WO2021197243A1

WO2021197243A1 - Method for detecting basketball moves on basis of wearable device, and wearable device

Info

Publication number: WO2021197243A1
Application number: PCT/CN2021/083465
Authority: WO
Inventors: 徐腾; 刘海波; 陈霄汉
Original assignee: 荣耀终端有限公司
Priority date: 2020-03-31
Filing date: 2021-03-27
Publication date: 2021-10-07
Also published as: CN113457096A; CN113457096B

Abstract

A method for detecting basketball moves on the basis of a wearable device, and a wearable device. The wearable device comprises a sound wave collection apparatus and a motion sensor. In the method, a wearable device can collect first motion data, such as a movement speed and a motion distance, of a user within a first time period by means of a motion sensor; the wearable device can collect a first sound wave signal within the first time period by means of a sound wave collection apparatus, and determine, according to the first sound wave signal, whether the user produces a dribbling move within the first time period; and if it is determined that the user produces a dribbling move, the type of the dribbling move, such as stationary dribbling or running dribbling, is determined according to the first motion data. The wearable device can detect the specific control a user has over a basketball when the user is playing basketball, thereby effectively assisting the user in improving his/her ability to play basketball.

Description

Method for detecting basketball action based on wearable device and wearable device

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on March 31, 2020, the application number is 202010260267.X, and the application name is "Methods for detecting basketball actions based on wearable devices and wearable devices", all of which The content is incorporated in this application by reference.

Technical field

This application relates to the field of terminal technology, and in particular to a method for detecting basketball actions based on a wearable device and a wearable device.

Background technique

Basketball is a popular sport. The actions in basketball mainly include running, jumping, dribbling, passing and shooting. The wearable device can record the user's movement data when playing basketball, and assist the user to improve the ability of playing basketball.

At present, the wearable device can collect the user's angular velocity signal and acceleration signal when playing basketball through the six-axis sensor. Based on the angular velocity signal and acceleration signal, the wearable device can calculate the user's vertical jump height, vertical jump number and movement speed and other motion data .

However, in basketball, the user's ability to dribble, pass and shoot is the key factor that affects the user's basketball level. The current wearable device can only record the user's walking, running and jumping movement data on the foot, and cannot monitor the user. The specific control of basketball when playing basketball, such as dribbling on the spot, running dribbling, and running without the ball, is difficult to effectively assist users in improving their ability to play basketball.

Summary of the invention

This application provides a method for detecting basketball actions based on a wearable device and a wearable device. The wearable device can collect the sound wave signal through the sound wave acquisition device to determine whether the user is dribbling, and combine the user's walking, running and jumping movement data recorded by the motion sensor to realize the monitoring of the user's actions when playing basketball , Thereby effectively assisting users to improve their ability to play basketball.

In the first aspect, an embodiment of the present application provides a method for detecting basketball actions based on a wearable device. The wearable device includes a sound wave acquisition device and a motion sensor. The method includes: The first movement data in the segment; the first movement data includes one or more of the following: moving speed, movement distance; the wearable device collects the first sound wave signal in the first time period through the sound wave acquisition device; wearable According to the first sound wave signal, the device determines whether the user has made a dribble action in the first time period; if it is determined that the user has made a dribble action in the first time period, it is determined according to the first motion data The type of dribble action.

In combination with the method provided in the first aspect, the wearable device can obtain the user's movement data of walking, running and jumping on the feet in the same time period and the judgment result of whether a dribble action has occurred. In this way, the wearable device can determine the user's specific control of basketball when playing basketball, such as dribbling on the spot and running dribbling, thereby effectively assisting the user in improving the ability of playing basketball.

In the embodiment of the present application, the wearable device may be buckled on the user's shoes. In this way, the wearable device can more accurately use the motion sensor to record the movement data of the user walking, running and jumping on the foot, and use the sound wave collection device to collect the sound wave signal generated by the basketball colliding with the ground when the user is dribbling to determine the user Whether to produce a dribble action.

Optionally, the wearable device can be worn on the user's wrist.

With reference to the first aspect, in some embodiments, the wearable device displays a first user interface in which a first control is displayed; the wearable device detects a first user operation acting on the first control; In response to the first user operation, the wearable device determines whether the motion sensor and the sound wave acquisition device are turned on, and if they are not turned on, the motion sensor and the sound wave acquisition device are turned on.

Optionally, the wearable device may receive the first instruction from the electronic device. When receiving the first instruction, the wearable device determines whether the motion sensor and the sound wave acquisition device are turned on, and if they are not turned on, the motion sensor and the sound wave acquisition device are turned on. Specifically, the electronic device may display controls for turning on the motion sensor and the sound wave acquisition device on the user interface. When a user operation, such as a touch operation, that acts on the control of the motion sensor and the sound wave collection device is detected, the electronic device may send the first instruction to the wearable device. Wherein, the wearable device establishes a communication connection relationship with the electronic device. For example, the wearable device can be connected to the electronic device via Bluetooth.

With reference to the first aspect, in some embodiments, the wearable device determines the first similarity based on the feature parameters of the first acoustic signal and the first Gaussian mixture model; the training data of the first Gaussian mixture model is the first feature Parameter, the first characteristic parameter is a characteristic parameter of the acoustic signal during dribbling; the characteristic parameter of the first acoustic signal and the first characteristic parameter both include at least one or more of the following: energy, frequency, and peak; The first Gaussian mixture model includes multiple Gaussian distributions, the mean and variance of the multiple Gaussian distributions converge, and the weights of the multiple Gaussian distributions in the first Gaussian mixture model converge; the first similarity is used to indicate the The similarity between the characteristic parameter of the first acoustic wave signal and the first characteristic parameter; if the first similarity is higher than the first threshold, the wearable device determines that the user performs a dribbling action in the first time period.

Optionally, the sonic signal during dribbling may be the sonic signal during dribbling of the user. Specifically, the wearable device may pre-collect the acoustic wave signal of the user during dribbling, and use the characteristic parameter of the acoustic wave signal as the first characteristic parameter to train the first Gaussian mixture model. In this way, the first Gaussian mixture model can reduce the influence of other people's dribbling actions, thereby more accurately determining whether the user has dribbling actions.

In the embodiment of the present application, the type of the dribbling action includes one or more of the following: in-place dribbling and running dribbling.

When the movement speed in the first movement data is less than the first speed and/or the movement distance in the first movement data is less than the first distance, the wearable device determines that the type of action is dribbling in place; when the movement in the first movement data is When the movement speed is greater than the second speed and/or the movement distance in the first movement data is greater than the second distance, the wearable device determines that the type of action is running dribbling; the first speed is less than or equal to the second speed, and the first speed is less than or equal to the second speed. The distance is less than or equal to the second distance.

In the embodiment of the present application, the wearable device may also determine, according to the first sound wave signal, the user's passing motion or shooting motion in the first time period.

Specifically, if it is determined that the user is dribbling in the first sub-period according to the first acoustic signal in the first sub-period, and it is determined that the user is dribbling in the first sub-period according to the first acoustic signal in the second sub-period If there is no dribble in the second sub-time period, the wearable device determines that the user produces a passing or shooting action in the first time period; the first sub-time period and the second sub-time period are the first sub-time period. Two adjacent time segments within a period of time.

In the embodiment of the present application, after the wearable device determines the user's passing motion or shooting motion in the first time period according to the first sound wave signal, the method further includes: if the second sub-time period is If the moving speed of is greater than the second speed and/or the movement distance in the second sub-period is greater than the second distance, the wearable device determines that the user generates a running motion during the first period of time; running; Moving shots include running passes and running shots.

In the embodiment of the present application, the first movement data further includes the vertical jump height. After the wearable device determines the user's passing motion or shooting motion in the first time period according to the first sound wave signal, the method further includes: if the vertical jump height in the second sub-time period is greater than the first time period. Height, the wearable device determines that the user has made a vertical jump pass within the first time period; the vertical jump pass includes a vertical jump pass and a vertical jump shot.

In the embodiment of the present application, the wearable device may also determine that the user produces one or more of the following actions in the first time period: running without the ball and jumping without the ball.

Specifically, if it is determined that the user did not make a dribble action in the first time period, and the movement speed in the first time period is greater than the second speed and/or the movement distance in the first time period is greater than the For the second distance, the wearable device determines that the user runs without the ball during the first time period. If it is determined that there is no dribbling action in the first time period, and the vertical jump height in the first time period is greater than the first height, the wearable device determines that the user has no ball vertical jump in the first time period Actions.

In the embodiment of the present application, the wearable device displays the first information. The first information indicates whether the user has made a dribble action in the first time period.

Exemplarily, when it is determined that the user has made a dribble action in the first time period, the wearable device may calculate the number of dribbles and the dribble time of the user in the first time period, and display the sum of the number of dribbles. Dribble time.

With reference to the first aspect, in some embodiments, the first information may also include first motion data. For example, moving speed and moving distance.

In the embodiment of the present application, the wearable device may send the first information to the electronic device. The wearable device establishes a communication connection relationship with the electronic device. For example, the wearable device can be connected to the electronic device via Bluetooth.

When receiving the first information, the electronic device can display it.

Optionally, the electronic device may also provide targeted exercise suggestions to the user according to the first information. Exemplarily, when it is determined that the value of the vertical jump height of the user is low, the electronic device may provide the user with exercise suggestions to improve the jumping ability. In this way, it can effectively assist the user to improve the ability to play basketball.

With reference to the first aspect, in some embodiments, the wearable device can determine the user's number position in the first time period.

Specifically, the wearable device determines the number of dribbles and/or dribbling time of the user in the first time period according to the first sound wave signal; the wearable device determines the basketball movement data of the user in the first time period Determine the number position of the user in the first time period; the basketball data of the user in the first time period includes one or more of the following: the number of dribbles of the user in the first time period , Dribbling time, movement speed, movement distance.

Exemplarily, the wearable device may determine the user's number position in the first time period through template matching. Among them, the number position template library contains various basketball data templates for each number position (such as power forward, center, small forward, shooting guard, and point guard). The template indicates that the general user is a certain number on the basketball court is the value range of various basketball data. The wearable device can calculate the correlation coefficient between the user’s basketball data in the first time period and the basketball data in the number template library, and determine that the user is in the first time period by determining the number corresponding to the largest correlation coefficient The number position.

In the embodiment of the present application, the wearable device can realize the detection of the user's actions when playing basketball and the user's number position, thereby effectively assisting the user to improve the ability of playing basketball.

In a second aspect, an embodiment of the present application provides a wearable device, the wearable device comprising: a motion sensor, a sound wave collecting device, and a processor coupled with each other; the motion sensor is used to collect the user's The first movement data; the first movement data includes one or more of the following: moving speed, movement distance; the sound wave acquisition device for collecting the first sound wave signal in the first time period; the processor is used for , According to the first sound wave signal, determine whether the user has made a dribble action in the first time period; the processor is also used to, if it is determined that the user has made a dribble action in the first time period, then The type of the user's dribbling action is determined according to the first movement data.

In the embodiment of the present application, the wearable device may be buckled on the user's shoes. In this way, the motion sensor can more accurately record the motion data of the user walking, running and jumping on the footsteps. The sound wave collection device can better collect the sound wave signal generated by the collision of the basketball and the ground when the user dribbles. In this way, the processor can more accurately detect whether the user has made a dribble action.

Optionally, the wearable device can be worn on the user's wrist.

The wearable device provided in the second aspect can realize: determining the user's movement data of walking, running, and jumping on the feet in the same time period and the judgment result of whether a dribble action is generated. In this way, the wearable device can determine the user's specific control of basketball when playing basketball, such as dribbling on the spot and running dribbling, thereby effectively assisting the user in improving the ability of playing basketball.

With reference to the second aspect, the wearable device further includes a display screen and a touch panel; the display screen is used to display a first user interface, and a first control is displayed in the first user interface; the touch panel detects that the first user interface acts on the A first user operation on a control; the processor is also used to determine whether the motion sensor and the sound wave acquisition device are turned on, and if they are not turned on, turn on the motion sensor and the sound wave acquisition device.

With reference to the second aspect, in some embodiments, the wearable device can receive the first instruction from the electronic device. When receiving the first instruction, the processor can determine whether the motion sensor and the sound wave acquisition device are turned on, and if they are not turned on, the processor turns on the motion sensor and the sound wave acquisition device. Specifically, the electronic device may display controls for turning on the motion sensor and the sound wave acquisition device on the user interface. When a user operation, such as a touch operation, that acts on the control of the motion sensor and the sound wave collection device is detected, the electronic device may send the first instruction to the wearable device. Wherein, the wearable device establishes a communication connection relationship with the electronic device. For example, the wearable device can be connected to the electronic device via Bluetooth.

