KR20240049065A - Electronic device and method for performing fall detection - Google Patents

Abstract

According to one embodiment, the electronic device includes at least one sensor, memory, and processor. The processor is configured to obtain first information about a first walking pattern of the user of the electronic device and second information about the user's walking environment. The processor is configured to identify a first value indicating a difference between the first walking pattern and the reference walking pattern, based on the first information and third information about the reference walking pattern stored in the memory. The processor is configured to identify a second value representing a difference between the first and second gait patterns. The processor is configured to identify a threshold value associated with fall detection based on the first value, the second value, and the second information. The processor is configured to perform the fall detection.

Description

Electronic device and method for performing fall detection {ELECTRONIC DEVICE AND METHOD FOR PERFORMING FALL DETECTION}

The descriptions below relate to electronic devices and methods for performing fall detection.

With the development of technology, various services are being provided through electronic devices. The electronic device may use at least one sensor to identify the movement of the user carrying the electronic device. An electronic device can identify various activity states of a user based on the user's movements. For example, the electronic device can identify information about the user's steps. Electronic devices can provide users with various services related to their steps.

The above information may be provided as background art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing can be applied as prior art to the present disclosure.

According to one embodiment, an electronic device may include at least one sensor, memory, and processor. The processor may be set to obtain first information about the first walking pattern of the user of the electronic device and second information about the user's walking environment using the at least one sensor. The processor may be set to identify a first value indicating a difference between the first walking pattern and the reference walking pattern, based on the first information and third information about the reference walking pattern stored in the memory. there is. Based on the first information and fourth information about the second walking pattern of the user, which is stored in the memory and identified based on the walking history of the user, the first walking pattern and the second walking pattern It can be set to identify a second value that represents a difference between gait patterns. The processor may be configured to identify a threshold value related to fall detection based on the first value, the second value, and the second information. The processor may be configured to perform the fall detection based on a comparison between the threshold value and a value obtained through the at least one sensor.

According to one embodiment, a method of an electronic device includes first information about a first walking pattern of a user of the electronic device and second information about the user's walking environment using at least one sensor of the electronic device. Obtaining, based on the first information and third information about the reference walking pattern stored in the memory, identifying a first value indicating a difference between the first walking pattern and the reference walking pattern, Based on the first information and fourth information about the second walking pattern of the user, which is stored in the memory and identified based on the walking history of the user, between the first walking pattern and the second walking pattern identifying a second value representing a difference between, identifying a threshold value associated with fall detection based on the first value, the second value, and the second information; It may include an operation of executing the fall detection based on comparison between values obtained through the sensor.

1 is a block diagram of an electronic device in a network environment, according to one embodiment.
Figure 2 is a simplified block diagram of an electronic device, according to an embodiment.
Figure 3 shows a simplified block diagram of a processor included in an electronic device, according to one embodiment.
FIG. 4 is a flowchart illustrating the operation of an electronic device, according to an embodiment.
FIG. 5 is a flowchart illustrating the operation of an electronic device, according to an embodiment.
Figures 6A to 6C show examples of trends for identifying a user's walking environment, according to one embodiment.
7A to 7C show examples of trends for identifying a user's walking environment, according to an embodiment.
Figure 8 shows an example of a trend for identifying a user's walking environment, according to one embodiment.
FIG. 9 illustrates an example of an operation of an electronic device to learn data according to an embodiment.
FIG. 10 is a flowchart illustrating the operation of an electronic device, according to an embodiment.
Figure 11 shows an example of an operation of an electronic device according to an embodiment.
Figure 12 shows an example of an operation of an electronic device according to an embodiment.
FIG. 13 is a flowchart illustrating the operation of an electronic device, according to an embodiment.
Figure 14 shows an example of a designated matrix according to one embodiment.
Figure 15 shows an example of a matrix representing a population according to one embodiment.
Figure 16 shows an example of a matrix representing information on fitness according to an embodiment.
Figure 17 shows an example of a matrix representing at least a portion of the population according to one embodiment.
Figure 18 shows an example of a learning result for a walking pattern according to an embodiment.
Figure 19 shows an example of an operation mode of a processor according to an embodiment.
Figures 20A and 20B show an example in which values for a walking pattern according to an embodiment are displayed as three-dimensional coordinates.
Figures 21A and 21B show an example of a screen for warning of the risk of falling according to an embodiment.

1 is a block diagram of an electronic device in a network environment, according to one embodiment.

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

The processor 120, for example, executes software (e.g., program 140) to operate at least one other component (e.g., hardware or software component) of the electronic device 101 connected to the processor 120. It can be controlled and various data processing or calculations can be performed. According to one embodiment, as at least part of data processing or computation, the processor 120 stores commands or data received from another component (e.g., sensor module 176 or communication module 190) in volatile memory 132. The commands or data stored in the volatile memory 132 can be processed, and the resulting data can be stored in the non-volatile memory 134. According to one embodiment, the processor 120 includes a main processor 121 (e.g., a central processing unit or an application processor) or an auxiliary processor 123 that can operate independently or together (e.g., a graphics processing unit, a neural network processing unit ( It may include a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device 101 includes a main processor 121 and a secondary processor 123, the secondary processor 123 may be set to use lower power than the main processor 121 or be specialized for a designated function. You can. The auxiliary processor 123 may be implemented separately from the main processor 121 or as part of it.

The auxiliary processor 123 may, for example, act on behalf of the main processor 121 while the main processor 121 is in an inactive (e.g., sleep) state, or while the main processor 121 is in an active (e.g., application execution) state. ), together with the main processor 121, at least one of the components of the electronic device 101 (e.g., the display module 160, the sensor module 176, or the communication module 190) At least some of the functions or states related to can be controlled. According to one embodiment, co-processor 123 (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module 180 or communication module 190). there is. According to one embodiment, the auxiliary processor 123 (eg, neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. Artificial intelligence models can be created through machine learning. For example, such learning may be performed in the electronic device 101 itself on which the artificial intelligence model is performed, or may be performed through a separate server (e.g., server 108). Learning algorithms may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but It is not limited. An artificial intelligence model may include multiple artificial neural network layers. Artificial neural networks include deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), restricted boltzmann machine (RBM), belief deep network (DBN), bidirectional recurrent deep neural network (BRDNN), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the examples described above. In addition to hardware structures, artificial intelligence models may additionally or alternatively include software structures.

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

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

The input module 150 may receive commands or data to be used in a component of the electronic device 101 (e.g., the processor 120) from outside the electronic device 101 (e.g., a user). The input module 150 may include, for example, a microphone, mouse, keyboard, keys (eg, buttons), or digital pen (eg, stylus pen).

The sound output module 155 may output sound signals to the outside of the electronic device 101. The sound output module 155 may include, for example, a speaker or a receiver. Speakers can be used for general purposes such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part of it.

The display module 160 can visually provide information to the outside of the electronic device 101 (eg, a user). The display module 160 may include, for example, a display, a hologram device, or a projector, and a control circuit for controlling the device. According to 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 force generated by the touch.

The audio module 170 can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module 170 acquires sound through the input module 150, the sound output module 155, or an external electronic device (e.g., directly or wirelessly connected to the electronic device 101). Sound may be output through the electronic device 102 (e.g., speaker or headphone).

The sensor module 176 detects the operating state (e.g., power or temperature) of the electronic device 101 or the external environmental state (e.g., user state) and generates an electrical signal or data value corresponding to the detected state. can do. According to one embodiment, the sensor module 176 includes, for example, a gesture sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, It may include a temperature sensor, humidity sensor, or light sensor.

The interface 177 may support one or more designated protocols that can be used to connect the electronic device 101 directly or wirelessly with an external electronic device (eg, the electronic device 102). According to 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.

The connection terminal 178 may include a connector through which the electronic device 101 can be physically connected to an external electronic device (eg, the 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 (eg, a headphone connector).

The haptic module 179 can convert electrical signals into mechanical stimulation (e.g., vibration or movement) or electrical stimulation that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 180 can capture still images and moving images. According to one embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

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

The battery 189 may supply power to at least one component of the electronic device 101. According to one embodiment, the battery 189 may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

Communication module 190 is configured to provide a direct (e.g., wired) communication channel or wireless communication channel between electronic device 101 and an external electronic device (e.g., electronic device 102, electronic device 104, or server 108). It can support establishment and communication through established communication channels. Communication module 190 operates independently of processor 120 (e.g., an 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 is 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., : LAN (local area network) communication module, or power line communication module) may be included. Among these communication modules, the corresponding communication module is 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., legacy It may communicate with an external electronic device 104 through a telecommunication network such as a cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., LAN or WAN). These various types of communication modules may be integrated into one component (e.g., a single chip) or may be implemented as a plurality of separate components (e.g., multiple chips). The wireless communication module 192 uses subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199. The electronic device 101 can be confirmed or authenticated.

The wireless communication module 192 may support 5G networks after 4G networks and next-generation communication technologies, for example, NR access technology (new radio access technology). NR access technology provides high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and access to multiple terminals (massive machine type communications (mMTC)), or ultra-reliable and low-latency (URLLC). -latency communications)) can be supported. The wireless communication module 192 may support high frequency bands (eg, mmWave bands), for example, to achieve high data rates. The wireless communication module 192 uses various technologies to secure performance in high frequency bands, for example, beamforming, massive array multiple-input and multiple-output (MIMO), and full-dimensional multiplexing. It can support technologies such as input/output (FD-MIMO: full dimensional MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module 192 may support various requirements specified in the electronic device 101, an external electronic device (e.g., electronic device 104), or a network system (e.g., second network 199). According to one embodiment, the wireless communication module 192 supports Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mmTC, or U-plane latency (e.g., 164 dB or less) for realizing URLLC. Example: Downlink (DL) and uplink (UL) each of 0.5 ms or less, or round trip 1 ms or less) can be supported.

The antenna module 197 may transmit or receive signals or power to or from the outside (eg, an external electronic device). According to one embodiment, the antenna module 197 may include an antenna including a radiator made of a conductor or a conductive pattern formed on a substrate (eg, PCB). According to one embodiment, the antenna module 197 may include a plurality of antennas (eg, 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 is connected to the plurality of antennas by, for example, the communication module 190. can be selected. Signals or power may be transmitted or received between the communication module 190 and an external electronic device through the at least one selected antenna. According to some embodiments, in addition to the radiator, other components (eg, radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module 197.

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

At least some of the components are connected to each other through a communication method between peripheral devices (e.g., bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and signal ( (e.g. commands or data) can be exchanged with each other.

