Wearing state recognition method and device

Abstract

The application provides a wearing state recognition method and device, which can improve the accuracy of the wearable device in recognizing the wearing state under the premise of low cost. The method comprises the following steps: the wearable device can send a plurality of vibration signals with different parameters through a vibration motor. Then, the wearable device can collect the signal fed back by the vibration signal through the transmission medium (such as human fat, air or clothes, etc.) through a sensor, that is, the wearable device collects the feedback signal. Finally, the wearable device can recognize the wearing state of itself according to the feedback signal.

Description

Technical Field

[0001] This application relates to the field of communications, and more particularly to a method and apparatus for identifying wearing status. Background Technology

[0002] With the popularization of wearable devices, the technology of identifying whether a user is wearing a wearable device or the tightness of the wearer's fit has become one of the commonly used functions. Wearing status recognition technology is also a powerful guarantee for wearable devices to monitor the user's health status.

[0003] Currently, common methods for wearability status recognition include the following: One method involves using general-purpose sensors, such as infrared rays or ultrasound, to collect detection signals. The current wearing status of the wearable device, such as not wearing it or wearing it too tightly, is determined based on the detection signals returned by the general-purpose sensors. Another method involves using custom sensors to collect sensing signals. For example, a pressure sensor can collect the strain force applied to the wearable device, and the current wearing status of the corresponding wearable device is determined based on the readings of the custom sensor.

[0004] However, methods relying on general-purpose sensors to identify wearing status are susceptible to the influence of different transmission media, such as varying body fat percentages, leading to inaccurate measurements from different users and resulting in misjudgments. Furthermore, methods using custom sensors require additional sensors that are difficult to customize and often lack functionality beyond simply identifying wearing status, resulting in high costs. In conclusion, none of the aforementioned methods for identifying wearing status can simultaneously achieve both accuracy and cost-effectiveness. Summary of the Invention

[0005] This application provides a method and apparatus for identifying wearing status, which can solve the technical problem that the methods of identifying wearing status based on general sensors and those based on customized sensors cannot simultaneously achieve both accuracy and cost, thereby improving the accuracy of identifying wearing status and saving costs.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] Firstly, a method for identifying wearing status is provided, which can be applied to wearable devices. The wearable device may include one or more vibration motors and one or more sensors. The vibration motors are used to send vibration signals, and the sensors are used to collect feedback signals from the vibration signals. The wearable device can send N vibration signals, where N ≥ 2, and N is a positive integer. The signal parameters of the N vibration signals are different, and the signal parameters may include frequency and / or waveform. Then, the wearable device can collect the feedback signals from the N vibration signals. The feedback signals may include: signals fed back by the human body from the N vibration signals when the wearable device is in a wearing state, or signals fed back by other media from the N vibration signals when the wearable device is not in a wearing state. Finally, based on the feedback signals, the wearable device can identify its own wearing status. The wearing status of the wearable device can be either a wearing state or a non-wearing state.

[0008] In this application, during the process of identifying the wearing status, the wearable device can send multiple vibration signals with different parameters. Then, the wearable device can collect the feedback signal from the vibration signals after passing through a transmission medium (such as body fat, air, or clothing), i.e., the wearable device collects the feedback signal. Finally, the wearable device can identify its own wearing status (such as being worn or not worn) based on the feedback signal.

[0009] In summary, the method described in this application allows wearable devices to identify wearing status using the combined action of a vibration motor and sensors, eliminating the need for additional custom sensors and reducing costs. Furthermore, since transmission media (such as human fat with varying body fat content or air) have different filtering effects on different vibration signals (such as vibration signals with different frequencies and / or waveforms), this method allows the feedback signal to reflect the filtering effect of the transmission medium on different vibration signals in the current wearing state. The wearable device can then identify its wearing status from multiple different vibration signal perspectives based on this feedback signal. This reduces the impact of the transmission medium on the accuracy of wearing status identification, improving accuracy and thus solving the technical problem of not being able to simultaneously achieve both accuracy and cost in methods based on general-purpose sensors and methods based on custom sensors.

[0010] In one possible design of the first aspect, the wearable device may include multiple vibration motors, each positioned differently within the device. This difference in the location of the vibration signals generated by the different motors results in different transmission directions for the vibration signals. These different transmission directions lead to varying filtering effects of the transmission medium on the vibration signals. Consequently, the wearable device can identify the wearing status from different perspectives based on the feedback signals from the vibration signals, further reducing the influence of the transmission medium on the identification of the wearing status and improving the accuracy of the identification.

[0011] In another possible design approach of the first aspect, the worn state may include: a first loose state, a second loose state, and a third loose state. In the first loose state, the wearable device may be worn more loosely than normally; in the second loose state, the wearable device may be worn more tightly than normally; and in the third loose state, the wearable device may be worn at its normal tightness.

[0012] In other words, when a wearable device is in a worn state, it can also determine a tightness state (such as a first tightness state, a second tightness state, or a third tightness state) that characterizes the tightness of the wear. Based on the characteristics of these three tightness states, the first tightness state can also be called the "too loose" state, the second tightness state can also be called the "too tight" state, and the third tightness state can also be called the "suitable" state.

[0013] In another possible design of the first aspect, if the wearable device is in a first tight state, it can issue a first prompt message instructing the user to adjust the tightness of the wearable device. If the wearable device is in a second tight state, it can issue a second prompt message instructing the user to loosen the tightness of the wearable device.

[0014] In other words, if the wearable device is too loose, it can instruct the user to tighten it, and if it is too tight, it can instruct the user to loosen it.

[0015] In another possible design approach of the first aspect, the wearable device can adjust the measurement weights of the user's physiological data based on the tightness of the wearable device when it is worn. Specifically, the measurement weight in the third tightness state is greater than the measurement weight in the first tightness state, and the measurement weight in the third tightness state is also greater than the measurement weight in the second tightness state.

[0016] For example, when worn too loosely or too tightly, wearable devices can reduce the measurement weight of user physiological data, indicating that the reliability of physiological data measured under the current wearing condition is low. When worn properly, wearable devices can increase the measurement weight of user physiological data, indicating that the reliability of physiological data measured under the current wearing condition is high.

[0017] In another possible design of the first aspect, the wearable device can send N vibration signals, which may include: in response to a first operation by the user, the wearable device can send N vibration signals, the first operation being used to trigger the wearable device to measure the user's physiological data. Alternatively, in response to an incoming call, new message, or reminder event, the wearable device can send N vibration signals, the N vibration signals being used to indicate an incoming call, new message, or reminder event.

[0018] In this way, wearable devices can emit vibration signals to identify the wearing status when the user actively triggers the measurement of the user's physiological data. This can reduce the inaccuracy of measurement caused by improper tightness of the wearer, thereby improving the accuracy of wearable devices in measuring the user's physiological data.

[0019] Furthermore, wearable devices can also emit vibration signals to remind users in scenarios such as incoming calls, new messages, or reminder events, while simultaneously using the vibration signals to identify the wearing status. This can prevent the wearable device from vibrating suddenly when identifying the wearing status, thus avoiding any impact on the user experience.

[0020] In another possible design approach of the first aspect, if the wearable device is not being worn, it can control itself to enter a low-power mode to conserve the wearable device's resources.

[0021] In another possible design approach of the first aspect, the wearable device may include a preset recognition model, which has the ability to identify the wearing state of the wearable device based on feedback signals of N vibration signals. Accordingly, the aforementioned ability of the wearable device to identify its own wearing state based on feedback signals can include: the wearable device can use the preset recognition model to obtain its wearing state based on the feedback signals. Thus, using the preset recognition model allows for rapid identification of the wearable device's wearing state, improving recognition efficiency.

[0022] In another possible design approach of the first aspect, the preset recognition model can be a classifier. Accordingly, the wearable device can obtain its wearing state based on the feedback signal and the preset recognition model. This can include: the wearable device acquiring the signal characteristics of the feedback signal, using these characteristics as input to a classifier, running the classifier, and outputting the wearing state of the wearable device. The signal characteristics of the feedback signal can include: the root mean square of the signal amplitude of the feedback signal within a preset time period and the median frequency of the feedback signal.

[0023] In other words, wearable devices can pre-extract the signal features of the feedback signal (such as the root mean square of the signal amplitude and the median frequency of the feedback signal within a preset time period), and then use a classifier to quickly identify the wearing status of the wearable device based on the signal features, thereby improving the recognition efficiency.

[0024] In another possible design approach of the first aspect, the preset recognition model can be a neural network model. Accordingly, the wearable device can obtain its wearing state based on the feedback signal and the preset recognition model. This can include: the wearable device can use the feedback signal as input to the neural network model, run the neural network model, and output the wearing state of the wearable device. The neural network model can be used to acquire the signal characteristics of the feedback signal and, based on these characteristics, obtain and output the wearing state of the wearable device. The signal characteristics of the feedback signal can include: the root mean square of the signal amplitude of the feedback signal within a preset time period and the median frequency of the feedback signal.

[0025] In other words, wearable devices can utilize neural network models to extract signal features from feedback signals and identify wearing status based on signal features, thereby further improving recognition efficiency.

[0026] Specifically, if the root mean square (RMS) is greater than a first RMS threshold and the median frequency is less than a first frequency threshold, the wearable device can be in an unworn state. Alternatively, if the RMS is greater than a second RMS threshold and the median frequency is greater than a second frequency threshold, the wearable device can be in a worn state. The first and second RMS thresholds may be the same or different, and the first frequency threshold may be less than or equal to the second frequency threshold.

[0027] In other words, taking the signal characteristics, including the root mean square of the amplitude of the feedback signal within a preset time period and the median frequency of the feedback signal, as an example, the preset recognition model can quickly identify whether the wearable device is in a worn state or not when the root mean square and the median frequency meet the above conditions, thereby improving the efficiency of wearing state recognition.

[0028] Specifically, if the root mean square (RMS) is greater than the third RMS threshold and the median frequency is less than the third frequency threshold, the wearable device can be in the first loose / tight state. If the RMS is less than the fourth RMS threshold and the median frequency is greater than the fourth frequency threshold, the wearable device can be in the second loose / tight state. Here, the third RMS threshold is greater than or equal to the fourth RMS threshold, and the third frequency threshold is less than or equal to the fourth frequency threshold.

[0029] Continuing with the above example, the preset recognition model can also quickly identify the tightness of the wearable device when the root mean square and median frequency meet the above conditions, that is, whether the wearable device is in the first tightness state or the second tightness state, thereby improving the efficiency of wearing status recognition.

[0030] In another possible design approach of the first aspect, before the wearable device can obtain the wearing state of the wearable device by using a preset recognition model based on the feedback signal, the wearable device can acquire training samples and use the training samples to train the preset recognition model, so that the preset recognition model has the ability to recognize the wearing state of the wearable device based on the feedback signals of N vibration signals.

