Wearable electronic device for fall detection, operating method thereof, and storage medium

Abstract

A wearable electronic device according to an embodiment disclosed herein can identify, through a sensor, that a first interrupt (INT) has been generated, the first INT being generated at a first time point at which an acceleration sensor signal acquired by the sensor has a magnitude equal to or greater than a first threshold, discern, through the sensor, whether a second INT is generated within a first interval after the first time point, acquire first information through the sensor on the basis that the generation of the second INT has been discerned, the second INT being generated at a second time point at which the acceleration sensor signal has a magnitude less than the first threshold, and determine, on the basis of the first information, whether a first time section between the first time point and the second time point is a valid impact section associated with a fall.

Description

Wearable electronic device for fall detection, method of operation thereof, and storage medium

[0001] The present disclosure relates to a wearable electronic device for fall detection, an operating method thereof, and a storage medium.

[0002] A fall can occur when a user unintentionally falls and sustains injury. Falls are common among the elderly, children, or those physically vulnerable, and can have life-threatening consequences beyond the simple act of falling.

[0003] Wearable electronic devices, such as smartwatches, may include fall detection capabilities. These fall detection capabilities may include sensors that monitor impact events and detect falls based on the monitoring results.

[0004] Wearable electronic devices can detect a fall, triggering a notification or sending a message to emergency contacts, enabling rapid response to ensure the user's safety. Through wearable electronic devices, users can receive prompt assistance in the event of a fall, preventing serious injuries.

[0005] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0006] One embodiment of the present disclosure may provide a wearable electronic device for fall detection, an operating method thereof, and a storage medium.

[0007] One embodiment of the present disclosure can provide a wearable electronic device that accurately detects the time of occurrence of an impact due to a fall, an operating method thereof, and a storage medium.

[0008] One embodiment of the present disclosure may provide a wearable electronic device, an operating method thereof, and a storage medium for preventing a fall from being falsely detected by a noisy peak signal or a transient shock.

[0009] A wearable electronic device according to one embodiment of the present disclosure may include a sensor (210), a memory (220), and at least one processor (230) including a processing circuit. The memory (220) may store instructions that, when individually or collectively executed by the at least one processor (230), cause the wearable electronic device (201) to perform at least one operation. The at least one operation may include an operation of identifying that a first interrupt (INT) (710) has been generated through the sensor (210). The first INT (710) may be generated at a first point in time when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702). The at least one operation may include an operation of identifying whether a second INT (720) has been generated through the sensor (210) within a first time from the first point in time. The at least one operation may obtain first information through the sensor (210) based on the identification that the second INT (720) has occurred. The second INT (720) may be generated at a second time point when the acceleration sensor signal has a magnitude less than the first threshold value (702). The at least one operation may include an operation of determining, based on the first information, whether a first time period (706) between the first time point and the second time point is a valid impact period associated with a fall. The first information includes information indicating whether the first time period (706) is the valid impact period, and the information indicating whether the first time period (706) is the valid impact period may be obtained based on a change pattern of a signal on a first axis extracted from the acceleration sensor signal during a second time period determined based on the first time point.

[0010] A method for detecting a fall by a wearable electronic device (201) according to one embodiment of the present disclosure may include an operation (1502) of identifying that a first interrupt (INT) (710) has occurred through a sensor (210) included in the wearable electronic device (201). The first INT (710) may be generated at a first time point when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702). The method may include an operation (1504) of identifying whether a second INT (720) has occurred through the sensor (210) within a first time point from the first time point. The method may include an operation (1506) of acquiring first information through the sensor (210) based on the identification that the second INT (720) has occurred. The second INT (720) may be generated at a second time point when the acceleration sensor signal has a magnitude less than the first threshold value (702). The method may include an operation (1508) of determining whether a first time interval (706) between the first time point and the second time point is a valid impact interval associated with a fall based on the first information. The first information includes information indicating whether the first time interval (706) is the valid impact interval, and the information indicating whether the first time interval (706) is the valid impact interval may be obtained based on a change pattern of a signal on a first axis extracted from the acceleration sensor signal during a second time interval determined based on the first time point.

[0011] A storage medium storing at least one computer-readable instruction according to one embodiment of the present disclosure may cause the wearable electronic device (201) to perform at least one operation when the at least one instruction is executed by at least a part of at least one processor (230) of the wearable electronic device (201). The at least one operation may include an operation (1502) of identifying that a first interrupt (INT) (710) has been generated through a sensor (210) included in the wearable electronic device (201). The first INT (710) may be generated at a first point in time when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702). The at least one operation may include an operation (1504) of identifying whether a second INT (720) has been generated through the sensor (210) within a first time from the first point in time. The at least one operation may include an operation (1506) of obtaining first information via the sensor (210) based on the identification that the second INT (720) has occurred. The second INT (720) may be generated at a second time point when the acceleration sensor signal has a magnitude less than the first threshold value (702). The at least one operation may include an operation (1508) of determining, based on the first information, whether a first time interval (706) between the first time point and the second time point is a valid impact period associated with a fall. The first information includes information indicating whether the first time interval (706) is the valid impact period, and the information indicating whether the first time interval (706) is the valid impact period may be obtained based on a change pattern of a signal on a first axis extracted from the acceleration sensor signal during a second time interval determined based on the first time point.

[0012] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0013] FIG. 2 is a block diagram of a wearable electronic device according to one embodiment.

[0014] FIG. 3 is an example diagram of a wearable electronic device according to one embodiment.

[0015] FIG. 4 is a schematic diagram illustrating the operation of a sensor and an MCU of a wearable electronic device according to one embodiment.

[0016] FIG. 5 is a flowchart illustrating the operation of a sensor and an MCU in a wearable electronic device according to one embodiment.

[0017] FIG. 6A is a flowchart illustrating a generation operation of a first INT or a second INT performed by a sensor of a wearable electronic device according to one embodiment.

[0018] FIG. 6b is a flowchart illustrating a generation operation of a third INT or a fourth INT performed by a sensor of a wearable electronic device according to one embodiment.

[0019] FIG. 7 is a graph showing acceleration sensor signals associated with first INT to third INT generated in a wearable electronic device according to one embodiment.

[0020] FIG. 8 is a graph showing acceleration sensor signals associated with a first INT and a fourth INT generated in a wearable electronic device according to one embodiment.

[0021] FIG. 9 is a graph showing an acceleration sensor signal having a first pattern associated with a plurality of impact occurrence sections according to one embodiment.

[0022] FIG. 10 is a graph showing an acceleration sensor signal having a second pattern associated with a plurality of impact occurrence sections according to one embodiment.

[0023] FIG. 11 is a flowchart illustrating an operation of a wearable electronic device according to one embodiment to determine an effective impact zone due to a fall.

[0024] FIG. 12 is a graph showing an acceleration sensor signal and a U-axis signal of a first pattern for explaining an operation of identifying an effective impact section due to a fall in a wearable electronic device according to one embodiment.

[0025] FIG. 13 is a graph showing an acceleration sensor signal and a U-axis signal of a second pattern for explaining an operation of identifying an effective impact section due to a fall in a wearable electronic device according to one embodiment.

[0026] FIG. 14 is an exemplary diagram of a plurality of electronic devices performing a fall detection operation according to one embodiment.

[0027] FIG. 15 is a flowchart illustrating the operation of a wearable electronic device according to one embodiment.

[0028] FIG. 16 is a flowchart illustrating an operation of a wearable electronic device according to one embodiment to determine a point of impact of a fall.

[0029] Fig. 17 is a flowchart illustrating an operation of a wearable electronic device according to one embodiment to determine whether a fall has occurred.

[0030] The accompanying drawings are referenced in the following description, and specific examples of implementations are illustrated within the drawings. Furthermore, other examples may be utilized and structural changes may be made without departing from the scope of the various examples.

[0031] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0032] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0033] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0034] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or calculations. According to one embodiment, as at least a part of the data processing or calculations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or a secondary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor)) that can operate independently or together therewith. For example, if the electronic device (101) includes a main processor (121) and a secondary processor (123), the secondary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a specified function. The secondary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0035] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, in the electronic device (101) itself where artificial intelligence is performed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0036] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0037] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0038] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0039] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0040] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. In one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0041] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0042] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0043] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0044] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0045] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0046] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0047] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least a part of a power management integrated circuit (PMIC).

[0048] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0049] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0050] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0051] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the selected at least one antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0052] According to various embodiments, the antenna module (197) may generate a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band.

[0053] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0054] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0055] FIG. 2 is a block diagram of a wearable electronic device according to one embodiment.

[0056] Referring to FIG. 2, the wearable electronic device (201) may include a sensor (210), a memory (220), or a processor (230). According to one embodiment, the wearable electronic device (201) may include additional components (e.g., a display and / or a speaker) in addition to the illustrated components, or may omit at least one of the illustrated components.

[0057] According to one embodiment, the configuration of the wearable electronic device (201) may be partially or entirely identical to the configuration of the electronic device (101) of FIG. 1.

[0058] According to one embodiment, the sensor (210), the memory (220), or the processor (230) may be implemented identically or similarly to the sensor module (176), the memory (130), or the processor (120) of FIG. 1, respectively.

[0059] The sensor (210) can detect the movement or exercise status of the wearable electronic device (201) and output sensor data (or sensor information) based on the detection results. According to one embodiment, the sensor (210) may include an inertial sensor, an acceleration sensor, and / or a gyro sensor. The sensor data output from the sensor (210) may include acceleration sensor data and / or angular velocity sensor data.

[0060] An acceleration sensor can measure the acceleration of a wearable electronic device (201) and output acceleration sensor data indicating the measured acceleration. The acceleration sensor data can include, for example, data based on acceleration measured in the X-axis, Y-axis, or Z-axis of a body frame.

[0061] The gyro sensor can measure the angular velocity of the wearable electronic device (201) and output angular velocity sensor data indicating the measured angular velocity. The angular velocity is associated with the rotational direction and / or rotational speed of the wearable electronic device (201), and can be used to detect whether the wearable electronic device (201) is moving and / or the direction of movement. The angular velocity sensor data can include, for example, data based on the angular velocity measured in the X-axis, Y-axis, or Z-axis of the body coordinate system.

[0062] According to one embodiment, the sensor (210) may include a memory (212). The memory (212) may store various information or data used by the sensor (210). For example, the memory (212) may store samples of sensor data output from the sensor (210) based on a set output data rate (ODR), at least one threshold value or time information used for impact or fall detection, or interrupt (INT) occurrence information (e.g., information on an INT occurrence condition or an INT occurrence time). Samples of sensor data may indicate a physical state that changes or is maintained over time. For example, samples of acceleration sensor data included in the sensor data may indicate an acceleration value that changes or is maintained over time.

[0063] The memory (220) can store various data used by at least one component (e.g., sensor (210) or processor (230)) of the wearable electronic device (201). For example, the memory (220) can store at least one program for processing and controlling the processor (230), and can store input and / or output data. The memory (220) can store at least one artificial intelligence (AI) model. The at least one AI model can include, for example, a fall classifier (hereinafter referred to as a “fall classifier”). The fall classifier can be used to analyze sensor data based on machine learning or deep learning technology and determine whether or not a fall has occurred based on the analysis result.

