A gesture interaction method, wearable device and computer-readable storage medium

Abstract

The present application provides a gesture interaction method, a wearable device, and a computer-readable storage medium, and relates to the technical field of wearable devices. The method can execute the operation corresponding to the user's gesture after determining that the user intends to use the gesture to trigger the corresponding function, which can reduce the risk of false touches and improve the user experience. In the method, the wearable device can execute the operation corresponding to the first gesture in response to receiving the first operation and the first gesture of the first user within a first time period.

Description

Technical Field

[0001] The present application relates to the technical field of wearable devices, and in particular to a gesture interaction method, a wearable device, and a computer-readable storage medium. Background Art

[0002] At present, wearable devices (such as wearable watches, wearable glasses, wearable rings, etc.) are becoming more and more popular. Among them, in addition to displaying time, wearable watches can also have functions such as making and receiving calls, health monitoring or payment. When users wear wearable devices, they can trigger functions through gestures (such as turning the wrist, shaking the wrist, clenching the fist, pinching the fingers, etc.). However, these interaction methods have the problem of false touches. For example, if a user shakes his wrist while exercising, the function corresponding to the gesture may be mistakenly triggered, which not only affects the user experience, but also causes additional power consumption to the wearable watch due to unnecessary operations. Summary of the invention

[0003] The embodiments of the present application provide a gesture interaction method, a wearable device, and a computer-readable storage medium, which are used to execute the operation corresponding to the user's gesture when it is determined that the user intends to trigger the corresponding function using the gesture, thereby reducing the risk of accidental touches and improving the user experience.

[0004] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0005] In the first aspect, an embodiment of the present application provides a gesture interaction method, which is applied to a wearable device. In this method, the wearable device may perform an operation corresponding to the first gesture in response to receiving a first operation and a first gesture of a first user within a first time period. Among them, the first user is a user wearing a wearable device, which is equivalent to the gesture interaction method provided in the embodiment of the present application being performed when the wearable device is worn by the user. The first gesture is an operation performed when the user wants to use the user gesture to trigger the corresponding function, and the wearable device receives the first gesture indicating that the first user wants to use the function corresponding to the first gesture. In other words, the gesture interaction method provided in the embodiment of the present application adds confirmation of the user's intention, and only performs the operation corresponding to the user gesture (such as the first gesture) when it is determined that the user has the intention to use the gesture to trigger the corresponding function, which can reduce the risk of false touches and improve the user experience.

[0006] In an implementation manner provided in the first aspect, the wearable device includes an electrocardiogram sensor, and the wearable device can obtain a biometric signal collected by the electrocardiogram sensor and determine that the above-mentioned first operation is received according to the biometric signal.

[0007] In an implementation manner provided in the first aspect, the wearable device further includes an accelerometer, and the wearable device may obtain an accelerometer signal collected by the accelerometer, and determine that the first gesture is received according to the accelerometer signal.

[0008] In an implementation manner provided in the first aspect, the accelerometer signal includes x-axis acceleration, y-axis acceleration and z-axis acceleration. When the wearable device determines that the first gesture is received according to the accelerometer signal, the wearable device can determine the first differential signal, the second differential signal, the third differential signal and the combined acceleration of the x-axis acceleration, the y-axis acceleration and the z-axis acceleration according to the x-axis acceleration, the y-axis acceleration and the z-axis acceleration, and then extract the characteristic information of the x-axis acceleration, the y-axis acceleration, the z-axis acceleration, the first differential signal, the second differential signal, the third differential signal and the combined acceleration respectively, and finally determine that the first gesture is received according to the plurality of characteristic information. The first differential signal is the differential signal of the x-axis acceleration, the second differential signal is the differential signal of the y-axis acceleration, and the third differential signal is the differential signal of the z-axis acceleration, and each characteristic information includes one or more of the number of peaks, the number of troughs, the peak value, the trough value, the peak-to-trough distance, the kurtosis and the slope. Compared to determining whether the first gesture is received based solely on the accelerometer signal, the present application can also refer to signals of more dimensions (such as the first differential signal, the second differential signal, the third differential signal and the combined acceleration) to improve the accuracy of the judgment result.

[0009] In an implementation provided in the first aspect, when determining that the first gesture is received based on multiple feature information, the wearable device can input the multiple feature information into a first classification model to obtain a first output result including the number of taps and the tapping position, and then determine that the first gesture is received based on the number of taps and the tapping position. In other words, after obtaining the feature information, the user gesture can be directly determined based on the feature information, which can speed up the processing flow and improve efficiency.

[0010] In an implementation provided in the first aspect, when it is determined that the first gesture is received according to multiple feature information, the wearable device may also input the multiple feature information into a decision tree model to obtain a second output result of the decision tree model, and input the multiple feature information into the first classification model when the second output result indicates that the accelerometer signal is a tapping signal. It can be seen that the accelerometer signal can be preliminarily screened by the decision tree model, and the feature information is input into the first classification model only when the accelerometer signal may be a tapping signal, which can reduce the number of times the first classification model is run, thereby saving computing resources.

[0011] In an implementation provided in the first aspect, when the tapping position is the first area of ​​the wearable device, such as the dial of a wearable watch, the wearable device can obtain the coordinate information of the tapping position, and then determine the tapping area according to the coordinate information of the tapping position, and then determine that the first gesture is received according to the number of taps and the tapping area. In this way, the number of user gestures that can be recognized by the wearable device can be increased, and more user gestures that can quickly start functions can be provided for users to choose, thereby improving the user experience.

[0012] In an implementation manner provided in the first aspect, the wearable device further includes a display screen, and the wearable device can also shield a touch event acting on the display screen in response to receiving the first operation. Shielding the touch event acting on the display screen can be understood as not responding to any touch operation of the user on the display screen, thereby avoiding the situation where the content displayed on the display screen jumps due to the user's first gesture.

[0013] In an implementation manner provided in the first aspect, the wearable device may receive the first operation at a first moment in a first time period, and may receive the first gesture at a second moment in the first time period, wherein the second moment is later than the first moment. In other words, the user may first perform the first operation and then use the first gesture, for example, when the user is wearing a wearable watch, first touches a button of the wearable watch and then double-clicks the dial of the wearable device.