[0031] The training samples can include input samples and output samples. The input samples can include multiple sample feedback signals or signal characteristics of multiple sample feedback signals. These multiple sample feedback signals can include: feedback signals from multiple users with different body fat percentages wearing the wearable device in response to N vibration signals, and feedback signals from other media in response to N vibration signals when the wearable device is not worn. Correspondingly, the output samples can be the actual wearing state corresponding to the input samples. Furthermore, the signal characteristics of the sample feedback signals can include: the root mean square of the signal amplitude of the sample feedback signal within a preset time period and the median frequency of the sample feedback signal.

[0032] Taking a preset recognition model as a classifier as an example, the input sample can include the signal features of multiple sample feedback signals, and the output sample can include the actual wearing state corresponding to the input sample. Thus, the trained classifier can identify the wearing state of the wearable device based on signal features when users with different body fat percentages wear the wearable device, or when the wearable device is not worn.

[0033] Taking a neural network model as an example, the input sample can include multiple sample feedback signals, and the output sample can include the actual wearing state corresponding to the input sample. Thus, the trained classifier can identify the wearing state of the wearable device based on the feedback signals when users with different body fat percentages wear the wearable device, or when the wearable device is not worn.

[0034] Secondly, embodiments of this application provide a wearable device, which may include one or more vibration motors, one or more sensors, a memory, and one or more processors. The one or more vibration motors, one or more sensors, the memory, and the processor are coupled together. The vibration motors can be used to generate vibration signals, the sensors can be used to collect feedback signals from the vibration signals, and the memory can be used to store computer program code, which may include computer instructions.

[0035] When the processor executes computer instructions, the wearable device performs the following operations: Sends N vibration signals, where N ≥ 2, and N is a positive integer. The N vibration signals have different signal parameters, including frequency and / or waveform. Collects feedback signals from the N vibration signals. These feedback signals include: signals fed back from the human body when the wearable device is worn, or signals fed back from other media when the wearable device is not worn. Based on the feedback signals, identifies the wearing status of the wearable device. The wearing status of the wearable device is either worn or not worn.

[0036] In one possible design approach of the second aspect, the wearable device may include multiple vibration motors, with different vibration motors located in different positions within the wearable device.

[0037] In another possible design approach in the second aspect, the worn state can include: a first loose state, a second loose state, and a third loose state. In the first loose state, the wearable device can be worn looser than normally; in the second loose state, the wearable device can be worn tighter than normally; and in the third loose state, the wearable device can be worn at its normal tightness.

[0038] In another possible design of the second aspect, when the processor executes computer instructions, the wearable device further performs the following steps: if the wearable device is in a first loose state, a first prompt message is issued, instructing the user to adjust the tightness of the wearable device; if the wearable device is in a second loose state, a second prompt message is issued, instructing the user to loosen the tightness of the wearable device.

[0039] In another possible design approach of the second aspect, when the processor executes computer instructions, the wearable device further performs the following steps: adjusting the measurement weights of the wearable device for measuring the user's physiological data based on the tightness of the wearable device. Specifically, the measurement weights in the third tightness state are greater than those in the first tightness state, and the measurement weights in the third tightness state are also greater than those in the second tightness state.

[0040] In another possible design approach of the second aspect, when the processor executes computer instructions, the wearable device also performs the following steps: in response to a first user action, sending N vibration signals, the first action being used to trigger the wearable device to measure the user's physiological data. Alternatively, in response to an incoming call, new message, or reminder event, sending N vibration signals, the N vibration signals being used to indicate an incoming call, new message, or reminder event.

[0041] In another possible design approach in the second aspect, when the processor executes computer instructions, the wearable device also performs the following steps: if the wearable device is not being worn, the wearable device is controlled to enter a low-power mode.

[0042] In another possible design approach of the second aspect, the wearable device may include a preset recognition model, which may be capable of recognizing the wearing state of the wearable device based on feedback signals of N vibration signals. Accordingly, when the processor executes computer instructions, the wearable device further performs the following steps: based on the feedback signals, using the preset recognition model, to obtain the wearing state of the wearable device.

[0043] In another possible design approach for the second aspect, the preset recognition model can be a classifier. Accordingly, when the processor executes computer instructions, the wearable device further performs the following steps: acquiring signal characteristics of the feedback signal, which may include the root mean square of the signal amplitude of the feedback signal over a preset duration and the median frequency of the feedback signal. Using the signal characteristics as input to the classifier, the classifier is run, and the wearing status of the wearable device is output.

[0044] In another possible design approach of the second aspect, the preset recognition model can be a neural network model. Accordingly, when the processor executes computer instructions, the wearable device further performs the following steps: using the feedback signal as input to the neural network model, running the neural network model, and outputting the wearing state of the wearable device. The neural network model can be used to acquire the signal characteristics of the feedback signal and, based on these characteristics, obtain and output the wearing state of the wearable device. These signal characteristics may include: the root mean square of the signal amplitude of the feedback signal within a preset time period and the median frequency of the feedback signal.

[0045] In another possible design approach of the second aspect, if the root mean square (RMS) is greater than a first RMS threshold and the median frequency is less than a first frequency threshold, the wearable device is in an unworn state. Alternatively, if the RMS is greater than a second RMS threshold and the median frequency is greater than a second frequency threshold, the wearable device is in a worn state. Here, the first RMS threshold and the second RMS threshold may be the same or different, and the first frequency threshold is less than or equal to the second frequency threshold.

[0046] In another possible design approach of the second aspect, when the wearable device is in a worn state, if the root mean square (RMS) is greater than a third RMS threshold and the median frequency is less than a third frequency threshold, the wearable device is in a first loose / tight state. If the RMS is less than a fourth RMS threshold and the median frequency is greater than a fourth frequency threshold, the wearable device is in a second loose / tight state. Here, the third RMS threshold is greater than or equal to the fourth RMS threshold, and the third frequency threshold is less than or equal to the fourth frequency threshold.

[0047] In another possible design approach of the second aspect, when the processor executes computer instructions, the wearable device also performs the following steps: acquiring training samples and using the training samples to train a preset recognition model, so that the preset recognition model has the ability to recognize the wearing status of the wearable device based on the feedback signals of N vibration signals.

[0048] The training samples may include input samples and output samples. The input samples may include multiple sample feedback signals or signal characteristics of multiple sample feedback signals. These multiple sample feedback signals may include: feedback signals from multiple users with different body fat percentages wearing the wearable device in response to N vibration signals, and feedback signals from other media in response to N vibration signals when the wearable device is not worn. The output samples may be the actual wearing state corresponding to the input samples. The signal characteristics of the aforementioned sample feedback signals may include: the root mean square of the signal amplitude of the sample feedback signal within a preset time period and the median frequency of the sample feedback signal.

[0049] Thirdly, embodiments of this application provide a chip system applied to a wearable device including one or more vibration motors and one or more sensors. The chip system includes one or more interface circuits and one or more processors. The interface circuits and processors are interconnected via lines. The interface circuits are used to receive signals from the wearable device's memory and send signals to the processor, the signals including computer instructions stored in the memory; when the processor executes the computer instructions, the wearable device performs the method described in the first aspect and any possible design of the method.

[0050] Fourthly, embodiments of this application provide a computer storage medium including computer instructions that, when executed on a wearable device, cause the wearable device to perform the method described in the first aspect and any possible design thereof.

[0051] Fifthly, embodiments of this application provide a computer program product that, when run on a computer, causes the computer to perform the method described in the first aspect and any possible design thereof. The computer may be a wearable device as described in the second aspect and any possible design thereof.

[0052] It is understood that the beneficial effects achieved by the wearable device described in the second aspect, the chip system described in the third aspect, the computer storage medium described in the fourth aspect, and the computer program product described in the fifth aspect can be referred to as the beneficial effects in the first aspect and any possible design, which will not be repeated here. Attached Figure Description

[0053] Figure 1 A flowchart illustrating a method for identifying the wearing status of a wearable device;

[0054] Figure 2 This is a schematic diagram of the structure of a wearable device provided in an embodiment of this application;

[0055] Figure 3 A schematic diagram of the structure of the smartwatch provided in the embodiments of this application. Figure 1 ;

[0056] Figure 4 A schematic diagram of the structure of the smartwatch provided in the embodiments of this application. Figure 2 ;

[0057] Figure 5 A schematic diagram of the structure of the smart belt provided in the embodiments of this application. Figure 1 ;

[0058] Figure 6 A schematic diagram of the structure of the smart belt provided in the embodiments of this application. Figure 2 ;

[0059] Figure 7 A flowchart illustrating a method for recognizing wearing status provided in an embodiment of this application;

[0060] Figure 8 This is a schematic diagram of the display interface of a wearable device provided in an embodiment of this application;

[0061] Figure 9 This is a schematic diagram of the display interface of another wearable device provided in an embodiment of this application;

[0062] Figure 10 This is a schematic diagram of module interaction for a wearable device provided in an embodiment of this application;

[0063] Figure 11 This is a schematic diagram of a chip system provided in an embodiment of this application. Detailed Implementation

[0064] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "a plurality of" means two or more.

[0065] For ease of understanding, this application provides a detailed description of the wearing status recognition method to illustrate that conventional wearing status recognition methods are difficult to balance accuracy and cost.

[0066] For wearable devices that utilize general-purpose sensors to identify wearing status, the device can include a signal generator and a general-purpose sensor. The signal generator (such as a speaker or LED light) can generate detection signals (such as ultrasonic signals, sound wave signals, or photoplethysmography signals). The general-purpose sensor (such as a microphone or photoelectric sensor) can collect the detection signals transmitted through a transmission medium, and the wearable device can identify the wearing status based on the collected detection signals.

[0067] For example, Figure 1 (a) in the diagram illustrates the process of a wearable device identifying its wearing status. Figure 1 Wearable devices can use a signal generator to produce a detection signal (such as a first detection signal), and then use a general sensor to collect the transmitted detection signal (such as a second detection signal). Because the detection signal is affected by different transmission media (such as human fat or air with different body fat contents) during transmission under different wearing conditions, the detection signal collected by the wearable device will differ depending on whether the device is worn or not. Therefore, the wearing status of the wearable device can be identified based on the detection signal.

[0068] like Figure 1 As shown in (a), after the wearable device collects the second detection signal, it can extract the signal features of the second detection signal (such as time domain features, frequency domain features, or time-frequency domain features), and perform wearing status recognition based on the signal features to obtain the wearing status of the wearable device (worn or not worn), thus realizing the mapping from the signal features of the detection signal to the wearing status.

[0069] Furthermore, when the wearable device is in a worn state, it can also identify the tightness of the wear based on the signal characteristics of the second detection signal. The specific implementation method for identifying the tightness can be found in the aforementioned implementation method for wearable devices to identify wearing status, and will not be repeated here.

