Wrist-raising detection method, smart wearable device, and computer-readable storage medium

Abstract

The present application relates to the field of smart terminals, and in particular to a wrist-raising detection method, a smart wearable device, and a computer-readable storage medium. In the wrist-raising detection method of the embodiment of the present application, a second detection is performed on the basis of the first detection, which is equivalent to further verifying the correctness of the first result, which can effectively reduce the probability of misjudgment and effectively improve the detection accuracy; in addition, the first detection of the wrist-raising action using the downsampled data can effectively reduce memory consumption and calculation amount, which helps to reduce the power consumption of the smart wearable device; the second detection using the monitoring data with a higher sampling frequency can effectively reduce the detection delay to prevent misjudgment.

Description

Technical Field

[0001] The present application relates to the field of smart terminals, and in particular to a wrist-raising detection method, a smart wearable device, and a computer-readable storage medium. Background Art

[0002] With the development of electronic products, smart wearable devices such as smart watches have gradually become popular. In order to reduce the power consumption of smart wearable devices and improve their battery life, smart wearable devices are usually equipped with an automatic screen-off function. For example, if a smart watch is set to automatically turn off the screen, if the user does not operate the screen of the smart watch for a period of time, the smart watch will automatically turn off the screen. In order to improve the user experience, the wrist-raising / turning wrist detection function came into being.

[0003] Wrist raising / turning occurs frequently in daily life. If accurate detection cannot be achieved, it will affect the user experience of waking up the screen or other functions. Therefore, the detection accuracy of wrist raising / turning by smart wearable devices is an urgent problem to be solved. Summary of the invention

[0004] The present application provides a wrist-raising detection method, a smart wearable device, and a computer-readable storage medium, which can effectively improve the accuracy of wrist-raising detection.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions: In a first aspect, a wrist raising detection method is provided, comprising: Performing a first detection on the wrist raising action according to the first monitoring data of the smart wearable device to obtain a first result; If the first result indicates that a wrist-raising action is detected, a second detection is performed according to the second monitoring data of the smart wearable device to obtain a second result; wherein the sampling frequency of the first monitoring data is lower than the sampling frequency of the second monitoring data; If the second result indicates that a wrist raising action is detected, the smart wearable device is controlled to light up the screen.

[0006] In an implementation of the first aspect, the method further includes: If the second result indicates that no wrist raising action is detected, the smart wearable device is controlled to keep the screen off.

[0007] If the first result indicates that no wrist raising action is detected, the smart wearable device is controlled to keep the screen off.

[0008] In an implementation of the first aspect, the second monitoring data is monitoring data acquired after the first monitoring data. For example, the wrist raising detection method may include: Obtaining first monitoring data corresponding to time t1; Perform a first detection on the wrist-raising action according to the first monitoring data to obtain a first result; If the first result indicates that a wrist-raising action is detected, the acceleration data of the smart wearable device from time t1 to time t2 is acquired to obtain second monitoring data; wherein time t2 is after time t1, and the time interval between time t1 and time t2 is greater than the sampling interval of the acceleration data; Perform a second test according to the second monitoring data to obtain a second result; If the second result indicates that a wrist raising action is detected, the smart wearable device is controlled to light up the screen.

[0009] In the above implementation, it is equivalent to performing a second test based on the raw data collected by the accelerometer after time t1 after performing a first test based on the first monitoring data at time t1. In this way, caching can be performed based on whether a second test is required, that is, when it is determined that a second test is required, the raw data collected by the accelerometer at the next sampling time is cached, and there is no need to cache the raw data at each sampling time, which greatly reduces memory usage.

[0010] In an implementation of the first aspect, the first monitoring data and the second monitoring data are three-axis accelerations. The three-axis accelerometer can capture small movement changes in three dimensions, providing a reliable data basis for subsequent wrist-raising detection.

[0011] In the embodiment of the present application, the second detection is performed on the basis of the first detection, which is equivalent to further verifying the correctness of the first result, which can effectively reduce the probability of misjudgment and effectively improve the detection accuracy. In addition, only when the first result indicates that a wrist-raising action is detected, the second detection is performed according to the second monitoring data; since the sampling frequency of the first monitoring data is lower than the sampling frequency of the second monitoring data, it is equivalent to using low-frequency sampling data for the first detection and high-frequency sampling data for the second detection. When the first result does not detect a wrist-raising action, there is no need to perform the second detection. In this way, the memory usage and data processing volume of the data in the wrist-raising detection process can be effectively reduced, thereby helping to reduce the impact of wrist-raising detection on the power consumption of smart wearable devices.

[0012] In an implementation of the first aspect, performing a first detection on the wrist raising action according to the first monitoring data of the smart wearable device to obtain a first result includes: Performing filtering processing on the first monitoring data to obtain filtered first monitoring data; A first detection is performed on the wrist raising action according to the first filtered monitoring data to obtain a first result.

[0013] Through filtering processing, the noise in the signal can be effectively filtered out, which helps to improve the accuracy of subsequent detection methods.

[0014] In an implementation of the first aspect, performing a first detection on the wrist raising action according to the filtered first monitoring data to obtain a first result includes: Calculating a speed parameter according to the first filtered monitoring data; A first detection is performed on the wrist raising action according to the speed parameter to obtain a first result.

[0015] For example, the velocity parameters may include the total acceleration and the differential acceleration. Specifically, through the formula Calculate the total acceleration of the filtered acceleration data. represents the total acceleration of the i-th group of acceleration data, ( ) represents the i-th group of acceleration data after filtering. Calculate the differential acceleration of the filtered acceleration data. ) represents the differential acceleration of the i-th group of acceleration data.

[0016] It can be understood that the speed parameter is calculated based on the acceleration data, which can characterize the acceleration properties of the smart wearable device and is used to more deeply describe and analyze the movement of the smart wearable device. Therefore, the speed parameter provides a reliable data basis for subsequent wrist lift detection.

[0017] In an implementation of the first aspect, performing a first detection on the wrist raising action according to the speed parameter to obtain a first result includes: Perform feature extraction processing according to the speed parameter to obtain feature data; A first detection is performed on the wrist raising action according to the characteristic data to obtain a first result.

[0018] Optionally, the feature data may include the current value (endValue), the average value (meanValue), the maximum value (maxValue) and its position in the buffer (maxIndex), the minimum value (minValue) and its position in the buffer (minIndex), the difference between the maximum value and the current value (maxEndGap), the difference between the minimum value and the current value (minEndGap), and the difference between the maximum value and the minimum value (maxMinGap).

[0019] Through feature extraction processing, it is possible to largely explore the intrinsic relationships, change trends and other characteristic information between data, provide a reliable data basis for subsequent wrist-raising detection, and help improve detection accuracy.

[0020] In an implementation of the first aspect, performing a first detection on the wrist raising action according to the characteristic data to obtain a first result includes: Inputting the feature data into the trained decision model and outputting the first result; The decision model includes a plurality of judgment rules, and each of the judgment rules includes a relationship between input data and a threshold.

[0021] It is understandable that one judgment rule is often difficult to summarize the characteristics of wrist raising / flipping in all scenarios. In order to adapt to different scenarios, multiple judgment rules can be set. In one implementation, if the first monitoring data satisfies any one of the judgment rules, the first result indicates that the wrist raising / flipping action is detected; if the first monitoring data does not satisfy any one of the judgment rules, the first result indicates that the wrist raising / flipping action is not detected. In another implementation, if the first monitoring data satisfies N judgment rules, the first result indicates that the wrist raising / flipping action is detected. Among them, N is greater than 1 and less than / equal to the total number of judgment rules.