According to one embodiment, commands or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199. Each of the external electronic devices 102 or 104 may be of the same or different type as the electronic device 101. According to one embodiment, all or part of the operations performed 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 must perform a certain function or service automatically or in response to a request from a user or another device, the electronic device 101 may perform the function or service instead of executing the function or service on its own. Alternatively, or additionally, one or more external electronic devices may be requested to perform at least part of the function or service. One or more external electronic devices that have received the request may execute at least part 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 part of a response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology can be used. The electronic device 101 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an Internet of Things (IoT) device. Server 108 may be an intelligent server using machine learning and/or neural networks. According to one embodiment, the external electronic device 104 or server 108 may be included in the second network 199. The electronic device 101 may be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

According to one embodiment, an electronic device (eg, the electronic device 101 of FIG. 1) may provide a notification to the user based on identifying that the user has fallen. The electronic device can learn the user's walking pattern before identifying that a fall has occurred. The electronic device may identify a threshold value related to detecting a fall for the user based on the difference between the learned walking pattern and the walking pattern identified through the sensor. The electronic device may perform fall detection based on the identified threshold.

In the following specification, based on the difference between the learned walking pattern and the walking pattern identified through the sensor, a threshold value related to fall detection is identified for the user, and based on the identified threshold value, an implementation for performing fall detection is performed. An example can be explained.

Figure 2 is a simplified block diagram of an electronic device, according to an embodiment.

Referring to FIG. 2, the electronic device 200 may be configured in various forms. The electronic device 200 may be implemented in various forms that can be carried by the user, such as a smart phone, smart watch, smart band, smart ring, wireless earphone, or smart glasses. For example, electronic device 200 may correspond to electronic device 101 in FIG. 1 .

According to one embodiment, the electronic device 200 may include a processor 210, a sensor 220, a memory 230, and/or a communication circuit 240. Depending on the embodiment, the electronic device 200 may include at least one of a processor 210, a sensor 220, a memory 230, and a communication circuit 240. For example, at least some of the processor 210, sensor 220, memory 230, and communication circuit 240 may be omitted depending on the embodiment.

According to one embodiment, the processor 210 may correspond to the processor 120 of FIG. 1. The processor 210 may be operatively or operably coupled with or connected with the sensor 220, the memory 230, and the communication circuit 240. For example, processor 210 being operatively coupled with another component may mean that processor 210 can control the other component. For example, the processor 210 may control the operation of the sensor 220. Processor 210 may activate or deactivate sensor 220. The processor 210 may process information obtained from the sensor 220.

According to one embodiment, the processor 210 may be comprised of at least one processor. Processor 210 may include at least one processor. According to one embodiment, the processor 210 may include hardware components for processing data based on one or more instructions. Hardware components for processing data may include, for example, an arithmetic and logic unit (ALU), a field programmable gate array (FPGA), and/or a central processing unit (CPU).

According to one embodiment, the electronic device 200 may include a sensor 220. Sensor 220 may be composed of at least one sensor. For example, sensor 430 may correspond to sensor module 176 in FIG. 1 . For example, the sensor 220 may include at least one of an acceleration sensor 221, a gyro sensor 222, and an air pressure sensor 223.

For example, the acceleration sensor 221 may identify (or measure, detect) the acceleration of the electronic device 200 in three directions: x-axis, y-axis, and z-axis. For example, the gyro sensor 222 may identify (or measure or detect) the angular velocity of the electronic device 200 in three directions: x-axis, y-axis, and z-axis. Depending on the embodiment, the electronic device 200 may include an inertial sensor consisting of an acceleration sensor 221 and a gyro sensor 222.

For example, the barometric pressure sensor 223 may identify (or measure or sense) the barometric pressure around the electronic device 200. The processor 210 identifies the height (or altitude) at which the electronic device 200 is located above the ground based on data about the air pressure around the electronic device 200 identified using the air pressure sensor 223. can do.

Although not shown, the sensor 220 may further include a sensor for acquiring (or identifying, measuring, or detecting) various data about the user.

For example, sensor 220 may include a body temperature sensor. The processor 210 may measure the skin temperature of a part of the user's body through a body temperature sensor. The processor 210 may obtain the user's body temperature based on the skin temperature of a part of the user's body.

For example, sensor 220 may include a heart rate variability (HRV) sensor. The processor 210 may measure the regularity or variability of heart rate through the HRV sensor. The processor 210 may obtain information about the regularity or variability of heart rate through the HRV sensor.

According to one embodiment, the electronic device 200 may include a memory 230. Memory 230 may be used to store information or data. For example, memory 230 may be used to store data obtained from a user. For example, memory 230 may correspond to memory 130 of FIG. 1 . For example, memory 230 may be a volatile memory unit or units. For example, memory 230 may be a non-volatile memory unit or units. For example, memory 230 may be another form of computer-readable medium, such as a magnetic or optical disk. For example, the memory 230 may store data obtained based on an operation performed by the processor 210 (eg, an algorithm execution operation). For example, the memory 230 may store data obtained from the sensor 220 (eg, data regarding the user's walking).

According to one embodiment, the electronic device 200 may include a communication circuit 240. For example, communication circuit 240 may correspond to communication module 190 of FIG. 1 .

For example, communication circuitry 240 may be used for various radio access technologies (RATs). For example, the communication circuit 240 may be used to perform Bluetooth (Bluetooth) communication, wireless local area network (WLAN) communication, or ultra wideband (UWB) communication. For example, communications circuitry 240 may be used to perform cellular communications.

According to one embodiment, the electronic device 200 may include various components in addition to the components shown. For example, the electronic device 200 may include a display. The display can be used to display various screens. For example, a display can be used to output content, data, or signals on a screen. For example, the display may correspond to display module 160 in FIG. 1 . For example, the electronic device 200 may further include a global positioning system (GPS) circuit. GPS circuitry may be used to identify the location of the electronic device 200.

Figure 3 shows a simplified block diagram of a processor included in an electronic device, according to one embodiment.

Referring to FIG. 3 , the processor 210 may include a fall detection circuit 310, a fall risk identification circuit 320, and a fall notification circuit 330. The processor 210 can monitor whether a fall has occurred using the fall detection circuit 310. The processor 210 can predict the user's fall risk by using the fall risk identification circuit 320 to monitor the user's walking and analyze and learn the user's walking pattern before predicting the fall risk.

For example, the fall detection circuit 310 may include a fall motion analysis circuit 311, a fall environment analysis circuit 312, a fall sensitivity adjustment circuit 313, and a fall identification circuit 314. The processor 210 may use the fall motion analysis circuit 311 of the fall detection circuit 310 to identify the user's movement when detecting a fall. The processor 210 may use the fall environment analysis circuit 312 of the fall detection circuit 310 to identify the environment around the electronic device 200 (or the user) when detecting a fall. The processor 210 may use the fall sensitivity adjustment circuit 314 of the fall detection circuit 310 to change the sensitivity for fall identification when there is a high possibility that a user will fall. The processor 210 may use the fall identification circuit 314 of the fall detection circuit 310 to identify that a fall has occurred in the user based on information about the user's movement.

For example, the fall risk identification circuit 320 may include a walking environment identification circuit 321, a walking pattern learning circuit 322, a walking pattern analysis circuit 323, and a fall risk prediction circuit 324. The processor 210 may use the walking environment identification circuit 321 of the fall risk identification circuit 320 to identify the environment around the electronic device 200 (or the user) when the user is walking. The processor 210 can continuously learn the user's walking pattern when the user walks by using the walking pattern learning circuit 322 of the fall risk identification circuit 320. The processor 210 may use the walking pattern analysis circuit 323 of the fall risk identification circuit 320 to obtain and store information about the user's walking pattern. The processor 210 may use the fall risk prediction circuit 324 of the fall risk identification circuit 320 to identify the probability that a user will fall based on the walking environment and walking pattern.

For example, the fall notification circuit 330 may include a fall occurrence notification circuit 331 and a fall risk notification circuit 332. The processor 210 uses the fall occurrence notification circuit 331 of the fall notification circuit 330 to provide the user or another user with a notification indicating that a fall has occurred when the user falls. You can send a rescue signal through your contacts. The processor 210 may use the fall risk notification circuit 332 of the fall notification circuit 330 to provide a notification indicating that there is a high probability of a fall occurring to the user when the probability of a fall occurring is high.

FIG. 4 is a flowchart illustrating the operation of an electronic device, according to an embodiment.

Referring to FIG. 4 , in operation 410, the processor 210 may obtain first information about the first walking pattern and second information about the walking environment. For example, the processor 210 may use the sensor 220 (or at least one sensor) and/or the communication circuit 240 to collect first information about the first walking pattern of the user of the electronic device 200 and the user. Second information about the walking environment can be obtained.

According to one embodiment, the processor 210 may use the sensor 220 to obtain first information about the first walking pattern of the user of the electronic device 200. For example, the processor 210 may use the acceleration sensor 221 to obtain first information about the first walking pattern based on first data acquired during a designated time period. The processor 210 may acquire acceleration trends corresponding to each of the three axes during a designated time period. The processor 210 may identify the user's first walking pattern based on the obtained acceleration trends and the difference between sliding window summing. The operation of the processor 210 to identify the user's first walking pattern will be described later with reference to FIGS. 6A to 8.

According to one embodiment, the processor 210 may obtain second information about the walking environment of the user of the electronic device 200. For example, the processor 210 may operate on the user's data based on second data acquired using at least one of the acceleration sensor 221, the gyro sensor 222, the barometric pressure sensor 223, and the communication circuit 240. Second information about the walking environment can be obtained. For example, the second information may include information about the slope of the movement path of the electronic device 200, information about the movement state of the electronic device 200, and information about the weather during a designated time period. .

For example, the processor 210 may use at least a portion of the second data obtained using at least one of the acceleration sensor 221, the gyro sensor 222, and the barometric pressure sensor 223 as indicated by a plurality of parameters. By setting it as input data of a designated model (e.g., artificial intelligence model), information about the movement state of the electronic device 200 can be obtained. As an example, a plurality of parameters of a designated model may be set based on learning of third data identified according to the user's walking history. An embodiment in which the processor 210 obtains information about the movement state of the electronic device 200 using a designated model will be described later with reference to FIG. 9 .

For example, the processor 210 may obtain information about the weather for a designated time period from an external electronic device (eg, a server) using the communication circuit 240.

In operation 420, the processor 210 may identify a first value indicating a difference between the first walking pattern and the reference walking pattern. For example, the processor 210 identifies a first value representing the difference between the first gait pattern and the reference gait pattern based on the first information and third information about the reference gait pattern stored in memory 230. can do. For example, the processor 210 may identify a first degree of similarity between the first walking pattern and the reference walking pattern based on the first information and the third information.