[0070] However, based on the method of identifying wearing status using general sensors, the single detection signal emitted by wearable devices is easily affected by the different contents of the transmission medium, such as the body fat content of the human body, which leads to deviations in the signals measured by different users and causes misjudgments.

[0071] Furthermore, some general-purpose sensors (such as distance sensors, capacitive sensors, or photoplethysmography sensors) require additional openings in wearable devices to collect detection signals, which hinders waterproofing design and makes the devices more susceptible to damage. Moreover, general-purpose sensors are easily affected by environmental factors (such as light or temperature), which can lead to misjudgments.

[0072] Wearable devices can include custom sensors to identify wearing status. These custom sensors (such as capacitive plate sensors, strain gauges, pressure sensors, and resistance sensors) can collect sensing signals. For example, a pressure sensor can collect the strain force applied to the wearable device, and a capacitive plate sensor can collect the capacitance value on a capacitor plate. The wearable device can then identify its wearing status based on the collected sensing signals.

[0073] like Figure 1 As shown in (b) in the figure, Figure 1 (b) shows a schematic diagram of the process by which a wearable device identifies its wearing status. Figure 2 Wearable devices utilize custom sensors (such as capacitive plate sensors, strain gauges, pressure sensors, and resistance sensors) to collect sensing signals (such as strain applied to the wearable device, or capacitance values ​​on the capacitive plate). Because the user's perception of the sensing signals varies depending on the wearing state, the wearable device collects different sensing signals depending on whether it is in a worn state or not. This allows the wearer to identify the wearing status of the wearable device based on these sensing signals.

[0074] like Figure 1 As shown in (b), after collecting the sensor signal, the wearable device can identify the wearing status based on the sensor signal to obtain the wearing status (worn or not worn) of the wearable device, thus realizing the mapping from the sensor signal to the wearing status.

[0075] However, methods based on custom sensors to identify wearing status require additional custom sensors, which are difficult to implement for functions other than identifying wearing status, and are costly. In summary, none of the above-mentioned methods for identifying wearing status can simultaneously achieve both accuracy and cost.

[0076] This application provides a method for identifying wearing status, applied to a wearable device that may include a vibration motor and a sensor. Since different wearing statuses result in different filtering effects on vibration signals, after the wearable device emits N vibration signals, it can collect different feedback signals when it is not being worn or when it is being worn by different users, and identify its own wearing status based on these feedback signals. Thus, using the method of this application, the wearable device can identify its wearing status by utilizing the cooperation of the vibration motor and the sensor, eliminating the need for additional customized sensors and reducing costs.

[0077] Furthermore, since the transmission medium (such as human fat with different body fat percentages or air) has varying filtering effects on different vibration signals (such as vibration signals with different frequencies and / or waveforms), this method allows the feedback signal of the vibration signal to reflect the filtering effect of the transmission medium on different vibration signals in the current wearing state. The wearable device can then identify its wearing state from multiple different vibration signal perspectives based on this feedback signal. This reduces the impact of the transmission medium on the accuracy of wearing state identification, improving accuracy and thus solving the technical problem of not being able to simultaneously achieve both accuracy and cost in methods based on general-purpose sensors and methods based on customized sensors.

[0078] For example, the wearable device in this application embodiment may be an electronic device such as a smartwatch, wireless earphone, smart belt, and augmented reality (AR) / virtual reality (VR) device. This application embodiment does not impose any special restrictions on the specific form of the wearable device.

[0079] The embodiments of this application will now be described in detail with reference to the accompanying drawings. Please refer to... Figure 2 This is a structural schematic diagram of a wearable device 200 provided in an embodiment of this application. Figure 2As shown, the wearable device 200 may include: a processor 210, an external memory interface 210, an internal memory 221, a universal serial bus (USB) interface 230, a charging management module 240, a power management module 241, a battery 241, an antenna 1, an antenna 2, a mobile communication module 250, a wireless communication module 260, an audio module 270, a speaker 270A, a receiver 270B, a microphone 270C, a headphone jack 270D, a sensor module 280, buttons 290, a vibration motor 291, an indicator 291, a camera 293, a display screen 294, and a subscriber identification module (SIM) card interface 295, etc.

[0080] The aforementioned sensor module 280 may include sensors such as a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer, a distance sensor, a proximity sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, and a bone conduction sensor.

[0081] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the wearable device 200. In other embodiments, the wearable device 200 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0082] Processor 210 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, memory, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.

[0083] The controller can serve as the neural center and command center of the wearable device 200. The controller can generate operation control signals based on instruction opcodes and timing signals to control the fetching and execution of instructions.

[0084] The processor 210 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 210 is a cache memory. This memory can store instructions or data that the processor 210 has just used or that are used repeatedly. If the processor 210 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 210, and thus improves the efficiency of the system.

[0085] In some embodiments, the processor 210 may include one or more interfaces. Interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0086] It is understood that the interface connection relationships between the modules illustrated in this embodiment are merely illustrative and do not constitute a structural limitation on the wearable device 200. In other embodiments, the wearable device 200 may also employ different interface connection methods or combinations of multiple interface connection methods as described in the above embodiments.

[0087] The charging management module 240 receives charging input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 240 receives charging input from the wired charger via a USB interface 230. In some wireless charging embodiments, the charging management module 240 receives wireless charging input via the wireless charging coil of the wearable device 200. While charging the battery 241, the charging management module 240 can also supply power to the wearable device 200 via the power management module 241.

[0088] The power management module 241 connects the battery 241, the charging management module 240, and the processor 210. The power management module 241 receives input from the battery 241 and / or the charging management module 240, providing power to the processor 210, internal memory 221, external memory, display screen 294, camera 293, and wireless communication module 260. The power management module 241 can also monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage current, impedance). In some other embodiments, the power management module 241 may also be located within the processor 210. In other embodiments, the power management module 241 and the charging management module 240 may be housed in the same device.

[0089] The wireless communication function of the wearable device 200 can be implemented through antenna 1, antenna 2, mobile communication module 250, wireless communication module 260, modem processor, and baseband processor.

[0090] Antennas 1 and 2 are used to transmit and receive electromagnetic wave signals. Each antenna in the wearable device 200 can be used to cover one or more communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with a tuning switch.

[0091] The mobile communication module 250 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to wearable devices 200. The mobile communication module 250 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc.

[0092] The wireless communication module 260 can provide solutions for wireless communication applications such as wireless local area networks (WLAN), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technology for wearable devices 200. For example, the aforementioned WLAN can be a wireless fidelity (Wi-Fi) network.

[0093] The wireless communication module 260 can be one or more devices integrating at least one communication processing module. The wireless communication module 260 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signal, and sends the processed signal to processor 210. The wireless communication module 260 can also receive signals to be transmitted from processor 210, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2.

[0094] In some embodiments, the antenna 2 of the wearable device 200 is coupled to the mobile communication module 250, and the antenna 2 is coupled to the wireless communication module 260, so that the wearable device 200 can communicate with the network and other devices through wireless communication technology.

[0095] The wearable device 200 implements display functions through a GPU, a display screen 294, and an application processor. The GPU is a microprocessor for image processing, connected to the display screen 294 and the application processor. The GPU performs mathematical and geometric calculations for graphics rendering. The processor 210 may include one or more GPUs, which execute program instructions to generate or modify display information. The display screen 294 may be a touchscreen, used to display images, videos, etc. The display screen 294 includes a display panel.

[0096] The wearable device 200 can implement shooting functions through an ISP, a camera 293, a video codec, a GPU, a display 294, and an application processor. The ISP is used to process data fed back by the camera 293. In some embodiments, the ISP can be set in the camera 293. The camera 293 is used to capture still images or videos. In some embodiments, the wearable device 200 may include one or M cameras 293, where M is a positive integer greater than 1.

[0097] Digital signal processors (DSPs) are used to process digital signals. Besides digital image signals, they can also process other digital signals. For example, when a wearable device 200 receives a feedback signal, the DSP can perform signal feature extraction, Fourier transform, or wavelet transform on the analog-to-digital converted feedback signal. The signal features can include the time-domain features (such as the root mean square of the signal amplitude within a preset time period), frequency-domain features (such as the median frequency of the feedback signal), and time-frequency-domain features of the feedback signal.

[0098] An NPU (Neural Processing Unit) is a neural network (NN) computing processor that, by borrowing from the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, rapidly processes input information and can continuously learn on its own. In this embodiment, the NPU can determine the wearing state of the wearable device 200 based on feedback signals and a preset recognition model. The NPU enables intelligent cognitive applications of the wearable device 200, such as image recognition, face recognition, speech recognition, and text understanding.

[0099] The external storage interface 210 can be used to connect an external storage card, such as a Micro SD card, to expand the storage capacity of the wearable device 200. The external storage card communicates with the processor 210 through the external storage interface 210 to perform data storage functions. For example, music, video, and other files can be saved on the external storage card.

[0100] Internal memory 221 can be used to store computer executable program code, which includes instructions. Processor 210 executes various functional applications and data processing of wearable device 200 by running the instructions stored in internal memory 221. For example, in this embodiment, processor 210 can execute instructions stored in internal memory 221, which may include a program storage area and a data storage area.

[0101] The program storage area can store the operating system, at least one application program required for a function (such as sound playback, image playback, etc.). The data storage area can store data created during the use of the wearable device 200 (such as audio data, phonebook, etc.). Furthermore, the internal memory 221 can include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0102] The wearable device 200 can implement audio functions, such as music playback and recording, through an audio module 270, a speaker 270A, a receiver 270B, a microphone 270C, a headphone jack 270D, and an application processor.

[0103] Audio module 270 is used to convert digital audio information into analog audio signal output, and also to convert analog audio input into digital audio signal. Headphone jack 270D is used to connect wired headphones. Headphone jack 270D can be a USB interface 230, or a 3.5mm Open Mobile Terminal Platform (OMTP) standard interface, or a CTIA (Cellular Telecommunications Industry Association of the USA) standard interface.

[0104] The headphone jack 270D is used to connect wired headphones. The headphone jack 270D can be a USB 230 interface or a 3.5mm Open Mobile Terminal Platform (OMTP) standard interface, a CTIA (Cellular Telecommunications Industry Association of the USA) standard interface.

[0105] Buttons 290 include a power button, volume buttons, etc. Buttons 290 can be mechanical buttons or touch buttons. The wearable device 200 can receive button input and generate key signal inputs related to user settings and function control of the wearable device 200.

[0106] Vibration motor 291, also known as a motor, can be used for vibration alerts. Vibration motor 291 can be used for incoming call vibration alerts or for touch vibration feedback. For example, different vibration feedback effects can be emitted for touch operations applied to different applications (such as taking photos, playing audio, etc.). Vibration motor 291 can also provide different vibration feedback effects for touch operations applied to different areas of the display screen 294. Different application scenarios (such as time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also be customized.

