind) and the slope.

[0045] S102, obtaining basic information of cycling users, and classifying the users into corresponding groups based on physiological characteristics of the group through big data analysis;

[0046] The basic information of users is obtained through smart terminals (such as mobile phones). An APP is deployed on the terminal to enter user information, including gender, age, height, weight, bicycle type, tire type, etc. The terminal can also be used for data communication and data synchronization. The terminal can be connected to the meter to upload the collected data in the meter, and can connect to the remote server to classify users and obtain the relationship coefficient.

[0047] Collect a large amount of user data and classify users according to certain standards through big data analysis.

[0048] Specifically, the population is divided at least according to gender, age, weight, height and athletic ability so that people in the same group have similar physiological levels.

[0049] For example, gender only includes male and female; age can be divided into 8 stages, starting from 0 years old, in increments of 10 years old, 0-10, 10-20, 20-30, 30-40, 40-50, 50-60, 60-70, 70+, etc.; user training level can be divided into 6 levels, including novice, entry, intermediate, advanced, expert, and world-class player. In this way, a total of 3×2×8×6=288 groups can be divided.

[0050] The athletic ability rating is an evaluation index of the user's cycling ability. The stronger the user's athletic ability and the higher the professional level, the higher the rating. Different ratings will result in different coefficients in the various equations used to calculate calories.

[0051] The user's athletic ability is graded based on the user's riding record and historical riding record. The grading evaluation indicators include but are not limited to average riding speed, maximum riding speed, average riding power, maximum riding power and riding distance. For example, if the user's average speed exceeds 60% of all people, the score is 60, and the maximum speed exceeds 50%, the score is 50, and so on. The rest get 70, 40, and 90, and the average score is 62 points, and the athletic ability is classified as intermediate.

[0052] S103, obtaining, according to the population group to which the user belongs, a correlation coefficient corresponding to the same calorie estimation scheme in the corresponding population group;

[0053] After dividing the users into different groups, the correlation coefficient corresponding to the calorie estimation scheme in the group is obtained. If a power meter is used for estimation, the correlation coefficient corresponding to the power meter in the group, that is, the conversion ratio, is obtained.

[0054] Wherein, the relationship coefficient is a relationship coefficient obtained by calibrating the coefficient of the second-highest precision calorie estimation scheme through the high-precision calorie estimation result based on machine learning;

[0055] Before estimating the calories burned by the user while riding, the cycle computer needs to obtain the relationship coefficient in the estimation scheme. The relationship coefficient is obtained by the remote server through a machine learning model after calibrating the relationship coefficient in each estimation scheme. The relationship coefficients corresponding to different user groups and different estimation schemes are different.

[0056] Specifically, in the same group, the result of the most accurate calorie estimation scheme is obtained as the true value, and the true value is used as the target value of the sub-accurate calorie estimation scheme, and the riding data collected by the sub-accurate calorie estimation scheme is used as input, and the relationship coefficient of the sub-accurate calorie estimation scheme is calibrated through the machine learning model;

[0057] The calorie estimation schemes include an estimation scheme based on a power meter, an estimation scheme based on maximum oxygen uptake, an estimation scheme based on heart rate, an estimation scheme based on physical principles, and an estimation scheme based on an empirical formula. The accuracy of each estimation scheme decreases in turn, and the estimation scheme based on a power meter has the highest accuracy.

[0058] The calorie estimation results measured in the laboratory are used as target values ​​to calibrate the relationship coefficients of the estimation scheme based on the power meter.

[0059] For example, taking power calibration heart rate as an example, the forward process of the calorie calculation heart rate solution is: according to the user configuration, the age A and weight information W are obtained, and the calorie consumption per second is calculated as follows:

[0060] cal = (C0 * HR + C1 * W + C2 * A + C3) / 4.186

[0061] Among them, C0~C3 are the relationship coefficients obtained from the server at the beginning of riding, and HR is the heart rate obtained from the peripheral device every second. Substituting them into the formula can obtain cal.

[0062] The calorie estimate with higher accuracy (i.e. the estimate based on the power meter) is used as the target value, and the W, A, and HR use the values ​​in the cycling record. A set of data (HR, W, A, cal) is collected every second, and there are several sets of data in one ride. The values ​​of C0~C3 can be inferred based on these collected data.