[0014] In an implementation provided in the first aspect, the wearable device may also receive the first gesture at a first moment in a first time period, and may also receive the first operation at a second moment in the first time period. That is, the user may first use the first gesture and then perform the first operation, for example, when the user is wearing a wearable watch, first double-clicking the dial of the wearable device and then touching a button of the wearable watch.

[0015] In an implementation manner provided in the first aspect, the wearable device may also receive the first operation and the first gesture at a first moment in the first time period. That is, the user may use the first gesture while performing the first operation, for example, when the user is wearing a wearable watch, while pressing and touching a button of the wearable watch, double-clicking the dial of the wearable device.

[0016] In an embodiment provided in the first aspect, the wearable device includes an electrocardiogram sensor, the electrocardiogram sensor includes a first electrode and a second electrode, the first operation includes an operation in which the user simultaneously contacts the first electrode and the second electrode with the skin, and the first gesture is a gesture in which the user taps a preset position of the wearable device.

[0017] In a second aspect, an embodiment of the present application provides a wearable device, comprising: a memory and a processor; the processor is coupled to the memory; wherein the memory is used to store computer program code, and the computer program code includes computer instructions; when the computer instructions are executed by the processor, the wearable device executes the method of the first aspect and any one of its embodiments.

[0018] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, including computer instructions; when the computer instructions are executed on a wearable device, the wearable device executes a method as in the first aspect and any one of its implementations.

[0019] In a fourth aspect, an embodiment of the present application provides a computer program product, comprising computer instructions; when the computer instructions are executed on a wearable device, the wearable device executes the method of the first aspect and any one of its implementations.

[0020] Among them, the technical effects brought about by any implementation method in the second to fourth aspects can refer to the technical effects brought about by different design methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of an interactive scenario of a wearable device provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of the hardware structure of a wearable watch provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of the structure of a wearable watch provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of another interactive scenario of a wearable device provided in an embodiment of the present application;

[0025] Figure 5 A waveform diagram of a biometric signal provided in an embodiment of the present application;

[0026] Figure 6 A schematic diagram of a process for detecting an electrocardiogram signal provided in an embodiment of the present application;

[0027] Figure 7 A flowchart of a method for identifying user gestures provided in an embodiment of the present application;

[0028] Figure 8 A schematic diagram of the structure of a classification and regression tree model provided in an embodiment of the present application;

[0029] Fig. 9A schematic diagram of the position division of a dial provided in an embodiment of the present application;

[0030] Fig.10 An interface diagram for setting interactive gestures provided in an embodiment of the present application;

[0031] Fig.11 A flowchart of a gesture interaction method provided in an embodiment of the present application;

[0032] Fig.12 A schematic diagram of the structure of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this embodiment, unless otherwise specified, "plurality" means two or more.

[0034] Meanwhile, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete manner for ease of understanding.

[0035] Figure 1 A schematic diagram of an interactive scenario of a wearable device is shown. Figure 1 The wearable device 101 is taken as a wearable watch for example, but in other implementations, the wearable device 101 may also be other devices, such as wearable glasses, wearable rings, etc., and no specific limitation is made here.

[0036] After detecting the user's wrist rotation gesture, the wearable device 101 can perform an operation corresponding to the gesture. Figure 1 The operation corresponding to the wrist rotation gesture is to display the payment code as an example for illustration, but in other embodiments, the operation corresponding to the wrist rotation gesture may also be other operations, such as making a call, turning on a sports health function, etc., which are not specifically limited here. Figure 1 As shown, the wearable device 101 can display the payment code 102 after detecting the user's wrist rotation gesture.

[0037] It should be noted that Figure 1The interaction scenario shown is only an example. In other implementations, the user can also interact with the wearable device 101 through other gestures, such as shaking the wrist, clenching the fist, pinching the fingers, etc., without specific limitation here.

[0038] However, the above interaction method has the problem of false touches. For example, when a user turns his wrist while wearing the wearable device 101 and exercising, the wearable device 101 may mistakenly display the payment code 102, interrupting the operation originally performed by the wearable device 101 before detecting that the user has turned his wrist (such as displaying the sports and health interface). This not only affects the user experience, but also causes additional power consumption to the wearable watch due to the execution of unnecessary operations.

[0039] To at least solve the above problems, an embodiment of the present application provides a gesture interaction method that can be applied to a wearable device. In this method, the wearable device can perform an operation corresponding to the first gesture when receiving a first operation and a first gesture of a first user. The first user is a user wearing the wearable device. In other words, the gesture interaction method provided in the embodiment of the present application is a method performed when the wearable device is worn by a user, that is, the present application will not be repeated in the following text.

[0040] Among them, the wearable device receiving the first operation indicates that the first user has the intention to use the gesture to trigger the corresponding function. On this basis, if the wearable device also receives the first gesture of the first user, it means that the first user wants to use the function corresponding to the first gesture, so the wearable device executes the operation corresponding to the first gesture. It can be seen that compared with the solution of executing the corresponding operation only after receiving the user gesture, the gesture interaction method provided in the embodiment of the present application increases the confirmation of the user's intention, and only executes the operation corresponding to the user's gesture when it is determined that the user has the intention to use the gesture to trigger the corresponding function, which can reduce the risk of accidental touch and improve the user experience.

[0041] In an optional implementation, the wearable device may perform an operation corresponding to the first gesture when receiving a first operation and a first gesture of a first user within a first time period, and the duration of the first time period is less than a first threshold.

[0042] Optionally, the wearable device may receive the first operation at a first moment in the first time period, and receive the first gesture at a second moment in the first time period, wherein the second moment is later than the first moment. In other words, the user may perform the first operation first, and then use the first gesture.

[0043] Optionally, the wearable device may also receive the first gesture at a first moment in the first time period, and receive the first operation at a second moment in the first time period. That is, the user may first use the first gesture and then perform the first operation.

[0044] Optionally, the wearable device may also receive the first operation and the first gesture at a first moment in the first time period. That is, the user may use the first gesture while performing the first operation.