With reference to the second aspect, in some embodiments, the processor is specifically configured to: determine the first similarity based on the characteristic parameters of the first acoustic signal and the first Gaussian mixture model; training data of the first Gaussian mixture model Is the first characteristic parameter, which is the characteristic parameter of the acoustic signal during dribbling; both the characteristic parameter of the first acoustic signal and the first characteristic parameter include at least one or more of the following: energy, frequency And the peak value; the first Gaussian mixture model includes a plurality of Gaussian distributions, the mean and variance of the plurality of Gaussian distributions converge, and the weights of the plurality of Gaussian distributions in the first Gaussian mixture model converge; the first degree of similarity is used It indicates the similarity between the characteristic parameter of the first acoustic wave signal and the first characteristic parameter; if the first similarity is higher than the first threshold, it is determined that the user has made a dribbling action in the first time period.

Optionally, the sound wave signal during dribbling is a sound wave signal pre-collected by the sound wave collecting device during dribbling of the user.

In the embodiment of the present application, the type of the dribbling action includes one or more of the following: in-place dribbling and running dribbling. Wherein, the processor is specifically configured to: when the movement speed in the first movement data is less than the first speed and/or the movement distance in the first movement data is less than the first distance, determine that the type of the action is dribbling in place ; When the movement speed in the first movement data is greater than the second speed and/or the movement distance in the first movement data is greater than the second distance, it is determined that the type of action is running dribbling; the first speed is less than or equal to For the second speed, the first distance is less than or equal to the second distance.

In the embodiment of the present application, the processor may determine that the type of action generated by the user in the first time period is a passing action or a shooting action. Wherein, the processor is specifically configured to: if it is determined according to the first sound wave signal in the first sub-time period that the user is dribbling the ball in the first sub-time period, and according to the first sound wave signal in the second sub-time period The signal determines that the user did not dribble in the second sub-time period, then it is determined that the user has passed or shot the ball in the first time period; the first sub-time period and the second sub-time period Are two consecutive time segments in the first time period.

In the embodiment of the present application, after determining that the user produces a passing action or a shooting action in the first time period, the processor is further configured to: if the moving speed in the second sub-time period is greater than the second time period If the speed and/or the movement distance in the second sub-time period is greater than the second distance, it is determined that the user has a running pass and throw action in the first time period; the running pass includes running pass and running Active shooting.

In the embodiment of the present application, the first movement data further includes the vertical jump height. After determining that the user makes a passing action or a shooting action in the first time period, the processor is further configured to: if the vertical jump height in the second sub-time period is greater than the first height, determine that the user is in Vertical jump shots are generated in the first time period; vertical jump shots include vertical jump passes and vertical jump shots.

In the embodiment of the present application, the processor may determine that the user produces one or more of the following actions in the first time period: running without the ball and jumping without the ball. Wherein, the processor is specifically configured to: if it is determined that the user has not made a dribble action in the first time period, and the moving speed in the first time period is greater than the second speed and/or in the first time period If the movement distance of is greater than the second distance, it is determined that the user has an action of running without the ball in the first time period. If it is determined that there is no dribbling action in the first time period, and the vertical jump height in the first time period is greater than the first height, it is determined that the user has a ball-free vertical jump action in the first time period.

In the embodiment of the present application, the display screen is also used to display the first information. The first information indicates whether the user has made a dribble action in the first time period.

Exemplarily, when it is determined that the user has made a dribble action in the first time period, the processor may calculate the number of dribbles and the dribble time of the user in the first time period. The display screen can display the number of dribbles and the dribble time.

When receiving the first information, the electronic device can display it.

With reference to the second aspect, in some embodiments, the processor may be further configured to: determine the number of dribbles and/or dribble time of the user in the first time period according to the first acoustic signal; The basketball movement data in the first time period determines the user's number position in the first time period; the basketball movement data of the user in the first time period includes one or more of the following: the user is in the first time period The number of dribbles, dribbling time, movement speed, and movement distance within the time period.

In the third aspect, the embodiments of the present application provide a computer program product containing instructions. When the computer program product is run on a wearable device, the wearable device can execute any of the first aspect and the first aspect. Implement the method described in the method.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions, when the foregoing instructions are executed on a wearable device, the wearable device can perform any of the possible methods in the first aspect and the first aspect. Implement the method described in the method.

Understandably, the wearable device provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to implement the methods provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

Description of the drawings

FIG. 1 is a usage scenario of a wearable device provided by an embodiment of the present application;

FIG. 2 is a schematic diagram of starting/ending a basketball mode provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of another basketball mode enabled according to an embodiment of the present application;

FIG. 4 is a schematic diagram of another basketball mode enabled according to an embodiment of the present application;

FIG. 5 is a flowchart of a method for a wearable device to monitor a user's basketball action provided by an embodiment of the present application;

FIG. 6 is a flowchart of another method for a wearable device to monitor a user's basketball action provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of a wearable device prompting a user to enter personal dribbling data according to an embodiment of the present application;

FIG. 8 is a schematic diagram of another wearable device prompting a user to enter personal dribbling data according to an embodiment of the present application;

FIG. 9 is a schematic diagram of another wearable device provided by an embodiment of the present application prompting a user to enter personal dribbling data;

10 and 11 are the intentions of the application interfaces of some electronic devices provided by the embodiments of the present application;

FIG. 12 is a schematic diagram of a wearable device displaying exercise data according to an embodiment of the present application;

FIG. 13 is a schematic structural diagram of a wearable device provided by an embodiment of the present application.

Detailed ways

The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a", "an", "said", "above", "the" and "this" are intended to also Including plural expressions, unless the context clearly indicates to the contrary. It should also be understood that the term "and/or" used in this application refers to and includes any or all possible combinations of one or more of the listed items.

The embodiment of the present application provides a method for detecting basketball actions based on a wearable device. In this method, in addition to collecting the acceleration signal and angular velocity signal of the user's foot through the accelerometer and gyroscope, the wearable device can also use a microphone to collect sound wave signals. Among them, the wearable device can use the acceleration signal and the angular velocity signal to analyze whether the user is running or jumping and other foot actions. The wearable device can use the sound wave signal to analyze whether the user is dribbling. In this way, the wearable device can monitor the user's overall movement when playing basketball, combining the user's foot movement at the same time and the analysis result of whether or not to dribble. That is, basketball actions, such as dribbling in place, running dribbling, running without the ball, vertical jump without the ball, and vertical jump shot. So as to effectively assist the user to improve the ability to play basketball.

When the user is dribbling the ball (such as dribbling on the spot, running dribble), the basketball will hit the ground and produce a loud sound. The sound wave signal collected by the wearable device when the user is dribbling is quite different from the sound wave signal collected when the user is not dribbling. Among them, in the spectrogram of the acoustic signal collected by the wearable device, the peak value and energy of the acoustic signal generated by dribbling are much greater than the peak value and energy of the acoustic signal generated by no dribbling. Through this distinction, the wearable device can tell whether the user is dribbling.

Specifically, when the user is playing basketball, the sound wave signal collected by the microphone may include the sound wave signal generated by dribbling (such as dribbling in place, running dribble) and not dribbling (such as running without the ball, running without the ball). Jump, vertical jump shot) generated by the sound wave signal. The wearable device can use the trained Gaussian mixture model to recognize the sound wave signal collected by the microphone to distinguish the sound wave signal generated by dribbling and the sound wave signal generated by no dribbling. In this way, the wearable device can analyze whether the user dribbles, and calculate the user's dribbling time and the number of dribbles.

The dribbling mentioned in the embodiments of the present application may refer to an action in which the user continuously slaps the basketball with one hand or alternately slaps the basketball with both hands while in place or while moving, and makes the basketball bounce from the ground. Dribbling can include dribbling in place and running dribbling.

The wearable device in the embodiment of the present application will be introduced below. Please refer to FIG. 1, which shows a usage scenario of a wearable device provided by an embodiment of the present application. As shown in FIG. 1, the wearable device 100 may be buckled on the user's shoes. The wearable device 100 may include a device main body 110 and a wearable part 120. in:

An accelerometer, a gyroscope, and a microphone are configured in the device main body 110. The device main body 110 can use the accelerometer, gyroscope, and microphone to collect acceleration signals, angular velocity signals, and sound wave signals, respectively. The device main body 110 may include a display screen 111 and a touch control 112. The display screen 111 can be used to display the time, the power of the main body 110 of the device, the received messages, and the sports data of the user playing basketball. The touch control 112 can be used to light up the display screen, turn on and end the basketball mode, and so on.

The device main body 110 can also record the number of steps the user has moved and the calories consumed, and has basic functions such as call reminders and message notifications.

The device main body 110 may establish a wireless communication connection with an electronic device, such as a mobile phone or a tablet computer.

In a possible implementation manner, the device main body 110 may establish a wireless communication connection with a mobile phone via Bluetooth. The device main body 110 may send the user's basketball sports data to the connected mobile phone. Moreover, when the aforementioned mobile phone receives an incoming call or message notification, the device main body 110 may receive an instruction from the aforementioned mobile phone to remind the user that there is an incoming call or message notification.

The wearing part 120 is used to install the device main body 110. The wearing part 120 may be a shoe buckle or other device that enables the main body 110 of the device to be attached to the user's foot.

The wearable device 100 is buckled on the user's shoes, so that the accelerometer and gyroscope can collect acceleration signals and angular velocity signals of the user's feet to monitor the movement of the user's feet. At the same time, it is also convenient for the microphone to collect the sound wave signal generated by the collision between the basketball and the ground when the user is dribbling, so as to monitor whether the user is dribbling.

In addition to being buckled on the user's shoes, the wearable device can also be worn on the user's wrist.

In a possible implementation manner, the wearing component 120 may also be a wristband or other device that enables the main body 110 of the device to be attached to the user's wrist.

That is, the user can switch the way in which the device body 110 is worn. When playing basketball, the user can install the device body 110 on the shoe buckle. In this way, the main body 110 of the device can be fastened to the shoe through the shoe buckle. In daily use, the user can install the main body 110 of the device on the wristband. In this way, the device main body 110 can be worn on the wrist through the wristband.

When the device body 110 is installed on the bracelet, the device body 110 may refuse to turn on the basketball mode.

In a possible implementation manner, when the device body 110 is installed on the shoe buckle and a user operation for turning on the basketball mode is monitored, the device body 110 may turn on the basketball mode. When the device main body 110 is installed on the bracelet and a user operation for turning on the basketball mode is detected, the device main body 110 may prompt the user that the wearable device 100 is not buckled on the shoes, and the basketball mode cannot be turned on.

The wearable device 100 monitors the user's actions when playing basketball and needs to record the movement data of the user's feet. The above implementation restricts the usage scenario of the device main body 110 in the basketball mode to the application scenario where the wearable device 100 is buckled on the shoes. In this way, the basketball mode can be avoided when the device main body 110 is worn on the user's wrist, and the accuracy of the device main body 110 in monitoring the user's actions when playing basketball can be improved.

The concept of basketball mode is introduced below.

Basketball mode: refers to a function of the device main body 110, which can be used to record the user's movement data when playing basketball and monitor the user's actions when playing basketball. When the basketball mode is turned on, the microphone, accelerometer, and gyroscope in the device main body 110 are all in working state, and can be used to collect sound wave signals, foot acceleration signals, and angular velocity signals when the user is playing basketball, respectively. The device main body 110 can process the above-mentioned sound wave signals, acceleration signals, and angular velocity signals to obtain movement data such as vertical jump height and the number of dribbles, so as to determine the overall actions of the user when playing basketball.

The device main body 110 can start or end the basketball mode by monitoring user operations on the touch control 112.

In a possible implementation manner, when a long press operation on the touch control 112 is monitored, the device main body 110 may start or end the basketball mode. As shown in FIG. 2, when the device main body 110 does not turn on the basketball mode and a long press operation on the touch control 112 is monitored, the device main body 110 can start the basketball mode after a countdown of 3 seconds after the vibration. When the basketball mode is turned on, the device main body 110 may display the basketball icon and the text "basketball mode" on the display screen 111. In this way, the user device main body 110 can be notified that the basketball mode has been turned on.

