Method and related equipment for monitoring motion information

By filtering and fitting the motion data and combining historical trend analysis, the problem of inaccurate maximum oxygen uptake results during exercise is solved, and the accuracy of the results is improved.

CN118447999BActive Publication Date: 2024-11-29HONOR DEVICE CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311325238.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-10-11
Publication Date
2024-11-29
Estimated Expiration
2043-10-11

AI Technical Summary

Technical Problem

The prior art is difficult to accurately obtain the maximum oxygen uptake during exercise, especially when the heart rate and speed changes are complex, resulting in large errors in the result.

Method used

By obtaining user speed and heart rate data, determining movement status, performing data filtering and fitting, combining historical data for trend analysis, and using linear interpolation and smoothing to improve the accuracy of maximum oxygen uptake results.

Benefits of technology

Improves the accuracy of maximum oxygen uptake results, reduces errors, and provides a more reliable assessment of cardiopulmonary function.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118447999B_ABST
    Figure CN118447999B_ABST
Patent Text Reader

Abstract

The present application provides a method and related equipment for monitoring motion information, belonging to the field of terminal technology. The method includes: obtaining valid data of the user in a stable state of motion through heart rate, speed, etc. analysis, and storing it in a buffer; then, performing slope analysis and regression factor analysis on the data in the buffer to filter the data to obtain a more accurate heart rate-speed pair associated with the maximum oxygen uptake; then, performing trend analysis on the current results based on historical results, so that the trend of changes in the maximum oxygen uptake is more in line with reality, and finally obtaining the output result of the maximum oxygen uptake. The method obtains accurate input data by performing multiple screening and filtering on the data in a stable motion state, and after preliminarily obtaining the maximum oxygen uptake result, multiple processing is performed on the maximum oxygen uptake result, thereby effectively improving the accuracy of obtaining the maximum oxygen uptake result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of terminal technology, and in particular to a method for monitoring motion information and related equipment. Background Art

[0002] As people pay more attention to health, more and more users are used to using smart wearable devices to monitor their health. Especially for users who love sports, smart wearable devices can easily record relevant data during exercise (such as speed, time, heart rate, maximum oxygen consumption (VO2max) etc.). After the exercise, users can view intuitive data on the smart wearable device to obtain whether the exercise has achieved the predetermined goal or the expected effect.

[0003] Currently, the method of obtaining the user's maximum oxygen uptake during exercise needs to be based on exercise data. However, in many scenarios, the user's actual exercise situation is often more complicated than theoretical analysis. For example, when the user is running, the changes in heart rate and speed are relatively complex, and it is difficult to obtain reliable data fragments, resulting in large errors in the results.

[0004] Therefore, how to select points or obtain data segments based on sports with complex trend changes in order to more accurately obtain the user's maximum oxygen uptake during exercise has become a problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a method and related equipment for monitoring exercise information, which can solve the problem of inaccurate results of calculating maximum oxygen uptake during exercise.

[0006] In a first aspect, a method for monitoring motion information is provided, which is applied to a first electronic device, and includes:

[0007] Get the speed and heart rate of the user's exercise;

[0008] Determining, according to the speed and heart rate, that the motion state corresponding to the user's motion meets a point selection condition;

[0009] Acquire valid data points, wherein the valid data points include the speed, heart rate, exercise state label, and duration of the user corresponding to the point selection condition, wherein the exercise state label is used to indicate the exercise type and exercise intensity corresponding to the user's exercise;

[0010] Filter the valid data points once according to the motion state label to obtain a first data point;

[0011] Performing linear fitting on the speed and heart rate corresponding to the first data points respectively, and performing secondary filtering on the outliers according to residual analysis to obtain second data points;

[0012] Obtaining a first result corresponding to the user's maximum exercise oxygen uptake according to the second data point;

[0013] Linear interpolation is performed on the first result according to the historical maximum oxygen uptake result, and single exponential smoothing and double exponential smoothing are performed on the linear interpolation to obtain a second result corresponding to the maximum oxygen uptake of the user during exercise.

[0014] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0015] Acquire the exercise type corresponding to the user's exercise according to the speed and heart rate; and

[0016] Acquire the exercise intensity corresponding to the user's exercise according to the heart rate;

[0017] The exercise state label is acquired according to the exercise type and the exercise intensity.

[0018] According to the method of motion monitoring provided by the embodiment of the present application, valid data of the user in a stable state of motion is obtained through analysis of heart rate, speed, etc., and stored in a buffer; then, slope analysis and regression factor analysis are performed on the data in the buffer to filter the data to obtain a more accurate heart rate-speed pair associated with the maximum oxygen uptake; then, trend analysis is performed on the current results based on historical results to make the trend of the maximum oxygen uptake more realistic, and finally the output result of the maximum oxygen uptake is obtained. This method obtains accurate input data by performing multiple screening and filtering on the data in a stable motion state, and after preliminarily obtaining the maximum oxygen uptake result, multiple processing is performed on the maximum oxygen uptake result, thereby effectively improving the accuracy of obtaining the maximum oxygen uptake result.

[0019] In combination with the first aspect, in some implementations of the first aspect, filtering the valid data points once according to the motion state tag to obtain the first data point specifically includes:

[0020] Delete the valid data points whose motion state label is the first motion state label, where the first motion state label is used to indicate that the speed does not reach the first pace; or, the speed variance corresponding to the motion state is equal to or greater than a first preset value; or, the difference between the maximum speed and the minimum speed corresponding to the motion state is equal to or greater than a second preset value; or, when the speed is fixed, the heart rate change value is equal to or greater than a third preset value.

[0021] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0022] Obtaining the number of the first data points;

[0023] When the number of the first data points is 0, obtaining historical data corresponding to the maximum oxygen uptake;

[0024] Display the historical data corresponding to the maximum oxygen uptake of the previous exercise corresponding to the current user exercise.

[0025] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0026] Obtaining the number of the first data points;

[0027] When the number of the first data points is 2, obtaining a third result of the maximum oxygen uptake and a fourth result of the maximum oxygen uptake respectively corresponding to the first data points;

[0028] When the difference between the third result and the fourth result is greater than a third preset value, obtaining historical data corresponding to the maximum oxygen uptake;

[0029] Display the historical data corresponding to the maximum oxygen uptake of the previous exercise corresponding to the current user exercise.

[0030] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0031] When the difference between the third result and the fourth result is equal to or less than the third preset value, calculating an average value of the third result and the fourth result;

[0032] An average of the third result and the fourth result is displayed.

[0033] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0034] Obtaining the number of the first data points;

[0035] When the number of the first data points is greater than 2, linear fitting is performed on the speeds and heart rates respectively corresponding to the first data points, and outliers are filtered twice according to residual analysis to obtain second data points.

[0036] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0037] The second data point is input into a regression model corresponding to the maximum oxygen uptake, where the regression model includes a mapping relationship between the speed and heart rate corresponding to the user's exercise and the maximum oxygen uptake result.

[0038] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0039] Determining whether the duration of the user's exercise reaches a first preset time;

[0040] If the preset time is reached, determining whether the point selection window corresponding to the speed and heart rate reaches a second preset time, the point selection window being a time unit for selecting the valid data point;

[0041] If the point selection window reaches a second preset time, the valid data point is obtained.

[0042] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0043] Establishing Bluetooth pairing with a second electronic device, wherein the first electronic device and the second electronic device respectively store historical data of maximum oxygen uptake corresponding to the user;

[0044] The local maximum oxygen uptake history data of the first electronic device is sent to the second electronic device, so that when the maximum oxygen uptake history data stored in the first electronic device is inconsistent with that in the second electronic device, the second electronic device updates the maximum oxygen uptake history data according to the local maximum oxygen uptake history data of the first electronic device.

[0045] In combination with the first aspect, in some implementations of the first aspect, the method further includes:

[0046] receiving user information sent by the second electronic device;

[0047] Determining, according to the user information, whether a second user account corresponding to the second electronic device is consistent with a first user account corresponding to the first electronic device, wherein both the first user account and the second user account are accounts associated with an application for obtaining maximum oxygen uptake;

[0048] When the first user account is consistent with the second user account, the local maximum oxygen uptake history data of the first electronic device is sent to the second electronic device.

[0049] In a second aspect, an electronic device is provided, including:

[0050] one or more processors;

[0051] one or more memories;

[0052] The one or more memories store one or more computer programs, and the one or more computer programs include instructions. When the instructions are executed by the one or more processors, the electronic device executes the method as described in any one of the first aspects above.

[0053] In a third aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable program instructions, and when the computer-executable program instructions are executed on a computer, the computer executes the method as described in any one of the above-mentioned first aspects.

[0054] In a fourth aspect, a computer program product is provided, the computer program product comprising a computer program code, and when the computer program code is run on a computer, the computer is caused to execute the method as described in any implementation manner of the above-mentioned first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figures 1A to 1E A schematic diagram of a GUI that may be involved in the implementation of some motion information monitoring methods provided in the embodiments of the present application.

[0056] Figure 2 A schematic diagram of the system architecture of a method for jointly performing motion information monitoring by a smart watch and a mobile phone provided in an embodiment of the present application.

[0057] Figure 3 A schematic structural diagram of an electronic device 100 provided in an embodiment of the present application.

[0058] Figure 4 A software structure block diagram of the electronic device 100 provided in an embodiment of the present application.

[0059] Figure 5 A schematic diagram of obtaining a user's maximum oxygen uptake during exercise through a professional device provided in an embodiment of the present application.

[0060] Figure 6 A schematic diagram of the changes in heart rate and oxygen uptake over time obtained based on a professional device provided in an embodiment of the present application.

[0061] Figure 7 A schematic flowchart of a method for monitoring motion information provided in an embodiment of the present application.

[0062] Figure 8 A schematic diagram of an outdoor sports scene provided in an embodiment of the present application.

[0063] Fig. 9 A schematic diagram of the changes in heart rate and speed over time under different exercise states provided in an embodiment of the present application.

[0064] Fig.10 A schematic diagram of the correspondence between an AR state recognition moment and a time window provided in an embodiment of the present application.

[0065] Fig.11 A schematic diagram of a GUI that may be involved in the implementation of a method for monitoring motion information provided in an embodiment of the present application.

[0066] Fig.12 A schematic diagram of the changes in heart rate and speed over time during an interval running exercise provided in an embodiment of the present application.

[0067] Fig.13 A speed segment schematic diagram provided in an embodiment of the present application.

[0068] Fig.14 A schematic diagram of the results of linear fitting and residual analysis when performing secondary filtering on valid data points provided in an embodiment of the present application.

[0069] Fig.15 A schematic flowchart of another method for monitoring motion information provided in an embodiment of the present application.

[0070] Fig.16 A schematic flowchart of another method for monitoring motion information provided in an embodiment of the present application.

[0071] Fig.17 A schematic flowchart of another method for monitoring motion information provided in an embodiment of the present application.

[0072] Fig.18 A schematic flowchart of another method for monitoring motion information provided in an embodiment of the present application. DETAILED DESCRIPTION

[0073] It should be noted that the terms used in the implementation method part of the embodiments of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated obstacles, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two, "at least one" and "one or more" mean one, two or more than two.

[0074] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, it is defined that the "first" and "second" features may explicitly or implicitly include one or more of the features.

[0075] References to "one embodiment" or "some embodiments" etc. described in this specification mean that a particular feature, structure or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing at different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0076] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0077] In order to better understand the method for monitoring motion information provided in the embodiments of the present application, the concepts and definitions that may appear below are first introduced.

[0078] 1. VO2max

[0079] Maximum oxygen uptake refers to the maximum amount of oxygen that the human body can absorb and use per minute when a large number of muscle groups participate in exercise for a long time and the cardiopulmonary oxygen uptake capacity reaches the human body's limit. Maximum oxygen uptake is the most reliable and effective physiological indicator for evaluating the body's aerobic function and cardiopulmonary endurance. The greater the maximum oxygen uptake, the higher the cardiopulmonary capacity and the better the running results.

[0080] 2. Graded exercise testing (GXT)

[0081] Incremental load running, also known as cardiopulmonary exercise test, is a test of the body's various responses (respiration, blood pressure, heart rate, gas metabolism, clinical symptoms and signs, etc.) to the gradual increase in exercise intensity and oxygen demand.

[0082] In the embodiment of the present application, the user's physical signs can be made to reach the maximum oxygen uptake state through incremental load running, so as to provide maximum oxygen uptake result data.

[0083] 3. Activity recognition (AR)

[0084] Activity recognition can also be described as AR state recognition.