[0045] According to the above content, it can be known that the method provided in the embodiment of the present application can increase the temporal correlation between the first operation and the first gesture. Only when the first operation is received when the first gesture is received or the first operation is received within a certain period of time before / after receiving the first gesture, it is confirmed that the first operation is used to indicate that the user wishes to use the gesture to trigger the corresponding function, that is, the user's intention is truly confirmed, which can further reduce the risk of accidental touches.

[0046] It should be noted that the wearable device provided in the embodiments of the present application may be a wearable watch, wearable glasses, a wearable ring, a wearable helmet or other devices, and no specific limitation is made here.

[0047] The present application embodiment takes a wearable watch as an example to illustrate the circuit structure of the wearable device. Figure 2 , is a schematic diagram of the hardware structure of a wearable watch provided in an embodiment of the present application. Figure 2 As shown, the wearable watch 200 may include a processor 210 , a memory 220 , a communication circuit 230 , an antenna 240 , a sensor module 250 , and a display screen 260 .

[0048] Among them, the processor 210 can be used to read and execute computer-readable instructions. In a specific implementation, the processor 210 may mainly include a controller, an arithmetic unit and a register. Among them, the controller is mainly responsible for instruction decoding and issuing control data for the operation corresponding to the instruction. The arithmetic unit is mainly responsible for saving register operands and intermediate operation results temporarily stored during the execution of instructions. In a specific implementation, the hardware architecture of the processor 210 can be an application-specific integrated circuit (ASIC) architecture, a microprocessor without interlocked pipelined stages (MIPS) architecture, an advanced reduced instruction set machine (ARM) architecture or a network processor (NP) architecture, etc., without specific restrictions here.

[0049] In some embodiments, the processor 210 may be configured to parse data received by the communication circuit 230 .

[0050] The memory 220 is coupled to the processor 210 and is used to store various software programs and / or multiple sets of instructions. In a specific implementation, the memory 220 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. The memory 220 may store an operating system, such as uCOS, VxWorks, RTLinux, and other embedded operating systems. The memory 220 may also store a communication program, which may be used to communicate with other devices.

[0051] The communication circuit 230 can provide wireless communication solutions including wireless local area network (WLAN), such as wireless fidelity (Wi-Fi) network, Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., applied to the wearable watch 200. In other embodiments, the communication circuit 230 can also transmit data so that other devices can find the wearable watch 200.

[0052] The wireless communication function of the wearable watch 200 can be realized through the communication circuit 230, the antenna 240, the modem processor, etc.

[0053] Antenna 240 can be used to transmit and receive electromagnetic wave data. Each antenna in wearable watch 200 can be used to cover a single or multiple communication frequency bands. In some embodiments, the number of antennas 240 of communication circuit 230 can be multiple.

[0054] The sensor module 250 can sense changes inside or around the wearable watch 200 and convert the changes into electrical data for use by the wearable watch 200. The sensor module 250 may include an electrocardiogram (ECG) sensor 251, an accelerometer (ACC) 252, and an ambient light sensor 253. In addition, the sensor module 250 may also include other sensors, such as a gyroscope, a magnetometer, an altimeter, an optical heart rate sensor, etc., which are not limited in this application. In an optional embodiment, the gyroscope, magnetometer, and accelerometer 252 may be integrated into an inertial measurement unit (IMU).

[0055] The ECG sensor 251 is a device for monitoring and recording the electrical activity of the heart. It can capture the bioelectrical signal generated by the electrical activity of the heart, i.e., the electrocardiogram signal, through electrodes in contact with the skin. The number of electrodes included in the ECG sensor 251 may vary depending on its application scenario and the required measurement accuracy. For example, in a scenario where the heart rate needs to be detected, an ECG sensor including only one electrode (which may be called a single-lead ECG) may be used.

[0056] In the embodiment of the present application, the ECG sensor 251 may include two electrodes, for example, electrode 1 and electrode 2. Figure 3 , is a schematic diagram of the structure of the wearable watch 200 provided in the embodiment of the present application. Figure 3 As shown, the wearable watch 200 includes a watch case 301, a watch dial 302, and a button 303. The watch dial 302 is embedded in the first surface (for example, the front surface) of the watch case 301, and the electrode 1 ( Figure 3 The first electrode 301 is provided on the second side of the watch case 301 opposite to the first side, the button 303 is provided on the side of the watch case 301, and the electrode 2 is provided on the button 303. When the user wears the wearable watch 200, the electrode 1 is in contact with the user's wrist; when the user touches the button 303 with a finger, the electrode 2 is in contact with the user's finger.

[0057] It should be noted that the above-mentioned wearable device may also be wearable glasses, wearable rings or wearable helmets, etc., wherein the ECG sensor of the wearable device includes at least two electrodes, and the positions of the at least two electrodes may be set according to the specific structure of the wearable device. For example, wearable glasses include two electrodes, one of which is set on the glasses holder, and the other is set on the glasses frame. For another example, a wearable ring includes two electrodes, one of which is set on the inside of the ring, and the other is set on the outside.

[0058] In an embodiment of the present application, the wearable watch 200 can determine whether the above-mentioned first operation is received based on the biometric signal output by the ECG sensor 251. The detailed principle will be introduced in detail later and will not be described here.

[0059] The accelerometer 252 may be a three-axis accelerometer, which may be used to collect an ACC signal, wherein the ACC signal includes the wearable watch 200 at a certain time. Figure 3 The acceleration signals in the x, y, and z axis directions are shown.

[0060] In an embodiment of the present application, the wearable watch 200 can recognize user gestures based on the ACC signal. The detailed principle will be introduced in detail later and will not be described here.

[0061] The display screen 260 can be used to display images, prompt information, etc. The display screen can be a liquid crystal display (LCD), an organic light-emitting diode (OLED) display screen, an active-matrix organic light-emitting diode (AMOLED) display screen, a flexible light-emitting diode (FLED) display screen, a quantum dot light-emitting diode (QLED) display screen, etc. The display screen 260 can also detect a user's touch operation.

