A step counting method, training method and electronic device based on a smart wearable device

Abstract

A step counting method, a training method and an electronic device based on a smart wearable device provided by an embodiment of the present application relate to the technical field of step counting methods. The method is applied to an electronic device and includes the following steps: obtaining real-time motion data collected by a smart wearable device of a target user; performing frequency domain transformation on the real-time motion data to obtain first frequency domain information; obtaining real-time pressure data on the surface of a running belt of a treadmill collected by a sensor array of the treadmill; performing frequency domain transformation on the real-time pressure data to obtain second frequency domain information; at preset time intervals, determining whether the motion in the current time period is effective motion according to the similarity between the main frequencies of the first frequency domain information and the second frequency domain information in the current time period; when it is determined that the motion in the current time period is effective motion, calculating the number of running steps in the current time period according to a step frequency and step number model. The step counting method based on a smart wearable device provided by the embodiment of the present application can obtain accurate step counting data.

Description

Technical Field

[0001] The present application relates to the technical field of step counting methods, and particularly to a step counting method, a training method and an electronic device based on a smart wearable device. Background Art

[0002] The number of exercise steps is an important parameter in the fitness process, which directly reflects the amount of exercise. The more steps there are, usually the longer the exercise time and the greater the amount of exercise, which has a positive effect on improving cardiopulmonary function and enhancing physical fitness.

[0003] Related step counting methods use the step length and the mileage counted by the treadmill to count steps. Since the mileage will also increase when the treadmill is idling, the step count value obtained based on the mileage may be inaccurate, which will affect the exercise training plan.

[0004] Therefore, how to obtain an accurate step count value is a technical problem to be solved urgently. Summary of the Invention

[0005] In view of this, the embodiments of the present application provide a step counting method, a training method and an electronic device based on a smart wearable device, which can obtain accurate step count data.

[0006] In a first aspect, the embodiments of the present application provide a step counting method based on a smart wearable device. The step counting method is applied to an electronic device, and the method includes: obtaining real-time motion data collected by a smart wearable device of a target user; performing frequency domain transformation on the real-time motion data to obtain first frequency domain information; obtaining real-time pressure data on the surface of the running belt of the treadmill collected by the treadmill through a sensor array; performing frequency domain transformation on the real-time pressure data to obtain second frequency domain information; at every preset time interval, determining whether the motion in the current time period is effective motion according to the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information in the current time period; when it is determined that the motion in the current time period is effective motion, calculating the number of running steps in the current time period according to the step frequency and step number model.

[0007] With this solution, when counting steps, on the one hand, with the help of the target user's smart wearable device, the movement data of the target user is collected in real time to record the changes in the body's movements; on the other hand, the sensor array on the treadmill is used to capture the real-time pressure data on the surface of the running belt to sense the interaction between the feet and the running belt; then, frequency domain transformation is performed on these two sets of data respectively to obtain the first frequency domain information and the second frequency domain information. By comparing, the similarity of the main frequencies of the two is obtained, and effective movement and ineffective movement are distinguished according to the similarity, avoiding misjudgment of step counting caused by unreasonable step counting methods, such as misjudgment of steps caused by the treadmill idling or non-movement operations of the user on the treadmill (such as device adjustment, short pause). After determining that the movement in the current time period is effective movement, the number of steps is calculated according to the step frequency-step number model, which is conducive to fully considering the difference between step frequency and the number of steps in different movement scenarios. Compared with the traditional step counting method based on a single data source, the step counting method provided by this solution is more accurate, can provide reliable movement data reference for users, and helps users scientifically formulate fitness plans.

[0008] In some possible implementation manners, when it is determined that the movement in the current time period is not effective movement, an alarm message can be sent, such as sending a voice reminder: It is necessary to calibrate the treadmill and / or confirm whether the smart wearable device is correctly worn.

[0009] Combined with the first aspect, in the first possible implementation manner of the first aspect, the step frequency-step number model includes: number of steps = step frequency × duration × coefficient; where the step frequency is determined by the main frequency of the first frequency domain information and / or the main frequency of the second frequency domain information, and the coefficient is determined by the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the age of the target user, and the slope of the running belt. It can be understood that the electronic device can obtain the slope information of the running belt of the treadmill through the communication module.

[0010] This solution introduces the step frequency-step number model. The step frequency is determined by the main frequency obtained after frequency domain transformation of the data collected by the smart wearable device and / or the treadmill. The coefficient in the formula for calculating the number of steps comprehensively considers the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the age of the target user, and the slope of the running belt. This solution considers multiple influencing factors when determining the number of steps, which is conducive to obtaining a more accurate step counting result.

[0011] Combined with the first aspect, in the second possible implementation manner of the first aspect, when the step frequency is determined by the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the method further includes: setting a first weight value ω1 corresponding to the main frequency f1 of the first frequency domain information and a second weight value ω2 corresponding to the main frequency f2 of the second frequency domain information, ω1 + ω2 = 1; calculating the step frequency F1, F1 = f1×ω1 + f2×ω2.

[0012] In this solution, the importance of the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information is adjusted using weight values. Each of the two main frequencies corresponds to a weight value. Then, the step frequency is calculated by multiplying the main frequency by the weight value and summing them up. In this way, the obtained step frequency integrates the data information collected by the smart wearable device and the sensor array respectively, making the step frequency used for calculation more accurate, which is beneficial to making the step count value calculated using the step frequency value more accurate.

[0013] Combined with the first aspect, in the third possible implementation manner of the first aspect, when the step frequency is determined by the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information, the method further includes: the weight ω4 corresponding to the main frequency f4 of the second frequency-domain information is determined according to the calibration frequency of the treadmill and / or the duration between the end time of the last calibration and the start time of the current time period; the first weight value ω3 corresponding to the main frequency f3 of the first frequency-domain information is ω3 = 1 - ω4; calculate the step frequency F2, F2 = f3×ω3 + f4×ω4.

[0014] In this solution, the calibration situation of the treadmill is considered when calculating the step frequency. If the treadmill is calibrated frequently, or it has not been long since the end of the last calibration, the weight corresponding to the main frequency of the second frequency-domain information will be reasonably adjusted. Then, the weight of the main frequency of the first frequency-domain information of the smart wearable device is determined according to the weight corresponding to the main frequency of the second frequency-domain information. The two main frequencies are multiplied by their respective weights and then summed up to calculate the step frequency. This solution combines the information of treadmill calibration, which is beneficial to improving the accuracy of the step frequency value.

[0015] Combined with the first aspect, in the fourth possible implementation manner of the first aspect, the step counting method further includes: obtaining the heart rate information of the target user through the smart wearable device; when the heart rate information exceeds the first heart rate threshold, sending a reminder message; the first heart rate threshold is determined by the age, exercise ability, and physical condition of the target user.

