Earphone control method, earphone and computer readable storage medium

Abstract

The invention discloses an earphone control method, an earphone and a computer readable storage medium. The earphone comprises a sensor module, and the control method of the earphone comprises the steps that motion behaviors of a user wearing the earphone in a preset time window are recognized, and each motion behavior corresponds to a preset behavior parameter calculation algorithm; on the basis of a behavior parameter calculation algorithm, according to detection data collected by the sensor module when the user executes the exercise line, behavior parameters corresponding to the exercise behaviors are obtained; and outputting the fatigue degree of the user wearing the earphone in the time window according to the behavior parameters corresponding to all the motion behaviors in the time window and a preset fatigue detection model.

Description

Technical Field

[0001] The present application relates to the technical field of earphones, and more specifically, to an earphone control method, an earphone, and a computer-readable storage medium. Background Art

[0002] As a new type of smart terminal, earphones will accompany users in many activities, such as exercise and rest, and can effectively record users' activity tracks and activity status information. However, current earphones cannot obtain the degree of human fatigue and have limited application scenarios. Summary of the invention

[0003] Embodiments of the present application provide a method for controlling an earphone, an earphone, and a computer-readable storage medium.

[0004] The earphones of the embodiment of the present application include a sensor module, and the control method of the earphones includes: identifying the movement behavior of a user wearing the earphones in a preset time window, each of the movement behaviors corresponding to a preset behavior parameter calculation algorithm; based on the behavior parameter calculation algorithm, obtaining the behavior parameters corresponding to the movement behavior according to the detection data collected by the sensor module when the user performs the movement behavior; outputting the fatigue level of the user wearing the earphones in the time window according to the behavior parameters corresponding to all the movement behaviors in the time window and a preset fatigue detection model.

[0005] In some embodiments, identifying the movement behavior of the user wearing the headset in the time window includes: identifying the movement behavior of the user wearing the headset in the time window based on detection data collected by the sensor module in the time window.

[0006] In some embodiments, the sensor module includes an accelerometer, and the detection data includes three-axis acceleration detected by the accelerometer.

[0007] In some embodiments, the sensor module includes a gyroscope, and the detection data includes three-axis angular velocity detected by the gyroscope.

[0008] In some embodiments, the headset further includes an instruction receiving module. The identifying the movement behavior of the user wearing the headset in the time window includes: determining the movement behavior of the user wearing the headset in the time window based on the movement behavior instruction received by the instruction receiving module.

[0009] In some embodiments, the headset further includes a control box assembly and a battery box assembly, wherein the control box assembly includes a control box, and the battery box assembly includes a battery box. The instruction receiving module includes an input module disposed on the control box or on the battery box, wherein the input module is used to input user instructions, and the input module includes at least one of a button and a touch screen.

[0010] In some embodiments, the headset further includes a control box assembly and a battery box assembly, the control box assembly includes a control box, and the battery box assembly includes a battery box. The headset further includes a communication module, the instruction receiving module includes the communication module disposed in the control box or the battery box, and the communication module is used to receive instructions sent by an external device, and the external device includes at least one of a mobile phone, a watch, a server, a computer, and a tablet computer.

[0011] In some embodiments, the control method further includes: analyzing the fatigue level in each of the time windows within a predetermined period of time pushed forward from the time window to obtain a fatigue trend of the user wearing the headset within the predetermined period of time.

[0012] In certain embodiments, the time window comprises days and the predetermined period comprises years.

[0013] In some embodiments, the control method also includes: evaluating the fatigue condition of the user's body parts when performing the exercise behavior and / or the user's exercise ability when performing the exercise behavior based on the fatigue level in the time window and the behavior parameters corresponding to each of the exercise behaviors, so as to output a first evaluation result; and providing a first exercise recommendation in the next time window based on the first evaluation result and the fatigue trend in the predetermined period.

[0014] In some embodiments, the first exercise suggestion includes: at least one of the type of exercise behavior to be performed, the exercise duration of each exercise behavior, the exercise intensity, and the exercise interval.

[0015] In some embodiments, the control method also includes: evaluating the fatigue condition of the user's body parts when performing the exercise behavior and / or the user's exercise ability when performing the exercise behavior based on the fatigue trend within the predetermined period and the behavioral parameters corresponding to each of the exercise behaviors, so as to output a second evaluation result; and providing a second exercise recommendation within the next predetermined period based on the second evaluation result and the fatigue trend within the predetermined period.

[0016] In some embodiments, the second exercise suggestion includes at least one of the type of exercise behavior to be performed, the total exercise duration, and the intensity and duration distribution of each exercise behavior.

[0017] In some embodiments, the movement behavior includes at least one of swimming, cervical spine activity, jumping, cycling, running, skipping rope, skiing, and mountain climbing; the behavior parameter calculation algorithm includes at least one of a swimming algorithm, a cervical spine activity algorithm, a jumping algorithm, a cycling algorithm, a running algorithm, a skipping rope algorithm, a skiing algorithm, and a mountain climbing algorithm.

[0018] In certain embodiments, when the movement behavior includes swimming, the behavior parameter calculation algorithm includes a swimming algorithm, and the behavior parameters include at least one of swimming style, proportion of each swimming style, breathing frequency, freestyle breathing angle, freestyle maximum breathing angle, freestyle pitch angle, breaststroke breathing angle, breaststroke maximum breathing angle, breaststroke total gliding time and total duration.

[0019] In certain embodiments, when the movement behavior includes moving the cervical spine, the behavior parameter calculation algorithm includes a cervical spine mobility algorithm, and the behavior parameters include at least one of the head left rotation angle, head right rotation angle, head forward tilt angle, head backward angle, head left tilt angle and head right tilt angle.

[0020] In some embodiments, when the movement behavior includes bouncing, the behavior parameter calculation algorithm includes a bouncing algorithm, and the behavior parameter includes a bouncing height.

[0021] The present application also provides an earphone, the earphone comprising a sensor module and a control module. The sensor module is used to collect detection data. The control module is connected to the sensor module in communication and is used to execute the control method described in any one of the above embodiments.

[0022] In some embodiments, the earphones in the above embodiments are bone conduction earphones or air conduction earphones.

[0023] The present application also provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the control method described in any one of the above embodiments is implemented.

[0024] In the control method of the earphones, the earphones and the computer-readable storage medium provided by the present application, the control module of the earphones can identify the user's motion behavior when the user performs the motion behavior within a preset time window, and obtain the behavior parameters corresponding to the motion behavior based on the behavior parameter calculation algorithm corresponding to the motion behavior and the detection data collected by the sensor module, and obtain the fatigue level of the user wearing the earphones in the time window based on the behavior parameters corresponding to all motion behaviors in the time window and the preset fatigue detection model, so that the user can obtain data feedback (i.e., fatigue level) under the motion behavior.