According to one embodiment, the processor 210 may store third information about the reference walking pattern in the memory 230. For example, the reference walking pattern may mean the walking pattern of general users. As an example, the processor 210 may receive third information about the reference walking pattern from an external electronic device (eg, a server) using the communication circuit 240. The processor 210 may store the received third information in the memory 230. The third information may be obtained based on walking patterns related to a plurality of users stored in an external electronic device (eg, server). As an example, the third information about the standard walking pattern may be stored in the memory 230 of the electronic device 200.

According to one embodiment, the processor 210 may identify a first value indicating the difference between the first walking pattern and the reference walking pattern based on the first information and the third information. The processor 210 may identify values related to the first walking pattern. The processor 210 may identify values related to the reference walking pattern. The processor 210 determines the first walking pattern and A first value representing the difference between the reference walking patterns may be identified. The processor 210 may identify a first degree of similarity between the first walking pattern and the reference walking pattern based on the Euclidean distance between the values related to the first walking pattern and the values related to the reference walking pattern. For example, the first value indicating the difference between the first walking pattern and the reference walking pattern and the first similarity may be inversely proportional. The larger the first value representing the difference between the first walking pattern and the reference walking pattern, the smaller the first similarity may be. The smaller the first value indicating the difference between the first walking pattern and the reference walking pattern, the greater the first similarity may be.

In operation 430, the processor 210 may identify a second value indicating the difference between the first and second walking patterns. For example, the processor 210 may determine the first walking pattern based on the first information and the fourth information regarding the user's second walking pattern, which is stored in the memory 230 and identified based on the user's walking history. and a second value representing the difference between the second walking patterns may be identified. For example, the processor 210 may identify a second similarity between the first walking pattern and the second walking pattern based on the first information and the fourth information.

According to one embodiment, the processor 210 may store fourth information about the second walking pattern in the memory 230. The processor 210 may identify fourth information about the second walking pattern based on the user's walking history. For example, the processor 210 may perform learning about the user's walking pattern based on the user's walking history. The processor 210 may obtain fourth information about the second walking pattern based on learning about the user's walking pattern. The processor 210 may store the obtained fourth information in the memory 230. For example, the fourth information regarding the second walking pattern may be stored in the memory 230 of the electronic device 200.

For example, the processor 210 may identify a population containing values related to walking patterns according to a plurality of steps of the user, based on the user's walking history. As an example, the processor 210 may use the sensor 220 to identify the user's first steps. The processor 210 may identify feature values according to the first steps based on identifying that the number of first steps is greater than or equal to a specified number. The processor 210 may identify feature values for the user's second steps that occurred before the first steps were identified. Feature values for the second steps may be stored in the memory 230. For example, feature values for the second steps may be values learned according to the user's walking history.

The processor 210 may identify values related to the walking pattern according to the first steps, based on the characteristic values according to the first steps. The processor 210 may identify values related to the walking pattern according to the second steps, based on the characteristic values according to the second steps. The processor 210 may configure values related to the walking pattern according to the first steps and values related to the walking pattern according to the second steps into a population including values related to the walking pattern according to a plurality of steps.

For example, the processor 210 may identify at least a portion of the population according to information about fitness according to a plurality of steps, which is obtained based on the identified population. The processor 210 may perform learning about the user's walking pattern based on at least a portion of the population. A specific example of an operation for learning a user's walking pattern will be described later with reference to FIGS. 10 to 18.

According to one embodiment, the processor 210 may identify a second value indicating the difference between the first walking pattern and the second walking pattern based on the first information and the fourth information. The processor 210 may identify values related to the first walking pattern. The processor 210 may identify values related to the second walking pattern. Processor 210 may identify a second value representing the difference between the first and second walking patterns, based on the Euclidean distance between the values for the first walking pattern and the values for the second walking pattern. You can. The processor 210 may identify a second similarity between the first and second walking patterns based on the Euclidean distance between the values for the first walking pattern and the values for the second walking pattern. For example, the second value indicating the difference between the first and second walking patterns and the second similarity may be inversely proportional. The larger the second value representing the difference between the first and second walking patterns, the smaller the second similarity may be. The smaller the second value representing the difference between the first and second walking patterns, the greater the second similarity may be.

At operation 440, processor 210 may identify a threshold value associated with fall detection. For example, the processor 210 may identify a threshold value related to fall detection based on the first value, the second value, and the second information.

At operation 450, the processor 210 may perform fall detection. For example, processor 210 may perform fall detection based on a comparison between an identified threshold value and a value obtained through sensor 220 .

For example, a threshold value related to fall detection may include a reference value for determining whether a fall has occurred to the user. The value obtained through the sensor 220 may include a value related to the amount of impact, a value related to the amount of change in air pressure, and/or a value related to the time when the user's activity was stopped. As an example, the processor 210 may identify that a fall has occurred in the user based on identifying that the value for determining the user's fall is greater than or equal to a threshold value. For example, the thresholds associated with fall detection may include a first threshold related to the amount of impact, a second threshold related to the amount of change in barometric pressure, and/or a third threshold related to the duration of inactivity (or time during inactivity). It can be included.

For example, the processor 210 may identify that a fall has occurred in the user based on identifying that the value related to the amount of impact obtained through the sensor 220 is greater than or equal to the first threshold. For example, the processor 210 may identify that a fall has occurred in the user based on identifying that the value related to the change in air pressure obtained through the sensor 220 is greater than or equal to the second threshold. For example, the processor 210 may identify that a fall occurred in the user based on identifying that the time during which the user's activity was interrupted is greater than or equal to a third threshold.

For example, the processor 210 determines that the value related to the amount of impact obtained through the sensor 220 is greater than or equal to the first threshold value, and the value related to the change in air pressure obtained through the sensor 220 is equal to or greater than the second threshold value, Based on identifying that the time when the user's activity was interrupted is more than the third threshold, it can be identified that the user has fallen.

According to one embodiment, the processor 210 may identify a probability value of a user falling based on the first value, the second value, and the second information. The processor 210 may identify the threshold as one of a plurality of candidate threshold values based on the identified probability value. For example, the processor 210 may identify the risk of falling as one of 'low', 'moderate', 'high', and 'very high' based on the probability value of the user falling. The processor 210 may identify one of a plurality of candidate threshold values according to the risk of falling. For example, a plurality of candidate threshold values according to fall risk can be set as shown in Table 1.

Referring to Table 1, a plurality of candidate threshold values can be set according to the risk of falling. For example, if the risk of falling is 'low', the first threshold value regarding the amount of impact may be set to 20 [G]. If the risk of falling is 'low', the second threshold value regarding the amount of change in air pressure may be set to 0.4 [hPa]. If the risk of falling is 'low', the third threshold regarding the time to stop activity can be set to 60 [s](second). For example, if the risk of falling is 'normal', the first threshold value regarding the amount of impact may be set to 20 [G]. If the risk of falling is 'normal', the second threshold value regarding the amount of change in air pressure may be set to 0.4 [hPa]. If the risk of falling is 'moderate', the third threshold regarding the time to stop activity can be set to 60 [s](second). For example, if the risk of falling is 'high', the first threshold value regarding the amount of impact may be set to 15 [G]. If the risk of falling is 'high', the second threshold value regarding the amount of change in air pressure may be set to 0.32 [hPa]. If the risk of falling is 'high', the third threshold regarding the time to stop activity can be set to 40 [s](second). For example, if the risk of falling is 'very high', the first threshold value regarding the amount of impact may be set to 10 [G]. If the risk of falling is 'very high', the second threshold value regarding the amount of change in air pressure may be set to 0.32 [hPa]. If the risk of falling is 'very high', the third threshold regarding the time to stop activity can be set to 40 [s](second).

According to one embodiment, the processor 210 may identify a probability value of a fall occurring in the user and identify the risk of falling based on the identified probability value. The processor 210 may change the sensitivity of the fall detection algorithm by changing the threshold value related to fall detection according to the fall risk. The processor 210 can quickly identify that a fall has occurred in a user by changing threshold values (eg, first threshold, second threshold, and third threshold) related to fall detection.

For example, the processor 210 is connected to the electronic device 200, based on the identified probability value and the second information, and provides a notification to warn the user of the risk of falling through an external electronic device worn by the user. To do so, a signal for triggering the external electronic device may be transmitted to the external electronic device.

FIG. 5 is a flowchart illustrating the operation of an electronic device, according to an embodiment.

Referring to FIG. 5 , in operation 510, the processor 210 may identify data regarding the user's walking. For example, the processor 210 may identify data regarding the acceleration of the electronic device 200 using the acceleration sensor 221. For example, the processor 210 may use the gyro sensor 222 to identify data regarding the angular velocity of the electronic device 200. For example, processor 210 may use barometric pressure sensor 223 to identify data regarding barometric pressure (or altitude of electronic device 200).

At operation 520, processor 210 may identify the user's gait. For example, the processor 210 may identify the user's gait based on data about the user's gait.

According to one embodiment, the processor 210 may identify the user's steps based on data about the user's steps. The processor 210 may identify the user's steps based on data on three-axis acceleration. Processor 210 may identify the user's gait based on identifying that the user's steps are more than a specified number of times.

In operation 530, the processor 210 may identify the amount of change in air pressure based on identifying the user's gait. For example, the processor 210 may identify the amount of change in air pressure through data identified using the air pressure sensor 223, based on identifying the user's walking. For example, data identified using the barometric pressure sensor 223 may be used to identify the altitude of the electronic device 200. The processor 210 may identify whether the altitude of the electronic device 200 changes based on data identified using the barometric pressure sensor 223.

In operation 540, the processor 210 may identify whether the amount of change in air pressure is less than the first amount of change in air pressure. The processor 210 may identify whether the amount of change in atmospheric pressure during a designated time period is less than the first amount of change in atmospheric pressure. The processor 210 may identify that the atmospheric pressure decreases during the specified time interval, based on identifying that the amount of change in atmospheric pressure during the specified time section is less than the first amount of change in atmospheric pressure.

In operation 550, if the amount of change in air pressure is less than the first amount of change in air pressure, the processor 210 may identify that the user is walking uphill. The processor 210 may identify that the user is walking uphill based on identifying that the amount of change in air pressure is less than the first amount of change in air pressure.

In operation 560, when the amount of change in air pressure is greater than or equal to the first amount of change in air pressure, the processor 210 may identify whether the amount of change in air pressure is greater than or equal to the second amount of change in air pressure. For example, the processor 210 may identify whether the amount of change in air pressure is greater than or equal to the second amount of change in air pressure, based on identifying that the amount of change in air pressure is greater than or equal to the first amount of change in air pressure. For example, the processor 210 may identify whether the amount of change in atmospheric pressure during a designated time period is greater than or equal to the second amount of change in atmospheric pressure. The processor 210 may identify that the atmospheric pressure increases during the specified time interval based on identifying that the amount of change in atmospheric pressure during the specified time section is greater than or equal to the second amount of change in atmospheric pressure.