[0064] The processor (230) can control the overall operation of the wearable electronic device (201). The processor (230) can control at least one other component (e.g., a sensor (210) and / or a memory (220)) of the wearable electronic device (201) or perform calculations or data processing. The processor (230) can include a processing circuit and execute instructions of a program stored in the memory (220).

[0065] According to one embodiment, the processor (230) may include an application processor (AP) (232) and / or a microcontroller unit (MCU) (234). The AP (232) may determine whether a fall has occurred through a fall classifier based on sensor data at the time of impact occurrence. The MCU (234) may process sensor data output from the sensor (210) or perform an operation based on an INT event transmitted from the sensor (210). The MCU (234) may be driven in an Always-on mode and may operate at low power to reduce battery consumption.

[0066] According to one embodiment, the processor (230) may be an integrated processor that includes the functions of an AP (232) and an MCU (234).

[0067] According to one embodiment, the processor (230) may or may not further include at least one of a central processing unit (CPU), a neural processing unit (NPU), a graphics processing unit (GPU), a micro processing unit (MPU), a communication processor (CP), a system on chip (SoC), or an integrated circuit (IC) sensor hub, a supplementary processor, a communication processor, an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA), and may have multiple cores.

[0068] According to one embodiment, a wearable electronic device includes a sensor (210), a memory (220), and at least one processor (230) including a processing circuit, wherein the memory (220) is configured to, when individually or collectively executed by the at least one processor (230), cause the wearable electronic device (201) to: identify that a first interrupt (INT) (710) has occurred through the sensor (210), wherein the first INT (710) is generated at a first time point when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702), identify whether a second INT (720) has occurred through the sensor (210) within a first time point from the first time point, and acquire first information through the sensor (210) based on the identification that the second INT (720) has occurred, and The second INT (720) stores commands that are caused to determine whether a first time interval (706) between the first time interval and the second time interval is a valid impact interval associated with a fall based on the first information, wherein the first information includes information indicating whether the first time interval (706) is the valid impact interval, and the information indicating whether the first time interval (706) is the valid impact interval can be obtained based on a change pattern of a signal on a first axis extracted from the acceleration sensor signal during a second time interval determined based on the first time interval.

[0069] According to one embodiment, the change pattern of the signal on the first axis can be identified based on at least one of a rate of change (gradient) of the signal on the first axis or a difference between a maximum value and a minimum value (peak to peak) of the signal on the first axis.

[0070] According to one embodiment, the first information may include information indicating that the first time period (706) is the valid impact period based on the rate of change of the signal on the first axis being less than or equal to a second threshold value and the difference between the maximum and minimum values ​​of the signal on the first axis being greater than or equal to a third threshold value.

[0071] According to one embodiment, the memory (220) may store instructions that, when individually or collectively executed by the at least one processor (230), cause the wearable electronic device (201) to: identify information about a peak value of the acceleration sensor signal of the valid impact period, or a duration of the valid impact period, based on the first time period (706) being determined as the valid impact period; determine that the valid impact period is a period including the impact caused by the fall, based on the peak value of the acceleration sensor signal being equal to or greater than a fourth threshold value and the duration being equal to or less than a fifth threshold value; and determine that the first time point is a time point at which the impact caused by the fall occurs, based on the determination that the valid impact period is a period including the impact caused by the fall.

[0072] According to one embodiment, samples of the acceleration sensor signal based on a set output data rate (ODR) are stored in a memory (212) included in the sensor (210), and the first INT (710) can be generated based on a set number of samples among the samples of the acceleration sensor signal having a size greater than or equal to the first threshold value (702) in succession.

[0073] According to one embodiment, the signal on the first axis includes a signal on the U-axis of the ENU (east-north-up) coordinate system obtained from the acceleration sensor signal, and the first information may include information indicating that the first time period (706) is the valid impact period based on the fact that the signal on the first axis has a pattern of changing from a positive direction to a negative direction during the second time period.

[0074] According to one embodiment, the memory (220) may store instructions that, when individually or collectively executed by the at least one processor (230), cause the wearable electronic device (201) to: identify, based on a second time (708) elapsed from the first time point or the second time point, that a third INT (730) has been generated through the sensor (210); and determine, based on the generation of the third INT (730), whether the first time period (706) is the valid impact period based on the first information.

[0075] According to one embodiment, the memory (220) stores instructions that, when individually or collectively executed by the at least one processor (230), cause the wearable electronic device (201) to: identify that the first INT and the second INT have been additionally generated before a second time (708) has elapsed from the first time point or the second time point, identify that the third INT has been generated through the sensor (210) based on the second time having elapsed from a third time point at which the first INT has been additionally generated or a fourth time point at which the second INT has been additionally generated, and determine, based on the generation of the third INT, whether a third time interval between the third time point and the fourth time point is the valid impact interval, based on second information acquired from the sensor (210), whether the third time interval between the third time point and the fourth time point is the valid impact interval, wherein the second information includes information indicating whether the third time interval is the valid impact interval, and the information indicating whether the third time interval is the valid impact interval comprises: It can be obtained based on the change pattern of the signal on the first axis extracted from the acceleration sensor signal during the fourth time period determined based on the third time point.

[0076] According to one embodiment, the memory (220) may store instructions that, when individually or collectively executed by the at least one processor (230), cause the wearable electronic device (201) to: identify that a fourth INT (840) has occurred through the sensor (210) based on the identification that the second INT (720) has not occurred, and identify that an error condition associated with the sensor (210) has occurred based on the identification that the fourth INT (840) has occurred.

[0077] According to one embodiment, the memory (220) may store instructions that, when individually or collectively executed by the at least one processor (230), cause the wearable electronic device (201) to determine the first threshold value (702) based on at least one of: the activity state of the user identified through the sensor (210), the weight, gender, or age of the user.

[0078] FIG. 3 is an example diagram of a wearable electronic device according to one embodiment.

[0079] Referring to FIG. 3, the wearable electronic device (201) may be any one of various types of electronic devices. For example, the wearable electronic device (201) may be any one of a smart watch (302), a smart ring (304), wireless earphones or earbuds (306), a head mounted display (HMD) (308), or smart glasses (310), but is not limited thereto. The wearable electronic device (201) may also be another type of electronic device that can be worn on a user's body (e.g., a smart band or a healthcare device).

[0080] According to one embodiment, the wearable electronic device (201) can detect an impact occurrence situation based on an acceleration sensor signal acquired by the sensor (210). The acceleration sensor signal may be a signal based on samples of acceleration sensor data output from the sensor (210) based on a set ODR. The impact occurrence situation may be monitored to detect whether an impact due to a fall has occurred based on the acceleration sensor signal. According to one embodiment, the magnitude of the acceleration sensor signal (e.g., acceleration value) may correspond to an amount of impact or an impact level.

[0081] According to one embodiment, the sensor (210) may generate an acceleration INT when an impact occurrence situation is detected through monitoring. For example, the sensor (210) may generate an acceleration INT when an impact amount greater than a threshold is detected. The sensor (210) may transmit an impact detection event to the MCU (234) based on the generation of the acceleration INT. The MCU (234) may receive the impact detection event from the sensor (210) and identify that an impact has occurred based on the received impact detection event.

[0082] According to one embodiment, the sensor (210) may generate an acceleration INT when the amount of impact is greater than or equal to a threshold value. For example, the sensor (210) may generate an acceleration INT when the amount of impact due to a noisy peak signal or a temporary impact (e.g., an impact caused by the wearable electronic device (201) slightly bumping into a wall or table) is greater than or equal to the threshold value. The MCU (234) may predict the time of occurrence of the acceleration INT as the time of occurrence of the fall impact. However, since the time of occurrence of the acceleration INT is not caused by an actual fall, it may cause a false recognition of a fall.

[0083] In one embodiment, since acceleration INT can be generated when the impact amount is greater than or equal to a threshold regardless of whether it is a collision or a fall, if a fall occurs after a collision, acceleration INT can be generated at the collision time, not at the fall time. For example, if the impact amount at the collision time is 40G and the impact amount at the fall time is 100G, the impact amounts at both the collision time and the fall time can be greater than or equal to the threshold of 20G. In this case, acceleration INT can be generated preferentially at the collision time, and the collision time at which acceleration INT is generated can be incorrectly detected as the fall time. Based on the incorrect detection of the fall time, sensor data at the collision time, not the fall time, can be input to the fall classifier, which can result in a decrease in the fall recognition rate.

[0084] To prevent the aforementioned decline in fall recognition rates, a fall detection operation based on stepwise acceleration INT can be performed. A detailed description of this is provided below.

[0085] FIG. 4 is a schematic diagram illustrating the operation of a sensor and an MCU of a wearable electronic device according to one embodiment.

[0086] The operations illustrated in FIG. 4 are not limited to the illustrated order and may be performed in various orders. In one embodiment, at least some of the operations illustrated in FIG. 4 may be omitted, or more operations may be performed than those illustrated in FIG. 4.

[0087] Referring to FIG. 4, a sensor (210) of a wearable electronic device (201) may monitor an acceleration sensor signal. According to one embodiment, the acceleration sensor signal may be generated based on acceleration sensor data (or samples of acceleration sensor data) output based on a set ODR. The set ODR is for high sampling of acceleration sensor data, and may be, for example, 400 Hz or higher. The high-sampled acceleration sensor data may be used to more clearly detect an impact occurrence situation.

[0088] In one embodiment, the acceleration sensor signal is monitored from the sensor (210) instead of the MCU (234) where the sensor-based algorithm is driven, thereby reducing battery consumption of the MCU (234) and increasing the operating cycle of the MCU (234).

[0089] In operation 402, the sensor (210) analyzes the amount of impact, the duration of impact, or the movement in the direction perpendicular to the ground based on the monitored acceleration sensor signal, and detects a valid impact zone based on the analysis results. The valid impact zone may be a zone where an impact due to a fall is predicted. In one embodiment, the sensor (210) may transmit information about the valid impact zone to the MCU (234).

[0090] In operation 404, the sensor (210) may generate an acceleration INT based on the amount of impact and transmit an INT event based on the generated acceleration INT to the MCU (234). Operation 404 may be performed simultaneously with operation 402 or may be performed before operation 402.

[0091] According to one embodiment, the generated acceleration INT may include any one of the four INTs shown in [Table 1] below.

[0092] Occurrence Conditions 1st INT The acceleration sensor signal has a magnitude greater than or equal to the impact threshold, or the acceleration sensor signal has a magnitude greater than or equal to the impact threshold for a set period of time. 2nd INT The first INT occurs and the acceleration sensor signal has a magnitude less than or equal to the impact threshold within a first period of time. 3rd INT The second period of time elapses from the time the first INT or the second INT occurs. 4th INT The first INT occurs and the acceleration sensor signal does not have a magnitude less than or equal to the impact threshold within a first period of time, or the first INT occurs and the second INT does not occur within a first period of time.