[0016] In this solution, the heart rate monitoring function is added, which is helpful for sports safety and health management. By obtaining the heart rate information of the target user through the smart wearable device, the state of the target user's heart during exercise can be monitored. In addition, the first heart rate threshold comprehensively considers the age, exercise ability, and physical condition of the target user. When the heart rate exceeds the threshold customized for the target user, a reminder message is sent. In this way, when the exercise is too intense, the heart rate is too fast and dangerous, or the body has a sudden condition resulting in abnormal heart rate, it can be discovered in time. This is not only beneficial to ensuring the safety of the target user's exercise, but also beneficial to the target user to adjust the exercise intensity according to the physical condition.

[0017] In combination with the first aspect, in the fifth possible implementation manner of the first aspect, before obtaining the real-time motion data acquired by the intelligent wearable device of the target user, the step counting method further includes: identifying the current user using the treadmill based on biometric features, and when the current user is a user authorized to use the treadmill, determining the current user as the target user; or, obtaining the recognition result of the treadmill's recognition of the current user using the treadmill based on biometric features, and when the current user is a user authorized to use the treadmill, the treadmill determines the current user as the target user; the biometric features include at least one of the following features: weight and face information.

[0018] In this solution, users are identified through biometric features such as weight and face information. Only authorized users can use the treadmill smoothly and start their exercise plans. Identifying the target user in advance can also more accurately plan the exercise plan or adjust the parameters of the treadmill according to the personal information of the target user, such as weight.

[0019] In some possible implementation manners, when it is determined that the current user is not the target user (i.e., has no usage permission), the following operations can be performed: sending a prompt message, for example, displaying a prominent prompt through the display screen of the treadmill and playing a voice prompt at the same time. The treadmill can also be locked to prevent unauthorized users from operating the treadmill without permission and avoid possible safety accidents and equipment damage.

[0020] In a second aspect, an embodiment of the present application provides a training method based on an intelligent wearable device. The method is applied to an electronic device and includes: identifying the current user using the treadmill, and when the current user is a user authorized to use the treadmill, determining the current user as the target user; or, obtaining the recognition result of the treadmill's recognition of the current user using the treadmill, and when the current user is a user authorized to use the treadmill, the treadmill determines the current user as the target user; obtaining the training plan of the target user; establishing connections with the treadmill and the intelligent wearable device of the target user; performing step counting by executing the step counting method based on the intelligent wearable device provided in the first aspect and any of its possible implementation manners; and sending a reminder message when the cumulative step count value in the current training reaches the target count value in the training plan.

[0021] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a communication module, and a memory coupled to the processor and the communication module; the communication module is configured to communicate with a smart wearable device and a treadmill; the memory is configured to store computer-executable instructions, and when the computer-executable instructions are run by the processor, the processor performs step counting by executing the step counting method based on a smart wearable device provided in the first aspect and any possible implementation manner thereof, or performs training by executing the training method based on a smart wearable device provided in the second aspect and any possible implementation manner thereof.

[0022] In a fourth aspect, an embodiment of the present application provides a sports training system, including: an electronic device, and a smart wearable device and a treadmill communicating with the electronic device, where the electronic device is as described in any possible implementation manner of the third aspect.

[0023] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable medium stores computer program code, and when the computer program code runs on a computer, the computer performs step counting by executing the step counting method based on a smart wearable device provided in the first aspect and any possible implementation manner thereof, or performs training by executing the training method based on a smart wearable device provided in the second aspect and any possible implementation manner thereof.

[0024] In a sixth aspect, an embodiment of the present application provides a computer program product, where the computer program product includes computer program code, and when the computer program code runs on a computer, the computer performs step counting by executing the step counting method based on a smart wearable device provided in the first aspect and any possible implementation manner thereof, or performs training by executing the training method based on a smart wearable device provided in the second aspect and any possible implementation manner thereof.

[0025] In a seventh aspect, an embodiment of the present application provides a chip system. When the chip system is applied to an electronic device, the chip system includes one or more processors, and the one or more processors are configured to call computer instructions to cause the electronic device to execute the step counting method based on a smart wearable device provided in the first aspect and any possible implementation manner thereof, or execute the training method based on a smart wearable device provided in the second aspect and any possible implementation manner thereof.

[0026] It can be understood that the beneficial effects that can be achieved by the training method based on a smart wearable device in the second aspect, the electronic device in the third aspect, the sports training system in the fourth aspect, the computer-readable storage medium in the fifth aspect, the computer program product in the sixth aspect, and the chip system in the seventh aspect provided above can refer to the beneficial effects in the first aspect and any possible implementation manner thereof, and will not be elaborated herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 FIG. 1 is a schematic diagram of an application scenario according to an embodiment of the present application;

[0028] Figure 2 FIG. 2 is a schematic flowchart of a step counting method based on a smart wearable device provided in Embodiment 1 of the present application;

[0029] Figure 3 FIG. 3 is a schematic flowchart of a step counting method based on a smart wearable device provided in Embodiment 2 of the present application;

[0030] Figure 4 FIG. 4 is a schematic flowchart of a step counting method based on a smart wearable device provided in Embodiment 3 of the present application;

[0031] Figure 5 FIG. 5 is a schematic flowchart of a training method based on a smart wearable device provided in Embodiment 4 of the present application;

[0032] Figure 6 FIG. 6 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To make the objectives, technical solutions, and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0034] It should be understood that the term "plurality" as mentioned in the present application refers to two or more. In the description of the present application, unless otherwise specified, " / " means "or", for example, A / B may mean A or B; the "and / or" in this article is merely a description of the association relationship of the associated objects, indicating that three relationships may exist, for example, A and / or B may mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, for the convenience of clearly describing the technical solutions of the present application, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the terms "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different.

[0035] Currently, a treadmill usually counts steps by using the step length and the moving mileage of the running belt. In scenarios such as when the treadmill is idling, the mileage will also increase, which may lead to inaccurate step count values obtained based on the mileage.

[0036] In view of the above problems, the present application proposes a step counting method, a training method, and an electronic device based on a smart wearable device, which can obtain accurate step counting data. In the embodiments of the present application, when counting steps, on the one hand, with the help of the smart wearable device of the target user, the motion data of the target user is collected in real time to record the changes in the body's movements; on the other hand, the sensor array on the treadmill is used to capture the real-time pressure data on the surface of the running belt to sense the interaction between the footsteps and the running belt; then, frequency domain transformation is performed on these two sets of data respectively to obtain the first frequency domain information and the second frequency domain information. By comparing, the similarity of the main frequencies of the two is obtained, and effective motion and ineffective motion are distinguished according to the similarity. After determining that the motion in the current time period is effective motion, the number of steps is calculated according to the step frequency and step number model. The step counting value obtained by using the step counting method based on the smart wearable device provided by the embodiments of the present application is more accurate than the step counting value obtained by the traditional method of using a single data source for step counting.