[0025] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0027] Figure 1 It is a flowchart of the control method of the headset of the present application;

[0028] Figure 2 This is a schematic diagram of the algorithm of the headset control method of this application

[0029] Figure 3 is a three-dimensional schematic diagram of headphones according to certain embodiments of the present application;

[0030] Figure 4 is a schematic diagram of the structure of the interaction between the headset and the external device in some embodiments of the present application;

[0031] Figure 5 yes Figure 3 A three-dimensional schematic diagram of the structure of part of the middle earphone;

[0032] Figure 6 is a schematic diagram of the breathing angle of freestyle swimming in certain embodiments of the present application;

[0033] Figure 7 is a flowchart of a method for controlling headphones in other embodiments of the present application;

[0034] Figure 8 is a flowchart of a method for controlling headphones in other embodiments of the present application;

[0035] Fig. 9 is a flowchart of a method for controlling headphones in other embodiments of the present application;

[0036] Fig.10 is a flowchart of a method for controlling headphones in some implementation modes of the present application;

[0037] Fig.11 is a flowchart of a method for controlling headphones in some implementation modes of the present application;

[0038] Fig.12 It is a schematic diagram of the connection status of a computer-readable storage medium and a processor in certain embodiments of the present application.

[0039] Description of main component symbols:

[0040] Headphones 10;

[0041] Control module 11; sensor module 12; gyroscope 121; accelerometer 122; instruction receiving module 15;

[0042] Battery box 117; control box 119.

[0043] Processor 20;

[0044] Computer readable storage medium 200 ; program 202 . DETAILED DESCRIPTION

[0045] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of the present application, and cannot be understood as limiting the embodiments of the present application.

[0046] As a new type of smart terminal, earphones will accompany users in many activities, such as exercise and rest, and can effectively record the user's activity trajectory and activity status information. However, current earphones cannot obtain the degree of fatigue of the human body, and the application scenarios are limited. In order to solve this problem, the present application provides an earphone 10 (such as Figures 3 to 5 as shown), earphone control method (as shown Figure 1 , Figure 2 , Figures 6 to 11 As shown), and a computer readable storage medium (such as Fig.12 shown).

[0047] See also Figures 1 to 6 , the headset control method of the embodiment of the present application includes:

[0048] 02: Identify the movement behavior of the user wearing the headset 10 in a preset time window, and each movement behavior corresponds to a preset behavior parameter calculation algorithm;

[0049] 03: Based on the behavior parameter calculation algorithm, according to the detection data collected by the sensor module 12 when the user performs the exercise, the behavior parameter corresponding to the exercise behavior is obtained; and

[0050] 04: Output the fatigue level of the user wearing the headset 10 in the time window according to the behavior parameters corresponding to all the movement behaviors in the time window and the preset fatigue detection model.

[0051] The control method of the above-mentioned earphone 10 can be applied to the earphone 10. The earphone 10 of the embodiment of the present application includes a sensor module 12 and a control module 11. The sensor module 12 is used to collect detection data, and the control module 11 is used to: identify the movement behavior of a user wearing the earphone 10 in a preset time window, each movement behavior corresponds to a preset behavior parameter calculation algorithm; based on the behavior parameter calculation algorithm, according to the detection data collected by the sensor module 12 when the user performs the movement, obtain the behavior parameters corresponding to the movement behavior; according to the behavior parameters corresponding to all the movement behaviors in the time window and the preset fatigue detection model, output the fatigue level of the user wearing the earphone 10 in the time window.

[0052] Specifically, the earphone 10 is an audio device, which is mainly used for sound-to-electric conversion, such as converting audio signals into sound, so that users can hear music, movies, games or other audio content, or converting sound into electrical signals. The design of the earphone 10 is intended to provide a private listening environment, so that users can enjoy the audio content alone without affecting the people around them. The earphone 10 can be worn on the user's ear and can be used in conjunction with devices such as mobile phones, computers, smart wearable devices (such as smart watches, smart bracelets, smart glasses and smart helmets, etc.), head-mounted display devices and virtual reality devices. In some embodiments, the earphone 10 includes air conduction earphones and bone conduction earphones. Air conduction earphones, that is, air conduction earphones, are earphones that transmit sound through air vibrations. Bone conduction earphones, that is, bone conduction earphones, are earphones that convert sound into different mechanical vibrations and transmit sound waves through the human skull, bony labyrinth, inner ear lymph, spiral organ, auditory center, etc. Air conduction earphones and bone conduction earphones can be applied to scenes, increasing the applicability of the earphone 10.

[0053] The earphone 10 includes a battery box assembly for placing batteries and / or a control box assembly with a control function. The control box assembly includes a control box 119, and the battery box assembly includes a battery box 117. The control box 119 can be used to control the power on and off of the earphone 10 and adjust the volume of the earphone 10, and the battery box 117 is used to load batteries, and the batteries are used to power the earphone 10 so that the earphone 10 can work normally.

[0054] The earphone 10 also includes a to-be-connected part 13, which includes an ear hook 137 and / or a back hook 139. When the user wears the earphone 10, the back hook 139 of the earphone 10 is worn on the head, and the ear hook 137 of the earphone 10 is worn on the back of the ear, thereby improving the wearing stability of the earphone 10, and the earphone 10 is not easy to fall off when the user is outdoors or exercising. The back hook 139 is used to connect the battery box 117 and the control box 119. The earphone 10 also includes a transducer component 30, and the ear hook 137 is used to connect the battery box 117 and the transducer component 30, and to connect the control box 119 and the transducer component 30. The transducer component 30 is used to fit with the skin of the human body. When the earphone 10 is in use, the transducer component 30 can vibrate mechanically to enable the user to hear the sound.

[0055] More specifically, see Figure 3 The earphone 10 also includes a control module 11, a sensor module 12 and a command receiving module 15.

[0056] The control module 11 is a module inside the earphone 10 that is responsible for processing various data and coordinating various functions (including but not limited to audio processing, connecting devices, power management, user interaction, etc.). The control module 11 is in communication connection with the sensor module 12. Among them, the control module 11 and the sensor module 12 can form a wired communication connection through a data line, or a wireless communication connection through a wireless signal. The control module 11 obtains the detection data collected by the sensor module 12 in a manner that the control module 11 directly reads the detection data collected by the sensor module 12; the control module 11 periodically sends a request to poll the sensor module 12 to obtain the latest detection data; or the sensor module 12 and the control module 11 are wirelessly connected, and the control module 11 obtains the detection data collected by the sensor module 12 through a wireless communication protocol.