[0093] Referring to [Table 1], the occurrence conditions of the first INT to the fourth INT may be different. The occurrence conditions of the first INT to the fourth INT may be stored in the memory (212) of the sensor (210). The sensor (210) may generate the first INT to the fourth INT based on the occurrence conditions stored in the memory (212).

[0094] In one embodiment, the first INT through the fourth INT may occur at different times, and at least two of the first INT through the fourth INT may occur in stages (or sequentially). For example, the first INT through the third INT may occur in stages, or the first INT and the fourth INT may occur in stages.

[0095] According to one embodiment, the sensor (210) can generate a first INT based on the acceleration sensor signal having a magnitude greater than or equal to an impact threshold. The sensor (210) can also generate the first INT based on a debounce delay check operation. The debounce delay check operation can include an operation of checking whether the acceleration sensor signal has a magnitude greater than or equal to the impact threshold for a set period of time or longer to prevent a fall from being detected by a noisy peak signal. By generating the first INT based on the acceleration sensor signal having a magnitude greater than or equal to the impact threshold for a set period of time or longer, the sensor (210) can increase the reliability of the first INT generation.

[0096] According to one embodiment, the sensor (210) may generate a second INT based on the first INT occurring and the acceleration sensor signal having a magnitude below the impact threshold within a first time period.

[0097] According to one embodiment, the sensor (210) may generate a third INT based on the second period of time elapsed from the time the first INT or the second INT occurred. The period from the time the first INT or the second INT occurred to the time the second period of time elapsed may be designated as an impact pattern generation period. The impact pattern generation period may be a period in which the sensor (210) monitors whether the first INT and / or the second INT additionally occurs. The sensor (210) may generate a third INT and terminate the session of the impact pattern generation period based on the second period of time elapsed from the time the first INT or the second INT occurred. The second period of time may be different from the first period of time. For example, the second period of time may be longer than the first period of time.

[0098] In one embodiment, the sensor (210) may generate a fourth INT based on the occurrence of a first INT and the acceleration sensor signal not having a magnitude below the impact threshold within a first time period, or the occurrence of a second INT not occurring within a second time period after the occurrence of the first INT. The occurrence of the fourth INT may indicate a state in which an unexpected error has occurred in the sensor (210) and the acceleration INT generation logic is not operating normally.

[0099] According to one embodiment, the MCU (234) may receive an INT event based on the generated INT from the sensor (210) when any one of the first INT to the fourth INT occurs at a specific time based on the occurrence conditions as shown in [Table 1]. For example, the MCU (234) may receive a first INT event from the sensor (210) based on the occurrence of the first INT, receive a second INT event from the sensor (210) based on the occurrence of the second INT, receive a third INT event from the sensor (210) based on the occurrence of the third INT, or receive a fourth INT event from the sensor (210) based on the occurrence of the fourth INT.

[0100] In operation 406, the MCU (234) can determine the time of occurrence of a fall impact based on information about the received INT event or the valid impact period. The MCU (234) can acquire sensor data for a time period based on the identified time of occurrence of the impact and determine whether a fall has occurred through a fall classifier.

[0101] FIG. 5 is a flowchart illustrating the operation of a sensor and an MCU in a wearable electronic device according to one embodiment.

[0102] The operations illustrated in FIG. 5 are not limited to the illustrated order and may be performed in various orders. In one embodiment, at least some of the operations illustrated in FIG. 5 may be omitted, or more operations may be performed than those illustrated in FIG. 5.

[0103] Referring to FIG. 5, according to one embodiment, in operation 502, the sensor (210) may acquire sensor data. The sensor data may be acquired based on a set ODR (e.g., an ODR of 400 Hz or more) and may include acceleration sensor data and / or angular velocity sensor data.

[0104] According to one embodiment, in operation 504, the sensor (210) may extract an acceleration sensor signal from the acquired sensor data. For example, the acceleration sensor signal may correspond to an acceleration norm signal for checking the amount of impact regardless of the posture of the wearable electronic device (201). The acceleration norm signal may be a three-axis norm signal based on acceleration sensor data measured in the X-axis, Y-axis, or Z-axis.

[0105] According to one embodiment, the sensor (210) can generate an acceleration INT based on an acceleration sensor signal. The acceleration value, or the magnitude or level of acceleration indicated by the acceleration sensor signal, can correspond to an amount of impact. The sensor (210) can generate any one of the first INT to the fourth INT as an acceleration INT at a specific point in time. The specific point in time can indicate a point in time when any one of the generation conditions described in [Table 1] is satisfied.

[0106] According to one embodiment, operations 506 to 522 associated with the first INT to the third INT may be performed sequentially, or operations 506 to 510 and 524 to 528 associated with the first INT and the fourth INT may be performed sequentially.

[0107] According to one embodiment, in operation 506, the sensor (210) may generate a first INT when a condition for generating the first INT is satisfied. The condition for generating the first INT may include a condition in which the acceleration sensor signal has a magnitude greater than or equal to an impact threshold, or a condition in which the acceleration sensor signal has a magnitude greater than or equal to the impact threshold for a set period of time.

[0108] According to one embodiment, at operation 508, the sensor (210) may transmit a first INT event to the MCU (234) indicating the occurrence of a first INT.

[0109] According to one embodiment, in operation 510, the MCU (234) may identify the occurrence time of the first INT based on the first INT event, and may identify the identified occurrence time of the first INT as the occurrence time of an impact. The MCU (234) may store information about the identified occurrence time of an impact in the memory (220) to determine whether the identified occurrence time of an impact is the occurrence time of an impact due to a fall.

[0110] According to one embodiment, in operation 512, if the occurrence condition of the second INT is satisfied, the sensor (210) can generate a second INT and determine whether the shock occurrence period between the occurrence time of the first INT and the occurrence time of the second INT is a valid shock period. The occurrence condition of the second INT can include a condition in which the first INT occurs and the acceleration sensor signal has a magnitude less than the shock threshold within a first time.

[0111] According to one embodiment, the sensor (210) can determine whether an impact occurrence section is a valid impact section based on a movement or pattern in a direction perpendicular to the ground. The valid impact section may be a section in which an impact due to a fall is predicted. In order to identify a movement or pattern in a direction perpendicular to the ground, the sensor (210) can convert an acceleration sensor signal on a body coordinate system corresponding to a time period including a first INT occurrence time period (e.g., a time period from the time point of the first INT occurrence to the time after the first INT occurrence) into a signal on a navigation frame or an east-north-up (ENU) coordinate system.

[0112] According to one embodiment, the sensor (210) can extract a U-axis signal from the converted signal and check whether movement of the wearable electronic device (201) in the direction of the ground has occurred based on the extracted U-axis signal. If the sensor (210) identifies that movement of the wearable electronic device (201) in the direction of the ground has occurred, the sensor (210) can identify the impact generation section as a valid impact section.

[0113] According to one embodiment, in operation 514, the sensor (210) may transmit a second INT event indicating the occurrence of a second INT and valid impact period indication information to the MCU (234). The valid impact period indication information may include information indicating whether an impact occurrence period is a valid impact period. The valid impact period indication information may include information about a peak and a duration of the valid impact period based on whether the impact occurrence period is indicated as a valid impact period. The peak of the valid impact period may indicate a maximum value (or a maximum acceleration value or a maximum impact amount) of the valid impact period, and the duration of the valid impact period may indicate a duration of the valid impact period.

[0114] According to one embodiment, in operation 516, the MCU (234) can identify that a second INT has occurred based on the second INT event, and can identify the peak and duration of the valid impact period based on the valid impact period indication information.

[0115] According to one embodiment, in operation 518, the sensor (210) may generate a third INT and terminate the session of the impact pattern generation period when the occurrence condition of the third INT is satisfied. The occurrence condition of the third INT may include a condition that a second time has elapsed since the time when the first INT or the second INT occurred.

[0116] According to one embodiment, at operation 520, the sensor (210) may transmit a third INT event to the MCU (234) indicating the occurrence of a third INT.

[0117] According to one embodiment, in operation 522, the MCU (234) can identify that a third INT has occurred based on the third INT event and determine whether a fall has occurred and the time of impact of the fall.

[0118] According to one embodiment, the MCU (234) can determine whether the valid impact section was caused by a fall based on peak and duration information of the valid impact section. According to one embodiment, the MCU (234) can determine that the valid impact section was caused by a fall if the peak is greater than or equal to a first threshold value and the duration is less than or equal to a second threshold value. If the MCU (234) determines that the valid impact section was caused by a fall, the MCU (234) can determine the first INT occurrence time, which is the impact occurrence time identified in operation 510, as the fall impact time.

[0119] According to one embodiment, the MCU (234) may acquire sensor data (e.g., acceleration sensor data and / or angular velocity sensor data) for a set time period based on the determined point of impact of the fall. The MCU (234) may extract features and patterns for the acquired sensor data, and transmit information on the extracted features and patterns to the AP (232). The AP (232) may input the information received from the MCU (234) into a fall classifier, and determine whether or not a fall has occurred based on the output result of the fall classifier.

[0120] In one embodiment, the first INT and the second INT may additionally occur before the third INT occurs. In this case, operations 506 to 516 may be repeatedly performed, and the third INT may occur at a point in time when a second amount of time has elapsed since the most recent occurrence of the first or second INT.

[0121] According to one embodiment, after operations 506 to 510 are performed, operation 524 may be performed. In operation 524, the sensor (210) may generate a fourth INT if a condition for generating a fourth INT is satisfied. The condition for generating the fourth INT may include a condition in which a first INT occurs and an acceleration sensor signal does not have a magnitude less than an impact threshold within a first time period, or a condition in which a second INT does not occur within a first time period after the first INT occurs.

[0122] According to one embodiment, at operation 526, the sensor (210) may transmit a fourth INT event to the MCU (234) indicating the occurrence of a fourth INT.

[0123] In one embodiment, at operation 528, the MCU (234) may identify that an error condition associated with the sensor (210) has occurred based on the fourth INT event. In one embodiment, the MCU (234) may ignore the first INT based on identifying that an error condition has occurred.

[0124] Referring to FIGS. 6a and 6b below, the generation operation of acceleration INT is described.

[0125] The operations illustrated in FIGS. 6A and 6B are not limited to the order illustrated and may be performed in various orders. In one embodiment, at least some of the operations illustrated in FIGS. 6A and 6B may be omitted, or more operations may be performed than those illustrated in FIGS. 6A and 6B.

[0126] FIG. 6A is a flowchart illustrating a generation operation of a first INT or a second INT performed by a sensor of a wearable electronic device according to one embodiment.

[0127] Referring to FIG. 6A, according to one embodiment, in operation 602, the sensor (210) may set status, which represents status information, to a set value (e.g., 0).

[0128] According to one embodiment, in operation 604, the sensor (210) may acquire acceleration sensor data based on a set ODR (e.g., 480 Hz).