When the device main body 110 has turned on the basketball mode and a long press operation on the touch control 112 is monitored, the device main body 110 may end the basketball mode after shaking.

The device main body 110 may automatically turn off the display screen 111 after a period of time, such as 1 minute or 2 minutes, after the basketball mode is turned on. When a short press operation on the touch control 112 is detected, the main body 110 of the device can light up the display screen 111. The display screen 111 can display the basketball icon and the text "basketball mode" as shown in FIG. 2 after being lit. Further, if a long press operation on the touch control 112 is detected, the device main body 110 may end the basketball mode after the vibration.

The device main body 110 automatically turns off the display screen 111 after the basketball mode is turned on for a period of time, which can effectively save the power consumption of the device main body 110.

The embodiment of the present application does not limit the content displayed on the display screen 111 after the device main body 110 starts the basketball mode.

That is, when the user needs to turn on the basketball mode, the user can first install the main body 110 of the device on the wearing part 120, and then press and hold the touch control 112 for a long time. After the device main body 110 vibrates, count down for 3 seconds to start the basketball mode. When the user needs to end the basketball mode, the user can first short-press the touch control 112, and then long-press the touch control 112 after the display screen 111 is turned on. The basketball mode can be ended after the device main body 110 vibrates.

In some embodiments, the device body 110 may detect whether the motion sensors (such as accelerometers and gyroscopes) and the microphone are in working state before the basketball mode is turned on.

Figure 3 shows another schematic diagram of turning on the basketball mode. When a user operation for turning on the basketball is monitored, such as a long-press operation on the touch control 112, the device main body 110 may display a user interface as shown in FIG. 3 on the display screen 111, and the user interface may include a prompt box 130. Cancel the control 131 and open the control 132. in:

The prompt box 130 may be used to remind the user that when the basketball mode is turned on, the motion sensors (such as accelerometer and gyroscope) and the microphone in the device main body 110 will be in working state to determine whether the user needs to turn on the basketball mode.

The cancel control 131 can be used to cancel the activation of the basketball mode.

The opening control 131 can be used to start the basketball mode. In response to a user operation on the opening control 131, such as a touch operation, the device main body 110 can detect whether the motion sensor (such as an accelerometer and a gyroscope) and a microphone are in an operating state. If the motion sensor and the microphone are not in the working state, the device main body 110 can automatically make the motion sensor and the microphone in the working state. In this way, the device main body 110 can turn on the basketball mode, and remind the user that the basketball mode is turned on by means of vibration.

The device main body 110 may also start or end the basketball mode by receiving an instruction to start or end the basketball mode sent by the electronic device.

In a possible implementation manner, the device main body 110 may establish a communication connection relationship with an electronic device (such as a mobile phone, a tablet computer, etc.). When a user operation for starting or ending the basketball mode is monitored, the electronic device may send an instruction to start or end the basketball mode to the main device 110. When receiving an instruction for turning on or ending the basketball mode, the device main body 110 may turn on or end the basketball mode.

As shown in (A) in FIG. 4, the electronic device displays a main screen interface 200. The home screen interface 200 may include icons 201 of application programs for exercise and health, and icons of other applications (such as mail, gallery, and music, etc.). The icon of any application can be used to respond to a user's operation, such as a touch operation, so that the electronic device starts the application corresponding to the icon. in:

The sports fitness icon 210 can be used to start the sports fitness application. The sports health application can be used to establish a communication connection between the electronic device and the wearable device 100. The electronic device can show the user's exercise data to the user through the sports health application. The embodiment of the present application does not limit the application program used to connect the electronic device and the wearable device 100, and may be other application programs in addition to sports health.

As shown in (A) and (B) of FIG. 4, in response to a user operation, such as a touch operation, acting on the sports health icon 201, the electronic device may display the sports health application interface 210. The application interface 210 may include an interface view option 211, an added device option 212, and an added device 213. in:

The interface viewing options 211 may include health options, exercise options, discovery options, device options, and my options. Any option can be used to respond to a user's operation, such as a touch operation, so that the electronic device displays the content corresponding to the option on the application interface 210. For example, the content corresponding to the device option 211a may include device information that has been added in the electronic device and controls for adding a new device. When the electronic device monitors a user operation, such as a touch operation, that acts on the device option 211a, the electronic device can display the application interface 210 as shown in (B) of FIG. 4.

The add device 213 can be used to add a new device. The new device is a device that establishes a communication connection relationship with the above-mentioned electronic device for the first time. When a user operation on the adding device 213 is monitored, such as a touch operation, the electronic device may display an adding device setting interface, so that the electronic device establishes a communication connection relationship with the new device. The above add device device interface allows users to search for new devices and establish communication connections, such as Bluetooth connections. The embodiment of the present application does not limit the process of establishing a communication connection relationship between the electronic device and the new device.

The added device option 212 may include viewing controls for multiple wearable devices or other electronic devices. All of the aforementioned multiple wearable devices or other electronic devices have established a communication connection relationship with the electronic device. For example, the electronic device has established a communication connection relationship with the wearable device, the electronic device A, and the electronic device B. When a user operation, such as a touch operation, acting on the viewing control of any device in the added device options 212 is monitored, the electronic device can display related information corresponding to the device.

As shown in (B) and (C) in FIG. 4, when the viewing control acting on the wearable device in the added device option 212 is monitored, the electronic device can display the application interface 220. The application interface 220 may include a return control 221, a device status 222, exercise data 223, and a professional exercise mode 224. in:

The return control 221 can be used to return to the upper level interface of the application interface 220. In response to a user operation acting on the return control 221, the electronic device may display the application interface 210.

The device status 222 can be used to prompt the connection status of the wearable device 100 and the electronic device and the power of the wearable device 100. Exemplarily, when it is detected that the electronic device has established a communication connection relationship with the wearable device 100 through the Bluetooth connection mode, the device status 222 may prompt that the connection mode is Bluetooth connection and the connection status is "connected". Further, the electronic device can obtain the power information of the wearable device 100. The device status 222 may indicate the current power of the wearable device 100, for example, 77%. The content prompted by the device status 222 may include more, which is not limited in the embodiment of the present application.

The exercise data 223 may include the number of steps moved, the calories consumed, and the distance moved by the user recorded by the wearable device 100. The data in the exercise data 223 is data recorded by the wearable device 100 in the working state of the user within a day. It can include the total number of steps moved, the calories consumed, and the distance moved by the user during daily activities such as walking, playing basketball, and running. In response to user operations on the sports data 223, such as touch operations, the electronic device can display professional sports data of the user's activities such as playing basketball and running, respectively.

The professional sports mode 224 can be used to start or end the basketball mode and the running mode. The professional sports mode 224 may include a basketball mode 224a, an open button 224b for turning on the basketball mode, a running mode, and an open button for turning on the running mode. In response to a user operation, such as a touch operation, acting on the turn-on button 224b, the electronic device may send an instruction to turn on the basketball mode to the wearable device 100 and display the user interface 220 as shown in (D) in FIG. 4. Wherein, the electronic device may display an end button 224c for ending the basketball mode. In response to a user operation on the end button 226c, such as a touch operation, the electronic device may send an instruction to end the basketball mode to the wearable device 100 and display the user interface 220 as shown in (C) in FIG. 4. Among them, the electronic device can display an opening button 224b for opening the basketball mode.

When receiving an instruction to turn on the basketball mode sent by the electronic device, the wearable device 100 (ie, the device body 110) can turn on the basketball mode after a countdown of 3 seconds after the vibration. When the basketball mode is turned on, the device main body 110 can display the basketball icon and the text "basketball mode" on the display screen 111. In this way, the user device main body 110 can be notified that the basketball mode has been turned on.

When receiving an instruction to end the basketball mode sent by the electronic device, the wearable device 100 (ie, the device body 110) can end the basketball mode after shaking.

In addition, when the basketball mode is turned on, the wearable device 100 may automatically turn on the do not disturb mode. Exemplarily, when the Do Not Disturb mode is turned on, when the electronic device receives an incoming call or message notification, the wearable device 100 may shield the reminder instruction of the incoming call or message notification sent by the electronic device. That is, the wearable device 100 will not remind the user of incoming calls or message notifications by means of vibration or ringing. In this way, when the wearable device 100 has turned on the basketball mode and there is an incoming call or message notification, the wearable device 100 will not interfere with the user playing basketball.

It should be noted that, when the above-mentioned running mode is turned on, the wearable device 100 can record the user's movement data such as the touch time and the way of landing while running, so as to realize the monitoring of the user's running action. The embodiment of the present application does not limit the exercise data recorded by the wearable device 100 after the running mode is turned on. The professional sports mode 226 may also include more or fewer sports modes, which are not limited in the embodiment of the present application.

In some embodiments, the device main body 110 may also adaptively turn on or end the basketball mode.

When the basketball mode is not turned on and it is detected that the user is in a state of playing basketball, the device main body 110 may automatically turn on the basketball mode. Wherein, the device main body 110 can determine that the user is in the state of playing basketball. According to the acceleration signal and angular velocity signal collected by the accelerometer and gyroscope, the device main body 110 calculates that the user has running and vertical jumping actions, and running. The movement data such as speed and vertical jump height are close to the movement data of the user when playing basketball, and the device main body 110 can determine that the user is in the state of playing basketball. The device main body 110 may also determine that the user is in the state of playing basketball according to other methods, which is not limited in the embodiment of the present application.

Or, when another professional sports mode is turned on, such as a running mode, but it is detected that the user is playing basketball, the device main body 110 may automatically switch the other professional sports mode to the basketball mode. That is, the device main body 110 can end other professional sports modes and start the basketball mode.

When the basketball mode is turned on and it is detected that the user is not in a state of playing basketball, the device main body 110 may automatically end the basketball mode. The device main body 110 can determine that the user is not in a basketball state. According to the collected sound wave signals, acceleration signals, and angular velocity signals, the device main body 110 calculates that the number of dribbles is basically zero, the running speed and the user is walking or When the speed at rest is close, the device main body 110 can determine that the user is not in a state of playing basketball. The device main body 110 may also determine that it is not in a basketball state according to other methods, which is not limited in the embodiment of the present application.

In this way, when the user forgets to turn on the basketball mode while playing basketball, or the professional sports mode that is turned on is wrongly selected, the device body 110 can adaptively turn on the basketball mode to monitor the user's overall actions and sports data when playing basketball this time to assist The user improves the ability to play basketball. Moreover, when the user forgets to end the basketball mode after starting the basketball mode, the device main body 110 can end the basketball mode adaptively, thereby reducing the power consumption of the device main body 110.

In addition to the aforementioned monitoring of user operations on the touch control 112 and receiving instructions sent by the electronic device to turn on or end the basketball mode, and adaptively turn on or end the basketball mode, the wearable device 100 can also turn on or end basketball in other ways. Mode, such as turning on or ending the basketball mode through somatosensory gestures.

The following describes the implementation process of the device main body 110 calculating the user's exercise data.

When the basketball mode is turned on, the accelerometer, gyroscope, and microphone in the device main body 110 are all in working state. Among them, the microphone, accelerometer and gyroscope can respectively collect sound wave signals and the acceleration signals and angular velocity signals of the user on the feet.

The device body 110 can process the aforementioned acceleration signal and the aforementioned angular velocity signal to monitor the user's single-step gait characteristics, and then calculate the user's movement data such as the flight time, vertical jump height, and movement speed of the user.

In a possible implementation manner, when the acceleration signal and the angular velocity signal are obtained, the main body of the device can perform waveform feature detection on the waveform of the acceleration signal and the angular velocity signal to obtain the waveform feature of the acceleration signal and the angular velocity signal. According to the waveform characteristic of the acceleration signal and the waveform characteristic of the angular velocity signal, the device main body 110 can detect the moment when the user leaves the place and touches the place. Based on the time of departure and touchdown, the device body 110 can calculate the user's flight time. Wherein, the flight time of the user in a vertical jump may be the time interval between consecutive departures and touchdowns. Based on the integration of the acceleration change in the time interval between the departure point and the touch point, the device main body 110 can calculate the vertical jump height of the user. Utilizing the waveform characteristics of the acceleration signal, the device main body 110 can integrate the acceleration to obtain the user's moving speed. According to the integral of the movement speed change, the device main body 110 can obtain the movement distance of the user. The embodiments of the present application do not limit the above-mentioned methods for calculating the user's flight time, vertical jump height, and movement speed, and other motion data can also be used to calculate the user's flight time, vertical jump height, and other signals collected by accelerometers and gyroscopes. The method of movement data such as movement speed.

