Electronic device and method by which electronic device acquires biometric information

Abstract

An electronic device according to an embodiment of the present disclosure comprises at least one sensor, a memory storing instructions, and at least one processor. The instructions, when executed by the at least one processor, may cause the electronic device to: acquire a biometric signal of a user by using the at least one sensor; recognize at least one of an exercise state or an exercise type of the user on the basis of sensor data acquired by using the at least one sensor; determine a weight to be applied to biometric data corresponding to the biometric signal on the basis of at least one of the exercise state or the exercise type; apply the determined weight to the biometric data; acquire biometric data preprocessed by normalizing, on the basis of at least one of the exercise state or the exercise type, the weight-applied biometric data by a designated normalization method; remove noise related to movement of the electronic device from the preprocessed biometric data; and acquire biometric information about the user on the basis of the noise-removed biometric data.

Description

Electronic devices and methods for obtaining biometric information from electronic devices

[0001] Embodiments disclosed in this document relate to a technique for obtaining biometric information of a user in an electronic device.

[0002] Portable electronic devices can provide a variety of functions, in addition to communication with external devices. For example, with the proliferation of various portable electronic devices, such as smartphones and wearable devices, research is being conducted on methods for measuring biometric information using portable electronic devices. By measuring biometric information using portable electronic devices, healthcare services can be provided to users. For example, an electronic device may include at least one biometric sensor for acquiring biometric information and at least one electrode for measuring a user's biosignal.

[0003] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above is applicable as prior art related to the present disclosure.

[0004] An electronic device according to an embodiment disclosed in the present document comprises at least one sensor, a memory storing instructions, and at least one processor, wherein the instructions, when executed by the at least one processor, cause the electronic device to obtain a biosignal of a user using the at least one sensor, recognize at least one of a movement state or a movement type of the user based on sensor data obtained using the at least one sensor, determine a weight to be applied to biodata corresponding to the biosignal based on at least one of the movement state or the movement type, apply the determined weight to the biodata, normalize the biodata to which the weight has been applied based on at least one of the movement state or the movement type using a specified normalization method to obtain preprocessed biodata, remove noise related to a movement of the electronic device from the preprocessed biodata, and obtain bioinformation of the user based on the biodata from which the noise has been removed.

[0005] In addition, a method according to an embodiment disclosed in the present document may include an operation of acquiring a biosignal of a user using at least one sensor of an electronic device, an operation of recognizing at least one of a movement state or a movement type of the user based on sensor data acquired using the at least one sensor, an operation of determining a weight to be applied to biodata corresponding to the biosignal based on at least one of the movement state or the movement type, an operation of applying the determined weight to the biodata, an operation of acquiring a preprocessed biosignal by normalizing the biodata to which the weight has been applied based on at least one of the movement state or the movement type using a specified normalization method, an operation of removing noise related to a movement of the electronic device from the preprocessed biodata, and an operation of acquiring bioinformation of the user based on the biodata from which the noise has been removed.

[0006] In addition, a storage medium according to an embodiment disclosed in the present document may store instructions and / or a program that, when executed by at least one processor of an electronic device, causes the electronic device to obtain a biosignal of a user using at least one sensor of the electronic device, recognize at least one of a movement state or a movement type of the user based on sensor data obtained using the at least one sensor, determine a weight to be applied to biodata corresponding to the biosignal based on at least one of the movement state or the movement type, apply the determined weight to the biodata, normalize the biodata to which the weight has been applied based on at least one of the movement state or the movement type in a specified normalization manner to obtain preprocessed biodata, remove noise related to a movement of the electronic device from the preprocessed biodata, and obtain bioinformation of the user based on the biodata from which the noise has been removed.

[0007] FIG. 1 is a block diagram of an electronic device according to one embodiment.

[0008] FIG. 2 is a drawing for explaining an operation of obtaining biometric information of an electronic device according to one embodiment.

[0009] FIG. 3 is a diagram illustrating an electronic device according to one embodiment.

[0010] FIG. 4 is a diagram illustrating a biometric sensor of an electronic device according to one embodiment.

[0011] FIG. 5 is a diagram for explaining an operation of applying weights to biosignals of an electronic device according to one embodiment.

[0012] Fig. 6 is a flowchart of a method for obtaining biometric information of an electronic device according to one embodiment.

[0013] Fig. 7 is a flowchart of a method for obtaining biometric information of an electronic device according to one embodiment.

[0014] Fig. 8 is a flowchart of a method for obtaining biometric information of an electronic device according to one embodiment.

[0015] FIGS. 9A to 9C are examples of a user interface including biometric information provided by an electronic device according to one embodiment.

[0016] FIGS. 10A and 10B are diagrams showing the results of measuring heart rate in an electronic device according to one embodiment.

[0017] FIG. 11 is a block diagram of an exemplary electronic device capable of performing the operations described in this document.

[0018] Figures 12a and 12b are perspective views of an electronic device according to one embodiment.

[0019] Figure 13 is an exploded perspective view of an electronic device according to one embodiment.

[0020] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0021] FIG. 1 is a block diagram of an electronic device according to one embodiment.

[0022] According to one embodiment, an electronic device (100) (e.g., an electronic device (300) of FIG. 3, an electronic device (1100) of FIG. 11, an electronic device (1200) of FIG. 12, or an electronic device (1301) of FIG. 13) includes at least one sensor (110) (e.g., a PPG sensor (201) of FIG. 2, an acceleration sensor (203) of FIG. 3, a biometric sensor (310) of FIG. 3, a temperature sensor (340) of FIG. 5, a biometric sensor (510) of FIG. 11, a sensor (1170) of FIG. 11, or a sensor module (1211) of FIG. 12), a display (120) (e.g., a display (320) of FIG. 3, a display (1140) of FIG. 11, or a display (1220) of FIGS. 12 and 13), a memory (130) (e.g., a memory (1120) of FIG. 11), and at least one processor (140) (e.g., a memory (1120) of FIG. 11). The electronic device (100) may include a processor (1110). The electronic device (100) may include a wearable device (e.g., a smart watch) worn on at least a part of the user's body. In the present disclosure, it is assumed that the electronic device (100) is a wearable device, but the present disclosure is not limited thereto, and the electronic device (100) may include a device and / or a mobile terminal attached and / or placed at a location corresponding to a part of the user's body.

[0023] According to one embodiment, at least one sensor (110) may include at least one biosensor for measuring a biosignal. For example, the biosignal may include a photoplethysmography (PPG), an electrocardiogram (ECG), a galvanic skin response (GSR), an electroencephalogram (EEG), and / or a bioelectrical impedance analysis (BIA) signal. According to various embodiments, the biosignal may include various biosignals other than PPG, ECG, GSR, EEG, and BIA.

[0024] According to one embodiment, at least one sensor (110) may include at least one sensor for detecting a state and / or movement of the electronic device (100). For example, at least one sensor (110) may include, but is not limited to, an inertial sensor (e.g., an acceleration sensor, a gyro sensor, and / or a geomagnetic sensor), an ambient light sensor, a barometric pressure sensor, a temperature sensor, a proximity sensor, an electrode sensor, and / or an ultrasonic sensor.

[0025] According to one embodiment, the display (120) may display information related to the operation of the electronic device (100). For example, the display (120) may output a user interface including information related to the user's exercise status and / or the user's biometric information. For example, when an application related to the user's health information (or exercise information) is executed, the display (120) may output an execution screen of the application.

[0026] According to one embodiment, the memory (130) may store instructions that control the operation of the electronic device (100) when executed individually or collectively by at least one processor (140). For example, the instructions may be stored in one memory (130) or in multiple memories (130). The memory (130) may at least temporarily store information and / or data related to the operations of the electronic device (100). For example, the memory (130) may store information related to a user's bio-signal, bio-information, and / or exercise status. For example, the memory (130) may store at least one artificial intelligence-based learned model. For example, the learned model may be used to determine a weight to be applied to a bio-signal.

[0027] According to one embodiment, at least one processor (140) can individually or collectively control the operations of the electronic device (100) by executing instructions stored in the memory (130). For example, operations described as being performed by the 'processor (140)' in the present disclosure can be understood as being performed by at least one processor (140) individually or collectively. For example, at least one processor (140) can independently or collectively control each of the operations of the electronic device (100) described below. According to one embodiment, at least one processor (140) can include a circuit such as a central processing unit (CPU), a microprocessor unit (MPU), an application processor (AP), a communication processor (CP), a system on chip (SoC), and / or an integrated circuit (IC).

[0028] The processor (140) can obtain a user's bio-signal. The processor (140) can be worn on at least a part of the user's body (e.g., a wrist). The processor (140) can obtain a user's bio-signal (e.g., a PPG signal) using a bio-sensor (110) (e.g., a PPG sensor (110)). For example, the processor (140) can emit light toward the user's body using the bio-sensor (110) and receive light reflected from the user's body. The processor (140) can obtain the user's bio-signal based on the light received using the bio-sensor (110). The processor (140) can obtain bio-signals of multiple channels using the bio-sensor (110). For example, when the bio-sensor (110) includes multiple light-receiving units, the processor (140) can obtain bio-signals of multiple channels corresponding to the multiple light-receiving units based on light received through each light-receiving unit. The processor (140) may convert the acquired biosignals into ADC (analog to digital) to acquire biodata corresponding to the biosignals. When the processor (140) acquires at least one raw biosignal using the biosensor (110), the processor (140) may filter biodata related to designated bioinformation (e.g., heart rate) based on a filter corresponding to a designated frequency band (e.g., 0.5 Hz to 5 Hz, but not limited thereto) from the raw data corresponding to the raw biosignal. The processor (140) may first normalize the biodata before applying a weight to the biodata. The processor (140) may first normalize biodata corresponding to biosignals of a plurality of channels based on a z-score.

[0029] The processor (140) can recognize at least one of the user's exercise state or exercise type based on sensor data. The processor (140) can obtain sensor data using at least one sensor (110) (e.g., an inertial sensor (e.g., an acceleration sensor (110))). For example, the following description assumes at least one inertial sensor, but the at least one sensor is not limited thereto. For example, the at least one sensor may include a gyro sensor, a temperature sensor, a barometric pressure sensor, a light sensor, a proximity sensor, and / or a biometric sensor.

[0030] For example, the exercise state may include a plurality of specified states. The plurality of states may include, but are not limited to, a state in which the user's body (e.g., wrist) wearing the electronic device (100) is performing a strong exercise, a state in which the user is performing an exercise that generates a regular movement, or a state in which the user is performing an exercise that generates an irregular movement. For example, the processor (140) may recognize a type of exercise (e.g., walking, running, soccer, basketball, swimming, treadmill running, stretching, tennis, golf, or table tennis) performed by the user based on at least one of a biosignal or a movement of the electronic device (100). The type of exercise is not limited to the examples listed above.