[0037] Embodiment 1

[0038] This embodiment provides a step counting method based on a smart wearable device, which is applied to an electronic device, such as Figure 2 As shown, the step counting method based on the smart wearable device includes the following steps: S201 to S206.

[0039] S201. Obtain the real-time motion data collected by the smart wearable device of the target user.

[0040] The smart wearable device of the target user can be a device such as an earphone, a bracelet, or a watch worn by the target user. The smart wearable device communicates with the treadmill in a wired or wireless manner. The electronic device can be a terminal such as a mobile phone, a tablet, or a computer that communicates with the smart wearable device and the treadmill. In the embodiments of the present application, the electronic device is described as a mobile phone. As Figure 1 shown, Figure 1 is a schematic diagram of an application scenario corresponding to an embodiment. In this embodiment, the electronic device is a mobile phone, the smart wearable device is a watch worn by the target user, and the watch and the treadmill communicate with the electronic device via Bluetooth.

[0041] The smart wearable device has an Inertial Measurement Unit (IMU) and can obtain real-time motion data. The real-time motion data can be data such as speed, acceleration, and three-axis attitude angle. For the sake of simplicity, in the description of this embodiment, the motion data is described by taking acceleration as an example.

[0042] S202. Perform frequency domain transformation on the real-time motion data to obtain the first frequency domain information.

[0043] Among them, the frequency-domain transformation can be the Fourier Transform (FT) or other frequency-domain transformations. For simplicity, in the description of the embodiments of the present application, the frequency-domain transformation is described by taking FT as an example. FT can convert the acceleration data in the time domain into the first frequency-domain information. By extracting the features in the first frequency-domain information, the main frequency of the first frequency-domain information can be obtained. The main frequency can reflect the main rhythm of running, and generally refers to the frequency point corresponding to the position with the largest amplitude in the spectrogram.

[0044] Taking the example that the target user runs on a treadmill and the mobile phone obtains the acceleration data through the IMU of the watch carried by the target user, the first frequency-domain information is obtained after performing FT on the acceleration data. The first frequency-domain information shows the amplitude distribution of the acceleration at different frequencies. The amplitude represents the relative intensity or energy magnitude of the acceleration in the signal. The frequency corresponding to the point where the amplitude reaches the maximum value is the main frequency. For example, in the frequency-domain analysis of the acceleration data, if at the frequency point of 2 Hz, its corresponding amplitude is the largest in the entire spectrum, then the main frequency is 2 Hz. The main frequency is related to the frequency of the target user's feet landing when running. For example, if the main frequency is 2 Hz, it means that the target user's feet land approximately 2 times per second. Assuming the target user runs for 1 minute, that is, 60 seconds, when the main frequency is 2, the number of steps the target user runs within 1 minute can be calculated as 60×2 = 120 steps.

[0045] S203. Obtain the real-time pressure data on the surface of the running belt of the treadmill collected by the sensor array.

[0046] In some possible implementation manners, the sensor array can be disposed on the frame of the treadmill or on the running belt of the treadmill, etc. When the user runs, the sensor array can collect the real-time pressure data on the surface of the running belt when the target user runs on the treadmill.

[0047] S204. Perform a frequency-domain transformation on the real-time pressure data to obtain the second frequency-domain information.

[0048] In some possible implementation manners, FT can be used to convert the real-time pressure data in the time domain into the second frequency-domain information. By extracting the features in the frequency-domain information, the main frequency of the second frequency-domain information is obtained. The main frequency can reflect the main rhythm of running, and is the frequency point corresponding to the position with the largest amplitude in the spectrogram.

[0049] S205. Every preset duration, determine whether the movement in the current time period is effective according to the similarity between the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information in the current time period.

[0050] It should be noted that the preset duration can be an initial value automatically set by the electronic device or a random value within a certain range, or it can be a value set by the user. For example, the preset duration can be T.

[0051] It should be noted that every preset duration, it is determined whether the movement within the current time period is a valid movement. What is meant here is that at the end of each period with a duration of T, an operation is performed: according to the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information within the current time period, it is determined whether the movement within the current time period is a valid movement. For example, if the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information is greater than a preset value (such as 50%), it is determined that the movement within the current time period is a valid movement. If the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information is not greater than the preset value, it is determined that the movement within the current time period is not a valid movement.

[0052] S206. When it is determined that the movement within the current time period is a valid movement, calculate the number of running steps within the current time period according to the stride frequency and step number model.

[0053] In some possible implementation manners, when it is determined that the movement within the current time period is not a valid movement, an alarm message can be sent. The alarm message can be a voice reminder, such as reminding that the treadmill needs to be calibrated and confirming whether the smart wearable device is correctly worn, etc.

[0054] It should be noted that the running step number can correspond to the movement state of running or walking on the treadmill. For the sake of simple description, in the embodiments of the present application, the running step number corresponding to running is taken as an example for description.

[0055] In some possible implementation manners, the stride frequency and step number model includes: number of steps = stride frequency × duration × coefficient; where the stride frequency is determined by the main frequency of the first frequency domain information and / or the main frequency of the second frequency domain information, and the coefficient is determined by the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the age of the target user, and the slope of the running belt. The electronic device can obtain the slope information of the running belt of the treadmill through the communication module.

[0056] The similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information reflects the matching degree between the motion data collected by the smart wearable device and the data collected by the treadmill pressure sensor. The higher the similarity, the more it indicates that the user is indeed running normally on the treadmill, and the coefficient can reflect the relationship between the stride frequency and the number of steps; the lower the similarity, there may be data interference or abnormal situations.

[0057] In some possible implementation manners, when the main frequency of the first frequency-domain information is approximate to that of the second frequency-domain information (for example, the similarity is greater than 95%), the step frequency can be determined by the main frequency of the first frequency-domain information or by the main frequency of the second frequency-domain information. In some other possible implementation manners, the step frequency can also be determined by the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information. For example, the step frequency can be the average value of the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information. For example, if the target user is running on a treadmill and the similarity between the main frequency of the first frequency-domain information obtained from the motion data collected by the intelligent wearable device and the main frequency of the second frequency-domain information obtained from the treadmill pressure sensor in the current time period is very high, reaching 96%, indicating that the data is well matched, and the relationship between the step frequency and the number of steps is relatively stable at this time, the step frequency can be the main frequency of the first frequency-domain information, or the step frequency can be the main frequency of the second frequency-domain information. In some possible implementation manners, the step frequency can also be the average value of the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information, and all are feasible and can be set in advance.