[0022] By setting multiple judgment rules, the scalability of the detection method can be improved. When it is necessary to add more scenarios or the detection accuracy in a certain scenario is low, the judgment rules for the scenario can be optimized separately, so that the first detection method can adapt to different scenarios and expand the application scope of the first detection method.

[0023] Optionally, the decision model can be a decision tree model. Since the decision tree model has good interpretability, the structure of the model is intuitive, easy to understand and interpret, and can process numerical and categorical data; and the computational complexity is low, there is no need to rely on a large amount of training data, and the model training speed is fast. Therefore, using the decision tree model for the first detection helps to reduce the computational complexity of the first detection process and the power consumption caused by the first detection.

[0024] In an implementation of the first aspect, performing a second detection according to the second monitoring data of the smart wearable device to obtain a second result includes: Calculating an acceleration difference according to the second monitoring data; If the acceleration difference is less than or equal to a preset threshold, the second result indicates that a wrist raising action is detected; If the acceleration difference is greater than a preset threshold, the second result indicates that no wrist raising action is detected.

[0025] Optionally, the acceleration difference includes a first difference and a second difference; the preset threshold includes a first threshold and a second threshold; wherein the first difference is the acceleration difference between the second monitoring data at different sampling times; and the second difference is the difference between the combined acceleration corresponding to the second monitoring data and the gravitational acceleration; The second detection step comprises: If the first difference is less than or equal to the first threshold, and the second difference is less than or equal to the second threshold, the second result indicates that a wrist raising action is detected; If the first difference is greater than the first threshold, and / or the second difference is greater than the second threshold, the second result indicates that no wrist raising action is detected.

[0026] For example, by the formula Calculate the first difference. Where, The total acceleration corresponding to the second monitoring data at time, is the first threshold. m is an integer greater than 0 and less than n, where n is the downsampling ratio. is the sampling interval of the accelerometer.

[0027] For example, by the formula Calculate the second difference. Where, is the acceleration due to gravity, is the second threshold.

[0028] In this implementation, the acceleration difference between the monitoring data and the difference between the monitoring data and the gravity acceleration are considered at the same time, which is equivalent to considering both the acceleration change of the smart wearable device itself and the acceleration change of the smart wearable device relative to the environment. This method can effectively improve the detection accuracy.

[0029] In an implementation of the first aspect, the method further includes: If the user is in motion, the preset threshold is set to a first preset value; If the user is in a non-exercise state, the preset threshold is set to a second preset value; wherein the first preset value is greater than the second preset value.

[0030] It is understandable that the acceleration fluctuations of the human body are different when the human body is in motion and when the human body is stationary. In the above embodiment, it is equivalent to appropriately relaxing the data range in the judgment condition when the user is in motion. Since the combined acceleration changes significantly when the human body is in motion, and the combined acceleration is not close to the acceleration of gravity, appropriately relaxing the data range in the judgment condition in this case can effectively reduce the probability of misjudgment and help improve the detection accuracy.

[0031] In an implementation of the first aspect, the method further includes: Calculate the change value of acceleration according to the third monitoring data; If the change value is greater than a third threshold, it is determined that the user is in a motion state; If the change value is less than or equal to a third threshold, it is determined that the user is in a non-motion state; wherein, the sampling frequency of the third monitoring data is the same as the sampling frequency of the second monitoring data, and the third monitoring data is the monitoring data acquired within a preset time window before the first monitoring data.

[0032] It can be understood that the recognition detection of the motion state is equivalent to being performed based on the original data before downsampling processing, the first detection is performed based on the data after downsampling processing, and the second detection is performed based on the original data before downsampling processing.

[0033] In the embodiment of the present application, the judgment threshold of the second detection is set according to the user's motion state, so that the judgment condition of the second detection can adapt to the two different states of the user's motion and non-motion, effectively improving the detection accuracy of the user's wrist-raising action in different states. In addition, the motion state recognition detection is performed based on the original data before downsampling, which effectively reduces the delay of the second detection.

[0034] In a second aspect, a smart wearable device is provided, comprising: one or more processors; one or more memories; The memory stores a computer program, and when the computer program is executed by the processor, the smart wearable device implements the method as described in any one of the first aspects.

[0035] According to a third aspect, a chip system is provided, comprising a processor coupled to a memory, wherein the processor is configured to run a computer program stored in the memory to implement a method as described in any one of the first aspects.

[0036] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the method according to any one of the first aspects is implemented.

[0037] According to a fifth aspect, a computer program product is provided, wherein the computer program product comprises a computer program code, and when the computer program code runs on an electronic device, the electronic device implements the method as described in any one of the first aspects.

[0038] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of a scenario of illuminating the screen by raising the wrist or turning the wrist provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a smart wearable device provided in an embodiment of the present application; Figure 3 A software structure block diagram of the smart wearable device 100 according to an embodiment of the present application; Figure 4 A schematic diagram of a setting interface provided in an embodiment of the present application; Figure 5 A schematic diagram of a process flow of a wrist-lift detection method provided in an embodiment of the present application; Figure 6 A schematic diagram of an acceleration coordinate system provided in an embodiment of the present application; Figure 7 A schematic diagram of the overall process of the wrist-lift detection method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In the following description, specific details such as specific system structures and technologies are provided for illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details.

[0041] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0042] It should also be understood that in the embodiments of the present application, "one or more" refers to one, two or more than two; "and / or" describes the association relationship of associated objects, indicating that three relationships may exist; for example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B may be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0043] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", "fourth", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0044] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0045] With the development of electronic products, smart wearable devices such as smart watches have gradually become popular. In order to reduce the power consumption of smart wearable devices and improve their battery life, smart wearable devices are usually equipped with an automatic screen-off function. For example, if a smart watch is set to automatically turn off the screen, if the user does not operate the screen of the smart watch for a period of time, the smart watch will automatically turn off the screen. In order to improve the user experience, the wrist-raising / turning wrist detection function came into being.

[0046] In one application scenario, the wrist-raise / wrist-turn detection function can be used to wake up the screen. Figure 1 As shown in (a) in the figure, in the screen-off state, the smartwatch detects the user's wrist-raising / turning action through the wrist-raising / turning detection function; when the user's wrist-raising / turning action is detected, the smartwatch automatically turns on the screen. With the wrist-raising / turning detection function, when the user needs to check the time or messages, there is no need to manually click the screen or operate physical buttons. The smartwatch can automatically turn on the screen by simply raising the wrist / turning the wrist, thereby improving the intelligence level of smart wearable devices.

[0047] In another application scenario, the wrist-raising / turning detection function can be used for wake-up functions, such as waking up a voice assistant or quickly opening an application. Figure 1 As shown in (b), in the screen-off state, the smartwatch detects the user's wrist-raising / wrist-turning action through the wrist-raising / wrist-turning detection function; when the user's wrist-raising / wrist-turning action is detected, the smartwatch automatically lights up the screen, automatically turns on the camera, and displays the shooting interface. Through the wrist-raising / wrist-turning detection function, when the user needs to quickly wake up a function, there is no need to manually light up the screen and then operate the screen controls to turn on a function. Just raise your wrist / turn your wrist, and the smartwatch will automatically light up the screen and automatically wake up the function, thereby improving the intelligence level of smart wearable devices, reducing user operations, and helping to improve user experience.

[0048] Wrist raising / turning occurs frequently in daily life. If accurate detection cannot be achieved, it will affect the user experience of waking up the screen or other functions. Therefore, the detection accuracy of wrist raising / turning by smart wearable devices is an urgent problem to be solved.