The device main body 110 can process the above-mentioned sound wave signals, use a trained Gaussian mixture model to distinguish between the sound wave signals belonging to the user's dribbling and the sound wave signals belonging to the user not dribbling, and then calculate the dribbling time and the number of dribbles.

The principle and training process of the Gaussian mixture model are introduced below.

Gaussian mixture model: The Gaussian mixture model is a probability statistical model, which can describe the statistical distribution of the characteristic parameters of the acoustic signal through the linear weighted combination of the Gaussian probability density function. The average vector of each Gaussian distribution in the Gaussian mixture model can represent a type of acoustic signal generated by dribbling or no dribbling, and the covariance matrix of each Gaussian distribution can represent the variability of the acoustic signal category. The acoustic signals generated by dribbling and without dribbling are different in the value of characteristic parameters (such as energy, frequency, peak value, etc.), so the distribution of different types of acoustic signals can be established according to these different characteristic parameter values. These different distributions can be used to distinguish acoustic signals generated by dribbling and non-dribbling.

In the embodiment of the present application, the trained Gaussian mixture model used by the device main body 110 may be a dribbling Gaussian mixture model. The dribbling Gaussian mixture model means that each individual Gaussian distribution in the mixture model represents a distribution of acoustic signals generated by dribbling. According to the difference in the size of the characteristic parameter value, the acoustic wave signal can be divided into the acoustic wave signal produced by dribbling and the acoustic wave signal produced by no dribbling. Furthermore, the acoustic wave signal produced by the dribbling depends on the difference in the magnitude of the characteristic parameter value. It can also be divided into multiple categories. The multiple Gaussian distributions included in the dribbling Gaussian mixture model are the distributions of different types of acoustic signals generated by the dribbling. The device main body 110 may perform similarity matching calculation between the characteristic parameters of the collected sound wave signal and the trained Gaussian mixture model of dribbling to determine whether the sound wave signal is a sound wave signal generated by dribbling.

The above-mentioned dribbling Gaussian mixture model can be obtained by training using acoustic signals generated by dribbling.

In a possible implementation manner, the device main body 110 may perform audio signal processing on the sound wave signal generated by dribbling, so as to realize the framing and multi-dimensional feature parameter extraction of the sound wave signal. The dimension of the above-mentioned multi-dimensional characteristic parameter may be M, which may include characteristic parameters such as energy, frequency, and peak value of the acoustic signal. M is a positive integer. For the above audio signal processing process, reference may be made to the audio signal processing method in the prior art, which is not described in detail in the embodiment of the present application. The embodiments of the present application do not specifically limit the parameters included in the above-mentioned multi-dimensional feature parameters.

The device main body 110 may establish a dribbling Gaussian mixture model. The dribbling Gaussian mixture model may include N individual Gaussian distributions, and one of the Gaussian distributions may represent the distribution of an acoustic signal generated by the dribbling. The dribbling Gaussian mixture model can be expressed with N M-dimensional Gaussian probability density functions linearly weighted, and the expression can be as shown in formula (1):

Among them, X = (x ₁ ,...,x _j ,...,x _M ) can represent the M-dimensional feature parameters of the acoustic signal, and ω _i can represent the weight of the i-th Gaussian probability density function, and

f _i (X) can represent the Gaussian probability density function of the i-th Gaussian distribution, where i=1,...,N. The expression of f _i (X) can be as shown in formula (2):

Among them, μ _i and C _i are the mean vector and covariance matrix of the i-th Gaussian probability density function, respectively.

When the M-dimensional characteristic parameters of the acoustic signal generated by the dribble are obtained, the device body 110 can use these M-dimensional characteristic parameters to train the dribbling Gaussian mixture model to obtain the dribbling Gaussian mixture model parameters λ={ω _i ,μ _i ,C _i }'s optimal solution.

In a possible implementation manner, the main body 110 of the device may use an iterative calculation of an expectation maximization algorithm to estimate the optimal solution of the above-mentioned parameter λ.

The distribution of the acoustic signal used to train the dribbling Gaussian mixture model specifically belongs to which Gaussian distribution in the dribbling Gaussian mixture model is unknown. The expectation maximization algorithm first assumes the initial value of the parameter λ, that is, the acoustic signal used for training. The information of which Gaussian distribution in the dribbling Gaussian mixture model belongs to is known. Then, a desired step is performed. The desired step is to calculate which Gaussian distribution in the dribbling Gaussian mixture model the acoustic signal used for training is generated according to the value of the parameter λ, that is, to classify the data used for training. Then, a maximization step is performed according to the classification result. The maximization step represents the maximum likelihood estimation of the parameter λ, that is, the value of the parameter λ is updated. Repeat the desired step and maximize step above. When the value of the parameter λ converges, the device body 110 can stop the training process, and use the value obtained from the last update of the parameter λ as the optimal solution of the parameter λ, so that a trained Gaussian mixture model of dribbling can be obtained.

The value convergence of the above parameter λ may mean that the difference between the parameter λ that is updated in two consecutive maximization steps is smaller than the set threshold, that is, the value of the parameter λ can be considered to be stable.

The following describes the implementation process of the device main body 110 using the trained dribbling Gaussian mixture model to determine whether the user is dribbling.

When the trained dribbling Gaussian mixture model is obtained, the device main body 110 can use the trained dribbling Gaussian mixture model to distinguish the acoustic wave signal generated by the dribble and the acoustic wave signal generated by no dribble among the acoustic signals collected by the microphone. Exemplarily, the device main body 110 performs audio signal processing on the sound wave signal collected by the microphone to obtain the M-dimensional characteristic parameter X=(x ₁ ,..., x _j ,..., x _M ) of a certain frame of the sound wave signal. According to the characteristic parameter X, the device main body 110 can perform similarity matching calculation between this frame of sound wave signal and the trained Gaussian mixture model of dribbling. Wherein, the device main body 110 can calculate the posterior probability generated by the i-th Gaussian distribution in the dribbling Gaussian mixture model under the condition that the M-dimensional characteristic parameters of this frame of acoustic signal are known. The specific calculation formula can be as shown in formula (3):

Then the sound wave signal of this frame is generated by the N Gaussian distribution in the dribbling Gaussian mixture model, and the sum of the posterior probabilities is

The above-mentioned probability sum Q can indicate the similarity between the sound wave signal of this frame and the Gaussian mixture model of dribbling. The device body 110 can set a matching threshold. When the above-mentioned sum of posterior probabilities Q is greater than the matching threshold, the device main body 110 can determine that the sound wave signal of this frame is the sound wave signal generated by dribbling. Otherwise, the device main body 110 can determine that the sound wave signal of this frame is a sound wave signal generated by no dribbling. The embodiment of the present application does not specifically limit the size of the matching threshold.

The embodiment of the present application does not limit the calculation method of the above-mentioned similarity matching, and may also be other similarity matching methods.

Further, when judging the sound wave signal generated by the dribble, the device main body 110 can calculate the total dribbling time of the user during one basketball game, that is, the sum of the time of the sound wave signal generated by the dribble in each frame.

The main body 110 of the device can calculate the total number of dribbles that the user has in one basketball game, that is, the number of frames of the sound wave signal generated by the dribble. Wherein, when the sonic signal of the user playing basketball is divided into frames, the device main body 110 can determine the length of a frame of sonic signal according to the frequency of dribbling by a general user. For example, the length of a frame of sonic signal can be 500 milliseconds. When it is determined that a certain frame of sound wave signal is a sound wave signal generated by a dribble, the device body 110 can determine that the user has performed a dribble, that is, the number of frames of the sound wave signal generated by the dribble is the process of the user playing basketball at one time. The total number of dribbles.

The dribbling Gaussian mixture model is a linear weighted combination of multiple Gaussian probability density functions, and the linear weighted combination of several Gaussian probability density functions can approximate an arbitrary distribution, so the dribbling Gaussian mixture model can be used to describe the sound waves generated by the dribble Signal distribution. In this way, the device main body 110 can use the dribbling Gaussian mixture model to determine whether the user dribbles. Combining the user's foot movement obtained by analyzing the acceleration signal and the angular velocity signal, the device main body 110 can monitor the user's overall movement when playing basketball (such as dribbling in place, running dribbling, running without the ball, etc.), So as to better assist users to improve their ability to play basketball.

The embodiment of the application does not limit the method of processing the acoustic signal to determine whether the user is dribbling. In addition to the algorithm of the Gaussian mixture model, the algorithm of the hidden Markov model or the neural network algorithm can also be used for other acoustic signal recognition. algorithm.

Fig. 5 shows a flow chart of a method for monitoring the overall actions of a user when playing basketball.

As shown in Fig. 5, the method may include steps S101 to S105. in:

S101. The device main body 110 collects acceleration signals, angular velocity signals, and sound wave signals.

When the basketball mode is turned on, the microphone, accelerometer, and gyroscope in the device main body 110 can respectively collect the sound wave signal when the user is playing basketball, and the acceleration signal and angular velocity signal of the user's foot.

S102. The device main body 110 performs waveform feature detection on the acceleration signal and the angular velocity signal to obtain the waveform characteristics of the acceleration signal and the angular velocity signal; the device main body 110 performs audio signal processing on the acoustic wave signal to obtain the characteristic parameter of the acoustic wave signal.

The aforementioned audio signal processing may include framing and feature parameter extraction of the sound wave signal. The device body 110 can determine the length of a frame of sound wave signal according to the frequency of dribbling by a general user. Exemplarily, it takes 500 milliseconds for a general user to dribble once, so when the device main body 110 divides the sound wave signal into frames, the sound wave signal may be divided into 500 milliseconds as one frame. In this way, if it is determined that a frame of sound wave signal is a sound wave signal generated by dribbling, the device main body 110 can determine that the user dribbles once. It should be noted that the above-mentioned user dribbling once may indicate that the user with the ball slaps and presses the basketball once in the process of staying or moving, and the basketball is bounced off the ground.

The main body 110 of the device may extract characteristic parameters of each frame of acoustic signal, and the extracted parameters may include M-dimensional characteristic parameters such as energy, frequency, and peak value of the acoustic signal of this frame. The above M is a positive integer.

S103. The device main body 110 performs similarity matching calculation on the characteristic parameters of the acoustic signal and the Gaussian mixture model of the dribble, and determines the acoustic signal generated by the dribble.

The dribbling Gaussian mixture model can include N individual Gaussian distributions. Each Gaussian distribution can represent a type of acoustic signal generated by dribbling. The device main body 110 can calculate the posterior probability generated by the i-th Gaussian distribution in the dribbling Gaussian mixture model under the condition that the M-dimensional characteristic parameters of a frame of acoustic signal are known according to formula (3). In this way, the device main body 110 can obtain the sum Q of posterior probabilities generated by the N Gaussian distributions in the dribbling Gaussian mixture model of this frame of acoustic signal. in

It can indicate the similarity between the sound wave signal of this frame and the Gaussian mixture model of dribbling.

The device body 110 can set a matching threshold. When the above-mentioned sum of posterior probabilities Q is greater than the matching threshold, the main body 110 of the device may determine that this frame of sound wave signal is a sound wave signal generated by dribbling. The embodiment of the present application does not specifically limit the size of the matching threshold.

S104. The device main body 110 calculates the flight time, vertical jump height, moving speed and movement distance according to the waveform characteristics of the acceleration signal and the angular velocity signal; the device main body 110 calculates the dribbling time and the number of dribbles according to the sound wave signal generated by the dribble.

According to the waveform characteristic of the acceleration signal and the waveform characteristic of the angular velocity signal, the device main body 110 can detect the moment when the user leaves the place and touches the place. Based on the time of departure and touchdown, the device body 110 can calculate the user's flight time. Wherein, the flight time of the user in a vertical jump may be the time interval between consecutive departures and touchdowns. Based on the integration of the acceleration change in the time interval between the departure point and the touch point, the device main body 110 can calculate the vertical jump height of the user. Utilizing the waveform characteristics of the acceleration signal, the device main body 110 can integrate the acceleration to obtain the user's moving speed. According to the integral of the movement speed change, the device main body 110 can obtain the movement distance of the user. Not limited to the above-mentioned flight time, vertical jump height, moving speed and moving distance, the device main body 110 can also calculate other users' walking, running and jumping motion data on the feet according to the waveform characteristics of the acceleration signal and the angular velocity signal.