[0058] In some other possible implementation manners, the step frequency can be determined by a preset formula. For example, the first weight value corresponding to the main frequency f1 of the first frequency-domain information is preset as ω1, and the second weight value corresponding to the main frequency f2 of the second frequency-domain information is preset as ω2, and ω1 + ω2 = 1; when calculating the step frequency F1, F1 = f1×ω1 + f2×ω2.

[0059] In this solution, the importance of the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information is adjusted by weight values. Each of the two main frequencies corresponds to a weight value, and then the step frequency is calculated by multiplying the main frequency by the weight value and then adding them together. The step frequency obtained in this way integrates the data information collected by the sensor arrays of the intelligent wearable device and the treadmill respectively, making the calculation of the step frequency more accurate. In this way, the step count result calculated using the step frequency value is more in line with the actual motion situation.

[0060] It should be noted that in some possible implementation manners, the step frequency and step number model includes: step number = step frequency × duration × coefficient, where the coefficient is determined by the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the age of the target user, and the slope of the running belt. When the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information is relatively high, for example, when the similarity is above 95%, the coefficient in the formula is 1. For example, if the age of the target user is 26 years old and he is running on a treadmill with a slope of 0 (flat ground). The main frequency of the first frequency domain information obtained by processing the motion data collected by the intelligent wearable device has a similarity of 96% with the main frequency of the second frequency domain information obtained from the data collected by the treadmill pressure sensor. The high similarity indicates a relatively high data matching degree between the intelligent wearable device and the treadmill, indicating that the target user is running normally and the data is accurate and reliable. Therefore, the coefficient can be taken as 1. If the step frequency of the target user while running is 160 steps per minute and he runs for 30 minutes. According to the formula "step number = step frequency × time × coefficient", the number of steps corresponding to the target user running on the treadmill is 160×30×1 = 4800 steps.

[0061] When the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information is of medium similarity, for example, during the current time period, the target user occasionally adjusted his posture while running, resulting in the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information being reduced to 92%, which is in the range of 90% - 95%. The coefficient corresponding to this range can be 0.9. If the step frequency is still 160 steps per minute and the running time is still 30 minutes. The number of steps the target user runs on the treadmill is 160×30×0.9 = 4320 steps. The decrease in similarity may mean that there are some small deviations in the data, and the coefficient can be adjusted to more accurately determine the number of steps.

[0062] It should be noted that in some possible implementation manners, the age of the target user also affects the coefficient in the formula. For example, both target users, Xiao Li (25 years old) and Grandpa Zhang (65 years old), are running on a treadmill with a slope of 0, and the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information for both of them has reached 97%. Xiao Li's step frequency is 160 steps per minute and he runs for 30 minutes, and the number of steps is 160×30×1 = 4800 steps. However, due to his older age, Grandpa Zhang's physical function is not as good as Xiao Li's. With the same step frequency of 160 steps per minute and running for 30 minutes, his actual exercise efficiency and physical condition determine that the calculation of his number of steps cannot simply use the same standard as Xiao Li's. According to a large amount of data statistics, for Grandpa Zhang's age group, in this case, the coefficient is adjusted to 0.8. Then the number of steps Grandpa Zhang runs is 160×30×0.8 = 3840 steps. This reflects the influence of age on the coefficient. People of different ages have different physical conditions. Even if the step frequency and time are the same, the actual number of steps will be affected, and different coefficients obtained through statistics can be used for calculation.

[0063] It should be noted that in some possible implementation manners, the slope of the running belt also affects the coefficient in the formula. For example, when Xiao Li is running and the slope of the treadmill is 0, the similarity between the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information is 96%, the coefficient is 1, the step frequency is 160 steps per minute, and he runs for 30 minutes, and the number of steps is 4,800 steps. When he raises the slope of the treadmill to 15%, running becomes strenuous. Although the step frequency still remains at 160 steps per minute and he runs for 30 minutes, the similarity between the two main frequencies is still 95% at this time. Due to the influence of the slope, the coefficient needs to be adjusted. According to the statistically obtained data, the coefficient becomes 0.85 at this slope. Then, in this scenario, the number of steps counted for Xiao Li running on the treadmill is 160×30×0.85 = 4,080 steps. This is because the slope changes the difficulty and manner of running, and the actual motion conditions are different for the same step frequency. By adjusting the coefficient, an accurate step count value can be obtained.

[0064] It should be noted that in some possible implementation manners, the coefficient can also be determined by any combination of two of the similarity between the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information, the age of the target user, and the slope of the running belt, or by the three parameters together. The principle is similar to the influence of a single parameter on the coefficient described above, and will not be elaborated here. Since the coefficient in the formula comprehensively considers the similarity between the main frequencies of the first and second frequency-domain information, the age of the target user, and the slope of the running belt. Therefore, the step count value obtained by using this solution to determine the number of steps of the target user running on the treadmill is more accurate.

[0065] In some other possible implementation manners, when the step frequency is determined by the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information, the weight ω4 corresponding to the main frequency f4 of the second frequency-domain information is determined according to the calibration frequency of the treadmill and / or the duration between the end time of the last calibration and the start time of the current time period; the first weight value corresponding to the main frequency f3 of the first frequency-domain information is ω3, and ω3 = 1 - ω4; when calculating the step frequency F2, F2 = f3×ω3 + f4×ω4.

[0066] In this solution, when calculating the step frequency, the calibration situation of the treadmill is considered. If the treadmill is calibrated frequently, or it has not been long since the end of the last calibration, the weight corresponding to the main frequency of the second frequency-domain information can be relatively large. Then, according to this weight, the weight of the main frequency of the first frequency-domain information of the smart wearable device is determined. Multiply the two main frequencies by their respective weights and add them to calculate the step frequency. This solution considers the calibration status of the treadmill and is beneficial to improving the accuracy of step frequency calculation.

[0067] It is understandable that the calibration frequency and calibration time of the treadmill will directly affect the accuracy of the data collected by its pressure sensor. A high calibration frequency means that the treadmill can correct the sensor error more promptly, ensuring the accuracy of data collection; the closer the calibration time is to the current usage time, the higher the accuracy of the data. The second frequency domain information is obtained based on the data collected by the treadmill pressure sensor. It is reasonable to determine the weight value corresponding to its main frequency according to the treadmill calibration frequency and calibration time. By dynamically adjusting the weight value, the finally determined step frequency can more accurately reflect the actual running situation of the user.