[0031] For example, the processor (140) may include information on a movement state and / or movement type mapped to sensor data. The information on a movement state and / or movement type mapped to the sensor data may be pre-stored in the memory of the electronic device. The processor (140) may recognize a movement state and / or movement type corresponding to the sensor data based on the information on a movement state and / or movement type mapped to the pre-stored sensor data.

[0032] The processor (140) can recognize information related to the movement of the electronic device (e.g., movement, posture, and / or energy amount) based on sensor data. The processor (140) can identify the user's exercise state and / or exercise type based on the information related to the movement of the electronic device. For example, the processor (140) can recognize the user's exercise state and / or exercise type based on information about the user's exercise state and / or exercise type mapped to information related to the movement of the electronic device stored in a memory, and / or can infer the user's exercise state and / or exercise type based on information related to the movement of the electronic device.

[0033] The processor (140) may determine a weight to be applied to bio-data corresponding to a bio-signal based on at least one of a movement state or a movement type. For example, depending on the movement state of the user (e.g., intensity of movement of the body of the user wearing the electronic device, movement with regular movement, or movement with irregular movement) or movement type (e.g., stretching, table tennis, walking, running, soccer, or basketball (the movement types are not limited to those listed above)), a bio-signal (or data corresponding to a bio-signal) acquired through the bio-sensor (110) of the electronic device (100) may be detected irregularly, noise due to the movement of the electronic device (100) may be detected, or distortion may occur in the acquired bio-signal. The processor (140) may determine a weight to be applied to the bio-data based on the exercise state and / or exercise type in order to prevent the bio-signal (or data corresponding to the bio-signal) from being distorted or the bio-signal (or data corresponding to the bio-signal) from including unnecessary components (e.g., noise components due to the movement of the electronic device) depending on the exercise state and / or exercise type. For example, the weight may be determined based on information and / or data history when acquiring the previous bio-signal (and / or bio-information). The weight may be determined according to a pre-specified criterion depending on the exercise state and / or exercise type. For example, the processor (140) may determine the weight using an artificial intelligence-based learned model. For example, the processor (140) may analyze the correlation between the acceleration value and the bio-signal (and / or bio-data) using a machine learning (and / or deep learning) model (algorithm), and determine a weight value for correcting the bio-signal (and / or bio-data) based on the movement of the electronic device (100). Learned models based on artificial intelligence may include artificial neural network models.For example, an artificial neural network model may include, but is not limited to, a convolution neural network (CNN), a recurrent neural network (RNN), or a long short term memory (LSTM) network.

[0034] For example, when the electronic device (100) acquires bio-signals of multiple channels, the processor (140) may determine a weight matrix to be applied to multiple bio-data corresponding to the signals of the multiple channels. For example, the weight matrix may include multiple weight values ​​to be applied to the multiple bio-data. For example, the weight matrix (multiple weight values) may indicate which bio-data among the multiple bio-data will be used with a higher proportion to acquire bio-information. For example, the processor (140) may determine a weight for bio-data having relatively less distortion and / or less unnecessary components (noise components) among the multiple bio-data to be higher than a weight for bio-data having relatively more distortion and / or more unnecessary components (noise components) among the bio-data. For example, the processor (140) may determine, among a plurality of biometric data, biometric data having less distortion and / or relatively less unnecessary components (noise components), based on at least one of the values ​​of the biometric data (e.g., values ​​corresponding to the magnitude, waveform, and / or frequency components of the biometric signal corresponding to the biometric data) or information related to the posture, movement, and / or surrounding environment (e.g., temperature and / or humidity) of the electronic device when acquiring the biometric signal corresponding to the biometric data.

[0035] The processor (140) may apply determined weights to biometric data. For example, the processor (140) may obtain weighted biometric data (hereinafter referred to as “weighted sum data”, and “weighted sum data” in the present disclosure may correspond to “weighted sum signal”) by multiplying biometric signals of multiple channels by a weight matrix. For example, when the processor (140) applies weights to each of the biometric signals of multiple channels, the processor (140) may obtain a weighted sum of the biometric signals of multiple channels. For example, the processor (140) may apply different weights to each of the biometric signals of multiple channels and generate a signal (e.g., a weighted sum signal) by summing them. For example, the processor (140) may obtain a signal (e.g., a weighted sum data) by multiplying the weight matrix by a matrix corresponding to the biometric signals of multiple channels, and applying weights to each of the biometric signals.

[0036] The processor (140) may obtain preprocessed biometric data by normalizing weighted biometric data (e.g., weighted sum data) based on at least one of an exercise state or an exercise type using a designated normalization method. For example, the designated normalization method may include, but is not limited to, a normalization method based on a sigmoid function, a normalization method based on a z-score, and / or a method that does not perform normalization.

[0037] For example, the processor (140) may obtain preprocessed biometric data by normalizing the weighted biometric signal based on a sigmoid function and / or normalizing the weighted biometric signal based on a z-score based on a determination that the exercise state is a state in which the user wearing the electronic device (100) is performing a strong exercise with a movement of the body (e.g., wrist) (and / or the exercise type is a first type (e.g., but not limited to, swimming, tennis, golf, or table tennis)). The processor (140) may select biometric data that is more appropriate for obtaining the user's biometric information as the preprocessed biometric data among the biometric data normalized based on the sigmoid function and the biometric data normalized based on the z-score. The processor (140) may generate preprocessed biometric data with relatively less distortion (e.g., a high signal-to-noise ratio) by using the biometric data normalized based on the sigmoid function and the biometric data normalized based on the z-score.

[0038] The processor (140) can obtain preprocessed bio-data by normalizing the weighted bio-signals based on the z-score based on the determination that the exercise state is an exercise that generates regular movements (and / or a second type of exercise type (e.g., but not limited to, walking, tennis, or treadmill)).

[0039] The processor (140) may not normalize the weighted biometric data based on determining that the exercise state is an exercise that causes irregular movements (and / or a third type of exercise type (e.g., but not limited to, soccer or basketball)). The processor (140) may obtain the weighted biometric data as preprocessed biometric data without normalizing it.

[0040] The processor (140) can remove noise related to the movement of the electronic device (100) from the preprocessed biometric data. For example, the processor (140) can perform adaptive noise cancelling (ANC) based on data (for example, sensor data acquired using at least one sensor (110), but not limited thereto) that detects the movement of the electronic device (100) using at least one sensor (110) (for example, an inertial sensor (110) (for example, an acceleration sensor (110)), but not limited thereto). For example, the preprocessed biometric data and the data (for example, sensor data) that detects the movement of the electronic device may include the same frequency components generated according to the movement of the electronic device (and / or the movement of the user). The processor (140) can remove the same frequency components as the data that detects the movement of the preprocessed electronic device from the preprocessed biometric data by performing ANC. The processor (140) can remove or reduce dynamic noise (e.g., motion artifact) contained in the preprocessed biometric data through ANC.

[0041] The processor (140) can acquire the user's biometric information based on the biometric data from which noise has been removed. For example, the processor (140) can monitor the biometric data from which noise has been removed to acquire and / or track the user's biometric information (e.g., heart rate). The processor (140) can generate a user interface including the biometric information. The processor (140) can provide the generated UI through the display (120).

[0042] An electronic device according to one embodiment of the present disclosure generates a preprocessed biosignal (and / or biodata) by applying a weight to each of a plurality of biosignals (and / or biodata) and then adding them together, thereby reducing the amount of distortion or noise due to movement of the electronic device (and / or user) in raw biosignals (and / or biodata) acquired using a biosensor, and increasing the accuracy of bioinformation by acquiring bioinformation based on the preprocessed biosignals (and / or biodata).

[0043] According to various embodiments, the electronic device (100) may omit at least some components, or may further include at least one component (e.g., at least one of the components of the electronic device (300) of FIGS. 3 and 4, the electronic device (1100) of FIG. 11, the electronic device (1200) of FIGS. 12A and 12B, or the electronic device (1301) of FIG. 13).

[0044]

[0045] FIG. 2 is a diagram illustrating an operation of acquiring biometric information of an electronic device according to one embodiment. Hereinafter, the described part described as "signal (e.g., biometric signal)" may refer to an analog signal, but may also refer to a digital signal or digital data converted by an ADC (analog-to-digital converter).

[0046] According to one embodiment, an electronic device (e.g., electronic device (100) of FIG. 1, electronic device (300) of FIG. 3, electronic device (1100) of FIG. 11, electronic device (1200) of FIG. 12, or electronic device (1301) of FIG. 13) may include a PPG sensor (201) (e.g., sensor (110) of FIG. 1, biometric sensor (310) of FIG. 3, biometric sensor (510) of FIG. 5, sensor (1170) of FIG. 11, or sensor module (1211) of FIG. 12)) and an acceleration sensor (203) (e.g., sensor (1170) of FIG. 11, or sensor module (1211) of FIG. 12)). The electronic device may be worn on a part of a user's body (e.g., a wrist). The electronic device may emit light toward a part of the user's body through the PPG sensor (201). An electronic device can receive light reflected from a part of a user's body through a PPG sensor (201). The electronic device can obtain a raw PPG signal of the user based on the light received through the PPG sensor (201). For example, the PPG sensor (201) can include at least one light-emitting unit (e.g., an emitter) and a plurality of light-receiving units (e.g., receivers) (e.g., a photodiode (PD)). The PPG sensor (201) can emit light through at least one light-emitting unit and receive light reflected from the user's body through each of the plurality of light-receiving units. The PPG sensor (201) can obtain a plurality of raw PPG signals based on the light received through each of the plurality of light-receiving units. Each of the plurality of light-receiving units can correspond to a channel for obtaining the raw PPG signals. The PPG sensor (201) can obtain raw PPG signals of a plurality of channels corresponding to each of the plurality of light-receiving units.

[0047] In operation 210, the electronic device may preprocess the raw PPG signals. For example, in operation 221, the electronic device may filter the PPG signals of the plurality of channels in a designated frequency band (e.g., 0.5 Hz to 5 Hz) associated with a heartbeat from each of the raw PPG signals of the plurality of channels through a bandpass filter corresponding to the designated frequency band.

[0048] In operation 223, the electronic device may determine weights to be applied to PPG signals of multiple channels based on sensor data acquired through at least one sensor (e.g., including but not limited to, an acceleration sensor (203).