According to the sound wave signal generated by the dribble in each frame, the device main body 110 can calculate the total dribbling time and the number of dribbles in the process of one basketball play by the user. Among them, the dribbling time can be the sum of the time of the sound wave signal generated by the motion in each frame. The number of dribbles may be the number of frames of the sound wave signal generated by the dribble.

In addition to calculating the above-mentioned flight time, vertical jump height, movement speed, movement distance, dribbling time, and number of dribbles, the device main body 110 can also calculate movement data such as the number of steps moved by the user and the calories consumed. The embodiment of the present application does not limit the type of exercise data calculated by the device main body 110. The method of calculating the number of steps moved and the calories consumed by the user can refer to the calculation method of the prior art, which is not described in detail in the embodiment of the present application.

S105. Classify the user's basketball actions into dribbling actions and non-dribbling actions.

Combining the action on the user's foot at the same time and the analysis result of whether the user is dribbling, the device main body 110 can classify the user's basketball action into a dribbling action and a non-dribbling action.

The aforementioned dribbling action may include dribbling in place and running dribbling. in:

In-place dribble: If several consecutive frames of sound wave signal belong to the sound wave signal generated by dribbling, and the moving speed approaches 0 or less than the preset first speed threshold (the first 1 speed), or within the time period corresponding to several consecutive frames of sound wave signals, the movement distance approaches 0 or is less than the preset first distance threshold (first distance), the device body 110 can determine that the user is not moving on the basketball court , So as to determine that the user's action during this time period is a dribble on the spot.

Running dribbling: If several consecutive frames of sound wave signal belong to the sound wave signal generated by dribbling, and the moving speed is greater than the preset second speed threshold (second speed) during the time period corresponding to the consecutive frames of sound wave signal, or The movement distance during the time period corresponding to these consecutive frames of sound wave signals is greater than the preset second distance threshold (second distance). The device main body 110 can determine that the user is running on the basketball court, thereby determining the user's movement in this time period. The action is a running dribble.

It should be noted that the first speed threshold is less than or equal to the second speed threshold, and the first distance threshold is less than or equal to the second distance threshold.

It is not limited to in-situ dribbling and running dribbling. The dribbling action can also include more categories, which are not limited in the embodiment of the present application.

The aforementioned actions without dribbling may include running without the ball, vertical jump without the ball, running pass and vertical jump shot. in:

Running without the ball: If several consecutive frames of sound wave signals belong to the sound wave signals generated by no dribbling, and the moving speed is greater than the second speed threshold or the movement distance is greater than the second distance threshold during the time period corresponding to the consecutive frames of sound wave signals, The device main body 110 may determine that the user's action during this period of time is running without a ball. In the basketball rules, when a player has a ball in his hand and wants to move on the basketball court, he must move while dribbling the ball, but cannot move the basketball on the basketball court in his hand. In this way, when it is determined that the user does not dribble and the moving speed on the basketball court is high, the device main body 110 can determine that the user's action is running without the ball. Wherein, the above-mentioned second speed threshold may be determined according to the running speed of a general user when playing basketball. Exemplarily, a general user runs at a speed of 2 kilometers per hour when playing basketball. When several consecutive frames of acoustic signals belong to acoustic signals generated by no dribbling, and the moving speed is greater than 2 kilometers per hour during the time period corresponding to these consecutive frames of acoustic signals, the main body 110 of the device can determine the user’s The action is to run without the ball. The embodiment of the present application does not limit the specific value of the foregoing second speed threshold. The above-mentioned second distance threshold may also be determined according to the movement distance of the general user during the basketball running time period. Exemplarily, when a general user is playing basketball and running, the movement distance in a time period corresponding to each frame of sound wave signal (for example, 500 milliseconds) is 0.3 meters. When several consecutive frames of sound wave signals belong to the sound wave signal generated by dribbling or not, and the user's movement distance in the time period corresponding to each frame of the sound wave signal in these consecutive frames is greater than 0.3 meters, the device main body 110 can determine the supply The user's action during this time period is running without the ball. The embodiment of the present application does not limit the specific value of the foregoing second distance threshold.

No ball vertical jump: If several consecutive frames of sound wave signal belong to the sound wave signal generated by no dribbling, the consecutive frames of the sound wave signal before the continuous frame sound wave signal also belong to the sound wave signal generated by no dribble, and there are several consecutive frames here. The vertical jump height in the time period corresponding to the frame sound wave signal is not 0 or greater than the preset height threshold (first height), and the device main body 110 may determine that the user's action in this time period is a ballless vertical jump. The above-mentioned height threshold may be determined according to the minimum height of a general user jumping upwards when playing basketball. Exemplarily, the minimum height for a general user to jump upwards when playing basketball is 10 cm. The device body 110 may preset the height threshold to 10 cm. When the user's vertical jump height is greater than 10 cm, the device main body 110 can determine that the user has made an upward jump. The embodiment of the present application does not limit the specific data of the above-mentioned height threshold.

Running and throwing: If several consecutive frames of sound wave signal belong to the sound wave signal generated by no dribbling, the consecutive frames of the sound wave signal before these consecutive frames of sound wave signal also belong to the sound wave signal generated by no dribbling, and these consecutive frames During the time period corresponding to the sound wave signal and several consecutive frames of the sound wave signal before it, the moving speed is greater than the second speed threshold or the moving distance is greater than the second distance threshold. The device body 110 can determine that the user's action during this time period is running and throwing. . According to the change of the sound wave signal, the user's action changes from dribbling to no dribbling, and the device main body 110 can determine that the user has made a pass or a shot. During this time period, the user made a running action. In this way, the device main body 110 can determine that the user's action during this period of time is a running shot.

Longitudinal jump shot: If several consecutive frames of sound wave signal belong to the sound wave signal generated by no dribbling, the consecutive frames of the sound wave signal before the continuous frame sound wave signal belong to the sound wave signal generated by dribbling, and there are several consecutive frames of sound wave signal. The vertical jump height within the time period corresponding to the signal and several consecutive frames of sound wave signals before it is not 0 or exceeds a preset height threshold, and the device body 110 can determine that the user's action in this time period is a vertical jump shot. According to the change of the sound wave signal, the user's action changes from dribbling to no dribbling, and the device main body 110 can determine that the user has passed or shot the ball. During this time period, the user made an upward jump. In this way, the device main body 110 can determine that the user's action during this time period is a vertical jump shot.

It is not limited to running without the ball, vertical jump without the ball, running pass and vertical jump pass, and the action without dribbling may also include more categories, which are not limited in the embodiments of the present application.

The device main body 110 may monitor the user's actions when playing basketball, and classify the user's actions when playing basketball. In this way, according to the user's actions when playing basketball, the device main body 110 can provide the user with exercise suggestions to assist the user in improving the ability of playing basketball. Exemplarily, a long time for the user to dribble in place may indicate that the user is easily hindered by others when playing basketball and has weak offensive ability. When it is detected that the user has dribble in place for a long time, the device main body 110 may display sports suggestions for improving the offensive ability of playing basketball through the electronic device.

The following describes another implementation method for obtaining a trained dribble Gaussian mixture model.

In some embodiments, the device main body 110 may first pre-collect the acoustic signal generated by the user's dribbling. Using the pre-collected sound wave signal, the device main body 110 can train a dribbling Gaussian mixture model. Part of the Gaussian distribution in the trained dribble Gaussian mixture model has a relatively large weight. This part of the Gaussian distribution may be the Gaussian distribution that generates the acoustic signal generated by the user's dribbling. In this way, the trained dribbling Gaussian mixture model can be used to more accurately determine the acoustic signal generated by the user's dribbling, and reduce the influence of the acoustic signal generated by the dribbling of others on the calculation of the user's dribbling time and the number of dribbles and other sports data.

According to the above-mentioned another implementation method for obtaining a trained dribble Gaussian mixture model, FIG. 6 shows a flowchart of another method for monitoring the overall actions of the user when playing basketball.

As shown in Fig. 6, the method may include steps S201 to S207. in:

S201: Pre-collect the acoustic signal generated by the user's dribbling.

Pre-collecting the sound wave signal generated by the user's dribbling may be that the device main body 110 enters personal dribbling data before the basketball mode is turned on for the first time, that is, the sound wave signal generated by the user's dribble is entered.

When the user uses the wearable device 100 to turn on the basketball mode for the first time, the user needs to record the sound wave signal generated by the personal dribble first. That is, the personal dribbling data entry is first turned on, the wearable device 100 is buckled on the shoe, and dribbling actions such as in-situ dribbling or running dribbling are performed. After the personal dribble data entry is over, the user can turn on the basketball mode to monitor the personal basketball sports data.

S202: Train the dribbling Gaussian mixture model by using the pre-collected acoustic signal to obtain the user's dribbling Gaussian mixture model.

When the pre-collected acoustic wave signal is obtained, the device main body 110 may perform audio signal processing on the pre-collected acoustic wave signal to obtain the M-dimensional characteristic parameters of the pre-collected acoustic wave signal. The dribbling Gaussian mixture model is trained by using the pre-collected M-dimensional feature parameters of the acoustic signal, and the device main body 110 can obtain the user's dribbling Gaussian mixture model. The user's dribbling Gaussian mixture model can be used to more accurately determine the sound wave signal generated by the user's dribble.

S203. Collect acceleration signals, angular velocity signals, and sound wave signals.

S204: Perform waveform feature detection on the acceleration signal and the angular velocity signal to obtain waveform features of the acceleration signal and the angular velocity signal; perform audio signal processing on the acoustic wave signal to obtain characteristic parameters of the acoustic wave signal.

S205: Perform similarity matching calculation between the characteristic parameters of the acoustic signal and the Gaussian mixture model of the user's dribble, and determine the acoustic signal generated by the dribble belonging to the user.

S206: Calculate the flight time, vertical jump height, movement speed and movement distance according to the waveform characteristics of the acceleration signal and the angular velocity signal; calculate the dribbling time and the number of dribbles according to the acoustic wave signal generated by the dribble.

S207. Classify the user's basketball action into a dribbling action and an action without dribbling.

For the above steps S203 to S207, reference may be made to steps S101 to S105, which will not be repeated here.

The following describes a way for the device main body 110 to prompt the user to enter personal dribbling data when the basketball mode is first turned on.

When the basketball mode is turned on for the first time and the user's personal dribbling data is not monitored, the device main body 110 may prompt the user to enter the personal dribbling data.

In some embodiments, when the user operation for turning on the basketball mode on the device body 110 as shown in FIG. 2 is monitored, and the user's personal dribbling data is not monitored, the device body 110 may be displayed on the display screen 111. The user interface 310 as shown in (A) in FIG. 7 is displayed on the top. The user interface 310 may be used to prompt the user to enter personal dribble data. The user interface 310 may include a determination option 311 and a cancellation option 312. in:

The determination option 311 can be used for personal dribbling data entry. In response to a user operation acting on the determination option 311, such as a touch operation, the device main body 110 may display a user interface 320 as shown in (B) of FIG. 7 on the display screen 111. The content on the determination option 311 may be "Yes", "OK" or other content, which is not specifically limited in the embodiment of the present application.

The cancel option 312 can be used to cancel personal dribble data entry. In response to a user operation on the cancel option 313, such as a touch operation, the device main body 110 may display an icon of a basketball as shown in FIG. 2 and the text "basketball mode" on the display screen 111.

That is, if the user currently wants to enter personal dribbling data, the user can touch the OK option 311. If the user currently does not want to enter personal dribble data, the user can touch the cancel option 312.

When a user operation for determining an option is monitored, the device main body 110 displays a user interface 320 as shown in (B) of FIG. 7 on the display screen 111. The user interface 320 may be used for the user to select the length of time for the personal dribble data entry. The user interface 320 may include a time option 321. in:

The time option 321 may include a 3-minute option, a 5-minute option, and a 10-minute option. This embodiment of the present application does not limit this, and the time option 321 may include more or fewer options. In response to a user operation acting on any one of the time options 321, such as a touch operation, the device main body 110 may display a user interface 330 as shown in (C) in FIG. 7 on the display screen 111. Exemplarily, when a user operation acting on the 5-minute option is monitored, the device main body 110 may display the user interface 330 and end the personal dribble data entry 5 minutes after the start of the personal dribble data entry.

As shown in (C) in Figure 7, the user interface 330 can be used to prompt the user device main body 110 to start the personal dribble data entry mark, and the need to do dribble in the personal dribble data entry time to run dribbling The act of dribbling the ball.