[0085] In some embodiments, the process of AR state recognition may include: sensor data collection, feature extraction, model training and evaluation, etc. Specifically, AR state recognition first needs to collect activity data through sensors. The sensor may include, for example, an accelerometer (or acceleration sensor), a gyroscope, a magnetometer, etc., which are used to measure acceleration, angular velocity and direction information of human body movement, etc. These sensors are usually embedded in wearable devices, such as smart watches, smart bracelets, etc. After the data collection is completed, the data needs to be feature extracted for subsequent model classification and recognition tasks. Feature extraction is the process of converting raw sensor data into representative feature vectors. Common feature extraction methods include time domain features and frequency domain features. Time domain features refer to statistical analysis of data on the time axis, such as mean, variance, maximum value, minimum value, etc. Frequency domain features refer to Fourier transforming the data to extract spectral information. After the feature extraction is completed, a suitable classification algorithm needs to be used to model the classification task of the feature vector. Commonly used classification algorithms include support vector machine (SVM), random forest (RF), artificial neural network (ANN), etc. These algorithms can build models based on existing training samples to classify and predict new feature vectors. The accuracy and reliability of activity recognition depends on the quantity and quality of training samples. Therefore, in the process of model training, it is necessary to collect enough sample data, label and classify them. Through training samples, the parameters of the algorithm can be optimized and the accuracy of the model can be improved. After the model training is completed, it is necessary to evaluate and verify to ensure the performance and reliability of the model in practical applications.

[0086] In order to better understand the maximum oxygen uptake during exercise, users usually wear smart watches, which can display exercise data in real time through the dial. After the user finishes the exercise, the smart watch uses an algorithm to calculate the exercise data for that time, obtain and display the maximum oxygen uptake to the user.

[0087] For example, Figures 1A to 1E , which is a schematic diagram of a graphical user interface (GUI) that may be involved in the implementation of a method for monitoring exercise information provided in an embodiment of the present application. For ease of understanding, the interface of a smart watch is used as an example for introduction.

[0088] For example, Figure 1AAs shown, the main interface of the App of the smart watch. The main interface of the App may include one or more Apps currently installed / bound to the smart watch, such as a short message App, a weather App, a sleep App, a heart rate App, a sports App 10, etc. In addition, the main interface of the App may also include other information such as a time indicator.

[0089] In some embodiments, Figure 1B As shown, when the smart watch detects the user inputting an operation 11 (such as clicking the sports app icon) to enter the sports app 10 on the smart watch, the operation 11 may be displayed as shown in FIG. Figure 1C The main interface of the sports app shown. Exemplarily, the main interface of the sports app may include a sports mode list, which includes various types of sports modes, such as outdoor running, indoor running, outdoor walking, etc., and each sports mode may be followed by a setting button corresponding to the sports mode.

[0090] In some embodiments, when the smartwatch detects that the user inputs a selection operation 12 for the outdoor running mode (such as clicking the outdoor running sports mode icon) on the main interface of the sports app, the outdoor running sports mode can be turned on in response to the selection operation 12. Figure 1D As shown, the smart watch can monitor and display multiple data of the user during exercise through the dial, such as exercise time, heart rate, calories, etc.

[0091] In some embodiments, when the user finishes exercising, the user can input an operation to end the exercise on the smart watch (not shown in the figure). In response to the operation to end the exercise, the smart watch can obtain the maximum oxygen uptake during the exercise based on the data of the exercise, and use the following methods to calculate the maximum oxygen uptake during the exercise: Figure 1E The interface shown displays the maximum oxygen uptake results to the user.

[0092] It should be understood that by calculating the maximum oxygen uptake of the user during exercise and displaying the result of the maximum oxygen uptake to the user, the user can intuitively obtain his or her cardiopulmonary capacity. Therefore, the accuracy of the maximum oxygen uptake result greatly affects the user's experience. However, there are some difficulties in obtaining the maximum oxygen uptake at present, such as: (1) During running, the user's heart rate and speed changes are relatively complex, and it is difficult to obtain reliable data fragments for calculating the maximum oxygen uptake; (2) The running trend changes are complex, which will increase the difficulty of data point selection and algorithm prediction, and a detailed analysis of the movement state is required; (3) When calculating the maximum oxygen uptake result, the movement state needs to be tracked for a long time. How to achieve long-term and accurate tracking of exercise is related to user experience and algorithm accuracy.

[0093] In view of this, the embodiment of the present application provides a method for monitoring sports information, which obtains valid data of the user in a stable state of exercise through analysis of heart rate, speed, ACC intensity, etc., and stores it in a buffer; then, the data in the buffer is subjected to slope analysis and regression factor analysis to filter the data to obtain a more accurate heart rate-speed pair associated with the maximum oxygen uptake; then, the current result is subjected to trend analysis based on historical results, so that the trend of the maximum oxygen uptake is more in line with reality, and finally the output result of the maximum oxygen uptake is obtained. The method obtains accurate input data by performing multiple screening and filtering on the data in a stable state of exercise, and after initially obtaining the maximum oxygen uptake result, the maximum oxygen uptake result is subjected to multiple processing, thereby effectively improving the accuracy of obtaining the maximum oxygen uptake result.

[0094] The method for monitoring motion information provided in the embodiment of the present application can be applied to the scenario of obtaining the maximum oxygen uptake during the user's exercise process. The method can be executed by an electronic device as the main body, and the electronic device here can be, for example, a wearable device such as a smart watch or a bracelet; and / or, it can also be other devices such as mobile phones and tablet computers that can be wirelessly connected to wearable devices. Exemplarily, the method for monitoring motion information provided in the embodiment of the present application can be executed by a smart watch, or it can be executed jointly by a smart watch and a mobile phone. The embodiment of the present application does not limit the specific device type of the execution subject.

[0095] For example, Figure 2 2 is a schematic diagram of a system architecture of a method for jointly performing motion information monitoring by a smart watch and a mobile phone provided in an embodiment of the present application. The system architecture includes a smart watch 20 and a mobile phone 30.

[0096] It should be understood that the smart watch 20 in this article is only an example of a wearable device, and the mobile phone is only an example of a device with high computing power and capable of being bound to a wearable device. In practical applications, the type of the wearable device is not limited to a smart watch, for example, it can also be a smart bracelet; the device bound to the wearable device is not limited to a mobile phone, for example, it can also be a tablet computer, a laptop computer, etc., and the embodiments of this application do not limit this.

[0097] In some embodiments, the smartwatch is used to monitor the user's data during exercise, such as the user's heart rate and speed, etc. The mobile phone can store basic information of the user, such as the user's height, weight, age, etc. Optionally, the smartwatch and / or mobile phone can also store historical data of the user's exercise, such as storing the user's historical maximum oxygen uptake.

[0098] In some embodiments, the smart watch can establish a wireless connection with the mobile phone, such as a Bluetooth (BT) connection, or a wireless connection established through wireless fidelity (Wi-Fi), etc., which is not limited in the embodiments of the present application. The smart watch can send the monitored data to the mobile phone in real time through the wireless connection. In addition, when the user pre-selects a sports mode in the smart watch, the smart watch can also send the sports mode selected by the user to the mobile phone; or, when the user pre-selects a sports mode in the mobile phone, the mobile phone can record the sports mode selected by the user.

[0099] In some embodiments, after the mobile phone obtains the data corresponding to the exercise, it can obtain effective data features based on the user's basic information, running intensity, real-time exercise speed and heart rate data, combined with the state judgment of the exercise, data point selection and data filtering operations; and use these effective data features as sample inputs, and obtain the mapping relationship between multi-dimensional variable inputs and maximum oxygen uptake through artificial intelligence (AI) modeling; finally, the maximum oxygen uptake result is obtained by performing result fusion and historical smoothing operations. After obtaining the maximum oxygen uptake result corresponding to this exercise, the mobile phone can display the maximum oxygen uptake result to the user through its own display screen and / or through the display screen of the smart watch.

[0100] It should be noted that since mobile phones have stronger computing power than smart watches, the smart watch can collect the user's vital sign data and / or exercise data during exercise, and the mobile phone can then identify the actual exercise type based on this data and calculate the maximum oxygen uptake result based on the corresponding model, which can improve the efficiency of calculation.

[0101] certainly, Figure 2 The embodiment only provides an example of a method for performing motion information monitoring. In practical applications, the method for motion information monitoring provided in the embodiment of the present application can also be performed by a smart watch alone, that is, the smart watch is based on the user's basic information, running intensity, real-time motion speed and heart rate related data, combined with the state judgment of the motion, data point selection and data filtering operations, to obtain effective data features; and these effective data features are used as sample inputs, and the mapping relationship between multi-dimensional variable input and maximum oxygen uptake is obtained through AI modeling; finally, the maximum oxygen uptake result is obtained by performing result fusion and historical smoothing operations. After obtaining the maximum oxygen uptake result corresponding to this exercise, the receiver can only display the maximum oxygen uptake result to the user through its own dial display interface.

[0102] The embodiments of the present application do not impose any limitation on the subject of the method for monitoring the motion information. For ease of description, the following embodiments are all introduced by taking the subject of the method for monitoring the motion information as a wearable device as an example (specifically, a smart watch is used as an example).

[0103] For example, Figure 3 , which is a schematic structural diagram of an electronic device 100 provided in an embodiment of the present application. The electronic device 100 may correspond to the wearable device (such as a smart watch) mentioned above or a device bound to a smart watch (such as a mobile phone).

[0104] The electronic device 100 may include a processor 110, a memory 120, an audio module 130, a display screen 140, a camera 150, a subscriber identification module (SIM) card interface 160, a positioning module 170, a sensor module 180, a charging management module 190, a power management module 191, a battery 192, etc.

[0105] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or separate some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0106] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0107] The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0108] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0109] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0110] It is understandable that the interface connection relationship between the modules illustrated in the embodiment of the present invention is only a schematic illustration and does not constitute a structural limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0111] The memory 120 can be used to store computer executable program codes, and the executable program codes include instructions. The memory 120 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application (application, App) required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data (such as audio data, image data, etc.) created during the use of the electronic device 100, etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (universal flash storage, UFS), etc. The processor 110 executes various functional applications and data processing of the electronic device 100 by running instructions stored in the memory 120, and / or instructions stored in a memory provided in the processor 110.

[0112] The electronic device 100 can implement audio functions through an audio module 130, a speaker 131, a receiver 132, a microphone 133, and an application processor (AP). For example, music playing, recording, etc. Among them, the speaker 131, also known as a "speaker", is used to summon audio electrical signals into sound signals. The electronic device 100 can listen to music or listen to hands-free calls through the speaker 131. The microphone 133, also known as a "microphone" or a "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak by putting his mouth close to the microphone 135 to input the sound signal into the microphone 133.

[0113] The display screen 140 can be used to display images, videos, etc. When the electronic device 100 is a smart watch, the display screen can be one or more, for example, including a display screen arranged on the front of the smart watch and a display screen arranged on the back of the smart watch, wherein the display screen arranged on the front of the smart watch can also be referred to as the "main screen" or "first display screen"; the display screen arranged on the back of the smart watch can also be referred to as the "sub-screen" or "second display screen". The display screen 140 is a display panel. The display panel can adopt a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active matrix organic light-emitting diode or an active matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light emitting diode (QLED), etc.

[0114] The electronic device 100 can realize the shooting function through the ISP, the camera 150, the video codec, the display screen 140, the GPU and the application processor.

[0115] The SIM card interface 160 is used to connect a SIM card. The SIM card can be connected to and separated from the electronic device 100 by inserting it into the SIM card interface 160 or pulling it out from the SIM card interface 160. The SIM card interface 160 can support Nano SIM cards, MicroSIM cards, SIM cards, etc. Multiple cards can be inserted into the same SIM card interface 160 at the same time. The types of the multiple cards can be the same or different. The SIM card interface 160 can also be compatible with different types of SIM cards. The SIM card interface 160 can also be compatible with external memory cards. The electronic device 100 can interact with the network through the SIM card to realize functions such as calls and data communications. In some embodiments, the electronic device 100 can also use an eSIM, that is, an embedded SIM card. The eSIM card can be embedded in the electronic device 100.

[0116] The sensor module 180 of the electronic device 100 may include an acceleration sensor 180A, a gyroscope 180B, a magnetic induction sensor 180C, a Hall sensor 180D, and the like.