[0063] Specifically, set a set of iteration basic values ​​of C0~C3, for example, all are 0.5; substitute the first set (HR, W, A) to calculate a cal value, which will be compared with the corresponding cal value. If it is larger, reduce the value of C0~C3, otherwise increase it; repeat the above process, substitute each remaining set of values ​​in turn, and reduce or increase C0~C3 according to the results; when the end condition is met (such as all collected data have been tried or the coefficient has changed little), stop execution and return to C0~C3.

[0064] The data of each user's ride will be calculated once to obtain a set of coefficients for each plan. The estimated plan coefficients are analyzed using big data technology. From all the coefficient groups of the group, a set of the most accurate or most suitable coefficients is selected as the calculation coefficients for the group. The selection method includes but is not limited to taking the average value, median, etc. The estimated plan coefficients based on the power meter are continuously updated by the actual measurement results in the laboratory.

[0065] S104, calculating the calories consumed by cycling in real time according to the relationship coefficient and data collected by external devices;

[0066] Before each ride, the relationship coefficient obtained by the server through machine learning calibration will be synchronized to the cycle meter. The cycle meter will find the corresponding relationship coefficient according to the group (or population) to which the user belongs, and combine it with the power, maximum oxygen uptake or heart rate data collected by external devices to calculate the calories consumed in real time.

[0067] Specifically, if the external device is a power meter:

[0068] The computer receives the power data sent by the power meter and uses it to calculate the calorie consumption at a frequency of 1 Hz.

[0069] Calorie value is calculated according to the formula:

[0070] W = P * 1;

[0071] cal = f(P) * W / 4.186;

[0072] In the formula, W represents the work done by the user in 1s, in J (joule); P is the user's cycling power, in watts; cal is the amount of heat consumed by the user, in calories (about 4.186J); f(P) is the conversion ratio between the work done by the user and the heat consumed, which is a dimensionless function of P.

[0073] Because cycling work only accounts for 20% to 25% of the body's calorie consumption, it is necessary to multiply it by a coefficient to get the actual calorie consumption. According to research, f(P) is a nonlinear function of P, which has the following form:

[0074] ;

[0075] Where N is the order, which can be between 3 and 6, depending on the allowable error (i.e., the error allowed by the product specifications. Generally, the smaller the required error, the larger the N value). a i Represents the relationship coefficient, which can be obtained from the server.

[0076] Accumulate the calorie consumption value per second and divide the accumulated value by 1000 to get the user's real-time calories.

[0077] If the external device is a sports bracelet / watch:

[0078] The meter obtains the maximum oxygen uptake and heart rate data from the sports watch / bracelet every second and calculates the calorie consumption at a frequency of 1Hz;

[0079] Calorie consumption is calculated using the following formula:

[0080] cal = C0 * VO2max + C1 * HR + C2 * W + C3 * A + C4;

[0081] In the formula, cal is the calories consumed by the user, VO2max is the maximum oxygen uptake, HR is the heart rate, W is the user's weight, A is the user's age, and C0~C4 are relationship coefficients, which can be obtained from the server.

[0082] Accumulate the calorie consumption value per second and divide the accumulated value by 1000 to get the user's real-time calories.

[0083] If the external device is a heart rate monitor:

[0084] The computer obtains heart rate data from the heart rate belt every second and calculates calorie consumption at a frequency of 1Hz;

[0085] Calorie consumption is calculated using the following formula:

[0086] cal = C0 * HR + C1 * W + C2 * A + C3;

[0087] Where cal is the calories consumed by the user, H is the heart rate, W is the user's weight, A is the user's age, and C0~C3 are relationship coefficients that can be obtained from the server.

[0088] Accumulate the calorie consumption value per second and divide the accumulated value by 1000 to get the user's real-time calories.

[0089] S105: If the cycling computer has no external device connected, the calories consumed by cycling are calculated according to the relationship coefficient and the principle of physics.

[0090] When there is no external device connected to the computer, that is, no power meter, sports wearable device or heart rate belt, the calories burned by cycling are estimated based on the principles of physics. The correlation coefficient can be found according to the user's group category.

[0091] Specifically, the meter obtains GPS information every second, including the current GPS location (latitude and longitude) and GPS speed, and uploads it to the terminal. Based on the GPS location, the terminal obtains the meteorological data of the current location from the server, including weather, wind speed, wind direction, and road surface conditions and air resistance coefficient Ca;

[0092] The terminal calculates the direction of travel based on the current location information and the location information of the previous second, and then calculates the speed of movement relative to the wind. The calculation formula is as follows:

[0093] v r = v - v * v W * cosθ ;

[0094] In the formula, v r is the speed of the rider relative to the wind, v is the riding speed, v W is the wind speed, θ is the angle between the forward direction and the wind direction;

[0095] After the calculation is completed, v r Send to the code table.