When a user operation acting on any one of the time options 321 is detected, the device main body 110 displays the user interface 330 and generates vibration. When the vibration is over, the device main body 110 starts to record personal dribbling data, where the microphone in the device main body 110 starts to collect sound wave signals. The device main body 110 can train the dribbling Gaussian mixture model by using the acoustic signal collected during the personal dribbling data entry period to obtain the trained user's dribbling Gaussian mixture model.

The embodiment of the present application does not limit the manner in which the device main body 110 starts the personal dribbling data entry and ends the personal dribble data entry. In addition to expressing the start and end of personal dribbling data entry by means of vibration, other methods can also be used.

When it is monitored that the length of time corresponding to the option selected in the time option 321 has elapsed since the start of personal dribbling data entry, the device body 110 may vibrate and display on the display screen 111 as shown in (D) in FIG. 7 User interface 340. The user interface 340 may be used to prompt the user to complete the entry of personal dribbling data.

Among them, when the user is entering personal dribbling data, that is, when the user is doing dribbling and running dribbling, it is inconvenient for the user to directly see the content on the display screen 111. The main body 110 of the device may vibrate to remind the user that the personal dribbling data entry is complete. In this way, the user can stop dribbling actions such as in-place dribbling and running dribbling after the device main body 110 vibrates.

The following describes another way for the device main body 110 to prompt the user to enter the personal dribble data when the basketball mode is turned on for the first time.

In some embodiments, when the electronic device detects the user's operation on the turn-on button 224b as shown in Figure 4(C), and does not detect the user's personal dribbling data, the electronic device may prompt the user to perform personal Entry of dribble data.

When the user operation of the open button 224b for starting the basketball mode on the application interface 220 is monitored, and the user's personal dribbling data is not monitored, the electronic device can display the application interface 220 as shown in FIG. 8 ( A) The dialog box 230 shown. The dialog box 230 may be used to prompt the user to enter personal dribble data. The dialog box 230 may include a confirm option 231 and a cancel option 232. in:

The determination option 231 can be used for personal dribbling data entry. In response to a user operation acting on the determination option 231, such as a touch operation, the electronic device may display a dialog box 240 as shown in (B) of FIG. 8 on the application interface 220.

The cancel option 232 can be used to cancel personal dribble data entry. In response to a user operation acting on the cancel option 232, such as a touch operation, the electronic device may display the application interface 220.

That is, if the user currently wants to enter personal dribble data, the user can touch the confirm option 231. If the user does not currently want to enter personal dribble data, the user can touch the cancel option 232.

As shown in (B) of FIG. 8, the electronic device displays a dialog box 240 on the application interface 220. The dialog box 240 can be used for the user to select the length of time for the personal dribble data entry. The dialog box 240 may include a time option 241. in:

The time option 241 may include a 3-minute option, a 5-minute option, and a 10-minute option. This embodiment of the present application does not limit this, and the time option 241 may include more or fewer options. In response to a user operation acting on any one of the time options 241, such as a touch operation, the electronic device may display a dialog box 250 as shown in (C) in FIG. 8 on the application interface 220, and send a start to the device main body 110 An instruction to input personal dribble data and the time corresponding to the selected option in the time option 241, for example, 5 minutes.

As shown in (C) in FIG. 8, the electronic device displays an operation prompt box 250 on the application interface 220. The operation prompt box 250 can be used to prompt the user device main body 110 to start the mark of personal dribbling data entry, and to perform dribbling actions such as in-place dribble and running dribble within the entry time of personal dribble data.

When receiving an instruction to start personal dribbling data entry and the time corresponding to the selected option in the time option 241, the device main body 110 can vibrate and start personal dribbling data entry after the vibration ends. That is, the device main body 110 starts to collect the sound wave signal, and uses the sound wave signal collected during the personal dribble data entry period to train the dribbling Gaussian mixture model to obtain the trained user's dribble Gaussian mixture model. After the time corresponding to the selected option in the time option 241, the device main body 110 ends the personal dribble data entry. The main body 110 of the device may vibrate and display the user interface 340 as shown in (D) in FIG. 7 on the display screen 111 to prompt the user to complete the input of personal dribbling data.

The following describes an embodiment in which the main body of the device can enter the personal dribble data multiple times.

In some embodiments, the device main body 110 may enter personal dribbling data multiple times. The main body 110 of the device can train the dribbling Gaussian mixture model by using the acoustic signals collected during each personal dribbling data entry, thereby adjusting the user's dribbling Gaussian mixture model, and improving the user's dribbling Gaussian mixture model for judging whether the user is dribbling or not. The accuracy of the ball.

As shown in (A) in FIG. 9, the application interface 220 of the electronic device may include a dribble data entry 225. In response to a user operation on the dribble data entry 225, such as a touch operation, the electronic device may display an application interface 260 as shown in (B) of FIG. 9.

The application interface 260 may be used for the user to select the length of time for entering personal dribble data, and the application interface 260 may include a time option 261. The time option 261 may include a 3-minute option, a 5-minute option, and a 10-minute option. This embodiment of the present application does not limit this, and the time option 261 may include more or fewer options. In response to a user operation acting on any one of the time options 261, such as a touch operation, the electronic device may display an application interface 270 as shown in (C) in FIG. 9 and send data to the device main body 110 to start personal dribbling The entered instruction and the time corresponding to the selected option in the time option 261, for example, 5 minutes.

As shown in (C) in Figure 9, the application interface 270 can be used to prompt the user device main body 110 to start the personal dribbling data entry mark, and the need to do dribble and running dribble within the entry time of the personal dribble data. The act of dribbling the ball.

When the device main body 110 receives an instruction to start personal dribbling data entry and the time corresponding to the selected option in the time option 261, the device main body 110 can start the personal dribble data entry after shaking. When the time corresponding to the selected option in the time option 261 has elapsed, the device main body 110 may vibrate and end the personal dribble data entry.

The characteristic parameters such as energy, frequency and peak value of the acoustic signal generated by different users dribble are different. The device main body 110 pre-collects the acoustic signal generated by the user dribbling to train the dribbling Gaussian mixture model, and can obtain the dribbling Gaussian mixture model suitable for monitoring whether the user dribbles. In this way, it is possible to reduce the probability of judging the sound wave signal generated by another person's dribbling as the sound wave signal generated by the user dribbling, thereby improving the accuracy of judging whether the user is dribbling the ball. Moreover, in addition to pre-collecting the sound wave signal generated by the user's dribbling before the basketball mode is turned on for the first time, the main body 110 of the device can also enter personal dribbling data multiple times. The device main body 110 can train the dribbling Gaussian mixture model by using the acoustic signals collected during the personal dribbling data input multiple times, thereby adjusting the user's dribbling Gaussian mixture model multiple times to improve the accuracy of judging whether the user is dribbling. When the user believes that the exercise data recorded by the device main body 110 is significantly different from personal cognition, the user can re-enter the personal dribble data. In this way, the user experience can be improved.

The following describes the implementation process of the device main body 110 determining the user's number position on the basketball court.

In some embodiments, the device main body 110 may determine the user's number position on the basketball court according to the user's motion data. Wherein, the above-mentioned user's sports data may include movement distance, movement speed, vertical jump height, number of dribbles, and dribbling time. According to the rules of the basketball game, users' positions on the basketball court can be divided into five positions: point guard, shooting guard, center, small forward, and power forward.

Different numbers on the basketball court have different division of labor and different play styles, so the value ranges of the corresponding sports data are different. For example, the point guard is responsible for organizing offenses, launching tactics, and distributing the ball appropriately. The point guard has more dribbles and moves faster. The small forward is responsible for long-range shots, mid-range shots, low singles, fast breaks, and breakthroughs in the opponent's defense, creating scoring opportunities for teammates. The small forwards have more dribbles and vertical jumps.

The general range corresponding to the user when a certain number of bits in the basketball court motion data, the device body 110 may be stored in a template library bit number y _a (k). The value of a can be 1, 2, 3, 4, and 5, which can represent point guard, shooting guard, center, small forward, and power forward, respectively. k can represent the kth index. This indicator represents a kind of sports data, such as the distance of movement, the speed of movement, the height of vertical jump, the number of dribbles, and the time of dribbling. k=1,2,...,K. K is a positive integer, and the embodiment of the present application does not limit the value of K, and there may be multiple indexes used to measure a number position in the number position template library.

According to the number position template library y _a (k), the device main body 110 can template match various sports data of the user during a basketball game with the index of each number position in the number position template library. According to the template matching result, the main body of the device can determine the user's number position when playing basketball this time. The above-mentioned playing basketball may represent a continuous process of the device main body 110 from starting the basketball mode to ending the basketball mode.

In a possible implementation manner, the method for the main body of the device to perform template matching may be to calculate the correlation coefficient between various sports data of the user during a basketball game and the index of each number position in the number position template library. Among them, the number position corresponding to the largest correlation coefficient is the number position of the user playing basketball this time. Specifically, the device main body 110 may perform normalization processing on the indicators in the number position template library to eliminate the dimensional influence between different indicators. The above normalization formula can be as shown in formula (4):

When the index for normalization processing is obtained, the device body 110 can perform template matching, that is, calculate the correlation coefficient between the various sports data of the user during a basketball game and the index of each number position in the number position template library, and select the largest The number position corresponding to the correlation coefficient. The template matching rule can be as shown in formula (5):

Among them, R(a,b) can represent the correlation coefficient between the index of the a-th number position in the number position template library and various sports data recorded when the device main body 110 turns on the basketball mode for the bth time.

It can represent the mean value of the k-th index of the 5 number positions in the number position template library. which is

G _b (k) may represent the kth movement data recorded when the device main body 110 turns on the basketball mode for the bth time. The aforementioned k-th index is the same as the aforementioned k-th motion data. For example, distance of movement, speed of movement, height of vertical jump, number of dribbles and dribbling time, etc. Wherein, the movement speed recorded when the device main body 110 turns on the basketball mode for the bth time may be an average movement speed or a maximum movement speed, etc., and the vertical jump height may be an average vertical jump height or a maximum vertical jump height, etc. This embodiment of the application does not limit this.

It can represent the average value of the k-th motion data when the basketball mode is turned on for the bth time by the main body of the device and the k-th motion data when the basketball mode is turned on for the c times before the basketball mode is turned on for the b-th time. Exemplarily, when the value of b is 5 and the value of c is 3,

It can represent the average value of the k-th exercise data recorded when the device main body 110 turns on the basketball mode for the second time, the third time, the fourth time, and the fifth time. C is a positive integer. The embodiment of the present application does not limit the specific value of c.

When the correlation coefficients between the various sports data of the user playing basketball at one time and the indicators of the 5 number positions in the number position template library are obtained, the main body 110 of the device can determine that the number position of the user playing basketball corresponds to the largest correlation coefficient. Number position.

The embodiment of the present application does not limit the method for template matching. In addition to template matching based on correlation coefficients, other methods for template matching can also be used.

According to the above-mentioned determination of the user's number position on the basketball court, the device main body 110 can display the user's performance on this number position and provide the user with training suggestions for this number position. This can better assist users to improve their ability to play basketball.

According to the signals collected by the accelerometer, gyroscope, and microphone, the device main body 110 can calculate multiple sports data of the user when playing basketball. When multiple sports data is obtained, the device main body 110 may send the multiple sports data to the electronic device. The electronic device can display the multiple sports data on the application interface.

The following introduces some application interfaces for electronic devices to display these multiple sports data.

In response to a user operation, such as a touch operation, acting on the motion data 223 as shown in (C) in FIG. 4, the electronic device may display an application interface 410 as shown in (A) in FIG. 10. The application interface 410 may include basketball movement data 411 and running movement data. The application interface 410 may also include other types of motion data, which is not limited in the embodiment of the present application.

In response to a user operation, such as a touch operation, acting on the basketball movement data 411, the electronic device may display an application interface 420 as shown in (B) of FIG. 10. The application interface 420 may include a return control 421, a chart control 422, a detail control 423, a vertical jump height 424, and a flight time 425. in:

The return control 421 can be used to return to the upper level interface of the application interface 420. In response to a user operation on the return control 421, such as a touch operation, the electronic device may display the application interface 410.

The electronic device can display these multiple sports data in the form of charts or specific data analysis.

Specifically, the chart control 422 can be used to display the multiple pieces of sports data in a chart. The detail control 423 can be used to display the multiple pieces of exercise data in a specific data analysis manner. It is not limited to these two methods of displaying multiple sports data, and the electronic device can also display the multiple sports data in other ways.

