KR20220045489A - Electronic device identifying information related to walking and operation method of the same - Google Patents

Abstract

The present invention relates to an electronic device for checking information related to walking, which checks a stride with high accuracy without using GPS data and an operation method thereof. According to various embodiments of the present invention, the electronic device comprises an acceleration sensor, a memory storing a stride model representing a relationship between a walking frequency and a stride, and at least one processor. The at least one processor is configured to acquire first acceleration data through the acceleration sensor; check a stride correction model on the basis of the first acceleration data; acquire second acceleration data through the acceleration sensor; check a first stride on the basis of the walking frequency based on the second acceleration data and the stride model; check a stride correction value on the basis of the second acceleration data and the stride correction model; and check a second stride on the basis of the first stride and the stride correction value.

Description

An electronic device for checking information about walking and a method of operating an electronic device for checking information about walking

Various embodiments relate to an electronic device for checking information about walking and a method of operating the electronic device for checking information about walking.

As interest in personal health grows, electronic devices for checking information about walking have become widespread. For example, when the user lifts the electronic device or walks while wearing the electronic device, the electronic device may check the number of steps taken by the user. Furthermore, the electronic device may check the amount of calories consumed by the user through walking or check the distance the user has walked.

The electronic device for checking information about walking acquires acceleration data through an acceleration sensor, checks a step frequency based on the obtained acceleration data, stores a step length model related to a relationship between step frequency and stride length, and stores the checked The stride length can be determined by applying the stride length model to the step frequency. However, since the stride model is checked irrespective of the gait pattern of the user of the electronic device, the accuracy of the stride length obtained based on the stride model may decrease depending on the gait habit of the user.

In order to improve the accuracy of the stride, the electronic device may correct the stride obtained based on the stride model using GPS data. However, when the electronic device corrects the stride length using GPS data, the accuracy of the checked stride may still be limited in an environment in which the use of GPS is restricted. Also, an electronic device that does not have a circuit for performing GPS communication cannot perform calibration using GPS data.

The electronic device according to an embodiment derives a stride length value by applying a stride model to a step frequency derived based on acceleration data, and calculates a stride length correction value based on the stride length correction model based on other parameters based on the acceleration data. After confirming, the stride length can be finally determined based on the stride length value derived by applying the stride length correction value and the stride length model.

An electronic device according to an embodiment includes an acceleration sensor, a memory for storing a step length model representing a relationship between a walking frequency and a stride length, and at least one processor, wherein the at least one processor is configured to operate through the acceleration sensor. Acquire first acceleration data, confirm a step length correction model based on the first acceleration data, obtain second acceleration data through the acceleration sensor, and obtain a gait frequency based on the second acceleration data and the stride length model based on the second acceleration data to check the first stride length, check the step length correction value based on the second acceleration data and the stride length correction model, and determine the second stride length based on the first stride length and the stride length correction value. .

According to an embodiment of the present disclosure, a method performed in an electronic device includes obtaining first acceleration data through an acceleration sensor, identifying a step length correction model based on the first acceleration data, and performing a first step through the acceleration sensor. 2 The operation of acquiring acceleration data, the operation of confirming the first stride length based on the walking frequency and the stride length model based on the second acceleration data, the operation of confirming the step length correction value based on the second acceleration data and the stride length correction model and checking the second stride length based on the first stride length and the stride length correction value.

An electronic device according to an embodiment includes an acceleration sensor, a memory for storing a step length model representing a relationship between a walking frequency and a step length, a communication circuit, and at least one processor, wherein the at least one processor is configured to: Receive a step length correction model from an external electronic device through a circuit, check a type of the external electronic device, obtain acceleration data through the acceleration sensor, and walk frequency based on the acceleration data and based on the step length model A first step length is checked, a step length compensation value is checked based on the acceleration data and the step length compensation model, and a second step length compensation value is confirmed based on the first step length, the step length compensation value, and a weight based on the type of the external electronic device. It may be configured to check the stride length.

According to one or more exemplary embodiments, an electronic device for checking information about walking and a method of operating the electronic device for checking information about walking are provided. The electronic device according to an embodiment may check the stride length correction model based on parameters based on acceleration data and correct the stride length using the stride length correction model. Accordingly, the electronic device according to an embodiment may check the stride length with high accuracy without using GPS data.

1 is a block diagram of an electronic device in a network environment, according to various embodiments of the present disclosure;
2 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure;
3 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure;
4A illustrates an example of an acceleration magnitude according to walking, according to various embodiments.
4B illustrates an example of an SWS difference value according to walking, according to various embodiments.
5 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure;
6 illustrates an example of a plurality of gait characteristic information classified into a plurality of clusters, according to various embodiments.
7A illustrates an example of a first stride length correction model based on a maximum acceleration magnitude according to various embodiments of the present disclosure;
7B shows an example of a second stride correction model based on variance, in accordance with various embodiments.
8 illustrates an example of a stride length model representing a relationship between a gait frequency and a stride length, according to various embodiments.
9 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure;
10 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure;
11A illustrates an example of a screen displayed on an electronic device according to various embodiments of the present disclosure;
11B illustrates an example of a screen displayed on an electronic device, according to various embodiments of the present disclosure.
12 illustrates an example of a screen displayed on an electronic device, according to various embodiments of the present disclosure.
13 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure;
14 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure;

1 is a block diagram of an electronic device 101 in a network environment 100 according to various embodiments. Referring to FIG. 1 , in a network environment 100 , an electronic device 101 communicates with an electronic device 102 through a first network 198 (eg, a short-range wireless communication network) or a second network 199 . It may communicate with the electronic device 104 or the server 108 through (eg, a long-distance wireless communication network). According to an embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108 . According to an embodiment, the electronic device 101 includes a processor 120 , a memory 130 , an input module 150 , a sound 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 an antenna module 197 may be included. 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 (eg, sensor module 176 , camera module 180 , or antenna module 197 ) are integrated into one component (eg, display module 160 ). can be

The processor 120, for example, executes software (eg, a program 140) to execute at least one other component (eg, a hardware or software component) of the electronic device 101 connected to the processor 120 . It can control and perform various data processing or operations. According to one embodiment, as at least part of data processing or operation, the processor 120 converts commands or data received from other components (eg, the sensor module 176 or the communication module 190 ) to the volatile memory 132 . may be stored in the volatile memory 132 , and may process commands or data stored in the volatile memory 132 , and store the result data in the non-volatile memory 134 . According to an embodiment, the processor 120 is the main processor 121 (eg, a central processing unit or an application processor) or a secondary processor 123 (eg, a graphic processing unit, a neural network processing unit) a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, when the electronic device 101 includes the main processor 121 and the sub-processor 123 , the sub-processor 123 may use less power than the main processor 121 or may be set to be specialized for a specified function. can The auxiliary processor 123 may be implemented separately from or as a part of the main processor 121 .

The auxiliary processor 123 is, for example, on behalf of the main processor 121 while the main processor 121 is in an inactive (eg, sleep) state, or the main processor 121 is active (eg, executing an application). ), together with the main processor 121, at least one of the components of the electronic device 101 (eg, the display module 160, the sensor module 176, or the communication module 190) It is possible to control at least some of the related functions or states. According to an embodiment, the co-processor 123 (eg, an image signal processor or a communication processor) may be implemented as part of another functionally related component (eg, the camera module 180 or the communication module 190). there is. According to an embodiment, the auxiliary processor 123 (eg, a neural network processing device) may include a hardware structure specialized for processing an artificial intelligence model. Artificial intelligence models can be created through machine learning. Such learning may be performed, for example, in the electronic device 101 itself on which artificial intelligence is performed, or may be performed through a separate server (eg, the server 108). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but in the above example not limited The artificial intelligence model may include a plurality of artificial neural network layers. Artificial neural networks include deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the above example. The artificial intelligence model may include, in addition to, or alternatively, a software structure in addition to the hardware structure.

The memory 130 may store various data used by at least one component of the electronic device 101 (eg, the processor 120 or the sensor module 176 ). The data may include, for example, input data or output data for software (eg, the program 140 ) and instructions related thereto. The memory 130 may include a volatile memory 132 or a 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 an application 146 .

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

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

The display module 160 may visually provide information to the outside (eg, a user) of the electronic device 101 . The display module 160 may include, for example, a control circuit for controlling a display, a hologram device, or a projector and a corresponding device. According to an embodiment, the display module 160 may include a touch sensor configured to sense a touch or a pressure sensor configured to measure the intensity of a force generated by the touch.

The audio module 170 may convert a sound into an electric signal or, conversely, convert an electric signal into a sound. According to an embodiment, the audio module 170 acquires a sound through the input module 150 , or an external electronic device (eg, a sound output module 155 ) connected directly or wirelessly with the electronic device 101 . A sound may be output through the electronic device 102 (eg, a speaker or headphones).

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

The interface 177 may support one or more designated protocols that may be used by the electronic device 101 to directly or wirelessly connect with an external electronic device (eg, the electronic device 102 ). According to an 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 an 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 may convert an electrical signal into a mechanical stimulus (eg, vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic sense. According to an embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

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

The power management module 188 may manage power supplied to the electronic device 101 . According to an embodiment, the power management module 188 may be implemented as, for example, at least a part of 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, battery 189 may include, for example, a non-rechargeable primary cell, a rechargeable secondary cell, or a fuel cell.