In operation 570, when the amount of change in air pressure is greater than or equal to the second amount of change in air pressure, the processor 210 may identify that the user is walking downhill. The processor 210 may identify that the user is walking downhill based on identifying that the amount of change in air pressure is greater than or equal to the second amount of change in air pressure.

In operation 580, when the amount of change in air pressure is less than the second amount of change in air pressure, the processor 210 may identify that the user is walking on level ground. For example, processor 210 may identify that the user is walking on level ground based on identifying that the amount of change in air pressure is less than the second amount of change in air pressure. For example, the processor 210 may identify that the user is walking on level ground based on identifying that the amount of change in air pressure is greater than or equal to the first amount of change in air pressure and less than the second amount of change in air pressure during a designated time period.

6A to 6C show examples of trends for identifying a user's walking environment, according to an embodiment.

7A to 7C show examples of trends for identifying a user's walking environment, according to an embodiment.

Figure 8 shows an example of a trend for identifying a user's walking environment, according to one embodiment.

Referring to FIGS. 6A to 6C , trends 610 to 630 represent changes in acceleration of the electronic device 200 over time. The processor 210 may identify the acceleration of the electronic device 200 in three axes using the acceleration sensor 221. The processor 210 may identify the trend 610 by monitoring acceleration in the first direction (or x-axis direction) over time. The processor 210 may identify the trend 620 by monitoring acceleration in the second direction (or y-axis direction) over time. The processor 210 may identify the trend 630 by monitoring acceleration in the third direction (or z-axis direction) over time. The processor 210 can identify the magnitude of acceleration in three axes. The processor 210 may identify a trend indicating the magnitude of acceleration in three axes. For example, the processor 210 can identify the magnitude of acceleration in three axes using Equation 1.

Referring to Equation 1, a _NORM is the magnitude of acceleration in three axes. x is the magnitude of acceleration in the first direction. y is the magnitude of acceleration in the second direction. z is the magnitude of acceleration in the third direction. The processor 210 may identify a trend indicating the magnitude of acceleration over time based on identifying the magnitude of acceleration in three axes at a specific point in time.

According to one embodiment, the processor 210 may identify a difference value of sliding window summing based on acceleration trends in three axes over time. The processor 210 may identify a trend 640 indicating a change in the difference value of the sum of movement sections over time. For example, the processor 210 may identify the movement section sum using Equation 2. The processor 210 can identify the difference value of the sum of the movement sections using Equation 3.

Referring to Equation 2, SWS(k) represents the sum of the movement sections for the magnitude of acceleration in three axes. The processor 210 may identify SWS(k) by identifying the sum of the movement sections for the magnitude of acceleration from time point k-N+1 to time k.

Referring to Equation 3, SWS _diff (k) represents the difference value of the sum of the movement sections for the magnitude of acceleration in the three axes. The processor 210 may identify the difference between the sum of the movement sections at time point k-N+1 as the difference value of the sum of the movement sections at time point k.

According to one embodiment, the processor 210 may identify the trend 640 by setting the k and N values so that the trend of the difference value of the sum of the movement sections is configured as a sin waveform. The processor 210 may identify at least one zero-crossing point based on the trend 640. Time point 641, time point 642, and time point 643 may be examples of zero crossing points.

For example, the processor 210 may identify a step based on the zero crossing point. The processor 210 divides the time interval into a time interval representing one step between a first zero crossing point (e.g., time point 643) and a second zero crossing point (e.g., time point 642) identified before the first zero crossing point. can be identified. The processor 210 may identify the number of zero crossing points within the trend 640 as the number of steps. The processor 210 may identify that the user is walking based on identifying that the number of zero crossing points within a specified time interval is greater than or equal to a specified number.

According to one embodiment, the processor 210 may identify the amount of change in air pressure based on identifying that the user is walking. The processor 210 may identify a trend 650 of barometric pressure over time within a designated time interval. The processor 210 may identify the amount of change in air pressure within a specified time period based on the trend 650. Based on the trend 650, the processor 210 may identify that the amount of change in atmospheric pressure is greater than or equal to the first amount of change in atmospheric pressure and less than the amount of change in second atmospheric pressure within the specified time interval. The processor 210 may identify that the user is walking on level ground based on identifying that the amount of change in air pressure is greater than or equal to the first amount of change in air pressure and less than the second amount of change in air pressure within the designated time interval. For example, processor 210 may identify that the user is walking on level ground based on identifying that the barometric pressure is maintained within a specified time period.

Referring to FIGS. 7A to 7C , trends 710 to 730 represent changes in acceleration of the electronic device 200 over time. Trend 710 may correspond to trend 610 in FIG. 6A. Trend 720 may correspond to trend 620 in FIG. 6A. Trend 730 may correspond to trend 630 in FIG. 6A. The processor 210 can identify the trend 740 indicating a change in the difference value of the sum of the movement sections over time by identifying the magnitude of acceleration in the three axes based on the trends 710 to 730. Trend 740 may correspond to trend 640 in FIG. 6B.

According to one embodiment, the processor 210 may identify at least one zero crossing point based on the trend 740. The processor 210 may identify the number of zero crossing points within the trend 740 as the number of steps. The processor 210 may identify that the user is walking based on identifying that the number of zero crossing points within a specified time interval is greater than or equal to a specified number.

According to one embodiment, the processor 210 may identify the amount of change in air pressure based on identifying that the user is walking. The processor 210 may identify a trend 750 of barometric pressure over time within a designated time interval. Trend 750 may correspond to trend 650 in FIG. 6C. Based on the trend 750, the processor 210 may identify that the amount of change in air pressure within the specified time period is greater than or equal to the second amount of change in air pressure. The processor 210 may identify that the user is walking downhill based on identifying that the amount of change in air pressure within the specified time interval is greater than or equal to the second amount of change in air pressure. For example, processor 210 may identify that the user is walking downhill based on identifying an increase in barometric pressure within a specified time period.

Although not shown, the processor 210 may identify that the amount of change in atmospheric pressure is less than the first amount of change in atmospheric pressure within the specified time interval. The processor 210 may identify that the user is walking uphill based on identifying that the amount of change in air pressure within the specified time interval is less than the first amount of change in air pressure. For example, processor 210 may identify that the user is walking uphill based on identifying a decrease in barometric pressure within a specified time period.

Referring to FIG. 8, the processor 210 can identify a trend 810 indicating a change in the difference value of the sum of movement sections over time by identifying the magnitude of acceleration in three axes. Trend 810 may correspond to trend 640 in FIG. 6B or trend 740 in FIG. 7B.

According to one embodiment, the processor 210 may identify at least one zero crossing point based on the trend 810. Processor 210 may identify the time interval between zero crossing points. For example, processor 210 may identify time interval 811, time interval 812, and time interval 813. The processor 210 may identify a plurality of time sections including a time section 811, a time section 812, and a time section 813.

According to one embodiment, the processor 210 may identify the walking frequency based on a plurality of time sections. The processor 210 may identify the walking frequency based on a representative value (eg, average value or median value) of a plurality of time intervals. For example, the processor 210 may identify a representative value of a plurality of time sections as the time section 811. The processor 210 may identify the walking frequency based on the time interval 811. For example, the processor 210 may identify the walking frequency using Equation 4.

Referring to Equation 4, f is the walking frequency. te is a representative value of a plurality of time intervals. The processor 210 may identify the user's walking speed by identifying the walking frequency using representative values of a plurality of time sections.

Figure 9 shows an example of an operation of an electronic device according to an embodiment.

Referring to FIG. 9, in operation 910, the processor 210 may obtain second data. For example, the processor 210 may acquire second data using at least one of the sensor 220 and/or the communication circuit 240. For example, the processor 210 may acquire second data using at least one of the acceleration sensor 221, the gyro sensor 222, the barometric pressure sensor 223, and the communication circuit 240. For example, the processor 210 may obtain second data and/or third data based on preprocessing data acquired through the sensor 220. For example, the second data and third data may include at least one of a change in posture for hand motion, frequency characteristics, magnitude of movement for hand motion, and/or direction. As an example, hand motion may mean a state in which the user holds (or grips) the electronic device 200. The processor 210 identifies at least one of a change in posture for hand motion, frequency characteristics, size, and/or direction of movement for hand motion by identifying movement while the user is holding the electronic device 200. can do.

For example, the second data and the third data are data about the acceleration of the electronic device 200 acquired through the acceleration sensor 221, and data about the angular velocity of the electronic device 200 obtained through the gyro sensor 222. It may include at least one of data, data about the air pressure around the electronic device 200 obtained through the air pressure sensor 223, and information about the weather obtained from an external electronic device through the communication circuit 240.

As an example, second data may mean data acquired at a second time point. As an example, third data may mean data acquired at a first time point earlier than the second time point.

In operations 920 and 930, the processor 210 may learn second data and/or third data. The processor 210 may set a plurality of parameters of the designated model 940 based on learning the second data and/or the third data. For example, designated model 940 may include an artificial intelligence model. For example, the designated model 940 is configured based on machine learning, such as decision trees (DTs), support vector machines (SVMs), k-nearest neighbors (KNNs), and/or multi-layer perceptrons (MLPs). or designed).

For example, the third data may be obtained according to the user's walking history. The processor 210 may obtain third data based on the user's walking history. The first time point at which the third data is acquired may be different from the second time point at which the second data is acquired. The first time point at which the third data is acquired may be earlier than the second time point at which the second data is acquired. For example, the processor 210 may set (or change or update) the designated model 940 by learning third data acquired at the first time point. The processor 210 may set (or change, or update) a plurality of parameters of the designated model 940 using the third data acquired at the first time point. The processor 210 may set the designated model 940 by learning the second data acquired at the second time point. The processor 210 may set (or change, or update) a plurality of parameters of the designated model 940 using the second data acquired at the second time point.

According to one embodiment, the processor 210 may use at least part or all of the second data to learn the designated model 940. The processor 210 may set at least part or all of the second data as input data of the designated model 940. For example, the processor 210 may learn the second data while the operation mode of the designated model 940 is a learning mode (or training phase). For example, the processor 210 may set the second data as input data of the designated model 940 while the operation mode of the designated model 940 is an identification mode (or recognition phase).

In operation 950, the processor 210 may obtain information about the movement state of the electronic device 200. For example, the processor 210 may obtain information about the movement state of the electronic device 200 based on setting at least part or all of the second data as input data of the designated model 940. For example, information about the movement state of the electronic device 200 may include information about the posture in which the user carries the electronic device 200.