[0049] For example, the electronic device may store in memory information about the user's exercise state (e.g., stationary (e.g., not exercising), sedentary, exercise with strong movement of the body on which the electronic device is worn, exercise with regular movement, or exercise with irregular movement) and / or exercise type (e.g., a type of sport including walking, running, cycling, tennis, swimming, or basketball) corresponding to the sensor data. The electronic device may recognize the exercise state and / or exercise type corresponding to the sensor data based on the stored information. The electronic device may determine weights to be applied to a plurality of PPG signals based on the exercise state and / or exercise type.

[0050] For example, the weights may be determined based on the posture, intensity, degree (e.g., momentum), pattern, and / or frequency of the movement of the electronic device detected using at least one sensor (e.g., the acceleration sensor (203)). For example, the electronic device may detect the movement of the electronic device using sensor data measured using the acceleration sensor (203). The electronic device may determine the weights to be applied to the PPG signals of the multiple channels based on the movement of the electronic device. Although only the acceleration sensor (203) is illustrated in FIG. 2, the sensors that the electronic device uses to detect movement are not limited thereto. In addition to the movement of the electronic device, the electronic device may also determine the weights by additionally considering the external environment (e.g., external temperature, humidity, and / or illuminance) detected using at least one sensor.

[0051]

[0052] An electronic device may apply weights to each of the PPG signals of a plurality of channels. The electronic device may add up the PPG signals of the plurality of channels to which the weights have been applied to generate a signal for obtaining biometric information (hereinafter referred to as a "weighted sum signal"). For example, the electronic device may determine, based on sensor data acquired using at least one sensor (e.g., an acceleration sensor), the same or different weights of the PPG signals of the plurality of channels corresponding to each of the plurality of light-receiving units based on at least one of movement of each of the plurality of light-receiving units of the PPG sensor, change in position relative to the user's body, change in distance, and / or intensity, waveform, and / or frequency of the raw PPG signal acquired through each of the light-receiving units, and may apply and add the determined weights to each of the PPG signals to generate a weighted sum signal.

[0053] For example, the weights may include a weight matrix including a plurality of weight values ​​corresponding to each of the PPG signals of the plurality of channels. The electronic device may generate a weighted sum signal by multiplying the matrix corresponding to the PPG signals of the plurality of channels by the weight matrix. For example, the distance and / or contact state of the PPG sensor (e.g., a plurality of light-receiving units) of the electronic device with the body (e.g., a wrist) of a user wearing the electronic device may vary depending on the movement of the electronic device (e.g., the movement of the user), and thus, each of the PPG signals of the plurality of channels corresponding to the plurality of light-receiving units may include different levels of noise or have different degrees of distortion. For example, if there is a PPG signal among the plurality of PPG signals that contains a lot of noise or has a high degree of distortion, when the plurality of PPG signals are directly added to acquire biometric information, the accuracy of the acquired biometric information may be reduced. The electronic device may generate a weighted sum signal by applying a different weight to each of the plurality of PPG signals, giving a relatively small weight to a PPG signal that contains a lot of noise or has a high degree of distortion among the plurality of PPG signals. For example, the electronic device may determine a weight of a PPG signal with relatively high distortion to be lower than a weight of a PPG signal with relatively low distortion. The electronic device may determine a weight of a PPG signal with relatively high noise to be lower than a weight of a PPG signal with relatively low noise. For example, the value of the weight may be 0 or greater. If the value of the weight is 0, the PPG signal with the corresponding weight applied may not be used to obtain bio-information (e.g., obtain a weighted sum signal). In operation 225, the electronic device may normalize a weighted PPG signal (e.g., a weighted sum signal) to obtain a preprocessed bio-signal. For example, the electronic device may determine a normalization method based on the user's exercise state and / or exercise type.For example, if the electronic device determines that the user's exercise state is a strong exercise with a body part wearing the electronic device, the electronic device may obtain a preprocessed biosignal by normalizing a biosignal to which weights are applied based on a sigmoid function and / or normalizing a biosignal to which weights are applied based on a z-score. In this case, the electronic device may generate a preprocessed biosignal based on the biosignal normalized based on the sigmoid function and the biosignal normalized based on the z-score. For example, the electronic device may add the biosignal normalized based on the sigmoid function and the biosignal normalized based on the z-score, select a signal having a more suitable value for obtaining bioinformation among the normalized biosignal and the biosignal normalized based on the z-score, and / or apply a weight to the normalized biosignal and the biosignal normalized based on the z-score and add them to generate a preprocessed biosignal. If the electronic device determines that the user is exercising with regular movements, the electronic device may obtain a preprocessed biosignal by normalizing the weighted biosignal based on the z-score. If the electronic device determines that the user is exercising with irregular movements, the electronic device may not normalize the weighted biosignal. The electronic device may obtain the unnormalized weighted sum signal as the preprocessed biosignal.

[0054] For example, the biosignal (i.e., the preprocessed biosignal) that is weighted and preprocessed through operations 223 and 225 may be a signal with reduced distortion and / or noise components due to the movement of the electronic device (i.e., the movement of the user). The electronic device may perform operations (e.g., operations 230 to 250) for acquiring bioinformation using the preprocessed biosignal, thereby improving the accuracy of the bioinformation.

[0055] In operation 230, the electronic device may obtain a signal related to the movement of the electronic device (e.g., the signal may include the posture of the electronic device, the range of the movement, the intensity, and / or the amount of kinetic energy) using at least one sensor (e.g., the acceleration sensor (203)). The electronic device may preprocess the signal related to the movement of the electronic device. For example, the electronic device may convert the obtained signal related to the movement of the electronic device into an ADC and store it, extract only the main components of the signal related to the movement of the electronic device, or remove unnecessary components.

[0056] In operation 240, the electronic device can perform active noise cancelling (ANC). For example, the electronic device can remove components other than the biosignal (e.g., components related to the movement of the electronic device (user)) from the preprocessed biosignal based on signals related to the movement of the preprocessed electronic device. For example, the preprocessed biosignal and the signals related to the movement of the preprocessed electronic device can include the same frequency components generated according to the movement of the electronic device (and / or the movement of the user). The electronic device can remove the same frequency components as the signals related to the movement of the preprocessed electronic device from the preprocessed biosignal by performing ANC. The electronic device can remove or reduce dynamic noise (e.g., motion artifact) included in the preprocessed biosignal through ANC.

[0057] In operation 250, the electronic device can obtain the user's biometric information (e.g., heart rate) based on the noise-removed biometric signal. For example, the electronic device can continuously track the user's heart rate. Based on the tracking results (output), the electronic device can provide the user with a UI containing the biometric information.

[0058]

[0059] FIG. 3 is a diagram illustrating an electronic device according to one embodiment.

[0060] According to one embodiment, the electronic device (300) (e.g., the electronic device (100) of FIG. 1, the electronic device (1100) of FIG. 11, the electronic device (1200) of FIG. 12, or the electronic device (1301) of FIG. 13) comprises a housing (e.g., the housing (1210)), a biosensor (310) (e.g., the sensor (110) of FIG. 1, the PPG sensor (201) of FIG. 2, the biosensor (510) of FIG. 5, the sensor (1170) of FIG. 11, or the sensor module (1211) of FIG. 12), a display (320) (e.g., the display (120) of FIG. 1, the display (1140) of FIG. 11, or the display (1220) of FIGS. 12 and 13), an electrode sensor (not shown), an input device (335, 337), a processor (not shown) (e.g., the processor (140) of FIG. 1 or the processor (1301) of FIG. 11). It may include a processor (1110)), memory (not shown) (e.g., memory (130) of FIG. 1 or memory (1120) of FIG. 11), a communication module (not shown) (e.g., communication circuit (1160) of FIG. 11), a microphone (not shown), a speaker (not shown), a battery (not shown) (e.g., battery (1370), a PMIC (not shown), and a temperature sensor (340).

[0061] In one embodiment, the housing may be configured to be worn on a portion of the user's body (e.g., the wrist). For example, the housing may include a front portion that exposes at least a portion of the display (320), a rear portion that contacts the user's body, and a side portion that is positioned between the front portion and the rear portion. The housing may be composed of, but is not limited to, titanium, stainless steel, aluminum, and / or ceramic materials.

[0062] According to one embodiment, the biosensor (310) can measure a biosignal of a user. For example, the biosensor (310) can include at least one emitter, at least one receiver, and a sensor control unit. The emitter can include at least one light-emitting element that emits light. For example, the light-emitting element can include, but is not limited to, at least one light emitting diode (LED) element, a laser element, or a vertical cavity surface emitting laser (VCSEL) element. The emitter can emit light of a designated band through the light-emitting element. The designated band can correspond to at least one of various wavelengths of light including red light, green light, blue light, yellow light, infrared light, and ultraviolet light.

[0063] For example, the light receiving unit may receive light emitted from the light emitting unit that is reflected or scattered by an external object (e.g., a user), and / or light that is incident by transmitting through an external object. The light receiving unit may include at least one photodiode (PD) or an image sensor (e.g., a camera). For example, the light receiving unit may include at least one filter. The filter may transmit light of a specified band or prevent light of a band other than the specified band from incident on the light receiving unit (e.g., the PD and / or the image sensor).

[0064] For example, the sensor control unit may include an integrated circuit (IC) and / or an analog front-end (AFE) module. The sensor control unit may control the operation of the light emitter and the light receiver, and transmit data (e.g., signals) corresponding to light received through the light receiver to the processor and / or memory.

[0065] For example, the biosensor (310) may include a PPG sensor that detects pulse waves based on light. The electronic device (300) may detect the user's heart rate (HR), heart rate variability (HRV), saturation pulse oxygen (SpO2), and / or blood pressure using the biosensor (310) (e.g., PPG sensor).

[0066] In the present disclosure, the biosensor (310) is described with a focus on a sensor that measures a biosignal based on light, but the biosensor (310) is not limited thereto. For example, the biosensor (310) may include a sensor that measures a biosignal based on sound waves and / or a biomarker sensor. For example, the biomarker sensor may detect a specific substance or component within the user's body. For example, the biomarker sensor may measure cells, blood vessels, proteins, DNA, RNA, and / or metabolites within the user's body, and may detect blood sugar, blood alcohol concentration, advanced glycation end-products (AGEs), and / or antioxidant information. The structure of the biosensor (310) will be described in more detail below with reference to FIG. 4.

[0067] According to one embodiment, the input device may be positioned on a side (e.g., a side housing) of the electronic device (300). For example, the input device may include a button for receiving a physical input from a user and / or a touch sensor for detecting a touch input. The input device may be formed integrally with an electrode sensor (e.g., at least some of the first to fourth electrodes (331, 333, 335, 337)).

[0068] The memory can store information and / or data (e.g., sensor data and / or communication data). The memory can be formed in a configuration integrated with the processor.