[0129] According to one embodiment, in operation 606, the sensor (210) can obtain a three-axis norm based on the acquired acceleration sensor data. The three-axis norm may be based on acceleration sensor data measured in the X-axis, Y-axis, or Z-axis of the body coordinate system. Hereinafter, the three-axis norm will be simply referred to as norm. The sensor (210) can obtain a norm for each sample of the acceleration sensor data.

[0130] According to one embodiment, in operation 608, the sensor (210) can determine whether the status is 0 or 2 and the norm of N consecutive samples of acceleration sensor data is greater than or equal to an impact threshold. N can be a natural number greater than or equal to 1, and the N consecutive samples can correspond to a set time used in the occurrence condition (or debounce delay check operation) associated with the first INT of [Table 1].

[0131] In one embodiment, the sensor (210) may generate a first INT based on status being 0 or 2 and a norm of N consecutive samples of acceleration sensor data being greater than or equal to an impact threshold. At operation 610, the sensor (210) may transmit a first INT event to the MCU (234) and set status to 1 based on the generation of the first INT. The sensor (210) may perform operation 610 and then perform operation 604 again.

[0132] According to one embodiment, at operation 608, the sensor (210) may perform operation 612 based on status being 0 or 2 and a norm of N consecutive samples of acceleration sensor data not being greater than an impact threshold.

[0133] According to one embodiment, at operation 612, the sensor (210) may determine whether status is 1 and norm is below the impact threshold. The sensor (210) may perform operation 614 based on status being 1 and norm being below the impact threshold.

[0134] In one embodiment, at operation 614, the sensor (210) may determine whether the previous peak is less than the current peak. Based on the previous peak not being less than the current peak, the sensor (210) may set status to 2 at operation 620 and perform operation 604 again.

[0135] According to one embodiment, the sensor (210) may change the impact occurrence time to the most recent first INT occurrence time at operation 616 based on the previous peak being less than the current peak.

[0136] According to one embodiment, at operation 618, the sensor (210) may transmit a second INT event to the MCU (234) based on the occurrence of a first INT and the occurrence of a second INT within a first time period.

[0137] According to one embodiment, at operation 620, the sensor (210) may set status to 2 and perform operation 604.

[0138] According to one embodiment, at operation 612, the sensor (210) may perform operation 622 of FIG. 6B, indicated by symbol B, based on status being 1 and norm not being less than the impact threshold.

[0139] FIG. 6b is a flowchart illustrating a generation operation of a third INT or a fourth INT performed by a sensor of a wearable electronic device according to one embodiment.

[0140] Referring to FIG. 6B, according to one embodiment, in operation 622, the sensor (210) may determine whether status is 1 and the elapsed time from the occurrence time of the first INT is greater than or equal to a first threshold time. According to one embodiment, the first threshold time may correspond to the first time used in the occurrence condition associated with the fourth INT of [Table 1].

[0141] According to one embodiment, the sensor (210) may generate a fourth INT based on the status being 1 and the elapsed time from the time of occurrence of the first INT being greater than or equal to a first threshold time.

[0142] According to one embodiment, at operation 624, the sensor (210) may transmit a fourth INT event to the MCU (234) based on the occurrence of the fourth INT and set status to 0.

[0143] According to one embodiment, in operation 622, the sensor (210) may perform operation 604 of FIG. 6A again based on the status being 1 and the elapsed time from the time of occurrence of the first INT being not greater than or equal to the first threshold time.

[0144] In one embodiment, operation 626 may be performed subsequent to operation 606 of FIG. 6A, indicated by symbol A. In operation 626, the sensor (210) may determine whether status is 2 and the elapsed time from the occurrence of the first INT is greater than or equal to a second threshold time. In one embodiment, the second threshold time may correspond to the second time used in the occurrence condition associated with the third INT of [Table 1].

[0145] According to one embodiment, the sensor (210) may generate a third INT based on the status being 2 and the elapsed time from the time of occurrence of the first INT being greater than or equal to a second threshold time.

[0146] According to one embodiment, at operation 628, the sensor (210) may transmit a third INT event to the MCU (234) based on the occurrence of the third INT and set status to 0.

[0147] According to one embodiment, the sensor (210) may perform operation 604 of FIG. 6A again based on the status being 2 and the elapsed time from the time of occurrence of the first INT being not greater than or equal to the second threshold time.

[0148] FIG. 7 is a graph showing acceleration sensor signals associated with first INT to third INT generated in a wearable electronic device according to one embodiment.

[0149] Referring to Figure 7, in the graph according to one embodiment, the y-axis is in a set unit (e.g., m / s). 2) can indicate an acceleration value, and the x-axis can indicate a sample number (or sample index) of acceleration sensor data that can be indicated by a natural number greater than or equal to 0. According to one embodiment, the acceleration sensor signal can be generated based on a norm associated with the acceleration value of each consecutive sample of the acceleration sensor data. The norm corresponding to each sample can indicate an acceleration value, an amount of impact, or an impact level.

[0150] In one embodiment, a strong impact may occur when a user wearing a wearable electronic device (201) falls forward and places his / her hands on the ground. At the point when a strong impact is detected in the wearable electronic device (201), the norm is set to an impact threshold (e.g., 200 m / s). 2 )(702) may have a size greater than or equal to the impact threshold (702). The wearable electronic device (201) may generate a first INT (710) when the impact has a size greater than or equal to the impact threshold (702) for a time period exceeding the norm set based on the debounce delay check operation.

[0151] According to one embodiment, the wearable electronic device (201) may generate a second INT (720) when a first INT (710) occurs and the norm has a magnitude less than the impact threshold (702) within a first time period.

[0152] According to one embodiment, the wearable electronic device (201) can determine whether the interval (impact occurrence interval) between the time point of occurrence of the first INT (710) and the time point of occurrence of the second INT (720) is a valid impact interval based on a movement or pattern in a direction perpendicular to the ground during a time point including the time point of occurrence of the first INT (710).

[0153] According to one embodiment, if the impact occurrence section is determined to be a valid impact section, the wearable electronic device (201) can identify information about the peak (704) and duration (706) of the valid impact section. The wearable electronic device (201) can use the peak (704) and duration (706) of the valid impact section to determine whether a fall has occurred or the point in time of the fall impact.

[0154] According to one embodiment, the wearable electronic device (201) may generate a third INT (730) when a third amount of time has elapsed from the time at which the first INT (710) or the second INT (720) occurs.

[0155] According to one embodiment, the period between the occurrence time of the first INT (710) or the second INT (720) and the occurrence time of the third INT (730) may be an impact pattern occurrence period (708). The wearable electronic device (201) may monitor whether an additional impact occurs during the impact pattern occurrence period (708). For example, the wearable electronic device (201) may monitor whether an additional impact occurrence period based on the first INT and the second INT occurs.

[0156] According to one embodiment, if the wearable electronic device (201) identifies that one or more additional shock occurrence periods have occurred during the shock pattern occurrence period (708), the wearable electronic device (201) may change the occurrence time of the third INT (730) based on the occurrence time of the most recently occurred first INT or second INT. For example, the wearable electronic device (201) may change the occurrence time of the third INT (730) to a time point after a second period of time has elapsed from the occurrence time of the most recently occurred first INT or second INT.

[0157] FIG. 8 is a graph showing acceleration sensor signals associated with a first INT and a fourth INT generated in a wearable electronic device according to one embodiment.

[0158] Referring to FIG. 8, in the graph according to one embodiment, the y-axis is in a set unit (e.g., m / s). 2 ) can indicate an acceleration value, and the x-axis can indicate a sample number (or sample index) of acceleration sensor data that can be indicated by a natural number greater than or equal to 0. According to one embodiment, the acceleration sensor signal can be generated based on a norm associated with the acceleration value of each consecutive sample of the acceleration sensor data. The norm corresponding to each sample can indicate an acceleration value, an amount of impact, or an impact level.

[0159] According to one embodiment, the wearable electronic device (201) may generate a fourth INT (840) based on whether the first INT (810) occurs and the norm of the acceleration sensor signal does not have a magnitude less than or equal to the impact threshold (802) within a second time period, or whether the first INT (810) occurs and the second INT does not occur within a first time period (804).

[0160] According to one embodiment, the wearable electronic device (201) may determine that an error condition associated with the sensor (210) has occurred based on the occurrence of the fourth INT (840) and may ignore the first INT (810).

[0161] FIG. 9 is a graph showing an acceleration sensor signal having a first pattern associated with a plurality of impact occurrence sections according to one embodiment.

[0162] Referring to FIG. 9, in a graph according to one embodiment, the y-axis is in a set unit (e.g., m / s). 2) can indicate an acceleration value, and the x-axis can indicate a sample number (or sample index) of acceleration sensor data that can be indicated by a natural number greater than or equal to 0. According to one embodiment, the acceleration sensor signal can be generated based on a norm associated with the acceleration value of each consecutive sample of the acceleration sensor data. The norm corresponding to each sample can indicate an acceleration value, an amount of impact, or an impact level.

[0163] According to one embodiment, a wearable electronic device (201) can identify a plurality of impact occurrence sections based on an acceleration sensor signal having a first pattern. The plurality of impact occurrence sections may be sections generated based on a first INT and a second INT occurring at different times, and may be sections in which the norm of the acceleration sensor signal is greater than or equal to an impact threshold value (902).

[0164] In one embodiment, when a user wearing a wearable electronic device (201) hits a wall head-on and falls backward while moving, the wearable electronic device (201) can identify multiple impact occurrence sections.

[0165] According to one embodiment, the plurality of impact generating sections may include a first impact generating section (910), a second impact generating section (920), or a third impact generating section (930).

[0166] In one embodiment, a first impact generation segment (910) may be generated based on an impact from a user colliding with a wall, a second impact generation segment (920) may be generated when a strong impact occurs due to a fall where the user falls backwards, and a third impact generation segment (930) may be generated based on an additional impact occurring after a fall.

[0167] According to one embodiment, the second shock occurrence period (920) or the third shock occurrence period (930) may be generated during the shock pattern occurrence period. The shock pattern occurrence period may represent a period within a second time from the time at which the first INT or the second INT associated with the first shock occurrence period (910) occurs.

[0168] In one embodiment, when a second impact occurrence period (920) is generated, the impact pattern occurrence period may be updated. For example, the impact pattern occurrence period may be updated to a period within a second time period from the time at which the first INT or the second INT associated with the second impact occurrence period (920) is generated.

[0169] In one embodiment, the third shock occurrence period (930) may be generated within the updated shock pattern occurrence period. Once the third shock occurrence period (930) is generated, the updated shock pattern occurrence period may be further updated. For example, the updated shock pattern occurrence period may be further updated to a period within a second time period from the time at which the first INT or the second INT associated with the third shock occurrence period (930) occurs. When the additionally updated shock pattern occurrence period ends, the third INT may be generated.