For example, the processor 210 may identify that the user is holding the electronic device 200 using his or her hand, based on setting at least part or all of the second data as input data of the designated model 940. You can.

For example, the processor 210 may identify that the user is carrying the electronic device 200 using a pocket, based on setting at least some or all of the second data to the input data of the designated model 940. You can.

For example, based on setting at least part or all of the second data as input data of the designated model 940, the processor 210 determines that the user swings his arm while holding the electronic device 200. It can be identified that it exists.

FIG. 10 is a flowchart illustrating the operation of an electronic device, according to an embodiment.

Referring to FIG. 10, in operation 1010, the processor 210 may identify the user's first steps. For example, the processor 210 may use the acceleration sensor 221 to identify the user's first steps based on the magnitude of acceleration in three axes. For example, the processor 210 creates a trend (e.g., trend 640 in FIG. 6B, trend 740 in FIG. 7B) indicating a change in the difference value of the sum of movement sections over time, based on the magnitude of acceleration in the three axes. )) can be identified. The processor 210 may identify the user's first steps based on at least one zero crossing point related to the identified trend.

According to one embodiment, the processor 210 may identify the first steps by excluding steps identified as outliers among the user's steps. For example, the processor 210 may identify the first steps by excluding outliers among the user's steps based on the z-score.

In operation 1020, the processor 210 may identify whether the number of first steps is greater than or equal to a specified number. For example, the processor 210 may identify whether the number of first steps is more than a specified number (eg, 12) to identify a valid walking section. The processor 210 identifies whether the user's steps occur continuously more than a specified number of times, based on a trend indicating a change in the difference value of the sum of the movement sections over time, which is identified based on the magnitude of acceleration in the three axes. can do. Depending on the embodiment, the processor 210 may identify the number of first steps as at least one valid walking section according to a designated number of steps.

According to one embodiment, the processor 210 may perform operation 1010 based on identifying that the number of first steps is not more than a specified number. For example, processor 210 may re-identify the user's first steps based on identifying that the number of first steps is not more than a specified number.

In operation 1030, the processor 210 may identify feature values according to the first steps. For example, the processor 210 may identify feature values according to the first steps based on identifying that the number of the first steps is a specified number or more.

According to one embodiment, the feature values may include values representing a walking pattern or walking stability. For example, the feature values may include values for the magnitude of acceleration in three axes. For example, feature values include minimum value, maximum value, average value, standard deviation, root mean squared (RMS) value, peak-to-peak (P2P) value, peak count value, signal magnitude area (SMA) value, and MAD ( It may include at least one of a mean amplitude deviation) value and a COV (coefficient of variance) value.

At operation 1040, processor 210 may identify the population. For example, the processor 210 may identify a population based on feature values according to the first steps. According to one embodiment, the population may be composed of values related to the walking pattern according to the user's plural steps. For example, the processor 210 may identify feature values according to first steps and feature values according to second steps that occurred before the first steps were identified. The processor 210 may identify values related to the walking pattern according to the first steps, based on the characteristic values according to the first steps. The processor 210 may identify values related to the walking pattern according to the second steps, based on the characteristic values according to the second steps. The processor 210 may configure the values related to the walking pattern according to the first steps and the values related to the walking pattern according to the second steps into a population including values related to the walking pattern according to a plurality of steps. . The processor 210 may perform learning about the user's walking pattern based on the population. For example, the processor 210 may perform feature scaling by normalizing the population. The processor 210 may perform learning about the user's walking pattern based on feature-scaled data.

Hereinafter, specific examples of operations of the processor 210 according to operations 1010 to 1040 will be described.

Figure 11 shows an example of an operation of an electronic device according to an embodiment.

Figure 12 shows an example of an operation of an electronic device according to an embodiment.

Referring to FIG. 11 , the processor 210 may use the acceleration sensor 221 to identify trends indicating acceleration in three axes. For example, the processor 210 may identify a trend 1110 indicating acceleration in the first direction (or x-axis direction). The processor 210 may identify a trend 1120 indicating acceleration in the second direction (or y-axis direction). The processor 210 may identify a trend 1130 indicating acceleration in the third direction (or z-axis direction). The processor 210 may identify a trend 1140 indicating a change in the difference value of the sum of movement sections based on the trends 1110 to 1130.

According to one embodiment, the processor 210 may identify at least one zero crossing point based on the trend 1140. Processor 210 may identify the user's steps based on identifying at least one zero crossing point. The processor 210 may identify a valid walking section based on the user's steps.

According to one embodiment, the processor 210 may identify a valid walking section every designated number of times (eg, 10 times). For example, the processor 210 may identify a valid walking section 1151, a valid walking section 1152, and a valid walking section 1153. The processor 210 may identify a valid walking section every designated number of times, based on identifying that the number of steps of the user is greater than or equal to a designated number of times.

According to one embodiment, the processor 210 may identify first steps among the steps constituting the effective walking section 1151, excluding the step 1141 identified as an outlier. The processor 210 may identify feature values according to the first steps. The processor 210 may identify characteristic values of steps constituting the effective walking section 1152 and the effective walking section 1153.

Referring to FIG. 12, the processor 210 can identify 10 feature values per step. The processor 210 may configure 10 feature values according to the first steps consisting of 10 steps into a matrix 1210. The matrix 1210 may be composed of 10X10 (10 by 10). The feature values constituting the matrix 1210 are illustrative and may be changed.

According to one embodiment, the processor 210 may identify feature values based on the trend 1140. The processor 210 may identify feature values using differential values of the sum of movement sections constituting one step. For example, the processor 210 may divide a trend indicating a change in the difference value of the sum of movement sections constituting one step into discrete values (eg, n) according to unit time intervals. The processor 210 may identify feature values using the separated values.

For example, the first column may mean the minimum value (min). The processor 210 may identify the minimum value of the difference values of the sum of the movement sections constituting one step as the value of the first column.

For example, the second column may mean the maximum value (max). The processor 210 may identify the maximum value of the difference values of the sum of the movement sections constituting one step as the value of the second column.

For example, the third column may mean the average value. The processor 210 may identify the average value of the difference values of the sum of the movement sections constituting one step as the value of the third column.

For example, the fourth column may mean standard deviation. The processor 210 may identify the standard deviation of the difference values of the sum of movement sections constituting one step as the value in the fourth column.

For example, the fifth column may mean the root mean squared (RMS) value. The processor 210 may identify the RMS value of the difference values of the sum of the movement sections constituting one step as the value in the fifth column.

For example, the sixth column may mean a P2P (peak-to-peak) value. The processor 210 may identify the difference between the peak values of the trend representing the difference values of the sum of the movement sections constituting one step as the value in the sixth column.

For example, the 7th column may mean the peak count value. The processor 210 may identify the number of peak values of the trend representing the difference values of the sum of the movement sections constituting one step as the value in the seventh column.

For example, the 8th column may mean a signal magnitude area (SMA) value. The processor 210 may identify the SMA value of the trend representing the difference values of the sum of the movement sections constituting one step as the value in the eighth column.

For example, the 9th column may refer to the mean amplitude deviation (MAD) value. The processor 210 may identify the MAD value of the trend representing the difference values of the sum of the movement sections constituting one step as the value in the ninth column.

For example, the 10th column may indicate a coefficient of variance (COV) value. The processor 210 may identify the coefficient of variance (COV) value of the difference values of the sum of movement sections constituting one step as the value in the tenth column.

FIG. 13 is a flowchart illustrating the operation of an electronic device, according to an embodiment.

Referring to FIG. 13, in operation 1310, the processor 210 may identify values related to the walking pattern according to the first steps. For example, the processor 210 may identify values related to a walking pattern according to the first steps, based on feature values according to the first steps. For example, the processor 210 may multiply a matrix constructed based on feature values according to the first steps by a designated matrix to identify a first matrix composed of values related to the walking pattern according to the first steps.

In operation 1320, the processor 210 may identify values related to the walking pattern according to the second steps. For example, the processor 210 may identify values related to a walking pattern according to the second steps, based on feature values according to the second steps. For example, the processor 210 may multiply a matrix constructed based on feature values according to the second steps by a designated matrix to identify a second matrix composed of values related to the walking pattern according to the second steps. For example, values related to the walking pattern according to the second steps may be values learned according to the user's walking history.

According to one embodiment, as the feature values of the first steps and the feature values of the second steps increase, the amount of computation increases and the learning effect of the designated model may decrease. Accordingly, the processor 210 can reduce the dimension of the walking pattern by identifying various feature values as feature values according to the walking pattern.

At operation 1330, processor 210 may construct the population. For example, the processor 210 divides the values related to the walking pattern according to the first steps and the values related to the walking pattern according to the second steps into a population containing the values related to the walking pattern according to the plurality of steps. It can be configured.

For example, the processor 210 may identify values related to the walking pattern according to the first steps and values related to the walking pattern according to the second steps as values related to the walking pattern according to the plurality of steps. The processor 210 may express a population including values related to walking patterns according to a plurality of steps as a third matrix.

In operation 1340, the processor 210 may identify at least a portion of the population based on information about fitness according to a plurality of steps. For example, the processor 210 may identify at least a portion of the population based on information about fitness according to a plurality of steps, which is obtained based on the population.

According to one embodiment, the processor 210 may obtain information about the fitness of a plurality of steps based on the population. For example, the processor 210 may identify a representative value of each column among the population represented by the third matrix. As an example, the processor 210 may identify the mean value of each column among the population represented by the third matrix as a representative value. The processor 210 may obtain information about the degree of fitness according to a plurality of steps based on identifying the average value of each column as a representative value among the population represented by the third matrix. Information about fitness according to a plurality of steps can be expressed as a fourth matrix.

According to one embodiment, the processor 210 may identify at least a portion of the population based on information about fitness according to a plurality of steps. The processor 210 may identify at least a portion of the population in descending order of suitability according to a plurality of steps.

In operation 1350, the processor 210 may perform learning about the walking pattern. For example, the processor 210 may perform learning about the user's walking pattern based on at least a portion of the population.

According to one embodiment, the processor 210 may update the walking pattern by repeating learning about the walking pattern. The processor 210 may identify that the walking pattern has been sufficiently learned based on identifying that the amount of change in the walking pattern resulting from learning the walking pattern is within a reference range. Processor 210 may stop learning the gait pattern based on identifying that the gait pattern has been sufficiently learned.

Specific examples of operations according to operations 1310 to 1350 will be described later with reference to FIGS. 14 to 18.

Figure 14 shows an example of a designated matrix according to one embodiment.