The communication module 190 is a direct (eg, wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (eg, the electronic device 102, the electronic device 104, or the server 108). It can support establishment and communication performance through the established communication channel. The communication module 190 may include one or more communication processors that operate independently of the processor 120 (eg, an application processor) and support direct (eg, wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (eg, 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 (eg, : It may include a LAN (local area network) communication module, or a power line communication module). A corresponding communication module among these communication modules is a first network 198 (eg, a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (eg, legacy It may communicate with the external electronic device 104 through a cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (eg, a telecommunication network such as a LAN or a WAN). These various types of communication modules may be integrated into one component (eg, a single chip) or may be implemented as a plurality of components (eg, multiple chips) separate from each other. The wireless communication module 192 uses the subscriber information (eg, 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 may be identified or authenticated.

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

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

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, the mmWave antenna module comprises a printed circuit board, an RFIC disposed on or adjacent to a first side (eg, bottom side) of the printed circuit board and capable of supporting a designated high frequency band (eg, mmWave band); and a plurality of antennas (eg, an array antenna) disposed on or adjacent to a second side (eg, top or side) of the printed circuit board and capable of transmitting or receiving signals of 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 (eg, a bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and a signal ( eg commands or data) can be exchanged with each other.

According to an embodiment, the command 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 the same as or different from the electronic device 101 . According to an embodiment, all or a part of operations executed in the electronic device 101 may be executed in one or more external electronic devices 102 , 104 , or 108 . For example, when the electronic device 101 is to perform a function or service automatically or in response to a request from a user or other device, the electronic device 101 may perform the function or service itself instead of executing the function or service itself. Alternatively or additionally, one or more external electronic devices may be requested to perform at least a part of the function or the service. One or more external electronic devices that have received the request may execute at least a part of the requested function or service, or an additional function or service related to the request, and transmit a result of the execution to the electronic device 101 . The electronic device 101 may process the result as it is or additionally and provide it as at least a part of a response to the request. For this, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may 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 an embodiment, the external electronic device 104 or the server 108 may be included in the second network 199 . The electronic device 101 may be applied to an intelligent service (eg, smart home, smart city, smart car, or health care) based on 5G communication technology and IoT-related technology.

2 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure; According to various embodiments, the electronic device performing the operations illustrated in FIG. 2 may be the electronic device 101 of FIG. 1 . Hereinafter, description will be made with reference to the reference numerals of FIG. 1 , but the electronic device according to various embodiments is not limited to the electronic device 101 of FIG. 1 . According to various embodiments, the electronic device that performs the operations shown in FIG. 2 may be an electronic device that does not include at least one of the components of the electronic device 101 shown in FIG. 1 . According to various embodiments, the electronic device performing the operations illustrated in FIG. 2 may be a wearable electronic device such as a watch or an earbud. Alternatively, according to various embodiments, the electronic device may be an electronic device that the user can hold, such as a smartphone or a tablet. The above description may be applied not only to FIG. 2 but also to an electronic device that performs operations illustrated in FIGS. 3, 5, 9, 10, 13, and 14 below.

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs an acceleration sensor (eg, the sensor module 176 ) in operation 210 . The first acceleration data may be acquired through an acceleration sensor included in the .

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) checks the step length correction model based on the first acceleration data in operation 220 . can An operation of confirming the stride length correction model based on the first acceleration data will be described later with reference to FIGS. 3 and 5 .

According to various embodiments, at least one processor (eg, processor 120 ) of the electronic device (eg, electronic device 101 ) may in operation 230 an acceleration sensor (eg, sensor module 176 ) The second acceleration data may be acquired through an acceleration sensor included in the .

According to various embodiments, at least one processor (eg, processor 120) of the electronic device (eg, electronic device 101) checks the gait frequency based on the second acceleration data in operation 240, The first stride length may be identified based on the checked gait frequency and the stride length model representing the relationship between the gait frequency and the stride length stored in the memory (eg, the memory 130 ).

According to various embodiments, the stride model may be identified regardless of acceleration data obtained through the acceleration sensor of the electronic device 101 . For example, the stride length model may be a relationship between gait frequency and stride length derived through an experiment. According to various embodiments, the stride model may be stored in the memory 130 when the electronic device 101 is manufactured. According to various embodiments, the electronic device 101 may receive a stride model from an external electronic device through a communication circuit (eg, the communication module 190 ) and store it in the memory 130 . An example of the stride length model will be described later with reference to FIG. 8 .

According to various embodiments, at least one processor (eg, processor 120 ) of the electronic device (eg, electronic device 101 ) performs a step length based on the second acceleration data and the step length correction model in operation 250 . You can check the correction value. A detailed process of confirming the stride length correction value will be described later with reference to FIG. 9 .

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs a second step based on the first stride length and the stride correction value in operation 260 . You can check the stride length. According to various embodiments, the at least one processor 120 may determine the sum of the first stride length and the stride correction value as the second stride length. According to other various embodiments, the at least one processor 120 multiplies the step length correction value by a weight, and determines a value obtained by adding the weight to the first stride length as the second stride length.

3 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure; Specifically, FIG. 3 is a flowchart illustrating operations performed by an electronic device to check gait characteristic information based on acceleration data.

은 수학식 1과 같이 정의될 수 있다.According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) may determine the magnitude of the acceleration based on the acceleration data in operation 310 . . magnitude of acceleration

may be defined as in Equation 1.

In Equation 1, x, y, and z are the magnitudes of 3-axis acceleration, respectively.

4A illustrates an example of an acceleration magnitude according to walking, according to various embodiments. Referring to FIG. 4A , as footsteps are periodically repeated, it can be seen that the acceleration magnitude value 410 also periodically rises and falls according to the footstep cycle. 4A and 4B , the horizontal axis may mean the number of samples. According to various embodiments, samples may be acquired in units of 10 ms, and in this case, 100 samples may mean 1 second.

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) may check a sliding window summing (SWS) difference value in operation 320 . . An SWS value corresponding to a window having a size of N may be defined as in Equation (2).

The SWS difference value may be defined as in Equation (3).

According to various embodiments, at least one processor (eg, processor 120 ) of the electronic device (eg, electronic device 101 ) performs zero crossing (ZC) based on the SWS difference value in operation 330 . points can be checked. According to various embodiments, the ZC point may mean a point at which the SWS difference value becomes 0 while the SWS difference value changes from a positive number to a negative number. According to other various embodiments, the ZC point may mean a point at which the SWS difference value becomes 0 while the SWS difference value is changed from a negative number to a positive number.

4B illustrates an example of an SWS difference value according to walking, according to various embodiments. Referring to FIG. 4B , as footsteps are periodically repeated, it can be seen that the SWS difference value 420 also periodically rises and falls according to the footstep cycle. In addition, the points at which the SWS difference value becomes 0 in the process of changing the SWS difference value 420 from a positive number to a negative number may be ZC points 431, 432, 433, 434, 435, 436, 437, 438, 439. .

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs a step for a step section based on the ZC points in operation 340 . You can check gait characteristic information. The one-step section may be defined between two adjacent ZC points among the ZC points 431 , 432 , 433 , 434 , 435 , 436 , 437 , 438 , and 439 . According to various embodiments, the gait characteristic information may include a gait frequency, a maximum acceleration magnitude, and variance. In the example of FIG. 4B , since there are nine ZC points 431 , 432 , 433 , 434 , 435 , 436 , 437 , 438 , 439 , 8 step intervals can be defined, and each of the 8 step intervals For , gait characteristic information including a gait frequency, a maximum acceleration magnitude, and a variance may be identified.

The walking frequency F may be defined as in Equation (4).

는 n번째 ZC 지점에서의 시간,

는 n-1번째 ZC 지점에서의 시간이다.In Equation 4,

is the time at the nth ZC point,

is the time at the n-1 th ZC point.

과

사이의 시간 구간에 대하여,

의 최댓값으로 정의될 수 있다. 여기서,

는

과

사이의 임의의 시간을 의미할 수 있다.The maximum value of the acceleration magnitude for the step interval between the n-1st ZC point and the nth ZC point is

class

for the time interval between

It can be defined as the maximum value of here,

Is

class

It can mean any time in between.

The variance V for the one-step section between the n-1 th ZC point and the n th ZC point may be defined as in Equation 5.

는

과

사이의 임의의 시간

에서의 3축 가속도의 벡터이고,

는

과

사이의 시간 구간에 대한 3축 가속도의 각 성분의 평균값을 성분으로 갖는 평균 가속도 벡터이다. N은

과

사이의 시간 구간 내의 샘플 수이다.here,

Is

class

any time between

is the vector of the three-axis acceleration at

Is

class

It is an average acceleration vector having as a component the average value of each component of the three-axis acceleration for the time interval between them. N is

class

The number of samples in the time interval between

In general, the smaller the stride length, the smaller the maximum acceleration magnitude, and the larger the stride length, the larger the maximum acceleration magnitude. In addition, the smaller the stride length, the smaller the variance, and the larger the stride length, the greater the variance.