[0062] In one example, the display screen 260 includes a touch panel and a display panel, wherein the display panel may be located at the bottom layer of the display screen, and the touch panel may be located at the top layer of the display screen. The touch panel may also be referred to as a touch sensor, and the display screen 260 may also be referred to as a touch screen or a touch screen. The touch panel may transmit the detected touch operation to the processor 210 to determine the type of touch event (e.g., a tap event in the present application), and may display an interface related to the touch operation on the display screen 260 (e.g., an interface such as a touch screen). Figure 4 interface shown in ).

[0063] It should be noted that the display screen 260 and the above-mentioned dial 302 provided in the embodiment of the present application are integrated into a display component. Therefore, when the user taps the dial 302, the touch panel can obtain the coordinate information corresponding to the tapping gesture to indicate the specific position of the tapping gesture.

[0064] It is understood that the structure shown in the embodiment of the present application does not constitute a specific limitation on the wearable watch 200. In other embodiments, the wearable watch 200 may include Figure 2 More or fewer components, or combining some components, or splitting some components, or different component arrangements. The components shown in the figure can be implemented in hardware, software, or a combination of software and hardware.

[0065] The following continues to take the wearable device as a wearable watch 200 as an example, and introduces the gesture interaction method provided in the embodiment of the present application in combination with the accompanying drawings.

[0066] In the embodiments of the present application, Figure 4As shown, when the wearable watch 200 is worn by the user, the wearable watch 200 can respond to receiving the user's first operation (e.g., the user touching the button 303) and the first gesture (e.g., the gesture of double-clicking the top of the watch case 301), and perform the operation corresponding to the first gesture (e.g., displaying the payment code 401). The following will respectively describe the process of the wearable watch 200 recognizing the first operation and the first gesture in conjunction with the accompanying drawings.

[0067] In the embodiment of the present application, the biometric signal output by the ECG sensor 251 may be different according to the following operations performed by the user on the wearable watch 200:

[0068] (1) The user directly touches the button 303 with the skin while wearing the wearable watch.

[0069] (2) The user directly touches button 303 with the skin when not wearing the wearable watch, or the user does not touch button 303 while wearing the wearable watch, or the user neither wears the wearable watch nor directly touches button 303 with the skin, or the user touches button 303 with a non-conductive object while wearing the wearable watch, for example, the user touches button 303 after wearing the wearable watch and insulating gloves.

[0070] (3) The user holds a conductive object and touches button 303 while wearing the wearable watch.

[0071] In the above operation (1), when the user wears the wearable watch, electrode 1 is in contact with the skin, and at the same time, the skin directly touches the button 303, and electrode 2 is also in contact with the skin, so that electrode 1 and electrode 2 form a conductive loop, and the ECG sensor 251 outputs as follows: Figure 5 Normal ECG signal shown.

[0072] In the above operation (2), when the user is not wearing the wearable watch, electrode 1 is not in contact with the skin, when the user does not touch the button 303, electrode 2 is not in contact with the skin, and when the user touches the button 303 with a non-conductive object, electrode 2 is not in contact with the skin. In other words, in operation (2), electrode 1 and electrode 2 cannot form a conductive loop, and the ECG sensor 251 outputs Figure 5 Baseline signal shown.

[0073] In the above operation (3), although electrode 1 and electrode 2 form a conductive loop, since the user holds a conductive object, the ECG sensor 251 may output Figure 5 The abnormal ECG signal shown. A simple comparison of the curves of the normal ECG signal, the baseline signal and the abnormal ECG signal shows that the amplitude of the abnormal ECG signal is stronger than the baseline signal, but weaker than the normal ECG signal.

[0074] Therefore, the wearable watch 200 can identify the user's operation on the wearable watch 200 through the biometric signal output by the ECG sensor 251, and then distinguish whether the user intends to trigger the corresponding function by gesture. For example, the wearable watch 200 can determine that the user performs the above operation (1) when the above normal ECG signal is detected; the wearable watch 200 can determine that the user performs the above operation (2) when the above baseline signal is detected; the wearable watch 200 can determine that the user performs the above operation (3) when the above abnormal ECG signal is detected.

[0075] In the embodiment of the present application, in order to eliminate the interference of the user's operation of not touching the button 303, the first operation can be the above operation (1) or operation (3). In this case, the wearable watch 200 can determine that the first operation is received when the ECG signal (the above normal ECG signal or abnormal ECG signal) is detected, and further determine that the user intends to use the gesture to start the corresponding function.

[0076] In an optional implementation, the wearable watch 200 may calculate the amplitude of the biometric signal, and determine that the electrocardiogram signal is detected when the amplitude of the biometric signal is greater than the second threshold. Figure 5 As shown in the curves of normal ECG signals, baseline signals and abnormal ECG signals, the amplitude of ECG signals (including normal ECG signals and abnormal ECG signals) is significantly greater than the amplitude of baseline signals. Therefore, the second threshold is set to a value that the amplitude of the baseline signal cannot reach (such as the second threshold), and the ECG signal can be detected when the amplitude of the biometric signal is greater than the second threshold. This method has a small amount of calculation, a simple process, and only requires a small amount of memory to implement.

[0077] However, considering that the biometric signal may also carry noise, the noise will affect the amplitude of the biometric signal, thereby causing the judgment result based on the amplitude of the biometric signal to be inaccurate. Therefore, the embodiment of the present application also provides another method, such as Figure 6 As shown, the wearable watch 200 can input the biometric signal collected by the ECG sensor 251 into the classification model 1, and the classification model 1 can output a classification result, which can be used to indicate whether the input biometric signal is an electrocardiogram signal. It can be understood that when the classification result indicates that the input biometric signal is an electrocardiogram signal, the wearable watch 200 can determine that the electrocardiogram signal is detected, and then determine that the first operation is received. When the classification result indicates that the input biometric signal is not an electrocardiogram signal, the wearable watch 200 can determine that the electrocardiogram signal is not detected, and then determine that the first operation is not received.

[0078] In an optional implementation, the classification model 1 may be one of logistic regression, decision tree, convolutional neural networks (CNN), etc., or a combination thereof.