[0057] The sensor module 12 is a module for collecting detection data. The sensor module 12 can monitor and collect signals of the user in the process of wearing the headset 10 in real time, and transmit the detection data formed by the signal to the control module 11. The sensor module 12 includes but is not limited to one or more of an inertial measurement unit (IMU), a pressure sensor, an electrocardiogram sensor, an electrocardiogram sensor, and a temperature sensor. The detection data includes but is not limited to one or more of three-axis acceleration, three-axis angular acceleration, pressure, heart rate, and temperature. The detection data collected by the sensor module 12 can be relevant data of the human body (such as heart rate) or relevant data of the external environment (such as ambient temperature). The headset 10 of the present application includes at least one sensor module 12. In an embodiment in which the headset 10 includes multiple sensor modules 12, the types of detection data collected by different sensor modules 12 can be the same or different. The detection data formed by the signal can characterize the current state of the user. The way in which the sensor module 12 collects detection data includes but is not limited to sampling at a constant sampling rate, sampling at a variable sampling rate, and sampling at a time window. In the present application, the sensor samples at a constant sampling rate. The constant sampling rate is simple and convenient, and can continuously collect detection data to achieve continuous monitoring, and it is not easy to miss state changes in the detection data.

[0058] See also Figure 5 In some embodiments, the sensor module 12 includes a gyroscope 121 , and the detection data includes three-axis angular velocity detected by the gyroscope 121 .

[0059] Specifically, the gyroscope 121 can measure the angular velocity of the wearing part (such as the user's head) in three spatial dimensions (X, Y, and Z axes), and the three-axis angular velocity includes the X-axis angular velocity, the Y-axis angular velocity, and the Z-axis angular velocity. The X-axis angular velocity represents the angular change of the head rotating around the X-axis, the Y-axis angular velocity represents the angular change of the head rotating around the Y-axis, and the Z-axis angular velocity represents the angular change of the head rotating around the Z-axis. Therefore, the three-axis angular velocity includes the angular velocity of three spatial dimensions. Compared with the single-axis angular velocity, the three-axis angular velocity can fully express the overall angular velocity of the head.

[0060] See also Figure 5 In some embodiments, the sensor module 12 includes an accelerometer 122 , and the detection data includes three-axis acceleration detected by the accelerometer 122 .

[0061] Specifically, the accelerometer 122 can collect and measure the acceleration of the head in three spatial dimensions (X, Y, and Z axes). That is, when the user wears headphones, the accelerometer can measure the three-axis acceleration of the wearing part (such as the user's head), and the three-axis acceleration includes X-axis acceleration, Y-axis acceleration, and Z-axis acceleration. The X-axis acceleration characterizes the change in the movement speed of the head along the X-axis direction, the Y-axis acceleration characterizes the change in the movement speed of the head along the Y-axis direction, and the Z-axis acceleration characterizes the change in the movement speed of the head along the Z-axis direction. Therefore, the three-axis acceleration includes accelerations in three spatial dimensions. Compared with the single-axis acceleration, the three-axis acceleration can fully express the overall acceleration of the head.

[0062] See also Figure 3 and Figure 4 The instruction receiving module 15 is used to receive instructions sent by an external device (such as Figure 3 As shown), the external device includes at least one of a mobile phone, a watch, a server, a computer and a tablet computer.

[0063] In some embodiments, the instruction receiving module 15 includes an input module (not shown) disposed on the control box 117 or the battery box 119, the input module is used to input user instructions, and the input module includes at least one of a button and a touch screen. The input module is used to input user instructions, and the user instructions at least include motion behavior instructions, so that the control module 11 can determine the current user's motion behavior based on whether the instruction receiving module 15 receives the motion behavior instruction.

[0064] In some embodiments, the headset 10 also includes a communication module (not shown), and the instruction receiving module 15 includes a communication module disposed in the control box 117 or the battery box 119. Specifically, the instruction receiving module 15 can receive instructions sent by an external device and can transmit the instructions to the control module 11.

[0065] In the method of 02, the user usually performs a series of sports behaviors while wearing the headset 10. In some embodiments, the sports behaviors include at least one of swimming, moving the cervical spine, bouncing, cycling, running, skipping, skiing, and mountain climbing.

[0066] The control module 11 can identify movement behaviors, and the control module 11 internally stores a preset behavior parameter calculation algorithm corresponding to each movement behavior, so as to match the detection data collected by the sensor module 12 with the behavior parameter calculation algorithm, thereby obtaining the behavior parameters corresponding to the movement behavior.

[0067] In some embodiments, the behavior parameter calculation algorithm includes at least one of a swimming algorithm, a cervical vertebrae activity algorithm, a bouncing algorithm, a cycling algorithm, a running algorithm, a rope skipping algorithm, a skiing algorithm, and a mountaineering algorithm. It is understandable that when the sports behavior includes swimming, the behavior parameter calculation algorithm includes the swimming algorithm; when the sports behavior includes bouncing, the behavior parameter calculation algorithm includes the bouncing algorithm, and the corresponding relationship between other sports behaviors and behavior parameter calculation algorithms is also the same, which will not be repeated here.

[0068] Among them, the preset time window is the time range for the control module 11 to obtain detection data once and identify the motion behavior. In the method of 03, the control module 11 can analyze the detection data (such as three-axis acceleration and three-axis angular velocity) collected by the sensor module 12 when the user performs the motion based on the preset behavior parameter calculation algorithm, and obtain the behavior parameters corresponding to the motion behavior (such as freestyle breathing angle) after processing and conversion of the detection data. The behavior parameters can characterize the performance and characteristics of the user in the motion behavior.

[0069] In this application, the sensor module 12 is an accelerometer 122 and a gyroscope 121. The detection data collected by the accelerometer 122 is a three-axis acceleration, and the detection data collected by the gyroscope 121 is a three-axis angular velocity. The implementation methods corresponding to the three movement behaviors of swimming, moving the cervical spine, and bouncing illustrate the process of the control module 11 obtaining the behavior parameters based on the behavior parameter calculation algorithm and the detection data.

[0070] For example, in some embodiments, when the movement behavior includes swimming, the behavior parameter calculation algorithm includes a swimming algorithm, and the behavior parameters include at least one of swimming style, proportion of each swimming style, breathing frequency, freestyle breathing angle, freestyle maximum breathing angle, freestyle pitch angle, breaststroke breathing angle, breaststroke maximum breathing angle, breaststroke total gliding time and total duration.

[0071] Among them, the freestyle breathing angle α (such as Figure 6 The pitch angle (as shown) refers to the relative position and direction of the head and the water surface when the head is above the water surface for breathing during freestyle swimming. Therefore, it is very important for the user to maintain the correct breathing angle during swimming to maintain body balance, improve swimming efficiency and avoid choking. The pitch angle usually refers to the angle change of the swimmer's body posture and head position underwater relative to the water surface. Therefore, it is very important for the user to maintain a good pitch angle during swimming to improve swimming efficiency, reduce resistance, maintain a correct breathing method and improve overall performance. Therefore, the swimming behavior parameters obtained by the control module 11 based on the detection data and the behavior parameter calculation algorithm can more intuitively characterize the user's motion characteristics and performance in swimming situations compared to the unprocessed detection data.