[0170] According to one embodiment, the wearable electronic device (201) may determine the second impact generation section (920) having the largest peak among the first impact generation section (910), the second impact generation section (920), or the third impact generation section (930) as the fall impact section based on the occurrence of the third INT. Since the second impact generation section (920) is a section created by an impact due to a fall, the fall can be more clearly indicated through the fall classifier.

[0171] FIG. 10 is a graph showing an acceleration sensor signal having a second pattern associated with a plurality of impact occurrence sections according to one embodiment.

[0172] Referring to Figure 10, in the graph according to one embodiment, the y-axis is in a set unit (e.g., m / s). 2 ) can indicate an acceleration value, and the x-axis can indicate a sample number (or sample index) of acceleration sensor data that can be indicated by a natural number greater than or equal to 0. According to one embodiment, the acceleration sensor signal can be generated based on a norm associated with the acceleration value of each consecutive sample of the acceleration sensor data. The norm corresponding to each sample can indicate an acceleration value, an amount of impact, or an impact level.

[0173] According to one embodiment, the wearable electronic device (201) can identify a plurality of impact occurrence sections based on the acceleration sensor signal of the second pattern. The plurality of impact occurrence sections may be sections generated based on the first INT and the second INT occurring at different times, and may be sections in which the norm of the acceleration sensor signal is greater than or equal to the impact threshold value (1002).

[0174] In one embodiment, when a user wearing a wearable electronic device (201) collides head-on with a wall and falls backward while moving, the wearable electronic device (201) can identify multiple impact occurrence points. Although the situation is substantially the same as described in FIG. 9, the acceleration sensor signal may appear in a second pattern different from the first pattern.

[0175] According to one embodiment, the plurality of impact generation sections may include a first impact generation section (1010), a second impact generation section (1020), or a third impact generation section (1030).

[0176] In one embodiment, a first impact generation segment (1010) may be generated based on a strong impact from a user colliding with a wall, a second impact generation segment (1020) may be generated based on a somewhat weaker impact from a fall where the user falls backwards, and a third impact generation segment (1030) may be generated based on an additional impact occurring after a fall.

[0177] According to one embodiment, the wearable electronic device (201) may determine the first impact generation section (1010) having the largest peak among the first impact generation section (1010), the second impact generation section (1020), or the third impact generation section (1030) as the fall impact section. Since the first impact generation section (1010) is not a section created by an impact due to a fall, an error may occur in determining whether or not a fall has occurred using a fall classifier. Therefore, the following method may be used to detect the second impact generation section (1020), which is the actual point of fall, as the fall impact section, rather than the first impact generation section (1010).

[0178] FIG. 11 is a flowchart illustrating an operation of a wearable electronic device according to one embodiment to determine an effective impact zone due to a fall.

[0179] According to one embodiment, operations 1102 to 1116 may be understood to be performed in a processor (e.g., processor (230) of FIG. 2) of an electronic device (e.g., electronic device (201) of FIG. 2).

[0180] The operations illustrated in FIG. 11 are not limited to the order illustrated and may be performed in various orders. In one embodiment, at least some of the operations illustrated in FIG. 11 may be omitted, or more operations may be performed than those illustrated in FIG. 11.

[0181] Referring to FIG. 11, in operation 1102, the wearable electronic device (201) can obtain acceleration sensor data through the sensor (210).

[0182] According to one embodiment, in operation 1104, the wearable electronic device (201) can convert acceleration sensor data on a body coordinate system into data on a navigation coordinate system.

[0183] According to one embodiment, in operation 1106, the wearable electronic device (201) may determine whether a second INT has occurred. Based on the occurrence condition of the second INT, the wearable electronic device (201) may determine whether the second INT has occurred within a first time after the first INT has occurred.

[0184] According to one embodiment, the wearable electronic device (201) may perform operation 1102 based on the second INT not occurring.

[0185] According to one embodiment, the wearable electronic device (201) may extract U-axis data for a time period based on the time point at which the first INT occurs and the time point at which the second INT occurs within the first time period, in operation 1108. The wearable electronic device (201) may extract U-axis data, which is acceleration of the gravity component for a set period based on the time point at which the first INT occurs, from data on the navigation coordinate system.

[0186] According to one embodiment, the wearable electronic device (201) can identify, based on the U-axis data, that the wearable electronic device (201) has moved upward or downward on an axis perpendicular to the ground. For example, if the U-axis data is greater than 0, the wearable electronic device (201) can identify that the wearable electronic device (201) has moved in a direction opposite to gravity (e.g., toward the sky), and if the U-axis data is less than 0, the wearable electronic device (201) can identify that the wearable electronic device (201) has moved in a direction of gravity (e.g., toward the ground).

[0187] According to one embodiment, in operation 1110, the wearable electronic device (201) can identify a rate of change and / or peak-to-peak (P2P) of U-axis data over a time period based on a first INT occurrence time point. P2P can represent a difference between a maximum value and a minimum value of U-axis data over a time period based on a first INT occurrence time point.

[0188] According to one embodiment, in operation 1112, the wearable electronic device (201) may determine whether the rate of change is less than or equal to a first threshold and whether P2P is greater than or equal to a second threshold.

[0189] According to one embodiment, in operation 1114, the wearable electronic device (201) may determine that the interval between the first INT occurrence time and the second INT occurrence time is a valid impact interval due to a fall, based on the change rate being less than or equal to a first threshold and the P2P being greater than or equal to a second threshold.

[0190] According to one embodiment, in operation 1116, the wearable electronic device (201) may determine that the interval between the first INT occurrence time and the second INT occurrence time is not a valid impact interval due to a fall, based on whether the rate of change is not less than or equal to a first threshold or whether P2P is not greater than or equal to a second threshold.

[0191] FIG. 12 is a graph showing an acceleration sensor signal and a U-axis signal of a first pattern for explaining an operation of identifying an effective impact section due to a fall in a wearable electronic device according to one embodiment.

[0192] Referring to Figure 12, in the graph according to one embodiment, the y-axis is in a set unit (e.g., m / s). 2) can indicate an acceleration value, and the x-axis can indicate a sample number (or sample index) of acceleration sensor data that can be indicated by a natural number greater than or equal to 0. According to one embodiment, the acceleration sensor signal can be generated based on a norm associated with the acceleration value of each consecutive sample of the acceleration sensor data. The norm corresponding to each sample can indicate an acceleration value, an amount of impact, or an impact level.

[0193] In one embodiment, if a user wearing a wearable electronic device (201) hits a wall head-on while moving and falls backward, an impact greater than the impact threshold (1202) may occur.

[0194] According to one embodiment, the pattern of the U-axis signal at the time of impact occurrence due to wall collision (1204) and the time of impact occurrence due to fall (1206) may appear differently.

[0195] According to one embodiment, the U-axis signal at the time of impact occurrence (1204) due to wall collision may have a relatively small fluctuation pattern due to the shaking caused by the collision.

[0196] According to one embodiment, the U-axis signal at the time of impact occurrence (1206) due to a fall may have a pattern (1210) in which the signal rapidly increases in the positive (+) direction due to a movement that occurs as the user falls backwards and raises his / her hand upwards or a movement of raising his / her hand and struggling (1208) just before the impact of the fall occurs, and then rapidly decreases in the negative (-) direction due to the fall.

[0197] According to one embodiment, considering the difference in the aforementioned pattern, the wearable electronic device (201) can more accurately determine whether a collision or a fall has occurred based on the gradient and / or P2P value of the U-axis signal for a certain period before and after the impact occurrence time.

[0198] For example, the wearable electronic device (201) can determine that a fall has occurred based on the fact that the rate of change for the U-axis signal is less than or equal to a first threshold and that P2P is greater than or equal to a second threshold, and can identify the corresponding impact occurrence section as a valid impact section due to the fall.

[0199] For example, the wearable electronic device (201) may determine that a collision has occurred based on the fact that the rate of change for the U-axis signal is less than or equal to a first threshold and that P2P is not greater than or equal to a second threshold, and may not determine the corresponding impact occurrence section as a valid impact section due to a fall.

[0200] FIG. 13 is a graph showing an acceleration sensor signal and a U-axis signal of a second pattern for explaining an operation of identifying an effective impact section due to a fall in a wearable electronic device according to one embodiment.

[0201] Referring to Figure 13, in the graph according to one embodiment, the y-axis is in a set unit (e.g., m / s). 2 ) can indicate an acceleration value, and the x-axis can indicate a sample number (or sample index) of acceleration sensor data that can be indicated by a natural number greater than or equal to 0. According to one embodiment, the acceleration sensor signal can be generated based on a norm associated with the acceleration value of each consecutive sample of the acceleration sensor data. The norm corresponding to each sample can indicate an acceleration value, an amount of impact, or an impact level.

[0202] In one embodiment, if a user wearing a wearable electronic device (201) hits a wall head-on while moving and falls backward, an impact greater than the impact threshold (1302) may occur.

[0203] According to one embodiment, the pattern of the U-axis signal at the time of impact by wall collision (1304) may be different from that at the time of impact by fall (1306), based on the fact that the amount of impact at the time of impact by wall collision (1304) is greater than that at the time of impact by fall (1306).

[0204] In one embodiment, the U-axis signal at the time of impact occurrence (1304) due to wall collision may have a relatively small fluctuation pattern due to the shaking caused by the collision, even though a fairly strong impact occurred.

[0205] According to one embodiment, the U-axis signal at the time of impact occurrence (1306) due to a fall may have a pattern (1310) in which the signal rapidly increases in the positive (+) direction due to a movement that occurs as the user falls backwards and raises his / her hand upwards or a movement of raising his / her hand and struggling (1308) just before the impact of the fall occurs, and then rapidly decreases in the negative (-) direction due to the fall.

[0206] As mentioned above, regardless of the magnitude of the impact, the pattern of the U-axis signal may vary depending on the type of impact. For example, the pattern of the U-axis signal in the case of a horizontal impact (e.g., hitting a wall) may differ from the pattern in the case of a vertical impact (e.g., falling).

[0207] According to one embodiment, the wearable electronic device (201) can more accurately detect the time of impact due to a fall by determining whether the impact generated is a horizontal impact or a vertical impact based on the pattern of the U-axis signal. For example, the wearable electronic device (201) can more accurately detect the time of impact due to a fall even in cases where a fall occurs after a collision.

[0208] FIG. 14 is an exemplary diagram of a plurality of electronic devices performing a fall detection operation according to one embodiment.

[0209] Referring to FIG. 14, the plurality of electronic devices may include a wearable electronic device such as a smart watch (1402) or a smart ring (1404), or a mobile terminal (1406) such as a mobile phone. Each of the smart watch (1402), the smart ring (1404), or the mobile terminal (1406) may have a configuration as illustrated in FIG. 1 or FIG. 2, and may perform the fall detection operation described with reference to FIGS. 4 to 13.