In response to a user operation on the chart control 422, such as a touch operation, the electronic device may display an application interface 420 as shown in (B) of FIG. 10.

The vertical jump height 424 may include an average vertical jump height 424a, a maximum vertical jump height 424b, and a vertical jump height distribution map 424c. The average vertical jump height 424a may be the average vertical jump height of the user during a basketball game. The maximum vertical jump height 424b may be the maximum vertical jump height of the user during a basketball game. The vertical jump height distribution map 424c may use a histogram to indicate the time point of each vertical jump and the vertical jump height of the user during a basketball game.

The flight time 425 may indicate the time for the user to jump up and stay in the air. The flight time 425 may include an average flight time 425a, a maximum flight time 425b, and a flight time distribution map 425c. Wherein, the average empty time 425a may be the average empty time of the user during one basketball game. The maximum flight time 425b may be the maximum flight time of the user during one basketball game. The emptying time distribution map 425c may use a histogram to indicate the time point of each emptying time and the emptying time length of the user during a basketball game.

In response to a user operation on the detail control 425, the electronic device may display a user interface 430 as shown in FIG. 11. In response to a user operation of sliding up or down on the user interface 430, the electronic device may display the difference as shown in (A), (B), (C) and (D) in FIG. 11 on the user interface 430. Content.

As shown in (A) in FIG. 11, the application interface 430 may include a date 431, a comprehensive performance 432, and itemized sports data 433. in:

The date 431 may indicate the time when the device main body 110 recorded the exercise data contained in the current application interface 430. The date 431 may include year, month, day and time. For example, at 17:01 on January 1, 2020. That is, the movement data of the user playing basketball at this time is the movement data contained in the current application interface 430. It should be noted that the exercise data included in the application interface 420 and the exercise data included in the application interface 430 are the exercise data recorded by the device main body 110 at the same time when the basketball mode is turned on.

The overall performance 432 can be scored with a full score of 100, and the score indicates the user's overall level of playing basketball this time. The device main body 110 can obtain the user's score in the comprehensive performance 432 according to the movement data such as the vertical jump height and the moving speed. The specific calculation method may refer to the calculation method in the prior art, which is not limited in the embodiment of the present application.

The itemized sports data 433 may include sports time 433a, active time 433b, active time proportion 433c, and dribbling time 433d. In response to a user operation of sliding upward on the application interface 430 as shown in (A) in FIG. 11, the electronic device may display the application interface 430 as shown in (B), (C), and (D) in FIG. 11 . Wherein, in the application interface 430 shown in (B) of FIG. 11, the itemized exercise data 433 may also include the proportion of dribbling time 433e, the exercise distance 433f, the calories 433g, and the number of steps 433h. Wherein, the exercise time 433a may represent the length of a continuous process from when the main body 110 of the device starts the basketball mode to the end of the basketball mode. That is, the length of time the user plays basketball this time. The active time 433b can be determined according to the moving speed. The time when the user's moving speed is greater than 2 kilometers per hour can be the user's active time. The embodiment of the present application does not limit the judgment condition of the active time. The active time proportion 433c may be the ratio of the active time 433b to the exercise time 433a. The dribbling time 433d may be determined according to the length of time determined to be the sound wave signal generated by the dribbling. The dribbling time percentage 433e may be the ratio of the dribbling time 433d to the exercise time 433a. The movement distance 433f may indicate the distance moved by the user in the movement time 433a. The calories 433g may represent the calories consumed by the user during the exercise time 433a. The number of steps 433h may represent the number of steps the user moves during the exercise time 433a. The calculation method of the heat 433g and the number of steps 433h may refer to the calculation method in the prior art, which is not described in detail in the embodiment of the present application. The itemized sports data 433 may also include more sports data, which is not limited in the embodiment of the present application.

As shown in (B) of FIG. 11, the application interface 430 may also include a moving speed 434. The moving speed 434 may include a moving speed 434a, a maximum moving speed 434b, and a moving speed distribution map 534c. Wherein, the average moving speed 434a may be an average value of the moving speed of the user during one basketball game. The maximum moving speed 434b may be the maximum value of the moving speed of the user during one basketball game. The moving speed distribution map 534c may represent the proportions of the moving speeds of different sizes during a time when the user plays basketball. The embodiment of the present application does not limit the form of the change of the movement speed of the user during a basketball game. In addition to the movement speed distribution graph 534c, other methods may also be used.

As shown in (C) in FIG. 11, the application interface 430 may also include vertical jump data 435 and number position evaluation 436. in:

The vertical jump data 435 may include an average vertical jump height 435a, an average flight time 435b, and the number of vertical jumps 435c. Wherein, the average vertical jump height 435a may be the average vertical jump height of the user during a basketball game. The average flight time 435b may be the average flight time of the user during one basketball game. The number of vertical jumps 435c may be the number of times the user jumps upward during one basketball game.

The number position evaluation 436 may indicate the number position of the user on the basketball court when playing basketball this time. For example: point guard, shooting guard, center, small forward and power forward. The content of the number position evaluation 436 may be a result obtained by template matching of various sports data of the user playing basketball this time with the index of each number position in the number position template library by the main body of the device. If the correlation coefficient between the sports data of the user playing basketball this time and the indicator of the small forward in the number template library is the largest, the main body of the device can determine that the user's number on the basketball court this time playing basketball is the small forward. Then the content of the number evaluation 436 can be a small forward.

As shown in (D) in FIG. 11, the application interface 430 may also include exercise suggestions 437 and recommended training 438. Among them, the exercise suggestion 437 can be determined according to various sports data of the user playing basketball this time. Exemplarily, if the user's bounce ability is weak, the content of the exercise suggestion 437 may suggest that the user improve the bounce ability. The content of the recommended training 438 may be determined according to the sports suggestions and various sports data of the user playing basketball this time. Exemplarily, if the user's bounce ability is weak, the content of the recommended training 438 may include a training course "basketball bounce·basic strength" to improve the bounce ability. If the user's number position assessment 436 is a small forward, the content of the recommended training 438 may also include training courses such as "how to become a better small forward". The embodiment of the present application does not limit the content of the exercise recommendation 437 and the recommended training 438.

The application interface 430 may also contain more or less content, which is not limited in the embodiment of the present application.

The device main body 110 displays an application interface of exercise data.

In some embodiments, when the exercise data of the user playing basketball is obtained, the device main body 110 may display on the display screen 111 the exercise data obtained from the last time the basketball mode is turned on. Please refer to FIG. 12. FIG. 12 is a schematic diagram of a wearable device (ie, the device body 110) displaying exercise data according to an embodiment of the present application. When a user operation that acts on the left or right sliding on the application interface 520 as shown in Figure 12 is monitored, the device main body 110 can display on the application interface 520 as shown in (B), (C) and (D) in Figure 12 Show different content.

The device main body 110 may contain multiple applications, such as the application "basketball data" shown in (A) in FIG. 12. In response to a user operation of applying "basketball movement data" to the application interface 510, such as a touch operation, the device main body 110 may display the application interface 520 as shown in (B) of FIG. 12. The application interface 520 may include user information 521, exercise time 522, steps 523, and calories 524. Among them, the user information 521 may include the name of the user and the time when the device main body recently ended the basketball mode, that is, the time when the user played basketball the last time. In response to a user operation of sliding leftward on the application interface 520 as shown in (B) in FIG. 12, the device body 110 may display the application interface 520 as shown in (C) and (D) in FIG. 12. As shown in (C) and (D) in FIG. 12, the application interface 520 may also include the number of dribbles 525, the average vertical jump height 526, the average moving speed 527, and the number evaluation 528. For the above-mentioned exercise time 522, steps 523, calories 524, number of dribbles 525, average vertical jump height 526, average movement speed 527, and number evaluation 528, please refer to the introduction in FIG. 11, which will not be repeated here. The content displayed by the device main body 110 on the application interface 520 may also include more or less exercise data, which is not limited in the embodiment of the present application.

It can be seen from the above-mentioned electronic device that displays sports data and other content that the electronic device can display the user's basketball sports data and sports suggestions in detail. In this way, the user can fully understand the overall performance of the individual playing basketball, and use exercise suggestions to improve the individual's ability to play basketball. In addition, the device main body 110 may also display exercise data on the display screen 111. Wherein, since the display screen 111 of the device main body 110 is small, the exercise data displayed by the device main body 110 may be part of the exercise data. In this way, the user can easily understand part of the key sports data for playing basketball.

The wearable device (ie, the device body 110) collects acceleration signals, angular velocity signals, and sound wave signals of the user when playing basketball through an accelerometer, a gyroscope, and a microphone. Using the collected signals, the wearable device can monitor the movement data of the user walking, running and jumping on the feet and the movement data of the dribble when playing basketball, so as to obtain the overall movement of the user when playing basketball, for example, the original Ground dribble, running dribble, running without the ball, vertical jump without the ball and vertical jump pass. Moreover, according to the user's various sports data, the wearable device can realize the evaluation of the user's number position on the basketball court. In this way, combined with the user's exercise data, exercise classification, and number evaluation results, the device main body 110 can provide exercise suggestions to the user, effectively assisting the user in improving the ability to play basketball.

In the embodiment of the present application, the wearable device collects the first movement data of the user in the first time period through the motion sensor, and the wearable device collects the first sound wave signal in the first time period through the sound wave collecting device. The first time period may be a time period for the user to play basketball at a time, that is, a continuous period of time from when the wearable device is started to the end of basketball. The first time period may also be a time segment in the time period when the user plays basketball at a time, such as 5 seconds, 1 minute, 5 minutes, and so on.

In the embodiment of the present application, the first sound wave signal may include a sound wave signal when the user is dribbling and a sound wave signal when the user is not dribbling.

In the embodiment of the present application, the wearable device determines the first similarity based on the characteristic parameters of the first acoustic wave signal and the first Gaussian mixture model. The aforementioned first Gaussian mixture model may be a trained dribbling Gaussian mixture model or a trained user's dribbling Gaussian mixture model. The aforementioned first degree of similarity may be the sum of the posterior probabilities of the first acoustic wave signal generated from multiple Gaussian distributions in the first Gaussian mixture model.

In the embodiment of the present application, the wearable device determines the user's number position in the first time period according to the basketball movement data of the user in the first time period. Among them, the wearable device can calculate the correlation coefficient between the user’s basketball data in the first time period and the basketball data in the number template library, and determine the user’s number in the first time by determining the number corresponding to the largest correlation coefficient. The number position within the segment. In addition to the foregoing method of matching according to the number position template library, the wearable device can also use other methods to determine the user's number position in the first time period, which is not limited in the embodiment of the present application.

Fig. 13 shows a schematic structural diagram of a wearable device. As shown in FIG. 13, the wearable device (ie, the device main body 110) may include a motion sensor 610, a memory 620, a processor 630, a sound wave acquisition device 640, and a display screen 650 connected by a bus. in:

The motion sensor 610 may be used to collect the first motion data of the user in the first time period. The first movement data may be movement data of the user's feet when playing basketball, and may include one or more of the following: movement speed, movement distance, vertical jump height, and flight time.

The motion sensor 610 may include an accelerometer 611 and a gyroscope 612. When the device main body 110 turns on the basketball mode, the accelerometer 611 and the gyroscope 612 are both in working state. The accelerometer 611 can collect the acceleration signal of the user's foot, and the gyroscope 612 can collect the angular velocity signal of the user's foot. The motion sensor 610 may send the aforementioned acceleration signal and angular velocity signal to the processor 630. Not limited to accelerometers and gyroscopes, the motion sensor 610 may also include more types of motion sensors.

The acoustic wave collecting device 640 may be used to collect the first acoustic wave signal in the above-mentioned first time period. The sound wave collecting device 640 may be a microphone or other devices for collecting sound wave signals, which is not limited in the embodiment of the present application.

When the main body 110 of the equipment turns on the basketball mode, the sound wave collecting device 640 is in a working state. The sound wave collecting device 640 may send the first sound wave signal to the processor 630.

The memory 620 may be used to store the first Gaussian mixture model, number data template, motion data, and the like. The above-mentioned first Gaussian mixture model may be a trained dribbling Gaussian mixture model. The number position data template mentioned above can be a number position template library.

The processor 630 can process the acceleration signal and the angular velocity signal from the motion sensor 610 and the first sound wave signal from the sound wave collecting device 640.

The processor 630 can detect the waveform characteristics of the acceleration signal and the angular velocity signal, and obtain the waveform characteristics of the acceleration signal and the angular velocity signal, so as to calculate the user's motion data on the feet such as vertical jump height, flight time, and movement speed.