[0096] The terminal obtains the friction coefficient Cr by looking up the table according to the straight-moving vehicle information and bicycle tire information, current weather, and current road surface information configured by the user, and sends it to the code meter;

[0097] The computer calculates the current slope, and based on the speed in the previous second, calculates the acceleration a;

[0098] The code table calculates the current resultant force as follows: F = Fr + Fa + Fg + Facc;

[0099] In the formula, Fr = mg * Cr, Fa = Ca * v r ^2, Fg = mg * slope, Facc = m * a;

[0100] M is the user's weight plus the weight of the bicycle, g is the acceleration of gravity, Cr is the friction coefficient, Ca is the air resistance coefficient, v r is the speed of the rider relative to the wind, slope is the slope, and a is the forward acceleration, which only takes positive values.

[0101] Calculate 1s cycling power as: P = F * v;

[0102] The heat consumption in this 1s is calculated as: cal = f(P) * P;

[0103] Accumulate the calorie consumption value per second and divide the accumulated value by 1000 to get the user's real-time calories.

[0104] Optionally, if the computer communication is abnormal, the external device fails, or the basic user information cannot be obtained, the calories are calculated based on the empirical formula:

[0105] Cal=c0×v+c1×slope+c2×W+c3×A+c4;

[0106] Where Cal is the estimated calorie value, c0, c1, c2, c3, and c4 are relationship coefficients, v is the bicycle speed, slope is the riding slope, W is the user's weight, and A is the user's age.

[0107] like Figure 2 As shown, when an external device, a cycling computer, or a mobile phone used to input user information fails to collect data or communicate normally, calorie estimation is performed according to an empirical formula.

[0108] In this embodiment, users are divided based on big data and machine learning, and corresponding algorithms and relationship coefficients are used to calculate cycling calorie consumption according to different external devices, which can effectively improve the accuracy of the calculation results.

[0109] In one embodiment, if the user uses a power meter and a heart rate monitor:

[0110] When a user uses the app for the first time, he or she configures his or her personal information, including gender, age, height, weight, bicycle type, tire model, etc., and synchronizes it to the server. The server classifies the user for the first time and divides it into the corresponding group.

[0111] When riding starts, it is detected that the user has installed a power meter and is wearing a heart rate belt. The computer obtains the power conversion ratio function of the user's group from the server through the mobile phone and saves it locally.

[0112] The computer receives the power data from the power meter and calculates the calorie consumption once a second. The calculation formula is as follows:

[0113] W = P * 1;

[0114] cal = f(P) * W / 4.186;

[0115] The energy consumption is accumulated and divided by 1000 to get the calories, which are then displayed to the user.

[0116] The power, heart rate, riding speed, slope, GPS location, etc. at this time are recorded and sent to the mobile phone. Based on the GPS location, the mobile phone obtains the weather, road conditions, wind speed, wind direction and other information of the current location from the server every second. The movement direction is calculated based on the current GPS location and the GPS location of the previous second. If the wind direction is known, the angle θ between the movement direction and the wind direction can be calculated, and then the movement speed of the user relative to the wind can be calculated. The formula is as follows:

[0117] v r = v - v * v W * cosθ ;

[0118] Based on the type of bicycle, tire type, ground conditions, weather, etc., the current friction coefficient is calculated by looking up the table.

[0119] The mobile phone saves the data sent by the code computer, the friction coefficient, the calculated movement speed relative to the wind, etc.

[0120] When the ride is over, the mobile phone sends the ride record to the server.

[0121] The server parses the data and finds power data and heart rate data. It then uses the power meter data to calibrate the heart rate solution coefficient. The calibration process is as follows:

[0122] According to the user's group, obtain their power conversion ratio function and recalculate the heat consumption per second;

[0123] Combine the exercise data per second, including heart rate, weight, age and power-recalculated calorie consumption, use the power-recalculated calorie consumption as the target value of the heart rate program, use heart rate, weight and age as input, and use machine learning to calculate the coefficients of each relationship;

[0124] The calculated coefficient is added to the heart rate coefficient library of the population, and the most universal heart rate coefficient is calculated using big data, and is used as the latest heart rate coefficient of the current population. The calculation method can be weighted average, etc.