Although not shown in FIG. 3 , according to various embodiments, the at least one processor 120 of the electronic device 101 determines whether the user is walking or running based on the ZC points identified in operation 330 and , operation 340 may be performed only when it is confirmed that the user is walking or running. According to various embodiments, when it is determined that the interval between adjacent ZC points is constant and the interval between adjacent ZC points is within a predetermined range, the at least one processor 120 of the electronic device 101 allows the user to walk or run You can check that it is in progress.

According to various embodiments, the at least one processor 120 may check time intervals between adjacent ZC points among the plurality of ZC points 431 , 432 , 433 , 434 , 435 , 436 , 437 , 438 , 439 . And, when the deviation between the time intervals between the confirmed adjacent ZC points is less than or equal to a predetermined level, it can be confirmed that the intervals of the adjacent ZC points are constant.

According to various embodiments, the at least one processor 120 determines that the interval between the adjacent ZC points is within a predetermined range when the number of time intervals within a predetermined range among the time intervals between the adjacent ZC points is greater than or equal to a predetermined number or greater than a predetermined ratio. You can check that it is inside. According to various embodiments, the predetermined range may be an interval between ZC points corresponding to normal walking and running.

5 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure; Specifically, FIG. 5 illustrates operations performed in the electronic device to confirm the stride length correction model based on the first acceleration data.

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs the gait characteristic acquired based on the first acceleration data in operation 510 . Information may be stored in a memory (eg, memory 130 ). Details of the gait characteristic information have been described above with reference to operation 340 of FIG. 3 .

는 수학식 6과 같이 정의될 수 있다.According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs the variability of gait frequency among the stored gait characteristic information in operation 520 ( variability) can be checked. The variability of walking frequency is a measure of how widely distributed the walking frequency values are from the mean. According to various embodiments, the variability of the walking frequency may be defined as a difference between the maximum value and the minimum value of the walking frequency. According to various embodiments, the variability of the walking frequency may be defined as a variance of the walking frequency. According to various embodiments, the variability of the walking frequency may be defined as an interquartile range of the walking frequency. Interquartile range of walking frequency

can be defined as in Equation (6).

는 보행 빈도 값들을 오름차순으로 나열하였을 때 하위 75%의 보행 빈도를 의미할 수 있다.

는 보행 빈도 값들을 오름차순으로 나열하였을 때 하위 25%의 보행 빈도를 의미할 수 있다. In Equation 6,

may mean the lower 75% of walking frequency when the walking frequency values are arranged in ascending order.

may mean the walking frequency of the lower 25% when the walking frequency values are arranged in ascending order.

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) determines in operation 530 , the number of stored gait characteristic information exceeds the first threshold. and whether the variability of the walking frequency exceeds the second threshold may be checked. According to various embodiments, the fact that the number of stored gait characteristic information exceeds the first threshold may mean that the number of stored samples is sufficiently large. According to various embodiments, that the variability of the gait frequency exceeds the second threshold may mean that the stored sample includes data on a sufficiently diverse gait pattern.

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) may classify the stored gait characteristic information according to the gait pattern in operation 540 . can According to various embodiments, the at least one processor 120 may perform operation 540 using various clustering algorithms. For example, the at least one processor 120 may include k-mean, affinity propagation (AP), Gaussian mixture model (GMM), hierarchical agglomerative clustering (HAC), spectral clustering (SC), and density-based spatial clustering (DBSCAN). of applications with noise) can be used to classify gait characteristic information according to gait patterns.

6 illustrates an example of a plurality of gait characteristic information classified into a plurality of clusters, according to various embodiments. Specifically, FIG. 6 shows a result of classifying a plurality of gait characteristic information into six clusters 610, 620, 630, 640, 650, and 660 using the k-mean method. In FIG. 6 , the gait frequency, the maximum acceleration magnitude, and the variance constituting the gait characteristic information indicated by each axis were normalized, respectively. In the example of FIG. 6 , min-max normalization was used. According to various embodiments, before classifying a plurality of gait characteristic information into a plurality of clusters, in addition to minimum-maximum value normalization, various normalization methods such as z-score normalization may be used.

6 illustrates an example in which a plurality of gait characteristic information is classified into six clusters, which is a relatively small number, for convenience of illustration. However, as shown in FIGS. 7A and 7B , according to various embodiments, at least one processor Reference numeral 120 classifies the plurality of gait characteristic information into a larger number of clusters.

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs a first step length correction based on the maximum acceleration magnitude in operation 550 . A second step length correction model based on the model and variance can be identified. 7A illustrates an example of a first stride length correction model based on a maximum acceleration magnitude according to various embodiments of the present disclosure; 7B shows an example of a second stride correction model based on variance, in accordance with various embodiments.

Referring to FIG. 7A , the first stride length correction model may include an upper limit model 720a of the first stride length correction model and a lower limit model 730a of the first stride length correction model. Each point indicated in FIG. 7A represents a centroid of each cluster classified in operation 540 . According to various embodiments, the gait frequency-acceleration magnitude maximal model 710a of FIG. 7A is polynomial regression based on the gait frequency and acceleration magnitude maxima of a plurality of center points, which are represented by the plurality of points shown in FIG. 7A . It may be a result of performing modeling. According to various embodiments, various modeling methods other than polynomial regression modeling may be used to derive the gait frequency-acceleration magnitude maximum model 710a.

According to various embodiments, the upper limit model 720a of the first stride length correction model is a model obtained by moving the walking frequency-acceleration magnitude maximum value model 710a in parallel in the vertical axis direction. It may be defined as a model in which the number of center points having a maximum acceleration magnitude among the center points of is greater than the upper limit model 720a of the first stride correction model corresponds to a first predetermined ratio. For example, when the predetermined first ratio is 15%, 15% of the center points among the plurality of center points shown in FIG. 7A may be located above the upper limit model 720a of the first stride length correction model.

According to various embodiments, the lower limit model 730a of the first step length correction model is a model obtained by moving the walking frequency-acceleration magnitude maximum value model 710a in parallel in the vertical axis direction. It may be defined as a model in which the number of center points having the maximum acceleration magnitude among the center points of is smaller than the lower limit model 730a of the first step length correction model corresponds to a first predetermined ratio. For example, when the first predetermined ratio is 15%, 15% of the center points among the plurality of center points shown in FIG. 7A may be located below the lower limit model 730a of the first stride length correction model.

Referring to FIG. 7B , the second stride length correction model may include an upper limit model 720b of the second stride length correction model and a lower limit model 730b of the second stride length correction model. Each point indicated in FIG. 7B represents a centroid of each cluster classified in operation 540 . According to various embodiments, the gait frequency-variance model 710b of FIG. 7B performs polynomial regression modeling based on the gait frequency and variance of a plurality of center points, which are represented by the plurality of points shown in FIG. 7B . could be the result. According to various embodiments, various modeling methods other than polynomial regression modeling may be used to derive the gait frequency-variance model 710b.

According to various embodiments, the upper limit model 720b of the second step length correction model is a model obtained by moving the walking frequency-dispersion model 710b in parallel in the vertical axis direction, and is represented by a plurality of points shown in FIG. 7B , a plurality of center points The middle variance may be defined as a model such that the number of center points greater than the upper limit model 720b of the second stride correction model corresponds to the first predetermined ratio. For example, when the first predetermined ratio is 15%, 15% of the center points among the plurality of center points shown in FIG. 7B may be located above the upper limit model 720b of the second stride length correction model.

According to various embodiments, the lower limit model 730b of the second step length correction model is a model obtained by moving the walking frequency-dispersion model 710b in parallel in the vertical axis direction, and is represented by a plurality of points shown in FIG. 7B , a plurality of center points. The middle variance may be defined as a model such that the number of center points smaller than the lower limit model 730b of the second stride correction model corresponds to the first predetermined ratio. For example, when the first predetermined ratio is 15%, 15% of the center points among the plurality of center points shown in FIG. 7B may be located below the lower limit model 730b of the second stride length correction model.

8 illustrates an example of a stride length model representing a relationship between a gait frequency and a stride length, according to various embodiments. Referring to FIG. 8 , the gait frequency and stride length indicated by the plurality of dots shown in FIG. 8 are measured with respect to the gait of a person other than the user of the electronic device (eg, the electronic device 101 ) according to various embodiments. It may be a value obtained by performing the operation. According to various embodiments, the walking frequency and stride length indicated by the plurality of dots illustrated in FIG. 8 may be values obtained through an experiment performed by the manufacturer of the electronic device 101 .

According to various embodiments, the stride length model may be a result of performing polynomial regression modeling based on the gait frequency and stride length indicated by the plurality of points illustrated in FIG. 8 . According to various embodiments, various modeling methods other than polynomial regression modeling may be used to derive the stride length model.

9 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure; Specifically, FIG. 9 illustrates operations performed by the electronic device to confirm a step length correction value based on the stride length correction model.

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) checks gait characteristic information based on the second acceleration data in operation 910 . can According to various embodiments, the at least one processor 120 may check the gait characteristic information by performing the operations illustrated in FIG. 3 on the second acceleration data.