[0072] Take the freestyle breathing angle α as an example. The preset time window includes multiple groups of three-axis accelerations and three-axis angular velocities, each group of three-axis accelerations includes at least X-axis acceleration, Y-axis acceleration and Z-axis acceleration, and each group of three-axis angular velocities includes at least X-axis angular velocity, Y-axis angular velocity and Z-axis angular velocity. Multiple groups of three-axis accelerations and three-axis angular velocities at predetermined moments are fused separately to obtain fused acceleration values ​​and fused angular velocity values ​​at multiple predetermined moments. It can be understood that the fusion process includes filtering and denoising, and filtering includes but is not limited to Kalman filtering, Gaussian filtering and median filtering. Filtering can remove part of the noise in the three-axis acceleration and three-axis angular velocity, and improve the accuracy of the fused acceleration value and the fused angular velocity value.

[0073] In the swimming algorithm, there are multiple scheduled moments in the time window T, and the scheduled moment t1, the scheduled moment t2, the scheduled moment t3, ... the scheduled moment tn form a time series. The preset time window T includes the three-axis acceleration a1 (which is a set of X, Y, Z three-axis accelerations ax1, ay1 and az1) at the predetermined time t1, the three-axis acceleration a2 (which is a set of X, Y, Z three-axis accelerations ax2, ay2 and az2) at the predetermined time t2, the three-axis acceleration a3 (which is a set of X, Y, Z three-axis accelerations ax3, ay3 and az3) at the predetermined time t3... the three-axis acceleration an (which is a set of X, Y, Z three-axis accelerations axn, ayn and azn) at the predetermined time tn. After the three-axis accelerations are fused respectively, the three-axis acceleration a1 is fused to obtain the fused acceleration value A1 at the predetermined time t1, the three-axis acceleration a2 is fused to obtain the fused acceleration value A2 at the predetermined time t2, the three-axis acceleration a3 is fused to obtain the fused acceleration value A3 at the predetermined time t3... the three-axis acceleration an is fused to obtain the fused acceleration value An at the predetermined time tn. The fused acceleration value carries more information and can more accurately represent the current state of the head of the user wearing the headset 10 than the non-fused acceleration value. The fusion process also helps to eliminate occasional abnormal values ​​or instantaneous large fluctuations, making the method of 03 more resistant to interference and robust.

[0074] Similarly, within the preset time window T, the three-axis angular velocity ω1 at the predetermined time t1 (which is the set of X, Y, Z three-axis acceleration ωx1, ωy1 and ωz1), the three-axis angular velocity ω2 at the predetermined time t2 (which is the set of X, Y, Z three-axis acceleration ωx2, ωy2 and ωz2), the three-axis angular velocity ω3 at the predetermined time t3 (which is the set of X, Y, Z three-axis acceleration ωx3, ωy3 and ωz3)... The three-axis angular velocity ω at the predetermined time tm m (is the set of X, Y, Z three-axis acceleration ωxm, ωym and ωzm), after the three-axis angular velocity is fused respectively, the three-axis angular velocity ω1 is fused to obtain the fused angular velocity value Ω1 at the predetermined time t1, the three-axis angular velocity ω2 is fused to obtain the fused angular velocity value Ω2 at the predetermined time t2, the three-axis angular velocity ω3 is fused to obtain the fused angular velocity value Ω3 at the predetermined time t3... The three-axis angular velocity ωm is fused to obtain the fused angular velocity value Ωm at the predetermined time tm.

[0075] Further, the control module 11 performs complementary filtering fusion processing based on the fused angular velocity value Ωm and the fused acceleration value An, thereby obtaining quaternion data. The quaternion consists of a real part and three imaginary parts, and can be used to represent the mathematical concept of rotation and direction in three-dimensional space. The control module 11 can obtain the roll angle Roll by solving the quaternion data q. Then, the freestyle breathing angle α is determined according to the fused acceleration value An, the fused angular velocity value Ωm and the roll angle Roll.

[0076] Among them, the solution formula for the roll angle is:

[0077] Roll=atan2(2*q2*q3+2*q0*q1,-2*q1*q1-2*q2*q2);

[0078] In the above formula, quaternion data q = [q0, q1, q2, q3] T, Roll is the roll angle. After obtaining the roll angle Roll, the control module 11 obtains the peak maximum value and the trough average value of the fused acceleration value An and the fused angular velocity value Ωm; and within the first preset period, when the roll angle first rises and then falls, and the fused acceleration value An and the fused angular velocity value Ωm both have at least two peak maximum values ​​greater than the first preset peak threshold and at least two trough average values ​​less than the first preset trough threshold, the maximum roll angle within the first preset period is determined to be the freestyle breathing angle α. Among them, the first preset period is a signal detection period preset inside the earphone 10. Within the first preset period, when the roll angle first rises and then falls, and the fused acceleration value An and the fused angular velocity value Ωm both have at least two peak maximum values ​​greater than the first preset peak threshold and at least two trough average values ​​less than the first preset trough threshold, the control module 11 determines that the maximum roll angle within the first preset period is the freestyle breathing angle α.

[0079] For another example, in certain embodiments, when the movement behavior includes moving the cervical spine, the behavior parameter calculation algorithm includes a cervical spine mobility algorithm, and the behavior parameters include at least one of the head left rotation angle, head right rotation angle, head forward angle, head backward angle, head left tilt angle, and head right tilt angle.

[0080] The left rotation angle of the head, the right rotation angle of the head, the forward tilt angle of the head, the backward tilt angle of the head, the left tilt angle of the head and the right tilt angle of the head of the active cervical vertebra, as well as the freestyle breathing angle of swimming, are all posture angles. Therefore, the process of the control module 11 obtaining the fused acceleration value Aq and the fused angular velocity value Ωq of the behavioral parameters of the active cervical vertebra is consistent with the swimming algorithm and will not be repeated. The difference is that the freestyle breathing angle is obtained based on the solution formula of the roll angle, and the left rotation angle of the head, the right rotation angle of the head, the forward tilt angle of the head, the backward tilt angle of the head, the left tilt angle of the head and the right tilt angle of the head can be obtained based on their respective corresponding formulas.

[0081] For another example, in some embodiments, when the movement behavior includes bouncing, the behavior parameter calculation algorithm includes a bouncing algorithm, and the behavior parameter includes a bouncing height.