[0125] At the same time, the power meter data can also be used to calibrate the physical solution and calibrate the empirical formula.

[0126] The user's athletic ability level is evaluated based on the average speed, maximum speed, riding distance, average power, maximum power and other data in the cycling record. The better the performance, the greater the athletic ability level. If the athletic ability level changes, the user will be moved to the corresponding group.

[0127] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0128] Figure 3 A schematic diagram of a cycling calorie consumption calculation system provided by an embodiment of the present invention, the system at least includes:

[0129] The code meter 310 is used to obtain the connected external device and obtain the correlation coefficient corresponding to the same calorie estimation scheme according to the group to which the user belongs, and calculate the calories consumed by riding in real time according to the correlation coefficient and the data collected by the external device;

[0130] The external device is one of a power meter, a sports wearable device for measuring maximum oxygen uptake and heart rate, and a heart rate belt;

[0131] If the computer is not connected to an external device, the calories consumed during cycling are calculated based on the relationship coefficient and the principle of physics.

[0132] The cycling computer 310 at least includes a GPS, a barometric altimeter, an ANT communication module and a Bluetooth communication module.

[0133] The intelligent terminal 320 is used to obtain basic information of the cycling user, upload the data collected by the meter and the basic information of the user to the server, and synchronize the relationship coefficient and user classification calibrated by the server to the meter;

[0134] The smart terminal can also be used to calculate the riding speed, the riding speed relative to the wind direction, etc., obtain the weather, road conditions, wind direction and speed data queried by the server, and send the riding speed data to the meter.

[0135] Server 330 is used to classify users into corresponding population groups through big data analysis based on the physiological characteristics of the population, and calibrate the relationship coefficient of the second highest precision calorie estimation scheme through the high precision calorie estimation result based on machine learning.

[0136] Among them, the population is divided at least according to gender, age, weight, height and athletic ability, so that people in the same group have similar physiological levels.

[0137] Specifically, in the same group, the result of the most accurate calorie estimation scheme is obtained as the true value, and the true value is used as the target value of the sub-accurate calorie estimation scheme, and the riding data collected by the sub-accurate calorie estimation scheme is used as input, and the relationship coefficient of the sub-accurate calorie estimation scheme is calibrated through the machine learning model;

[0138] The calorie estimation schemes include an estimation scheme based on a power meter, an estimation scheme based on maximum oxygen uptake, an estimation scheme based on heart rate, an estimation scheme based on physical principles, and an estimation scheme based on an empirical formula. The accuracy of each estimation scheme decreases in turn, and the estimation scheme based on a power meter has the highest accuracy.

[0139] The calorie estimation results measured in the laboratory are used as target values ​​to calibrate the relationship coefficients of the estimation scheme based on the power meter.

[0140] Optionally, if the computer communication is abnormal, the external device fails, or the basic user information cannot be obtained, the calories are calculated based on the empirical formula:

[0141] Cal=c0×v+c1×slope+c2×W+c3×A+c4;

[0142] Where Cal is the estimated calorie value, c0, c1, c2, c3, and c4 are relationship coefficients, v is the bicycle speed, slope is the riding slope, W is the user's weight, and A is the user's age.

[0143] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described system and module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0144] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0145] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes steps S101 to S105, and the storage medium includes ROM / RAM, etc.

[0146] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0147] As described above, 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, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced 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 of the embodiments of the present invention.

Claims

1. A method for calculating cycling calorie consumption, characterized in that: include: Obtaining a connected external device through a code table, wherein the external device is one of a power meter, a sports wearable device for measuring maximum oxygen uptake and heart rate, and a heart rate belt; Obtain basic information of cycling users and classify them into corresponding groups based on their physiological characteristics through big data analysis; According to the population group to which the user belongs, obtaining the relationship coefficient corresponding to the same calorie estimation scheme in the corresponding population group; Wherein, the relationship coefficient is a relationship coefficient obtained by calibrating the coefficient of the second-highest precision calorie estimation scheme through the high-precision calorie estimation result based on machine learning; The relationship coefficients obtained by calibrating the coefficients of the second highest precision calorie estimation scheme with the high precision calorie estimation result include: In the same group, the result of the most accurate calorie estimation scheme is obtained as the true value, and the true value is used as the target value of the sub-accurate calorie estimation scheme. The riding data collected by the sub-accurate calorie estimation scheme is used as input, and the relationship coefficient of the sub-accurate calorie estimation scheme is calibrated through the machine learning model; The calorie estimation schemes include an estimation scheme based on a power meter, an estimation scheme based on maximum oxygen uptake, an estimation scheme based on heart rate, an estimation scheme based on physical principles, and an estimation scheme based on an empirical formula. The accuracy of each estimation scheme decreases in turn, and the estimation scheme based on a power meter has the highest accuracy. Among them, the calorie estimation results measured in the laboratory are used as target values ​​to calibrate the relationship coefficients of the estimation scheme based on the power meter; Calculate the calories consumed by cycling in real time according to the relationship coefficient and data collected by external devices; If the cycling computer has no external device connected, the calories consumed by cycling are calculated according to the relationship coefficient and the principle of physics.