According to various embodiments, at least one processor (eg, processor 120 ) of the electronic device (eg, electronic device 101 ) identifies a gait pattern based on the gait pattern classification model in operation 920 , and , it is possible to check the center point information corresponding to the walking pattern. According to various embodiments, the checking of the gait pattern may include checking which cluster the gait characteristic information corresponding to the second acceleration data belongs to among the plurality of clusters described above with reference to operation 540 of FIG. 5 . According to various embodiments, the at least one processor 120 may determine to which cluster the gait characteristic information corresponding to the second acceleration data belongs by using the various clustering algorithms described above with reference to operation 540 of FIG. 5 . According to various embodiments, the center point corresponding to the gait pattern may be the center point of a cluster to which the gait characteristic information corresponding to the second acceleration data belongs. According to various embodiments, the center point information may include a walking frequency, a maximum acceleration magnitude, and a variance corresponding to the center point.

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs a first step for the upper limit model of the first stride length correction model in operation 930 . The output, the second output for the lower limit model of the first stride length correction model, the third output for the upper limit model of the second stride length correction model, and the fourth output for the lower limit model of the second stride length correction model may be checked. According to various embodiments, the first output for the upper limit model of the first stride length correction model is the acceleration magnitude derived by substituting the gait frequency value of the gait characteristic information corresponding to the second acceleration data to the upper limit model of the first stride length correction model. It can be the maximum value. According to various embodiments, the second output of the lower limit model of the first stride length correction model may be an acceleration derived by substituting a gait frequency value of gait characteristic information corresponding to the second acceleration data to the lower limit model of the first stride length correction model. It can be the maximum size. According to various embodiments, the third output of the upper limit model of the second stride length correction model is a variance derived by substituting the gait frequency value of the gait characteristic information corresponding to the second acceleration data to the upper limit model of the second stride length correction model. can be According to various embodiments, the fourth output of the lower limit model of the second stride length correction model is a variance derived by substituting the gait frequency value of the gait characteristic information corresponding to the second acceleration data to the lower limit model of the second stride length correction model. can be

According to various embodiments, in operation 940 , at least one processor (eg, processor 120 ) of the electronic device (eg, electronic device 101 ) has a maximum acceleration magnitude of the central point greater than the first output. , it is possible to check whether the variance of the center point is greater than the third output. The fact that the maximum value of the acceleration magnitude of the central point is greater than the first output and the dispersion of the central point is greater than the third output means that the central point representing the gait pattern confirmed based on the second acceleration data is the user of the electronic device 101 . Being larger than the first output and the third output representing the usual gait pattern, in other words, may mean that the second acceleration data represents a relatively larger maximum and variance of the acceleration magnitude compared to the user's usual gait pattern. In general, the smaller the stride length, the smaller the maximum acceleration magnitude, and the larger the stride length, the larger the acceleration magnitude maximum. It indicates that you are walking with a large stride.

은 수학식 7과 같이 정의될 수 있다.In operation 940 , when it is confirmed that the maximum value of the acceleration magnitude of the central point is greater than the first output and the dispersion of the central point is greater than the third output, the at least one processor (eg, the processor 120 ) configures the acceleration magnitude of the central point in operation 945 . The stride correction value may be confirmed based on the maximum value, the variance of the center point, the first output, and the third output. According to various embodiments, the stride correction value

can be defined as in Equation 7.

은 수학식 8과 같이 정의될 수 있다.In Equation 7,

can be defined as in Equation (8).

은 제1 출력을 의미하고,

은 중심점의 가속도 크기 최댓값을 의미한다. In Equation 8,

means the first output,

is the maximum value of the acceleration magnitude of the central point.

은 수학식 9와 같이 정의될 수 있다.In Equation 7,

can be defined as in Equation (9).

은 제3 출력을 의미하고,

은 중심점의 분산을 의미한다. 수학식 7에서,

는 0 이상 1 이하의 값으로 설정될 수 있다. 수학식 7에서,

는 제1 보폭 보정 모델 및 제2 보폭 보정 모델에 기초하여 확인된 오차 값을 보폭과 동일 차원을 갖는 보폭 보정값으로 변환하기 위한 양의 상수일 수 있다. 수학식 8을 참조하면

이 양수이고, 수학식 9를 참조하면

이 양수이므로, 수학식 7에서 도출되는 보폭 보정값

은 양의 값을 갖는다. 즉, 사용자가 평소보다 더 큰 보폭으로 보행하였다고 확인될 때, 보폭 보정값

은 양의 값을 가질 수 있다.In Equation 9,

means the third output,

is the variance of the center point. In Equation 7,

may be set to a value of 0 or more and 1 or less. In Equation 7,

may be a positive constant for converting an error value identified based on the first stride length correction model and the second stride length correction model into a stride length correction value having the same dimension as the stride length. Referring to Equation 8,

is a positive number, and referring to Equation 9,

Since this is a positive number, the stride correction value derived from Equation 7

has a positive value. That is, when it is confirmed that the user walked with a larger stride than usual, the stride correction value

may have a positive value.

In operation 940 , if it is determined that the maximum value of the acceleration magnitude of the central point is equal to or less than the first output or the dispersion of the central point is less than or equal to the third output, in operation 950 , at least one processor (eg, the processor 120 ) configures the acceleration of the central point in operation 950 . It may be checked whether the maximum magnitude value is smaller than the second output and the variance of the center point is smaller than the fourth output.

The fact that the maximum value of the acceleration magnitude of the central point is smaller than the second output and the dispersion of the central point is smaller than the fourth output means that the central point representing the gait pattern confirmed based on the second acceleration data is the user of the electronic device 101 greater than the second and fourth outputs representing the usual gait pattern of . In general, the smaller the stride length, the smaller the maximum acceleration magnitude, and the larger the stride length, the larger the maximum acceleration magnitude. It indicates that they walked with a smaller stride.

은 수학식 10과 같이 정의될 수 있다.In operation 950 , if it is confirmed that the maximum value of the acceleration magnitude of the central point is smaller than the second output and the dispersion of the central point is smaller than the fourth output, at least one processor (eg, the processor 120 ) configures the acceleration magnitude of the central point in operation 955 . The stride correction value may be confirmed based on the maximum value, the variance of the center point, the second output, and the fourth output. According to various embodiments, the stride correction value

can be defined as in Equation (10).

은 수학식 11과 같이 정의될 수 있다.In Equation 10,

can be defined as in Equation 11.

은 제2 출력을 의미하고,

은 중심점의 가속도 크기 최댓값을 의미한다. In Equation 11,

means the second output,

is the maximum value of the acceleration magnitude of the central point.

은 수학식 12와 같이 정의될 수 있다.In Equation 9,

can be defined as in Equation (12).

은 제4 출력을 의미하고,

은 중심점의 분산을 의미한다. 수학식 10에서,

는 0 이상 1 이하의 값으로 설정될 수 있다. 수학식 10에서,

는 제1 보폭 보정 모델 및 제2 보폭 보정 모델에 기초하여 확인된 오차 값을 보폭과 동일 차원을 갖는 보폭 보정값으로 변환하기 위한 양의 상수일 수 있다. 수학식 11을 참조하면

이 양수이고, 수학식 12를 참조하면

이 양수이므로, 수학식 10에서 도출되는 보폭 보정값

은 음의 값을 갖는다. 즉, 사용자가 평소보다 더 작은 보폭으로 보행하였다고 확인될 때, 보폭 보정값

은 음의 값을 가질 수 있다.In Equation 12,

means the fourth output,

is the variance of the center point. In Equation 10,

may be set to a value of 0 or more and 1 or less. In Equation 10,

may be a positive constant for converting an error value identified based on the first stride length correction model and the second stride length correction model into a stride length correction value having the same dimension as the stride length. Referring to Equation 11,

is a positive number, and referring to Equation 12,

Since this is a positive number, the stride correction value derived from Equation 10

has a negative value. That is, when it is confirmed that the user walked with a shorter stride than usual, the stride correction value

may have a negative value.

In operation 950 , if it is confirmed that the maximum value of the acceleration magnitude of the central point is equal to or greater than the second output or the dispersion of the central point is greater than or equal to the fourth output, at least one processor (eg, the processor 120 ) performs stride correction in operation 960 . You can confirm that you won't. According to various embodiments, when the at least one processor 120 determines the sum of the first stride length and the stride correction value as the second stride length, the at least one processor 120 determines that the stride correction value is 0, thereby You can confirm that no calibration is performed. According to various embodiments, the at least one processor 120 does not define a stride correction value and may determine that the stride correction is not performed. In this case, the second stride length may be the same as the first stride length.

10 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure; Specifically, FIG. 10 illustrates operations performed to check a stride length in an electronic device that receives a correction model from an external electronic device.

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) may receive the stride correction model from the external electronic device in operation 1010 . there is. According to various embodiments of the present disclosure, the stride length correction model received from the external electronic device may include a first stride length correction model based on a gait frequency and maximum acceleration magnitude and a second stride length correction model based on a gait frequency and variance. The first stride length correction model may include an upper limit model of the first stride length correction model and a lower limit model of the first stride length correction model, and the second stride length correction model includes an upper limit model of the second stride length correction model and an upper limit model of the second stride length correction model. A lower bound model may be included. Details regarding the step length correction model are the same as described above with reference to operation 550 of FIG. 5 and FIGS. 7A and 7B .