[0117] The acceleration sensor 180A can detect the magnitude and direction of the acceleration of the electronic device 100 in all directions (generally three axes). When the electronic device 100 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of the device, and is applied to horizontal and vertical screen switching, pedometers and other applications. The gyroscope 180B can be used to determine the motion posture of the electronic device 100. In some embodiments, the angular velocity of the electronic device 100 around three axes (i.e., x, y and z axes) can be determined by the gyroscope 180B. The magnetic induction sensor 180C, also known as an electronic compass, is used to locate the orientation of the device. In some embodiments, the electronic device 100 can calculate the posture of the electronic device based on the acceleration sensor 180A, the gyroscope 180B and the magnetic induction sensor 180C, and apply it to the pedometer application. When the electronic device 100 is a smart watch, the Hall sensor 180D can be used to detect whether the body of the smart watch is facing up or back-facing, so that the processor 110 can determine whether the smart watch enters the do not disturb mode / power saving mode / predefined mode, etc. The Hall sensor 180D can also be used to detect whether the body of the smart watch is separated from the shell, so that the processor 110 can determine whether to automatically answer the call, etc.

[0118] Optionally, the sensor module 180 may also include other sensors, such as a pressure sensor, a proximity light sensor, an ambient light sensor, a fingerprint sensor, a touch sensor, and the like. Among them, the pressure sensor is used to sense the pressure signal and can convert the pressure signal into an electrical signal. The proximity light sensor may include, for example, a light emitting diode (LED) and a light detector, such as a photodiode. The light emitting diode may be an infrared light emitting diode. The electronic device 100 emits infrared light outward through the light emitting diode. The ambient light sensor is used to sense the brightness of the ambient light. The electronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived brightness of the ambient light. The fingerprint sensor is used to collect fingerprints. The temperature sensor is used to detect the temperature. The touch sensor is also called a "touch panel". The touch sensor can be set on the display screen 194, and the touch sensor and the display screen 194 form a touch screen, also called a "touch screen". The touch sensor is used to detect touch operations acting on or near it. The bone conduction sensor can obtain vibration signals.

[0119] In addition, the sensor module 180 also includes an air pressure sensor and a distance sensor. The air pressure sensor is used to measure air pressure. In some embodiments, the electronic device 100 calculates the altitude through the air pressure value measured by the air pressure sensor to assist positioning and navigation. The distance sensor is used to measure the distance. The electronic device 100 can measure the distance through infrared or laser.

[0120] Of course, the electronic device 100 may also include other sensors, which will not be described in detail here.

[0121] The charging management module 190 is used to receive charging input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 190 can receive charging input from a wired charger through a USB interface. In some wireless charging embodiments, the charging management module 190 can receive wireless charging input through a wireless charging coil of the electronic device 100. While the charging management module 190 is charging the battery 192, it can also power the device through the power management module 191.

[0122] The power management module 191 is used to connect the battery 192, the charging management module 190 and the processor 110. The power management module 191 receives input from the battery 192 and / or the charging management module 190, and supplies power to the processor 110, the memory 120, the display screen 140, the camera 150, and the wireless communication module 160. The power management module 191 can also be used to monitor parameters such as battery capacity, battery cycle number, battery health status (leakage, impedance), etc. In some other embodiments, the power management module 191 can also be set in the processor 110. In other embodiments, the power management module 191 and the charging management module 190 can also be set in the same device.

[0123] The wireless communication function of the electronic device 100 can be implemented through the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0124] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G applied to the electronic device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves, filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor and convert it into electromagnetic waves for radiation. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

[0125] The modem processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be sent into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to a speaker 131, a receiver 132, etc.), or displays an image or video through a display screen 140. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be set in the same device as the mobile communication module 150 or other functional modules.

[0126] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the electronic device 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves, modulates the frequency of the electromagnetic wave signal and filters it, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation.

[0127] The digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals. For example, when the electronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy. The video codec is used to compress or decompress digital video. The NPU is a neural network (NN) computing processor that quickly processes input information by drawing on the structure of biological neural networks, such as the transmission mode between neurons in the human brain, and can also continuously self-learn.

[0128] Exemplarily, the software system of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. The embodiment of the present invention takes the Android system of the layered architecture as an example to exemplify the software structure of the electronic device 100. Figure 4 It is a software structure block diagram of the electronic device 100 according to an embodiment of the present application.

[0129] The layered architecture divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom: the application layer, the application framework layer, the Android runtime and system library, and the kernel layer.

[0130] The application layer can include a series of application packages. Figure 4 As shown, the application package may include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, cloned application, etc.

[0131] The application framework layer provides application programming interface (API) and programming framework for the applications in the application layer. The application framework layer includes some predefined functions. Figure 4 As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0132] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0133] Content providers are used to store and retrieve data and make it accessible to applications. The data may include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0134] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.

[0135] The phone manager is used to provide communication functions of the electronic device 100, such as management of call status (including connecting, hanging up, etc.).

[0136] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0137] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt sound is emitted, the terminal vibrates, the indicator light flashes, etc.

[0138] Android Runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system.

[0139] The core library consists of two parts: one part is the function that needs to be called by the Java language, and the other part is the Android core library.

[0140] The application layer and the application framework layer run in the virtual machine. The virtual machine executes the java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as obstacle life cycle management, stack management, thread management, security and exception management, and garbage collection.

[0141] The system library may include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), short-range Wi-Fi module, etc.

[0142] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

[0143] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0144] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0145] A 2D graphics engine is a drawing engine for 2D drawings.

[0146] The short-range Wi-Fi module is used to establish a hotspot on a Wi-Fi channel, such as establishing a Wi-Fi hotspot on a 2.4G channel or a 5G channel.

[0147] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.

[0148] In order to better understand the method for monitoring exercise information provided by the embodiment of the present application, the specific implementation process of the method for monitoring exercise information provided by the embodiment of the present application is introduced below in conjunction with the accompanying drawings. It should be understood that in order to accurately obtain the maximum oxygen uptake result, it is necessary to first model the analysis model corresponding to the maximum oxygen uptake.

[0149] Exemplarily, taking running as an example, the process of establishing a model for maximum oxygen uptake analysis may include the following process:

[0150] First, collect the basic user information of the tester and the real-time motion data of the running.

[0151] The basic user information may include, for example, the user's height, weight, age, gender, historical exercise data, etc. The real-time exercise data may include, for example, acceleration sensor (ACC), GPS speed, and photoplethysmography (PPG) data (or heart rate data), etc.

[0152] In some embodiments, the method of collecting basic user information may include: collecting basic user information corresponding to the tester through a smart watch worn by the tester, for example: method (1), the smart watch receives basic user information input by the athlete; method (2), the smart watch obtains basic user information from a terminal device (such as a mobile phone) with which a wireless connection is established. The embodiment of the present application does not limit the method of obtaining basic user information by a smart watch.

[0153] In some embodiments, the method of collecting the real-time motion data of the tester may include: collecting the heart rate, speed and other information of the tester through the smart watch worn by the tester. Figure 5 As shown, before exercising, the tester wears the smart watch 501 in advance and turns on the running exercise mode of the smart watch; thereafter, the tester exercises according to the preset exercise mode, such as performing standard incremental load running on a professional treadmill; during the exercise, the smart watch 501 can collect data such as the tester's real-time heart rate and speed.

[0154] In some embodiments, the basic information and real-time motion data of the user collected by the smart watch can be used as input data (or sample data) of the analysis model corresponding to the maximum oxygen uptake.

[0155] Secondly, collect standard data of the test subjects' maximum oxygen uptake during exercise.

[0156] In some embodiments, before establishing the VO2max analysis model, standard data of VO2max results may also be obtained through professional devices, which may include respiratory metabolic instrument equipment (such as a portable gas metabolic analyzer (COSMED K5 device)), Polar heart rate belt, etc.

[0157] Exemplarily, the process of obtaining standard data of maximum oxygen uptake results may include: Figure 5 As shown, before exercising, the test subjects wore professional devices (with Figure 5 Taking the respiratory metabolic meter device 502 shown as an example); thereafter, the tester can perform standard incremental load running on a professional treadmill until the exercise limit corresponding to the maximum oxygen uptake is reached; thereafter, the oxygen uptake result obtained by the professional device based on the corresponding data at the exercise limit can be regarded as the standard data of the accurate maximum oxygen uptake result.

[0158] As an example, incremental load running may include: the tester changes a speed step every 3 minutes, gradually increasing the running speed until the exercise limit corresponding to the maximum oxygen uptake is reached.

[0159] There are multiple ways to determine whether the tester has reached the exercise limit corresponding to the maximum oxygen uptake, such as: (1) the heart rate of the tester reaches a preset value, such as the difference between 220 and the age of the tester; (2) the respiratory quotient (RQ) of the tester reaches or exceeds 1.1; (3) the tester subjectively feels the fatigue level and compares it with the fatigue level in the rating of perceived exertion (RPE), and when the fatigue level corresponds to the exhaustion level (such as level 10), it is determined that the tester has reached the exercise limit corresponding to the maximum oxygen uptake. In practical applications, the above three ways can be used simultaneously to determine whether the tester has reached the exercise limit, such as first determining the fatigue level of the tester according to the RPE scale; if the tester reaches level 10 in the RPE scale, then it can be determined whether the heart rate of the tester has reached the preset value; if the heart rate of the tester reaches the preset value, then it can be further determined whether the respiratory quotient of the tester has reached 1.1, and if so, it means that the corresponding state of the tester is the state at the exercise limit.

[0160] It should be noted that the embodiments of the present application only take the three conditions of mode (1) to mode (3) being satisfied at the same time as an example, and introduce the test person reaching the exercise limit state. However, in actual application, it is also possible to judge whether the test person has reached the exercise limit by only any two of these three modes. In addition, the exercise limit state mentioned in the embodiments of the present application refers to the exercise state corresponding to when the test person reaches the maximum oxygen uptake.

[0161] It should also be noted that the embodiments of the present application are only based on Figure 5 In the example of the tester wearing a smart watch 501 and a respiratory metabolism instrument device 502, the tester is introduced. In actual applications, the tester can also wear more other devices. For example, the tester can also wear a heart rate belt, which can be used to collect the real-time heart rate of the athlete during exercise.

[0162] In some embodiments, the professional device can obtain the speed change trend data and the heart rate change trend data corresponding to the current exercise process; according to the speed change trend data and / or the heart rate change trend data, the trend of oxygen uptake change over time can be obtained. Figure 6 As shown in FIG. 1 , the oxygen uptake change trend based on heart rate is obtained, wherein the change trend of oxygen uptake over time is proportional to the change trend of heart rate over time. Figure 6 From the analysis of the changing trend, it can be obtained that the heart rate of the test person reaches the maximum from time T1 to time T2. Therefore, time T1 to time T2 can be regarded as the test person reaching the exercise limit, and the oxygen uptake corresponding to this stage can be regarded as the test person's maximum oxygen uptake.

[0163] Afterwards, the user's basic information, real-time exercise data and maximum oxygen uptake standard data are used as training data for the maximum oxygen uptake analysis model.

[0164] In some embodiments, AI modeling can be performed based on the user's basic information, real-time motion data, and maximum oxygen uptake obtained by professional equipment, and through training, a maximum oxygen uptake analysis model with a mapping relationship between the user's basic information, real-time motion data, and maximum oxygen uptake results can be obtained.

[0165] It should be noted that the step of obtaining the maximum oxygen uptake through professional oxygen uptake detection equipment can be used as a pre-step to establish the maximum oxygen uptake model. The maximum oxygen uptake results obtained by professional oxygen uptake detection equipment are more accurate, so they can be used as standard data for subsequent evaluation and calibration of the accuracy of the maximum oxygen uptake model. In other words, when other conditions are the same (such as the user's basic information and exercise mode are the same), the closer the maximum oxygen uptake result output by the maximum oxygen uptake model is to the result output by the maximum oxygen uptake detection equipment, the more accurate the maximum oxygen uptake model is.

[0166] For example, Figure 7 As shown, it is a schematic flow chart corresponding to a method for monitoring exercise information provided in an embodiment of the present application. The execution subject of the method may be a smart watch, and the smart watch is configured with a maximum oxygen uptake analysis model. The process may specifically include the following steps:

[0167] S701, algorithm initialization.

[0168] S702, session initialization.

[0169] Among them, in step S701 and step S702, the process of initializing the algorithm and initializing the session can refer to the existing process, and the embodiment of the present application will not be described in detail.

[0170] S703, periodically obtain heart rate, speed, ACC intensity and scene information.

[0171] In some embodiments, the user can periodically obtain heart rate, speed, ACC intensity and scene information through a smart watch.

[0172] In one possible scenario, Figure 8 As shown, assuming that the user is about to go for an outdoor running exercise, before starting to run, the user can wear a smart watch in advance and turn on the corresponding exercise mode in the smart watch. The method for the user to turn on the outdoor running exercise mode in the smart watch can be referred to above. Figures 1A to 1C The description in the embodiments will not be repeated here.