Figure 15 shows an example of a matrix representing a population according to one embodiment.

Figure 16 shows an example of a matrix representing information on fitness according to an embodiment.

Figure 17 shows an example of a matrix representing at least a portion of the population according to one embodiment.

Figure 18 shows an example of a learning result for a walking pattern according to an embodiment.

Referring to FIG. 14, the processor 210 may identify the matrix 1410. For example, the matrix 1410 may be stored in the memory 230. For example, the matrix 1410 may be modeled in advance. Depending on the embodiment, the processor 210 may receive the matrix 1410 from an external electronic device (eg, a server) connected to the electronic device 200.

According to one embodiment, the matrix 1410 may be used to identify values related to the walking pattern according to the first steps. Matrix 1410 may be used to identify values related to the walking pattern according to the second steps.

Referring to FIG. 15, the processor 210 multiplies a matrix representing feature values for the first steps (e.g., the matrix 1210 of FIG. 12) by the matrix 1410, thereby creating a walking pattern according to the first steps. Values related to can be identified. The processor 210 may represent values related to the walking pattern according to the first steps as a matrix 1512. For example, the number of first steps may be 10. Matrix 1512 may be composed of 10X3.

The processor 210 may identify values related to the walking pattern according to the second steps by multiplying the matrix 1410 by the matrix representing the feature values for the second steps. The processor 210 may represent values related to the walking pattern according to the second steps as a matrix 1511. For example, the number of second steps may be 10. Matrix 1511 may be composed of 10X3. For example, the second steps may occur before the first steps are identified. For example, the second steps may be steps learned in advance before the first steps are identified.

According to one embodiment, the processor 210 may configure a population. The processor 210 may configure values related to the walking pattern according to the first steps and values related to the walking pattern according to the second steps into a population including values related to the walking pattern according to a plurality of steps. For example, the processor 210 combines a matrix 1512 containing values related to a walking pattern according to first steps and a matrix 1511 containing values related to a walking pattern according to second steps, Matrix 1510 can be identified.

According to one embodiment, the matrix 1510 may be composed of values related to walking patterns according to a plurality of steps. A row of the matrix 1510 may represent a plurality of steps. The multiple steps may be 20. Matrix 1510 may be composed of 20X3.

Referring to FIG. 16, the processor 210 can represent each row in the matrix 1510 in a three-dimensional coordinate system. Column 1 of the matrix 1510 may represent the coordinate value of the x-axis. Column 2 of the matrix 1510 may mean coordinate values of the y-axis. Column 3 of the matrix 1510 may represent coordinate values of the z-axis. For example, row 1 of matrix 1510 may correspond to the first coordinate. Row 2 of matrix 1510 may correspond to the second coordinate. The processor 210 may identify first to twentieth coordinates based on the matrix 1510. The processor 210 may identify the average coordinate of the first to twentieth coordinates. The processor 210 may identify the Euclidean distance between each of the first to twentieth coordinates and the average coordinate. The processor 210 may identify information about the degree of fitness according to a plurality of steps by identifying the Euclidean distance between each coordinate from the first coordinate to the twentieth coordinate and the average coordinate. The processor 210 may represent information about fitness according to a plurality of steps as a matrix 1610. For example, each row of the matrix 1610 may mean fitness for each step. As an example, row 1 of the matrix 1610 may mean the degree of fitness for the first step of the second steps.

Referring to FIG. 17, the processor 210 may identify at least a portion of the population based on information about fitness according to a plurality of steps. For example, the processor 210 may identify at least a portion of the population by identifying the top 10 steps with high fitness. The processor 210 may represent values related to walking patterns according to the top 10 steps with high suitability as a matrix 1710.

Referring to FIG. 18, the processor 210 may learn about the user's walking pattern by performing the operations according to FIGS. 14 to 17.

According to one embodiment, the processor 210 may identify 10 first coordinates 1810 corresponding to the matrix 1710. The processor 210 may identify the second coordinates 1820 by performing learning on the walking pattern using the values related to the walking pattern included in the matrix 1710 and the newly acquired walking pattern values. there is. The processor 210 may identify the Euclidean distance between the representative value of the first coordinates 1810 and the second coordinates 1820. The processor 210 may identify the Euclidean distance between the representative value of the first coordinates 1810 and the second coordinates 1820 as the amount of change in the walking pattern according to learning. The processor 210 may identify whether the amount of change in the walking pattern due to learning is within a reference range.

According to one embodiment, the processor 210 may perform learning on the walking pattern whenever a valid walking section is identified. The processor 210 can evolutionary learn the user's walking pattern. For example, the processor 210 may repeat learning of the walking pattern based on identifying that the amount of change in the walking pattern resulting from learning is outside the reference range.

For example, the processor 210 may identify third coordinates 1830 according to learning about the walking pattern. The processor 210 may identify the Euclidean distance between the representative values of the second coordinates 1820 and the representative values of the third coordinates 1830 as the amount of change in the walking pattern due to learning. The processor 210 may identify that the amount of change in the walking pattern due to learning is outside the reference range. The processor 210 may identify fourth coordinates according to learning about the walking pattern. The processor 210 may identify the Euclidean distance between the representative values of the third coordinates 1830 and the representative values of the fourth coordinates 1840 as the amount of change in the walking pattern due to learning. The processor 210 may identify that the amount of change in the walking pattern due to learning is within the reference range. The processor 210 may identify that the walking pattern has been sufficiently learned based on identifying that the amount of change in the walking pattern due to learning is within the reference range. Processor 210 may stop learning the gait pattern based on identifying that the gait pattern has been sufficiently learned.

Figure 19 shows an example of an operation mode of a processor according to an embodiment.

Referring to FIG. 19 , the processor 210 may operate in one of a first mode 1910, a second mode 1920, a third mode 1930, and a fourth mode 1940. For example, the processor 210 may learn a walking pattern based on the operation mode.

According to one embodiment, the processor 210 may initialize the fourth information about the user's walking history and the second walking pattern stored in the memory 230 based on the first mode 1910. For example, the second walking pattern may be identified based on the user's walking history. The second walking pattern may mean a learned walking pattern. For example, in the first mode 1910, the processor 210 may operate without learning the walking pattern. For example, the first mode 1910 may be referred to as an idle mode (or idle state).

According to one embodiment, the processor 210 may obtain data about the user's walking pattern using the sensor 220 based on the second mode 1920. For example, the processor 210 may acquire data about the user's walking pattern in the second mode 1920 to learn the walking pattern. For example, in the second mode 1920, the processor 210 may identify a valid walking section. The processor 210 may obtain data about the walking pattern by identifying characteristic values related to steps within the effective walking section.

According to one embodiment, the processor 210 may learn data about the user's walking pattern based on the third mode 1930. For example, in the third mode 1930, the processor 210 may learn data about the walking pattern acquired while operating in the second mode 1920. When sufficient data about the walking pattern is acquired for learning, the processor 210 may learn the acquired data about the walking pattern in the third mode 1930. For example, the processor 210 may update the walking pattern by learning the user's normal walking pattern. The processor 210 may identify the learned walking pattern as the second walking pattern.

According to one embodiment, the processor 210 may stop learning data about the user's walking pattern based on the fourth mode 1940. For example, the processor 210 may stop the operation of learning data about the user's walking pattern based on identifying that the amount of change in the walking pattern due to learning is within the reference range.

According to one embodiment, the processor 210 may set the operation mode of the processor 210 to the first mode 1910 based on identifying that the user of the electronic device 200 has changed. The processor 210 may initialize fourth information about the second walking pattern, which is the walking pattern learned in the first mode 1910. As an example, in the first mode, the processor 210 may identify that the user has changed based on identifying that at least one of the user's gender and name has changed.

According to one embodiment, while operating in the first mode 1910, the processor 210 changes the operating mode of the processor 210 from the first mode 1910 to the second mode in response to identifying a valid walking segment. (1920).

According to one embodiment, the processor 210, while operating in the second mode 1920, in response to identifying that sufficient data regarding the gait pattern has been obtained to learn, switches the processor 210 to a second mode of operation. You can change from mode 1920 to third mode 1930.

According to one embodiment, the processor 210 changes the operating mode of the processor 210 from the third mode 1930 to the second mode in response to the learning of the gait pattern being completed while operating in the third mode 1930. You can change it to mode (1920). According to one embodiment, while operating in the third mode 1930, the processor 210 changes the operation mode of the processor 210 from the third mode 1930 to the second mode ( 1920). For example, the processor 210 may change the operation mode of the processor 210 from the third mode 1930 to the second mode 1920 based on identifying that the amount of change in the walking pattern is within the reference range. For example, the processor 210 changes the operation mode of the processor 210 from the third mode 1930 to the second mode ( 1920). For example, the processor 210 may change the operating mode of the processor 210 from the third mode 1930 to the second mode 1920 based on identifying that the time at which the gait pattern was learned is more than the reference time. there is.

According to one embodiment, the processor 210 changes the operating mode of the processor 210 from the fourth mode 1940 based on identifying that the user's body profile has changed while operating in the fourth mode 1940. You can change to the second mode (1920). According to one embodiment, while operating in the fourth mode 1940, the processor 210 changes the operation mode of the processor 210 to the fourth mode 1940 based on identifying that the amount of change in the walking pattern is outside the reference range. ) can be changed to the second mode (1920).

Figures 20A and 20B show an example in which values for a walking pattern according to an embodiment are displayed as three-dimensional coordinates.

According to one embodiment, the processor 210 determines that since each user has a different walking pattern (or walking habit), a fall may occur even if the user's walking pattern is different from the reference walking pattern (e.g., a general user's walking pattern). You may not judge that the probability is high. The processor 210 may change the probability of a fall occurring depending on the user's walking environment.

According to one embodiment, the processor 210 may include a first value indicating the difference between the user's first walking pattern and the reference walking pattern, the user's first walking pattern and the user's second walking pattern (e.g., a learned walking pattern). ) Based on the second value representing the difference between the two and the second information about the user's walking environment, a probability value of a fall occurring in the user may be identified.

For example, the processor 210 may identify the first similarity based on a first value indicating the difference between the first walking pattern and the reference walking pattern. The processor 210 may identify the second similarity based on a second value indicating the difference between the first and second walking patterns. The processor 210 may identify a probability value of a fall occurring in the user based on the first similarity, the second similarity, and second information about the user's walking environment.

For example, the processor 210 can use Equation 5 to identify the probability that a user will fall.