[0082] In the bouncing algorithm, in the time window T, the process of fusing multiple three-axis accelerations to obtain the fused acceleration value Ap is consistent with the process of obtaining the fused acceleration value An in the swimming algorithm, which is not repeated here. Further, the control module 11 extracts features of the fused acceleration value An, and the extracted features include the average slope of the fused acceleration value An, the maximum value of the fused acceleration value An, and the minimum value of the fused acceleration value An.

[0083] Specifically, the entire body movement process of the user performing the bounce can be divided into four parts, namely squatting, jumping, leaving the ground and landing. In this application, squatting, jumping and leaving the ground are divided into the current time window, and landing is divided into the next time window. In, since the user will drive the earphone 10 worn by the user to move downward during the squatting process, the fusion acceleration value An of the earphone 10 will change as the user squats, and the control module 11 performs squat detection on the user based on the maximum and minimum values ​​of the fusion acceleration value An in the current time window to output the squat detection result. Since the user will drive the earphone 10 worn by the user to move upward during the take-off process, the fusion acceleration value An of the earphone 10 will change as the user takes off, therefore, the control module 11 performs take-off detection on the user based on the maximum and minimum values ​​of the fusion acceleration value An in the current time window to output the take-off detection result. When the user is leaving the ground, the user will drive the headset 10 worn by the user to move upward, and the fused acceleration value An of the headset 10 will change as the user leaves the ground. At the same time, during the entire landing process, the average slope of the fused acceleration value An will also change. Therefore, the control module 11 performs a ground detection on the user based on the average slope of the fused acceleration value An in the current time window and the minimum value of the fused acceleration value An in the current time window to output the time of leaving the ground. When the user is landing, the user will drive the headset 10 worn by the user to move downward, and the fused acceleration value An of the headset 10 will change as the user lands. At the same time, during the entire landing process, the average slope of the fused acceleration value An will also change. Therefore, the control module 11 performs a landing detection on the user based on the average slope of the fused acceleration value An in the current time window, the maximum value and the minimum value of the fused acceleration value An in the next time window to output the landing time. Therefore, the control module 11 can obtain the air time according to the squat detection result, the take-off detection result, the ground departure time and the landing time. The flight time is the interval between the moment the user leaves the ground and the moment they land. The jumping height is obtained based on the flight time and gravity acceleration.

[0084] Thus, the control module 11 can determine the flying time of the user when performing the bounce according to the interval time between the moment when the user leaves the ground and the moment when the user lands. In the process of the user bouncing off the ground and landing, the user first makes his center of gravity leave the ground and moves upward to the highest point through inertia. The instantaneous speed of the user at the highest point in the air is zero. In this process, the user is only affected by the acceleration of gravity. After that, the user performs free fall under the influence of the acceleration of gravity until landing. Therefore, the rising time in the air is the same as the landing time, and the height of the free fall can be directly calculated according to the flying time and the acceleration of gravity. The height of the free fall is the jumping height.

[0085] In the method of 04, the fatigue detection model can determine the fatigue degree of the user wearing the headset 10 in the time window based on the behavior parameters corresponding to all the motion behaviors in the time window. More specifically, the fatigue detection model is a criterion for determining the fatigue degree pre-set in the control module 11. In some embodiments, the fatigue detection model can be a trained algorithm model.

[0086] For example, in the present application, the fatigue detection model is a trained machine learning model. The training database for fatigue detection model training is at least derived from historical data sets and standard sports behavior data. The historical data set is a data set formed by the detection data of different users collected by the sensor modules 12 of different headphones 10. It has a large amount of data, many data samples (i.e., users), and covers a wide range, which can improve the accuracy of the fatigue detection model and avoid model overfitting. The standard sports behavior data is derived from the reference standards of different sports behaviors, such as using the performance data of professional athletes as the reference standard. For example, in the sports behavior of swimming, different swimming styles correspond to different reference standards, and the reference standards include but are not limited to freestyle breathing angle, breaststroke breathing angle, breaststroke gliding time and breathing frequency. In the sports behavior of running, the reference standards include but are not limited to step frequency, stride, heart rate, oxygen consumption, etc. Therefore, the behavioral parameters corresponding to all sports behaviors in the time window can be compared with the reference standards to determine whether the behavioral parameters deviate from the reference standards. In addition, model training may also be combined with general physiological health standards and sports science research results, such as maximum heart rate, heart rate recovery time, post-exercise lactate threshold, etc., to provide a benchmark for evaluating the degree of fatigue for the model.

[0087] During the training process of the fatigue detection model based on the training database, the data of the training database will be preprocessed, such as filtering and normalization to reduce data noise. The data of the training database will then be extracted through feature information, and these feature information will be learned and pattern recognized using machine learning algorithms such as linear regression, support vector machine, random forest, gradient boosting decision tree or deep neural network, thereby constructing a fatigue detection model. During the training process, feature information of different fatigue levels will be labeled accordingly, such as mild fatigue, moderate fatigue and severe fatigue. These labeled feature information will be used to train the fatigue detection model so that it can output the fatigue level of the user wearing the headset 10 in the time window according to the behavioral parameters corresponding to all the motion behaviors in the input time window.

[0088] In addition, the fatigue detection model can also be personalized by considering individual differences of users, such as according to user instructions regarding the user's age, gender, height and weight received by the instruction receiving module 15, so that the results output by the fatigue detection model are more suitable for the user and more accurate.

[0089] In the earphones 10 and the control method of the earphones of the present application, the control module 11 of the earphones 10 can identify the user's motion behavior when the user performs motion behavior within a preset time window, and obtain the behavior parameters corresponding to the motion behavior based on the behavior parameter calculation algorithm corresponding to the motion behavior and the detection data collected by the sensor module 12, and obtain the fatigue level of the user wearing the earphones 10 in the time window based on the behavior parameters corresponding to all motion behaviors in the time window and the preset fatigue detection model, so that the user can obtain data feedback (i.e., fatigue level) under the motion behavior.

[0090] See also Figure 2 , Figure 3 and Figure 7 In certain embodiments, the method of 02 comprises:

[0091] 021: Based on the detection data collected by the sensor module 12 in the time window, identify the movement behavior of the user wearing the headset 10 in the time window.

[0092] The above-mentioned earphone control method can be applied to the earphone 10, and the control module 11 is also used to: identify the movement behavior of the user wearing the earphone 10 in the time window based on the detection data collected by the sensor module 12 in the time window.