[0049] Based on this, an embodiment of the present application provides a wrist-raising detection method. In the embodiment of the present application, a detection process for preventing misjudgment is added, which can effectively reduce the probability of misjudgment and effectively improve the detection accuracy. In addition, monitoring data with a lower sampling frequency is used for preliminary detection, and monitoring data with a higher sampling frequency is used for preventing misjudgment detection, which can reduce power consumption while also reducing detection delay.

[0050] The wrist-raising detection method provided in the embodiment of the present application can be applied to a smart wearable device with a screen. The smart wearable device may include a smart watch, a smart bracelet, etc. The embodiment of the present application does not limit the specific technology and specific device form adopted by the smart wearable device.

[0051] See also Figure 2 , which is a structural diagram of a smart wearable device provided in an embodiment of the present application. The smart wearable device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a touch sensor 180K, an ambient light sensor 180L, and the like.

[0052] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the smart wearable device 100. In other embodiments of the present application, the smart wearable device 100 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0053] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0054] The controller may be the nerve center and command center of the smart wearable device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0055] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0056] The external memory 120 generally refers to an external memory. In the embodiment of the present application, the external memory refers to a memory other than the memory of the electronic device and the cache of the processor, and the memory is generally a non-volatile memory.

[0057] The internal memory 121, which may also be referred to as "memory", may be used to store computer executable program codes, which include instructions. The internal memory 121 may include a program storage area and a data storage area. The program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), and the like.

[0058] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-OLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the smart wearable device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1. In some embodiments, the smart wearable device 100 displays a user interface through the display screen 194.

[0059] The smart wearable device 100 implements display functions through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

[0060] The smart wearable device 100 can realize the shooting function through ISP, camera 193, video codec, GPU, display screen 194 and application processor.

[0061] The camera 193 is used to capture still images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, and then passes the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV or other format. In some embodiments, the smart wearable device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.

[0062] The smart wearable device 100 also includes various sensors that can convert various physical signals into electrical signals. Exemplarily, the pressure sensor 180A is used to sense the pressure signal and can convert the pressure signal into an electrical signal. The gyroscope sensor 180B can be used to determine the motion posture of the smart wearable device 100. The air pressure sensor 180C is used to measure the air pressure. The magnetic sensor 180D includes a Hall sensor. The acceleration sensor 180E can detect the magnitude of the acceleration of the smart wearable device 100 in various directions (generally three axes). The distance sensor 180F is used to measure the distance. The smart wearable device 100 can measure the distance by infrared or laser. The proximity light sensor 180G may include, for example, a light emitting diode (LED) and a light detector, such as a photodiode. The ambient light sensor 180L is used to sense the brightness of the ambient light. The smart wearable device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived ambient light brightness. The fingerprint sensor 180H is used to collect fingerprints. The smart wearable device 100 can use the collected fingerprint characteristics to realize fingerprint unlocking, access application lock, fingerprint photography, fingerprint answering calls, etc. The temperature sensor 180J is used to detect temperature. In some embodiments, the smart wearable device 100 uses the temperature detected by the temperature sensor 180J to execute a temperature processing strategy. The bone conduction sensor 180M can obtain a vibration signal.

[0063] The touch sensor 180K is also called a "touch panel". The touch sensor 180K can be set on the display screen 194, and the touch sensor 180K and the display screen 194 form a touch screen, also called a "touch screen". The touch sensor 180K is used to detect touch operations acting on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to the touch operation can be provided through the display screen 194. In other embodiments, the touch sensor 180K can also be set on the surface of the smart wearable device 100, which is different from the position of the display screen 194.

[0064] Exemplarily, in an embodiment of the present application, the touch sensor 180K can detect a user's click operation on an application icon, and transmit the detected click operation to the application processor, determine that the click operation is used to start or run the application, and then execute the running operation of the application.

[0065] The wireless communication function of the smart wearable device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0066] The smart wearable device 100 can implement audio functions such as music playback and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D, and the application processor.

[0067] The above is a specific description of the embodiment of the present application using the smart wearable device 100 as an example. It should be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the smart wearable device 100. The smart wearable device 100 may have more or fewer components than those shown in the figure, may combine two or more components, or may have different component configurations. The various components shown in the figure may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and / or application-specific integrated circuits.

[0068] In addition, an operating system runs on the above components, such as the iOS operating system, the Android open source operating system, and the Windows operating system, etc. Application programs can be installed and run on the operating system.

[0069] The operating system of the smart wearable device 100 can adopt a layered architecture, an event-driven architecture, a micro-kernel architecture, a micro-service architecture, or a cloud architecture. The embodiment of the present application takes the Android system of the layered architecture as an example to illustrate the software structure of the smart wearable device 100.

[0070] Figure 3 1 is a software structure block diagram of the smart wearable device 100 according to an embodiment of the present application.

[0071] The layered architecture divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom: the application layer, the application framework layer, the system library and Android runtime (Android runtime), and the kernel layer.

[0072] The application layer can include a series of application packages.

[0073] like Figure 3 As shown, the application package may include applications such as camera, gallery, calendar, call, map, navigation, sports health, settings, music, video, short message, etc. For example, the setting application may include a wrist raising / turning detection function. When the smart wearable device turns on the wrist raising / turning detection function, the smart wearable device can obtain monitoring data through the wrist raising / turning detection function, and analyze and process the monitoring data to detect the user's wrist raising / turning action.

[0074] The application framework layer provides an application programming interface (API) and programming framework for applications in the application layer. The application framework layer includes some predefined functions.

[0075] like Figure 3 As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0076] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0077] The content provider is used to store and obtain data and make the data accessible to the application. The data may include monitoring data obtained by the sensor module 180 (such as acceleration data obtained by the acceleration sensor 180E), video, image, audio, calls made and received, browsing history and bookmarks, phone book, etc.

[0078] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.

[0079] The phone manager is used to provide communication functions for the smart wearable device 100, such as management of call status (including answering, hanging up, etc.).

[0080] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0081] The notification manager allows applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify the completion of downloads, message reminders (such as travel messages, etc.). The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is prompted in the status bar, a prompt sound is emitted, the device vibrates, the indicator light flashes, etc.

[0082] In the embodiment of the present application, the application framework layer may include a camera access interface, wherein the camera access interface is used to provide an application programming interface and a programming framework for the camera application.

[0083] Android runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system.

[0084] The core library consists of two parts: one part is the function that needs to be called by the Java language, and the other part is the Android core library.

[0085] The application layer and the application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.

[0086] The system layer can include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.

[0087] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

[0088] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0089] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, synthesis and layer processing.

[0090] A 2D graphics engine is a drawing engine for 2D drawings.

[0091] The kernel layer is the layer between hardware and software. The kernel layer includes at least display driver, camera driver, audio driver, and sensor driver. For example, when the settings application detects the user's wrist raising / turning motion through the wrist raising / turning detection function, it can send instructions to the display driver of the kernel layer through the application framework layer and the system layer to wake up the screen of the smart wearable device.

[0092] The following is an introduction to the wrist raising / turning detection function involved in the embodiment of the present application. It is understandable that the wrist raising / turning detection function can be implemented on a smart wearable device having the above hardware structure / software structure.

[0093] In one case, the wrist-raising / turning-over detection function on the smart wearable device can be set to be enabled by default. For example, as long as the smart wearable device is powered on, the wrist-raising / turning-over detection function is enabled.

[0094] In another case, the wrist raising / turning detection function can be manually turned on or off by the user. Figure 4 , is a schematic diagram of the setting interface provided in the embodiment of the present application. Figure 4 As shown, the setting interface includes an information area 401 and a selection control 402. The information area 401 is used to display the name of the wrist raising / turning detection function. The selection control 402 is used to implement the corresponding software function when the user clicks / touches it. The selection control 402 corresponds to the function displayed in the above information area. Figure 4 As shown in (a) in FIG. 4 , the selection control 402 is in an unselected state, indicating that the wrist raising / turning detection function is turned off at this time. Figure 4 As shown in (b) in FIG. 1 , the selection control 402 is in a selected state, indicating that the wrist raising / turning detection function is now turned on.