[0079] It should be noted that when the wearable device is other devices, such as wearable glasses, wearable rings or wearable helmets, the above-mentioned first operation includes the operation of the user contacting the electrode 1 and the electrode 2 with the skin at the same time, which can be specifically set according to the distribution position of the electrodes of the ECG sensor on the wearable device. For example, when the wearable device is wearable glasses, the first operation can be the operation of the user touching the position where the electrodes are set on the glasses frame after wearing the wearable glasses; for another example, when the wearable device is a wearable ring, the first operation can be the operation of the user touching the position where the electrodes are set on the outside of the ring after wearing the wearable ring. In addition, the wearable device can also identify the user operation and determine the user's intention based on the biometric signal output by the ECG sensor. The principle is similar to the principle of the wearable watch 200 identifying the first operation, which will not be repeated here.

[0080] In the embodiment of the present application, the first gesture may be a gesture of the user tapping a preset position of the wearable watch 200. The first gesture may be different depending on the number of times the user taps the wearable watch 200 (referred to as the number of taps) and the position where the user taps the wearable watch 200 (referred to as the tap position).

[0081] The number of taps may be 2, 3 or more. The tapping position may be the top of the watch case 301, the bottom of the watch case 301 or the dial 302. Thus, the first gesture may be any one of a gesture of the user double-clicking the top of the watch case 301, a gesture of the user double-clicking the bottom of the watch case 301, a gesture of the user double-clicking the dial 302, a gesture of the user triple-clicking the top of the watch case 301, a gesture of the user triple-clicking the bottom of the watch case 301, and a gesture of the user triple-clicking the dial 302.

[0082] It can be understood that the ACC signal output by the accelerometer 252 is different according to the different tapping positions. The ACC signal includes an acceleration signal in the x-axis direction (which may be referred to as x-axis acceleration), an acceleration signal in the y-axis direction (which may be referred to as y-axis acceleration), and an acceleration signal in the z-axis direction (which may be referred to as z-axis acceleration):

[0083] (1) When the user taps the top of the watch case 301, an impact response is formed in the negative direction of the y-axis of the wearable watch 200, and the impact response can cause the y-axis acceleration to form a trough.

[0084] (2) When the user taps the bottom of the watch case 301, an impact response is formed in the positive direction of the y-axis of the wearable watch 200, and the impact response can cause the y-axis acceleration to form a peak.

[0085] (3) When the user taps the dial 302, an impulse response is formed in the positive or negative direction of the z-axis of the wearable watch 200, and the impulse response can cause the z-axis acceleration to form a peak or a trough.

[0086] According to the above content, one tap can form a peak or a trough, so the wearable watch 200 can determine the number of taps according to the number of peaks or the number of troughs. Also, different tap positions correspond to peaks or troughs in different directions (for example, the x-axis, y-axis, or z-axis), so the wearable watch 200 can determine the tap position according to the direction of the peak or trough. In other words, the wearable watch 200 can determine the number of taps and the tap position according to the ACC signal output by the accelerometer 252, and then determine the first gesture.

[0087] For example, when the y-axis acceleration includes two troughs, the wearable watch 200 can determine that the number of taps is 2 and the tap position is the top of the case 301, thereby determining that the first gesture is a double-click on the top of the case 301.

[0088] For another example, when the y-axis acceleration includes two peaks, the wearable watch 200 can determine that the number of taps is 2 and the tap position is the bottom of the case 301 , thereby determining that the first gesture is a double-click on the bottom of the case 301 .

[0089] For another example, when the z-axis acceleration includes three peaks, the wearable watch 200 can determine that the number of taps is 3 and the tap position is the dial 302 , thereby determining that the first gesture is the user tapping the dial 302 three times.

[0090] In an optional embodiment, in order to distinguish between non-continuous multiple taps, double taps (tap twice in a row), and triple taps (tap three times in a row) by the user, the wearable watch 200 can determine the number of taps by the number of troughs (or peaks) and the time interval between the troughs (or peaks) (which can be called the trough-to-trough interval). For example, the wearable watch 200 can determine that the number of taps is 2 when it detects that there are 2 peaks (or troughs) in the ACC signal and the time interval between the two peaks (or troughs) (which can be called the peak-to-peak interval) is less than the third threshold. For another example, the wearable watch 200 can also determine that the number of taps is 3 when it detects that there are 3 peaks in the ACC signal (for example, including peak 1, peak 2, and peak 3 in chronological order) and the time interval between peak 1 and peak 3 is less than the fourth threshold.

[0091] In this way, the above example can be adjusted as follows: when the y-axis acceleration includes two troughs and the time interval between the two troughs is less than the third threshold, the wearable watch 200 can determine that the number of taps is 2 and the tap position is the top of the case 301, thereby determining that the first gesture is a double-click on the top of the case 301. When the y-axis acceleration includes two peaks and the time interval between the two peaks is less than the third threshold, the wearable watch 200 can determine that the number of taps is 2 and the tap position is the bottom of the case 301, thereby determining that the first gesture is a double-click on the bottom of the case 301. When the z-axis acceleration includes three peaks and the time interval between two adjacent peaks is less than the third threshold, the wearable watch 200 can determine that the number of taps is 3 and the tap position is the dial 302, thereby determining that the first gesture is that the user tapped the dial 302 three times.

[0092] When identifying the above-mentioned peaks and troughs, the wearable watch 200 can extract the peak value and trough value of the ACC signal, and determine that the ACC signal includes a peak when the peak value is greater than or equal to the fourth threshold, and determine that the ACC signal includes a trough when the absolute value of the trough value is greater than or equal to the fourth threshold.

[0093] However, considering that the ACC signal may also carry noise, the noise will affect the peak and valley values ​​of the ACC signal, thereby causing the peaks and valleys identified based on the peak and valley values ​​to be inaccurate. Therefore, the embodiment of the present application also provides another method. Please refer to Figure 7 , is a flow chart of a method for recognizing user gestures provided in an embodiment of the present application. Figure 7 As shown, the method includes S701~S705.

[0094] S701, the wearable watch 200 obtains an ACC signal, where the ACC signal includes x-axis acceleration, y-axis acceleration, and z-axis acceleration.

[0095] As can be seen from the foregoing, the wearable watch 200 can collect accelerometer signals through the accelerometer 252 .