The processor 630 may determine, according to the first sound wave signal, whether the user has made a dribble motion in the first time period. Specifically, the processor 630 may perform audio signal processing on the first sound wave signal to obtain characteristic parameters of the first sound wave signal, so as to use the first Gaussian mixture model in the processor 630 to determine whether the first sound wave signal includes the first sound wave signal. The sound wave signal generated by the ball. The above-mentioned sound wave signal generated by dribbling can indicate that the user is dribbling.

Further, according to the sound wave signal generated by the dribble, the processor 630 can obtain the dribbling time and the number of dribbles. According to basketball movement data such as vertical jump height, flight time, movement speed, dribbling time, and number of dribbles, the processor 630 can determine the user's overall actions when playing basketball, for example, dribbling in place, running dribble, no ball Running, vertical jump without the ball and vertical jump pass. And the processor 630 may also determine the user's number position on the basketball court when playing basketball, for example, point guard, shooting guard, center, small forward, and power forward.

The display screen 650 can be used to display a user interface including a control for turning on the basketball mode, a user interface including basketball movement data, and other user interfaces.

It should be noted that the device main body 110 further includes a touch panel coupled with the processor 630. The display screen 650 may display a user interface including a control for turning on the basketball mode. When the touch panel detects a user operation, such as a touch operation, that acts on the above-mentioned control for turning on the basketball mode, the processor 630 can determine whether the motion sensor 610 and the sound wave collection device 640 are turned on. If it is not turned on, the processor 630 may turn on the motion sensor 610 and the sound wave collecting device 640.

As used in the above embodiments, depending on the context, the term "when" can be interpreted as meaning "if..." or "after" or "in response to determining..." or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detected (statement or event)" can be interpreted as meaning "if determined..." or "in response to determining..." or "when detected (Condition or event stated)" or "in response to detection of (condition or event stated)".

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, it can be implemented in the form of a computer program product in whole or in part. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center. Transmission to another website site, computer, server or data center via wired (such as coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media. The usable medium may be a magnetic medium, (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state hard disk).

A person of ordinary skill in the art can understand that all or part of the process in the above-mentioned embodiment method can be realized. The process can be completed by a computer program instructing relevant hardware. The program can be stored in a computer readable storage medium. , May include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random storage RAM, magnetic disks or optical disks and other media that can store program codes.

Claims

A method for detecting basketball actions based on a wearable device, wherein the wearable device includes a sound wave acquisition device and a motion sensor; the method includes:

The wearable device collects the user's first motion data in a first time period through the motion sensor; the first motion data includes one or more of the following: moving speed and moving distance;

Collecting, by the wearable device, the first acoustic wave signal in the first time period through the acoustic wave collecting device;

The wearable device determines, according to the first sound wave signal, whether the user has made a dribble motion in the first time period;

If it is determined that the user has made a dribbling action in the first time period, the type of the dribbling action is determined according to the first movement data.
The method according to claim 1, wherein the method further comprises:

The wearable device displays a first user interface, and a first control is displayed on the first user interface;

The wearable device detects a first user operation acting on the first control;

In response to the first user operation, the wearable device determines whether the motion sensor and the sound wave collection device are turned on, and if they are not turned on, the motion sensor and the sound wave collection device are turned on.
The method according to claim 2, wherein the wearable device determines whether the user has made a dribble action in the first time period according to the first sound wave signal, and the method comprises:

The wearable device determines the first similarity based on the characteristic parameters of the first acoustic wave signal and the first Gaussian mixture model; the training data of the first Gaussian mixture model is the first characteristic parameter, and the first characteristic The parameter is the characteristic parameter of the acoustic signal during dribbling; the characteristic parameter of the first acoustic signal and the first characteristic parameter both include at least one or more of the following: energy, frequency, and peak value; the first Gaussian The mixture model includes a plurality of Gaussian distributions, the mean and variance of the plurality of Gaussian distributions converge, and the weights of the plurality of Gaussian distributions in the first Gaussian mixture model converge; the first degree of similarity is used to indicate The similarity between the characteristic parameter of the first acoustic wave signal and the first characteristic parameter;

If the first degree of similarity is higher than a first threshold, the wearable device determines that the user performs a dribbling action in the first time period.
The method according to claim 3, wherein the acoustic signal during dribbling is the acoustic signal during dribbling of the user pre-collected by the wearable device through the acoustic wave collecting device.
The method according to any one of claims 1 to 4, wherein the type of the dribbling action includes one or more of the following:

Dribble and running dribble;

The determining the type of the dribbling action according to the first movement data specifically includes: when the movement speed in the first movement data is less than the first speed and/or the movement distance in the first movement data When the distance is less than the first distance, the wearable device determines that the type is the dribble in place; when the movement speed in the first movement data is greater than the second speed and/or the movement in the first movement data When the distance is greater than the second distance, the wearable device determines that the type is the running dribble; the first speed is less than or equal to the second speed, and the first distance is less than or equal to the second distance .
The method according to any one of claims 1 to 4, wherein the method further comprises:

If it is determined that the user is dribbling the ball in the first sub-period according to the first acoustic signal in the first sub-period, and the user is determined according to the first acoustic signal in the second sub-period If the user does not dribble in the second sub-time period, the wearable device determines that the user produces a passing action or a shooting action in the first time period; the first sub-time period The second sub-time period and the second sub-time period are two consecutive time segments in the first time period.
The method according to claim 6, characterized in that, after the wearable device determines that the user produces a passing action or a shooting action within the first time period, the method further comprises:

If the moving speed in the second sub-period is greater than the second speed and/or the moving distance in the second sub-period is greater than the second distance, the wearable device determines that the user is In the first time period, an action of running shot is generated; the running shot includes running pass and running shot.
The method according to claim 6, wherein the first motion data further includes a vertical jump height, and the wearable device determines that the user performs a pass or shoot during the first time period. After the action, the method further includes:

If the vertical jump height in the second sub-time period is greater than the first height, the wearable device determines that the user produces a vertical jump shot in the first time period; the vertical jump shot Including vertical jump pass and vertical jump shot.
The method according to any one of claims 1 to 8, wherein the method further comprises:

The wearable device displays first information; the first information indicates whether the user has made a dribbling action in the first time period.
The method according to any one of claims 1 to 8, wherein the method further comprises:

Determining, by the wearable device, the number of dribbles and/or the dribbling time of the user in the first time period according to the first sound wave signal;

The wearable device determines the number position of the user in the first time period according to the basketball movement data of the user in the first time period; the basketball of the user in the first time period The movement data includes one or more of the following: the number of dribbles, dribbling time, moving speed, and movement distance of the user in the first time period.
A wearable device, characterized in that it comprises:

Mutually coupled motion sensor, sound wave acquisition device, and processor;

The motion sensor is used to collect first motion data of the user in a first time period; the first motion data includes one or more of the following: moving speed and moving distance;

The acoustic wave collecting device is used to collect the first acoustic wave signal in the first time period;

The processor is configured to determine, according to the first sound wave signal, whether the user has made a dribble action in the first time period;

The processor is further configured to, if it is determined that the user has made a dribble action during the first time period, determine the type of the user's dribble action according to the first movement data.
The wearable device according to claim 11, wherein the wearable device further comprises a display screen and a touch panel; the display screen is used to display a first user interface, and the first user interface displays A first control; the touch panel detects a first user operation acting on the first control; the processor is further configured to:

It is determined whether the motion sensor and the sound wave collection device are turned on, and if they are not turned on, the motion sensor and the sound wave collection device are turned on.
The wearable device according to claim 12, wherein the determining whether the user has made a dribble action in the first time period according to the first sound wave signal, the processor specifically uses At:

The first similarity is determined based on the characteristic parameters of the first acoustic signal and the first Gaussian mixture model; the training data of the first Gaussian mixture model is the first characteristic parameter, and the first characteristic parameter is the dribble time The characteristic parameter of the acoustic signal; the characteristic parameter of the first acoustic signal and the first characteristic parameter each include at least one or more of the following: energy, frequency, and peak; the first Gaussian mixture model includes multiple Gaussian distribution, the mean and variance of the multiple Gaussian distributions converge, and the weights of the multiple Gaussian distributions in the first Gaussian mixture model converge; the first degree of similarity is used to indicate the first sound wave The similarity between the characteristic parameter of the signal and the first characteristic parameter;

If the first degree of similarity is higher than a first threshold, it is determined that the user has made a dribbling action in the first time period.
The wearable device according to claim 13, wherein the sound wave signal during dribbling is a sound wave signal pre-collected by the sound wave collecting device when the user is dribbling.
The wearable device according to any one of claims 11 to 14, wherein the type of the dribbling action includes one or more of the following:

Dribble and running dribble;

The determining the type of the dribbling motion according to the first motion data, the processor is specifically configured to: when the moving speed in the first motion data is less than the first speed and/or the first motion When the movement distance in the data is less than the first distance, it is determined that the type is the in-place dribble; when the movement speed in the first movement data is greater than the second speed and/or the movement in the first movement data When the distance is greater than the second distance, it is determined that the type is the running dribble; the first speed is less than or equal to the second speed, and the first distance is less than or equal to the second distance.
The wearable device according to any one of claims 11 to 14, wherein the processor is further configured to:

If it is determined that the user is dribbling the ball in the first sub-period according to the first acoustic signal in the first sub-period, and the user is determined according to the first acoustic signal in the second sub-period If the user does not dribble the ball in the second sub-time period, it is determined that the user has a passing action or a shooting action in the first time period; the first sub-time period and the second sub-time period The sub-time periods are two adjacent time periods in the first time period.
The wearable device according to claim 16, wherein after the determining that the user produces a passing action or a shooting action in the first time period, the processor is further configured to:

If the moving speed in the second sub-period is greater than the second speed and/or the moving distance in the second sub-period is greater than the second distance, it is determined that the user is in the first time An action of running pass and throw is generated in a segment; the running pass and throw include running pass and running shot.
The wearable device according to claim 16, wherein the first motion data further includes a vertical jump height, and the determining the user's passing motion or shooting motion in the first time period After that, the processor is also used to:

If the vertical jump height in the second sub-time period is greater than the first height, it is determined that the user produces a vertical jump pass during the first time period; the vertical jump pass includes a vertical jump pass And vertical jump shot.
The wearable device according to any one of claims 11 to 18, wherein the display screen is also used for:

First information is displayed; the first information indicates whether the user has made a dribble action in the first time period.
The wearable device according to any one of claims 11 to 18, wherein the processor is further configured to:

Determining the number of dribbles and/or dribbling time of the user in the first time period according to the first sound wave signal;

Determine the number position of the user in the first time period according to the basketball data of the user in the first time period; the basketball data of the user in the first time period includes the following: Item or multiple items: the number of dribbles, dribbling time, moving speed, and moving distance of the user in the first time period.
A method for detecting basketball actions based on a wearable device, wherein the wearable device includes a sound wave collecting device, and the method includes:

The wearable device displays a first user interface, and a first control is displayed on the first user interface;

The wearable device detects a first user operation acting on the first control;

In response to the operation of the first user, the wearable device determines whether the sound wave collection device is turned on, and if it is not turned on, turns on the sound wave collection device;

The wearable device collects the first sound wave signal in the first time period through the sound wave collecting device, and determines whether the user has a dribbling action in the first time period according to the first sound wave signal.
The method according to claim 11, wherein the determining whether a user has made a dribble action in the first time period according to the first sound wave signal, the method comprising:

The wearable device determines the first similarity based on the characteristic parameters of the first acoustic wave signal and the first Gaussian mixture model; the training data of the first Gaussian mixture model is the first characteristic parameter, and the first characteristic The parameter is the characteristic parameter of the acoustic signal during dribbling; the characteristic parameter of the first acoustic signal and the first characteristic parameter both include at least one or more of the following: energy, frequency, and peak value; the first Gaussian The mixture model includes a plurality of Gaussian distributions, the mean and variance of the plurality of Gaussian distributions converge, and the weights of the plurality of Gaussian distributions in the first Gaussian mixture model converge; the first degree of similarity is used to indicate The similarity between the characteristic parameter of the first acoustic wave signal and the first characteristic parameter;

If the first degree of similarity is higher than a first threshold, the wearable device determines that the user performs a dribbling action in the first time period.
The method according to claim 21 or 22, wherein the method further comprises:

The wearable device displays first information; the first information indicates whether the user has made a dribbling action in the first time period.