[0210] In one embodiment, a plurality of electronic devices can perform communication. For example, a smart watch (1402) or a smart ring (1404) can perform communication with a mobile terminal (1406), and the smart watch (1402) and the smart ring (1404) can perform communication with each other. The communication between the smart watch (1402) or the smart ring (1404) and the mobile terminal (1406), or the communication between the smart watch (1402) and the smart ring (1404) can be performed based on any of various wired or wireless communication protocols, such as Ethernet, GSM (global system for mobile communications), EDGE (enhanced data GSM environment), CDMA (code division multiple access), TDMA (time division multiplexing access), LTE (long term evolution), LTE-A (LTE advance), NR (new radio), Wi-Fi (wireless fidelity), or Bluetooth.

[0211] In one embodiment, multiple electronic devices can individually perform fall detection operations. For example, smartwatch (1402) can detect a fall based on the fall detection operation. Smartwatch (1402) can provide a user experience (UX) related to fall detection based on the fall detection. For example, smartwatch (1402) can display a fall detection message indicating that a fall has been detected (e.g., fall detected. Need help?) on the display or output it through the speaker. Smartwatch (1402) can send a notification message to an emergency contact to notify the user of the fall immediately after the fall detection or after a set time (e.g., 5 seconds) has elapsed after the fall detection, based on the user's settings or selection. Smartwatch (1402) can also display a display object (e.g., a cancel fall notification or a send fall notification icon) on the display to receive a user's selection related to the fall notification.

[0212] In one embodiment, a mobile terminal (1406) or a smart ring (1404) may also perform fall detection operations similar to those of a smart watch (1406). However, since the smart ring (1404) may not include a display, the fall detection message may be output through a speaker and / or vibration.

[0213] In one embodiment, the smart ring (1404) can perform a fall detection operation while connected to a smart watch (1402) or a mobile terminal (1406). Based on the detection of a fall, the smart ring (1404) can transmit a fall detection message to the smart watch (1402) or the mobile terminal (1406).

[0214] According to one embodiment, the smart watch (1402) or the mobile terminal (1406) may receive a fall detection message from the smart ring (1404) and, based on the received fall detection message, display a message indicating that a fall has been detected by the smart ring (1404) on the display or output a message through a speaker and / or vibration. The smart watch (1402) or the mobile terminal (1406) may transmit a notification message to an emergency contact to notify the user of the fall immediately after the fall or after a set time (e.g., 5 seconds) has elapsed after the fall, based on the user's settings or selections.

[0215] According to one embodiment, the mobile terminal (1406) may be connected to wearable electronic devices (e.g., a smart watch (1402), a smart ring (1404), or an HMD (not shown)) mounted on different parts of the user's body. The mobile terminal (1406) may receive a fall detection message from at least one of the connected wearable electronic devices, and may determine the risk of falling based on the mounting location of the wearable electronic device that transmitted the fall detection message.

[0216] For example, when a fall detection message is received from a wearable electronic device (e.g., HMD) mounted on the user's head, the mobile terminal (1406) can determine that an impact due to a fall has occurred on the user's head and set the fall risk level to the highest level.

[0217] For example, when a fall detection message is received from a wearable electronic device (e.g., a smart watch (1402) or a smart ring (1404)) mounted on a user's hand or wrist, the mobile terminal (1406) may determine that an impact due to a fall has occurred on the user's hand or wrist and may set the fall risk level to a relatively lower level than the highest level.

[0218] According to one embodiment, the mobile terminal (1406) may transmit a notification message to an emergency contact immediately after a fall is detected to notify the user of a fall when the fall risk level is set to the highest level.

[0219] According to one embodiment, the mobile terminal (1406) may transmit a notification message to an emergency contact to notify the user of a fall after a set time (e.g., 5 seconds) has elapsed after a fall is detected, when the fall risk level is set to a relatively lower level than the highest level.

[0220] FIG. 15 is a flowchart illustrating the operation of a wearable electronic device according to one embodiment.

[0221] According to one embodiment, operations 1502 to 1508 may be understood to be performed in a processor (e.g., processor (230) of FIG. 2) of an electronic device (e.g., electronic device (201) of FIG. 2).

[0222] The operations illustrated in FIG. 15 are not limited to the illustrated order and may be performed in various orders. In one embodiment, at least some of the operations illustrated in FIG. 15 may be omitted, or more operations may be performed than those illustrated in FIG. 15.

[0223] Referring to FIG. 15, in operation 1502, the wearable electronic device (201) may identify that a first INT (e.g., the first INT (710) of FIG. 7) has occurred through the sensor (210). According to one embodiment, the first INT may be generated at a first point in time when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (or impact threshold value).

[0224] According to one embodiment, samples of an acceleration sensor signal based on a set ODR may be stored in a memory (212) included in the sensor (210), and a first INT may be generated based on a set number of samples of the acceleration sensor signal having a size greater than or equal to a first threshold value consecutively.

[0225] In operation 1504, the wearable electronic device (201) can identify whether a second INT (e.g., the second INT (720) of FIG. 7) occurs within a first time from a first point in time.

[0226] In operation 1506, the wearable electronic device (201) may obtain first information via the sensor (210) based on the identification that a second INT has occurred. In one embodiment, the second INT may occur at a second point in time when the acceleration sensor signal has a magnitude less than a first threshold.

[0227] According to one embodiment, the wearable electronic device (201) can identify that a fourth INT (e.g., the fourth INT (840) of FIG. 8) has occurred through the sensor (210) based on the identification that a second INT has not occurred, and can identify that an error condition associated with the sensor (210) has occurred based on the identification that the fourth INT has occurred.

[0228] In operation 1508, the wearable electronic device (201) may determine, based on the first information, whether a first time interval (e.g., duration (706) of FIG. 7) between the occurrence time of the first INT (first time interval) and the occurrence time of the second INT (second time interval) is a valid impact interval associated with a fall.

[0229] In one embodiment, the first information may include information indicating whether the first time interval is a valid impact interval. The information indicating whether the first time interval is a valid impact interval may be obtained based on a change pattern of a signal on the first axis extracted from an acceleration sensor signal during a second time interval determined based on the first time point.

[0230] According to one embodiment, the change pattern of the signal on the first axis can be identified based on at least one of a rate of change of the signal on the first axis or a P2P of the signal on the first axis.

[0231] According to one embodiment, the first information may include information indicating that the first time interval is a valid impact interval based on a rate of change of a signal on the first axis being less than or equal to a second threshold and a difference in P2P of the signal on the first axis being greater than or equal to a third threshold.

[0232] According to one embodiment, the signal on the first axis may include a signal on the U-axis of the ENU coordinate system obtained from an acceleration sensor signal.

[0233] According to one embodiment, the first information may include information indicating that the first time interval is a valid impact interval based on the signal on the U-axis having a pattern of changing from a positive to a negative direction during the second time interval.

[0234] According to one embodiment, the wearable electronic device (201) may identify, through the sensor (210), that a third INT (e.g., the third INT (730) of FIG. 7) has occurred based on the second time elapsed from the first time point or the second time point, and may determine, based on the occurrence of the third INT, whether the first time period is a valid impact period based on the first information.

[0235] According to one embodiment, the wearable electronic device (201) may identify that a first INT and a second INT have additionally occurred before a second period of time has elapsed from a first time point or a second time point, and may identify that a third INT has occurred through the sensor (210) based on the second period of time having elapsed from a third time point at which the first INT has additionally occurred or a fourth time point at which the second INT has additionally occurred, and may determine, based on the occurrence of the third INT, whether a third time period between the third time point and the fourth time point is a valid impact period based on second information acquired from the sensor (210). According to one embodiment, the second information may include information indicating whether the third time period is a valid impact period. The information indicating whether the third time period is a valid impact period may be acquired based on a change pattern of a signal on the first axis extracted from an acceleration sensor signal during a fourth time period determined based on the third time point.

[0236] According to one embodiment, the wearable electronic device (201) may determine a first threshold based on at least one of the user's activity status identified through the sensor (210), the user's weight, gender, or age.

[0237] According to one embodiment, a storage medium storing at least one computer-readable command may cause the wearable electronic device (201) to perform at least one operation when the at least one command is executed by at least a part of at least one processor (230) of the wearable electronic device (201). The at least one operation may include an operation (1502) of identifying that a first interrupt (INT) (710) has been generated through a sensor (210) included in the wearable electronic device (201). The first INT (710) may be generated at a first point in time when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702). The at least one operation may include an operation (1504) of identifying whether a second INT (720) has been generated through the sensor (210) within a first time from the first point in time. The at least one operation may include an operation (1506) of obtaining first information via the sensor (210) based on the identification that the second INT (720) has occurred. The second INT (720) may be generated at a second time point when the acceleration sensor signal has a magnitude less than the first threshold value (702). The at least one operation may include an operation (1508) of determining, based on the first information, whether a first time interval (706) between the first time point and the second time point is a valid impact period associated with a fall. The first information includes information indicating whether the first time interval (706) is the valid impact period, and the information indicating whether the first time interval (706) is the valid impact period may be obtained based on a change pattern of a signal on a first axis extracted from the acceleration sensor signal during a second time interval determined based on the first time point.

[0238] FIG. 16 is a flowchart illustrating an operation of a wearable electronic device according to one embodiment to determine a point of impact of a fall.

[0239] According to one embodiment, operations 1602 to 1608 may be understood to be performed in a processor (e.g., processor (230) of FIG. 2) of an electronic device (e.g., electronic device (201) of FIG. 2).

[0240] The operations illustrated in FIG. 16 are not limited to the illustrated order and may be performed in various orders. In one embodiment, at least some of the operations illustrated in FIG. 16 may be omitted, or more operations may be performed than those illustrated in FIG. 16.

[0241] Referring to FIG. 16, in operation 1602, the wearable electronic device (201) may determine a time period between the occurrence time of the first INT (e.g., the first INT (710) of FIG. 7) and the occurrence time of the second INT (e.g., the second INT (720) of FIG. 7) as a valid impact period.

[0242] In operation 1604, the wearable electronic device (201) can identify the peak of the acceleration sensor signal of the effective impact section or the duration of the effective impact section.

[0243] In operation 1606, the wearable electronic device (201) may determine that the valid impact section includes an impact due to a fall based on the maximum value or duration of the acceleration sensor signal. In one embodiment, the valid impact section may be determined to include an impact due to a fall based on the maximum value or duration of the acceleration sensor signal being equal to or greater than a fourth threshold value and equal to or less than a fifth threshold value.

[0244] In operation 1608, the wearable electronic device (201) may determine the occurrence time of the first INT as the impact time of the fall based on the determination that the effective impact section is a section including the impact caused by the fall.

[0245] Fig. 17 is a flowchart illustrating an operation of a wearable electronic device according to one embodiment to determine whether a fall has occurred.

[0246] According to one embodiment, operations 1702 to 1708 may be understood to be performed in a processor (e.g., processor (230) of FIG. 2) of an electronic device (e.g., electronic device (201) of FIG. 2).

[0247] The operations illustrated in FIG. 17 are not limited to the illustrated order and may be performed in various orders. In one embodiment, at least some of the operations illustrated in FIG. 17 may be omitted, or more operations may be performed than those illustrated in FIG. 17.