[0093] Specifically, the control module 11 can include identifying motor behavior according to the detection data collected by the sensor module 12 in the time window. The mode of identification includes but is not limited to the mode of identification can be threshold determination, that is, the control module 11 sets a specific threshold, and when the detection data of the sensor module 12 exceeds or is lower than these thresholds, it is identified as a specific motor behavior; The mode of identification can be to use a machine learning algorithm, such as a classification algorithm, to train and identify the detection data to distinguish different motor behaviors. The mode of identification can be feature extraction, and the control module 11 is based on the frequency characteristics, time domain characteristics or time-frequency characteristics of the detection data, and if it meets the characteristics of the data of a certain specific motor behavior, the motor behavior is determined. The mode of identification can be to carry out time series analysis to the detection data, to identify the dynamic changes and duration of the motor behavior. The control module 11 identifies the motor behavior based on real-time detection data, and the accuracy is higher, which can better reflect the motor behavior of the user in the time window.

[0094] See also Figure 3 , Figure 4 and Figure 8 In some embodiments, the method of 02 further comprises:

[0095] 023: Based on the exercise behavior instruction received by the instruction receiving module 15, determine the exercise behavior of the user wearing the headset 10 in the time window.

[0096] The above-mentioned earphone control method can be applied to the earphone 10 , and the control module 11 is further used to determine the movement behavior of the user wearing the earphone 10 in the time window based on the movement behavior instruction received by the instruction receiving module 15 .

[0097] Specifically, the motion behavior instruction can come from other modules of the earphone 10, or from an external device. The external device includes at least one of a mobile phone, a watch, a server, a computer, and a tablet computer. For example, a user can turn on the riding mode through a button or a touch screen of a watch, and the watch sends the instruction to the instruction receiving module 15, so that the earphone 10 can identify the motion behavior. The control module 11 determines the motion behavior of the user wearing the earphone 10 in the time window through the motion behavior instruction efficiently and accurately, can improve the accuracy of motion behavior recognition, and does not need the control module 11 to make a judgment, can save the memory of the control module 11.

[0098] It is understandable that control module 11 can perform the method of 021 and the method of 023, that is, control module 11 can jointly carry out the determination of motor behavior by motor behavior instruction and detection data, increase the accuracy determined by motor behavior thus.That is, the determination of motor behavior can be adjusted by real-time feedback.For example, the motor behavior instruction that control module 11 receives based on instruction receiving module 15, after determining the motor behavior of the user, the user may interrupt or change the motor behavior in the time window.In this case, the motor behavior that control module 11 determines based on the detection data of sensor module 12 gathering in the time window may be inconsistent with the motor behavior determined based on the motor behavior instruction, at this moment, earphone 10 can send abnormal reminder (for example vibration prompt), remind the user to confirm the motor behavior of the user, whether consistent with the motor behavior of the user determined by the motor behavior instruction.Thus, the accuracy that control module 11 determines motor behavior can be improved.

[0099] In addition, improving the accuracy of the motor behavior determined by the control module 11 can improve the accuracy of the behavior parameters corresponding to the motor behavior.More specifically, the motor behavior instruction and the detection data jointly carry out the determination of the motor behavior, and the motor behavior corresponding to different time windows can be more accurately divided, thus, the detection data can be better classified, under different time windows, the detection data corresponding to the motor behavior, thereby reducing the noise of the behavior parameters obtained based on the detection data and the motor behavior.For example, after the user inputs the motor behavior instruction of riding, the user changes to running during riding, but the user does not re-enter the running motor behavior instruction.In this case, if the control module 11 continues to determine the motor behavior as riding, the detection data under this time window will be continuously identified as the detection data of the motor behavior of riding by the control module 11, contrary to the actual motor behavior of the user in running, causing the behavior parameters of the subsequent riding obtained to be larger deviations will be produced with normal values, causing the determination of the subsequent fatigue degree to be biased.Therefore, the control module 11 jointly carries out the determination of the motor behavior by the motor behavior instruction and the detection data, and can also improve the accuracy of the behavior parameters corresponding to the following motor behavior.

[0100] See also Figure 3 and Fig. 9 In some embodiments, the method for controlling the headset further includes:

[0101] 05: Analyze the fatigue level of each time window within a predetermined period pushed forward from the time window to obtain the fatigue trend of the user wearing the headset 10 within the predetermined period.

[0102] The above-mentioned earphone control method can be applied to the earphone 10, and the control module 11 is also used to: analyze the fatigue level of each time window within a predetermined period pushed forward from the time window to obtain the fatigue trend of the user wearing the earphone 10 within the predetermined period.

[0103] Specifically, the fatigue degree of each time window within the predetermined period pushed forward from the time window is analyzed, that is, the time window is a time window with a fixed length but rolling with time, and the control module 11 obtains the detection data collected by the sensor module 12 at a constant time interval. For example, the fixed length of the time window is 5 minutes, then the control module 11 takes the current moment as the center, and obtains the detection data collected by the sensor module 12 at the current moment, the detection data collected by the sensor module 12 2 minutes before the current moment, and the detection data collected by the sensor module 12 2 minutes after the current moment. At the next moment, the control module 11 takes the next moment as the center, and obtains the detection data collected by the sensor module 12 at the next moment, the detection data collected by the sensor module 12 2 minutes before the next moment, and the detection data collected by the sensor module 12 2 minutes after the next moment. Using the time window to collect detection data can reduce the interference of related data, improve the accuracy of the control module 11 in determining the current state of the head of the user wearing the headset 10, and can also reduce the calculation burden of the control module 11, avoid too much detection data, resulting in a heavy burden on the control module 11. The rolling time window can provide continuous and time-ordered detection data, which can more accurately determine the movement behavior. Thus, the control module 11 can analyze the fatigue degree of each time window. That is, the control module 11 can analyze the fatigue degree of different time windows under the user's exercise behavior within a certain period of time (i.e., a predetermined period), thereby characterizing the fatigue degree of the user at different stages of the exercise behavior.

[0104] Based on the fatigue levels of multiple time windows, the fatigue trend of the user in the interval where the multiple time windows are located (i.e., the predetermined period) can be reflected. That is, the multiple time windows have a certain time sequence, therefore, the fatigue levels of the multiple time windows occur according to the time series, and by analyzing the fatigue levels of the multiple time windows, the fatigue trend within the predetermined period can be obtained. The analysis of the time series within the predetermined period includes but is not limited to autoregressive models, moving average models, autoregressive moving average models, autoregressive integral sliding average models, and seasonal autoregressive integral sliding average models. The fatigue trend can be used to predict the fatigue level of the next time window, and can also be stored as historical data in the control module 11 for correcting behavioral parameters.

[0105] See also Figure 3 and Fig. 9 In some embodiments, the time window includes days; the predetermined period includes years.

[0106] Specifically, the time window includes a daily time window, and the sensor module 12 can obtain the user's complete detection data for one day, which is conducive to analyzing the user's fatigue level for one day. The predetermined period includes a yearly time window, and the control module 11 can obtain the user's fatigue trend for one year. The long timeline and large analysis sample can make the fatigue trend more accurate.