[0173] In some embodiments, the smartwatch can periodically obtain the user's heart rate, speed, cadence, and scene information during exercise through multiple sensors. The sensors here can include, for example, a heart rate sensor, an acceleration sensor (such as a sensor corresponding to Figure 3 The acceleration sensor 180A in Figure 3 Gyroscope 180B in, magnetic induction sensor (such as corresponding to Figure 3 Magnetic induction sensor 180C), Hall sensor (such as corresponding to Figure 3 Hall sensor 180D) and positioning sensor (such as GPS sensor), etc.

[0174] Specifically, when the smart watch turns on the function of monitoring maximum oxygen uptake, the heart rate sensor in the smart watch can periodically and continuously collect the user's heart rate; when the smart watch detects that the user is in motion (such as continuous speed segments, or detects that the user manually turns on a certain exercise mode, etc.), the heart rate data can be read periodically.

[0175] Smart watches can also sense acceleration through an acceleration sensor and convert it into an electrical signal to estimate values ​​such as the number of steps and movement distance. In an embodiment of the present application, the acceleration sensor can be a gravity acceleration sensor. The smart watch can detect the angular velocity of the movement through a gyroscope and accurately track it during the movement. The smart watch can combine the data obtained based on the gyroscope and the data obtained by other sensors to determine whether the user is actually running or jogging / walking somewhere. In addition, the gyroscope can also eliminate data that is mistakenly believed to be caused by violent shaking of the wrist. The smart watch can determine the exact coordinates of the user's location through a magnetic sensor and / or a positioning sensor, which can be used to improve the accuracy of motion tracking. In addition, the GPS sensor can also obtain the trajectory of the user's movement based on the location information.

[0176] In addition, the smart watch can determine whether the user is currently in an indoor scene or an outdoor scene based on the location information collected by the GPS sensor. For example, the smart watch can determine whether the GPS coordinates of the user's location belong to the outdoor area in the map based on the GPS coordinates of the user's location and a pre-acquired map (such as an offline map). If so, the user's current scene information is determined to be an outdoor scene; if not, the user's current scene information is determined to be an indoor scene.

[0177] It should be noted that the sensors introduced in the embodiments of the present application are only examples. In actual applications, the smart watch may also include other types of sensors and obtain other information through other types of sensors. The embodiments of the present application are not limited to this.

[0178] In some embodiments, the smartwatch can collect information such as heart rate and speed through sensors when the user starts exercising. Specifically, the smartwatch can collect corresponding data in units of time windows, and the time window can be, for example, a first duration (such as 1 minute). Fig. 9 As shown, a schematic diagram of the change of heart rate over time after the start of exercise and a schematic diagram of the change of speed over time provided by an embodiment of the present application. The smart watch can store data corresponding to each time window in units of time windows. Among them, the time window can slide over time according to a preset period, such as sliding backward once every first period of the time window. The duration corresponding to the first period can be less than or equal to the first duration corresponding to the time window.

[0179] In some embodiments, the smart watch can periodically read and store the corresponding data in each window, for example, reading and storing data 12 times in 1 minute (that is, the data sampling rate is 12 times per minute). For example, as shown in Table 1 below, an example of the corresponding relationship between the time window and the data stored in the smart watch is:

[0180] Table 1

[0181]

[0182] It should be noted that the representation of the time window identifier in Table 1 above is only an example. In actual applications, the identifier of the time window can also be represented by other information, such as the time range corresponding to the time window, etc., and the embodiments of the present application do not limit this. In addition, the information type corresponding to the time window shown in Table 1 is also only an example. In actual applications, the information type corresponding to each time window can also include more or fewer types, and the embodiments of the present application do not limit this.

[0183] It should be noted that two adjacent time windows may have overlapping time parts. For example, the time range corresponding to time window 1 is 8:00:00-8:01:00, and the time range corresponding to time window 2 is 8:00:02-8:01:02. Then the smart terminal can first store the data corresponding to each time window, and then process the data of two or more time windows with overlapping time ranges.

[0184] In some embodiments, the smartwatch can also determine whether the user's current exercise time reaches a preset time (such as 10 minutes). If the preset time is reached, the next steps are executed; if the preset time is not reached, the subsequent steps are not executed until the preset time is reached.

[0185] It should be noted that even if the user's current exercise time has not reached the preset time, since the user has started exercising, the smart watch can start collecting data corresponding to each time window.

[0186] It should also be noted that the operation of determining whether the user's current exercise time reaches the preset time in this step is an optional operation, and this operation can also be performed in the subsequent step S709.

[0187] S704, analyzing the motion state.

[0188] The motion state here may include a stable motion state and an unstable motion state. A stable motion state may include, for example, a quiet state, a medium-intensity stable state, and a high-intensity stable state. An unstable motion state may include, for example, a motion rising state and a motion falling state.

[0189] Among them, the quiet state may specifically refer to a state in which the user is not exercising. The moderate-intensity exercise state may specifically refer to an exercise state corresponding to a speed greater than a first threshold but less than or equal to a second threshold, and the speed remains stable; or, a heart rate greater than a third threshold but less than or equal to a fourth threshold, and the heart rate remains stable. The high-intensity exercise state may specifically refer to an exercise state corresponding to a speed greater than a fourth threshold, and the speed remains stable; or, a heart rate greater than a fourth threshold, and the heart rate remains stable. Among them, keeping the speed stable may include: the speed change amplitude does not exceed the first range; keeping the heart rate stable may include: the heart rate change amplitude does not exceed the second range.

[0190] The rising state of movement may specifically refer to a state in which the speed gradually increases during movement (or a state in which the heart rate gradually increases). The falling state of movement may specifically refer to a state in which the speed gradually decreases during movement (or a state in which the heart rate gradually decreases).

[0191] The purpose of analyzing the exercise state in this step is mainly to determine the stable exercise state in order to obtain effective data and then analyze the maximum oxygen uptake. The specific process of the smart watch analyzing the exercise state will be described in detail below and will not be described in detail here.

[0192] In some embodiments, in this step, the smartwatch can also obtain the type of exercise performed by the user through AR state recognition. Specifically, the smartwatch can periodically perform exercise type recognition based on sensor data through the AR state recognition module. Among them, taking the user's exercise type when the smartwatch recognizes the second moment as an example, the smartwatch can identify the type of exercise performed by the user at the second moment in units of data in the second time window to which the second moment belongs. Among them, the relationship between the second moment and the second time window to which the second moment belongs may include: the duration corresponding to the second window is the first duration before the second moment, and the second time window includes the second moment. For example, if the second moment is 8:01:05 and the first duration is 1min, then the time window corresponding to the second moment is 8:00:05-8:01:05; for another example, if the second moment is 8:00:05 and the first duration is 1min, then the time window corresponding to the second moment can also be 7:59:35-8:01:35, at which time the time window corresponding to the second moment includes the second moment, but the second moment is the middle moment of the time window.

[0193] In some embodiments, the smart watch can identify the type of exercise performed by the user every second period of time. Fig.10As shown, the smart watch identifies the user's exercise type at T1, T2, T3, and T4 respectively, where taking T3 and T4 as examples, the time window corresponding to T3 is the time range corresponding to the first duration before it, that is, T1-T3; the time window corresponding to T4 is the time range corresponding to the first duration before it, that is, T2-T4.

[0194] In some embodiments, the specific method for a smart watch to perform AR state recognition may include: the AR state recognition module of the electronic device periodically reads the data collected by the sensor at a certain sampling rate, and then periodically identifies the corresponding motion type of the user at the current moment based on the data obtained each time; thereafter, the number of times and / or the percentage corresponding to each motion type are counted; when a certain motion type (recorded as the first motion type) is recognized the most times and / or has the highest percentage, and the number of times it is recognized is equal to or greater than the first number and / or the percentage is equal to or greater than the first ratio, it is determined that the motion performed by the user within the time window is the first motion type.

[0195] As an example, Fig.10 As shown, assuming that the electronic device detects that the user starts exercising from T1 (such as corresponding to 13:00:00), and the second time length corresponding to the preset time window is 1min, and the interval between two consecutive time window data is 1s (that is, the period of time window sliding is 1s), then the time period corresponding to the first time window collected by the electronic device is: 13:00:00-13:01:00; the time period corresponding to the second time window is: 13:00:01-13:01:01, and so on. When the electronic device performs AR state recognition on the user's motion type at time T3 (such as corresponding to 13:01:01), the AR state recognition module can obtain data corresponding to multiple moments in the first time window (i.e., T1-T3, 13:00:01-13:01:01) from the sensor according to the preset sampling rate, and then analyze the data corresponding to the multiple moments respectively to obtain the corresponding motion type; thereafter, the electronic device can perform statistical analysis on the motion type corresponding to the first time window, and determine the motion type that appears the most times, and / or has the highest percentage, and the number of occurrences is equal to or greater than the first number, and / or the percentage is equal to or greater than the first ratio as the first motion type performed by the user in the first time window. Exemplarily, assuming that the motion types after analysis include walking, running, and skipping rope, and the first number is 20 times, the first ratio is 70%, and the number and percentage corresponding to each motion type are shown in Table 2 below:

[0196] Table 2

[0197]

[0198] Combined with the analysis in the above table, in some embodiments, the AR module of the electronic device can read the sensor data every 1s, and then use the activity recognition AR algorithm to identify the real-time motion state, and count it as one calculation. After the next second, the AR module continues to read the sensor data according to the cycle, and performs real-time calculations to obtain the motion type, and so on. When the number of calculations reaches the number corresponding to the time window, such as the time window is 1min, then the number of calculations reaches the number corresponding to the time window when the number is 60 times, then these AR state recognition results can be regarded as the recognition data corresponding to the time window. Afterwards, the recognition data used for the time window can be statistically analyzed, and the proportion of various types of motion can be counted to obtain the real type of motion. As shown in the data in Table 1 above, within the first time window, after AR state recognition based on 60 data, 50 of the data AR state recognition motion types are walking, 10 of the data AR state recognition motion types are running, and 0 of the data are recognized as skipping. That is to say, the percentage of walking in all sports categories in the first time window is 83.3%, the percentage of running in all sports types in the first time window is 16.7%, and the percentage of rope skipping in all sports types in the first time window is 0%. After comparison, it can be known that walking is the sports with the most occurrences and the highest proportion in the first time window; next, the occurrences and / or the percentage of walking can be compared with the corresponding first number (20 times) and / or the first proportion (70%), respectively. Since the occurrences of walking are greater than the first number, and / or the percentage of walking is greater than the first proportion, it can be determined that the type of sports performed by the user in the first time window is walking.

[0199] It should be noted that the method for motion monitoring provided in the embodiments of the present application can be mainly applicable to specific types of motion such as walking, running, swimming, etc. Therefore, in some embodiments, when it is determined that the current type of motion performed by the user belongs to a specific type of motion, the next motion information monitoring process can be continued; if it is determined that the current type of motion performed by the user does not belong to a specific type of motion, the process can be terminated directly.

[0200] When the process is ended directly, the data provided by the smartwatch to the user may not include the maximum oxygen uptake, or other icons may be displayed to indicate the maximum oxygen uptake result, such as: Fig.11 The “--” shown indicates the maximum oxygen uptake result.

[0201] In some embodiments, after analyzing the motion state, a motion label corresponding to the motion state may be input, which is used to indicate the specific type of the motion state, such as quiet low intensity, quiet medium intensity, quiet high intensity, walking medium intensity, running high intensity, running ascending period, running descending period, etc.

[0202] S705, judging whether the point selection condition is met.

[0203] In some embodiments, the point selection condition may be: whether the user's motion state reaches a speed greater than the first pace and the motion state reaches a stable state.

[0204] Exemplarily, the motion states that meet the point selection conditions in the embodiments of the present application may include: medium-intensity walking, medium-intensity running, high-intensity running, etc.

[0205] It should be noted that although there can be multiple stable states, not every stable state meets the point selection condition. For example, when a user is running at a certain pace, although the user's running time increases, the user's heart rate may first rise and then stabilize. At this time, the exercise state corresponding to the user's stable heart rate can be regarded as meeting the point selection condition.

[0206] In some embodiments, before performing data point selection, it can be determined whether the currently acquired data meets the point selection conditions. If the point selection conditions are met, the data point selection operation is performed; if the point selection conditions are not met, the step of acquiring data (i.e., step S703) can be returned to. If the point selection conditions are met, the smart watch can eventually provide the user with a maximum oxygen uptake result through the dial; if the point selection conditions are not met, the smart watch will not display the maximum oxygen uptake result, or, in this case, the smart watch can use other symbols to represent the maximum oxygen uptake result, such as displaying Fig.11 The “--” shown indicates the maximum oxygen uptake result.