[0096] S702, the wearable watch 200 determines the combined acceleration, the differential signal of the x-axis acceleration (which may be referred to as differential signal 1), the differential signal of the y-axis acceleration (which may be referred to as differential signal 2), and the differential signal of the z-axis acceleration (which may be referred to as differential signal 3) according to the x-axis acceleration, the y-axis acceleration, and the z-axis acceleration.

[0097] The total acceleration is the total acceleration of the x-axis acceleration, the y-axis acceleration, and the z-axis acceleration.

[0098] When determining the above differential signal 1, the wearable watch 200 can translate the x-axis acceleration forward or backward, and then calculate the difference between the x-axis acceleration and the forward or backward translation x-axis acceleration to obtain the differential signal 1. Similarly, the differential signal 2 and the differential signal 3 can also be determined in a similar manner, which will not be repeated here.

[0099] S703, the wearable watch 200 extracts the number of peaks, the number of troughs, the peak value, the valley value, the peak-to-valley distance, the kurtosis, and the slope of the x-axis acceleration, the y-axis acceleration, the z-axis acceleration, the combined acceleration, the differential signal 1, the differential signal 2, and the differential signal 3 respectively to obtain feature information i (i=1~7).

[0100] Among them, characteristic information i (i=1~7) represents characteristic information of x-axis acceleration, y-axis acceleration, z-axis acceleration, combined acceleration, differential signal 1, differential signal 2 and differential signal 3 respectively, and characteristic information i includes number of peaks i, number of troughs i, peak value i, valley value i, peak-to-valley distance i, kurtosis i, slope i, i=1~7. For example, number of peaks 2 is the number of peaks of y-axis acceleration, and number of troughs 3 is the number of troughs of z-axis acceleration.

[0101] The peak-to-valley interval is the time interval between the peak and the trough. Kurtosis can be used to characterize the degree of signal spikes. The higher the kurtosis, the sharper the signal spikes. The higher the kurtosis, the flatter the signal spikes. The slope is the maximum value of the signal slope and can be used to characterize the rate of signal change. The larger the slope, the higher the rate of signal change. The smaller the slope, the slower the rate of signal change.

[0102] It is understandable that the user's action of tapping the wearable watch 200 has a certain force, and after tapping, an inertial fall will be formed, that is, a peak or a trough is generated and then quickly returns to normal, so the peak-to-valley interval should be less than the fifth threshold value so that it meets the change trend of the ACC signal generated by the tapping gesture. In addition, considering that some non-tapping gestures (such as the gesture of shaking the wrist after the user wears the wearable watch 200) can also form peaks or troughs, but their peaks or troughs are relatively gentle, the above-mentioned kurtosis should be greater than the sixth threshold value (which can be called threshold 2), and the slope should be greater than the seventh threshold value (which can be called threshold 3) to eliminate the interference of the above-mentioned non-tapping gestures.

[0103] It should be noted that the above-mentioned characteristic information i may also include one or more of the number of peaks i, the number of troughs i, the peak value i, the valley value i, the peak-to-valley distance i, the kurtosis i, and the slope i, or include more features than the above examples.

[0104] S704: The wearable watch 200 determines whether the ACC signal is a tapping signal according to the characteristic information i.

[0105] The tapping signal is a signal formed by a tapping gesture of the user.

[0106] If the ACC signal is a knock signal, execute S705; if the ACC signal is not a knock signal, end the process.

[0107] In an optional embodiment, when the wearable watch 200 determines whether the ACC signal is a tapping signal, 7 sets of feature signals can be input into a pre-trained classification and regression tree (CART) model to obtain a judgment result of whether the user gesture is received. The above-mentioned CART model includes internal nodes (also referred to as decision nodes) and leaf nodes. Among them, each internal node contains a decision rule, and the data needs to be divided into its child nodes according to the decision rule until it reaches the leaf node. The leaf node does not need to make a decision, but directly gives the prediction result. It should be noted that the first node to make a decision can be called the root node.

[0108] For example, the CART model provided in the embodiments of the present application can be Figure 8 As shown. Among them, the root node is used to determine whether the number of peaks 2 is greater than 1, and points to child node 1 when the number of peaks 2 is greater than 1, and points to child node 2 when the number of peaks 2 is less than or equal to 1. Child node 1 is used to determine whether the peak-to-valley distance 2 is less than or equal to threshold 1, and child node 2 is used to determine whether the number of peaks 3 is greater than 1. Among them, when the peak-to-valley distance 2 is less than or equal to threshold 1, it points to child node 3, and when the peak-to-valley distance 2 is greater than threshold 1, it points to child node 4. Child node 3 is used to determine whether the kurtosis 2 is greater than or equal to threshold 2, and child node 4 is used to determine whether the number of troughs 3 is greater than 1. When the kurtosis 2 is greater than or equal to threshold 2, it points to child node 5, and when the kurtosis 2 is less than threshold 2, it points to child node 6. Child node 5 is used to determine whether the slope 2 is greater than or equal to threshold 3, and points to leaf node 1 when the slope 2 is greater than or equal to threshold 3, and points to leaf node 2 when the slope 2 is less than threshold 3. Leaf node 1 indicates that the ACC signal is a knock signal, and leaf node 2 indicates that the ACC signal is not a knock signal. It should be noted that Figure 8 Only the two branches of leaf node 1 and leaf node 2 are used as examples to determine whether the ACC signal is a knock signal. Figure 8 The nodes marked with dotted lines can also form other feature combinations for judgment, and the actual CART model can be compared with Figure 8 The CART model shown is completely different and is not specifically limited here.

[0109] S705, the wearable watch 200 inputs the feature information i into the classification model 2 to obtain the number of tapping times and tapping positions.

[0110] Among them, classification model 2 is a multimodal task model, which can be used to output the number of taps and the tapping position. Optionally, there can be three classification results for the number of taps, namely: 2 times, 3 times, and others. There are also three classification results for the tapping position: the top of the case 301, the bottom of the case 301, and the dial 302. In this way, the wearable watch 200 can determine the first gesture according to the number of taps and the tapping position.