[0069] The communication module can transmit and receive information and / or data with an external electronic device (300) via wired or wireless communication. For example, the communication module can support, but is not limited to, Bluetooth, BLE (Bluetooth Low Energy), Zigbee, Wi-Fi, cellular communication, NFC (Near Field Communication), ANT+ (Advanced and Adaptive Network Technology Plus), RFID (Radio Frequency Identification), UWB (Ultra Wide Band), and / or GNSS (Global Navigation Satellite System) communication protocols. For example, the communication module can include at least one antenna.

[0070] The battery can supply power to the electronic device (300). A power management integrated circuit (PMIC) can charge the battery based on power supplied from an external power source, or supply power from the battery to components within the electronic device (300).

[0071] The microphone can detect the user's voice or external sounds. The speaker can output sounds corresponding to information and / or data processed by the electronic device (300) (e.g., processor).

[0072] The display (320) can visually display information and / or data generated, processed, and / or stored by the electronic device (300). For example, the display (320) can display a user interface that includes the user's biometric information.

[0073] The temperature sensor (340) can measure the temperature of an external object (e.g., a user), an external temperature, and / or the temperature of an internal component of the electronic device (300). The temperature sensor (340) can include a contact temperature sensor (340) and / or a non-contact temperature sensor (340). The temperature sensor (340) can transmit the measured temperature to a memory and / or a processor. For example, the measured temperature can be used to determine the body temperature of the user.

[0074] The electrode sensor may include first to fourth electrodes (331, 333, 335, 337). Although the first to fourth electrodes (331, 333, 335, 337) are illustrated in FIG. 3, the number of electrodes is not limited thereto, and the electrode sensor may include at least one electrode. For example, the first to fourth electrodes (331, 333, 335, 337) may be used to measure a biosignal of the user by coming into contact with the user's body. For example, the electrode sensor may detect electrical characteristics (e.g., voltage, current, impedance) of the user's body through at least one of the first to fourth electrodes (331, 333, 335, 337). For example, the electrode sensor can detect the user's electrocardiogram (ECG), electromyogram (EMG), and / or electroencephalogram (EEG). The electrode sensor can measure the user's body impedance analysis (BIA) and detect the user's body composition (e.g., body fat and body water) using the first to fourth electrodes (331, 333, 335, 337). For example, at least one of the first to fourth electrodes (331, 333, 335, 337) (e.g., the first electrode (331) or the second electrode (333)) can be used to increase the accuracy of measuring the biosignal by adjusting the potential reference of the biosignal. The electrode sensor can detect EDA (electrodermal activity) by measuring the user's skin electrical response using at least two of the first to fourth electrodes (331, 333, 335, 337). For example, EDA can include skin conductance (GSR, EDR), electrodermal response (EDR), and / or phychogalvanic reflex (PGR).

[0075] For example, although not illustrated in FIG. 3, the electronic device (300) may further include at least one sensor in addition to the biosensor (310), the electrode sensor, and the temperature sensor (340). For example, the electronic device (300) may include a barometric pressure sensor that detects air pressure and / or a light sensor that detects the brightness of external light, and the types of sensors included in the electronic device (300) are not limited thereto.

[0076] The processor can control the overall operation of the electronic device (300). For example, the processor can control the operation of each component included in the electronic device (300).

[0077] At least one of the components of the electronic device (300) can be mounted on a flexible printed circuit board (FPCB) placed inside the housing.

[0078]

[0079] FIG. 4 is a diagram illustrating a biometric sensor of an electronic device according to one embodiment.

[0080] According to one embodiment, an electronic device (e.g., an electronic device (100) of FIG. 1, an electronic device (300) of FIG. 3, an electronic device (1100) of FIG. 11, an electronic device (1200) of FIG. 12, or an electronic device (1301) of FIG. 13) may include at least one biosensor (310) (e.g., a sensor (110) of FIG. 1, a PPG sensor (201) of FIG. 2, a biosensor (510) of FIG. 5, a sensor (1170) of FIG. 11, or a sensor module (1211) of FIG. 12). The biosensor (310) may include at least one light-emitting element (410) (e.g., an emitter) and at least one light-receiving element (420) (e.g., a receiver).

[0081] The biosensor (310) can emit light of a specified wavelength using at least one light-emitting element (410). The light emitted from the light-emitting element (410) can be reflected or scattered by an external object (e.g., a user). At least some of the light reflected or scattered by the external object can be incident on at least one light-receiving element (420). The biosensor (310) can obtain a biosignal based on the light received using the at least one light-receiving element (420). For example, the biosensor (310) can obtain a biosignal of the user based on light reflected by the user and received through the light-receiving element (420).

[0082] For example, each of the light-emitting elements (410) can be used to measure the same or different biosignals. For example, the electronic device can emit light through the fifth light-emitting element (419) and obtain a biosignal for antioxidant measurement based on the light received through at least one light-receiving element (420). The electronic device can emit light through the third light-emitting element (415) and the fourth light-emitting element (417) and obtain a biosignal for measuring advanced glycation end-products (AGEs) based on the light received through at least one light-receiving element (420). The electronic device can emit green light through the first light-emitting element (411) and the second light-emitting element (413) and obtain a PPG signal based on the light received through at least one light-receiving element (420). For example, when receiving light through a plurality of light-receiving elements (420), the biosensor (310) can obtain biosignals of a plurality of channels corresponding to each of the plurality of light-receiving elements (420). For example, when receiving light through a first light-receiving element (421), a second light-receiving element (423), a third light-receiving element (425), and a fourth light-receiving element (427), the biosensor (310) can obtain a PPG signal of a first channel corresponding to the first light-receiving element (421), a PPG signal of a second channel corresponding to the second light-receiving element (423), a PPG signal of a third channel corresponding to the third light-receiving element (425), and a PPG signal of a fourth channel corresponding to the fourth light-receiving element (427). The biosignals corresponding to each channel can be converted into data values ​​through an analog to digital converter (ADC) and stored. The biosignals corresponding to each channel can be summed, grouped, and / or compensated (e.g., weighted) to obtain bioinformation.

[0083] According to various embodiments, the operation of the light emitting elements (410) and the light receiving elements (420) (e.g., the wavelength (band) of the light emitted and / or the combination of the light emitting elements (410) that operate together) and the acquired biosignals are not limited to those described above. In FIG. 4, five light emitting elements (410) and four light receiving elements (420) are illustrated, but the number, positions, and arrangement of the light emitting elements (410) and the light receiving elements (420) included in the biosensor (310) are not limited to those illustrated in FIG. 4.

[0084]

[0085] FIG. 5 is a diagram for explaining an operation of applying weights to biosignals of an electronic device according to one embodiment. For example, FIG. 5 assumes a case in which biosignals of four channels are acquired through a biosensor (510) (e.g., sensor (110) of FIG. 1, PPG sensor (201) of FIG. 2, biosensor (310) of FIGS. 3 and 4, sensor (1170) of FIG. 11, or sensor module (1211) of FIG. 12), but is not limited thereto.

[0086] A biosensor (510) (e.g., a PPG sensor) can emit light and obtain biosignals (520) of multiple channels (e.g., a biosignal of a first channel (521), a biosignal of a second channel (522), a biosignal of a third channel (523), and a biosignal of a fourth channel (524)) based on the light reflected and received by the user.

[0087] An electronic device (e.g., an electronic device (100) of FIG. 1, an electronic device (300) of FIG. 3, an electronic device (1100) of FIG. 11, an electronic device (1200) of FIG. 12, or an electronic device (1301) of FIG. 13) may determine a weight matrix (530) to be applied to bio-signals (520) of multiple channels based on a user's exercise state and / or exercise type. For example, the electronic device may detect sensor data (e.g., data related to the movement of the electronic device, data of external temperature, and / or external air pressure) acquired using at least one sensor. The electronic device may determine the user's exercise state and / or exercise type based on the sensor data. For example, the exercise state may be classified according to a specified criterion. For example, the electronic device may determine whether the user is exercising with a strong movement of a body part (e.g., a wrist) on which the user is wearing the electronic device, exercising with regular movements, or exercising with irregular movements. For example, the specified criteria may be determined based on information about the exercise state and / or exercise type mapped to sensor data stored in the electronic device.

[0088] The electronic device may determine the values ​​of the weight matrix (530) (w11, w12, w13, w14, w21, w22, w23, w24, w31, w32, w33, w34, w41, w42, w43, w44) based at least in part on the exercise state. For example, the electronic device may directly determine the values ​​of the weight matrix (530) based on sensor data without determining the exercise state and / or exercise type.

[0089] For example, the weight matrix (530) may be determined to correspond to the number of channels of the biosignal. For example, when the number of channels is N, the weight matrix (530) may be a matrix.

[0090] An electronic device can obtain a weighted biosignal (540) (e.g., a weighted sum signal) using a biosignal of multiple channels and a weight matrix (530). The electronic device can obtain a weighted biosignal (540) according to the following mathematical expression 1.

[0091]

[0092]

[0093] In mathematical expression 1, the desired signal means a matrix representing a weighted biosignal (540) (weighted sum signal), the weight matrix means a weight matrix (530), and the raw signal means a matrix representing biosignals (520) corresponding to multiple channels before applying weights. For example, the electronic device can obtain a signal (540) (referred to as a 'weighted sum signal' in the present disclosure) ([desired signal]) that is a sum of biosignals (520) to which weights are applied by multiplying the weight matrix (530) ([weight matrix]) and the matrix of biosignals (520) ([raw signal]).

[0094]

[0095] An electronic device according to one embodiment of the present disclosure (e.g., the electronic device (100) of FIG. 1, the electronic device (300) of FIG. 3, the electronic device (1100) of FIG. 11, the electronic device (1200) of FIG. 12, or the electronic device (1301) of FIG. 13) may include at least one sensor, a memory for storing instructions, and at least one processor.

[0096] The above instructions, when executed by the at least one processor, may cause the electronic device to obtain a user's biosignal using the at least one sensor.

[0097] The instructions, when executed by the at least one processor, may cause the electronic device to recognize at least one of the user's exercise state or exercise type based on sensor data acquired using the at least one sensor.

[0098] The instructions, when executed by the at least one processor, may cause the electronic device to determine a weight to apply to bio-data corresponding to the bio-signal based on at least one of the movement state or the movement type.

[0099] The above instructions, when executed by the at least one processor, may cause the electronic device to apply the determined weight to the biometric data.

[0100] The instructions, when executed by the at least one processor, may cause the electronic device to obtain preprocessed biometric data by normalizing the weighted biometric data in a specified normalization manner based on at least one of the exercise state or the exercise type.

[0101] The instructions, when executed by the at least one processor, may cause the electronic device to remove noise related to movement of the electronic device from the preprocessed biometric data.