[0207] Alternatively, in some other embodiments, if the smartwatch acquires and stores the historical maximum oxygen uptake of the tester, then when the selection point condition is not met, the smartwatch can provide the historical maximum oxygen uptake to the user through the dial. It should be understood that since the maximum oxygen uptake usually does not change significantly within a certain period of time, when the selection point condition is not met, the historical maximum oxygen uptake is used as the result of this time, and the user can also know his or her oxygen uptake data on the basis of ensuring the accuracy of the maximum oxygen uptake result.

[0208] In some embodiments, it may be periodically determined whether the point selection condition is met, and if so, data point selection is performed in the manner described above.

[0209] In some embodiments, judging whether the point selection condition is met may specifically include: determining whether the point selection condition is met according to the motion label of the point selection time window corresponding to the point selection moment. If the motion label of the point selection time window indicates that the motion state in the time window is an unstable motion state (such as a running ascending period, a running descending period, etc.), it means that the point selection moment does not meet the point selection condition; or, if the motion label of the point selection time window indicates that the motion state in the time window is an abnormal motion state, such as quiet low intensity, quiet medium intensity and quiet high intensity, it also means that the point selection moment does not meet the point selection condition; or, or, if the motion label of the point selection time window indicates that the motion state in the time window is a heart rate deviation state, it also means that the point selection moment does not meet the point selection condition.

[0210] The heart rate drift state may be, for example, a state where the speed does not change but the heart rate changes significantly. Fig.12 As shown in the figure, when the user is doing intermittent running, within the time range represented by the two dotted lines, the user's running speed does not change each time, but the heart rate corresponding to each run changes significantly, which reflects that when the user stops running for a period of time and then runs again, the heart rate will change significantly, that is, the heart rate drift occurs. In this case, the exercise data cannot accurately obtain the maximum oxygen uptake, so the heart rate drift state is also considered to not meet the point selection condition.

[0211] In some embodiments, if the point selection condition is met (that is, the judgment result of this step is "yes"), step S706 can be executed next; if the point selection condition is not met (that is, the judgment result of this step is "no"), step S703 can be re-executed next.

[0212] S706, store the heart rate and speed.

[0213] In some implementations, the smartwatch can store exercise data according to a time window. For example, as the user's exercise time changes, the time window slides accordingly. The smartwatch can store exercise data in each time unit in units of time windows. The time window corresponds to a duration of Ns, for example. The exercise data can include real-time heart rate and real-time speed in each time window.

[0214] In some embodiments, a specific method for data point selection may include: when the point selection moment is reached, obtaining motion data in a time window corresponding to the point selection moment; judging whether there are valid data points in the time window (that is, data points that meet the point selection conditions) based on the motion data; if there are valid data points, these data points may be stored in a buffer.

[0215] In some embodiments, the buffer may store data pairs corresponding to valid data, and each data pair may include, for example, a sequence number (order), a speed average, a heart rate average, a duration, and a motion state label. For example, the i-th valid data in the buffer may be represented as: {order_i, v_i, hr_i, t_i, i}. Among them, order_i may represent the sequence number of the i-th data, vi_i may represent the average speed corresponding to the i-th data, hr_i may represent the average heart rate corresponding to the i-th data, t_i may represent the data duration corresponding to the i-th data (for example, the duration of a point selection window), and i may represent the motion state corresponding to the i-th data (such as medium-intensity walking, high-intensity running, etc.).

[0216] Among them, each point selection moment can be spaced at a fixed period, such as performing a point selection operation once every 1 second. Different point selection moments correspond to different time windows. Exemplarily, the correspondence between different moments and time windows may include: the point selection time window corresponding to the point selection moment is the Ms time range before the point selection moment, and the point selection time window includes the point selection moment. For example, if the point selection moment is 8:00:05 and the value of M is 2, then the point selection time window corresponding to the point selection moment is 8:00:03-8:00:05. Optionally, for another example, if the point selection moment is 8:00:05 and the value of N is 2, then the point selection time window corresponding to the point selection moment can also be 8:00:04-8:00:06.

[0217] It should be noted that due to different exercise states, there may be multiple valid data points during an exercise. For example, when the tester performs interval running, there is a stable exercise state in each running segment, and multiple valid data points can be obtained. At this time, the obtained valid data points can be stored in the buffer first, and after the exercise is completed, these data points can be filtered, and the filtered data points can be used as model input data to obtain the maximum oxygen uptake results.

[0218] S707, determine whether the exercise is finished.

[0219] In some embodiments, the method of determining whether the movement is finished may include, for example, determining whether there is a continuous speed segment within a preset time period. In which, when in an indoor scene, the speed segment may be an ACC speed segment; when in an outdoor scene, the speed segment may be a GPS speed segment.

[0220] For example, the speed segment in the embodiment of the present application may refer to the user's speed not being zero within the second time period (such as within 1 minute). The continuous speed segment may refer to each speed segment being continuous, or the interval between two consecutive speed segments not exceeding a preset time interval (such as 5 minutes or 10 minutes). Fig.13 As shown, it is a schematic diagram of the speed change of the user within 10 minutes. Among them, within the duration of 0-2.5 minutes, the corresponding speeds are not 0, so there are speed segments in this time period (for example, it can be specifically divided into speed segment 1 corresponding to 0-1 minutes, speed segment 2 corresponding to 1-2 minutes, and speed segment 3 corresponding to 1-2 minutes); the corresponding speeds from 2.5 to 4 minutes are all 0, and the corresponding speeds from 4 to 6 minutes are not 0, but because the duration from 2.5 minutes to 4 minutes is 1.5 minutes, the time interval is less than the preset time interval (such as 5 minutes or 10 minutes), so the 2.5-6 minutes are considered to have a speed segment; similarly, the speed corresponding to 6-7 minutes is 0, and the speed corresponding to 7-10 minutes is not 0, but because the duration from 6-7 minutes is 1 minute, the time interval is less than the preset time interval (such as 5 minutes or 10 minutes), so the 6-7 minutes are considered to have a speed segment. Based on the above analysis, in Fig.13 In the case of speed change shown in the figure, the 0-10 minute period can be regarded as a continuous speed segment. If the speed from the 10-30 minute period is 0 ( Fig.11 (not shown), since this duration is 20 minutes, reaching the preset time interval, it can be considered that there is a continuous speed segment from 0-10 minutes, but there is no continuous speed segment from 0-30 minutes.

[0221] In some embodiments, the electronic device may obtain whether there is a speed segment based on one or more of a speed sensor, an acceleration sensor, a GPS sensor, a time sensor, etc. For example, when the speed of the user obtained by the electronic device based on the speed sensor and the time sensor within the first time period is not zero, it can be determined that there is a speed segment; for another example, when the acceleration of the user obtained by the electronic device based on the acceleration sensor and the time sensor within the first time period is greater than zero, it can be determined that there is a speed segment; for another example, when the position of the user obtained by the electronic device based on the GPS sensor and the time sensor within the first time period continues to change, it can be determined that there is a speed segment.

[0222] In some embodiments, if the movement is completed (that is, the judgment result of this step is "yes"), step S708 can be executed next; if the movement is not completed (that is, the judgment result of this step is "no"), step S703 can be re-executed next.

[0223] S708, filter data.

[0224] In some embodiments, among the valid data stored in the buffer, there may be two or more cases where the speed is the same or similar but the heart rate is different. In this case, the data with a later time can be filtered out to exclude abnormal data caused by human physiological reasons.

[0225] As an example, if a user runs at 8 km / h for 10 minutes, then rests for 5 minutes, and then continues to run at 8 km / h for 5 minutes, during the second run, the user's heart rate is higher than the user's heart rate in the first run by a preset threshold, that is, the speeds corresponding to the first run and the second run are the same, but the user's heart rate corresponding to the latter is higher; then, the data corresponding to these two runs are stored in the buffer. Then, when filtering data in this step, you can first obtain the data corresponding to the two runs from the buffer according to the speed; then, you can further compare whether the heart rate data corresponding to the two runs differ by more than the preset threshold; if the heart rate difference between the two exceeds the preset threshold, it means that the data corresponding to the second run may not appear during the user's normal exercise, but is affected by the user's physiological reasons. In order to avoid the data causing deviations in the results of the maximum oxygen uptake, the second run data can be filtered out of the buffer.

[0226] As another example, if the user runs at a speed of 8 km / h for 10 minutes, then rests for 5 minutes, and then continues to run at a speed of 8 km / h for 5 minutes, during the second running period, the difference between the user's heart rate and the user's heart rate in the first running period is less than the preset threshold, then the data corresponding to the first running period and the data corresponding to the second running period in the buffer can be merged and sorted. For example, the first speed average of the first running period and the second speed average of the second running period can be calculated, and then the first speed average and the second speed average are averaged to obtain the third speed average; and the first heart rate average of the heart rate of the first running period and the second heart rate average of the heart rate of the second running period are calculated, and then the first heart rate average and the second heart rate average are averaged to obtain the third heart rate average; in addition, the exercise time corresponding to the first running period (10 minutes) and the exercise time corresponding to the second running period (5 minutes) can be summed to obtain the duration corresponding to the exercise (15 minutes). Afterwards, the merged data can be stored in the buffer, and the data originally corresponding to the first running period and the data corresponding to the second running period can be filtered out.

[0227] It should be understood that filtering the valid data in the buffer according to speed and heart rate can be described as preliminary filtering, the purpose of which is to prevent data with the same speed but different heart rates from having a significant impact on the accuracy of the maximum oxygen uptake result. In order to further ensure the accuracy of the maximum oxygen uptake result, further filtering (or secondary filtering) can be performed after completing the preliminary filtering.

[0228] Exemplarily, the secondary filtering method may include, for example: filtering according to the number of valid data points corresponding to each point selection window during the motion process. Specifically, the following situations may be included:

[0229] Case (1): When the number of valid data points in each point selection window is 0 (or the number of valid data points in the buffer is 0), that is, there are no valid data points in the point selection window. This situation also means that the user's exercise state is unstable and does not meet the point selection conditions, then you can check whether there is a maximum oxygen uptake result in the historical data. If so, the maximum oxygen uptake result in the historical data can be used as the maximum oxygen uptake result output for this exercise; if not, the maximum oxygen uptake result that was not detected can be output (such as not outputting the maximum oxygen uptake, or other indicators can be displayed to indicate the maximum oxygen uptake result, such as displaying the following: Fig.11 The “--” shown here indicates the VO2max result).

[0230] Case (2): When the number of valid data points in each point selection window is 1 (or the number of valid data points in the buffer is 1), that is, there is only one valid data point in the point selection window. Then the data corresponding to this one valid data point is used as input data to calculate the maximum oxygen uptake.

[0231] Case (3): When the number of valid data points in each point selection window is 2 (or the number of valid data points in the buffer is 2), that is, there are only 2 valid data points in the point selection window. Then the data corresponding to these two valid data points can be used as input data separately to calculate the maximum oxygen uptake. At this time, there are also two results of the maximum oxygen uptake. If the difference between the two maximum oxygen uptake results is less than a certain range, then the average of the two maximum oxygen uptake results can be calculated, and the average value can be regarded as the result of the maximum oxygen uptake; if the difference between the two maximum oxygen uptake results is equal to or greater than a certain range, the data of this exercise can be regarded as abnormal. At this time, it is possible to query whether there is a maximum oxygen uptake result in the historical data. If so, the maximum oxygen uptake result in the historical data can be used as the maximum oxygen uptake result output for this exercise; if not, the maximum oxygen uptake result that was not detected can be output (such as not outputting the maximum oxygen uptake, or other symbols can be displayed to indicate the maximum oxygen uptake result, such as displaying Fig.11The “--” shown here indicates the VO2max result).

[0232] Case (4): When the number of valid data points in each point selection window corresponding to the current exercise stored in the buffer is 3 or more, then in this case, the speed and / or heart rate in each valid data point can be used for linear fitting, and then the abnormal valid data points can be filtered out using outlier analysis. For example, if a total of 6 valid data points are obtained from the buffer, and the specific data corresponding to the 6 valid data points are shown in Table 3 below; the result of linear fitting using the speed and heart rate of these 6 valid data points through linear regression can be as follows Fig.14 As shown; then, the outliers can be obtained through residual analysis. The outliers are far away from the standard linear straight line, that is, Fig.14 The first point in is an outlier. Then in the secondary filtering, the outlier can be deleted.

[0233] The reason for filtering outliers obtained through residual analysis is that under normal exercise intensity, the result of fitting the user's heart rate and speed should be close to a straight line. Based on this assumption, the embodiment of the present application regards points that deviate more from the straight line as abnormal data points and filters them.

[0234] Table 3

[0235]

[0236]

[0237] S709, determining whether the calculation conditions are met.