[0111] In an optional implementation, the classification model 2 may be one or a combination of logistic regression, decision tree, convolutional neural network (CNN), etc. In an optional implementation, the classification model 2 may be referred to as a first classification model.

[0112] It can be understood that the embodiment of the present application performs a preliminary screening of the ACC signal through S704, and inputs the feature information i into the classification model 2 only when the ACC signal may be a knocking signal. This can reduce the number of times the classification model 2 is run, thereby saving computing resources.

[0113] Optionally, the wearable watch 200 may execute S705 directly without executing S704, which can speed up the processing flow and improve efficiency.

[0114] In the embodiment of the present application, the wearable watch 200 also pre-stores the correspondence between the user gesture and the operation (referred to as operation) to be performed after receiving the user gesture. In this way, after the wearable watch 200 determines the first gesture, the operation corresponding to the first gesture can be obtained according to the first gesture and the above correspondence, and the corresponding operation can be performed. Exemplarily, the above correspondence can be expressed in the form of a user gesture-operation correspondence table, as shown in Table 1.

[0115] Table 1

[0116]

[0117] According to Table 1, if the first gesture is double-clicking the top of the case, the wearable watch 200 can turn on the sports mode; if the first gesture is triple-clicking the dial, the wearable watch 200 can answer the call.

[0118] Considering that the user gestures that can be distinguished by the tapping position and the number of tapping times are limited, in another optional implementation, the user gestures can be further distinguished by the specific position where the user taps the dial. Specifically, when the tapping position is determined to be the dial 302, the wearable watch 200 can also determine the tapping area according to the coordinate information corresponding to the first gesture, and the tapping area is, for example, Fig. 9The middle area 801, the upper left area 802, the lower left area 803, the upper right area 804, the lower right area 805, etc. of the dial 302 are shown. In this case, the above correspondence can be as shown in Table 2.

[0119] Taking the following Table 2 as an example, when the wearable watch 200 is worn, in response to the user touching the button 303 and the user double-clicking the top of the case 301, the wearable watch 200 can turn on the sports mode; in response to the user touching the button 303 and the user double-clicking the bottom of the case, the wearable watch 200 can turn on the smart voice assistant.

[0120] Table 2

[0121]

[0122] It should be noted that the corresponding relationships shown in Table 1 and Table 2 are only examples, and in actual application, the operations corresponding to the user gestures can be set according to the user's own needs.

[0123] Among them, the user can quickly double-click the top of the case 301 after touching the button 303, or quickly touch the button 303 after double-clicking the top of the case 301, or touch the button 303 and double-click the top of the case 301 at the same time (for example, double-click the top of the case 301 while holding down the button 303). The same applies to other user gestures, which will not be described in detail here.

[0124] See also Fig.10 , is an interface diagram for setting interactive gestures. Fig.10 As shown, the wearable watch 200 can display interface 901, which is an interface for setting applications. The interface 901 includes options such as auxiliary function 902, wallet, sports health, etc. The wearable watch 200 can receive the user's operation on the auxiliary function 902. In response to the operation, the wearable watch 200 can display interface 903, which is an interface for auxiliary functions, including options such as gesture 904 and hand washing. The wearable watch 200 can receive the user's operation on gesture 904. In response to the operation, the wearable watch 200 can display interface 905, which includes multiple user gestures and more options corresponding to each user gesture. For example, multiple user gestures include double-clicking the top of the case and double-clicking the dial. If the user wants to set the operation corresponding to the user gesture of "double-clicking the top of the case", he can click on more options 906 corresponding to double-clicking the top of the case. In response to the operation, the wearable watch 200 can display interface 907, and interface 907 can provide multiple operations for the user to choose, such as opening the payment code 908, opening the sports mode, etc. In response to the user's operation of clicking to open the payment code 908, the wearable watch 200 sets the operation corresponding to the user gesture of double-clicking the top of the watch case as opening the payment code.

[0125] It should be noted that the user can also set the interactive gesture on the mobile phone or tablet connected to the wearable watch 200, and the process is the same as Fig.10 The process shown is similar and will not be repeated here.

[0126] In an optional implementation, the wearable watch 200 may also shield the screen touch event after recognizing and receiving the above-mentioned first operation. Shielding the screen touch event can be understood as not responding to any touch operation of the user on the dial 302, so as to avoid the situation where the content displayed on the dial 302 jumps due to the user's first gesture.

[0127] See also Fig.11 , is a flow chart of a gesture interaction method provided in an embodiment of the present application. Fig.11 As shown, the gesture interaction method includes S1101~S1107.

[0128] S1101, determining whether the wearable watch is worn by the user.

[0129] If the wearable watch is worn by the user, execute S1102 and S1104; if the wearable watch is not worn by the user, end the process.

[0130] S1102, obtaining an ACC signal.

[0131] S1103: Determine a first gesture according to the ACC signal.

[0132] The process of determining the first gesture according to the ACC signal can be found in the previous text and will not be repeated here.

[0133] S1104, acquiring ECG signal.

[0134] S1105: Determine whether a first operation is received according to the ECG signal.

[0135] If the first operation is received, S1106 and S1107 are executed; if the first operation is not received, the process ends.

[0136] The process of determining whether the first operation is received according to the ECG signal can be found in the previous text and will not be repeated here.

[0137] S1106, executing an operation corresponding to the first gesture.

[0138] S1107, shielding screen touch events.

[0139] It should be noted that Fig.11The process shown is for illustration only, and the above S1105 may be executed before S1102 or after S1102, or simultaneously with S1102. It is only necessary to complete S1105 before executing the operation corresponding to the first gesture (ie, before S1106).

[0140] It can be seen that the gesture interaction method provided in the embodiment of the present application will only execute the operation corresponding to the user gesture when it is determined that the user has the intention to use the gesture to trigger the corresponding function, which can reduce the risk of accidental touches and improve the user experience.