[0107] The vibration motor 291 in this embodiment can generate N vibration signals in response to a user triggering the wearable device to measure the user's physiological data. The vibration motor 291 can also generate N vibration signals based on incoming calls, messages, and / or reminders, where N ≥ 2 and N is a positive integer. These vibration signals can also be used to detect the wearing status of the wearable device 200. In some embodiments, the wearable device 200 may include one or more vibration motors 291.

[0108] For example, the wearable device described above may include multiple vibration motors 291. Different vibration motors 291 are set in different positions in the wearable device, and different vibration motors 291 generate vibration signals at different positions, so the parameters of different vibration signals (such as the transmission direction of vibration signals) are also different.

[0109] For example, taking the wearable device 200 mentioned above as a smartwatch, the smartwatch may include a first vibration motor and a second vibration motor. Figure 3 In the smartwatch shown, the first vibration motor and the second vibration motor can be respectively set at both ends of the circuit board inside the smartwatch's compartment, and coupled to the processor 210 through the circuit board. Figure 4 In the smartwatch shown, the first vibration motor and the second vibration motor can be respectively installed in the two sides of the watch band. The first vibration motor and the second vibration motor are connected to the circuit board through wires, and then coupled to the processor 210 through the connected circuit board.

[0110] For example, taking the aforementioned wearable device 200 as a smart belt, the smart belt may include a third vibration motor and a fourth vibration motor. Figure 5 In the smart belt shown, the third and fourth vibration motors can be respectively installed at both ends of the smart belt. Figure 6 In the smart belt shown, the third and fourth vibration motors can be installed inside the straps on both sides of the smart belt.

[0111] Understandably, when the user is wearing the wearable device 200, the N vibration signals generated by the vibration motor 291 can be fed back through the human body to obtain a feedback signal. When the user is not wearing the wearable device 200, the N vibration signals generated by the vibration motor 291 can be fed back through other media to obtain a feedback signal.

[0112] Indicator 291 can be an indicator light, which can be used to indicate charging status, power changes, messages, missed calls, notifications, etc.

[0113] The SIM card interface 295 is used to connect a SIM card. The SIM card can be inserted into or removed from the SIM card interface 295 to make contact with and detach from the wearable device 200. The wearable device 200 can support one or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 295 can support Nano SIM cards, Micro SIM cards, and other SIM cards.

[0114] A gyroscope sensor can be used to determine the motion posture of the wearable device 200. A barometric pressure sensor is used to measure air pressure. Magnetic sensors include Hall effect sensors. The wearable device 200 can utilize magnetic sensors as overcurrent protection drivers for high-power devices, becoming a control element in the self-control loop.

[0115] The accelerometer can detect the magnitude of the acceleration of the wearable device 200 in various directions (generally three axes). When the wearable device 200 is stationary, it can detect the magnitude and direction of gravity. It can also be used to identify the posture of electronic devices and applied to applications such as screen orientation switching and pedometers. The accelerometer can also perform the functions of the sensor in the embodiments of this application, collecting feedback signals of N vibration signals and sending the feedback signals to the processor 210.

[0116] In some embodiments, the wearable device 200 may include one or more accelerometer sensors. Taking the wearable device 200 as an example, a smartwatch may include an accelerometer sensor, which can be set in... Figure 3 or Figure 4 On the circuit board inside a smartwatch. Taking the aforementioned wearable device 200 as an example, which is a smart belt, the smart belt may include an accelerometer, which can be set in... Figure 5 or Figure 6 The smart belt shown contains an accelerometer that can collect signals (i.e., feedback signals) from the human body or other media, and send these feedback signals to the processor 210 via a circuit board.

[0117] A distance sensor is used to measure distance. Wearable device 200 can measure distance using infrared or laser. The proximity sensor may include, for example, a light-emitting diode (LED) and a light detector, such as a photodiode. The LED may be an infrared LED. Wearable device 200 emits infrared light outward through the LED. Wearable device 200 uses a photodiode to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that an object is near wearable device 200.

[0118] An ambient light sensor is used to detect ambient light intensity. It can also be used to automatically adjust white balance when taking photos. The ambient light sensor can also work with a proximity sensor to detect if the wearable device 200 is in a pocket, preventing accidental touches. A fingerprint sensor is used to collect fingerprints. The wearable device 200 can use the collected fingerprint characteristics to unlock the device, access applications, take photos, and answer calls. A temperature sensor is used to detect temperature. A touch sensor, also known as a "touch panel," can be located on the display screen 294. The touch sensor 180K and the display screen 294 together form a touchscreen, also known as a "touch screen." The touch sensor detects touch operations applied to or near it. It can then transmit the detected touch operation to the application processor to determine the type of touch event.

[0119] The methods described in the following embodiments can all be implemented in the wearable device 200 having the above-described hardware structure. The following embodiments use a smartwatch as an example to illustrate the methods of this application's embodiments.

[0120] This application provides a method for identifying wearing status, which can be applied to smartwatches. A smartwatch may include one or more vibration motors and one or more sensors. In this application scenario, using the method of this application embodiment, the smartwatch can identify its wearing status by vibrating the motors and sensors. For example, as shown... Figure 7 As shown, the method for recognizing the wearing state may include S701-S703:

[0121] S701, the smartwatch can send N vibration signals, N≥2, where N is a positive integer.

[0122] Among them, the N vibration signals have different signal parameters, which may include frequency and / or waveform.

[0123] For example, the N vibration signals can be signals emitted by the vibration motor in the smartwatch, and the vibration motor can be as described above. Figure 2 The vibration motor 191 shown above. The signal parameters of the aforementioned vibration signal can be used to represent the signal attributes of the vibration signal, such as the frequency and waveform of the vibration signal. The differences in the signal parameters of N vibration signals can be manifested in several aspects, which will be explained below.

[0124] On the one hand, the difference in signal parameters can be manifested as different frequencies of N vibration signals. Taking N=2 as an example, the two vibration signals can be vibration signal 1 with a frequency of 5kHz and vibration signal 2 with a frequency of 10kHz.

[0125] On the other hand, different signal parameters can manifest as different waveforms of N vibration signals. Taking N=2 as an example, the two vibration signals can be vibration signal 3 with a sine wave waveform and vibration signal 4 with a square wave waveform.

[0126] On the other hand, different signal parameters can manifest as N vibration signals having different waveforms and frequencies. Taking N=2 as an example, the two vibration signals can be scanning signals whose frequency and / or waveform change over time at different time intervals, such as a step sine scanning signal with a frequency varying within the range of [5kHz, 10kHz].

[0127] On the other hand, different signal parameters of N vibration signals can also indicate that the locations where the N vibration signals are generated are different, that is, the locations of the vibration motors in the smartwatch are different.

[0128] In other embodiments, the smartwatch may include multiple vibration motors. These multiple vibration motors may be located in different positions within the smartwatch.

[0129] For example, because the vibratory motors are located at different positions, the N vibration signals generated by multiple vibratory motors will also be located at different positions, resulting in different transmission directions for the N vibration signals. Therefore, the difference in signal parameters can also be manifested as different transmission directions for the N vibration signals. Figure 3 Taking the smartwatch shown as an example, the smartwatch may include a first vibration motor and a second vibration motor, and the smartwatch can send N=2 vibration signals. The two vibration signals can be vibration signal 7 generated by the first vibration motor and vibration signal 8 generated by the second vibration motor, respectively. The transmission direction of vibration signal 7 can be from the first vibration motor to the transmission medium, and then from the transmission medium to the accelerometer. The transmission direction of vibration signal 7 can also be from the second vibration motor to the transmission medium, and then from the transmission medium to the accelerometer.

[0130] Understandably, the vibration signal changes differently after transmission depending on the wearing state. When the smartwatch is not worn or is worn by different users, it can collect different feedback signals and identify its own wearing state based on these signals. The specific implementation of the smartwatch's wearing state recognition can be found in the relevant content of S703 below, and will not be elaborated upon here.

[0131] Furthermore, in addition to being affected by the wearing status, the vibration signal is also affected by different filtering effects of different transmission media (such as human fat with different body fat content, or air, etc.) during transmission, which makes it easy for smartwatches to make errors in recognizing the wearing status. For the specific implementation of how different transmission media affect the vibration signal, please refer to the relevant content of S702 below, which will not be repeated here.

[0132] It is also understandable that when a smartwatch includes multiple vibration motors, each vibration motor can generate one or more vibration signals, allowing the smartwatch to emit N vibration signals with different signal parameters. When a smartwatch includes a single vibration motor, the smartwatch can emit N vibration signals with different signal parameters (such as frequency and / or waveform) through that motor.

[0133] For example, the N vibration signals described in this application embodiment can be transmitted separately by multiple vibration motors, or they can be transmitted by a single vibration motor in time intervals. Taking vibration signal 1 and vibration signal 2 as examples, the vibration motor can transmit vibration signal 1 with a frequency of 5 kHz in the first time interval, but not vibration signal 2 with a frequency of 10 kHz. In the second time interval, the vibration motor can transmit vibration signal 2 with a frequency of 10 kHz, but not vibration signal 1 with a frequency of 5 kHz. The intersection of the first and second time intervals can be an empty set, thereby realizing the function of transmitting N vibration signals by a single motor and saving costs.

[0134] It is understandable that there are multiple scenarios that can trigger the wearing status recognition function of a smartwatch, which will be explained below.

[0135] Option 1: When the user triggers the smartwatch's physiological data measurement function, the smartwatch can also trigger the wearing status recognition function to ensure the quality of the physiological data measurement.

[0136] Specifically, the above S701 may include: the smartwatch can respond to the user's first operation by sending N vibration signals, the first operation being used to trigger the smartwatch to measure the user's physiological data.

[0137] For example, the first operation can be triggered by the user when the smartwatch is in a screen-off state, or it can be triggered by the user when the smartwatch displays the first interface.

[0138] In some embodiments, when the smartwatch is in a screen-off state, the aforementioned first operation can be a user's tap operation on the smartwatch (such as a double-tap or knuckle tap), or a preset gesture input by the user within the smartwatch's sensing area, such as an S-shaped gesture or a checkmark gesture. The smartwatch's sensing area is a pre-defined area that can sense user gestures; this area can be the smartwatch's capacitive touchscreen or an area equipped with sensors. The preset gesture can be pre-configured within the smartwatch. Through the aforementioned first operation, the user can trigger the smartwatch to measure their physiological data and identify the smartwatch's wearing status.

[0139] In other embodiments, the smartwatch may display a first interface and receive a first operation from the user on the first interface. This first operation is used to trigger the smartwatch to measure the user's physiological data.

[0140] Specifically, the smartwatch can display the first interface of the first app. This first interface can be used to trigger the smartwatch to measure the user's physiological data. This first interface may include health management options, which can be used to trigger the smartwatch to measure the user's physiological data and to trigger the smartwatch to recognize its own wearing status.