[0238] In some embodiments, the method of determining whether the calculation condition is met may include: determining whether the user's current exercise time reaches a preset time, and the preset time can be set as needed, for example, 10 minutes. When the user's exercise time reaches the preset time, it is determined that the calculation condition is met, and the next process can be continued; when the user's exercise time does not reach the preset time, it is determined that the calculation condition is not met, and the subsequent steps may not be performed until the preset time is reached.

[0239] It should be noted that even if the user's current exercise time has not reached the preset time, since the user has started exercising, the smart watch can start collecting data corresponding to each time window.

[0240] It should also be noted that the operation of determining whether the user's current exercise time has reached the preset time in this step is an optional operation, and this operation can also be performed in the aforementioned step S703.

[0241] In some embodiments, if the calculation condition is met (that is, the judgment result of this step is "yes"), step S710A can be executed next; if the calculation condition is not met (that is, the judgment result of this step is "no"), step S710B can be re-executed next.

[0242] The following first introduces the situation where the calculation conditions are not met:

[0243] S710B, determining whether there is historical maximum oxygen uptake data.

[0244] In some embodiments, the smartwatch can determine whether there is historical VO2max data based on the user's historical data. The user's historical data may include, for example, the user's speed, heart rate, ACC intensity, scene information, VO2max results, etc. within the historical duration. The historical duration can be flexibly set as needed, for example, it can be set to 2 months, which is not limited in the embodiments of the present application.

[0245] In some embodiments, if there is no historical maximum oxygen uptake data (that is, the judgment result of this step is "no"), step S711B can be executed next; if there is historical maximum oxygen uptake data (that is, the judgment result of this step is "yes"), step S712B can be executed next.

[0246] S711B, output measurement failure error code.

[0247] In some embodiments, if there is no historical data, or the historical data does not include the maximum oxygen uptake result within the historical time period, a measurement failure error code may be directly output. In response to the output result, the smart watch may not display the maximum oxygen uptake result, or may display other indicators to indicate the maximum oxygen uptake result, such as displaying Fig.11 The “--” shown indicates the maximum oxygen uptake result.

[0248] S712B, returns historical data.

[0249] In some embodiments, if the historical data includes maximum oxygen uptake results within a historical period, then if the calculation conditions are not met, the maximum oxygen uptake results in the historical data can be provided to the user through the dial as the results corresponding to this exercise.

[0250] It should be understood that since the maximum oxygen uptake usually does not change significantly within a certain period of time, when the point selection conditions are not met, the historical maximum oxygen uptake is used as the result of this time. This can also ensure that the user knows his or her oxygen uptake data while ensuring the accuracy of the maximum oxygen uptake result.

[0251] The following describes the situations that meet the calculation conditions:

[0252] S710A, regression model prediction.

[0253] In some embodiments, if the calculation conditions are met, then the valid data after secondary filtering can be used for regression model prediction. The regression model prediction method can include: normalizing the durations corresponding to the valid data points to obtain the weights corresponding to the maximum oxygen uptake, and then outputting the maximum oxygen uptake results based on the valid data points and their corresponding weights.

[0254] In some embodiments, there may be multiple regression models, such as a Bayesian regression model, an ensemble tree regression model, and a multivariate regression model, etc., which is not limited in the embodiments of the present application.

[0255] Taking the Bayesian regression model as an example, the specific process of presetting the regression model may include: (1) collecting maximum oxygen uptake test data; (2) obtaining user basic information, resting heart rate, maximum heart rate, stable heart rate and pace, etc. as feature vector x; (3) using the user's maximum oxygen uptake test result as the target output value y; (4) constructing a training data set, using Bayesian regression to model y=f(x, ω), and obtaining the ω parameter.

[0256] Specifically, let y=f(x, ω), where y represents the continuous maximum oxygen uptake, x represents the input variable related to the maximum oxygen uptake, and ω represents a parameter set with a certain spatial distribution. The maximum oxygen uptake model prediction is essentially to obtain the linear or nonlinear relationship between y and ω, x through machine learning modeling. In some embodiments, the formulas involved in the process of maximum oxygen uptake model prediction can be found in the following formulas (1-1) to (1-4):

[0257]

[0258] Where D is the data set; x i represents the i-th sample, y i represents the maximum oxygen uptake corresponding to the i-th sample, d represents the characteristic dimension of the sample, and R represents the Euclidean space.

[0259] y i =W T x i +ε,ε~N(0,β-1),P(W)~N(0,α -1 I) (1-2)

[0260] Among them, ε represents the residual, α -1 I means that each parameter is independent, α represents the variance, and W represents the weight parameter of the d-dimensional feature vector.

[0261] P(y i |x i, w)=N(W T x i , β -1 ) (1-3)

[0262] Assume that y follows a Gaussian distribution, y i and x i It is known that we need to estimate the distribution of W through the Bayesian probability estimation method. Specifically, we can solve the distribution of W through the posterior probability and likelihood estimation:

[0263] P(w|x i ,y i )=N(W|μ n ,∈ n )>>w * =β(βX T X+αI) -1 X T Y (1-4)

[0264] The prior knowledge of αI represents the ridge regression regularization technique.

[0265] S711A, perform a weighted fusion strategy process, and assign corresponding weights according to the stable state, duration, and sequence.

[0266] The weighted fusion strategy process in the embodiment of the present application can also be described as a single result weighted fusion strategy process. The specific process can be found below Fig.16 The detailed introduction in will not be repeated here.

[0267] In some embodiments, the result fusion process may include: after obtaining the current maximum oxygen uptake, if there is also a maximum oxygen uptake result in the historical data, the current maximum oxygen uptake result and the maximum oxygen uptake result in the historical data may be fused, so that the maximum oxygen uptake result finally outputted this time is not much different from the maximum oxygen uptake result outputted within the historical time period.

[0268] S712A, based on the historical VO2max data, smooths and suppresses the preliminary results of VO2max and determines the trend.

[0269] It should be noted that, although the user's maximum oxygen uptake result will not change significantly in a short period of time, in some cases, as the user's exercise time increases, the maximum oxygen uptake will also change in a certain trend. For example, for some obese users, when they first start exercising, the corresponding maximum oxygen uptake result may be relatively low, but as the exercise increases, the maximum oxygen uptake result will gradually increase. Under normal circumstances, if a user's maximum oxygen uptake base is handed over, then as the exercise increases, the maximum oxygen uptake value will slowly rise within a certain period of time (such as two months or three months). Based on this situation, the embodiment of the present application is based on historical data within a certain period of time, and the maximum oxygen uptake result obtained this time is smoothed, suppressed and trended.

[0270] In some embodiments, the process of smoothing suppression and trend judgment may include: firstly, performing linear interpolation based on the maximum oxygen uptake result obtained this time and the historical maximum oxygen uptake results within a certain period of time, so as to obtain the maximum oxygen uptake result data corresponding to each day within the certain period of time; then, performing single exponential smoothing calculation based on the linear interpolation result, and obtaining the result S of the single exponential smoothing calculation t1 ; Then, based on the result of single exponential smoothing calculation S t1 Perform double exponential smoothing calculation and obtain the result S of the double exponential smoothing calculation t2 The result of the double exponential smoothing calculation S t2 This is the final model output value.

[0271] It should be noted that the single exponential smoothing method is applicable to the case where the sequence value is a constant, the mean fluctuates randomly above and below, and there is no trend or seasonal factor. The corresponding calculation formula can be found in formula (1-5):

[0272] S t1 =αY t +(1-α)S t-1 (1-5)

[0273] Among them, S t1 is the smoothed value at time t; Y t is the actual value at time t; S t-1 is the smoothing value at time t-1; α is the smoothing constant, which is between 0 and 1.

[0274] Double exponential smoothing is to perform single exponential smoothing twice (using the same parameters), which is suitable for sequences with linear trends and performs secondary smoothing on the single exponential smoothing model. The corresponding calculation formulas can be found in formulas (1-6) and (1-7):

[0275]

[0276]

[0277] Among them, S t (1) is the smoothed value at time t; Y t is the actual value at time t; is the smoothing value at time t-1; α is the smoothing constant, between 0 and 1; S t (2) is the quadratic smoothing value at time t; is the quadratic smoothing value at time t-1.

[0278] It should be understood that after smoothing suppression and trend judgment processing, the change trend between the current data and the historical maximum oxygen uptake results can be made to change slowly rather than abruptly, thereby making the change trend of the maximum oxygen uptake more in line with reality.

[0279] The specific implementation methods of smoothing suppression and trend judgment and the algorithms involved will be introduced below and will not be described in detail here.

[0280] S713, determine whether the value is successfully output.

[0281] In some embodiments, if the value is successfully obtained (that is, the judgment result of this step is "yes"), step S714 can be executed next; if the value is not successfully obtained (that is, the judgment result of this step is "no"), the process can be directly terminated next.

[0282] S714, storing the maximum oxygen uptake result data, updating the data to the App, and displaying the data through the App.

[0283] In some embodiments, the App here may refer to an App in an electronic device such as a mobile phone that is bound to a smart watch; the data here may refer to the maximum oxygen uptake result obtained this time.

[0284] In some embodiments, the method of updating data to the App may include, for example, the smartwatch stores the user account information and the maximum oxygen uptake result data locally on the smartwatch; each time the smartwatch is turned on or connected to the mobile phone, it can first determine whether the sports app currently running on the smartwatch and the mobile phone is the account of the same person; if so, the data of the sports app in the mobile phone is updated, wherein the maximum oxygen uptake results of the local smartwatch are stored in units of days, and when the data in the mobile phone is updated, it can be compared day by day, and the data that is not available on the mobile phone on some days can be supplemented. If the smartwatch and the mobile phone both have maximum oxygen uptake data on the same day, and the data of the two are different, then the larger value can be taken and recorded uniformly in the mobile phone and the smartwatch.

[0285] Among them, the specific process of updating the mobile phone side data will be introduced below and will not be described in detail here.

[0286] According to the method of motion monitoring provided by the embodiment of the present application, valid data of the user in a stable state of motion is obtained through analysis of heart rate, speed, etc., and stored in a buffer; then, slope analysis and regression factor analysis are performed on the data in the buffer to filter the data to obtain a more accurate heart rate-speed pair associated with the maximum oxygen uptake; then, trend analysis is performed on the current results based on historical results to make the trend of the maximum oxygen uptake more realistic, and finally the output result of the maximum oxygen uptake is obtained. This method obtains accurate input data by performing multiple screening and filtering on the data in a stable motion state, and after preliminarily obtaining the maximum oxygen uptake result, multiple processing is performed on the maximum oxygen uptake result, thereby effectively improving the accuracy of obtaining the maximum oxygen uptake result.

[0287] For example, Fig.15 FIG. 1 is a schematic flow chart of motion state analysis during implementation of a motion information monitoring method provided in an embodiment of the present application. The process may include the following steps:

[0288] S1501, after the exercise starts, obtain the user's basic information, sensor information, heart rate, speed, etc.

[0289] S1502, determining whether the user's current exercise time reaches a preset duration, and whether the point selection window satisfies a first duration.

[0290] In some embodiments, if the user's current exercise time does not reach the preset duration, or the point selection window does not meet the first duration (that is, the judgment result of this step is "no"), then step S1501 can be re-executed. If the user's current exercise time reaches the preset duration, and the point selection window meets the first duration (that is, the judgment result of this step is "yes"), then steps S1503 to S1506 and steps S1507 to S1512 can be executed.

[0291] First, the process corresponding to step S1503 to step S1506 is introduced:

[0292] S1503, extract IMU data features.

[0293] S1504, AR state identifies movement type.

[0294] In some embodiments, AR state recognition supports walking, running, cycling, elliptical machine, rowing machine, mountain climbing and other sports type recognition (or scene recognition). The principle of AR state recognition can be found in the above introduction and will not be repeated here.

[0295] S1505, counting the types of movement within the time window.

[0296] The method of counting the types of motion within the time window can be found in the introduction of S704 above, which will not be described again here.

[0297] S1506, output the current main motion type.

[0298] Next, the process corresponding to step S1507 to step S1510, and step S1507, step S1511 to step S1510 is introduced:

[0299] S1507, determining whether the speed variance in the point selection window is less than T1, and whether the maximum and minimum speed values ​​do not exceed T2.

[0300] In some embodiments, if the speed variance in the point selection window is less than T1, and the maximum and minimum speed values ​​do not exceed T2 (that is, the judgment result of this step is "yes"), then step S1508 can be re-executed. If the speed variance in the point selection window is equal to or greater than T1, or the maximum and minimum speed values ​​are equal to or exceed T2 (that is, the judgment result of this step is "no"), then step S1511 can be executed next.

[0301] S1508, dividing the exercise intensity into intervals according to the maximum heart rate.