[0095] In another case, the wrist raising / turning detection function can be turned on / off at a user-defined time. For example, if the user-defined time period is 07:00-22:00, the wrist raising / turning detection function is turned on at 07:00 and turned off at 22:00.

[0096] When the wrist-raise / turn-over detection function in a smart wearable device is turned on, the function can run in the foreground, and the device screen can only display the logo of the wrist-raise / turn-over detection function when the screen is off. When the wrist-raise / turn-over detection function in a smart wearable device is turned on, the function can run in the background, and the smart wearable device does not display the logo of the wrist-raise / turn-over detection function when the screen is off, but the function can obtain the monitoring data of the sensor in real time in the background, and wake up the screen when the wrist-raise / turn-over action is detected according to the monitoring data.

[0097] The following describes the wrist raising detection method involved in the wrist raising / turning wrist detection function. It should be noted that the wrist raising detection method of the embodiment of the present application can not only detect the wrist raising action, but also detect the wrist turning action.

[0098] See also Figure 5 , is a flowchart of the wrist-raising detection method provided in an embodiment of the present application. As an example and not a limitation, Figure 5 As shown, the wrist-raising detection method may include the following steps: S501, performing a first detection on the wrist raising action according to the first monitoring data to obtain a first result.

[0099] The monitoring data may be sampled data monitored by a sensor of the smart wearable device. The monitoring data may include acceleration data, distance data, etc. Optionally, in an embodiment of the present application, the monitoring data is acceleration data.

[0100] by Figure 2Taking the device structure shown as an example, the acceleration sensor 180E in the sensor module 180 acquires acceleration data at a certain sampling frequency, and sends the acquired acceleration data to the processor 110 in real time; the processor 110 records the received acceleration data as monitoring data, and executes the wrist-raising detection method of the embodiment of the present application according to the monitoring data.

[0101] Since acceleration sensors (such as accelerometers) are small in size and consume less power than other sensors (such as gyroscopes), only using acceleration data to detect wrist-raising / wrist-turning actions reduces the detection method's reliance on multiple sensor data, reduces the power consumption caused by sensor data collection during the detection process, and helps reduce the power consumption of smart wearable devices.

[0102] In the embodiment of the present application, a three-axis accelerometer can be used as an acceleration sensor. The three-axis accelerometer can reflect the acceleration changes of the device in three dimensions, and the acceleration data obtained is ( x raw , y raw , z raw ).in, x raw represents the acceleration change on the x-axis, y raw represents the acceleration change on the y-axis, z raw Indicates the acceleration change of the z-axis. The three-axis accelerometer can capture tiny movement changes in three dimensions, providing a reliable data basis for subsequent wrist-lift detection.

[0103] For example, see Figure 6 , is a schematic diagram of the acceleration coordinate system provided in the embodiment of the present application. Figure 6 As shown in (a) in the figure, the y-axis direction is along the direction of the strap, and the x-axis direction is perpendicular to the strap. Figure 6 As shown in (b), according to the right-hand rule, the z-axis is perpendicular to the direction of the dial.

[0104] It should be noted that the three axes of the acceleration coordinate system may also be defined in other ways, such as the x-axis direction being along the direction of the strap, the y-axis direction being perpendicular to the strap, etc. The embodiment of the present application does not limit the acceleration coordinate system.

[0105] In one embodiment, the acceleration data sent by the accelerometer may be downsampled, and the acceleration data after the downsampling process may be used as the first monitoring data.

[0106] For example, the downsampling ratio n can be preset. Taking n=5 as an example, assuming that the sampling frequency of the accelerometer is 100 Hz, the acceleration data is downsampled according to the downsampling ratio n=5, and the sampling frequency of the first monitoring data is 20 Hz. For example, the original data collected by the accelerometer is { whether 1, whether 2, whether 3, whether 4, whether 5, whether 6, ...}, after downsampling with n = 5, the first monitoring data obtained is { whether 1, whether 6,……}.

[0107] In one implementation, the accelerometer may perform downsampling processing, and send the obtained first monitoring data after the downsampling processing to the processor.

[0108] In another implementation, the processor may perform downsampling processing, that is, the accelerometer sends the collected raw data to the processor, and the processor performs downsampling processing to obtain the first monitoring data.

[0109] Optionally, the downsampled data is stored in buffer 1.

[0110] Through downsampling processing, not only can the memory usage of acceleration data be reduced, but the frequency of wrist-raise detection can also be reduced, which helps to reduce the power consumption of smart wearable devices.

[0111] In another embodiment, the first monitoring data may be preprocessed.

[0112] In one implementation, the preprocessing may include filtering. For example, filtering is performed on the downsampled data in buffer 1. The length of buffer 1 may be determined according to the setting parameters of the filter. For example, the setting parameters of the filter include filtering the data within 1 second. When the sampling frequency of the accelerometer is 100 Hz (i.e., 100 samples per second), the length of buffer 1 may be set to 20, i.e., 20 sets of acceleration data are stored.

[0113] Optionally, the buffer 1 may adopt a first-in-first-out storage method. Whenever the buffer 1 updates data (ie, stores a new set of acceleration data), the data in the current buffer 1 is filtered.

[0114] Optionally, Gaussian filtering, sliding average filtering, etc. may be used for filtering. The embodiment of the present application does not specifically limit the method used for filtering.

[0115] Through filtering processing, the noise in the signal can be effectively filtered out, which helps to improve the accuracy of subsequent detection methods.

[0116] In another implementation, the preprocessing may include calculating velocity parameters. For example, the velocity parameters may include the total acceleration and the differential acceleration. Specifically, by the formula Calculate the total acceleration of the filtered acceleration data. represents the total acceleration of the i-th group of acceleration data, ( ) represents the i-th group of acceleration data after filtering. Calculate the differential acceleration of the filtered acceleration data. ) represents the differential acceleration of the i-th group of acceleration data.

[0117] Optionally, the preprocessed data may be stored in the buffer 2. For example, for the i-th group of acceleration data, the preprocessed data includes { When the length of buffer 1 is 20, buffer 2 includes the pre-processed data corresponding to each of the 20 groups of acceleration data after filtering, that is, the data volume is 20×7.

[0118] It can be understood that the speed parameter is calculated based on the acceleration data, which can characterize the acceleration properties of the smart wearable device and is used to more deeply describe and analyze the movement of the smart wearable device. Therefore, the speed parameter provides a reliable data basis for subsequent wrist lift detection.

[0119] In another implementation, the preprocessing may include: filtering the first monitoring data to obtain filtered first monitoring data; and calculating the speed parameter according to the filtered first monitoring data.

[0120] In another embodiment, feature extraction processing may be performed on the preprocessed data to obtain feature data. For example, if speed parameters are obtained after preprocessing, feature extraction processing may be performed on the speed parameters to obtain feature data.

[0121] Optionally, the feature data may include the current value (endValue), the average value (meanValue), the maximum value (maxValue) and its position in the buffer (maxIndex), the minimum value (minValue) and its position in the buffer (minIndex), the difference between the maximum value and the current value (maxEndGap), the difference between the minimum value and the current value (minEndGap), and the difference between the maximum value and the minimum value (maxMinGap).