Referring to Equation 5, S is the probability value that a fall will occur in the user. S' can be set based on S ₁ . S ₁ is the degree of similarity between the second walking pattern and the reference walking pattern. If S ₁ is greater than the threshold (thrd in Equation 5), S' may be set to 0. If S ₁ is below the threshold, S' may be set to S ₂ . S ₂ is the first degree of similarity between the first walking pattern and the reference walking pattern. S ₃ is the second similarity between the first walking pattern and the second walking pattern. E is a value for the walking environment identified based on the second information. α(alpha), β(beta), and γ(gamma) are coefficients. For example, the processor 210 may identify a value (E) for the walking environment based on the second information. The processor 210 may identify a value (E) for the walking environment based on weather, slope, walking frequency (or walking speed), and/or the movement state of the electronic device 200. For example, the processor 210 may identify a value (E) for the walking environment based on a fuzzy set. For example, a fuzzy set can be constructed as shown in Table 2.

Referring to Table 2, the processor 210 can configure fuzzy sets. The set W may contain elements for weather. The set S may contain elements for gradients. The set F may contain an element for walking frequency. The set P may contain elements for movement states. The processor 210 may identify at least some of the elements of the set W, the set S, the set F, and the set P based on fuzzy inference according to the fuzzy membership function. The processor 210 may identify a value (E) for the walking environment based on the identified elements.

Referring to FIG. 20A, the processor 210 may identify first coordinates 2010 according to values related to the first walking pattern, which is the current walking pattern. For example, the current walking pattern may be obtained in a normal walking state. The processor 210 may identify second coordinates 2020 according to values related to the second walking pattern, which is a reference walking pattern. The processor 210 determines the similarity based on the Euclidean distance between the representative value (e.g., average value) of the first coordinates 2010 and the representative value (e.g., average value) of the second coordinates 2020. can be identified. For example, the shorter the Euclidean distance, the closer the similarity may be to 1. The processor 210 may identify the similarity as a value close to 1 based on the Euclidean distance between the representative values of the first coordinates 2010 and the representative values of the second coordinates 2020.

Referring to FIG. 20B, the processor 210 may identify third coordinates 2030 according to values related to the first walking pattern, which is the current walking pattern. For example, the current walking pattern may be obtained in an abnormal walking state. As an example, the current gait pattern may be obtained while the user is limping on one leg. The processor 210 may identify second coordinates 2020 according to values related to the second walking pattern, which is a reference walking pattern. The processor 210 may identify the degree of similarity based on the Euclidean distance between the representative values of the third coordinates 2030 and the representative values of the second coordinates 2020. For example, the processor 210 is based on the Euclidean distance between the representative value (e.g., average value) of the third coordinates 2030 and the representative value (e.g., average value) of the second coordinates 2020. Therefore, the similarity can be identified as a value close to 0.

21A and 21B show an example of a screen for warning of the risk of falling according to an embodiment.

Referring to FIGS. 21A and 21B , the processor 210 may provide a notification to warn in advance of the risk of falling through an external electronic device 2100 connected to the electronic device 200. For example, the processor 210 may transmit a signal to the external electronic device 2100 to cause the external electronic device 2100 to provide a notification to warn of a risk of falling.

According to one embodiment, the processor 210 may identify a probability value of a fall occurring in a user. The processor 210 may identify the threshold as one of a plurality of candidate threshold values based on the identified probability value. For example, the processor 210 may identify the risk of falling as one of 'low', 'moderate', 'high', and 'very high' based on the probability value of the user falling. The processor 210 may identify one of a plurality of candidate threshold values according to the risk of falling. For example, a plurality of candidate threshold values according to fall risk can be set as shown in Table 1 above.

According to one embodiment, the processor 210 may provide a notification to warn the user of the risk of falling in advance based on the probability value of a fall occurring satisfying a specified condition. Depending on the embodiment, the processor 210 may use the display of the electronic device 200 to display a notification to warn the user of the risk of falling.

Referring to FIG. 21A, the processor 210 may display a screen 2110 using the display of the external electronic device 2100. The screen 2110 may include text 2111 indicating the risk of falling and text 2112 indicating a warning about the walking environment. For example, the text 2112 may be configured to indicate information about the walking environment and information about risk factors. Text 2112 may be displayed to inform of the risk of rain.

Referring to FIG. 21B, the processor 210 may display a screen 2120 using the display of the external electronic device 2100. The screen 2120 may include text 2121 indicating the risk of falling and text 2122 indicating a warning about the walking environment. For example, the text 2122 may be configured to indicate information about the walking environment and information about risk factors. Text 2122 may be displayed to guide the user's actions on a snowy day.

According to one embodiment, the electronic device 200 may include at least one sensor 220, a memory 230, and a processor 210. The processor 210 uses the at least one sensor 220 to obtain first information about the first walking pattern of the user of the electronic device 200 and second information about the user's walking environment. It can be set to do so. The processor 210, based on the first information and third information about the reference walking pattern stored in the memory 230, generates a first value indicating the difference between the first walking pattern and the reference walking pattern. Can be set to identify. The processor 210, based on the first information and fourth information about the user's second walking pattern, which is stored in the memory 230 and identified based on the user's walking history, It may be set to identify a second value indicating the difference between the first walking pattern and the second walking pattern. The processor 210 may be set to identify a threshold value related to fall detection based on the first value, the second value, and the second information. The processor 210 may be configured to perform the fall detection based on a comparison between the threshold value and a value obtained through the at least one sensor 220.

According to one embodiment, the at least one sensor 220 may further include an acceleration sensor 220, a gyro sensor 220, and an air pressure sensor 220. The processor 210 may be set to obtain the first information about the first walking pattern based on first data acquired during a designated time period using the acceleration sensor 220. The processor 210 is based on second data acquired using at least one of the acceleration sensor 220, the gyro sensor 220, the barometric pressure sensor 220, and the communication circuit 240. , may be set to obtain the second information about the user's walking environment.

According to one embodiment, the processor 210 may be set to acquire acceleration trends corresponding to each of the three axes during the designated time period. The processor 210 may be set to identify the first walking pattern of the user based on the acceleration trends and the difference value of the sum of the movement sections.

According to one embodiment, the second information about the user's walking environment includes information about the slope of the movement path of the electronic device 200, information about the movement state of the electronic device 200, and the designated It may include at least one piece of information about the weather during the time interval.

According to one embodiment, the processor 210 sets at least part of the second data as input data of a designated model stored in the memory 230 and indicated by a plurality of parameters, thereby It may be set to obtain the above information about the moving state of the device 200. The plurality of parameters of the designated model may be set based on learning of third data obtained according to the user's walking history.

According to one embodiment, the electronic device 200 may include a communication circuit 240. The processor 210 may be set to receive the third information about the reference walking pattern from a server connected to the electronic device 200 using the communication circuit 240. The processor 210 may be set to store the third information in the memory 230. The third information may be obtained based on a plurality of walking patterns related to a plurality of users stored in the server.

According to one embodiment, the processor 210 may be set to identify the first value based on a Euclidean distance between values related to the first walking pattern and values related to the designated walking pattern. . The processor 210 may be configured to identify the second value based on a Euclidean distance between values for the first walking pattern and values for the second walking pattern.

According to one embodiment, the processor 210 may be set to perform learning about the user's walking pattern based on the user's walking history. The processor 210 may be set to obtain the fourth information about the second walking pattern based on learning about the user's walking pattern. The processor 210 may be set to store the fourth information in the memory 230.

According to one embodiment, the processor 210 is set to identify a population containing values related to walking patterns according to a plurality of steps of the user, based on the user's walking history. It can be. The processor 210 may be set to identify at least a portion of the population based on information about fitness according to the plurality of steps, which is obtained based on the population. The processor 210 may be set to perform learning about the user's walking pattern based on at least a portion of the population.

According to one embodiment, the processor 210 may be set to identify the user's first steps using the at least one sensor 220. The processor 210 may be set to identify feature values according to the first steps based on identifying that the number of the first steps is a specified number or more. The processor 210 may be set to configure the population based on feature values according to the first steps.

According to one embodiment, the processor 210 may be set to identify values related to a walking pattern according to the first steps, based on characteristic values according to the first steps. The processor 210, based on feature values according to the user's second steps, which are stored in the memory 230 and occurred before the first steps are identified, walks according to the second steps. It can be set to identify values related to the pattern. The processor 210 includes values related to the walking pattern according to the first steps and values related to the walking pattern according to the second steps, and values related to the walking pattern according to the plurality of steps. It can be set to consist of a population.

According to one embodiment, the processor 210 may be set to operate in one of the first to fourth modes. The processor 210 may be set to initialize the fourth information about the user's walking history and the second walking pattern, which are stored in the memory 230, based on the first mode. The processor 210 may be set to obtain data about the user's walking pattern using the at least one sensor 220 based on the second mode. The processor 210 may be set to learn data about the user's walking pattern based on the third mode. The processor 210 may be set to stop learning data about the user's walking pattern based on the fourth mode.

According to one embodiment, the processor 210 may be set to identify a probability value of a fall occurring in the user based on the first value, the second value, and the second information. The processor 210 may be configured to identify the threshold as one of a plurality of candidate threshold values based on the probability value.

According to one embodiment, the electronic device 200 may include a communication circuit 240. Based on the probability value and the second information, the processor 210 is connected to the electronic device 200 and detects a fall hazard through an external electronic device 2100 worn by the user. It may be set to transmit a signal to the external electronic device 2100 to cause the external electronic device 2100 to provide a notification for warning.

According to one embodiment, the method of the electronic device 200 uses at least one sensor 220 of the electronic device 200 to detect a first gait pattern of the user of the electronic device 200. It may include obtaining information and second information about the user's walking environment. The method identifies a first value indicating a difference between the first walking pattern and the reference walking pattern, based on the first information and third information about the reference walking pattern stored in the memory 230. Can include actions. The method is based on the first information and fourth information about the second walking pattern of the user, which is stored in the memory 230 and identified based on the walking history of the user, the first walking pattern and identifying a second value indicating a difference between the second walking patterns. The method may include identifying a threshold value related to fall detection based on the first value, the second value, and the second information. The method may include performing the fall detection based on a comparison between the threshold value and a value obtained through the at least one sensor 220.

According to one embodiment, the method uses the acceleration sensor 220 of the electronic device 200 to provide the first information about the first walking pattern based on first data acquired during a specified time period. It may include an operation to obtain. The method includes the acceleration sensor 220, the gyro sensor 220 of the electronic device 200, the barometric pressure sensor 220 of the electronic device 200, and the communication circuit 240 of the electronic device 200. ) may include an operation of acquiring the second information about the user's walking environment based on second data obtained using at least one of the following.

According to one embodiment, the method may include acquiring acceleration trends corresponding to each of the three axes during the designated time period. The method may include identifying the first walking pattern of the user based on the acceleration trends and a difference value of the sum of movement sections.