[0248] Referring to FIG. 17, in operation 1702, the wearable electronic device (201) can set a fall impact occurrence section based on the time of the fall impact.

[0249] In operation 1704, the wearable electronic device (201) can acquire sensor data during the fall impact occurrence period.

[0250] In operation 1706, the wearable electronic device (201) can extract feature or pattern information of sensor data.

[0251] In operation 1708, the wearable electronic device (201) can input the extracted information into a fall classifier for determining whether or not a fall has occurred.

[0252] According to one embodiment, the time of occurrence of an impact due to a fall can be more accurately detected in a wearable electronic device (201).

[0253] According to one embodiment, it is possible to prevent acceleration INT from being generated in a situation where a noisy peak signal or a temporary shock is applied to the wearable electronic device (201) (e.g., a situation where the wearable electronic device (201) lightly hits a hard object such as a table).

[0254] According to one embodiment, the wearable electronic device (201) can more accurately detect the actual time of falling to the ground as the time of impact of the fall, rather than the time of impact in a situation where a fall occurs after a collision.

[0255] According to one embodiment, the wearable electronic device (201) can check the user's activity level or activity status through the sensor (210), and change various thresholds associated with a fall detection operation based on the checked activity level or activity status. For example, the wearable electronic device (201) can identify whether the user is stationary, exercising with a regular pattern such as running, exercising with an irregular pattern such as soccer or basketball, or exercising with the wrist such as tennis or golf based on sensor data acquired through a sensor (e.g., an inertial sensor), and change the impact threshold based on the identification result, thereby preventing the impact applied by the exercise from being detected as an impact caused by a fall.

[0256] In one embodiment, the impact detection operation may be personalized based on the user's weight, gender, or age. For example, the wearable electronic device (201) may perform a fall detection operation based on the user's condition by changing various thresholds, including the impact threshold, based on personalized information such as the user's weight, gender, or age.

[0257] According to one embodiment, the wearable electronic device (201) can perform a user-customized fall detection operation by setting various thresholds or adjusting the fall notification frequency based on the user's settings.

[0258] According to one embodiment, when the wearable electronic device (201) is damaged or malfunctions, it can be identified based on reference information whether the cause of the damage or malfunction is related to the falling of the wearable electronic device (201). The reference information can include information acquired by a fall detection operation of the wearable electronic device (201), and can be stored in the wearable electronic device (201) or stored and utilized in a server (e.g., a cloud server or an IoT (Internet of Things) server) associated with the wearable electronic device (201). The wearable electronic device (201) checks whether movement of the wearable electronic device (201) has occurred in the direction of the ground to detect an effective impact section due to a fall, and if a signal pattern of a weightless state appears in the detected effective impact section or it is identified that the wearable electronic device (201) has experienced a falling state, it can be stored as reference information. The service center can identify whether the wearable electronic device (201) has been dropped based on the reference information and provide appropriate service to the user based on the identified condition.

[0259] According to one embodiment, the wearable electronic device (201) may perform a fall detection operation using a barometric pressure sensor. When the displacement of the wearable electronic device (201) moves upward with respect to the ground (e.g., toward the sky), the barometric pressure value detected by the barometric pressure sensor may decrease, and when the displacement of the wearable electronic device (201) moves toward the ground, the barometric pressure value detected by the barometric pressure sensor may increase. Since the barometric pressure sensor may have an error depending on the surrounding environment, when the influence of the surrounding environment is small and the barometric pressure sensor has good performance, it may be checked whether the displacement of the wearable electronic device (201) has moved toward the ground using the barometric pressure sensor instead of the sensor (210).

[0260] According to one embodiment, the operation of the sensor (210) described above and the operation of the MCU (234) may be performed by a single integrated component. For example, the sensor (210) may perform the operation of the MCU (234) as well as the operation of the sensor (210). To perform the operation of the MCU (234), the sensor (210) may include a processor. The processor of the sensor (210) may perform operations such as processing sensor data for fall detection or controlling a sampling rate. Data processed by the processor of the sensor (210) may be transmitted to the processor (e.g., CPU, NPU, or GPU) (230), and the processor (230) may make a final determination as to whether or not a fall has occurred based on the transmitted data.

[0261] According to one embodiment, an acceleration triaxial norm may be used as a signal for identifying an impact situation. Since the posture of the wearable electronic device (201) when an impact occurs cannot be specified, the amount of impact in a free posture can be checked when the acceleration triaxial norm is used. Instead of the acceleration triaxial norm, raw data of each of the three acceleration axes may be used. Impact amount information (e.g., peak or duration) can be identified based on the raw data of each of the three acceleration axes, and an impact situation can be identified based on the identified information.

[0262] According to one embodiment, the sensor (210) can analyze the vertical movement of the ground in a section where a strong impact exceeding the impact threshold occurs to determine whether the section is a valid impact section due to a fall. This operation may also be performed by the MCU (234). The MCU (234) can receive information about the section where the impact occurred from the sensor (210) and determine whether a vertical movement of the ground occurred based on the received information.

[0263] A wearable electronic device (201) according to one embodiment may include a sensor (210); a memory (220); and at least one processor (230) including a processing circuit.

[0264] According to one embodiment, the memory (220), when individually or collectively executed by the at least one processor (230), causes the wearable electronic device (201) to: identify that a first interrupt (INT) (710) has occurred through the sensor (210), wherein the first INT (710) is generated at a first time point when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702), identify whether a second INT (720) has occurred through the sensor (210) within a first time point from the first time point, wherein the second INT (720) is generated at a second time point when the acceleration sensor signal has a magnitude less than the first threshold value (702), and acquire first information through the sensor (210) based on the identification that the second INT (720) has occurred, Commands may be stored that cause a determination to be made based on the first information whether a first time interval between the first time point and the second time point is a valid impact interval (706) associated with a fall.

[0265] The first information includes information indicating whether the first time period is the valid impact period (706), and the information indicating whether the first time period is the valid impact period (706) can be obtained based on a change pattern of a signal on the first axis extracted from the acceleration sensor signal during a second time period determined based on the first time point.

[0266] According to one embodiment, the change pattern of the signal on the first axis can be identified based on at least one of a rate of change (gradient) of the signal on the first axis or a difference between a maximum value and a minimum value (peak to peak) of the signal on the first axis.

[0267] According to one embodiment, the first information may include information indicating that the first time interval is the valid impact interval (706) based on the rate of change of the signal on the first axis being less than or equal to a second threshold value and the difference between the maximum and minimum values ​​of the signal on the first axis being greater than or equal to a third threshold value.

[0268] According to one embodiment, the memory (220), when individually or collectively executed by the at least one processor (230), may cause the wearable electronic device (201) to: identify information about a peak of the acceleration sensor signal of the valid impact period (706) or a duration of the valid impact period (706), based on the first time period being determined as the valid impact period (706); determine that the valid impact period (706) is a period including an impact due to the fall, based on the peak of the acceleration sensor signal being equal to or greater than a fourth threshold value and the duration being equal to or less than a fifth threshold value; and determine that the first time point is a time point at which an impact due to the fall occurs, based on the determination that the valid impact period (706) is a period including an impact due to the fall.

[0269] According to one embodiment, samples of the acceleration sensor signal based on a set output data rate (ODR) are stored in a memory (212) included in the sensor (210), and the first INT (710) can be generated based on a set number of samples among the samples of the acceleration sensor signal having a size greater than or equal to the first threshold value (702) in succession.

[0270] According to one embodiment, the signal on the first axis includes a signal on the U-axis of the ENU (east-north-up) coordinate system obtained from the acceleration sensor signal, and the first information may include information indicating that the first time period is the effective impact period (706) based on the fact that the signal on the U-axis has a pattern of changing from a positive direction to a negative direction during the second time period.

[0271] According to one embodiment, the memory (220), when individually or collectively executed by the at least one processor (230), may cause the wearable electronic device (201) to: identify, based on a second time (708) elapsed from the first time point or the second time point, that a third INT (730) has occurred through the sensor (210); and determine, based on the occurrence of the third INT (730), whether the first time period is the valid impact period (706) based on the first information.

[0272] According to one embodiment, the memory (220) may store instructions that, when individually or collectively executed by the at least one processor (230), cause the wearable electronic device (201) to: identify that the first INT and the second INT have been additionally generated before a second time (708) has elapsed from the first time point or the second time point, identify that the third INT has been generated through the sensor (210) based on the second time having elapsed from a third time point at which the first INT has been additionally generated or a fourth time point at which the second INT has been additionally generated, and determine, based on the generation of the third INT, whether a third time interval between the third time point and the fourth time point is the valid impact interval, based on second information acquired through the sensor (210), wherein the second information includes information indicating whether the third time interval is the valid impact interval, and the information indicating whether the third time interval is the valid impact interval It can be obtained based on the change pattern of the signal on the first axis extracted from the acceleration sensor signal during the fourth time period determined based on the third time point.

[0273] According to one embodiment, the memory (220), when individually or collectively executed by the at least one processor (230), may cause the wearable electronic device (201) to: identify that a fourth INT (840) has occurred through the sensor (210) based on the identification that the second INT (720) has not occurred, and identify that an error condition associated with the sensor (210) has occurred based on the identification that the fourth INT (840) has occurred.

[0274] According to one embodiment, the memory (220), when individually or collectively executed by the at least one processor (230), may cause the wearable electronic device (201) to determine the first threshold value (702) based on at least one of: the activity state of the user identified through the sensor (210), the weight, gender, or age of the user.

[0275] According to one embodiment, a method for detecting a fall by a wearable electronic device comprises: an operation (1502) of identifying that a first interrupt (INT) (710) has occurred through a sensor (210) included in the wearable electronic device (201), wherein the first INT (710) is generated at a first time point when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702); an operation (1504) of identifying whether a second INT (720) has occurred through the sensor (210) within a first time point from the first time point, wherein the second INT (720) has occurred at a second time point when the acceleration sensor signal has a magnitude less than or equal to the first threshold value (702); an operation (1506) of acquiring first information through the sensor (210) based on the identification that the second INT (720) has occurred; And an operation (1508) of determining whether a first time interval between the first time point and the second time point is a valid impact interval (706) associated with a fall based on the first information, wherein the first information includes information indicating whether the first time interval is the valid impact interval (706), and the information indicating whether the first time interval is the valid impact interval (706) can be obtained based on a change pattern of a signal on a first axis extracted from the acceleration sensor signal during a second time interval determined based on the first time point.

[0276] According to one embodiment, in a method for detecting a fall by a wearable electronic device, the change pattern of the signal on the first axis may be identified based on at least one of a change rate (gradient) of the signal on the first axis or a difference between a maximum value and a minimum value (peak to peak) of the signal on the first axis.

[0277] According to one embodiment, in a method for a wearable electronic device to detect a fall, the first information may be a method including information indicating that the first time period is the valid impact period (706) based on a rate of change of a signal on the first axis being less than or equal to a second threshold value and a difference between a maximum value and a minimum value of the signal on the first axis being greater than or equal to a third threshold value.