[0122] For example, for the i-th group of preprocessed data { } , whose characteristic data include , all in buffer 2 x The average value of all x The maximum value and its position in buffer 2, all the values ​​in buffer 2 x The minimum value in and its position in buffer 2, all the x The maximum value in The difference between all x The minimum value in The difference between all x The difference between the maximum and minimum values ​​in . For the i-th group of preprocessed data { } , whose characteristic data include , all in buffer 2 y The average value of all y The maximum value and its position in buffer 2, all the values ​​in buffer 2 y The minimum value in and its position in buffer 2, all the y The maximum value in The difference between all y The minimum value in The difference between all y The difference between the maximum value and the minimum value in . By analogy, for each data in each set of preprocessed data, its corresponding feature data is calculated. In other words, the amount of feature data corresponding to each set of preprocessed data is 7×9.

[0123] As described above, the feature data is obtained by calculating the statistical value of the data in the buffer 2. Optionally, the feature data may be obtained in other ways, such as inputting the data in the buffer 2 into a trained feature extraction model to extract the feature data.

[0124] It is understandable that more or less feature data may be used in actual applications, and the embodiment of the present application does not specifically limit the type and quantity of feature data.

[0125] Through feature extraction processing, it is possible to largely explore the intrinsic relationships, change trends and other characteristic information between data, provide a reliable data basis for subsequent wrist-raising detection, and help improve detection accuracy.

[0126] In one embodiment, the first detection in the embodiment of the present application can be judged by one or more judgment rules. Each judgment rule can include the relationship between data and a threshold value, and judging whether the first monitoring data satisfies the judgment rule, that is, judging the relationship between the first monitoring data and the threshold value.

[0127] For example, several judgment rules are as follows: 1) ; 2) ; 3) ; 4) .

[0128] Among them, "&" indicates that the conditions must be met at the same time. Taking the judgment rule 1) as an example, it represents the current value of the differential acceleration on the y-axis Less than or equal to 0.46, greater than 0.204, and the current value of the y-axis acceleration Greater than 0.093. Taking the judgment rule 4) as an example, it represents the current value of the y-axis differential acceleration Greater than 0.46, and the minimum value of the combined acceleration is within the buffer zone Greater than 15.5, and the current value of the z-axis acceleration Greater than 1.796.

[0129] It is understandable that one judgment rule is often difficult to summarize the characteristics of wrist raising / flipping in all scenarios. In order to adapt to different scenarios, multiple judgment rules can be set. In one implementation, if the first monitoring data satisfies any one of the judgment rules, the first result indicates that the wrist raising / flipping action is detected; if the first monitoring data does not satisfy any one of the judgment rules, the first result indicates that the wrist raising / flipping action is not detected. In another implementation, if the first monitoring data satisfies N judgment rules, the first result indicates that the wrist raising / flipping action is detected. Among them, N is greater than 1 and less than / equal to the total number of judgment rules.

[0130] By setting multiple judgment rules, the scalability of the detection method can be improved. When it is necessary to add more scenarios or the detection accuracy in a certain scenario is low, the judgment rules for the scenario can be optimized separately, so that the first detection method can adapt to different scenarios and expand the application scope of the first detection method.

[0131] In one implementation, the first detection method in S501 may include: The feature data is input into the trained decision model to output a first result, wherein the decision model includes a plurality of judgment rules, and each judgment rule includes a relationship between data and a threshold.

[0132] Optionally, the decision model may be a neural network model or a decision tree model.

[0133] Compared with the neural network model, the decision tree model has good interpretability, the structure of the model is intuitive, easy to understand and explain, and can process numerical and categorical data; and the computational complexity is low, there is no need to rely on a large amount of training data, and the model training speed is fast. Therefore, in the embodiment of the present application, the decision tree model can be used for the first detection, which helps to reduce the computational complexity of the first detection process and the power consumption caused by the first detection.

[0134] Among them, the decision tree model is a machine learning model that makes decisions based on a tree structure. The decision tree consists of nodes and branches. The nodes are divided into internal nodes and leaf nodes. The internal nodes represent a test on a feature or attribute, the branches represent the results of the test, and the leaf nodes represent the results of the decision, that is, the classification category or the numerical prediction of regression. Starting from the root node, the characteristics of the sample are tested, and according to the test results, it moves down along the corresponding branch until it reaches the leaf node to obtain the final decision result.

[0135] It can be understood that the judgment rules can be regarded as the combination of conditions represented by each path from the root node to the leaf node in the decision tree, and each path corresponds to a set of judgment rules in the form of "if...then...". Continuing with the above judgment rule example, if , then the wrist raising / turning action is detected. The judgment rule is composed of the conditions of the three paths from the root node to the leaf node of the decision tree, namely , and >0.093 each indicated a pathway.

[0136] In the process of training the decision tree model, different judgment rules can be obtained by adjusting the parameters of the decision tree. It can be understood that the completion of the training of the decision tree model is equivalent to determining the judgment rules. In other words, the training of the decision tree model refers to adjusting the parameters of the decision tree so that the determined judgment rules can correctly detect the wrist raising / turning action.

[0137] In one example, the training process of a decision tree model may include: inputting training data into the decision tree model and outputting a predicted label; wherein the predicted label is used to indicate whether a wrist raising / flipping action is detected, such as label "1" indicates that a wrist raising / flipping action is detected, and label "0" indicates that a wrist raising / flipping action is not detected; calculating the difference between the predicted label and the actual label corresponding to the training data; if the difference value is greater than or equal to a training threshold, the training ends, and the current decision tree model is determined as the trained decision tree model; if the difference value is less than the training threshold, the model parameters of the decision tree model are adjusted according to the difference value, and the adjusted decision tree model continues to be trained until the training ends.

[0138] In order to improve the detection accuracy of the decision tree model, the training data includes not only the positive scene data (including the data of wrist raising / flipping action), but also the reverse scene data (excluding the data of wrist raising / flipping action), such as data in daily activities, typing office, washing face / hands, running and swinging arms, etc. The reverse scene data can improve the detection accuracy of the decision tree model for wrist raising / flipping action.

[0139] In the embodiment of the present application, the decision tree model may include multiple judgment rules. It is understandable that different judgment rules may correspond to different application scenarios, that is, different judgment rules may be used to detect wrist raising actions in different application scenarios. By setting multiple judgment rules, the scalability and application scope of the detection method may be improved.

[0140] S502: If the first result indicates that a wrist-raising action is detected, a second detection is performed according to the second monitoring data to obtain a second result; wherein the sampling frequency of the first monitoring data is lower than the sampling frequency of the second monitoring data.

[0141] In one implementation, the wrist-raising detection method may include: Obtaining first monitoring data corresponding to time t1; Perform a first detection on the wrist-raising action according to the first monitoring data to obtain a first result; If the first result indicates that a wrist-raising action is detected, the acceleration data of the smart wearable device from time t0 to time t1 is acquired to obtain second monitoring data; wherein time t0 is before time t1, and the time interval between time t0 and time t1 is greater than the sampling interval of the acceleration data; Perform a second test according to the second monitoring data to obtain a second result; If the second result indicates that a wrist raising action is detected, the smart wearable device is controlled to light up the screen.

[0142] In the above implementation, it is equivalent to performing a second test based on the raw data collected by the accelerometer before time t1 after performing a first test based on the first monitoring data at time t1. In this method, the raw data collected by the accelerometer before time t1 needs to be cached, which is equivalent to the raw data collected by the accelerometer at each sampling moment needing to be cached first, and it is not until the next sampling moment that it is known whether these cached data need to be used for the second test; when the second test is not required, the memory usage is greatly increased.