[0141] For example, the first APP in this application embodiment can be as follows: Figure 8 The application corresponding to the icon "Health" 801 shown in (a) is as follows. Figure 8 As shown in (a), the smartwatch can receive a user's click on "Health" 801; in response to this click, the smartwatch can launch the first APP and display... Figure 8 The first APP homepage 802 (i.e., first interface 802) is shown in (b) in the figure. The first interface 802 can be a health management interface, and the first interface 802 can include a health management option, such as the "Measure user physiological data" option 803.

[0142] Among them, the health management option is used to trigger the smartwatch to perform health management. For example, the "Measure User Physiological Data" option 803 is used to trigger the smartwatch to measure the user's physiological data and to trigger the smartwatch to recognize the wearing status. The above-mentioned first operation can be the user's... Figure 8 The first operation can be a click operation (such as a single click) on the health management option shown in (b) of the first interface, for example, a click operation on the "Measure User Physiological Data" option 803. Alternatively, the first operation can also be a preset gesture entered by the user on the first interface 802, such as an S-shaped gesture, an L-shaped gesture, a two-finger upward swipe gesture, or a three-finger upward swipe gesture. Furthermore, the smartwatch can prompt the user with the preset gesture on the first interface 802, as well as the function triggered by the preset gesture (i.e., the function of measuring user physiological data and the function of wearing status recognition).

[0143] In this way, when a user actively triggers the measurement of their physiological data, the smartwatch can emit a vibration signal to identify the wearing status, thereby reducing inaccuracies caused by improper tightness and improving the accuracy of the smartwatch in measuring the user's physiological data.

[0144] In other embodiments, the smartwatch may display a second interface and receive a second operation from the user on the second interface, the second operation being used to trigger the smartwatch to recognize the wearing status.

[0145] Specifically, the smartwatch can display a second interface for smartwatch settings. This second interface can be used to adjust the smartwatch settings. This second interface may include a wearing status recognition option, which can be used to identify whether the smartwatch is being worn.

[0146] For example, the smartwatch settings in this application embodiment can be as follows: Figure 8 The icon shown in (a) corresponds to the application "Settings" 804. For example... Figure 8 As shown in (a), the smartwatch can receive a user's click on "Settings" 804; in response to this click, the smartwatch can initiate smartwatch settings and display... Figure 8 The smartwatch settings homepage 805 (i.e., second interface 805) is shown in (c). The second interface 805 can be the smartwatch settings interface, and it can include a wearing status recognition option, such as "Recognize Wearing Status" option 806.

[0147] The wearing status recognition option can be used to trigger the smartwatch to recognize the wearing status. For example, the "Recognize Wearing Status" option 806 is used to trigger the smartwatch to recognize the wearing status as a basis for measuring the user's physiological data. The aforementioned first operation can also be a user action... Figure 8 The click operation (such as a single click operation) of the wearing status recognition option shown in (c) in the figure, for example, the click operation of the “Recognize wearing status” option 806.

[0148] Furthermore, in response to the first operation, the smartwatch can display a third interface, which is used to prompt the user that the smartwatch is being worn.

[0149] For example, such as Figure 8 The third interface 807 shown in (d) can be a wearing status recognition interface. The smartwatch can prompt the user in the third interface 807 that the smartwatch is recognizing the wearing status, such as displaying the text prompt 808 "Recognizing wearing status, please wait!", to avoid the smartwatch suddenly emitting a vibration signal during wearing recognition, which would startle the user and affect the user experience.

[0150] Option 2: The smartwatch can use the vibration signals from incoming calls, new messages, or reminders received by the smartwatch to identify the wearing status of the smartwatch.

[0151] Specifically, the aforementioned S701 may include: the smartwatch can send N vibration signals in response to incoming calls, new messages, or reminder events, and the N vibration signals are used to indicate incoming calls, new messages, or reminder events.

[0152] For example, incoming calls, new messages, or reminders can be events received by the smartwatch from other terminal devices (such as mobile phones or personal computers), or events generated by the smartwatch itself, such as sedentary reminders or exercise reminders. In this way, the smartwatch can emit N vibration signals to alert the user during reminder scenarios such as incoming calls, new messages, or reminders, while simultaneously using N vibration signals to identify the wearing status. This avoids the smartwatch vibrating suddenly while identifying the wearing status, thus preventing it from affecting the user experience.

[0153] Understandably, smartwatches can also employ multiple trigger scenarios simultaneously to activate their wear detection function. Specifically, a smartwatch can trigger the wear detection function to ensure the quality of physiological data measurement when the user activates the watch's physiological data measurement function, or it can trigger the wear detection function to avoid sudden vibrations affecting the user experience when a vibration signal is needed to remind the user.

[0154] Thus, after recognizing the wearing status of the smartwatch, the smartwatch can adjust its working mode accordingly, preventing energy waste when not worn. The smartwatch can also output prompts to instruct the user to adjust the wearing status, ensuring reliable health monitoring. Furthermore, the smartwatch can adjust the measurement weights of the user's physiological data based on the current wearing status to achieve stable health monitoring. The specific implementation of these operations based on the wearing status can be found in section S703 below, and will not be elaborated upon here.

[0155] The S702 is a smartwatch that collects feedback signals from N vibration signals.

[0156] The feedback signals may include: N vibration signals fed back by the human body when the smartwatch is being worn, or N vibration signals fed back by other media when the smartwatch is not being worn.

[0157] For example, the aforementioned feedback signal can be a signal fed back by the transmission medium after N vibration signals have been transmitted through it. For instance, when the smartwatch is worn, it could be a first feedback signal fed back by the human body after N vibration signals have been transmitted through it. Or, when the smartwatch is not worn, it could be a second feedback signal fed back by another medium after N vibration signals have been transmitted through it.

[0158] In the S701 above, the vibration signal, after being emitted, is affected by different wearing conditions during transmission. The smartwatch can then identify its own wearing condition based on the feedback signal from the transmission medium (i.e., the aforementioned feedback signal). Besides being affected by the wearing condition, the vibration signal is also affected by the filtering effect of different transmission media (such as human fat with different body fat percentages, or air). For example, human fat with a lower body fat percentage has a less effective filtering effect on the vibration signal compared to human fat with a higher body fat percentage.

[0159] It should be understood that because transmission media (such as the human body, air, or clothing) have different filtering effects on vibration signals with different signal parameters, the feedback signal of the vibration signal after the vibration signals with different signal parameters pass through the transmission medium can reflect the filtering effect of the transmission medium on different vibration signals. Therefore, the smartwatch can identify its own wearing status from the perspective of different vibration signals based on the feedback signal, so as to reduce the impact of the content of the transmission medium on the accuracy of wearing recognition. This will be explained in detail below.

[0160] To ensure the smartwatch is compatible with users of varying body fat percentages and can accurately identify wearing status, we can utilize N vibration signals at different frequencies. Since body fat filters vibration signals of different frequencies to varying degrees, the feedback signals from these N signals can reflect the filtering effect of body fat on multiple frequencies. Thus, for users with different body fat percentages, the smartwatch can identify their wearing status from multiple frequency perspectives based on the filtering effect reflected in the feedback signals, thereby reducing the interference of body fat on the identification of wearing status and improving accuracy.

[0161] Similarly, we can also use N vibration signals with different waveforms. Since human fat has varying filtering effects on vibration signals with different waveforms, the feedback signals of N vibration signals can reflect the filtering effect of human fat on multiple vibration signals with different waveforms. In this way, for users with different body fat percentages, smartwatches can identify their wearing status from multiple different waveforms based on the filtering effect reflected in the feedback signals, thereby reducing the interference of human fat on the identification of wearing status and improving the accuracy of identification.

[0162] Furthermore, we can also generate N vibration signals at different locations. Since body fat has varying filtering effects on vibration signals generated at different locations, the feedback signals from these N vibration signals can reflect the filtering effect of body fat on multiple vibration signals generated at different locations. In this way, for users with different body fat percentages, the smartwatch can identify their wearing status from multiple different locations based on the filtering effect reflected in the feedback signals, thereby reducing the interference of body fat on the identification of wearing status and improving the accuracy of identification.

[0163] Similarly, when a single vibration motor sends N vibration signals in different time periods, the transmission medium will still produce different filtering effects on the N vibration signals. Therefore, the feedback signals of the N vibration signals that pass through the transmission medium in different time periods can still reflect the filtering effect of the transmission medium on multiple different signal parameters. Thus, the smartwatch can identify its own wearing status from the perspective of multiple different signal parameters based on the feedback signals, thereby reducing the interference of the transmission medium on the identification of the wearing status and improving the accuracy of the identification.

[0164] The S703 smartwatch can identify its own wearing status based on feedback signals.

[0165] The wearing status can be either worn or not worn.

[0166] For example, the "worn" state can be used to indicate that the smartwatch has been worn by the user, and the "not worn" state can be used to indicate that the smartwatch has not been worn by the user.

[0167] Understandably, since feedback signals can reflect the influence of the transmission medium on the wearing status recognition from different perspectives, and can also reflect the wearing status of the smartwatch from different perspectives, the smartwatch can use feedback signals to recognize the wearing status from different perspectives, reduce the influence of the transmission medium on the recognition of the wearing status, and improve the accuracy of recognition.

[0168] In other embodiments, when the smartwatch is being worn, it can also identify the tightness of the fit based on feedback signals.

[0169] Specifically, the aforementioned wearing state can include: a first loose state, a second loose state, and a third loose state. In the first loose state, the smartwatch is worn looser than normally; in the second loose state, the smartwatch is worn tighter than normally; and in the third loose state, the smartwatch is worn at a normal tightness.

[0170] For example, the first, second, and third tightness states described above can be used to represent different degrees of tightness when a user wears a smartwatch. Based on the characteristics of these three tightness states, the first tightness state can also be called the "too loose" state, the second tightness state can also be called the "too tight" state, and the third tightness state can also be called the "suitable" state.

[0171] For users, the third tightness setting indicates that the smartwatch fits snugly and comfortably. The first tightness setting, however, indicates the smartwatch is too loose, making it difficult to fit properly and resulting in lower comfort. It can also easily fall off during use, potentially damaging the smartwatch. The second tightness setting, compared to the third, indicates the smartwatch is too tight, pressing too closely against the user and restricting blood circulation, also leading to lower comfort.

[0172] For smartwatches, in the third tight position, the smartwatch fits the user snugly and accurately measures physiological data, achieving stable health monitoring. In the first tight position, the smartwatch is difficult to fit the user snugly, leading to errors in the measured physiological data (such as body temperature or heart rate), making stable health monitoring difficult. In the second tight position, the smartwatch is too close to the user, which can compress the user and restrict blood circulation, causing errors in some blood-based physiological data (such as heart rate or blood oxygen saturation), also making stable health monitoring difficult.