2. The method according to claim 1, characterized in that The code table at least includes a GPS, a barometric altimeter, an ANT communication module and a Bluetooth communication module.

3. The method according to claim 1, characterized in that The method of classifying users into corresponding groups based on physiological characteristics of the group through big data analysis also includes: The population is divided into at least sex, age, weight, height and athletic ability categories so that people in the same group have similar physiological levels.

4. The method according to claim 1, characterized in that: If the cycling computer is not connected to an external device, then according to the relationship coefficient and the principle of physics, calculating the calories consumed by cycling also includes: If the computer communication is abnormal, the external device fails, or the basic user information cannot be obtained, the calories are calculated based on the empirical formula: Cal=c0×v+c1×slope+c2×W+c3×A+c4; Where Cal is the estimated calorie value, c0, c1, c2, c3, and c4 are relationship coefficients, v is the bicycle speed, slope is the riding slope, W is the user's weight, and A is the user's age.

5. A cycling calorie consumption calculation system, characterized in that: At least: The cycling computer is used to obtain the connected external device and obtain the correlation coefficient corresponding to the same calorie estimation scheme according to the group to which the user belongs, and calculate the calories consumed by cycling in real time according to the correlation coefficient and the collected data of the external device, wherein the external device is one of a power meter, a sports wearable device for measuring maximum oxygen uptake and heart rate, and a heart rate belt; If the computer is not connected to an external device, the calories consumed during cycling are calculated based on the relationship coefficient and the principle of physics. The intelligent terminal is used to obtain basic information of cycling users, upload the data collected by the meter and basic information of users to the server, and synchronize the relationship coefficient and user classification calibrated by the server to the meter; A server, configured to classify users into corresponding groups of people through big data analysis based on physiological characteristics of the group, and to calibrate the relationship coefficient of the second-highest precision calorie estimation scheme through the high-precision calorie estimation result based on machine learning; The step of calibrating the relationship coefficient of the second highest precision calorie estimation scheme by using the high precision calorie estimation result includes: In the same group, the result of the most accurate calorie estimation scheme is obtained as the true value, and the true value is used as the target value of the sub-accurate calorie estimation scheme. The riding data collected by the sub-accurate calorie estimation scheme is used as input, and the relationship coefficient of the sub-accurate calorie estimation scheme is calibrated through the machine learning model; The calorie estimation schemes include an estimation scheme based on a power meter, an estimation scheme based on maximum oxygen uptake, an estimation scheme based on heart rate, an estimation scheme based on physical principles, and an estimation scheme based on an empirical formula. The accuracy of each estimation scheme decreases in turn, and the estimation scheme based on a power meter has the highest accuracy. The calorie estimation results measured in the laboratory are used as target values ​​to calibrate the relationship coefficients of the estimation scheme based on the power meter.

6. The system according to claim 5, characterized in that The code table at least includes a GPS, a barometric altimeter, an ANT communication module and a Bluetooth communication module.

7. The system according to claim 5, characterized in that The classification of users into corresponding groups based on physiological characteristics of the group through big data analysis includes: The population is divided into at least sex, age, weight, height and athletic ability categories so that people in the same group have similar physiological levels.

8. The system according to claim 5, characterized in that If the cycling computer is not connected to an external device, then according to the relationship coefficient and the principle of physics, calculating the calories consumed by cycling also includes: If the computer communication is abnormal, the external device fails, or the basic user information cannot be obtained, the calories are calculated based on the empirical formula: Cal=c0×v+c1×slope+c2×W+c3×A+c4; Where Cal is the estimated calorie value, c0, c1, c2, c3, and c4 are relationship coefficients, v is the bicycle speed, slope is the riding slope, W is the user's weight, and A is the user's age.

Images