[0102] The above instructions, when executed by the at least one processor, may cause the electronic device to obtain biometric information of the user based on the biometric data from which noise has been removed.

[0103] The at least one sensor may include a photoplethysmogram (PPG) sensor. The biosignal may include at least one signal representing the user's heart rate measured using the PPG sensor. The bioinformation may include information related to the heart rate.

[0104] The instructions, when executed by the at least one processor, may cause the electronic device to recognize at least one motion state or motion type among a plurality of designated motion states or a plurality of designated motion types based on the sensor data.

[0105] The above-mentioned normalization method may include at least one of a normalization method based on a sigmoid function, a normalization method based on a z-score, or a method that does not perform normalization.

[0106] The above instructions, when executed by the at least one processor, may cause the electronic device to first normalize biometric data corresponding to the acquired biometric signal before applying the weight to the biometric data.

[0107] The above instructions, when executed by the at least one processor, may cause the electronic device to apply the weight to the primary normalized biometric data.

[0108] The instructions, when executed by the at least one processor, may cause the electronic device to perform adaptive noise cancelling (ANC) on the preprocessed biometric data, at least in part based on the sensor data.

[0109] The above instructions, when executed by the at least one processor, may cause the electronic device to obtain a raw biosignal using the at least one sensor.

[0110] The instructions, when executed by the at least one processor, may cause the electronic device to extract the biometric data from raw data corresponding to the raw biometric signal based on a filter corresponding to a specified frequency band.

[0111] The at least one sensor may include a biosensor including light receiving units configured to acquire a plurality of biosignals corresponding to a plurality of channels.

[0112] The above instructions, when executed by the at least one processor, may cause the electronic device to obtain a plurality of biosignals corresponding to the plurality of channels based on light received using the light receiving units of the bogut of the biosensor.

[0113] The instructions, when executed by the at least one processor, may cause the electronic device to determine a weight matrix including weight values ​​for a plurality of bio-data corresponding to each of the plurality of bio-signals.

[0114] The above instructions, when executed by the at least one processor, may cause the electronic device to obtain biometric data to which the weights have been applied by applying the weight values ​​to the biometric data and then summing them based on the weight matrix.

[0115] The electronic device may further include a display. The instructions, when executed by the at least one processor, may cause the electronic device to provide a user interface (UI) including information related to at least one of the exercise state or the exercise type and the biometric information through the display.

[0116] The above instructions, when executed by the at least one processor, may cause the electronic device to determine the weights using a model learned based on artificial intelligence.

[0117] An electronic device according to one embodiment can improve the accuracy of obtaining bio-information by reducing noise input differently according to the movement of the user (e.g., movement of the electronic device) while the user is wearing the electronic device and compensating for distortion of the bio-signals (and / or bio-data) by applying weights corresponding to the movement of the user (e.g., movement of the electronic device) to the bio-signals (and / or bio-data) and thereby compensating for distortion of the bio-signals (and / or bio-data). An electronic device according to one embodiment of the present disclosure can improve the signal-to-noise ratio of the bio-signals (and / or bio-data) by applying different weight matrices and different normalization methods corresponding to the movement state (or movement type) of the bio-signals (and / or bio-data). An electronic device according to an embodiment of the present disclosure can reduce a noise level and improve the accuracy of biometric information measurement by obtaining biometric information based on a weighted sum of a plurality of biometric signals (and / or biometric data) without individually processing the biometric signals (and / or biometric data) corresponding to a plurality of channels. An electronic device according to an embodiment of the present disclosure can reduce the amount of distortion or noise due to movement of an electronic device (and / or a user) in a raw biometric signal (and / or biometric data) obtained using a biometric sensor by applying a weight to each of a plurality of biometric signals (and / or biometric data) and then adding them to generate a preprocessed biometric signal (and / or biometric data), and can obtain biometric information based on the preprocessed biometric signal (and / or biometric data), thereby improving the accuracy of the biometric information.

[0118]

[0119] Fig. 6 is a flowchart of a method for obtaining biometric information of an electronic device according to one embodiment.

[0120] According to one embodiment, in operation 610, an electronic device (e.g., an electronic device (100) of FIG. 1, an electronic device (300) of FIG. 3, an electronic device (1100) of FIG. 11, an electronic device (1200) of FIG. 12, or an electronic device (1301) of FIG. 13) may obtain a biosignal of a user. The electronic device may be worn on at least a part of the user's body (e.g., a wrist). The electronic device may obtain a biosignal (e.g., a PPG sensor) of the user by using a biosensor (e.g., a PPG sensor) (e.g., a sensor (110) of FIG. 1, a PPG sensor (201) of FIG. 2, a biosensor (310) of FIGS. 3 and 4, a biosensor (510) of FIG. 5, a sensor (1170) of FIG. 11, or a sensor module (1211) of FIG. 12). For example, the electronic device may emit light toward the user's body and receive light reflected from the user's body by using the biosensor. An electronic device may acquire a user's biosignal based on light received using a biosensor. The electronic device may acquire biosignals of multiple channels using the biosensor. For example, if the biosensor includes multiple light-receiving units, the electronic device may acquire biosignals of multiple channels corresponding to the multiple light-receiving units based on light received through each light-receiving unit. The electronic device may convert the acquired biosignals into ADC (analog-to-digital) to acquire biodata corresponding to the biosignals. When the electronic device acquires at least one raw biosignal using the biosensor, the electronic device may filter biodata related to specified bioinformation (e.g., heart rate) based on a filter corresponding to a specified frequency band (e.g., but not limited to, 0.5 Hz to 5 Hz) from raw data corresponding to the raw biosignal. The electronic device may perform primary normalization on the biodata (e.g., prior to applying weights to the biodata in operation 640).The electronic device can first normalize biometric data corresponding to biometric signals of multiple channels based on z-scores.

[0121] According to one embodiment, in operation 620, the electronic device can recognize at least one of the user's exercise state or exercise type based on sensor data. The electronic device can obtain the sensor data using at least one sensor (e.g., an inertial sensor (e.g., an acceleration sensor)). For example, in the following description, at least one sensor is assumed to be an inertial sensor, but the at least one sensor is not limited thereto. For example, the at least one sensor may include a gyro sensor, a temperature sensor, a barometric pressure sensor, a light sensor, a proximity sensor, and / or a biometric sensor.

[0122] For example, an exercise state may include a plurality of specified states. The plurality of states may include, but are not limited to, a state in which the user wearing the electronic device is exercising with strong body movement (e.g., wrist), an exercise that generates regular movements, or an exercise that generates irregular movements. For example, the electronic device may recognize the type of exercise the user is exercising (e.g., walking, running, soccer, basketball, swimming, treadmill running, stretching, tennis, golf, or table tennis) based on at least one of a biosignal or the movement of the electronic device. The types of exercise are not limited to the examples listed above.

[0123] For example, an electronic device may include information about a movement state and / or movement type mapped to sensor data. The information about the movement state and / or movement type mapped to the sensor data may be pre-stored in the memory of the electronic device. The electronic device may recognize a movement state and / or movement type corresponding to the sensor data based on the information about the movement state and / or movement type mapped to the previously stored sensor data.

[0124] An electronic device can recognize information related to the movement of the electronic device (e.g., movement, posture, and / or energy amount) based on sensor data. The electronic device can identify a user's exercise state and / or exercise type based on information related to the movement of the electronic device. For example, the electronic device can recognize a user's exercise state and / or exercise type based on information about the user's exercise state and / or exercise type mapped to information related to the movement of the electronic device stored in memory, and / or can infer a user's exercise state and / or exercise type based on information related to the movement of the electronic device.

[0125] According to one embodiment, in operation 630, the electronic device may determine a weight to be applied to biometric data corresponding to a biometric signal based on at least one of an exercise state or an exercise type. For example, depending on the exercise state of the user (e.g., intensity of movement of the body of the user wearing the electronic device, exercise with regular movement, or exercise with irregular movement) or exercise type (e.g., stretching, table tennis, walking, running, soccer, or basketball (exercise types are not limited to those listed above)), the biometric signal (or data corresponding to the biometric signal) acquired through the biometric sensor of the electronic device may be detected irregularly, noise due to the movement of the electronic device may be detected, or distortion may occur in the acquired biometric signal. The electronic device may determine a weight to be applied to the biometric data based on the exercise state and / or exercise type in order to prevent the biometric signal (or data corresponding to the biometric signal) from being distorted or the biometric signal (or data corresponding to the biometric signal) from including unnecessary components (e.g., noise components due to the movement of the electronic device) depending on the exercise state and / or exercise type. For example, weights may be determined based on information and / or data history from previous biosignal (and / or biometric) acquisitions. Weights may also be determined based on predefined criteria, depending on exercise status and / or exercise type. For example, an electronic device may determine weights using an artificial intelligence-based, learned model.

[0126] For example, when an electronic device acquires biometric signals of multiple channels in operation 610, the electronic device may determine a weight matrix to be applied to multiple biometric data corresponding to the signals of the multiple channels. For example, the weight matrix may include multiple weight values ​​to be applied to the multiple biometric data. For example, the weight matrix (multiple weight values) may indicate which biometric data among the multiple biometric data will be used with a higher proportion to acquire biometric information. For example, the electronic device may determine a weight for biometric data having relatively less distortion and / or less unnecessary components (noise components) among the multiple biometric data to be higher than a weight for biometric data having relatively more distortion and / or more unnecessary components (noise components) among the biometric data. For example, the electronic device may determine, among a plurality of biometric data, biometric data having less distortion and / or relatively less unnecessary components (noise components) based on at least one of the values ​​of the biometric data (e.g., values ​​corresponding to the magnitude, waveform, and / or frequency components of the biometric signal corresponding to the biometric data) or information related to the posture, movement, and / or surrounding environment (e.g., temperature and / or humidity) of the electronic device when acquiring the biometric signal corresponding to the biometric data.

[0127] According to one embodiment, in operation 640, the electronic device may apply a determined weight to the biometric data. For example, the electronic device may obtain weighted biometric data (hereinafter referred to as “weighted sum data”, and “weighted sum data” may correspond to “weighted sum signal” in the present disclosure) by multiplying the biometric signals of the plurality of channels by a weight matrix. For example, the electronic device may obtain a signal (e.g., weighted sum data) obtained by summing the biometric signals by applying a weight to each biometric signal by multiplying the weight matrix by a matrix corresponding to the biometric signals of the plurality of channels.

[0128] According to one embodiment, in operation 650, the electronic device may obtain preprocessed biometric data by normalizing weighted biometric data (e.g., weighted sum data) based on at least one of an exercise state or an exercise type using a designated normalization method. For example, the designated normalization method may include, but is not limited to, a normalization method based on a sigmoid function, a normalization method based on a z-score, and / or a method that does not perform normalization.