[0143] In another implementation, the wrist-raising detection method may include: Obtaining first monitoring data corresponding to time t1; Perform a first detection on the wrist-raising action according to the first monitoring data to obtain a first result; If the first result indicates that a wrist-raising action is detected, the acceleration data of the smart wearable device from time t1 to time t2 is acquired to obtain second monitoring data; wherein time t2 is after time t1, and the time interval between time t1 and time t2 is greater than the sampling interval of the acceleration data; Perform a second test according to the second monitoring data to obtain a second result; If the second result indicates that a wrist raising action is detected, the smart wearable device is controlled to light up the screen.

[0144] In the above implementation, it is equivalent to performing a second test based on the raw data collected by the accelerometer after time t1 after performing a first test based on the first monitoring data at time t1. In this way, caching can be performed based on whether a second test is required, that is, when it is determined that a second test is required, the raw data collected by the accelerometer at the next sampling time is cached, and there is no need to cache the raw data at each sampling time, which greatly reduces memory usage.

[0145] Optionally, both time t1 and time t2 are sampling times for collecting raw data corresponding to the first monitoring data. For example, the raw data collected by the accelerometer is { whether 1, whether 2, whether 3, whether 4, whether 5, whether 6, ...}, time t1 can be whether 1, t2 can be whether 6. The acceleration data from time t1 to time t2 includes { whether 1, whether 2, whether 3, whether 4, whether 5, whether 6}, recorded as the second monitoring data.

[0146] Optionally, time t1 is the sampling time for collecting the raw data corresponding to the first monitoring data, and time t2 is the time after time t1, that is, time t2 is not necessarily the sampling time. For example, the raw data collected by the accelerometer is { whether 1, whether 2, whether 3, whether 4, whether 5, whether 6, whether 7...}, time t1 can be whether 1, the sampling time t2 can be whether 6 and whether 7. The acceleration data from time t1 to time t2 includes { whether1, whether 2, whether 3, whether 4, whether 5, whether 6}, recorded as the second monitoring data. In this way, it is equivalent to appropriately extending the time range of the judgment condition. During the process of raising the wrist / turning the wrist, rather than just finishing the action, extending the time range of the judgment condition helps to obtain more accurate detection results.

[0147] In one embodiment, the second detection method in S502 may include: calculating the acceleration difference according to the second monitoring data; If the acceleration difference is less than or equal to the preset threshold, it means that the smart wearable device is in a stationary state relative to the human body, and the second result means that a wrist raising action is detected; If the acceleration difference is greater than a preset threshold, it indicates that the smart wearable device is in motion relative to the human body, and the second result indicates that no wrist-raising motion is detected.

[0148] Optionally, the acceleration difference may include a first difference in the combined acceleration between the second monitoring data at different sampling moments, and / or a second difference between the combined acceleration of the second monitoring data and the gravitational acceleration.

[0149] For example, by the formula Calculate the first difference. Where, The total acceleration corresponding to the second monitoring data at time, is the first threshold. m is an integer greater than 0 and less than n, where n is the downsampling ratio. is the sampling interval of the accelerometer.

[0150] For example, by the formula Calculate the second difference. Where, is the acceleration due to gravity, is the second threshold.

[0151] In one implementation, when the acceleration difference includes a first difference, the preset threshold includes the first threshold, and accordingly, the second detection method includes: calculating the first difference based on the combined acceleration of the second monitoring data; if the first difference is less than or equal to the first threshold, the second result indicates that a wrist raising action is detected; if the first difference is greater than the first threshold, the second result indicates that no wrist raising action is detected.

[0152] It can be understood that the first difference value may be calculated based on two adjacent second monitoring data, or may be calculated based on two non-adjacent second monitoring data.

[0153] Optionally, as long as there is a group of second monitoring data whose first difference is less than or equal to the first threshold value, it is determined that the wrist raising action is detected. For example, the second monitoring data includes { whether 1, whether 2, whether 3, whether 4, whether 5, whether 6}; Calculation whether 1 and whether 2, if the first difference is less than or equal to the first threshold, it is determined that the wrist raising action is detected; if the first difference is greater than the first threshold, then the calculation whether 2 and whether 3, and so on; if the calculated first differences are all greater than the first threshold, it is determined that no wrist raising action is detected.

[0154] Optionally, if the first difference of any group of the second monitoring data in the second monitoring data is less than or equal to the first threshold, it is determined that the wrist raising action is detected. For example, the second monitoring data includes { whether 1, whether 2, whether 3, whether 4, whether 5, whether 6}; Calculate separately whether 1 and whether 2, the first difference res1 of the total acceleration, whether 2 and whether 3, the first difference res2 of the total acceleration, whether 3 and whether 4, the first difference res3 of the total acceleration, whether 4 and whether 5, and whether 5 and whether 6; if the calculated first differences res1, res2, res3, res4 and res5 are all less than or equal to the first threshold, it is determined that the wrist-raising action is detected; if any one of the calculated first differences res1, res2, res3, res4 and res5 is greater than the first threshold, it is determined that the wrist-raising action is not detected.

[0155] Optionally, if the first difference of the second monitoring data at multiple consecutive moments in the second monitoring data is less than or equal to the first threshold, it is determined that the wrist raising action is detected. For example, the second monitoring data includes { whether 1, whether 2, whether 3, whether 4, whether 5, whether 6}; Calculate separately whether 1 and whether 2, the first difference res1 of the total acceleration, whether 2 and whether 3, the first difference res2 of the total acceleration, whether 3 and whether 4, the first difference res3 of the total acceleration, whether 4 and whether 5, and whether 5 and whether 6; if the calculated first differences res1, res2 and res3 are all less than or equal to the first threshold, or the first differences res2, res3 and res4 are all less than or equal to the first threshold, or the first differences res3, res4 and res5 are all less than or equal to the first threshold, it is determined that the wrist raising action is detected; otherwise, it is determined that the wrist raising action is not detected.

[0156] In another implementation, when the acceleration difference includes a second difference, the preset threshold includes the second threshold, and accordingly, the second detection method includes: calculating the second difference based on the combined acceleration of the second monitoring data; if the second difference is less than or equal to the second threshold, the second result indicates that the wrist raising action is detected; if the second difference is greater than the second threshold, the second result indicates that the wrist raising action is not detected.

[0157] In another implementation, when the acceleration difference includes a first difference and a second difference, the preset threshold includes the first threshold and the second threshold, and accordingly, the second detection method includes: calculating the first difference based on the combined acceleration of the second monitoring data; calculating the second difference based on the combined acceleration of the second monitoring data; if the first difference is less than or equal to the first threshold, and the second difference is less than or equal to the second threshold, then the second result indicates that a wrist raising action is detected; if the first difference is greater than the first threshold and / or the second difference is greater than the second threshold, then the second result indicates that no wrist raising action is detected.

[0158] In this implementation, the acceleration difference between the monitoring data and the difference between the monitoring data and the gravity acceleration are considered at the same time, which is equivalent to considering both the acceleration change of the smart wearable device itself and the acceleration change of the smart wearable device relative to the environment. This method can effectively improve the detection accuracy.

[0159] It should be noted that the acceleration difference can also be taken as the average value and / or standard deviation of the second monitoring data. ,and , then the second result indicates that a wrist-raising action is detected; wherein, express The standard deviation of the total acceleration of the second monitoring data corresponding to the time (such as the acceleration data collected from time t1 to time t2), express The average value of the combined acceleration of the second monitoring data corresponding to the time, and The specific implementation method is the same as the implementation method of the above-mentioned combined acceleration as the acceleration difference, which will not be repeated here. The embodiment of the present application does not limit the calculation method of the acceleration difference.

[0160] Since the acceleration fluctuations of the human body are different when the human body is in motion and when the human body is stationary, in order to improve the detection accuracy, a preset threshold value of the second detection may be set according to the motion state of the human body.