[0173] Optionally, the wearing state can also include other tightness states to further subdivide the tightness of the smartwatch being worn. For example, there are fourth and fifth tightness states. In the fourth tightness state, the smartwatch is worn looser than normally, but tighter than in the first tightness state. In the fifth tightness state, the smartwatch is worn tighter than normally, but looser than in the first tightness state. In other words, the fourth tightness state can be described as a "slightly loose" state, and the fifth tightness state can be described as a "slightly tight" state.

[0174] In some embodiments, when the smartwatch is being worn, the smartwatch can determine the tightness of the fit based on feedback signals, and then determine the tightness state of the smartwatch based on the tightness of the fit.

[0175] There are several ways to express the tightness of a garment, and it can be expressed as a discrete value. For example, the tightness of a garment can include: normal tightness, one degree loose, two degrees loose, three degrees loose, one degree tight, two degrees tight, and three degrees tight.

[0176] Correspondingly, if the tightness is normal, the wearable device can be identified as being in the third tightness state. If the tightness is one degree loose, two degrees loose, or three degrees loose, the wearable device can be identified as being in the first tightness state. If the tightness is one degree tight, two degrees tight, or three degrees tight, the wearable device can be identified as being in the second tightness state.

[0177] Furthermore, the tightness of the fit can also be expressed as a continuous value. For example, the tightness of the fit can be any value within the range of [-1, 1]. The smaller the value of the tightness of the fit, the looser the smartwatch is worn, and vice versa.

[0178] Correspondingly, if the tightness of the fit is within [-0.1, 0.1], the smartwatch can be determined to be in the third tightness state. If the tightness is within [-1, -0.1], the smartwatch can be determined to be in the first tightness state. If the tightness is within [0.1, 1], the smartwatch can be determined to be in the second tightness state. This application does not limit the specific manifestation of the tightness and tightness state.

[0179] In some embodiments, the smartwatch may include a preset recognition model, which has the ability to identify the wearing status of the smartwatch based on feedback signals of N vibration signals. Accordingly, S703 above may include: the smartwatch can obtain the wearing status of the smartwatch based on the feedback signals and using the preset recognition model.

[0180] For example, the preset recognition model can be a trained machine learning model. Mathematically, a machine learning model can be understood as a function that allows the preset recognition model to identify the wearing status of the smartwatch based on the feedback signals of N vibration signals.

[0181] There are several types of preset recognition models. A preset recognition model can be a classifier or a neural network model, and the input to the preset recognition model may also change depending on the type of preset recognition model. These will be explained separately below.

[0182] In some embodiments, the preset recognition model can be a classifier. Accordingly, the smartwatch can obtain the wearing status of the smartwatch based on the feedback signal and using the preset recognition model. This can include: the smartwatch acquiring the signal features of the feedback signal, using the signal features as input to the classifier, running the classifier, and outputting the wearing status of the smartwatch.

[0183] The signal characteristics may include: the root mean square of the amplitude of the feedback signal within a preset time period and the median frequency of the feedback signal.

[0184] For example, the classifier described above can map the input data (such as signal features) to one of a given category (such as multiple wearing states) based on a preset algorithm, thereby realizing the function of the preset recognition model. Optionally, the classifier can be a Hidden Markov Model, Random Forest Model, Support Vector Machine, Decision Tree, or Logistic Regression Classifier, etc. This application does not limit the specific type of classifier.

[0185] Furthermore, the signal characteristics of the feedback signal can be used to represent its properties in the time and / or frequency domains. Different types of signal characteristics can be classified based on the different dimensions they reflect. Signal characteristics can include: time-domain characteristics, frequency-domain characteristics, and time-frequency-domain characteristics. For example, the root mean square of the signal amplitude of the feedback signal within a preset time period can be considered a time-domain characteristic, representing the characteristics of the feedback signal in the time domain. The median frequency of the feedback signal can be considered a frequency-domain characteristic, representing the characteristics of the feedback signal in the frequency domain.

[0186] It is understandable that, since feedback signals can reflect the wearing status of a smartwatch from different perspectives, and signal characteristics can also reflect the influence of the wearing status on the corresponding vibration signal during transmission from multiple perspectives, there is a certain mapping relationship between signal characteristics and wearing status. The following explanation uses root mean square (RMS) and median frequency as examples.

[0187] If the root mean square (RMS) is greater than a first RMS threshold and the median frequency is less than a first frequency threshold, the smartwatch is in an unworn state. If the RMS is greater than a second RMS threshold and the median frequency is greater than a second frequency threshold, the smartwatch is in a worn state. The first and second RMS thresholds may be the same or different, and the first frequency threshold may be less than or equal to the second frequency threshold.

[0188] For example, the root mean square (RMS) of the feedback signal amplitude within a preset time period can be used to characterize the effective power value of the feedback signal within the preset time period. The magnitude of the RMS is related to the filtering effect of the transmission medium on the power of the vibration signal. A larger RMS indicates that the transmission medium has a poorer filtering effect on the signal power of the vibration signal, while a smaller RMS indicates that the transmission medium has a better filtering effect on the signal power of the vibration signal.

[0189] Furthermore, the median frequency of the feedback signal is the median frequency of the feedback signal on the power spectrum after Fourier transform. A larger median frequency indicates a poorer filtering effect of the transmission medium on the frequency of the vibration signal, while a smaller median frequency indicates a better filtering effect of the transmission medium on the frequency of the vibration signal.

[0190] In other words, a high root mean square (RMS) and low median frequency in the feedback signal indicate that the transmission medium has poor filtering effect on the signal power of the vibration signal, but good filtering effect on the frequency of the vibration signal. Since air has poor filtering effect on signal power but good filtering effect on signal frequency, the transmission medium is likely mainly air, and the feedback signal is likely a vibration signal fed back through the air, indicating that the smartwatch is more likely to be in an unworn state.

[0191] Furthermore, the large root mean square (RMS) and high median frequency of the feedback signal indicate that the transmission medium has poor filtering effects on the signal power and frequency of the N vibration signals. Since human fat has poor filtering effects on both signal power and frequency, the transmission medium is likely primarily composed of human fat. Therefore, the feedback signal is likely a vibration signal fed back through human fat, indicating a high probability that the smartwatch is being worn. Thus, the classifier can output the corresponding wearing status based on the above mapping relationship.

[0192] Similarly, when a smartwatch is worn, its signal characteristics can reflect the influence of the tightness of the fit on the corresponding vibration signal during transmission; that is, there is a certain mapping relationship between signal characteristics and the tightness of the fit. The following explanation will continue using the root mean square (RMS) and median frequency as examples.

[0193] When the smartwatch is worn, if the root mean square (RMS) is greater than the third RMS threshold and the median frequency is less than the third frequency threshold, the smartwatch is in a first "loose / tight" state. If the RMS is less than the fourth RMS threshold and the median frequency is greater than the fourth frequency threshold, the smartwatch is in a second "loose / tight" state. Specifically, the third RMS threshold is greater than or equal to the fourth RMS threshold, and the third frequency threshold is less than or equal to the fourth frequency threshold.

[0194] For example, when a smartwatch is worn, a larger root mean square (RMS) and lower median frequency in the feedback signal indicate that the transmission medium has a poorer filtering effect on the signal power of the N vibration signals, but a better filtering effect on the frequency of the N vibration signals. Since air is less effective at filtering signal power than body fat, and more effective at filtering signal frequency, the proportion of air in the transmission medium is likely greater than that of body fat. This means the vibration signals may be transmitted through a combination of air and body fat, indicating a higher probability that the smartwatch is in a loose-fitting state (e.g., too loose).

[0195] Similarly, the smaller the root mean square (RMS) of the feedback signal and the higher the median frequency, the better the transmission medium filters the signal power of the N vibration signals, but the worse it filters the frequencies of the N vibration signals. Since air filters signal power less effectively than human fat does, and air filters signal frequencies better than human fat, the proportion of human fat in the transmission medium is likely greater than that of air. This means the vibration signals may be transmitted through a combination of most of the human fat and a small amount of air, indicating a higher probability that the smartwatch is in a slightly loose state (e.g., worn too tightly).

[0196] Furthermore, the signal characteristics of the feedback signal can also include: time-domain characteristics such as the integral value and standard deviation of the signal amplitude within a preset time period; frequency-domain characteristics such as the frequency variance and average power frequency of the feedback signal in the power spectrum after Fourier transform; time-frequency domain characteristics such as the wavelet singular entropy of the feedback signal after wavelet transform; and time-frequency domain characteristics such as the wavelet packet model coefficient energy of the feedback signal after wavelet packet transform. The specific implementation of the mapping relationship between the above signal characteristics and the wearing state can be found in the mapping relationship between the root mean square and median frequency domains and the wearing state, which will not be elaborated here.

[0197] Method 2: The preset recognition model is a neural network model. Accordingly, the smartwatch can use the preset recognition model based on the feedback signal to obtain the wearing status of the smartwatch. This can include: the smartwatch can use the feedback signal as input to the neural network model, run the neural network model, and output the wearing status of the smartwatch.

[0198] The neural network model is used to obtain the signal characteristics of the feedback signal and to obtain and output the wearing status of the smartwatch based on the signal characteristics. The signal characteristics may include the root mean square of the signal amplitude of the feedback signal within a preset time period and the median frequency of the feedback signal.

[0199] For example, the neural network can process the input data (such as the feedback signal mentioned above) according to a preset procedure and output the processing result (such as the wearing status mentioned above). That is, the neural network can extract the signal features of the feedback signal according to the preset procedure, obtain and output the wearing status based on the signal features, thereby realizing the function of the preset recognition model mentioned above. The specific implementation method of the neural network to recognize the wearing status is similar to the specific implementation method of the smartwatch extracting the signal features of the feedback signal and using a classifier to recognize the wearing status in Method 1 above, and will not be repeated here.

[0200] Optionally, the aforementioned neural network can be a multi-layer fully connected network, a convolutional neural network, a recurrent neural network, a convolutional neural network with jumpers, etc. This application does not limit the specific type of neural network.

[0201] Understandably, smartwatches can acquire the aforementioned preset recognition models in various ways. Smartwatches can receive preset recognition models from network devices (such as servers) or other terminal devices (such as personal computers or mobile phones). Smartwatches can also train preset recognition models using training samples, thereby enabling these preset recognition models to recognize the wearing status.

[0202] Optionally, before the aforementioned smartwatch can determine its wearing status using a preset recognition model based on feedback signals, Figure 7 The method shown may also include: the smartwatch can acquire training samples and use the training samples to train a preset recognition model, so that the preset recognition model has the ability to recognize the wearing status of the smartwatch based on the feedback signals of N vibration signals.