[0302] In some embodiments, different maximum heart rates may correspond to different exercise intensity intervals. Specifically, the exercise intensity intervals corresponding to different maximum heart rate ranges may be obtained according to the heart rate-exercise intensity standard scale provided by the American Medical Association. Exemplarily, the heart rate-exercise intensity standard scale may be as shown in Table 4 below:

[0303] Table 4

[0304] Exercise intensity Quiet Very low Low middle Higher high Very high VO2max / <37% 37-45% 46-63% 64-90% 91-120% >120% Maximum heart rate / <57% 57-63% 64-76% 77-95% >96% /

[0305] Among them, the value corresponding to the maximum oxygen uptake in the above table can be regarded as a percentage of the standard maximum oxygen uptake; the value corresponding to the maximum heart rate can be regarded as a percentage of the standard maximum heart rate.

[0306] In some embodiments, the maximum heart rate in the point selection window can be obtained based on the heart rate data in the point selection window, and then the exercise intensity type is determined based on the corresponding relationship shown in the above table.

[0307] S1509, output the exercise intensity interval.

[0308] S1510, output the motion status label of the current window.

[0309] The motion state label (or motion label, state label) can be obtained based on the motion type and motion intensity obtained by AR state recognition. For example, if the motion type is running and the motion intensity is high, the motion state label can be output as running with high intensity; for another example, if the motion type is walking and the motion intensity is medium, the motion state label can be output as walking with medium intensity.

[0310] S1511, determine whether the difference between the average heart rate and speed in the second half of the point selection window and the average heart rate and speed in the first half is greater than T3.

[0311] In some embodiments, if the difference between the mean heart rate and speed of the second half of the point selection window and the mean heart rate and speed of the first half is greater than T3 (that is, the judgment result of this step is "yes"), then step S1512 can be re-executed next, that is, the movement rising period (or movement rising state) is output. If the difference between the mean heart rate and speed of the second half of the point selection window and the mean heart rate and speed of the first half is equal to or less than T3 (that is, the judgment result of this step is "no"), then step S1513 can be executed next, that is, the movement falling period (or movement falling state) is output.

[0312] According to the method for monitoring motion information provided in the embodiment of the present application, the user's motion type is obtained based on the user's basic information and motion data according to AR state recognition and statistics, and the exercise intensity is obtained based on the maximum heart rate and its correspondence with the exercise intensity. The corresponding exercise state label of the user within the selected point time window can be accurately obtained, so that valid data can be subsequently screened based on the exercise state label.

[0313] For example, Fig.16 FIG. 1 is a schematic flow chart of data point selection and data fusion in the implementation process of a method for motion information monitoring provided by an embodiment of the present application. The process may include the following steps:

[0314] S1601, output data dictionary buffer.

[0315] Among them, the data dictionary can correspond to valid data points in the buffer.

[0316] S1602, determine whether the dictionary length is 0.

[0317] The dictionary length here may correspond to the number of valid data points in the buffer.

[0318] In some embodiments, when the dictionary length is 0 (that is, the judgment result of this step is "yes"), the process can then proceed to step S1624, i.e., end the session and return a failure code; when the dictionary length is not 0 (that is, the judgment result of this step is "no"), the process can then proceed to step S1603.

[0319] S1603, determine whether the dictionary length is 1.

[0320] In some embodiments, when the dictionary length is 1 (ie, the judgment result of this step is "yes"), step S1604 may be performed next:

[0321] S1604, regression model prediction.

[0322] S1605, output result y1.

[0323] In some embodiments, when the dictionary length is not 1 (ie, the judgment result of this step is "No"), the process may proceed to step S1606:

[0324] S1606, determine whether the dictionary length is 2.

[0325] In some embodiments, when the dictionary length is 2 (ie, the judgment result of this step is "yes"), step S1607 may be performed next:

[0326] S1607, regression model prediction.

[0327] S1608, determine whether the difference between the two output values ​​is less than Tv.

[0328] In some embodiments, if the difference between the two output values ​​is less than Tv (ie, the judgment result of this step is "yes"), then step S1609 and step S1610 may be performed:

[0329] S1609, calculate the average of the two output values.

[0330] S1610, output result y2.

[0331] In some embodiments, if the difference between the two output values ​​in step S1608 is not less than Tv (ie, the judgment result of step S1608 is "no"), then steps S1611 and S1612 may be performed next:

[0332] S1611, determine whether there is a historical maximum oxygen uptake.

[0333] In some embodiments, if there is a historical maximum oxygen uptake (that is, the judgment result of this step is "yes"), then step S1612 can be executed next, that is, the previous historical maximum oxygen uptake is output. If there is no historical maximum oxygen uptake (that is, the judgment result of this step is "no"), then step S1624 can be executed next, that is, the session is terminated and a failure code is returned.

[0334] In some embodiments, when the dictionary length is not 2 (ie, the judgment result of step S1606 is "No"), step S1613 may be performed next:

[0335] S1613, determine whether the dictionary length is greater than 2.

[0336] Since the judgments in step S1602, step S1603 and step S1606 have been performed before, the judgment result of this step is "yes", that is, step S1614 can be executed next.

[0337] S1614, calculate the regression coefficient k of all data points.

[0338] S1615, remove outliers using residual analysis.

[0339] S1616, regression model prediction. S1617, obtaining regression model.

[0340] It should be noted that when the number of valid data points of this exercise stored in the buffer is 3 or more, the speed and / or heart rate corresponding to each valid data point can be used for linear fitting, and then the outliers can be obtained by residual analysis, and the outliers (valid data points that can be regarded as abnormal) can be filtered. For example, assuming that there are 6 valid data points in the buffer (these 6 valid data points have been filtered once according to the exercise status label), and the specific data corresponding to the 6 valid data points are shown in Table 3 above; the speed and heart rate of these 6 valid data points are used for linear fitting, and the results are as follows Fig.14 As shown; then, residual analysis can be used to obtain outliers, which are far from the standard linear straight line (such as Fig.14 The first point in is the outlier point); then, the data corresponding to the outlier point can be deleted.

[0341] In some embodiments, after deleting the outlier, the remaining valid data points can be weighted according to the duration corresponding to each valid data point. For example, as shown in Table 5 below, there are 5 valid data points remaining after deleting the outlier (that is, the valid data point with sequence number 6 in Table 3 above is deleted as an outlier); the durations corresponding to the 5 valid data points are: 60s, 60s, 75s, 70s, 30s; assuming that the duration variable is recorded as ci , the total duration is recorded as c all , then the maximum oxygen uptake weight coefficient of the valid data points corresponding to different serial numbers can be obtained by the following formula (1-8):

[0342] ω i =c i / c all (1-8)

[0343] The total duration may be the sum of the durations of each valid data point.

[0344] Table 5

[0345] Serial number Speed ​​(km / h) Heart rate Duration(s) Sports Tags 1 6 120 60 Walking moderate intensity 2 7 130 60 Moderate intensity running 3 8 145 75 Moderate intensity running 4 8.5 152 70 High intensity running 5 9 160 30 High intensity running

[0346] S1618, output result y3.

[0347] S1619, enter the single result weighted fusion process. The specific implementation of the decision fusion process includes step S1620.

[0348] It should be noted that step S1619 is an optional step, which is only used to indicate entering step S1620.

[0349] S1620, perform linear interpolation on the historical data on a daily basis.

[0350] In some embodiments, since the user may not exercise every day, the data may be discontinuous in the time dimension. For example, if the data is processed in units of days, there may not be corresponding valid point data for every day. Therefore, if the valid data is processed in units of days, the historical data can be linearly interpolated according to the day to obtain the historical valid data points corresponding to the day (such as the date of each day).

[0351] S1621, calculate the single exponential smoothing result St1.

[0352] S1622, calculate the double exponential smoothing result St2.

[0353] S1623, output results.

[0354] Among them, the specific implementation method of step S1621 and step S1622 can refer to the specific introduction in S712 above, and will not be repeated here.

[0355] S1624, end the session and return a failure code.

[0356] According to the method of motion monitoring provided by the embodiment of the present application, valid data of the user in a stable state of motion is obtained through analysis of heart rate, speed, etc., and stored in a buffer; then, slope analysis and regression factor analysis are performed on the data in the buffer to filter the data to obtain a more accurate heart rate-speed pair associated with the maximum oxygen uptake; then, trend analysis is performed on the current results based on historical results to make the trend of the maximum oxygen uptake more realistic, and finally the output result of the maximum oxygen uptake is obtained. This method obtains accurate input data by performing multiple screening and filtering on the data in a stable motion state, and after preliminarily obtaining the maximum oxygen uptake result, multiple processing is performed on the maximum oxygen uptake result, thereby effectively improving the accuracy of obtaining the maximum oxygen uptake result.

[0357] For example, Fig.17 As shown, it is a schematic flow chart of updating data on the mobile phone side App during the implementation of a method for monitoring sports information provided by an embodiment of the present application. The process may include the following steps:

[0358] S1701, Bluetooth pairing between smart watch and mobile phone.

[0359] S1702, the mobile phone sends App data to the smart watch.

[0360] Among them, App data may include App user account information, such as user name, App login ID, App login password, etc.

[0361] S1703, the smart watch obtains a local user account.

[0362] In some embodiments, the local user account may include: user name, App login ID, App login password, etc.

[0363] S1704, determining whether the user account on the mobile phone is consistent with the local user account on the smart watch.

[0364] In some embodiments, the smart watch can determine that the sports app account logged in on the smart watch and the mobile phone is the same user based on the user account information sent by the mobile phone to the smart watch and the local user account of the smart watch.

[0365] In some embodiments, if the user account on the mobile phone side and the local user account on the smart watch are consistent (that is, the judgment result of this step is "yes"), step S1705 can be executed next; if the user account on the mobile phone side and the local user account on the smart watch are inconsistent (that is, the judgment result of this step is "no"), step S1710 can be executed next, that is, clearing and updating the local data of the smart watch.

[0366] S1705, the mobile phone side obtains historical data from the smart watch side.

[0367] S1706, determining whether the maximum oxygen uptake data on the mobile phone side is updated.

[0368] In some embodiments, if the maximum oxygen uptake data on the mobile phone side is inconsistent with the historical maximum oxygen uptake data of the local smart watch, it is determined that the maximum oxygen uptake data on the mobile phone side needs to be updated; if the maximum oxygen uptake data on the mobile phone side is consistent with the historical maximum oxygen uptake data of the local smart watch, it is determined that the maximum oxygen uptake data on the mobile phone side does not need to be updated.

[0369] As an example, assuming that the mobile phone has not obtained the latest historical data sent by the smart watch, the maximum oxygen uptake data corresponding to its App is shown in Table 6; at this time, the local historical data of the smart watch is shown in Table 7, where the mobile phone does not store the maximum oxygen uptake data of 2023 / 08 / 01, 2023 / 08 / 02 and 2023 / 08 / 07, while the local data of the smart watch includes the maximum oxygen uptake data corresponding to these dates. Therefore, when the mobile phone obtains the historical data sent by the smart watch, the missing data can be supplemented according to the historical data. Exemplarily, the updated data can be shown in Table 8 below:

[0370] Table 6

[0371] Time (in days) VO2max 2023 / 06 / 30 45.8 2023 / 07 / 05 45.92 2023 / 07 / 08 45.98 2023 / 07 / 10 46.12 / / 2023 / 07 / 16 46.45 2023 / 07 / 22 45.38 2023 / 07 / 30 45.1 / / / / / / 2023 / 08 / 10 46.2 2023 / 08 / 12 46.5 2023 / 08 / 13 46.4

[0372] Table 7

[0373] Time (in days) VO2max 2023 / 06 / 30 45.8 / / 2023 / 07 / 08 45.98 2023 / 07 / 10 46.12 2023 / 07 / 13 46.37 2023 / 07 / 16 46.45 / / 2023 / 07 / 30 45.1 2023 / 08 / 01 45.2 2023 / 08 / 02 45.35 2023 / 08 / 07 45.9 2023 / 08 / 10 46.2 2023 / 08 / 12 46.5 2023 / 08 / 13 46.4

[0374] Table 8

[0375] Time (in days) VO2max 2023 / 06 / 30 45.8 2023 / 07 / 05 45.92 2023 / 07 / 08 45.98 2023 / 07 / 10 46.12 2023 / 07 / 13 46.37 2023 / 07 / 16 46.45 2023 / 07 / 22 45.38 2023 / 07 / 30 45.1 2023 / 08 / 01 45.2 2023 / 08 / 02 45.35 2023 / 08 / 07 45.9 2023 / 08 / 10 46.2 2023 / 08 / 12 46.5 2023 / 08 / 13 46.4

[0376] In some embodiments, if the maximum oxygen uptake data on the mobile phone side is updated (that is, the judgment result of this step is "yes"), step S1711 can be executed next, that is, updating local data and uploading App storage; if the maximum oxygen uptake data on the mobile phone side is not updated (that is, the judgment result of this step is "no"), step S1707 can be executed next.