[0161] In one embodiment, the method of setting the preset threshold may include: If the user is in motion, the preset threshold is set to a first preset value; If the user is in a non-exercise state, the preset threshold is set to a second preset value; wherein the first preset value is greater than the second preset value.

[0162] In the above embodiment, it is equivalent to appropriately relaxing the data range in the judgment condition when the user is in motion. Since the combined acceleration changes significantly when the human body is in motion, and the combined acceleration is not close to the gravity acceleration, appropriately relaxing the data range in the judgment condition in this case can effectively reduce the probability of misjudgment and help improve detection accuracy.

[0163] In one implementation, the motion state recognition method may be performed before the second detection. The motion state recognition method may include: Calculate the change value of acceleration according to the third monitoring data; if the change value is greater than the third threshold thresh 5, it is determined that the user is in motion; if the change value is less than or equal to the third threshold thresh 5, it is determined that the user is in a non-exercise state. The sampling frequency of the third monitoring data is the same as the sampling frequency of the second monitoring data, and the third monitoring data is the monitoring data acquired within a preset time window before the first monitoring data.

[0164] For example, the acceleration data collected by the accelerometer in time series is { whether 1, whether 2, whether 3, whether 4, whether 5, whether 6, whether 7...}, where the acquisition at time t1 is whether 2. Acquired at time t2 whether7. According to the acceleration data at time t1 whether 2 (First monitoring data) Detect the user's motion state corresponding to time t1; based on the acceleration data at time t1 whether 2 (first monitoring data) performs a first detection to obtain a first result; if the first result indicates that a wrist-raising action is detected, a preset threshold is set according to the user's motion state corresponding to time t1, and a second monitoring data { whether 2, whether 3, whether 4, whether 5, whether 6, whether 7} Perform a second test.

[0165] It can be understood that the recognition of the motion state is equivalent to being performed based on the original data before downsampling processing, the first detection is performed based on the data after downsampling processing, and the second detection is performed based on the original data before downsampling processing.

[0166] In one implementation, the formula Calculate the change value; where, represents the change value corresponding to the third monitoring data, represents the standard deviation of the combined acceleration of the third monitoring data, represents the average value of the combined acceleration of the third monitoring data, are preset constants.

[0167] Optionally, the preset time window can be set according to the storage capacity of the buffer 1. For example, the monitoring data within the preset time window is the data stored in the buffer 1. Accordingly, represents the standard deviation of the total acceleration of the data stored in buffer 1, Indicates the average value of the combined acceleration of the data stored in buffer 1.

[0168] It is understandable that the user's motion state can be determined based on a single motion state recognition result, or based on multiple motion state recognition results within a period of time. For example, if multiple recognition results within a period of time all indicate that the user is in motion, then the user is determined to be in motion; if only one or a few recognition results within a period of time indicate that the user is in motion, then the user is determined to be in a non-motion state.

[0169] Optionally, in order to reduce the probability of misidentification, the limit on the z-axis acceleration can be increased. The identification method of the motion state can include: Calculate the change value of the combined acceleration according to the third monitoring data; if the change value is greater than the third threshold and the acceleration of the z-axis at the current moment is greater than the fourth threshold thresh6, it is determined that the user is in motion; if the change value is less than or equal to the third threshold, and / or the acceleration of the z-axis at the current moment is less than the fourth threshold thresh 6, it is determined that the user is in a non-exercise state.

[0170] In the above method, by limiting the z-axis acceleration, it is equivalent to using the smart wearable device being in a horizontal or nearly horizontal state as a judgment condition, which can reduce the situation of misidentification and help improve the detection accuracy.

[0171] In the embodiment of the present application, the judgment threshold of the second detection is set according to the user's motion state, so that the judgment condition of the second detection can adapt to the two different states of the user's motion and non-motion, effectively improving the detection accuracy of the user's wrist-raising action in different states. In addition, the motion state recognition is performed based on the original data before downsampling, which effectively reduces the delay of the second detection.

[0172] S503: If the second result indicates that a wrist raising action is detected, control the smart wearable device to light up the screen.

[0173] It is understandable that if the second result indicates that no wrist raising action is detected, the screen of the smart wearable device remains off.

[0174] In the embodiment of the present application, the second detection is performed on the basis of the first detection, which is equivalent to further verifying the correctness of the first result, which can effectively reduce the probability of misjudgment and effectively improve the detection accuracy. In addition, only when the first result indicates that a wrist-raising action is detected, the second detection is performed according to the second monitoring data; since the sampling frequency of the first monitoring data is lower than the sampling frequency of the second monitoring data, it is equivalent to using low-frequency sampling data for the first detection and high-frequency sampling data for the second detection. When the first result does not detect a wrist-raising action, there is no need to perform the second detection. In this way, the memory usage and data processing volume of the data in the wrist-raising detection process can be effectively reduced, thereby helping to reduce the impact of wrist-raising detection on the power consumption of smart wearable devices.

[0175] For example, see Figure 7 , is a schematic diagram of the overall process of the wrist-raising detection method provided in the embodiment of the present application. As an example and not a limitation, Figure 7 As shown, the process of the wrist-raising detection method includes the following steps: S701, initialization.

[0176] In the embodiment of the present application, the initialization process may include clearing the cache, obtaining a preset threshold, obtaining a trained decision model, etc.

[0177] S702, obtaining the latest acceleration data.

[0178] As described in S501 , the module executing the wrist-raising detection method may acquire acceleration data from the acceleration sensor 180E of the sensor module 180 in real time.

[0179] S703, motion state identification.

[0180] The motion state is identified according to the latest acquired acceleration data. The implementation of step S703 can refer to the motion state identification method described in the embodiment of step S502, which will not be described in detail here.

[0181] Optionally, after the motion state is identified, the second flag bit may be set. For example, if it is identified that the user is in motion, the second flag bit is set to 1; if it is identified that the user is not in motion, the second flag bit is set to 0.

[0182] S704, determining whether a wrist raising action was detected last time.

[0183] If no wrist raising action was detected last time, execute S705; if a wrist raising action was detected last time, execute S710.

[0184] For example, it can be determined based on the first flag bit. Specifically, if the first flag bit is 1, it means that the wrist raising action was detected last time; if the first flag bit is 0, it means that the wrist raising action was not detected last time.

[0185] It is understandable that before executing S704, the acceleration data needs to be downsampled. In one implementation, if the interval between the latest acquired acceleration data and the acceleration data used for the last first detection reaches a preset interval; if the preset interval is reached, S704 is executed, and subsequent data preprocessing, feature extraction and first detection are performed on the latest acquired acceleration data; if the preset interval is not reached, the next set of acceleration data is acquired.

[0186] The preset duration can be determined according to the downsampling ratio. For example, if the downsampling ratio is n=5 and the sampling frequency of the accelerometer is 100 Hz, the preset duration is (1 / 100)×5=0.05s, which is equivalent to performing the first detection once for every 5 sets of acceleration data.

[0187] For example, the acceleration data collected by the accelerometer are in chronological order as follows: whether 1, whether 2, whether 3, whether 4, whether 5, whether 6, ...}, n = 5. If the last first detection will whether 1 is the first monitoring data. When the whether2, if the interval is less than the preset time, continue to obtain whether 3. When you get whether 6:00, the interval time reaches the preset time, and S704-S707 are executed. whether 6 performs the first detection as the first monitoring data.

[0188] S705, data preprocessing.

[0189] Data preprocessing may include filtering and calculating speed parameters. The specific implementation method can refer to the description of preprocessing the first monitoring data in the embodiment of S501, which will not be repeated here.

[0190] S706, feature extraction.