[0203] The training samples can include input samples and output samples. Input samples can include multiple sample feedback signals or signal characteristics of multiple sample feedback signals. Multiple sample feedback signals can include: training samples of feedback signals from N vibration signals from users with different body fat percentages wearing the smartwatch, and feedback signals from other media to N vibration signals when the smartwatch is not worn. The signal characteristics of the multiple sample feedback signals can include: the root mean square of the signal amplitude and the median frequency of the sample feedback signals within a preset time period. The output sample can be the actual wearing state corresponding to the input sample.

[0204] For example, training samples can be used to train machine learning models, enabling these models to perform specific tasks. For instance, training samples can be used to train a pre-defined recognition model, allowing the model to identify the wearing status of a smartwatch based on feedback signals from N vibration signals. These multiple sample feedback signals can include two types: one collected when the user is wearing the smartwatch, and the other collected when the user is not wearing the smartwatch.

[0205] Furthermore, to collect sample feedback signals, the smartwatch can emit one or more sets of vibration signals. Each set of vibration signals includes N vibration signals with different signal parameters. The parameters of vibration signals in different sets can be the same or different. For example, the first set of vibration signals may include vibration signal 1 with a frequency of 5 kHz and vibration signal 2 with a frequency of 10 kHz, and the second set of vibration signals may include vibration signal 3 with a frequency of 1 kHz and vibration signal 4 with a frequency of 2 kHz. The specific implementation of the signal characteristics of the sample feedback signal can be found in the above description of the signal characteristics of feedback signals, and will not be repeated here.

[0206] In other words, the smartwatch can emit multiple sets of N vibration signals and collect corresponding sample feedback signals when worn by multiple users with different body fat percentages. The smartwatch can also emit multiple sets of N vibration signals and collect corresponding sample feedback signals even when the user is not wearing the smartwatch. If the preset recognition model is a classifier, the smartwatch can use the signal features of multiple sample feedback signals as input samples and the actual wearing state corresponding to the input samples as output samples to train the preset recognition model. If the preset recognition model is a neural network, the smartwatch can use multiple sample feedback signals as input samples and the actual wearing state corresponding to the input samples as output samples to train the preset recognition model.

[0207] In this way, when users with different body fat percentages wear smartwatches, corresponding training samples are collected and a preset recognition model is trained. Subsequently, the preset recognition model can reduce the impact of body fat on the recognition of wearing status, thereby improving the accuracy of the recognition of wearing status.

[0208] Understandably, smartwatches can update the aforementioned preset recognition model during use. After recognizing the wearing status using the preset recognition model, the smartwatch can use the collected feedback signal or the signal features of the feedback signal as input samples, and the actual wearing status corresponding to the input samples as output samples. It can then use the input and output samples to train the preset recognition model and update its model parameters to improve the accuracy of the preset recognition model in recognizing the wearing status.

[0209] Among them, the smartwatch can use the wearing status output by the preset recognition model as the actual wearing status corresponding to the input sample, or it can ask the user to confirm the current actual wearing status of the smartwatch after completing the wearing status recognition.

[0210] Furthermore, since the same user repeatedly wears the smartwatch during daily use, the smartwatch can use the methods described above to collect data on the user's wearing status during daily use (such as feedback signals and corresponding actual wearing status). This data can then be used to update the preset recognition model based on the user's daily usage. As the user continues to use the smartwatch, the updated preset recognition model will become increasingly accurate in recognizing the wearing status of the smartwatch.

[0211] It should also be noted that updates to the preset recognition model can also be performed by network devices (such as servers) or other terminal devices (such as personal computers or mobile phones). The smartwatch can receive update parameters from network devices or other terminal devices and update the internally stored preset recognition model accordingly.

[0212] Understandably, smartwatches can also adjust their operating mode based on how they are worn to save energy and resources.

[0213] Specifically, if the smartwatch is not worn, it will enter a low-power mode. In low-power mode, the smartwatch can disable communication with other terminal devices (such as mobile phones and personal computers) and can also stop health monitoring functions, such as turning off health monitoring sensors like the photoplethysmography sensor.

[0214] Correspondingly, if the smartwatch is being worn, it will enter normal working mode. In normal working mode, the smartwatch can communicate with other terminal devices and also enable health monitoring functions.

[0215] It's also understandable that, while the smartwatch is being worn, it can provide guidance and suggestions based on how tightly it's worn.

[0216] In one implementation, the smartwatch can issue a prompt message (such as a first prompt message or a second prompt message) based on the tightness of its wear (such as a first tightness state or a second tightness state) to guide the user to adjust the tightness of the smartwatch.

[0217] Specifically, if the smartwatch is in a first tightness state, a first prompt message will be issued, instructing the user to adjust the tightness of the smartwatch. If the smartwatch is in a second tightness state, a second prompt message will be issued, instructing the user to loosen the tightness of the smartwatch.

[0218] For example, the aforementioned prompts (such as the first or second prompt) can be used to guide users to adjust the tightness of the smartwatch. The tightness of the smartwatch, or its overall fit, affects both the user's experience and the accuracy of health monitoring. If the smartwatch is too loose in the first tightness setting, it will not fit snugly against the user, making stable health monitoring difficult. If the smartwatch is too tight in the second tightness setting, it may compress the user, hindering blood circulation and also making stable health monitoring difficult.

[0219] In this way, smartwatches can improve the user experience and enhance the accuracy of health monitoring by sending reminder messages to users to adjust the tightness of the smartwatch.

[0220] It is understood that the aforementioned prompts can be explicit, for example, the first prompt may include information indicating "tighten the smartwatch". The aforementioned prompts can also be implicit, the first prompt may include information indicating "the smartwatch is too loose". This application does not specifically limit this.

[0221] Furthermore, the smartwatch can determine and issue a tightness indicator based on the current tightness of the smartwatch and the tightness under normal wearing conditions, and the tightness indicator is used to instruct the user to adjust the smartwatch according to the indicated tightness.

[0222] It is understandable that smartwatches may issue notifications in various scenarios, which will be explained below.

[0223] Scenario 1: The smartwatch can display the above prompt information.

[0224] In some embodiments, the smartwatch can display, for example... Figure 9 The third interface 901 is shown. The third interface 901 may include a prompt message 902, such as "Please adjust the wristband buckle to loosen the fit".

[0225] In other embodiments, the third interface 901 may further include an indicator of tightness (…). Figure 9 (not shown in the text), such as "Please loosen it by two degrees".

[0226] In other embodiments, the third interface 901 may also include a tightness state 903, such as "currently too tight".

[0227] In other embodiments, the third interface 901 may further include a schematic diagram of the wearing state adjustment, such as a schematic diagram 904 of adjusting from an overly tight wearing state to a normal wearing state. The adjustment schematic diagram 904 may include a schematic image a of the current tightness state of the smartwatch, and a schematic image b of the suggested tightness state of the smartwatch.

[0228] Scenario 2: Smartwatches can output prompts via voice. For example, the smartwatch's speaker can play "Please adjust the wristband clasp to relax the fit."

[0229] Scenario 3: The smartwatch can also send notification messages to other terminal devices (such as mobile phones, personal computers, etc.) and control other terminal devices to send the notification messages.

[0230] In another implementation, the smartwatch can adjust the measurement weights of the user's physiological data based on how tightly it is worn. Specifically, the measurement weight in the third tightness state is greater than that in the first tightness state, and the measurement weight in the third tightness state is also greater than that in the second tightness state.

[0231] For example, measurement weights can be used to characterize the reliability of user physiological data. The smartwatch can achieve stable health monitoring based on the user's physiological data and the measurement weights. Since the smartwatch struggles to accurately measure user physiological data in both the first and second loose states, it can determine a lower measurement weight. In the third state, the smartwatch can accurately measure user physiological data, thus determining a higher measurement weight.

[0232] In summary, using the method of this application embodiment, a smartwatch can identify its wearing status by utilizing the cooperation of a vibration motor and a sensor, eliminating the need for additional customized sensors and reducing costs. Furthermore, since the transmission medium has different filtering effects on vibration signals with different parameters, this method allows the feedback signal to reflect the filtering effect of the transmission medium on different vibration signals under the current wearing status. The wearable device can then identify its wearing status from multiple different vibration signal angles based on this feedback signal. This reduces the impact of the transmission medium on the accuracy of wearing status identification, improving accuracy and thus solving the technical problem of not being able to simultaneously achieve both accuracy and cost in methods based on general-purpose sensors and methods based on customized sensors.

[0233] Similarly, in the aforementioned wearable device 200, Figure 5 or Figure 6 When using the smart belt shown, the smart belt can also perform the methods described in the above embodiments. For example... Figure 5 or Figure 6 As shown, the smart belt may include one or more vibration motors (such as a third vibration motor and a fourth vibration motor) and one or more sensors (such as an acceleration sensor).

[0234] in, Figure 5 In the smart belt shown, the third and fourth vibration motors can be respectively installed at both ends of the smart belt, and the acceleration sensor can be installed inside the smart belt. Figure 6 In the smart belt shown, the third and fourth vibration motors can be installed inside the straps on both sides of the smart belt, and the acceleration sensor can be installed inside the smart belt.

[0235] In this way, the smart belt of this embodiment can emit N vibration signals with different signal parameters through a vibration motor, and receive feedback signals from the N vibration signals using sensors, thereby identifying its own wearing status based on the feedback signals. Thus, using the method of this embodiment, wearable devices can identify their wearing status by utilizing the cooperation of a vibration motor and sensors, eliminating the need for additional customized sensors and reducing costs.

[0236] Furthermore, since the same transmission medium has different filtering effects on different vibration signals (such as vibration signals with different frequencies and / or waveforms), this method allows the feedback signal of the vibration signal to reflect the filtering effect of the transmission medium on different vibration signals under the current wearing state. The smart belt can then identify its wearing state from multiple different vibration signal angles based on this feedback signal. This reduces the impact of different transmission medium contents on the accuracy of wearing state identification, improving accuracy. This solves the technical problem of not being able to balance accuracy and cost in methods based on general sensors and methods based on customized sensors. The specific implementation of the smart belt's wearing state identification can be found in the smartwatch implementation described in the above embodiments, and will not be repeated here.

[0237] The following is based on the above. Figure 2 Taking the schematic diagram of the wearable device shown as an example, the specific implementation of the wearing status recognition method provided in this application embodiment in the processor is described in detail.

[0238] For example, Figure 10 This is a module interaction diagram of a wearable device provided in an embodiment of this application. The wearable device can specifically implement the above-described features. Figure 7 The method for recognizing the wearing status is shown in the figure.

[0239] like Figure 10 As shown, the wearable device 1000 includes: a signal generation module 1001, a signal acquisition module 1002, a signal analysis module 1003, and a guidance analysis module 1004. These modules or components can communicate via one or more communication buses (I2C) or signal lines. Those skilled in the art will understand that... Figure 10 The modules or components shown do not constitute a limitation on the wearable device. The wearable device 1000 may include more or fewer parts than shown, or combine certain parts, or have different arrangements of parts.