[0141] The present application also provides a chip system, such as Fig.12 As shown, the chip system 1200 includes at least one processor 1201 and at least one interface circuit 1202. The processor 1201 and the interface circuit 1202 can be interconnected through lines. For example, the interface circuit 1202 can be used to receive signals from other devices (such as the memory of the electronic device). For another example, the interface circuit 1202 can be used to send signals to other devices (such as the processor 1201). Exemplarily, the interface circuit 1202 can read the instructions stored in the memory and send the instructions to the processor 1201. When the instructions are executed by the processor 1201, the electronic device or server can execute the various steps in the above embodiments. Of course, the chip system can also include other discrete devices, which are not specifically limited in the embodiments of the present application.

[0142] This embodiment also provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on an electronic device, the electronic device executes each function or step in the above method embodiment.

[0143] This embodiment also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute each function or step in the above method embodiment.

[0144] In addition, an embodiment of the present application also provides a device, which can specifically be a chip, component or module, and the device may include a connected processor and memory; wherein the memory is used to store computer-executable instructions, and when the device is running, the processor can execute the computer-executable instructions stored in the memory so that the chip executes each function or step performed by the mobile phone in the above method embodiment.

[0145] Among them, the electronic device, communication system, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above and will not be repeated here.

[0146] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0147] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0148] The unit described as a separate component may or may not be physically separated, and the component shown as a unit may be one physical unit or multiple physical units, that is, it may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0149] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0150] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A gesture interaction method, characterized in that: Applied to a wearable device, the wearable device includes a watch case, a watch dial, a button, and an electrocardiogram sensor, the electrocardiogram sensor includes a first electrode and a second electrode, the watch dial and the first electrode are respectively arranged on two opposite sides of the watch case, the button is arranged on a side of the watch case, and the second electrode is arranged on the button, the method includes: A first operation and a first gesture of a first user are received within a first time period, where the first user is a user wearing the wearable device; wherein the first operation includes an operation in which the first user simultaneously contacts the first electrode and the second electrode with skin, and the first gesture is a gesture in which the user taps a preset position of the wearable device, and the first gesture is associated with a tap count and a tap position, where the tap count is the number of times the first user taps the wearable device, and the tap position is the position where the first user taps the wearable device; Execute the operation corresponding to the first gesture; In response to receiving the first gesture but not receiving the first operation, the operation corresponding to the first gesture is not performed.

2. The method according to claim 1, characterized in that The wearable device includes an electrocardiogram sensor, and before receiving a first operation and a first gesture of a first user within a first time period, the method further includes: Acquiring a biometric signal collected by the electrocardiogram sensor; Receipt of the first operation is determined according to the biometric signal.

3. The method according to claim 1, characterized in that The wearable device further includes an accelerometer. Before receiving a first operation and a first gesture of a first user within a first time period, the method further includes: Acquiring an accelerometer signal collected by the accelerometer; Receipt of the first gesture is determined based on the accelerometer signal.

4. The method according to claim 3, characterized in that The accelerometer signal includes x-axis acceleration, y-axis acceleration, and z-axis acceleration, and determining that the first gesture is received according to the accelerometer signal includes: Determining a first differential signal, a second differential signal, a third differential signal, and a combined acceleration of the x-axis acceleration, the y-axis acceleration, and the z-axis acceleration according to the x-axis acceleration, the y-axis acceleration, and the z-axis acceleration, wherein the first differential signal is a differential signal of the x-axis acceleration, the second differential signal is a differential signal of the y-axis acceleration, and the third differential signal is a differential signal of the z-axis acceleration; Extracting characteristic information of the x-axis acceleration, the y-axis acceleration, the z-axis acceleration, the first differential signal, the second differential signal, the third differential signal and the combined acceleration respectively, each characteristic information comprising one or more of the number of peaks, the number of troughs, peak value, trough value, peak-to-trough distance, kurtosis and slope; It is determined that the first gesture is received based on the plurality of feature information.

5. The method according to claim 4, characterized in that The determining, according to the plurality of feature information, that the first gesture is received includes: Inputting the plurality of feature information into a first classification model to obtain a first output result of the first classification model, wherein the first output result includes the number of knocks and the knock position; It is determined that the first gesture is received according to the number of taps and the tap position.

6. The method according to claim 4, characterized in that Before inputting the plurality of feature information into a first classification model to obtain a first output result of the first classification model, the method further includes: Inputting the plurality of feature information into a decision tree model to obtain a second output result of the decision tree model; The step of inputting the plurality of feature information into a first classification model to obtain a first output result of the first classification model includes: When the second output result indicates that the accelerometer signal is a tapping signal, the multiple feature information are input into a first classification model to obtain a first output result of the first classification model, and the tapping signal is a signal generated by a user tapping the wearable device.

7. The method according to claim 5, characterized in that The determining, according to the number of taps and the tap position, that the first gesture is received includes: When the tapping position is the first area of ​​the wearable device, acquiring coordinate information of the tapping position; Determining a tapping area according to the coordinate information of the tapping position; It is determined that the first gesture is received according to the number of taps and the tap area.

8. The method according to any one of claims 1 to 7, characterized in that: The wearable device includes a display screen, and the method further includes: In response to receiving the first operation, the wearable device shields touch events acting on the display screen.

9. The method according to any one of claims 1 to 7, characterized in that: The receiving a first operation and a first gesture of a first user within a first time period includes: At a first moment in a first time period, receiving the first operation; At a second time after the first time within the first time period, the first gesture is received.

10. The method according to any one of claims 1 to 7, characterized in that: The receiving a first operation and a first gesture of a first user within a first time period includes: At a first moment in a first time period, receiving the first gesture; At a second time after the first time within the first time period, the first operation is received.

11. The method according to any one of claims 1 to 7, characterized in that: The receiving a first operation and a first gesture of a first user within a first time period includes: At a first moment in a first time period, the first operation and the first gesture are received.

12. A wearable device, characterized in that: The wearable device comprises: a memory and a processor; the processor is coupled to the memory; wherein the memory is used to store computer program code, and the computer program code comprises computer instructions; when the computer instructions are executed by the processor, the wearable device executes the method as described in any one of claims 1-11.

13. A computer-readable storage medium, characterized in that: The invention comprises computer instructions; when the computer instructions are executed on a wearable device, the wearable device executes the method as described in any one of claims 1 to 11.

Images