[0377] S1707, determine whether to start exercise.

[0378] In some embodiments, if exercise is turned on (that is, the judgment result of this step is "yes"), step S1708 can be executed next; if exercise is not turned on (that is, the judgment result of this step is "no"), step S1709 can be executed next, that is, updating the local data on the smart watch side and uploading it to the App storage.

[0379] S1708, determine whether there is a new maximum oxygen uptake output value.

[0380] In some embodiments, if there is a new maximum oxygen uptake output value (that is, the judgment result of this step is "yes"), step S1709 can be executed next, that is, updating the local data on the smart watch side and uploading it to the App storage; if there is no new maximum oxygen uptake output value (that is, the judgment result of this step is "no"), the process can be ended.

[0381] According to the method of motion monitoring provided by the embodiment of the present application, valid data of the user in a stable state of motion is obtained through analysis of heart rate, speed, etc., and stored in a buffer; then, slope analysis and regression factor analysis are performed on the data in the buffer to filter the data to obtain a more accurate heart rate-speed pair associated with the maximum oxygen uptake; then, trend analysis is performed on the current results based on historical results to make the trend of the maximum oxygen uptake more realistic, and finally the output result of the maximum oxygen uptake is obtained. This method obtains accurate input data by performing multiple screening and filtering on the data in a stable motion state, and after preliminarily obtaining the maximum oxygen uptake result, multiple processing is performed on the maximum oxygen uptake result, thereby effectively improving the accuracy of obtaining the maximum oxygen uptake result.

[0382] For example, Fig.18 FIG. 1 is a schematic flow chart of a method for monitoring motion information provided by an embodiment of the present application. The method may be performed by a smart watch, for example, and may specifically include the following steps:

[0383] S1801, obtaining the speed and heart rate corresponding to the user's exercise.

[0384] S1802: Determine, based on the speed and heart rate, whether the motion state corresponding to the user's motion satisfies a point selection condition.

[0385] S1803, obtaining valid data points, which include the speed, heart rate, exercise status label, and duration of the user corresponding to the point selection condition. The exercise status label is used to indicate the exercise type and exercise intensity corresponding to the user's exercise.

[0386] S1804: Filter valid data points according to the motion state tags to obtain a first data point.

[0387] S1805 , linearly fitting the speed and heart rate corresponding to the first data points, and performing secondary filtering on the outliers according to residual analysis to obtain second data points.

[0388] S1806: Obtain a first result corresponding to the user's maximum exercise oxygen uptake according to the second data point.

[0389] S1807, performing linear interpolation on the first result according to the historical maximum oxygen uptake result, and performing single exponential smoothing and double exponential smoothing on the linear interpolation to obtain a second result corresponding to the user's maximum exercise oxygen uptake.

[0390] In some embodiments, the method further includes: obtaining the exercise type corresponding to the user's exercise based on the speed and heart rate; and obtaining the exercise intensity corresponding to the user's exercise based on the heart rate; and obtaining the exercise state label based on the exercise type and the exercise intensity.

[0391] In some embodiments, filtering the valid data points once according to the motion state label to obtain the first data point specifically includes: deleting the valid data points whose motion state label is the first motion state label, and the first motion state label is used to indicate that the speed does not reach the first pace; or, the speed variance corresponding to the motion state is equal to or greater than a first preset value; or, the difference between the maximum speed and the minimum speed corresponding to the motion state is equal to or greater than a second preset value; or, when the speed is fixed, the heart rate change value is equal to or greater than a third preset value.

[0392] In some embodiments, the method further includes: obtaining the number of the first data points; when the number of the first data points is 0, obtaining historical data corresponding to the maximum oxygen uptake; and displaying the historical data corresponding to the maximum oxygen uptake of the previous exercise corresponding to the current user exercise.

[0393] In some embodiments, the method also includes: obtaining the number of the first data points; when the number of the first data points is 2, obtaining a third result of the maximum oxygen uptake and a fourth result of the maximum oxygen uptake corresponding to the first data points respectively; when the difference between the third result and the fourth result is greater than a third preset value, obtaining historical data corresponding to the maximum oxygen uptake; and displaying the historical data corresponding to the maximum oxygen uptake of the previous exercise corresponding to the current user exercise.

[0394] In some embodiments, the method further includes: when the difference between the third result and the fourth result is equal to or less than the third preset value, calculating the average value of the third result and the fourth result; and displaying the average value of the third result and the fourth result.

[0395] In some embodiments, the method further includes: obtaining the number of the first data points; when the number of the first data points is greater than 2, performing linear fitting on the speed and heart rate corresponding to the first data points respectively, and performing secondary filtering on the outliers based on residual analysis to obtain second data points.

[0396] In some embodiments, the method further includes: inputting the second data point into a regression model corresponding to the maximum oxygen uptake, wherein the regression model includes a mapping relationship between the speed and heart rate corresponding to the user's exercise and the maximum oxygen uptake result.

[0397] In some embodiments, the method further includes: determining whether the duration of the user's exercise reaches a first preset time;

[0398] If the preset time is reached, determine whether the point selection window corresponding to the speed and heart rate reaches a second preset time, and the point selection window is a time unit for selecting the valid data point; if the point selection window reaches the second preset time, obtain the valid data point.

[0399] In some embodiments, the method further includes: establishing Bluetooth pairing with a second electronic device, the first electronic device and the second electronic device respectively storing the maximum oxygen uptake history data corresponding to the user; sending the local maximum oxygen uptake history data of the first electronic device to the second electronic device, so that when the maximum oxygen uptake history data stored in the first electronic device is inconsistent with the maximum oxygen uptake history data stored in the second electronic device, the second electronic device updates the maximum oxygen uptake history data according to the local maximum oxygen uptake history data of the first electronic device.

[0400] In some embodiments, the method further includes: receiving user information sent by the second electronic device; judging, based on the user information, whether a second user account corresponding to the second electronic device is consistent with a first user account corresponding to the first electronic device, wherein the first user account and the second user account are both accounts associated with an application for obtaining maximum oxygen uptake; when the first user account is consistent with the second user account, sending the local maximum oxygen uptake history data of the first electronic device to the second electronic device.

[0401] According to the method of motion monitoring provided by the embodiment of the present application, valid data of the user in a stable state of motion is obtained through analysis of heart rate, speed, etc., and stored in a buffer; then, slope analysis and regression factor analysis are performed on the data in the buffer to filter the data to obtain a more accurate heart rate-speed pair associated with the maximum oxygen uptake; then, trend analysis is performed on the current results based on historical results to make the trend of the maximum oxygen uptake more realistic, and finally the output result of the maximum oxygen uptake is obtained. This method obtains accurate input data by performing multiple screening and filtering on the data in a stable motion state, and after preliminarily obtaining the maximum oxygen uptake result, multiple processing is performed on the maximum oxygen uptake result, thereby effectively improving the accuracy of obtaining the maximum oxygen uptake result.

[0402] Based on the same technical concept, an embodiment of the present application also provides an electronic device, including one or more processors; one or more memories; the one or more memories store one or more computer programs, and the one or more computer programs include instructions. When the instructions are executed by the one or more processors, the computer or processor executes one or more steps in any of the above methods.

[0403] Based on the same technical concept, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable program instructions. When the computer-executable program instructions are executed on a computer, the computer or processor executes one or more steps in any of the above methods.

[0404] Based on the same technical concept, an embodiment of the present application also provides a computer program product comprising instructions, wherein the computer program product includes computer program code. When the computer program code runs on a computer, the computer or processor executes one or more steps in any of the above methods.

[0405] 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 program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0406] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0407] The above is only a specific implementation of the embodiment of the present application, but the protection scope of the embodiment of the present application is not limited thereto, and any changes or replacements within the technical scope disclosed in the embodiment of the present application should be included in the protection scope of the embodiment of the present application. Therefore, the protection scope of the embodiment of the present application should be based on the protection scope of the claims.

Claims

1. A method for monitoring motion information, characterized in that: Applicable to a first electronic device, comprising: Get the speed and heart rate of the user's exercise; Determining, according to the speed and heart rate, that the motion state corresponding to the user's motion meets a point selection condition; Acquire valid data points, wherein the valid data points include the speed, heart rate, exercise state label, and duration of the user corresponding to the point selection condition, wherein the exercise state label is used to indicate the exercise type and exercise intensity corresponding to the user's exercise; Filter the valid data points once according to the motion state label to obtain a first data point; Performing linear fitting on the speed and heart rate corresponding to the first data points respectively, and performing secondary filtering on the outliers according to residual analysis to obtain second data points; Obtaining a first result corresponding to the user's maximum exercise oxygen uptake according to the second data point; Linear interpolation is performed on the first result according to the historical maximum oxygen uptake result, and single exponential smoothing and double exponential smoothing are performed on the linear interpolation to obtain a second result corresponding to the maximum oxygen uptake of the user during exercise.

2. The method according to claim 1, characterized in that The method further comprises: Acquire the exercise type corresponding to the user's exercise according to the speed and heart rate; and Acquire the exercise intensity corresponding to the user's exercise according to the heart rate; The exercise state label is acquired according to the exercise type and the exercise intensity.

3. The method according to claim 1, characterized in that The filtering the valid data points once according to the motion state tag to obtain the first data point specifically includes: Delete the valid data points whose motion state label is the first motion state label, where the first motion state label is used to indicate that the speed does not reach the first pace; or, the speed variance corresponding to the motion state is equal to or greater than a first preset value; or, the difference between the maximum speed and the minimum speed corresponding to the motion state is equal to or greater than a second preset value; or, when the speed is fixed, the heart rate change value is equal to or greater than a third preset value.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Obtaining the number of the first data points; When the number of the first data points is 0, obtaining historical data corresponding to the maximum oxygen uptake; Display the historical data corresponding to the maximum oxygen uptake of the previous exercise corresponding to the current user exercise.

5. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtaining the number of the first data points; When the number of the first data points is 2, obtaining a third result of the maximum oxygen uptake and a fourth result of the maximum oxygen uptake respectively corresponding to the first data points; When the difference between the third result and the fourth result is greater than a third preset value, obtaining historical data corresponding to the maximum oxygen uptake; Display the historical data corresponding to the maximum oxygen uptake of the previous exercise corresponding to the current user exercise.

6. The method according to claim 5, characterized in that The method further comprises: When the difference between the third result and the fourth result is equal to or less than the third preset value, calculating an average value of the third result and the fourth result; An average of the third result and the fourth result is displayed.

7. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Obtaining the number of the first data points; When the number of the first data points is greater than 2, linear fitting is performed on the speeds and heart rates respectively corresponding to the first data points, and outliers are filtered twice according to residual analysis to obtain second data points.

8. The method according to claim 7, characterized in that The method further comprises: The second data point is input into a regression model corresponding to the maximum oxygen uptake, where the regression model includes a mapping relationship between the speed and heart rate corresponding to the user's exercise and the maximum oxygen uptake result.

9. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Determining whether the duration of the user's exercise reaches a first preset time; If the preset time is reached, determining whether the point selection window corresponding to the speed and heart rate reaches a second preset time, the point selection window being a time unit for selecting the valid data point; If the point selection window reaches a second preset time, the valid data point is obtained.

10. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Establishing Bluetooth pairing with a second electronic device, wherein the first electronic device and the second electronic device respectively store historical data of maximum oxygen uptake corresponding to the user; The local maximum oxygen uptake history data of the first electronic device is sent to the second electronic device, so that when the maximum oxygen uptake history data stored in the first electronic device is inconsistent with that stored in the second electronic device, the second electronic device updates the maximum oxygen uptake history data according to the local maximum oxygen uptake history data of the first electronic device.

11. The method according to claim 10, characterized in that The method further comprises: receiving user information sent by the second electronic device; determining, according to the user information, whether a second user account corresponding to the second electronic device is consistent with a first user account corresponding to the first electronic device, wherein both the first user account and the second user account are accounts associated with an application for obtaining maximum oxygen uptake; When the first user account is consistent with the second user account, the local maximum oxygen uptake history data of the first electronic device is sent to the second electronic device.

12. An electronic device, characterized in that: include: one or more processors; one or more memories; The one or more memories store one or more computer programs, and the one or more computer programs include instructions, which, when executed by the one or more processors, enable the electronic device to perform the method as claimed in any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable program instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 11.

Citation Information

Patent Citations

  • Data processing method, wearable equipment and mobile terminal using same

    CN111078762A

  • Prediction method and device for improving cardio-pulmonary function effect through exercise and storage medium

    CN113284578A