[0129] For example, the electronic device may obtain preprocessed biometric data by normalizing the weighted biometric signal based on a sigmoid function and / or normalizing the weighted biometric signal based on a z-score based on a determination that the exercise state is a state in which the user wearing the electronic device is exercising with strong movement of the body (e.g., wrist) of the user (and / or the exercise type is a first type (e.g., but not limited to, swimming, tennis, golf, or table tennis)). The electronic device may select biometric data that is more suitable for obtaining biometric information of the user from among the biometric data normalized based on the sigmoid function and the biometric data normalized based on the z-score as the preprocessed biometric data. The electronic device may generate preprocessed biometric data with relatively less distortion (e.g., high signal-to-noise ratio) by using the biometric data normalized based on the sigmoid function and the biometric data normalized based on the z-score.

[0130] The electronic device may obtain preprocessed bio-data by normalizing the weighted bio-signals based on a z-score, based on whether the exercise state is determined to be an exercise that generates regular movements (and / or a second type of exercise type (e.g., but not limited to, walking, tennis, or treadmill)).

[0131] The electronic device may not normalize the weighted biometric data based on the determination that the exercise state is an exercise that causes irregular movements (and / or a third type of exercise type (e.g., but not limited to, soccer or basketball)). The electronic device may acquire the weighted biometric data as preprocessed biometric data without normalizing it.

[0132] According to one embodiment, in operation 660, the electronic device may remove noise related to the movement of the electronic device from the preprocessed biometric data. For example, the electronic device may perform adaptive noise cancelling (ANC) based on data (e.g., including but not limited to, sensor data acquired in operation 620) that detects the movement of the electronic device using at least one sensor (e.g., but not limited to, an inertial sensor (e.g., an acceleration sensor). For example, the preprocessed biometric data and the data (e.g., sensor data) that detects the movement of the electronic device may include the same frequency components generated according to the movement of the electronic device (and / or the movement of the user). The electronic device may remove the same frequency components as the data that detects the movement of the preprocessed electronic device from the preprocessed biometric data by performing ANC. The electronic device may remove or reduce dynamic noise (e.g., motion artifact) included in the preprocessed biometric data through ANC.

[0133] According to one embodiment, in operation 670, the electronic device may acquire the user's biometric information based on the de-noised biometric data. For example, the electronic device may monitor the de-noised biometric data to acquire and / or track the user's biometric information (e.g., heart rate). The electronic device may generate and provide a user interface including the biometric information.

[0134] According to a method according to one embodiment of the present disclosure, by applying a weight to each of a plurality of biosignals (and / or biodata) and then adding them together to generate a preprocessed biosignal (and / or biodata), the amount of distortion or noise due to movement of an electronic device (and / or a user) in a raw biosignal (and / or biodata) acquired using a biosensor can be reduced, and the bioinformation can be acquired based on the preprocessed biosignal (and / or biodata), thereby increasing the accuracy of the bioinformation.

[0135] According to various embodiments, the order of at least some of the operations of FIG. 6 may be changed, or they may be performed simultaneously, or at least one operation may be omitted, or at least one operation (e.g., at least one of the operations of FIGS. 7 and 8 ) may be added. For example, operation 620 may be performed independently and / or in parallel with other operations. The operations of FIG. 6 may be performed independently of, integrated with, or in conjunction with the operations of FIGS. 7 and 8 .

[0136]

[0137] Fig. 7 is a flowchart of a method for acquiring biometric information from an electronic device according to one embodiment. Below, any description overlapping with that of Fig. 6 will be omitted or briefly described.

[0138] According to one embodiment, in operation 710, an electronic device (e.g., the electronic device (100) of FIG. 1, the electronic device (300) of FIG. 3, the electronic device (1100) of FIG. 11, the electronic device (1200) of FIG. 12, or the electronic device (1301) of FIG. 13) may acquire raw PPG signals of a user using a biosensor (e.g., a PPG sensor). For example, the raw PPG signals may include a biosignal component and noise (e.g., a noise component due to movement of the electronic device, a distorted signal component, and / or white noise).

[0139] In one embodiment, in operation 720, the electronic device may extract PPG signals in a specified frequency band. For example, the electronic device may extract PPG signals in a specified frequency band from raw PPG signals using a filter corresponding to a specified frequency band (e.g., 0.5 Hz to 5 Hz) associated with desired biometric information (e.g., heart rate).

[0140] According to one embodiment, in operation 730, the electronic device may apply weights to the extracted PPG signals to correct for signal distortion caused by movement of the electronic device during exercise by the user. For example, when the electronic device acquires the user's PPG signals while being worn on the user's body (e.g., wrist), movement of the electronic device may occur according to the user's movement. In this case, the PPG signals measured by the electronic device may be distorted due to the movement of the electronic device. For example, the PPG signals acquired by the electronic device may include signal components distorted due to the movement of the electronic device (e.g., frequency components generated according to the movement of the user and / or the electronic device). Each of the PPG signals acquired by the electronic device may have a different degree of distortion and / or include a different amount of noise (noise components). The electronic device may determine a weight to be applied to the biosignal based on sensor data acquired through at least one sensor to generate a signal (e.g., a preprocessed signal) with less distortion or noise based on the PPG signals. For example, an electronic device may recognize a user's exercise state and / or exercise type based on sensor data, and determine weights to be applied to PPG signals based on the exercise state and / or exercise type. The electronic device may apply the determined weights to the PPG signals. The electronic device may generate a weighted sum signal by summing the weighted PPG signals. For example, when generating the weighted sum signal, the electronic device may relatively less reflect (i.e., apply relatively low weights to) PPG signals that have relatively high distortion and / or relatively high noise levels among the PPG signals.For example, an electronic device can compensate for distortion and noise caused by movement of the electronic device (and / or the user) when acquiring multiple PPG signals using a biometric sensor by generating a weighted sum signal for multiple PPG signals, and can acquire a signal (e.g., a weighted sum signal) suitable for acquiring biometric information. By generating the weighted sum signal, the electronic device can reduce the influence of distortion and / or noise components included in PPG signals prior to noise canceling (e.g., ANC of 740 operation).

[0141] The electronic device can obtain a preprocessed biosignal by normalizing a weighted biosignal (e.g., a weighted sum signal). The electronic device can obtain a preprocessed biosignal by normalizing the weighted biosignal (e.g., a weighted sum signal) based on the exercise state and / or exercise type based on a sigmoid function and / or a z-score. The electronic device can obtain a weighted biosignal (e.g., a weighted sum signal) as a preprocessed biosignal without normalization based on the exercise state and / or exercise type.

[0142] According to one embodiment, in operation 740, the electronic device may perform adaptive noise cancelling (ANC) based on a sensing value acquired using an acceleration sensor to generate a refined signal. For example, the electronic device may generate a refined signal by removing noise components based on movement of the electronic device from a preprocessed biosignal based on the sensing value (e.g., an acceleration measurement signal). For example, the preprocessed biosignal and the sensing value may include frequency components generated due to movement of the user (and / or the electronic device). The electronic device may dynamically remove noise of a frequency component corresponding to the sensing value from the preprocessed biosignal.

[0143] In one embodiment, in operation 750, the electronic device may obtain biometric information (e.g., heart rate) of the user based on the refined signal.

[0144] According to one embodiment, in operation 760, the electronic device may provide a UI including biometric information. For example, the UI may include information that classifies and / or analyzes biometric information (e.g., heart rate) during the user's movement (e.g., exercise) into a plurality of sections. For example, the electronic device may classify a heart rate of 95 to 114 bpm into a low-intensity exercise section, a heart rate of 115 to 133 bpm into a weight-control exercise section, a heart rate of 134 to 152 bpm into an aerobic exercise section, a heart rate of 153 to 171 bpm into an anaerobic exercise section, and a heart rate of 172 to 191 bpm into a maximum heart rate exercise section. The electronic device may provide information indicating the proportion (ratio) of each of the low-intensity exercise section, the weight-control exercise section, the aerobic exercise section, the anaerobic exercise section, and the maximum heart rate exercise section during the user's exercise through the UI. An electronic device may provide information regarding the user's average heart rate and maximum heart rate during exercise through a UI. According to various embodiments, the information related to biometric information provided by the electronic device through the UI is not limited to the information described above.

[0145] According to various embodiments, the order of at least some of the operations of FIG. 7 may be changed, or they may be performed simultaneously, at least one operation may be omitted, or at least one operation (e.g., at least one of the operations of FIGS. 6 and 8) may be added. The operations of FIG. 7 may be performed independently of, integrated with, or in conjunction with the operations of FIGS. 6 and 8.

[0146]

[0147] Fig. 8 is a flowchart of a method for acquiring biometric information of an electronic device according to one embodiment. Below, any descriptions that overlap with those of Figs. 6 and 7 are omitted or briefly described.

[0148] According to one embodiment, in operation 805, an electronic device (e.g., electronic device (100) of FIG. 1, electronic device (300) of FIG. 3, electronic device (1100) of FIG. 11, electronic device (1200) of FIG. 12, or electronic device (1301) of FIG. 13) may acquire raw PPG signals corresponding to multiple channels using a biosensor (e.g., a PPG sensor).

[0149] According to one embodiment, in operation 810, the electronic device may extract PPG signals in a specified frequency band from raw PPG signals corresponding to a plurality of channels using a filter corresponding to the frequency band associated with the specified biometric information (e.g., heart rate).

[0150] In one embodiment, in operation 815, the electronic device may first normalize the PPG signals. The electronic device may first normalize the PPG signals based on a z-score.

[0151] According to one embodiment, in operation 820, the electronic device may obtain an acceleration signal using an acceleration sensor. For example, the electronic device may detect an acceleration signal corresponding to the movement of the electronic device using the acceleration sensor.

[0152] According to one embodiment, in operation 825, the electronic device may recognize the user's exercise state and / or exercise type. For example, the electronic device may determine which of a plurality of specified exercise states and / or exercise types the user's exercise state and / or exercise type corresponds to based on bio-signals and / or acceleration signals. For example, in FIG. 8, the exercise state and / or exercise type are described assuming three cases, but the present invention is not limited thereto.

[0153] According to one embodiment, in operation 830, the electronic device may determine the user's exercise state as a designated first exercise state. For example, the first exercise state may indicate an exercise state in which the body (e.g., wrist) on which the electronic device is worn exhibits strong movement. For example, the first exercise state may correspond to a designated first exercise type (e.g., but not limited to, swimming, tennis, golf, and table tennis).