[0191] The specific implementation of feature extraction can refer to the description of the feature extraction process of the pre-processed first monitoring data in the S501 embodiment, which will not be repeated here.

[0192] S707, executing a first detection, determining whether a wrist raising action is detected according to the latest acquired acceleration data, and obtaining a first result.

[0193] If the first result indicates that the wrist raising action is not detected, S708 is executed; if the first result indicates that the wrist raising action is detected, S709 is executed.

[0194] In this step, the feature data obtained in S706 is input into the trained decision model to output the first result. The description of the decision model can be found in the embodiment of S501, which will not be repeated here.

[0195] S708, set the first flag bit to 0 and keep the screen off.

[0196] S709, set the first flag bit to 1 and keep the screen off.

[0197] The first flag bit is used to indicate the first result. If the first flag bit is 0, it indicates that the wrist raising action is not detected; if the first flag bit is 1, it indicates that the wrist raising action is detected.

[0198] S710, performing a second detection to determine whether the wrist-raising action detected last time is a misjudgment, and obtaining a second result.

[0199] If the second result indicates that the wrist raising motion is not detected, S708 is executed; if the second result indicates that the wrist raising motion is detected, S711 is executed.

[0200] In this step, the corresponding preset threshold is first obtained according to the second flag bit, and then the second detection is performed according to the preset threshold. The implementation of the second detection can refer to the description in the embodiment of S502, which will not be repeated here.

[0201] S711, control the screen of smart wearable devices.

[0202] For example, an application executing the wrist-raising detection method may send instructions to a display driver of a kernel layer through an application framework layer and a system layer to wake up the screen of a smart wearable device.

[0203] S712, determining whether the wrist-raising detection method is completed.

[0204] If not finished, continue to execute S702, that is, obtain the next set of acceleration data.

[0205] It is understandable that when the wrist raising / turning wrist detection function is turned on, the wrist raising detection method is not ended; when the wrist raising / turning wrist detection function is turned off, the wrist raising detection method is ended.

[0206] In the embodiment of the present application, if a wrist-raising action is detected at a certain moment, an anti-misjudgment detection is performed at the next moment, which can effectively intercept the false touch action, reduce the probability of misjudgment, and effectively improve the detection accuracy. Secondly, using monitoring data with a higher sampling frequency for anti-misjudgment detection can effectively reduce the detection delay of anti-misjudgment; thirdly, using the downsampled data for preliminary detection of wrist-raising actions can effectively reduce memory consumption and calculation amount, which helps to reduce the power consumption of smart wearable devices; in addition, using the decision model to preliminarily detect wrist-raising actions, multiple rules can be set to adapt to different application scenarios, effectively improving the application scope of the wrist-raising detection method.

[0207] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0208] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed on an electronic device, the steps in the above-mentioned method embodiments can be implemented.

[0209] The embodiment of the present application also provides a computer program product. When the computer program product is run on an electronic device or a wireless router, the electronic device can implement the steps in the above-mentioned various method embodiments.

[0210] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the first device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0211] The embodiment of the present application further provides a chip, the chip includes a processor, the processor is coupled to a memory, and the processor calls a computer program stored in the memory to implement the steps of any method embodiment of the present application. The chip can be a single chip or a chip module composed of multiple chips.

[0212] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0213] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0214] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A wrist-raising detection method, characterized in that: Applied to a smart wearable device, the method comprises: Performing a first detection on the wrist raising action according to the first monitoring data of the smart wearable device to obtain a first result; If the first result indicates that a wrist-raising action is detected, a second detection is performed according to the second monitoring data of the smart wearable device to obtain a second result; wherein the sampling frequency of the first monitoring data is lower than the sampling frequency of the second monitoring data; If the second result indicates that a wrist raising action is detected, the smart wearable device is controlled to light up the screen.

2. The method according to claim 1, characterized in that The first detection of the wrist raising action according to the first monitoring data of the smart wearable device to obtain a first result includes: Performing filtering processing on the first monitoring data to obtain filtered first monitoring data; A first detection is performed on the wrist raising action according to the first filtered monitoring data to obtain a first result.

3. The method according to claim 2, characterized in that The first detection of the wrist raising action according to the first filtered monitoring data to obtain a first result includes: Calculating a speed parameter according to the first filtered monitoring data; A first detection is performed on the wrist raising action according to the speed parameter to obtain a first result.

4. The method according to claim 3, characterized in that The first detection of the wrist raising action according to the speed parameter to obtain a first result includes: Perform feature extraction processing according to the speed parameter to obtain feature data; A first detection is performed on the wrist raising action according to the characteristic data to obtain a first result.

5. The method according to claim 4, characterized in that The first detection of the wrist raising action according to the characteristic data to obtain a first result includes: Inputting the feature data into the trained decision model and outputting the first result; The decision model includes a plurality of judgment rules, and each of the judgment rules includes a relationship between input data and a threshold.

6. The method according to claim 1, characterized in that The performing a second detection according to the second monitoring data of the smart wearable device to obtain a second result includes: Calculating an acceleration difference according to the second monitoring data; If the acceleration difference is less than or equal to a preset threshold, the second result indicates that a wrist raising action is detected; If the acceleration difference is greater than a preset threshold, the second result indicates that no wrist raising action is detected.

7. The method according to claim 6, characterized in that The acceleration difference includes a first difference and a second difference; the preset threshold includes a first threshold and a second threshold; wherein the first difference is the acceleration difference between the second monitoring data at different sampling times; the second difference is the difference between the resultant acceleration corresponding to the second monitoring data and the gravity acceleration; The second detection step comprises: If the first difference is less than or equal to the first threshold, and the second difference is less than or equal to the second threshold, the second result indicates that a wrist raising action is detected; If the first difference is greater than the first threshold, and / or the second difference is greater than the second threshold, the second result indicates that no wrist raising action is detected.

8. The method according to claim 6, characterized in that The method further comprises: If the user is in motion, the preset threshold is set to a first preset value; If the user is in a non-exercise state, the preset threshold is set to a second preset value; wherein the first preset value is greater than the second preset value.

9. The method according to claim 8, characterized in that The method further comprises: Calculate the change value of acceleration according to the third monitoring data; If the change value is greater than a third threshold, it is determined that the user is in a motion state; If the change value is less than or equal to a third threshold, it is determined that the user is in a non-motion state; wherein, the sampling frequency of the third monitoring data is the same as the sampling frequency of the second monitoring data, and the third monitoring data is the monitoring data acquired within a preset time window before the first monitoring data.

10. The method according to claim 1, characterized in that The method further comprises: If the second result indicates that no wrist raising action is detected, the smart wearable device is controlled to keep the screen off.

11. The method according to claim 1, characterized in that: The method further comprises: If the first result indicates that no wrist raising action is detected, the smart wearable device is controlled to keep the screen off.

12. The method according to any one of claims 1 to 11, characterized in that: The first monitoring data and the second monitoring data are three-axis accelerations.

13. The method according to any one of claims 1 to 11, characterized in that The second monitoring data is monitoring data acquired after the first monitoring data.

14. A smart wearable device, characterized in that: include: one or more processors; one or more memories; The memory stores a computer program, and when the computer program is executed by the processor, the smart wearable device implements the method according to any one of claims 1 to 13.

15. A chip system, characterized in that: The chip system includes a processor coupled to a memory, and the processor is used to run a computer program stored in the memory to implement the method according to any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the method according to any one of claims 1 to 13 is implemented.

17. A computer program product, characterized in that The computer program product comprises a computer program code, and when the computer program code is executed on an electronic device, the electronic device is enabled to implement the method according to any one of claims 1 to 13.

Images