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) may identify the type of the external electronic device in operation 1020 . According to various embodiments, the at least one processor 120 may receive a signal indicating the type of the external electronic device from the external electronic device through a communication circuit (eg, the communication module 190 ). Types of the external electronic device include, for example, a handheld device such as a smartphone, a wearable device worn on the wrist, an earphone-type device worn on the ear, a wearable device worn on the finger, a head mounted device worn on the head, and a headphone type. It may include a wearable device and a wearable device worn on the ankle. The head mounted device may take the form of, for example, glasses, a hat, or goggles.

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) may acquire acceleration data through the acceleration sensor in operation 1030 .

According to various embodiments, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) is configured to: The first stride length can be checked. The process of determining the gait frequency based on the acceleration data has been described above with reference to FIG. 3 . Details regarding the stride length model have been described above with reference to operation 240 of FIG. 2 and FIG. 8 .

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs a step length correction value based on the acceleration data and the stride length correction model in operation 1050 . can confirm. Here, the stride length correction model may be the stride length correction model received from the external electronic device in operation 1010 .

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) performs a first step length, a step length correction value, and an external electronic device in operation 1060 . The second stride length may be confirmed based on the weight based on the type of . According to various embodiments, the at least one processor 120 may check a value obtained by multiplying the stride length correction value by a weight and adding the first stride length thereto as the second stride length. According to various embodiments, the weight may vary according to the type of the external electronic device and the type of the electronic device 101 . In general, the greater the acceleration data, the greater the maximum acceleration magnitude and dispersion, and the shorter the distance between the electronic device 101 and the user's feet, the greater the acceleration data. According to various embodiments, when the electronic device 101 is farther from the user's foot than the external electronic device, the weight may be set to a value greater than 1, which increases the stride length correction value. Conversely, when the electronic device 101 has a shorter distance from the user's foot than the external electronic device, the weight may be set to a value smaller than 1, which makes the stride correction value smaller. According to various embodiments, a lookup table of weights corresponding to the type of the external electronic device may be stored in the memory (eg, the memory 130 ) of the electronic device 101 .

11A illustrates an example of a screen displayed on an electronic device according to various embodiments of the present disclosure; Specifically, FIG. 11A illustrates a screen displayed on the display module 160 of the electronic device 101 when a running coaching function of the electronic device (eg, the electronic device 101) is executed.

According to various embodiments, the running coaching function outputs a voice or visual message suggesting to run a little slower if the user's speed is too fast, and a function of outputting a voice or visual message suggesting to run a little faster if the user's speed is too slow can be Referring to FIG. 11A , the screen 1100 may include a user interface 1110 instructing to perform stride correction for improving coaching accuracy.

When the user interface 1110 is selected, the electronic device 101 may obtain acceleration data and check a stride correction model based on the acceleration data. 11B illustrates a screen that may be displayed after a stride model is checked in the electronic device (eg, the electronic device 101).

Referring to FIG. 11B , detailed exercise information 1130 calculated based on the corrected stride length derived based on the stride length correction may be displayed on the screen 1120 . In addition, the screen 1120 may include a message 1140 indicating that more accurate exercise information can be provided because learning on the stride length is completed.

12 illustrates an example of a screen displayed on an electronic device, according to various embodiments of the present disclosure. Specifically, FIG. 12 illustrates an example of a screen 1200 that displays the accumulated activity amount for one day in the electronic device (eg, the electronic device 101 ). Referring to FIG. 12 , daily consumption calories 1210 may be displayed on the screen 1200 . Daily calories consumed 1210 may be displayed in different colors according to the accuracy of the stride length correction model. Referring to FIG. 12 , the daily calories consumed for the 13th and 14th days may be values derived without performing the stride length correction in a state in which a sufficient number of acceleration data to confirm the stride length correction model has not been collected. The daily calorie consumption for the 15th and 16th days may be a value derived when a number of acceleration data enabling confirmation of the stride correction model have been collected, but acceleration data with sufficiently high accuracy have not been collected. The daily calorie consumption for the 17th and 18th days may be a value derived when the acceleration data are sufficiently collected so that the accuracy of the stride length correction model is sufficiently high. According to various embodiments, the at least one processor 120 of the electronic device 101 stores a predetermined section for the number of acceleration data, and sets different daily calorie consumption according to which section the number of collected acceleration data belongs to. can be indicated by color. According to various embodiments, the at least one processor 120 of the electronic device 101 may display a visual characteristic other than a color, for example, a shape or transparency differently. According to various embodiments, the at least one processor 120 of the electronic device 101 may display information about various user activities determined depending on the stride length, in addition to daily calories consumed, as different visual characteristics according to the accuracy of the stride length correction model. can be displayed.

Referring to FIG. 12 , on the screen 1200 , calories consumed by time of the selected date (17 days in the example of FIG. 12 ) may be displayed. According to various embodiments, the at least one processor 120 of the electronic device 101 stores a predetermined section for the number of acceleration data, and sets different calories consumed per time according to which section the number of collected acceleration data belongs to. can be indicated by color. For example, as shown in FIG. 12 , when the number of acceleration data on the screen 1200 is less than the first number, the number of calories consumed per hour 1221 and the number of acceleration data is greater than or equal to the first number, and the second number is greater than the first number. When the number is less than the number of calories consumed per hour 1222 , and when the number of acceleration data is equal to or greater than the second number, the number of calories consumed per hour 1223 may be displayed in different colors. According to various embodiments, when the at least one processor 120 of the electronic device 101 displays calories consumed by time, a visual characteristic other than a color, for example, a shape, or transparency may be differently changed according to the number of acceleration data. can be displayed

According to various embodiments, a walking distance 1230 and a calorie consumption 1240 corresponding to the selected date (17 days in the example of FIG. 12 ) may be displayed on the screen 1200 .

13 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure; Specifically, FIG. 13 illustrates operations performed by an electronic device capable of transmitting and receiving GPS data.

According to various embodiments, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) may determine whether GPS data is available in operation 1310 . According to various embodiments, when the electronic device 101 is located indoors and cannot receive a GPS signal, at least one processor 120 of the electronic device 101 may determine that GPS data is not available. According to various embodiments, when the location of the electronic device 101 cannot be determined because the number of satellites corresponding to the received GPS signal is not large enough, or when the location of the electronic device 101 can be determined only with limited accuracy, the electronic device 101 ) of at least one processor 120 may determine that GPS data is not available.

If it is determined in operation 1310 that the GPS data is available, the at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) is configured to perform the operation 1315 based on the GPS data. You can perform stride correction.

If it is determined in operation 1310 that the GPS data cannot be used, at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101) satisfies the posture change condition in operation 1320 . can check whether A specific method for the at least one processor 120 to determine whether the posture change condition is satisfied will be described later with reference to FIG. 14 .

If it is determined in operation 1320 that the posture change condition is not satisfied, at least one processor (eg, the processor 120) of the electronic device (eg, the electronic device 101) determines that the posture change condition is satisfied. It can be confirmed whether the posture change condition is satisfied until it is confirmed.

When it is determined that the posture change condition is satisfied in operation 1320 , at least one processor (eg, the processor 120 ) of the electronic device (eg, the electronic device 101 ) determines in operation 1330 based on the acceleration data Thus, stride correction can be performed. The stride length correction based on the acceleration data may refer to the stride length correction based on the acceleration data and the stride length correction model.

In FIG. 13 , when it is determined in operation 1310 that GPS data cannot be used, the at least one processor 120 confirms whether the posture change condition is satisfied in operation 1320 . However, according to various embodiments, at least one processor In operation 1310 , when it is determined that GPS data cannot be used, step 120 may perform stride correction based on the acceleration data regardless of the posture change condition. The stride length correction based on the acceleration data may refer to the stride length correction based on the acceleration data and the stride length correction model.

13 shows an example of performing stride correction based on acceleration data when GPS data is not available and performing stride correction based on GPS data when GPS data is available. Accordingly, even when GPS data is available, the at least one processor 120 may perform stride correction based on the acceleration data when the GPS data indicates that the location of the electronic device 101 is within a predetermined area. there is. In this case, in the predetermined area, like an area with many buildings, the trajectory of the GPS signal is distorted due to a multipath problem, so that the accuracy of the location determined when the location of the electronic device 101 is determined using GPS data is not It may be a restricted area.

14 is a flowchart illustrating operations performed by an electronic device according to various embodiments of the present disclosure; Specifically, FIG. 14 illustrates operations performed by the electronic device to determine whether a posture change condition is satisfied.

In operation 1410 , the at least one processor 120 of the electronic device 101 may determine whether gyro sensor data can be checked. According to various embodiments, the at least one processor 120 may determine whether the gyro sensor data can be checked based on whether the gyro sensor included in the electronic device 101 is activated.

When it is confirmed in operation 1410 that the gyro sensor data can be checked, the at least one processor 120 of the electronic device 101 may check the gyro sensor data sensed by the gyro sensor in operation 1420 .

In operation 1425 , the at least one processor 120 of the electronic device 101 may check a roll and a pitch of the electronic device 101 using sensor fusion based on the acceleration data and the gyro sensor data. .

If it is determined in operation 1410 that the gyro sensor data check is not possible, the at least one processor 120 of the electronic device 101 may check whether a posture change condition is satisfied based on the acceleration data without the gyro sensor data.