[0278] According to one embodiment, a method for detecting a fall by a wearable electronic device may further include: an operation (1604) of identifying information about a peak value of an acceleration sensor signal of the valid impact period (706) or a duration of the valid impact period (706) based on the first time period being determined as the valid impact period (706) (1602); an operation (1606) of determining that the valid impact period (706) is a period including an impact due to the fall based on the peak value of the acceleration sensor signal being equal to or greater than a fourth threshold value and the duration being equal to or less than a fifth threshold value; and an operation (1608) of determining that the first time point is a time point at which an impact due to the fall occurs based on the determination that the valid impact period (706) is a period including an impact due to the fall.

[0279] According to one embodiment, in a method for detecting a fall by a wearable electronic device, samples of the acceleration sensor signal based on a set output data rate (ODR) are stored in a memory (212) included in the sensor (210), and the first INT (710) can be generated based on a set number of samples among the samples of the acceleration sensor signal having a size greater than or equal to the first threshold value (702) in succession.

[0280] According to one embodiment, in a method for detecting a fall by a wearable electronic device, the signal on the first axis includes a signal on the U-axis of an ENU (east-north-up) coordinate system obtained from the acceleration sensor signal, and information indicating that the first time period is the valid impact period may be included in the first information based on the signal on the U-axis having a pattern of changing from a positive direction to a negative direction during the second time period.

[0281] According to one embodiment, in a method for detecting a fall by a wearable electronic device, the operation of determining whether the period is a valid impact period may include: an operation of identifying, through the sensor (210), that a third INT (730) has occurred based on the passage of a second time (708) from the first time point or the second time point; and an operation of determining, based on the identification that the third INT (730) has occurred, whether the first time period is a valid impact period based on the first information.

[0282] According to one embodiment, in a method for a wearable electronic device to detect a fall, the method comprises: an operation of identifying that the first INT and the second INT have additionally occurred before a second time (708) has elapsed from the first time point or the second time point; an operation of identifying that the third INT has occurred through the sensor (210) based on the second time having elapsed from a third time point at which the first INT has additionally occurred or a fourth time point at which the second INT has additionally occurred; And based on the occurrence of the third INT, based on the second information obtained from the sensor (210), an operation of determining whether a third time period between the third time point and the fourth time point is the valid impact period is further included, wherein the second information includes information indicating whether the third time period is the valid impact period, and the information indicating whether the third time period is the valid impact period can be obtained based on a change pattern of a signal on the first axis extracted from the acceleration sensor signal during a fourth time period determined based on the third time point.

[0283] According to one embodiment, a method for detecting a fall by a wearable electronic device may further include: an operation of identifying that a fourth INT (840) has occurred through the sensor (210) based on the identification that the second INT (720) has not occurred; and an operation of identifying that an error situation associated with the sensor (210) has occurred based on the identification that the fourth INT (840) has occurred.

[0284] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0285] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0286] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0287] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0288] According to one embodiment, the method according to various embodiments disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0289] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In a wearable electronic device (201), sensor (210); memory (220); and At least one processor (230) comprising a processing circuit, The above memory (220), when executed individually or collectively by the at least one processor (230), causes the wearable electronic device (201) to: Identifying that a first interrupt (INT) (710) has occurred through the sensor (210) - the first INT (710) is generated at a first point in time when the acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702) -, Within a first time from the first point in time, identifying whether a second INT (720) is generated through the sensor (210) - the second INT (720) is generated at a second point in time when the acceleration sensor signal has a magnitude less than the first threshold value (702); Based on the identification that the above second INT (720) has occurred, first information is acquired through the sensor (210), Store commands that cause a determination to be made based on the first information whether the first time interval between the first time point and the second time point is a valid impact interval (706) associated with a fall, A wearable electronic device, wherein the first information includes information indicating whether the first time period is the valid impact period (706), and the information indicating whether the first time period is the valid impact period (706) is obtained based on a change pattern of a signal on the first axis extracted from the acceleration sensor signal during a second time period determined based on the first time point.

2. In the first paragraph, the change pattern of the signal on the first axis is: A wearable electronic device identified based on at least one of a gradient of a signal on the first axis or a difference between a maximum and minimum value of a signal on the first axis (peak to peak).

3. In paragraph 1 or 2, the first information is: A wearable electronic device including information indicating that the first time period is the effective impact period (706) based on the rate of change of the signal on the first axis being less than or equal to a second threshold value and the difference between the maximum and minimum values ​​of the signal on the first axis being greater than or equal to a third threshold value.

4. In any one of the first to third paragraphs, the memory (220), when individually or collectively executed by the at least one processor (230), causes the wearable electronic device (201) to: Based on the first time period being determined as the effective impact section (706), information about the peak of the acceleration sensor signal of the effective impact section (706) or the duration of the effective impact section (706) is identified, Based on the fact that the maximum value of the acceleration sensor signal is greater than or equal to the fourth threshold and the duration is less than or equal to the fifth threshold, it is determined that the valid impact section (706) is a section including the impact caused by the fall. A wearable electronic device that stores commands that cause the first point in time to be determined as the point in time at which the impact due to the fall occurred, based on the determination that the effective impact section (706) includes the impact due to the fall.

5. In any one of paragraphs 1 to 4, Samples of the acceleration sensor signal based on the set ODR (output data rate) are stored in the memory (212) included in the sensor (210), A wearable electronic device, wherein the first INT (710) is generated based on a set number of samples among the samples of the acceleration sensor signal having a size greater than or equal to the first threshold value (702).

6. In any one of paragraphs 1 to 5, The signal on the first axis includes a signal on the U axis of the ENU (east-north-up) coordinate system obtained from the acceleration sensor signal, A wearable electronic device, wherein the first information includes information indicating that the first time period is the effective impact period (706), based on the fact that the signal on the U-axis has a pattern of changing from a positive direction to a negative direction during the second time period.

7. In any one of the first to sixth paragraphs, the memory (220), when individually or collectively executed by the at least one processor (230), causes the wearable electronic device (201) to: Based on the second time (708) elapsed from the first time point or the second time point, it is identified that a third INT (730) has occurred through the sensor (210), A wearable device storing commands that cause it to determine whether the first time period is the valid impact period (706) based on the first information, based on the occurrence of the third INT (730).

8. In any one of the first to seventh paragraphs, the memory (220), when individually or collectively executed by the at least one processor (230), causes the wearable electronic device (201) to: Before the second time (708) elapses from the first time point or the second time point, it is identified that the first INT and the second INT have additionally occurred, Based on the second time elapsed from the third time point at which the first INT was additionally generated or the fourth time point at which the second INT was additionally generated, it is identified through the sensor (210) that the third INT was additionally generated, Based on the occurrence of the third INT, based on the second information acquired through the sensor (210), commands are stored to determine whether the third time interval between the third time point and the fourth time point is the valid impact interval, A wearable electronic device, wherein the second information includes information indicating whether the third time period is the valid impact period, and the information indicating whether the third time period is the valid impact period is obtained based on a change pattern of a signal on the first axis extracted from the acceleration sensor signal during a fourth time period determined based on the third time point.

9. In any one of the first to eighth paragraphs, the memory (220), when individually or collectively executed by the at least one processor (230), causes the wearable electronic device (201) to: Based on the identification that the above second INT (720) did not occur, it is identified that the fourth INT (840) occurred through the sensor (210), A wearable device that stores commands that are caused to identify that an error situation associated with the sensor (210) has occurred based on the occurrence of the above fourth INT (840).

10. In any one of the first to ninth paragraphs, the memory (220), when individually or collectively executed by the at least one processor (230), causes the wearable electronic device (201) to: A wearable device that stores commands that cause the user to determine the first threshold value (702) based on at least one of the user's activity status identified through the sensor (210), the user's weight, gender, or age.

11. In a method for detecting a fall by a wearable electronic device (201), An operation (1502) of identifying that a first interrupt (INT) (710) has occurred through a sensor (210) included in the wearable electronic device (201) - the first INT (710) is generated at a first point in time when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702); An operation (1504) of identifying whether a second INT (720) is generated through the sensor (210) within a first time from the first time point, wherein the second INT (720) is generated at a second time point when the acceleration sensor signal has a magnitude less than the first threshold value (702); An operation (1506) of acquiring first information through the sensor (210) based on the identification that the above second INT (720) has occurred; and An operation (1508) for determining whether a first time interval between the first time point and the second time point is a valid impact interval (706) associated with a fall based on the first information, A method in which the first information includes information indicating whether the first time period is the valid impact period (706), and the information indicating whether the first time period is the valid impact period (706) is obtained based on a change pattern of a signal on the first axis extracted from the acceleration sensor signal during a second time period determined based on the first time point.

12. In the 11th paragraph, the change pattern of the signal on the first axis is: A method identified based on at least one of a gradient of a signal on the first axis or a difference between a maximum and minimum value of a signal on the first axis (peak to peak).

13. In paragraph 11 or 12, the first information is: A method including information indicating that the first time interval is the valid impact interval (706) based on the rate of change of the signal on the first axis being less than or equal to a second threshold value and the difference between the maximum and minimum values ​​of the signal on the first axis being greater than or equal to a third threshold value.

14. In any one of paragraphs 11 to 13, An operation (1604) of identifying information about the peak of the acceleration sensor signal of the effective impact section (706) or the duration of the effective impact section (706) based on the determination of the first time period as the effective impact section (706) (1602); An operation (1606) of determining that the valid impact section (706) includes an impact caused by the fall, based on the fact that the maximum value of the acceleration sensor signal is greater than or equal to the fourth threshold value and the duration is less than or equal to the fifth threshold value; and A method further comprising an operation (1608) of determining the first point in time as the point in time at which the impact due to the fall occurred, based on determining that the effective impact section includes the impact due to the fall.

15. A storage medium storing at least one computer-readable command, wherein the at least one command, when executed by at least a part of at least one processor (230) of a wearable electronic device (201), causes the wearable electronic device (201) to perform at least one operation. At least one of the above actions: An operation (1502) of identifying that a first interrupt (INT) (710) has occurred through a sensor (210) included in the wearable electronic device (201) - the first INT (710) is generated at a first point in time when an acceleration sensor signal acquired by the sensor (210) has a magnitude greater than or equal to a first threshold value (702); An operation (1504) of identifying whether a second INT (720) is generated through the sensor (210) within a first time from the first time point, wherein the second INT (720) is generated at a second time point when the acceleration sensor signal has a magnitude less than the first threshold value (702); An operation (1506) of acquiring first information through the sensor (210) based on the identification that the above second INT (720) has occurred; and An operation (1508) for determining whether a first time interval between the first time point and the second time point is a valid impact interval (706) associated with a fall based on the first information, A storage medium, wherein the first information includes information indicating whether the first time period is the valid impact period (706), and the information indicating whether the first time period is the valid impact period (706) is obtained based on a change pattern of a signal on the first axis extracted from the acceleration sensor signal during a second time period determined based on the first time point.

Images