[0240] Among them, such as Figure 10The signal generation module 1001 shown can control the vibration motor to generate N vibration signals. The signal generation module 1001 can respond to the user's operation of triggering the physiological data measurement function, or the user's operation of triggering the wearing status recognition function, or the response to incoming calls, new messages, or reminder events. The signal generation module 1001 can control one or more vibration motors to emit N vibration signals with different signal parameters, so that the vibration signals can be fed back through the human body or other media.

[0241] like Figure 10 The signal acquisition module 1002 shown can control the accelerometer to acquire feedback signals, that is, the vibration signals fed back by the human body or other media, and send the feedback signals to the information analysis module. Figure 10 (Not shown in the image).

[0242] like Figure 10 The signal analysis module 1003 shown can determine the wearing state and tightness state based on the feedback signal. In one possible design, when the preset recognition model is a classifier, the signal analysis module 1003 can extract the signal features of the feedback signal and use these features as input to run the preset recognition model to obtain the wearing state and tightness state of the wearable device. In another possible design, when the preset recognition model is a neural network, the signal analysis module 1003 can directly use the feedback signal as input to run the preset recognition model to obtain the wearing state and tightness state. This application embodiment does not limit the specific implementation of the preset recognition model. The signal analysis module 1003 can also send the wearing state and tightness state to the guidance analysis module 1004. Figure 10 (Not shown in the image).

[0243] like Figure 10 The guidance analysis module 1004 shown can determine guidance information based on the wearing status and tightness. On one hand, the guidance analysis module 1004 can adjust the working mode of the wearable device according to the current wearing status. For example, when the wearable device is not worn, the guidance analysis module 1004 can control the wearable device to enter a low-power mode to save resources. When the wearable device is worn, the guidance analysis module 1004 can control the wearable device to enter a normal working mode to achieve health monitoring of the user.

[0244] On the other hand, when the wearable device is in a worn state, the guidance analysis module 1004 can also adjust the measurement weights of the user's physiological data according to the tightness, so that the wearable device can achieve stable health monitoring functions based on the measurement weights and the user's physiological data. The guidance analysis module 1004 can also output guidance information in case of abnormal tightness to guide the user to adjust the tightness of the wearable device. For example, if the smartwatch is worn too tightly, the guidance analysis module 1004 can control the smartwatch's display to show the guidance information "Please adjust the wristband buckle to loosen the fit," guiding the user to loosen the smartwatch's tightness. As another example, if the smartwatch is worn too loosely, the guidance analysis module 1004 can also control the smartwatch's speaker to emit the voice guidance information "Currently worn too loose," guiding the user to tighten the smartwatch's tightness.

[0245] Other embodiments of this application provide an electronic device that may include: the aforementioned display screen (such as a touchscreen), a memory, and one or more processors. The display screen, memory, and processors are coupled. The memory stores computer program code, which includes computer instructions. When the processor executes the computer instructions, the electronic device can perform various functions or steps performed by the wearable device in the above method embodiments. The structure of the electronic device can be referred to... Figure 2 The structure of the wearable device 200 shown is illustrated.

[0246] This application also provides a chip system, such as... Figure 11 As shown, the chip system 1100 includes at least one processor 1101 and at least one interface circuit 1102. The processor 1101 and the interface circuit 1102 are interconnected via lines. For example, the interface circuit 1102 can be used to receive signals from other devices (e.g., the memory of an electronic device). As another example, the interface circuit 1102 can be used to send signals to other devices (e.g., the processor 1101). Exemplarily, the interface circuit 1102 can read instructions stored in memory and send those instructions to the processor 1101. When the instructions are executed by the processor 1101, the electronic device can perform the steps in the above embodiments. Of course, the chip system may also include other discrete devices, and this application embodiment does not specifically limit this.

[0247] This application also provides a computer storage medium that includes computer instructions. When the computer instructions are executed on the electronic device, the electronic device causes the electronic device to perform various functions or steps performed by the mobile phone in the above method embodiment.

[0248] This application also provides a computer program product that, when run on a computer, causes the computer to perform the various functions or steps performed by the mobile phone in the above method embodiments.

[0249] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above 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.

[0250] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0251] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0252] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0253] If the integrated unit is implemented as 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 solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0254] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for recognizing wearing status, characterized in that, The method, applied to wearable devices, includes one or more vibration motors and one or more sensors, wherein the vibration motors are used to send vibration signals, and the sensors are used to collect feedback signals from the vibration signals, the method comprising: In response to an incoming call, a new message, or a notification event, N vibration signals are sent, where N ≥ 2 and N is a positive integer; wherein the N vibration signals are used to indicate the incoming call, the new message, or the notification event, and the signal parameters of the N vibration signals are different, including frequency and / or waveform; The feedback signals of the N vibration signals are collected; wherein, the feedback signals include: the signals of the N vibration signals after being filtered by the human body when the wearable device is in the wearing state, or the signals of the N vibration signals after being filtered by other media when the wearable device is not in the wearing state; Based on the signal characteristics of each feedback signal, the wearing state of the wearable device is identified; wherein, the signal characteristics of the feedback signal include at least time-domain characteristics and frequency-domain characteristics, and the wearing state of the wearable device is either the worn state or the unworn state; wherein, the time-domain characteristics include the effective power value of the feedback signal within a preset duration, and the frequency-domain characteristics include the median frequency on the power spectrum of the feedback signal; if the effective power value is greater than a first preset threshold and the median frequency is less than a first frequency threshold, the wearable device is in an unworn state; if the effective power value is greater than a second preset threshold and the median frequency is greater than a second frequency threshold, the wearable device is in a worn state; Wherein, the first frequency threshold is less than or equal to the second frequency threshold.

2. The method for identifying wearing status according to claim 1, characterized in that, The wearable device includes multiple vibration motors, and the different vibration motors are located in different positions within the wearable device.

3. The method for recognizing wearing status according to claim 1, characterized in that, The worn state includes: a first loose state, a second loose state, and a third loose state; wherein, in the first loose state, the wearable device is worn looser than the normal tightness, in the second loose state, the wearable device is worn tighter than the normal tightness, and in the third loose state, the wearable device is worn at the normal tightness.

4. The method for recognizing wearing status according to claim 3, characterized in that, The method further includes: If the wearable device is in the first tightness state, a first prompt message is issued, which is used to instruct the user to adjust the tightness of the wearable device. If the wearable device is in the second tightness state, a second prompt message is issued, which instructs the user to loosen the tightness of the wearable device.

5. The method for recognizing wearing status according to claim 3, characterized in that, The method further includes: The measurement weights of the wearable device for measuring the user's physiological data are adjusted according to the tightness of the wearable device; wherein the measurement weight in the third tightness state is greater than the measurement weight in the first tightness state, and the measurement weight in the third tightness state is also greater than the measurement weight in the second tightness state.

6. The method for recognizing wearing status according to any one of claims 1-5, characterized in that, The method further includes: If the wearable device is in the unworn state, then the wearable device is controlled to enter a low-power mode.

7. The method for recognizing the wearing state according to any one of claims 3-5, characterized in that, The wearable device includes a preset recognition model, which has the ability to identify the wearing status of the wearable device based on the feedback signals of the N vibration signals; The step of identifying the wearing status of the wearable device based on the signal characteristics of each of the feedback signals includes: Based on the signal characteristics of each feedback signal, the wearing status of the wearable device is obtained using the preset recognition model.

8. The method for recognizing wearing status according to claim 7, characterized in that, The preset recognition model is a classifier; The step of obtaining the wearing status of the wearable device based on the signal characteristics of each feedback signal and using the preset recognition model includes: Obtain the signal characteristics of each of the feedback signals, wherein the signal characteristics include the root mean square of the signal amplitude of the feedback signal within a preset time period; Each of the aforementioned signal features is used as input to the classifier, which is then run to output the wearing status of the wearable device.

9. The method for recognizing wearing status according to claim 7, characterized in that, The preset recognition model is a neural network model; The step of obtaining the wearing status of the wearable device based on the signal characteristics of each feedback signal and using the preset recognition model includes: Each of the feedback signals is used as input to the neural network model, the neural network model is run, and the wearing status of the wearable device is output. The neural network model is used to acquire the signal characteristics of each feedback signal, and to obtain and output the wearing status of the wearable device based on each signal characteristic; the signal characteristics include: the root mean square of the signal amplitude of the feedback signal within a preset time period.

10. The method for recognizing wearing status according to claim 8, characterized in that, The first preset threshold is a first root mean square threshold, and the second preset threshold is a second root mean square threshold; If the root mean square (RMS) is greater than the first RMS threshold and the median frequency is less than the first frequency threshold, then the wearable device is in an unworn state; or, If the root mean square is greater than the second root mean square threshold and the median frequency is greater than the second frequency threshold, then the wearable device is in a worn state. Wherein, the first root mean square threshold is the same as or different from the second root mean square threshold.

11. The method for recognizing the wearing state according to any one of claims 8-10, characterized in that, When the wearable device is in a worn state If the root mean square is greater than the third root mean square threshold and the median frequency is less than the third frequency threshold, then the wearable device is in the first loose / tight state. If the root mean square is less than the fourth root mean square threshold and the median frequency is greater than the fourth frequency threshold, then the wearable device is in the second loose / tight state. Wherein, the third root mean square threshold is greater than or equal to the fourth root mean square threshold, and the third frequency threshold is less than or equal to the fourth frequency threshold.

12. The method for recognizing the wearing state according to any one of claims 8-10, characterized in that, Before obtaining the wearing state of the wearable device by using the preset recognition model based on the signal characteristics of each feedback signal, the method further includes: Acquire training samples and use the training samples to train the preset recognition model, so that the preset recognition model has the ability to identify the wearing status of the wearable device based on the feedback signals of the N vibration signals; The training samples include input samples and output samples; the input samples include multiple sample feedback signals or signal features of multiple sample feedback signals, the multiple sample feedback signals include: feedback signals of multiple users with different body fat contents wearing the wearable device for the N vibration signals, and feedback signals of other media for the N vibration signals when the wearable device is not worn; the output samples are the actual wearing state corresponding to the input samples; The signal characteristics of the sample feedback signal include: the root mean square of the signal amplitude of the sample feedback signal within a preset time period and the median frequency of the sample feedback signal.

13. A wearable device, characterized in that, The wearable device includes one or more vibration motors, one or more sensors, a memory, and one or more processors; the one or more vibration motors, the one or more sensors, the memory, and the processor are coupled; the vibration motors are used to generate vibration signals, the sensors are used to collect feedback signals of the vibration signals, and the memory is used to store computer program code, the computer program code including computer instructions; when the processor executes the computer instructions, the wearable device performs the method as described in any one of claims 1-12.

14. A computer storage medium, characterized in that, Includes computer instructions that, when executed on a wearable device, cause the wearable device to perform the method as described in any one of claims 1-12.

Images