[0107] See also Figure 2 , Figure 3 and Fig.10 In some embodiments, the method for controlling the headset further includes:

[0108] 06: Evaluate the fatigue of the user's body parts when performing the exercise behavior and / or the user's exercise ability according to the fatigue degree of the time window and the behavior parameters corresponding to each exercise behavior, so as to output a first evaluation result; and

[0109] 07: Provide a first exercise suggestion in a next time window according to the first evaluation result and the fatigue trend in a predetermined period.

[0110] The above-mentioned earphone control method can be applied to earphone 10, and the control module 11 is also used to: evaluate the fatigue of the user's body parts and / or the user's exercise ability when the user performs exercise behaviors according to the fatigue level in the time window and the behavior parameters corresponding to each exercise behavior, so as to output a first evaluation result; and provide a first exercise recommendation in the next time window according to the first evaluation result and the fatigue trend in a predetermined period.

[0111] Specifically, in the method of 06, the control module 11 can evaluate the user in the execution of the motor behavior. Wherein, the fatigue degree can characterize the fatigue condition of the user's body parts. The body parts include but are not limited to the user's head, hands, chest, waist and legs, etc. The user's motor ability is compared with the behavioral parameters corresponding to each motor behavior and the pre-stored standard parameters. For example, the control module 11 evaluates the behavioral parameters corresponding to the swimming posture of the user when swimming and the standard parameters corresponding to the swimming posture, and obtains the deviation value between the two groups of parameters. The control module 11 can thus obtain the degree of deviation between the swimming posture of the user and the standard swimming posture, and outputs the first evaluation result according to this. For example, the breathing angle and pitch angle of the freestyle of the user are larger than the breathing angle and pitch angle of the standard freestyle, which indicates that the most effective power technique has not been learned during the current freestyle breathing and gliding.

[0112] In the method of 07, in some embodiments, the first motion suggestion includes: at least one of the kind of motor behavior, the movement duration, the movement intensity and the movement interval of each motor behavior. For example, for the motor behavior of swimming, the first motion suggestion includes the movement duration, the movement intensity (such as represented by the calories consumed) of swimming and the interval of the user's swimming time during the motor behavior of swimming. The first motion suggestion also includes the movement parameter deviation value of the user's motor behavior compared to the standard parameters of the motor behavior. For example, when the breathing angle and the pitch angle of the freestyle of the above user are larger than the breathing angle and the pitch angle of the standard freestyle, the first motion suggestion also includes the information that the pitch angle is larger, and reminds the user when the user's motor behavior of swimming in the next time window. The first motion suggestion also includes the fatigue trend of the user, for example, if the movement duration of a certain motor behavior of the user in a predetermined period is longer, and the movement intensity exceeds the average level, then the first motion suggestion of the earphone 10 can include the motor behavior of reminding the user to swim in the next time window, or when other behaviors, pay attention to control the movement intensity to avoid sports injuries caused by excessive fatigue.

[0113] See also Figure 2 , Figure 3 and Fig.11 In some embodiments, the method for controlling the headset further includes:

[0114] 08: Evaluate the fatigue status of the user's body parts when performing the exercise behavior and / or the user's exercise ability according to the fatigue trend in the predetermined period and the behavior parameters corresponding to each exercise behavior, so as to output a second evaluation result; and

[0115] 09: Providing a second exercise suggestion within the next predetermined period according to the second evaluation result and the fatigue trend within the predetermined period.

[0116] The above-mentioned earphone control method can be applied to earphone 10, and the control module 11 is also used to: evaluate the fatigue status of the user's body parts when performing exercise behaviors and / or the user's exercise ability when the user performs exercise behaviors according to the fatigue trend within a predetermined period and the behavioral parameters corresponding to each exercise behavior, so as to output a second evaluation result; and provide a second exercise recommendation within the next predetermined period according to the second evaluation result and the fatigue trend within the predetermined period.

[0117] Specifically, in the method of 08, control module 11 can evaluate all motor behaviors performed in a predetermined period of time for a user. Wherein, fatigue trend can characterize the fatigue condition of a user's body part in a predetermined period of time. The predetermined period of time has a certain length of time, that is, the fatigue trend in the predetermined period of time can reflect the fatigue condition of the body part embodied by the motor behavior of the user in a long time and / or the athletic ability of the user. The accumulated fatigue trend helps to monitor the status of the long-term motor behavior of the user, and finds the problem of chronic fatigue or overtraining as early as possible.

[0118] Body parts include but are not limited to the user's head, hands, chest, waist and legs. The user's athletic ability is compared by comparing the behavioral parameters corresponding to each motor behavior with the pre-stored standard parameters. For example, the control module 11 evaluates the behavioral parameters corresponding to the user's swimming posture when swimming with the standard parameters corresponding to the swimming posture, and obtains the deviation value between the two sets of parameters. The control module 11 can thereby obtain the degree of deviation between the user's swimming posture and the standard swimming posture, and output a second evaluation result based on this. For example, the user's current breaststroke breathing angle is smaller than the historical average, indicating that the current breaststroke breathing has become more stable; the current gliding time is longer than the historical average, indicating that the body is more stretched in the current breaststroke gliding stage and the resistance is smaller when gliding. By comparing the current behavioral parameters generated by the user's current swimming with the historical behavioral parameters, it can help the user track his or her own swimming posture learning progress at any time, thereby further broadening the use scenario of the headset 10.

[0119] In the method of 09, in some embodiments, the second motion suggestion includes: at least one of the type of motor behavior, total duration of motion, and intensity and duration distribution of each motor behavior. For example, for the motor behavior of swimming, the second motion suggestion includes the motion duration of swimming, exercise intensity (such as characterized by the calories consumed) and the interval of the user's swimming time during the motor behavior of swimming. The second motion suggestion also includes the motion parameter deviation value of the user's motor behavior compared to the standard parameters of the motor behavior. For example, when the gliding time of the current breaststroke of the user above is longer than the historical average, the second motion suggestion also includes the information of increasing the arm swing, strengthening the leg kicking frequency, and reminding the user when the motor behavior of swimming in the next predetermined period of the user. The second motion suggestion also includes the fatigue trend of the user, such as if the motion duration of a certain motor behavior of the user in a predetermined period is longer, and the exercise intensity exceeds the average level, then the second motion suggestion of the earphone 10 can include the motor behavior of reminding the user to swim in the next predetermined period, or when other behaviors, pay attention to control the exercise intensity to avoid sports injuries caused by excessive fatigue.

[0120] See also Figure 1 , Figure 2 , Figure 3 , Fig.10 and Fig.12 The present application also provides a computer-readable storage medium 200 on which a program 202 is stored. When the program 202 is executed by the processor 20, the control method of any of the above-mentioned embodiments is implemented.