[0068] For example, if the target user, Xiao Li, uses a treadmill in a professional gym, which has a strict equipment maintenance system and calibrates the treadmill once a week, and when Xiao Li uses it, only one day has passed since the last calibration. In this case, the data collected by the pressure sensor of the treadmill is very accurate, and the reliability of the second frequency domain information is very high. Suppose the main frequency of the first frequency domain information (corresponding to the smart wearable device) is 160 times per minute, and the corresponding first weight value is set to 0.3; the main frequency of the second frequency domain information (corresponding to the treadmill) is 164 times per minute. Due to the high calibration frequency and the recent calibration time, the second weight value can be set to 0.7. Then the finally determined step frequency is approximately 163 steps per minute. Here, the higher second weight value reflects the trust in the treadmill data because its calibration situation ensures the accuracy of the data. In some possible implementation manners, the second weight value can be automatically reduced as the time since the last calibration increases during use. For example, when the time since the last calibration for Xiao Li's use has passed three days, the second weight value automatically drops to 0.6.

[0069] It is understandable that when the calibration frequency of the treadmill is low and the calibration time is far, for example, the target user, Xiao Zhang, uses his own treadmill at home and he rarely calibrates the treadmill, only calibrating it about once every six months, and three months have passed since the last calibration when he uses it this time. At this time, the treadmill pressure sensor may have some errors due to long-term use, and the accuracy of the collected data is relatively low. If the main frequency of the first frequency domain information is 160 times per minute and the first weight value is set to 0.7; the main frequency of the second frequency domain information is 166 times per minute. Considering the low calibration frequency and the far calibration time, the second weight value is set to 0.3. Then the finally determined step frequency is approximately 162 steps per minute. The lower second weight value indicates that there are reservations about the reliability of the treadmill data and more reference is made to the data of the smart wearable device.

[0070] Similarly, in a scenario with medium calibration frequency and moderate calibration time, for example, if the target user, Xiao Wang, uses a treadmill in the company gym and the treadmill is calibrated every two months, and he has used it for one month since the last calibration. In this case, the accuracy of the treadmill data is at a medium level. The main frequency of the first frequency-domain information is 158 times per minute, and the first weight value is set to 0.5; the main frequency of the second frequency-domain information is 162 times per minute, and the second weight value is also set to 0.5. The finally determined step frequency is 160 times per minute. At this time, the two weight values are the same, indicating that the reliability of the two data sources is equivalent and they are given the same reference value.

[0071] Embodiment 2

[0072] This embodiment provides a step counting method based on a smart wearable device, which is applied to a mobile phone. The main differences from Embodiment 1 include: adding a step of identifying the current user using the treadmill based on biometric characteristics. As Figure 3 shown, the step counting method based on the smart wearable device may include the following steps: S301 to S307.

[0073] S301. Identify the current user using the treadmill based on biometric characteristics. When the current user is a user with permission to use the treadmill, determine the current user as the target user.

[0074] Among them, the biometric characteristics can be face information or weight, etc. When the biometric characteristic is face information, the mobile phone identifies the current user using the treadmill through the camera; when the biometric characteristic is weight, the weight information can be obtained by the treadmill, and the mobile phone identifies the current user according to the obtained weight information.

[0075] In some possible implementation manners, the recognition result can be obtained through the treadmill. For example, obtain the recognition result of the treadmill for identifying the current user using the treadmill based on biometric characteristics. When the current user is a user with permission to use the treadmill, the treadmill determines the current user as the target user. For example, in a large public gym, the treadmill area is equipped with an advanced user recognition system. Xiao Wang is a frequent visitor here. He comes to a treadmill and is about to start exercising. This treadmill is equipped with a weight sensing device. When Xiao Wang steps on the running belt of the treadmill, the weight sensing device immediately works and accurately measures his weight as 70 kg. At the same time, the high-definition camera above the treadmill quickly captures Xiao Wang's face information. The user management system of the gym stores Xiao Wang's membership information, including his face photo and the weight data registered last time. The system compares the weight and face information collected by the treadmill with the data in the database. If it is found that the weight and face information highly match Xiao Wang's membership data, it is confirmed that Xiao Wang has the permission to use this treadmill. Then, the system determines Xiao Wang as the target user.

[0076] It is understandable that in some possible implementation manners, if it is determined that the current user is not the target user (i.e., without usage permission), a prompt message can be sent: a prominent prompt is displayed on the display screen of the treadmill, such as "You have no usage permission. Please contact the administrator", and at the same time, a voice prompt is played, such as "It is detected that you have no usage permission. If you need to use it, please contact the relevant personnel", so as to clearly inform the user that they have no usage qualification. In some other possible implementation manners, when it is determined that the current user is not the target user, the device can also be locked. For example, the operation panel of the treadmill is locked to make all control buttons ineffective, preventing unauthorized users from operating the treadmill without permission, which can avoid safety accidents and equipment damage that may be caused by non-target users. The situation of this recognition failure can also be recorded in the system log of the treadmill, including information such as the recognition time and the number of recognition attempts, which is convenient for subsequent administrators to view and analyze to detect abnormal operations or potential safety hazards. A notification can also be sent to the administrator, such as sending a text message, an email or pushing a message through the management system, to inform that an unauthorized user has attempted to use the treadmill, which is convenient for the administrator to handle in a timely manner, such as contacting the user to confirm the situation or strengthening the device management.

[0077] S302. Obtain the real-time motion data collected by the intelligent wearable device of the target user.

[0078] The intelligent wearable device of the target user can be a device such as an earphone, a bracelet or a watch worn by the target user. The intelligent wearable device communicates with the treadmill in a wired or wireless manner. The intelligent wearable device has an IMU and can obtain real-time motion data. The real-time motion data can be data such as speed, acceleration, and three-axis attitude angles. For the sake of simplicity, in the description of this embodiment, the motion data is described by taking acceleration as an example.

[0079] S303. Perform a frequency-domain transformation on the real-time motion data to obtain the first frequency-domain information.

[0080] Among them, the frequency-domain transformation can be FT or other frequency-domain transformations. For the sake of simplicity, in the description of the embodiments of this application, the frequency-domain transformation is described by taking FT as an example. FT can convert the acceleration data in the time domain into the first frequency-domain information. By extracting the features in the first frequency-domain information, the main frequency of the first frequency-domain information can be obtained. The main frequency can reflect the main rhythm of running and usually refers to the frequency point corresponding to the position with the largest amplitude in the spectrogram.

[0081] Taking the example that the target user runs on the treadmill and the treadmill obtains the acceleration data through the IMU of the watch carried by the target user, after performing FT on the acceleration data, the first frequency-domain information will be obtained. The first frequency-domain information shows the amplitude distribution of the acceleration at different frequencies. The amplitude represents the relative intensity or energy magnitude of the acceleration in the signal. The place with the largest frequency domain is the frequency corresponding to the point where the amplitude reaches the maximum value, that is, the main frequency.