[0154] According to one embodiment, in operation 835, the electronic device may apply a first weight to biosignals corresponding to a plurality of channels. For example, the first weight may include a first weight matrix including weight values ​​corresponding to each of the plurality of biosignals. The electronic device may determine different weights (e.g., different weight matrices) to be applied to the biosignals for each exercise type. The electronic device may multiply the weight matrix and the matrix representing the biosignals to obtain a weighted sum signal (e.g., a signal obtained by summing the biosignals by applying weights to each of the biosignals). For example, the biosignals corresponding to the plurality of channels may have different eigenvectors and values ​​between the channels. That is, the biosignals corresponding to the plurality of channels may have different signal-to-noise ratios. The electronic device may identify the eigenvectors of the biosignals for each channel, determine the degree of distortion of each channel based on the eigenvectors, and determine weight values ​​corresponding to the biosignals for each channel based on the eigenvectors. For example, when the types of exercise are different, the amount of exercise (e.g., degree of movement) applied to the location where the electronic device is worn may be different, and thus the level of noise coming in for each channel may also be different. The electronic device can compensate for noise and distortion that are input differently for each channel and / or exercise type in the biosignals by applying weights for each exercise type to the plurality of biosignals, and can obtain a biosignal (e.g., weighted sum signal) suitable for obtaining bioinformation. For example, rather than simply adding up the plurality of biosignals or selecting a specific biosignal, the electronic device can apply weights to the plurality of biosignals and add them to generate a signal (weighted sum signal) that reduces the distortion and noise components of the signal that occurred during the initial biosignal measurement through the biosignal.

[0155] According to one embodiment, in operation 840, the electronic device may normalize a biosignal to which a first weight is applied (e.g., a weighted sum signal) based on a sigmoid function and a z-score to generate a preprocessed biosignal. For example, normalization based on a sigmoid function may control values ​​that change significantly in an instant because the rate of increase or decrease of PPG signals may be maintained within a specified range. For example, normalization based on a z-score may be useful for controlling outlier values ​​of a biosignal because it utilizes a variance and / or a mean. When the exercise state is a first exercise state (and / or when the exercise type is a first exercise type), the electronic device may generate a preprocessed biosignal by comparing, analyzing, and / or summing a signal normalized based on a sigmoid function and a signal normalized based on a z-score. The electronic device may also determine a signal with less distortion among the signals normalized based on the sigmoid function and the signals normalized based on the z-score as a preprocessed biosignal for obtaining bioinformation.

[0156] In one embodiment, in operation 845, the electronic device may determine that the user's exercise state is a designated second exercise state. For example, the second exercise state may represent an exercise state in which regular movement occurs. For example, the second exercise state may correspond to a designated second exercise type (e.g., but not limited to, running, walking, and treadmill running).

[0157] According to one embodiment, in operation 850, the electronic device may apply a second weight, different from the first weight, to biosignals corresponding to the plurality of channels. For example, the second weight may include a second weight matrix including weight values ​​corresponding to each of the plurality of biosignals. The electronic device may apply the second weight to the biosignals corresponding to the plurality of channels to generate a weighted sum signal.

[0158] According to one embodiment, in operation 855, the electronic device may generate a preprocessed biosignal by normalizing a second weighted biosignal (e.g., a weighted sum signal) based on a z-score when the exercise state is a second exercise state (and / or when the exercise type is a third exercise type).

[0159] In one embodiment, in operation 860, the electronic device may determine that the user's exercise state is a designated third exercise state. For example, the third exercise state may represent an exercise state in which irregular movements occur. For example, the third exercise state may correspond to a designated third exercise type (e.g., but not limited to, soccer and basketball).

[0160] According to one embodiment, in operation 865, the electronic device may apply a third weight, which is different from the first weight and the second weight, to biosignals corresponding to the plurality of channels. For example, the third weight may include a third weight matrix including weight values ​​corresponding to each of the plurality of biosignals. The third weight matrix may be a matrix in which elements (weight values) included in the matrix are 1. The third weight matrix may be a matrix in which the average of elements included in the matrix is ​​1. The electronic device may generate a weighted sum signal by applying the third weight to the biosignals corresponding to the plurality of channels.

[0161] The electronic device may not perform normalization of the weighted biosignal (e.g., the weighted sum signal) when the motion state is the third motion state (and / or the motion type is the third motion type). For example, in the case of the third motion state that causes irregular movements, the acquired biosignal (e.g., the weighted sum signal) may also be an irregular signal, and in this case, performing normalization may cause the signal to diverge in a specific region (band). To prevent this, the electronic device may not perform normalization when it determines that the motion state is the third motion state (a motion state that causes irregular movements), and may acquire the weighted biosignal (e.g., the weighted sum signal) as a preprocessed biosignal.

[0162] In one embodiment, in operation 870, the electronic device may perform adaptive noise cancelling (ANC) using an acceleration signal. For example, the electronic device may dynamically remove noise components corresponding to the acceleration signal from the pre-processed biosignal.

[0163] In one embodiment, in operation 875, the electronic device may obtain the user's heart rate information from biosignals from which noise has been removed (e.g., a refined signal). The electronic device may track the user's heart rate.

[0164] According to one embodiment, in operation 880, the electronic device may provide heart rate-related information. For example, the electronic device may provide a user interface (UI) that includes heart rate-related information. For example, the electronic device may provide heart rate-related information through a workout and / or health-related application.

[0165] According to various embodiments, the order of at least some of the operations of FIG. 8 may be changed, or they may be performed simultaneously, at least one operation may be omitted, or at least one operation (e.g., at least one of the operations of FIGS. 6 and 7 ) may be added. The operations of FIG. 8 may be performed independently of, integrated with, or in conjunction with the operations of FIGS. 6 and 7 .

[0166]

[0167] A method for acquiring biometric information of an electronic device according to one embodiment of the present disclosure may include an operation of acquiring a biometric signal of a user using at least one sensor of the electronic device.

[0168] The method may include an operation of recognizing at least one of the user's exercise status or exercise type based on biometric data acquired using at least one sensor.

[0169] The method may include an operation of determining a weight to be applied to bio-data corresponding to the bio-signal based on at least one of the exercise state or the exercise type.

[0170] The method may include an operation of applying the determined weight to the biometric data.

[0171] The method may include an operation of obtaining preprocessed biometric data by normalizing the weighted biometric data using a specified normalization method based on at least one of the exercise state or exercise type.

[0172] The method may include an operation of removing noise related to movement of the electronic device from the preprocessed biometric data.

[0173] The above method may include an operation of obtaining biometric information of a user based on the biometric data from which the noise has been removed.

[0174] The at least one sensor may include a photoplethysmogram (PPG) sensor. The biosignal may include at least one signal representing the user's heart rate measured using the PPG sensor. The bioinformation may include information related to the heart rate.

[0175] The operation of recognizing at least one of the above movement states or movement types may include an operation of recognizing at least one movement state or movement type among a plurality of specified movement states or a plurality of specified movement types based on the sensor data.

[0176] The above-mentioned normalization method may include at least one of a normalization method based on a sigmoid function, a normalization method based on a z-score, or a method that does not perform normalization.

[0177] The method may include an operation of first normalizing the biometric data corresponding to the acquired biometric signal before applying the weight to the biometric data.

[0178] The operation of applying the above weight may include an operation of applying the above weight to the first normalized biometric data.

[0179] The operation of removing the noise may include performing adaptive noise cancelling (ANC) on the preprocessed biometric data based at least in part on the sensor data.

[0180] The method may include an operation of obtaining a raw biosignal using the at least one sensor.

[0181] The method may include an operation of extracting the biodata from raw data corresponding to the raw biosignal based on a filter corresponding to a specified frequency band.

[0182] The at least one sensor may include a biosensor including light receiving units configured to acquire a plurality of biosignals corresponding to a plurality of channels.

[0183] The operation of acquiring the biosignal may include an operation of acquiring a plurality of biosignals corresponding to the plurality of channels based on light received using a plurality of light receiving units of the biosensor.

[0184] The operation of determining the weight may include an operation of determining a weight matrix including weight values ​​for a plurality of bio-data corresponding to each of the plurality of bio-signals.

[0185] The operation of applying the weights may include an operation of applying the weight values ​​to the biometric data based on the weight matrix and then summing them to obtain biometric data to which the weights have been applied.

[0186] The method may include an operation of providing a user interface (UI) including information related to at least one of the exercise state or the exercise type and the biometric information through a display of the electronic device.

[0187] A storage medium according to one embodiment of the present disclosure may store instructions. The instructions, when executed by at least one processor of an electronic device, may cause the electronic device to obtain a biosignal of a user using at least one sensor of the electronic device, recognize at least one of a movement state or a movement type of the user based on sensor data obtained using the at least one sensor, determine a weight to be applied to biodata corresponding to the biosignal based on at least one of the movement state or the movement type, apply the determined weight to the biodata, normalize the biodata to which the weight has been applied based on at least one of the movement state or the movement type using a specified normalization method to obtain preprocessed biodata, remove noise related to a movement of the electronic device from the preprocessed biodata, and obtain bioinformation of the user based on the biodata from which the noise has been removed.

[0188] According to embodiments of the present disclosure, by applying weights corresponding to the user's movement (e.g., movement of the electronic device) to biosignals (and / or biodata), noise input differently depending on the user's movement (e.g., movement of the electronic device) while the user is wearing the electronic device can be reduced, and distortion of the biosignals (and / or biodata) can be compensated for, thereby improving the accuracy in obtaining bioinformation. According to embodiments of the present disclosure, by applying different weight matrices and different normalization methods corresponding to exercise states (or exercise types) to the biosignals (and / or biodata), the signal-to-noise ratio of the biosignals (and / or biodata) can be improved. According to embodiments of the present disclosure, bioinformation can be obtained based on a weighted sum of a plurality of biosignals (and / or biodata) without individually processing the biosignals (and / or biodata) corresponding to a plurality of channels, thereby reducing the noise level and improving the accuracy in measuring bioinformation. According to embodiments of the present disclosure, by applying a weight to each of a plurality of biosignals (and / or biodata) and then adding them together to generate a preprocessed biosignal (and / or biodata), the amount of distortion or noise due to movement of an electronic device (and / or a user) in a raw biosignal (and / or biodata) acquired using a biosensor can be reduced, and the bioinformation can be acquired based on the preprocessed biosignal (and / or biodata), thereby increasing the accuracy of the bioinformation.