[0121] For example, when the program 202 is executed by the processor 20, the following control method is implemented:

[0122] 02: Identify the movement behavior of the user wearing the headset 10 in a preset time window, and each movement behavior corresponds to a preset behavior parameter calculation algorithm;

[0123] 03: Based on the behavior parameter calculation algorithm, according to the detection data collected by the sensor module 12 when the user performs the exercise behavior, the behavior parameter corresponding to the exercise behavior is obtained;

[0124] 04: Output the fatigue level of the user wearing the headset 10 in the time window according to the behavior parameters corresponding to all the movement behaviors in the time window and the preset fatigue detection model.

[0125] For another example, when the program 202 is executed by the processor 20, the following control method is implemented:

[0126] 06: Evaluate the fatigue of the user's body parts when performing the exercise behavior and / or the user's exercise ability according to the fatigue degree of the time window and the behavior parameters corresponding to each exercise behavior, so as to output a first evaluation result;

[0127] 07: Provide a first exercise suggestion in a next time window according to the first evaluation result and the fatigue trend in a predetermined period.

[0128] For another example, when program 202 is executed by processor 20, the control methods in 02, 021, 023, 03, 04, 05, 06, 07, 08, and 09 can also be implemented.

[0129] In the computer-readable storage medium 200 in the present application, the control module 11 of the headset 10 can identify the user's motion behavior when the user performs motion behavior within a preset time window, and obtain the behavior parameters corresponding to the motion behavior based on the behavior parameter calculation algorithm corresponding to the motion behavior and the detection data collected by the sensor module 12, and obtain the fatigue level of the user wearing the headset 10 in the time window according to the behavior parameters corresponding to all motion behaviors in the time window and the preset fatigue detection model, so that the user can obtain data feedback under the motion behavior.

[0130] In the description of this specification, the descriptions with reference to the terms "certain embodiments", "in an example", "exemplarily", etc., mean that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0131] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0132] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for controlling headphones, characterized in that: The earphone includes a sensor module, and the control method includes: Identify the movement behavior of the user wearing the headset in a preset time window, each movement behavior corresponds to a preset behavior parameter calculation algorithm; Based on the behavior parameter calculation algorithm, according to the detection data collected by the sensor module when the user performs the movement behavior, the behavior parameter corresponding to the movement behavior is obtained; and The fatigue degree of the user wearing the headset in the time window is output according to the behavior parameters corresponding to all the movement behaviors in the time window and a preset fatigue detection model.

2. The control method according to claim 1, characterized in that: The identifying the movement behavior of the user wearing the headset in the time window includes: Based on the detection data collected by the sensor module in the time window, the movement behavior of the user wearing the headset in the time window is identified.

3. The control method according to claim 2, characterized in that: The sensor module includes an accelerometer, and the detection data includes three-axis acceleration detected by the accelerometer; and / or, The sensor module includes a gyroscope, and the detection data includes three-axis angular velocity detected by the gyroscope.

4. The control method according to claim 1, characterized in that: The headset further includes a command receiving module; and the identifying the movement behavior of the user wearing the headset in the time window includes: Based on the movement behavior instruction received by the instruction receiving module, the movement behavior of the user wearing the headset in the time window is determined.

5. The control method according to claim 4, characterized in that: The headset further comprises a control box assembly and a battery box assembly, wherein the control box assembly comprises a control box, and the battery box assembly comprises a battery box; The instruction receiving module includes an input module arranged on the control box or the battery box, the input module is used to input user instructions, and the input module includes at least one of a button and a touch screen; or, The headset also includes a communication module, the instruction receiving module includes the communication module arranged in the control box or the battery box, the communication module is used to receive instructions sent by an external device, and the external device includes at least one of a mobile phone, a watch, a server, a computer and a tablet computer.

6. The control method according to claim 1, characterized in that: The control method further comprises: The fatigue level of each of the time windows within a predetermined period pushed forward from the time window is analyzed to obtain a fatigue trend of the user wearing the headset within the predetermined period.

7. The control method according to claim 6, characterized in that: The time window may be measured in days; the predetermined period may be measured in years.

8. The control method according to claim 6, characterized in that: The control method further comprises: According to the fatigue degree of the time window and the behavior parameters corresponding to each of the movement behaviors, the fatigue condition of the body part of the user when performing the movement behavior and / or the movement ability of the user are evaluated to output a first evaluation result; and A first exercise suggestion is provided in the next time window according to the first evaluation result and the fatigue trend in the predetermined period.

9. The control method according to claim 8, characterized in that: The first exercise suggestion includes: at least one of the type of exercise behavior to be performed, the exercise duration for performing each exercise behavior, the exercise intensity and the exercise interval.

10. The control method according to claim 6, characterized in that: The control method further comprises: According to the fatigue trend in the predetermined period and the behavior parameters corresponding to each of the movement behaviors, the fatigue condition of the body part of the user when performing the movement behavior and / or the movement ability of the user are evaluated to output a second evaluation result; and A second exercise suggestion is provided within the next predetermined period according to the second evaluation result and the fatigue trend within the predetermined period.

11. The control method according to claim 10, characterized in that: The second exercise suggestion includes at least one of the type of exercise behavior to be performed, the total exercise duration, and the intensity and duration distribution of each exercise behavior.

12. The control method according to any one of claims 1 to 11, characterized in that: The sports behavior includes at least one of swimming, cervical vertebra activity, jumping, cycling, running, skipping rope, skiing, and mountain climbing; the behavior parameter calculation algorithm includes at least one of a swimming algorithm, a cervical vertebra activity algorithm, a jumping algorithm, a cycling algorithm, a running algorithm, a skipping rope algorithm, a skiing algorithm, and a mountain climbing algorithm.

13. The control method according to any one of claims 1 to 11, characterized in that: In the case where the sports behavior includes swimming, the behavior parameter calculation algorithm includes a swimming algorithm, and the behavior parameters include at least one of a swimming style, a proportion of each swimming style, a breathing frequency, a freestyle breathing angle, a freestyle maximum breathing angle, a freestyle pitch angle, a breaststroke breathing angle, a breaststroke maximum breathing angle, a breaststroke total gliding time, and a total duration; In the case where the movement behavior includes moving the cervical vertebra, the behavior parameter calculation algorithm includes a cervical vertebra activity algorithm, and the behavior parameter includes at least one of a head left rotation angle, a head right rotation angle, a head forward tilt angle, a head backward tilt angle, a head left tilt angle, and a head right tilt angle; In the case where the movement behavior includes bouncing, the behavior parameter calculation algorithm includes a bouncing algorithm, and the behavior parameter includes a bouncing height.

14. A headset, characterized in that: The earphone comprises: A sensor module, used to collect detection data; and A control module is communicatively connected to the sensor module and is used to execute the control method described in any one of claims 1-13.

15. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the control method described in any one of claims 1 to 13 is implemented.

Images