According to one embodiment, the second information about the user's walking environment includes information about the slope of the movement path of the electronic device 200, information about the movement state of the electronic device 200, and the designated It may include at least one piece of information about the weather during the time interval.

According to one embodiment, the method may include identifying the first value based on a Euclidean distance between values related to the first walking pattern and values related to the specified walking pattern. The method may include identifying the second value based on a Euclidean distance between values for the first walking pattern and values for the second walking pattern.

According to one embodiment, the method may include learning about the user's walking pattern based on the user's walking history. The method may include acquiring the fourth information about the second walking pattern based on learning about the user's walking pattern. The method may include storing the fourth information in the memory 230.

According to one embodiment, the processor 210 may identify the risk of falling before a fall accident occurs to the user. The processor 210 may provide a notification to warn the user of the risk of falling based on the risk of falling. The processor 210 may change the sensitivity of the fall detection algorithm when the risk of falling is high. For example, processor 210 may adaptively change (or adjust) a threshold value associated with fall detection. Electronic devices according to various embodiments disclosed in this document may be of various types. 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 embodiments of this document are not limited to the above-described devices.

The various embodiments of this document and the terms used herein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various changes, equivalents, or replacements of the embodiments. In connection with the description of the drawings, similar reference numbers 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 above items, unless the relevant context clearly indicates otherwise. As used herein, “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 “A Each of phrases such as “at least one of , B, or C” may include any one of the items listed together in the corresponding phrase, or any possible combination thereof. Terms such as "first", "second", or "first" or "second" may be used simply to distinguish one element from another, and may be used to distinguish such elements in other respects, such as importance or order) is not limited. One (e.g. first) component is said to be "coupled" or "connected" to another (e.g. second) component, with or without the terms "functionally" or "communicatively". Where mentioned, it means that any of the components can be connected to the other components directly (e.g. wired), wirelessly, or through a third component.

In various embodiments of this document, the term "module" used may include a unit implemented in hardware, software, or firmware, and is interchangeable with terms such as logic, logic block, component, or circuit, for example. It can be used as A module may be an integrated part or a minimum unit of the parts or a part thereof that performs one or more functions. For example, according to one embodiment, the module may be implemented in the form of an application-specific integrated circuit (ASIC).

Various embodiments of the present document are one or more instructions stored in a storage medium (e.g., built-in memory 136 or external memory 138) that can be read by a machine (e.g., electronic device 101). It may be implemented as software (e.g., program 140) including these. For example, a processor (e.g., processor 120) of a device (e.g., electronic device 101) may call at least one command among one or more commands stored from a storage medium and execute it. This allows the device to be operated to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. A storage medium that can be read by a device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain signals (e.g. electromagnetic waves). This term refers to cases where data is stored semi-permanently in the storage medium. There is no distinction between temporary storage cases.

According to one embodiment, methods according to various embodiments disclosed in this document may be provided and included in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. A 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 through an application store (e.g. Play Store), or on two user devices (e.g. : Smartphones) can be distributed (e.g. downloaded or uploaded) directly or online. In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

According to various embodiments, each component (e.g., module or program) of the above-described components may include a single or plural entity, and some of the plurality of entities may be separately placed in other components. there is. According to various embodiments, one or more of the components or operations described above may be omitted, or one or more other components or operations may be added. Alternatively or additionally, multiple components (eg, modules or programs) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each component of the plurality of components identically or similarly to those performed by the corresponding component of the plurality of components prior to the integration. . According to various embodiments, 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, or omitted. Alternatively, one or more other operations may be added.

Claims (20)

In the electronic device 200,
at least one sensor 220;
memory(230); and
Includes a processor 210, wherein the processor 210 includes,
Using the at least one sensor 220, obtain first information about the first walking pattern of the user of the electronic device 200 and second information about the user's walking environment,
Based on the first information and third information about the reference walking pattern stored in the memory 230, identify a first value indicating a difference between the first walking pattern and the reference walking pattern,
Based on the first information and fourth information about the user's second walking pattern, which is stored in the memory 230 and identified based on the user's walking history, the first walking pattern and the second walking pattern identify a second value representing a difference between gait patterns;
Based on the first value, the second value, and the second information, identify a threshold value associated with fall detection,
configured to perform the fall detection based on a comparison between the threshold value and a value obtained through the at least one sensor 220.
Electronic device (200).
According to claim 1,
The at least one sensor 220,
Acceleration sensor 220;
Gyro sensor 220; and
Further comprising an air pressure sensor 220,
The processor 210,
Using the acceleration sensor 220, the first information about the first walking pattern is acquired based on the first data acquired during a designated time period,
Based on second data acquired using at least one of the acceleration sensor 220, the gyro sensor 220, the barometric pressure sensor 220, and the communication circuit 240, the user's walking environment further configured to obtain the second information about
Electronic device (200).
The method of claim 2, wherein the processor 210:
During the designated time period, acceleration trends corresponding to each of the three axes are acquired,
Based on the acceleration trends, based on the difference value of the movement section sum, further configured to identify the first walking pattern of the user
Electronic device (200).
The method according to any one of claims 2 to 3, wherein the second information about the user's walking environment is,
Containing at least one of information about the slope of the movement path of the electronic device 200, information about the movement state of the electronic device 200, and information about the weather during the designated time period.
Electronic device (200).
The method of claim 4, wherein the processor 210:
Obtaining the information about the movement state of the electronic device 200 by setting at least part of the second data as input data of a designated model stored in the memory 230 and indicated by a plurality of parameters It is further set to
The plurality of parameters of the specified model are,
Set based on learning of third data obtained according to the user's walking history
Electronic device (200).
According to any one of claims 1 to 5,
Further comprising a communication circuit 240,
The processor 210,
Receiving the third information about the reference walking pattern from a server connected to the electronic device 200 using the communication circuit 240,
is set to store the third information in the memory 230,
The third information is,
Obtained based on a plurality of walking patterns related to a plurality of users stored in the server
Electronic device (200).
The method of any one of claims 1 to 6, wherein the processor 210:
Identifying the first value based on a Euclidean distance between the values for the first gait pattern and the values for the designated gait pattern,
further configured to identify the second value based on a Euclidean distance between the values for the first walking pattern and the values for the second walking pattern.
Electronic device (200).
The method of any one of claims 1 to 7, wherein the processor 210:
Based on the user's walking history, learn about the user's walking pattern,
Based on learning about the user's walking pattern, obtain the fourth information about the second walking pattern,
Further set to store the fourth information in the memory 230
Electronic device (200).
The method of claim 8, wherein the processor 210:
Based on the user's walking history, identify a population containing values regarding a walking pattern according to a plurality of steps of the user,
Identifying at least a portion of the population based on information about fitness according to the plurality of steps obtained based on the population,
Based on at least some of the population, set to perform learning about the user's walking pattern
Electronic device (200).
The method of claim 9, wherein the processor 210:
Using the at least one sensor 220, identify first steps of the user,
Based on identifying that the number of first steps is more than a specified number, identify feature values according to the first steps,
Based on the characteristic values according to the first steps, further configured to configure the population
Electronic device (200).
The method of claim 10, wherein the processor 210:
Based on the feature values according to the first steps, identify values related to a walking pattern according to the first steps,
Based on feature values according to the user's second steps, which are stored in the memory 230 and generated before the first steps are identified, identify values related to the walking pattern according to the second steps; ,
The values related to the walking pattern according to the first steps and the values related to the walking pattern according to the second steps are set to be configured as the population including the values related to the walking pattern according to the plurality of steps.
Electronic device (200).
The method of any one of claims 1 to 11, wherein the processor 210:
Operates in one of the first to fourth modes,
Based on the first mode, initializing the fourth information about the user's walking history and the second walking pattern stored in the memory 230,
Based on the second mode, obtain data about the user's walking pattern using the at least one sensor 220,
Based on the third mode, learn data about the user's walking pattern,
Based on the fourth mode, set to stop the operation of learning data about the user's walking pattern
Electronic device (200).
The method of any one of claims 1 to 12, wherein the processor 210:
Based on the first value, the second value, and the second information, identify a probability value of a fall occurring in the user,
Based on the probability value, set to identify the threshold as one of a plurality of candidate thresholds.
Electronic device (200).
According to claim 13,
Further comprising a communication circuit 240,
The processor 210,
Based on the probability value and the second information, to provide a notification to warn of a fall hazard through an external electronic device 2100 connected to the electronic device 200 and worn by the user. Further set to transmit a signal for causing the external electronic device 2100 to the external electronic device 2100
Electronic device (200).
In the method of the electronic device 200,
Obtaining first information about the first walking pattern of the user of the electronic device 200 and second information about the user's walking environment using at least one sensor 220 of the electronic device 200. movement;
An operation of identifying a first value indicating a difference between the first walking pattern and the reference walking pattern, based on the first information and third information about the reference walking pattern stored in the memory 230;
Based on the first information and fourth information about the user's second walking pattern, which is stored in the memory 230 of the electronic device 200 and identified based on the user's walking history, the first identifying a second value representing a difference between a gait pattern and the second gait pattern;
identifying a threshold value related to fall detection based on the first value, the second value, and the second information; and
Comprising the operation of executing the fall detection based on a comparison between the threshold value and a value obtained through the at least one sensor 220.
method.
According to claim 15,
Obtaining the first information about the first walking pattern using the acceleration sensor 220 of the electronic device 200, based on first data acquired during a designated time period; and
At least one of the acceleration sensor 220, the gyro sensor 220 of the electronic device 200, the barometric pressure sensor 220 of the electronic device 200, and the communication circuit 240 of the electronic device 200 Based on the second data obtained using, further comprising the operation of acquiring the second information about the user's walking environment.
method.
According to claim 16,
Obtaining acceleration trends corresponding to each of the three axes during the designated time period; and
Based on the acceleration trends, based on a difference value of the sum of movement sections, further comprising identifying the first walking pattern of the user
method.
The method of any one of claims 16 to 17, wherein the second information about the user's walking environment is,
Containing at least one of information about the slope of the movement path of the electronic device 200, information about the movement state of the electronic device 200, and information about the weather during the designated time period.
method.
The method according to any one of claims 15 to 18,
identifying the first value based on a Euclidean distance between values for the first walking pattern and values for the specified walking pattern; and
Further comprising identifying the second value based on a Euclidean distance between the values for the first walking pattern and the values for the second walking pattern.
method.
The method according to any one of claims 15 to 19,
An operation of learning about the user's walking pattern based on the user's walking history;
Obtaining the fourth information about the second walking pattern based on learning about the user's walking pattern; and
Further comprising the operation of storing the fourth information in the memory 230.
method.

Images