In operation 1430 , the at least one processor 120 may check an acceleration change amount. According to various embodiments, the acceleration change amount may include at least one of a change amount of the magnitude of the acceleration for a preset time interval or a change amount of a specific direction component of the acceleration for a preset time interval, which is confirmed based on the acceleration data. .

In operation 1435, the at least one processor 120 may determine whether the amount of acceleration change identified in operation 1430 is less than a third threshold. According to various embodiments of the present disclosure, the third threshold may be an amount of change in acceleration capable of confirming a roll and a pitch with a preset level of accuracy based on the acceleration data.

If it is determined in operation 1435 that the amount of acceleration change is equal to or greater than the third threshold, the at least one processor 120 may determine that the posture change condition is not satisfied in operation 1470 .

If it is determined in operation 1435 that the acceleration change amount is less than the third threshold, the at least one processor 120 checks the roll and pitch based on the acceleration data in operation 1440 , and checks the roll change amount and the pitch change amount in operation 1445 . can According to various embodiments, the amount of change of the roll and the amount of change of the pitch may be the difference between the maximum value and the minimum value of the roll and the difference between the maximum value and the minimum value of the pitch within a preset time interval.

In operation 1450 , the at least one processor 120 may determine whether the amount of change in the roll is less than the fourth threshold and whether the amount of change in the pitch is less than the fifth threshold. According to various embodiments of the present disclosure, the fourth threshold and the fifth threshold may be the amount of change in the roll and the amount of change in the pitch by which the user's gait pattern can be confirmed with a preset level of accuracy, respectively.

If it is determined in operation 1450 that the amount of change in the roll is less than the second threshold and the amount of change in the pitch is less than the third threshold, the at least one processor 120 may determine that the posture change condition is satisfied in operation 1460 .

If it is determined in operation 1450 that the amount of change in the roll is equal to or greater than the second threshold or greater than the third threshold, the at least one processor 120 may determine that the posture change condition is not satisfied in operation 1470 .

14, the electronic device 101 has been described on the premise that it includes both the acceleration sensor and the gyro sensor, but according to various embodiments, the electronic device 101 may include the acceleration sensor but not the gyro sensor, In this case, the electronic device 101 may perform operation 1430 after performing operation 1410 without performing operation 1410 , operation 1420 , and operation 1425 .

According to various embodiments, when the electronic device 101 includes both the acceleration sensor and the gyro sensor and the gyro sensor data can always be checked, operation 1410 is omitted and operation 1420 and operation 1425 are performed after operation 1410 is performed. This can be done.

In addition, although an example has been described in which it is checked whether the posture change condition is satisfied based on the amount of change of the roll and pitch in FIG. 14, according to various embodiments, in addition to the amount of change of the roll and the pitch, the user's with a preset level of accuracy It may be determined whether a posture change condition is satisfied based on various parameters that may indicate a state in which a gait pattern may be confirmed.

According to various embodiments of the present disclosure, an electronic device includes an acceleration sensor, a memory for storing a step length model representing a relationship between a walking frequency and a stride length, and at least one processor, wherein the at least one processor is configured to operate through the acceleration sensor Acquire first acceleration data, confirm a step length correction model based on the first acceleration data, obtain second acceleration data through the acceleration sensor, and obtain a gait frequency based on the second acceleration data and the stride length model based on the second acceleration data to check the first stride length, check the step length correction value based on the second acceleration data and the stride length correction model, and determine the second stride length based on the first stride length and the stride length correction value. .

According to various embodiments, the at least one processor checks a plurality of gait characteristic information based on the first acceleration data, and the plurality of gait characteristic information corresponds to one step section, respectively, and the plurality of gait characteristic information Storing the characteristic information, classifying the plurality of gait characteristic information into a plurality of clusters according to a gait pattern, based on the plurality of clusters, a first step length correction model based on the maximum acceleration magnitude and variance and identify a second stride length correction model, wherein the first stride length correction model and the second stride length correction model may be included in the stride length correction model.

According to various embodiments, each of the plurality of gait characteristic information may include a gait frequency, a maximum value of an acceleration magnitude, and a variance.

According to various embodiments of the present disclosure, the at least one processor may be configured to: A number of the stored plurality of gait characteristic information exceeds a first threshold, and a degree of variability in gait frequency included in the stored plurality of gait characteristic information exceeds a second threshold It may be configured to classify the plurality of gait characteristic information according to a gait pattern based on the confirmation that the gait is performed.

According to various embodiments, the first step length correction model may include an upper limit model of the first stride length correction model, and the plurality of center points based on walking frequency and maximum acceleration magnitudes of the plurality of center points corresponding to the plurality of clusters. and a lower limit model of the first step length correction model based on the maximum value of the walking frequency and acceleration magnitude of It may include an upper limit model, and a lower limit model of the second step length correction model based on the walking frequency and variance of the plurality of center points.

According to various embodiments of the present disclosure, the at least one processor may check second gait characteristic information based on the second acceleration data, and a first center point of a first cluster to which the second gait characteristic information belongs among the plurality of clusters. information is checked, the first output is confirmed by applying the upper limit model of the first stride length correction model to the gait frequency included in the second gait characteristic information, and the second gait frequency included in the second gait characteristic information is applied to the gait frequency. The second output is confirmed by applying the lower limit model of the first step length correction model, the third output is confirmed by applying the upper limit model of the second stride length correction model to the gait frequency included in the second gait characteristic information, and the third output is confirmed. 2 The fourth output is confirmed by applying the lower limit model of the second stride length correction model to the gait frequency included in the gait characteristic information, and the maximum acceleration magnitude included in the first central point information is greater than the first output, and the first Based on it is confirmed that the variance included in the first center point information is greater than the third output, the maximum acceleration magnitude included in the first center point information, the variance included in the first center point information, the first output, and the first 3 The stride correction value is checked based on the output, the maximum acceleration magnitude included in the first central point information is smaller than the second output, and it is confirmed that the variance included in the first central point information is smaller than the fourth output based on the first central point information, the maximum acceleration magnitude included in the information, the variance included in the first central point information, the second output, and the fourth output may be configured to check the stride correction value .

According to various embodiments, the at least one processor is configured to identify a walking frequency-acceleration magnitude maximum value model based on the walking frequency and acceleration magnitude maximum values of the plurality of center points, and the walking frequency-acceleration magnitude maximum value model based on the walking frequency-acceleration magnitude maximum value model. , Among the plurality of central points, the maximum value of the acceleration magnitude confirmed by applying the walking frequency of each of the plurality of central points to the upper limit model of the first step length correction model is smaller than the maximum value of the acceleration magnitude of each of the plurality of central points The number of central points is predetermined Check the upper limit model of the first step length correction model to correspond to the first ratio, and based on the walking frequency-acceleration magnitude maximum value model, the walking frequency of each of the plurality of center points among the plurality of center points is the first The first step length correction model in which the number of central points in which the maximum acceleration magnitude confirmed by applying to the lower limit model of the stride correction model is greater than the maximum acceleration magnitude of each of the plurality of central points corresponds to the first predetermined ratio Confirm the lower limit model of the step length correction model can be configured to

According to various embodiments of the present disclosure, the at least one processor is configured to identify a walking frequency-variance model based on the walking frequency and variance of the plurality of center points, and based on the walking frequency-variance model, among the plurality of center points, , the number of center points in which the variance of the walking frequency of each of the plurality of center points is smaller than the variance of each of the plurality of center points by applying to the upper limit model of the second step length correction model corresponds to a predetermined second ratio. Check the upper limit model of the stride length correction model, and based on the walking frequency-acceleration magnitude maximum model, the gait frequency of each of the plurality of central points among the plurality of central points is applied to the lower limit model of the second stride correction model. and identify a lower limit model of the second stride length correction model such that the number of center points in which the maximum acceleration magnitude is greater than the variance of each of the plurality of center points corresponds to the second predetermined ratio.

According to various embodiments, the electronic device further includes a GPS circuit, wherein the at least one processor determines whether GPS communication is available through the GPS circuit, and based on determining that the GPS communication is not available Accordingly, the step length correction value may be confirmed based on the second acceleration data and the stride length correction model.

According to various embodiments, the at least one processor determines whether a posture change condition indicating that the degree of movement of the electronic device is less than a predetermined level is satisfied based on it is determined that the GPS communication is not available; , based on it is confirmed that the posture change condition is satisfied, and confirm a step length correction value based on the second acceleration data and the stride length correction model.

According to various embodiments, an electronic device includes an acceleration sensor, a memory for storing a step length model representing a relationship between a walking frequency and a stride length, a communication circuit, and at least one processor, wherein the at least one processor is configured to: Receive a step length correction model from an external electronic device through a circuit, check a type of the external electronic device, obtain acceleration data through the acceleration sensor, and walk frequency based on the acceleration data and based on the step length model A first step length is checked, a step length compensation value is checked based on the acceleration data and the step length compensation model, and a second step length compensation value is confirmed based on the first step length, the step length compensation value, and a weight based on the type of the external electronic device. It may be configured to check the stride length.