[0082] S304. Obtain the real-time pressure data on the surface of the running belt of the treadmill collected by the sensor array.

[0083] In some possible implementation manners, the sensor array can be arranged on the frame of the treadmill or on the running belt of the treadmill, etc. When the user runs, the sensor array can collect the real-time pressure data on the surface of the running belt when the target user runs on the treadmill.

[0084] S305. Perform a frequency-domain transformation on the real-time pressure data to obtain second frequency-domain information.

[0085] In some possible implementation manners, the FT can be used to convert the real-time pressure data in the time domain into second frequency-domain information. By extracting the features in the frequency-domain information, the main frequency of the frequency-domain information can be obtained. The main frequency can reflect the main rhythm of running, and generally refers to the frequency point corresponding to the position with the largest amplitude in the spectrogram.

[0086] S306. Every preset duration, determine whether the movement in the current time period is effective according to the similarity between the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information in the current time period.

[0087] It should be noted that the preset duration can be the initial value automatically set actually or a random value within a certain time range, or a value set by the user, such as T. It should be noted that the meaning of "every preset duration" here is: an operation is performed at the end of each period with a duration of T: determine whether the movement in the current time period is effective according to the similarity between the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information in the current time period. Specifically, if the similarity between the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information is greater than the preset value (such as 50%), it is determined that the movement in the current time period is effective. If the similarity between the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information is not greater than the preset value of 50%, it is determined that the movement in the current time period is not effective.

[0088] S307. When it is determined that the movement in the current time period is effective, calculate the number of running steps in the current time period according to the step frequency and step number model.

[0089] In some possible implementation manners, when it is determined that the movement in the current time period is not effective, an alarm message can be sent, such as reminding to calibrate the treadmill and confirm whether the smart wearable device is correctly worn, etc.

[0090] In some possible implementations, the step frequency and step count model includes: Step count = Step frequency × Duration × Coefficient; where the step frequency is determined by the main frequency of the first frequency domain information and / or the main frequency of the second frequency domain information, and the coefficient is determined by the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the age of the target user, and the slope of the running belt.

[0091] In this solution, users are identified through biometric features such as weight and face information. Only authorized users can use the treadmill smoothly and start their exercise plans. By identifying the target user in advance, the exercise plan can be more accurately planned or the parameters of the treadmill can be adjusted according to the personal information of the target user, such as weight.

[0092] Embodiment III

[0093] This embodiment provides a step counting method based on a smart wearable device, which is applied to a mobile phone. The main differences from Embodiment II include: obtaining the heart rate information of the target user through the smart wearable device, and sending a reminder message when the heart rate information exceeds the threshold matching the target user. As Figure 4 shown, the step counting method based on the smart wearable device may include the following steps: S401 to S409.

[0094] S401. Identify the current user using the treadmill based on biometric features. When the current user is an authorized user to use the treadmill, determine the current user as the target user.

[0095] S402. Obtain the real-time motion data collected by the smart wearable device of the target user.

[0096] The smart wearable device of the target user can be a device such as an earphone, a bracelet or a watch worn by the target user. The smart wearable device communicates with the treadmill in a wired or wireless manner. The smart wearable device has an IMU and can obtain real-time motion data. The real-time motion data can be data such as speed, acceleration, and three-axis attitude angle. For simplicity, in the description of this embodiment, the motion data is described by taking acceleration as an example.

[0097] S403. Perform a frequency domain transformation on the real-time motion data to obtain the first frequency domain information.

[0098] Among them, the frequency domain transformation can be FT, and FT can convert the acceleration data in the time domain into the first frequency domain information. By extracting the features in the first frequency domain information, the main frequency of the first frequency domain information can be obtained. The main frequency can reflect the main rhythm of running and usually refers to the frequency point corresponding to the position with the largest amplitude in the spectrogram.

[0099] Taking the example of a target user running on a treadmill and the treadmill obtaining acceleration data through the IMU of a watch worn by the target user, after performing FT on the acceleration data, first frequency domain information will be obtained. The first frequency domain information shows the amplitude distribution of the acceleration at different frequencies. The amplitude represents the relative intensity or energy magnitude of the acceleration in the signal. The place with the largest frequency in the frequency domain is the frequency corresponding to the point where the amplitude reaches the maximum value, that is, the main frequency.

[0100] S404. Obtain the real-time pressure data on the surface of the running belt of the treadmill collected by the sensor array.

[0101] In some possible implementation manners, the sensor array can be set on the frame of the treadmill or on the running belt of the treadmill, etc. When the user runs, the sensor array can collect the real-time pressure data on the surface of the running belt when the target user runs on the treadmill.

[0102] S405. Perform frequency domain transformation on the real-time pressure data to obtain second frequency domain information.

[0103] In some possible implementation manners, FT can be used to convert the real-time pressure data in the time domain into second frequency domain information. By extracting the features in the frequency domain information, the main frequency of the frequency domain information can be obtained. The main frequency can reflect the main rhythm of running and usually refers to the frequency point corresponding to the position with the largest amplitude in the spectrogram.

[0104] S406. At every preset time interval, determine whether the movement in the current time period is effective movement according to the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information in the current time period.

[0105] S407. When it is determined that the movement in the current time period is effective movement, calculate the number of steps run in the current time period according to the step frequency and step number model.

[0106] In some possible implementation manners, when it is determined that the movement in the current time period is not effective movement, an alarm message can be sent, such as reminding to calibrate the treadmill and confirming whether the smart wearable device is correctly worn, etc.

[0107] In some possible implementation manners, the step frequency and step number model includes: number of steps = step frequency × duration × coefficient; where the step frequency is determined by the main frequency of the first frequency domain information and / or the main frequency of the second frequency domain information, and the coefficient is determined by the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the age of the target user, and the slope of the running belt.

[0108] S408. Obtain the heart rate information of the target user through the smart wearable device.

[0109] S409. When the heart rate information exceeds the first heart rate threshold, a reminder message is sent; the first heart rate threshold is determined by the age, exercise ability, and physical condition of the target user.

[0110] The reminder message can be a voice alarm, such as a voice reminder: "Your heart rate is too high. Please appropriately reduce the exercise intensity." At the same time, the warning light on the control panel of the treadmill flashes in red to form an obvious visual reminder.

[0111] The reminder message can also be: emitting a continuous beeping sound, displaying a prominent red warning message on the display screen, and reminding the user through voice broadcast: "Heart rate is abnormal. Please adjust the exercise intensity."