According to various embodiments of the present disclosure, the method performed in the electronic device includes obtaining first acceleration data through an acceleration sensor, identifying a step length correction model based on the first acceleration data, and performing a second operation through the acceleration sensor. The operation of acquiring acceleration data, the operation of confirming the first stride length based on the walking frequency and the stride length model based on the second acceleration data, the operation of confirming the step length correction value based on the second acceleration data and the stride length correction model , and confirming a second stride length based on the first stride length and the stride length correction value.

According to various embodiments, the checking of the step length correction model based on the first acceleration data may include checking a plurality of pieces of gait characteristic information corresponding to each step section based on the first acceleration data; A first step length correction model based on an operation of storing a plurality of gait characteristic information, an operation of classifying the plurality of gait characteristic information into a plurality of clusters according to a gait pattern, and a maximum value of an acceleration magnitude based on the plurality of clusters and checking a second stride length correction model based on variance, wherein the first stride length correction model and the second stride length correction model may be included in the stride length correction model.

According to various embodiments, each of the plurality of gait characteristic information may include a gait frequency, a maximum value of an acceleration magnitude, and a variance.

According to various embodiments, the classifying of the plurality of gait characteristic information according to the gait pattern may include: the number of the stored plurality of gait characteristic information exceeds a first threshold, and a gait frequency included in the stored plurality of gait characteristic information. It may be performed based on it is determined that the variability of ? exceeds the second threshold.

According to various embodiments, the first step length correction model may include an upper limit model of the first stride length correction model, and the plurality of center points based on walking frequency and maximum acceleration magnitudes of the plurality of center points corresponding to the plurality of clusters. and a lower limit model of the first step length correction model based on the maximum value of the walking frequency and acceleration magnitude of It may include an upper limit model, and a lower limit model of the second step length correction model based on the walking frequency and variance of the plurality of center points.

According to various embodiments, the confirming of the step length correction value based on the second acceleration data and the step length correction model may include identifying second gait characteristic information based on the second acceleration data, and the plurality of clusters. checking the first center point information of the first cluster to which the second gait characteristic information belongs, and applying the upper limit model of the first stride length correction model to the gait frequency included in the second gait characteristic information to obtain a first output Confirming operation, operation of confirming a second output by applying the lower limit model of the first stride length correction model to the gait frequency included in the second gait characteristic information, the second gait frequency included in the second gait characteristic information Checking the third output by applying the upper limit model of the second step length correction model, checking the fourth output by applying the lower limit model of the second stride length correction model to the gait frequency included in the second gait characteristic information; Acceleration included in the first central point information based on it being confirmed that the maximum acceleration magnitude included in the first central point information is greater than the first output and that the variance included in the first central point information is greater than the third output Checking the step length correction value based on the maximum magnitude value, the variance included in the first center point information, the first output, and the third output, and the maximum acceleration magnitude value included in the first center point information is the first 2, based on it being confirmed that the variance contained in the first center point information is smaller than the fourth output, the maximum acceleration magnitude included in the first center point information, the variance contained in the first center point information, and the and confirming the step length correction value based on the second output and the fourth output.

According to various embodiments, the checking of the first stride length correction model based on the maximum value of the acceleration magnitude based on the plurality of clusters may include, in the at least one processor, gait frequency and acceleration of the plurality of center points. Based on the maximum size, walking frequency-acceleration size maximum value model is confirmed The operation of confirming the upper limit model of the first stride correction model such that the number of central points in which the maximum acceleration magnitude checked by applying to the upper limit model of the model is smaller than the maximum acceleration magnitude of each of the plurality of central points corresponds to a first predetermined ratio; and based on the walking frequency-acceleration magnitude maximal model, among the plurality of central points, the gait frequency of each of the plurality of central points is applied to the lower limit model of the first step length correction model and the acceleration magnitude maximum value is the plurality of central points. and checking a lower limit model of the first stride length correction model such that the number of center points greater than each acceleration magnitude maximum value corresponds to the first predetermined ratio.

According to various embodiments, the checking of the second stride length correction model based on the variance based on the plurality of clusters may include, based on the walking frequency and variance of the plurality of center points, a walking frequency-variance model. Based on the gait frequency-variance model, the gait frequency of each of the plurality of center points among the plurality of center points is applied to the upper limit model of the second stride length correction model to determine the variance confirmed by the plurality of center points identifying an upper limit model of the second stride length correction model such that the number of center points smaller than each variance corresponds to a second predetermined ratio, and based on the walking frequency-acceleration magnitude maximum model, among the plurality of center points, The number of center points in which the gait frequency of each of the plurality of center points is larger than the variance of each of the plurality of center points by applying to the lower limit model of the second step length correction model to determine the maximum value of the center point corresponds to the predetermined second ratio. It may include checking the lower limit model of the second stride length correction model.

According to various embodiments, the method further includes checking whether GPS communication is available, and the checking of the step length correction value based on the second acceleration data and the step length correction model may include: may be performed in response to confirming that the .

The electronic device according to various embodiments disclosed in this document may have various types of devices. The electronic device may include, for example, a portable communication device (eg, a smart phone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a home appliance device. The electronic device according to the embodiment of the present document is not limited to the above-described devices.

The various embodiments of this document and terms used therein are not intended to limit the technical features described in this document to specific embodiments, but it should be understood to include various modifications, equivalents, or substitutions of the embodiments. In connection with the description of the drawings, like reference numerals may be used for similar or related components. The singular form of the noun corresponding to the item may include one or more of the item, unless the relevant context clearly dictates 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 , B, or C" each may include any one of, or all possible combinations of, items listed together in the corresponding one of the phrases. Terms such as "first", "second", or "first" or "second" may be used simply to distinguish an element from other elements in question, and may refer elements to other aspects (e.g., importance or order) is not limited. It is said that one (eg, first) component is "coupled" or "connected" to another (eg, second) component, with or without the terms "functionally" or "communicatively". When referenced, it means that one component can be connected to the other component directly (eg by wire), wirelessly, or through a third component.

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

According to various embodiments of the present document, one or more instructions stored in a storage medium (eg, internal memory 136 or external memory 138) readable by a machine (eg, electronic device 101) may be implemented as software (eg, the program 140) including For example, the processor (eg, the processor 120 ) of the device (eg, the electronic device 101 ) may call at least one command among one or more commands stored from a storage medium and execute it. This makes it possible for the device to be operated to perform at least one function according to the called at least one command. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The device-readable storage medium 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 a signal (eg, electromagnetic wave), and this term refers to the case where data is semi-permanently stored in the storage medium and It does not distinguish between temporary storage cases.

According to one embodiment, the method according to various embodiments disclosed in this document may be provided as included in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product is distributed in the form of a machine-readable storage medium (eg compact disc read only memory (CD-ROM)), or via an application store (eg Play Store ^TM ) or on two user devices ( It can be distributed (eg downloaded or uploaded) directly between smartphones (eg: smartphones) and online. In the case of online distribution, at least a part of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium such as a memory of a server of a manufacturer, a server of an application store, or a relay server.

According to various embodiments, each component (eg, module or program) of the above-described components may include a singular or a plurality of entities, and some of the plurality of entities may be separately disposed in other components. there is. According to various embodiments, one or more components or operations among the above-described corresponding components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (eg, a module or a program) may be integrated into one 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 among the plurality of components prior to the integration. . According to various embodiments, operations performed by a module, program, or other component are executed sequentially, in parallel, repeatedly, or heuristically, or one or more of the operations are executed in a different order, or omitted. or one or more other operations may be added.

Claims (20)