[0112] In some possible implementation manners, after detecting that the heart rate value exceeds the first heart rate threshold corresponding to the target user, in addition to sending a reminder message, a protection operation can also be triggered, such as: triggering the treadmill to reduce the running speed to a safe range or pausing the operation.

[0113] In this embodiment, a heart rate monitoring function is added during step counting, which is helpful for exercise safety and health management. The heart rate information of the target user is obtained through a smart wearable device, so that the state of the target user's heart during exercise can be monitored. In addition, the first heart rate threshold comprehensively considers the age, exercise ability, and physical condition of the target user. When the heart rate exceeds the threshold customized for the target user, a reminder message is sent. In this way, when the exercise is too intense and the heart rate is too fast and dangerous, or when the body suddenly has a condition resulting in abnormal heart rate, it can be detected in time. This is not only beneficial to ensuring the safety of the target user's exercise, but also beneficial to the target user to adjust the exercise intensity according to the physical condition and exercise scientifically.

[0114] Embodiment 4

[0115] This embodiment provides a training method based on a smart wearable device, which is applied to a treadmill. As Figure 5 shown, the training method based on a smart wearable device may include the following steps: S501 to S510.

[0116] S501. Identify the current user using the treadmill based on biometric features. When the current user is a user authorized to use the treadmill, determine the current user as the target user.

[0117] S502. Obtain the training plan of the target user.

[0118] S503. Establish a connection with the smart wearable device of the target user.

[0119] S504. Obtain the real-time exercise data collected by the smart wearable device of the target user.

[0120] The intelligent wearable device of the target user can be devices such as headphones, bracelets, or watches worn by the target user. The intelligent wearable device communicates with the treadmill in a wired or wireless manner. The intelligent wearable device has an IMU and can obtain real-time motion data, which can be data such as speed, acceleration, and three-axis attitude angles. For simplicity, in the description of this embodiment, the motion data is described by taking acceleration as an example.

[0121] S505. Perform a frequency-domain transformation on the real-time motion data to obtain first frequency-domain information.

[0122] Among them, the frequency-domain transformation can be FT or other frequency-domain transformations. For simplicity, in the description of the embodiments of this application, the frequency-domain transformation is described by taking FT as an example. FT can convert the acceleration data in the time domain into first frequency-domain information. By extracting the features in the first frequency-domain information, the main frequency of the first frequency-domain information can be obtained. The main frequency can reflect the main rhythm of running and usually refers to the frequency point corresponding to the position with the largest amplitude in the spectrogram.

[0123] Taking the example that the target user runs on the treadmill and the treadmill obtains acceleration data through the IMU of the watch worn by the target user, after performing FT on the acceleration data, first frequency-domain information will be obtained. The first frequency-domain information shows the amplitude distribution of the acceleration at different frequencies. The amplitude represents the relative intensity or energy magnitude of the acceleration in the signal. The place with the largest frequency domain is the frequency corresponding to the point where the amplitude reaches the maximum value, that is, the main frequency.

[0124] S506. Obtain the real-time pressure data on the surface of the running belt of the treadmill collected by the sensor array of the treadmill.

[0125] In some possible implementation manners, the sensor array can be set on the frame of the treadmill or on the running belt of the treadmill, etc. When the user runs, the sensor array can collect the real-time pressure data on the surface of the running belt when the target user runs on the treadmill.

[0126] S507. Perform a frequency-domain transformation on the real-time pressure data to obtain second frequency-domain information.

[0127] In some possible implementation manners, FT can be used to convert the real-time pressure data in the time domain into second frequency-domain information. By extracting the features in the frequency-domain information, the main frequency of the frequency-domain information can be obtained. The main frequency can reflect the main rhythm of running and usually refers to the frequency point corresponding to the position with the largest amplitude in the spectrogram.

[0128] S508. At every preset time interval, determine whether the motion in the current time period is effective motion according to the similarity between the main frequency of the first frequency-domain information and the main frequency of the second frequency-domain information in the current time period.

[0129] S509. When determining that the movement within the current time period is valid movement, calculate the number of running steps within the current time period according to the step frequency and step number model.

[0130] S510. When the cumulative step count value in the current training reaches the target count value in the training plan, send a reminder message.

[0131] For example, if the running step counting task in the current training in the training plan is 5000 steps, when the cumulative count in the current training reaches 5000, the treadmill sends a reminder message. For example, it sends a voice reminder through the built-in voice reminder module of the treadmill. The content of the voice reminder can be: "You have completed the step counting target of the current training plan", and at the same time, a completion reminder message is displayed on the display screen of the treadmill in a prominent color and font to ensure that the user can timely and accurately know that the training plan has been completed.

[0132] As Figure 6 shown, the present application further provides an electronic device: 600, including a processor 601, a communication module 602 coupled to the processor 601, and a memory 603; the communication module 602 is used to communicate with the smart wearable device and the treadmill; the memory 603 is used to store computer execution instructions. When the computer execution instructions are run by the processor 601, the following operations are performed: obtain the real-time motion data collected by the smart wearable device of the target user; perform frequency domain transformation on the real-time motion data to obtain first frequency domain information; obtain the real-time pressure data on the surface of the running belt of the treadmill collected by the sensor array of the treadmill; perform frequency domain transformation on the real-time pressure data to obtain second frequency domain information; at every preset time period, determine whether the movement within the current time period is valid movement according to the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information within the current time period; when determining that the movement within the current time period is valid movement, calculate the number of running steps within the current time period according to the step frequency and step number model. In some possible implementation manners, the step frequency and step number model called by the processor includes: number of steps = step frequency × time period × coefficient; wherein, the step frequency is determined by the main frequency of the first frequency domain information and / or the main frequency of the second frequency domain information, and the coefficient is determined by the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the age of the target user, and the slope of the running belt.

[0133] In some possible implementation manners, when the step frequency is determined by the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the processor is further configured to perform the following steps: set a first weight value ω1 corresponding to the main frequency f1 of the first frequency domain information and a second weight value ω2 corresponding to the main frequency f2 of the second frequency domain information, ω1 + ω2 = 1; calculate the step frequency F1, F1 = f1 × ω1 + f2 × ω2.

[0134] In some possible implementation manners, when the step frequency is determined by the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the processor is further configured to perform the following steps: The weight ω4 corresponding to the main frequency f4 of the second frequency domain information is determined according to the calibration frequency of the treadmill and / or the duration between the end time of the last calibration and the start time of the current time period; the first weight value ω3 corresponding to the main frequency f3 of the first frequency domain information is ω3 = 1 - ω4; calculate the step frequency F2, where F2 = f3×ω3 + f4×ω4.

[0135] In some possible implementation manners, the processor is further configured to perform the following steps: obtain the heart rate information of the target user through the smart wearable device; when the heart rate information exceeds the first heart rate threshold, send a reminder message; the first heart rate threshold is determined by the age, exercise ability, and physical condition of the target user.