In an electronic device,
accelerometer,
a memory storing a stride model representing a relationship between gait frequency and stride length; and
at least one processor;
the at least one processor,
acquiring first acceleration data through the acceleration sensor;
check the stride length correction model based on the first acceleration data;
acquiring second acceleration data through the acceleration sensor;
confirming the first stride length based on the gait frequency and the stride length model based on the second acceleration data;
check a step length correction value based on the second acceleration data and the stride length correction model;
and identify a second stride length based on the first stride length and the stride length correction value.
According to claim 1,
the at least one processor,
Based on the first acceleration data, a plurality of gait characteristic information is checked, and the plurality of gait characteristic information corresponds to one step section, respectively,
Storing the plurality of gait characteristic information,
Classifying the plurality of gait characteristic information into a plurality of clusters according to gait patterns,
and identify, based on the plurality of clusters, a first stride correction model based on an acceleration magnitude maximum and a second stride correction model based on variance;
and the first stride length correction model and the second stride length correction model are included in the stride length correction model.
3. The method of claim 2,
The electronic device, wherein each of the plurality of gait characteristic information includes a gait frequency, a maximum acceleration magnitude, and a variance.
The method of claim 3, wherein the at least one processor comprises:
Based on it being confirmed that the number of the stored plurality of gait characteristic information exceeds a first threshold and the degree of variability in gait frequency included in the stored plurality of gait characteristic information exceeds a second threshold, the plurality of gait characteristic information and classify according to a gait pattern.
3. The method of claim 2,
The first step length correction model,
An upper limit model of the first step length correction model, based on the maximum value of the walking frequency and acceleration magnitude of the plurality of center points corresponding to the plurality of clusters, and
a lower limit model of the first step length correction model based on the maximum value of the walking frequency and acceleration magnitude of the plurality of center points;
The second step length correction model,
an upper limit model of the second step length correction model based on the walking frequency and variance of the plurality of center points; and
and a lower limit model of the second step length correction model based on the walking frequency and variance of the plurality of center points.
6. The method of claim 5,
the at least one processor,
Checking second gait characteristic information based on the second acceleration data,
check first center point information of a first cluster to which the second gait characteristic information belongs among the plurality of clusters;
Check the first output by applying the upper limit model of the first stride length correction model to the gait frequency included in the second gait characteristic information,
Checking the second output by applying the lower limit model of the first stride length correction model to the gait frequency included in the second gait characteristic information,
Checking the third output by applying the upper limit model of the second stride length correction model to the gait frequency included in the second gait characteristic information,
A fourth output is confirmed by applying the lower limit model of the second stride length correction model to the gait frequency included in the second gait characteristic information,
Acceleration included in the first central point information based on it being confirmed that the maximum acceleration magnitude included in the first central point information is greater than the first output and that the variance included in the first central point information is greater than the third output Check the stride correction value based on the maximum magnitude value, the variance included in the first center point information, the first output, and the third output,
The acceleration included in the first central point information is based on it being confirmed that the maximum acceleration magnitude included in the first central point information is smaller than the second output and that the variance included in the first central point information is smaller than the fourth output and determine the stride correction value based on a magnitude maximum value, a variance included in the first center point information, the second output, and the fourth output.
6. The method of claim 5,
The at least one processor, based on the walking frequency and the maximum acceleration magnitude of the plurality of center points, identifies a walking frequency-acceleration magnitude maximum value model,
Based on the walking frequency-acceleration magnitude maximum model, among the plurality of central points, each of the plurality of central points is applied to the upper limit model of the first stride length correction model, and the acceleration magnitude maximum value confirmed by each of the plurality of central points Check the upper limit model of the first stride correction model such that the number of center points smaller than the maximum acceleration magnitude of the first step corresponds to a first predetermined ratio,
Based on the walking frequency-acceleration magnitude maximum model, among the plurality of central points, each of the plurality of central points is applied to the lower limit model of the first step length correction model to determine the maximum acceleration magnitude value, each of the plurality of central points and identify a lower bound model of the first stride correction model such that a number of center points greater than an acceleration magnitude maximum of n corresponds to the first predetermined ratio.
6. The method of claim 5,
The at least one processor, based on the walking frequency and variance of the plurality of center points, identifies a walking frequency-variance model,
Based on the walking frequency-variance model, among the plurality of center points, the variance confirmed by applying the walking frequency of each of the plurality of center points to the upper limit model of the second step length correction model is smaller than the variance of each of the plurality of center points confirming the upper limit model of the second stride length correction model such that the number of center points corresponds to a second predetermined ratio;
Based on the walking frequency-acceleration magnitude maximal model, among the plurality of central points, each of the plurality of central points is applied to the lower limit model of the second step length correction model, and the acceleration magnitude maximum value confirmed is each of the plurality of central points and identify a lower bound model of the second stride length correction model such that a number of centroids greater than a variance of n t corresponds to the second predetermined ratio.
According to claim 1,
The electronic device further comprises a GPS circuit,
the at least one processor,
Checking whether GPS data is available through the GPS circuit,
and determine a stride correction value based on the second acceleration data and the stride correction model based on determining that the GPS data is not available.
10. The method of claim 9,
the at least one processor,
Based on it is confirmed that the GPS data is not available, it is determined whether a posture change condition indicating that the degree of movement of the electronic device is less than a predetermined level is satisfied;
and confirm a step length correction value based on the second acceleration data and the stride length correction model based on it being confirmed that the posture change condition is satisfied.
A method performed in an electronic device, comprising:
acquiring first acceleration data through the acceleration sensor;
checking a step length correction model based on the first acceleration data;
acquiring second acceleration data through the acceleration sensor;
confirming the first stride length based on the gait frequency and the stride length model based on the second acceleration data;
checking a step length correction value based on the second acceleration data and the step length correction model; and
and determining a second stride length based on the first stride length and the stride length correction value.
12. The method of claim 11,
The operation of confirming the step length correction model based on the first acceleration data includes:
checking a plurality of pieces of gait characteristic information corresponding to each step section based on the first acceleration data;
storing the plurality of gait characteristic information;
classifying the plurality of gait characteristic information into a plurality of clusters according to gait patterns, and
based on the plurality of clusters, identifying a first stride length correction model based on the maximum acceleration magnitude and a second stride length correction model based on variance;
and the first stride correction model and the second stride correction model are included in the stride correction model.
13. The method of claim 12,
Each of the plurality of gait characteristic information includes a gait frequency, a maximum acceleration magnitude, and a variance.
14. The method of claim 13,
The operation of classifying the plurality of gait characteristic information according to gait patterns includes:
The method is performed on the basis of determining that the number of the stored plurality of gait characteristic information exceeds a first threshold, and the variability of gait frequency included in the stored plurality of gait characteristic information exceeds a second threshold.
13. The method of claim 12,
The first step length correction model,
An upper limit model of the first step length correction model, based on the maximum value of the walking frequency and acceleration magnitude of the plurality of center points corresponding to the plurality of clusters, and
a lower limit model of the first step length correction model based on the maximum value of the walking frequency and acceleration magnitude of the plurality of center points;
The second step length correction model,
an upper limit model of the second step length correction model based on the walking frequency and variance of the plurality of center points; and
and a lower bound model of the second stride length correction model based on the gait frequency and variance of the plurality of center points.
16. The method of claim 15,
Checking the step length correction value based on the second acceleration data and the stride length correction model includes:
checking second gait characteristic information based on the second acceleration data;
checking first center point information of a first cluster to which the second gait characteristic information belongs among the plurality of clusters;
checking the first output by applying the upper limit model of the first stride length correction model to the gait frequency included in the second gait characteristic information;
checking a second output by applying a lower limit model of the first stride length correction model to a gait frequency included in the second gait characteristic information;
confirming a third output by applying the upper limit model of the second stride length correction model to the gait frequency included in the second gait characteristic information;
confirming a fourth output by applying the lower limit model of the second stride length correction model to the gait frequency included in the second gait characteristic information;
Acceleration included in the first central point information based on it being confirmed that the maximum acceleration magnitude included in the first central point information is greater than the first output and that the variance included in the first central point information is greater than the third output checking the stride correction value based on the maximum magnitude value, the variance included in the first center point information, the first output, and the third output, and
Acceleration included in the first central point information based on it being confirmed that the maximum acceleration magnitude included in the first central point information is smaller than the second output and that the variance included in the first central point information is smaller than the fourth output and determining the stride correction value based on the maximum magnitude value, the variance included in the first center point information, the second output, and the fourth output.
16. The method of claim 15,
The operation of confirming the first step length correction model based on the maximum value of the acceleration magnitude based on the plurality of clusters,
the at least one processor, based on the walking frequency and the maximum acceleration magnitude of the plurality of center points, confirming a walking frequency-acceleration magnitude maximum value model;
Based on the walking frequency-acceleration magnitude maximum model, among the plurality of central points, each of the plurality of central points is applied to the upper limit model of the first stride length correction model, and the acceleration magnitude maximum value confirmed by each of the plurality of central points identifying an upper limit model of the first stride correction model such that the number of center points smaller than the maximum acceleration magnitude of
Based on the walking frequency-acceleration magnitude maximum model, among the plurality of central points, each of the plurality of central points is applied to the lower limit model of the first step length correction model to determine the maximum acceleration magnitude value, each of the plurality of central points and identifying a lower bound model of the first stride correction model such that the number of center points greater than the acceleration magnitude maximum of n corresponds to the first predetermined ratio.
16. The method of claim 15,
The operation of confirming the second stride length correction model based on the variance based on the plurality of clusters,
based on the walking frequency and variance of the plurality of center points, confirming a walking frequency-dispersion model;
Based on the walking frequency-variance model, among the plurality of center points, the variance confirmed by applying the walking frequency of each of the plurality of center points to the upper limit model of the second step length correction model is smaller than the variance of each of the plurality of center points identifying an upper limit model of the second stride length correction model such that the number of center points corresponds to a second predetermined ratio; and
Based on the walking frequency-acceleration magnitude maximal model, among the plurality of central points, each of the plurality of central points is applied to the lower limit model of the second step length correction model, and the acceleration magnitude maximum value confirmed is each of the plurality of central points identifying a lower bound model of the second stride length correction model such that a number of centroids greater than a variance of n t corresponds to the second predetermined ratio.
12. The method of claim 11,
The method further comprises the operation of checking whether GPS communication is available,
and determining the step length correction value based on the second acceleration data and the stride length correction model is performed in response to determining that the GPS communication is unavailable.
In an electronic device,
accelerometer,
a memory storing a stride model representing the relationship between gait frequency and stride length;
communication circuitry, and
at least one processor;
the at least one processor,
receiving a stride correction model from an external electronic device through the communication circuit;
Check the type of the external electronic device,
Acceleration data is obtained through the acceleration sensor,
confirming a first stride length based on the gait frequency and the stride length model based on the acceleration data;
check a step length correction value based on the acceleration data and the stride length correction model;
and identify a second stride length based on a weight based on the first stride length, the stride length correction value, and a type of the external electronic device.

Images