[0136] In some possible implementation manners, before obtaining the real-time motion data obtained by the smart wearable device of the target user, the processor is further configured to perform the following steps: identify the current user using the treadmill based on biometric features, and when the current user is a user authorized to use the treadmill, determine the current user as the target user; or, obtain the recognition result of the treadmill's recognition of the current user using the treadmill based on biometric features, and when the current user is a user authorized to use the treadmill, the treadmill determines the current user as the target user; the biometric features include at least one of the following features: weight and face information.

[0137] In some possible implementation manners, the processor is further configured to perform the following steps: identify the current user using the treadmill, and when the current user is a user authorized to use the treadmill, determine the current user as the target user; obtain the training plan of the target user; and count steps according to any of the previous step counting methods; when the cumulative step count value in the current training reaches the target count value in the training plan, send a reminder message.

[0138] An embodiment of the present application further provides a motion training system, including: an electronic device, and a smart wearable device and a treadmill communicatively connected to the electronic device, and the electronic device may be the electronic device provided in any of the previous electronic device embodiments.

[0139] An embodiment of the present application further provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, it causes the computer to count steps according to any of the previous step counting method embodiments provided based on the smart wearable device, or perform training according to any of the previous training method embodiments provided based on the smart wearable device.

[0140] An embodiment of the present application provides a computer program product. The computer program product includes computer program code. When the computer program code runs on a computer, it causes the computer to perform step counting according to the step counting method provided in any of the previous embodiments of the step counting method based on a smart wearable device, or to perform training according to the training method provided in any of the previous embodiments of the training method based on a smart wearable device.

[0141] An embodiment of the present application provides a chip system. When the chip system is applied to an electronic device, the chip system includes one or more processors. The one or more processors are used to call computer instructions to cause the electronic device to perform step counting according to the step counting method provided in any of the previous embodiments of the step counting method based on a smart wearable device, or to perform training according to the training method provided in any of the previous embodiments of the training method based on a smart wearable device.

[0142] It can be understood that for the beneficial effects that can be achieved by the above-mentioned training method, electronic device, motion training system, computer-readable storage medium, computer program product, and chip system based on a smart wearable device, reference can be made to the beneficial effects in the previous method embodiments, and details are not described herein again.

[0143] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a treadmill, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more available media integrated.

[0144] The above are optional embodiments provided by the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the technical scope disclosed in the present application shall be included in the protection scope of the present application.

Claims

1. A step counting method based on a smart wearable device, characterized in that: The method is applied to an electronic device, and the method comprises: Obtain real-time motion data collected by the target user's smart wearable device; Performing frequency domain transformation on the real-time motion data to obtain first frequency domain information; Acquire real-time pressure data of the running belt surface of the treadmill collected by the sensor array of the treadmill; Performing frequency domain transformation on the real-time pressure data to obtain second frequency domain information; At preset time intervals, according to the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information in the current time period, determining whether the motion in the current time period is a valid motion; When it is determined that the exercise in the current time period is a valid exercise, the number of steps in the current time period is calculated according to the step frequency and step number model.

2. The step counting method based on the smart wearable device according to claim 1, characterized in that: The step frequency and number of steps model includes: Number of steps = step frequency × duration × coefficient; wherein the step frequency is determined by the main frequency of the first frequency domain information and / or the main frequency of the second frequency domain information, and the coefficient is determined by the similarity between the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the age of the target user, and the slope of the treadmill.

3. The step counting method based on the smart wearable device according to claim 2 is characterized in that: When the step frequency is determined by the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the method further includes: Set a first weight value ω1 corresponding to the main frequency f1 of the first frequency domain information and a second weight value ω2 corresponding to the main frequency f2 of the second frequency domain information, ω1+ω2=1; Calculate the step frequency F1, F1=f1×ω1+f2×ω2.

4. The step counting method based on the smart wearable device according to claim 2, characterized in that: When the step frequency is determined by the main frequency of the first frequency domain information and the main frequency of the second frequency domain information, the method further includes: The weight ω4 corresponding to the main frequency f4 of the second frequency domain information is determined according to the calibration frequency of the treadmill and / or the time between the end of the last calibration and the start of the current time period; the first weight value ω3 corresponding to the main frequency f3 of the first frequency domain information is 1-ω4; Calculate the step frequency F2, F2=f3×ω3+f4×ω4.

5. The step counting method based on the smart wearable device according to any one of claims 1 to 4, characterized in that: The method further comprises: Acquiring the heart rate information of the target user through the smart wearable device; When the heart rate information exceeds a first heart rate threshold, a reminder message is issued; the first heart rate threshold is determined by the age, athletic ability, and physical condition of the target user.

6. The step counting method based on a smart wearable device according to any one of claims 1 to 4, characterized in that: Before acquiring the real-time motion data collected by the smart wearable device of the target user, the method further includes: Identifying a current user using the treadmill based on biometrics, and determining the current user as a target user when the current user is a user who has the authority to use the treadmill; Alternatively, obtaining an identification result of the treadmill identifying a current user using the treadmill based on biometrics, and when the current user is a user who has the authority to use the treadmill, the treadmill determines the current user as a target user; The biological feature includes at least one of the following features: weight and facial information.

7. A training method based on a smart wearable device, characterized in that: The method is applied to an electronic device, and the method comprises: Identify a current user using the treadmill, and when the current user is a user who has the authority to use the treadmill, determine the current user as a target user; or obtain an identification result of the treadmill identifying the current user using the treadmill, and when the current user is a user who has the authority to use the treadmill, the treadmill determines the current user as a target user; Obtaining a training plan for the target user; Establishing a connection with the treadmill and the smart wearable device of the target user; Execute the step counting method based on the smart wearable device as described in any one of claims 1 to 5 to count steps; When the accumulated step count value of this training reaches the target count value in the training plan, a reminder message is issued.

8. An electronic device, characterized in that: include: A processor, a communication module, and a memory coupled to the processor and the communication module; The communication module is used to communicate with the smart wearable device and the treadmill; The memory is used to store computer execution instructions. When the computer execution instructions are executed by the processor, the processor executes the step counting method based on the smart wearable device as described in any one of claims 1-6, or executes the training method based on the smart wearable device as described in claim 7.

9. A sports training system, characterized in that: include: An electronic device, and a smart wearable device and a treadmill that communicate with the electronic device, wherein the electronic device is as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable medium stores a computer program code, and when the computer program code runs on a computer, the computer executes the step counting method based on the smart wearable device as described in any one of claims 1 to 6, or executes the training method based on the smart wearable device as described in claim 7.

Images