[0189] FIGS. 9A to 9C are examples of user interfaces including biometric information provided by an electronic device (e.g., the electronic device (100) of FIG. 1, the electronic device (300) of FIG. 3, the electronic device (1100) of FIG. 11, the electronic device (1200) of FIG. 12, or the electronic device (1301) of FIG. 13) according to one embodiment. For example, the user interfaces (UIs) illustrated in FIGS. 9A to 9C may be UIs provided through an application (e.g., a health application or an exercise application) that provides biometric information of a user.

[0190] Referring to FIG. 9A, an example of a UI including the user's biometric information provided when the user engages in an exercise with strong wrist movement (e.g., swimming) is illustrated. The first UI may include a first region indicating the type of exercise, a second region indicating information related to the amount of exercise, a third region indicating information related to the exercise time, a fourth region indicating detailed information related to the exercise, and a fifth region indicating the user's biometric information during the exercise. For example, the first region may include a picture representing swimming. Although the first region of FIG. 9A is illustrated as including only a picture representing the end of an exercise (e.g., swimming), the first region is not limited thereto, and the first region may include a picture, diagram, and / or text representing the type of exercise. The second region may include information representing the amount of exercise (e.g., exercise distance). The third region may include information regarding the date, day of the week, and / or time the user exercised. For example, a fourth region may include information about exercise time, average pace, average heart rate, exercise calories, total strokes, and average swolf associated with an exercise performed by the user (e.g., swimming). A fifth region may include a chart representing the user's heart rate during the exercise. The first UI may include a sixth region that provides functions related to the first UI. The sixth region may include an affordance that provides a function to transmit or share information included in the first UI to another application (e.g., a social networking application), another electronic device (another user), or an external server (e.g., a cloud server), and / or an affordance that provides functions for manipulating the first UI (e.g., saving, editing, and / or exiting the first UI).

[0191] The second UI may include a seventh area indicating a type of exercise, an eighth area indicating a record related to the exercise, a ninth area indicating information analyzed from biometric information during the exercise, and a tenth area providing a function related to the second UI. The seventh area may include information indicating a type of exercise performed by the user (e.g., pool swimming). The eighth area may include records of each swimming round. The ninth area may include information indicating a proportion of each heart rate zone within the total exercise time. For example, the ninth area may include a graph indicating an exercise ratio for each of a plurality of zones classified by heart rate (e.g., low-intensity exercise, weight-control exercise, aerobic exercise, anaerobic exercise, and maximum heart rate exercise). The tenth area may correspond to the sixth area.

[0192] Referring to FIG. 9B, an example of a UI including biometric information of a user provided when a user engages in an exercise that involves regular movement (e.g., treadmill). The third UI may include an eleventh area indicating a type of exercise (e.g., treadmill), a twelfth area indicating information related to an amount of exercise (e.g., exercise distance), a thirteenth area indicating information related to an exercise time, a fourteenth area indicating detailed information related to the exercise, and a fifteenth area indicating biometric information of the user during the exercise (e.g., heart rate). The thirteenth area may include information regarding the date, day of the week, and / or time that the user exercised. For example, the fourteenth area may include information regarding an exercise time, average speed, average heart rate, exercise calories, average cadence, and number of steps associated with an exercise (e.g., treadmill) performed by the user. The fifteenth area may include a chart indicating the user's heart rate during the exercise.

[0193] The fourth UI may include a 16th area indicating the type of exercise (e.g., treadmill), a 17th area indicating exercise-related records, and an 18th area indicating information analyzed from biometric data during exercise. The 17th area may include information on the time, distance, and speed for each round of treadmill exercise. The 18th area may include information indicating exercise ratios for multiple intervals classified by heart rate (e.g., low-intensity exercise, weight-control exercise, aerobic exercise, anaerobic exercise, and maximum heart rate exercise).

[0194] Referring to FIG. 9C, an example of a UI including the user's biometric information provided when the user engages in an exercise that causes irregular movements (e.g., other exercise (e.g., basketball)) is illustrated. The fifth UI may include a 19th area indicating a type of exercise (e.g., basketball), a 20th area indicating information related to the amount of exercise (e.g., the duration of the exercise), a 21st area indicating information related to the duration of the exercise, a 22nd area indicating detailed information related to the exercise, and a 23rd area indicating the user's biometric information (e.g., heart rate) during the exercise. For example, the 22nd area may include information related to an average heart rate, a maximum heart rate, exercise calories, total calories, exercise time, and total time associated with an exercise (e.g., basketball) performed by the user. The 23rd area may include a chart indicating the user's heart rate during the exercise.

[0195] The sixth UI may include a 24th area indicating the type of exercise (e.g., other exercise (e.g., basketball)), a 25th area indicating biometric information during exercise, and a 26th area indicating information analyzed from the biometric information during exercise. The 25th area may correspond to the 23rd area. The 26th area may include information indicating exercise ratios for multiple intervals classified by heart rate (e.g., low-intensity exercise, weight-control exercise, aerobic exercise, anaerobic exercise, and maximum heart rate exercise).

[0196] According to embodiments of the present disclosure, an electronic device can recognize a user's exercise state, apply a weight according to the exercise state to the bio-signals acquired during the user's exercise to obtain bio-information (e.g., heart rate), thereby increasing the accuracy of measuring bio-information according to the exercise state, and provide a UI that can easily check bio-information during exercise.

[0197] According to various embodiments, the UI provided by the electronic device is not limited to that illustrated in FIGS. 9a to 9c, and the shape, configuration, layout, and / or information included in the UI may be changed.

[0198]

[0199] FIGS. 10A and 10B are diagrams showing the results of measuring a heart rate in an electronic device (e.g., the electronic device (100) of FIG. 1, the electronic device (300) of FIG. 3, the electronic device (1100) of FIG. 11, the electronic device (1200) of FIG. 12, or the electronic device (1301) of FIG. 13) according to one embodiment. For example, FIGS. 10A and 10B illustrate graphs showing the results of simulating the accuracy of a measurement value when weights are applied or not applied to a biosignal.

[0200] Referring to Fig. 10a, 1010 represents the result of measuring heart rate without applying a weight determined based on exercise status to the biosignal, and 1020 represents the result of measuring heart rate while applying a weight determined based on exercise status to the biosignal. For example, in the graph, reference represents a reference value predicted to be a normal heart rate, and measure represents the result of measuring an actual heart rate.

[0201] Referring to the first region (1011) of 1010, it indicates a case where the measured value has a large error compared to the reference value. For example, when the movement of the electronic device (e.g., the user) is severe, the noise caused by the movement of the electronic device may not be properly removed, resulting in a relatively large error in the measured value compared to the reference value, as in 1010. Referring to the second region (1021) of 1020, it can be confirmed that the heart rate measurement value is measured similarly to the reference value by applying a weight determined based on the exercise state to the biosignal. For example, the measurement accuracy (pass rate (%)) in 1010 is 75.4%, but the measurement accuracy (pass rate (%)) in 1020 can be 100%.

[0202] Referring to FIG. 10b, 1030 represents the result of measuring heart rate without applying a weight determined based on exercise status to the biosignal, and 1040 represents the result of measuring heart rate while applying a weight determined based on exercise status to the biosignal.

[0203] Referring to the third area (1031) of 1030, it indicates a case where the measured value has a large error compared to the reference value. For example, if the electronic device (e.g., the user) is moving a lot, the noise caused by the movement of the electronic device may not be properly removed, resulting in a relatively large error in the measured value compared to the reference value, as shown in 1030. Referring to the fourth area (1041) of 1040, it can be confirmed that the heart rate measurement value is measured similarly to the reference value by applying a weight determined based on the exercise state to the biosignal.

[0204] For example, the accuracy (pass rate(%)) of the measurement at 1030 is 59.5%, but the accuracy (pass rate(%)) of the measurement at 1040 can be improved to 95.8%.

[0205]

[0206] FIG. 11 is a block diagram of an exemplary electronic device (1100) capable of performing the operations described in this document.

[0207] Referring to FIG. 11, the electronic device (1100) may be one of various forms of electronic devices, such as a notebook (1190), smartphones (1191) having various form factors (e.g., a bar-type smartphone (1191-1), a foldable-type smartphone (1191-2), or a sliderable (or rollable) type smartphone (1191-3)), a tablet (1192), a cellular phone (not shown), and other similar computing devices (not shown). The components, their relationships, and their functions illustrated in FIG. 11 are exemplary only and do not limit the implementations described or claimed in this document. The electronic device (1100) may be referred to as a mobile device, a user device, a multi-function device, a portable device, or a server.

[0208] The electronic device (1100) may include components including at least one processor (1110) (hereinafter referred to as processor (1110)), at least one memory (1120) (hereinafter referred to as memory (1120)), at least one display (1140) (hereinafter referred to as display (1140)), at least one image sensor (1150) (hereinafter referred to as image sensor (1150)), at least one communication circuit (1160) (hereinafter referred to as communication circuit (1160)), and / or at least one sensor (1170) (hereinafter referred to as sensor (1170)). The above components are merely exemplary. For example, the electronic device (1100) may include other components (e.g., power management integrated circuitry (PMIC), audio processing circuitry, an antenna, a rechargeable battery, or an input / output interface). For example, some components may be omitted from the electronic device (1100). For example, several components can be combined into one component.

[0209] The processor (1110) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing. The processor (1110) may include at least one electrical circuit and may individually or collectively perform distributed processing of instructions (or programs, data, etc.) stored in the memory (1120). The processor (1110) may include a processor assembly including one or more processing circuits. The processor (1110) may include any processing circuit operative to control the performance and operations of one or more components of the electronic device (1100) (e.g., the memory (1120), the display (1140), the image sensor (1150), the communication circuit (1160), and / or the sensor (1170)). For example, the processor (1110) (e.g., an application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or chipset). For example, the processor (1110) may be implemented as multiple cores (or at least one core circuit), multiple chips, or multiple chipsets. For example, the processor (1110) may include one or more processing circuits. For example, the processor (1110) may include one or more processing circuits configured to individually and / or collectively perform various functions of the present disclosure. As a non-limiting example, at least a portion of the processor (1110) may be included in a first chip of the electronic device (1100), and at least another portion of the processor (1110) may be included in a second chip of the electronic device (1100) that is different from the first chip of the electronic device (1100).

[0210] For example, the processor (1110) may include a central processing unit (CPU) (1111), a graphics processing unit (GPU) (1112), a neural processing unit (NPU) (1113), an image signal processor (ISP) (1114), a display controller (1115), a memory controller (1116), a storage controller (1117), a communication processor (CP) (1118), and / or a sensor interface (1119). These components of the processor (1110) are merely exemplary. For example, the processor (1110) may further include other components. For example, some components of the processor (1110) may be omitted from the processor (1110). For example, some components of the processor (1110) may be included as separate components of the electronic device (1100) outside the processor (1110). For example, some components of the processor (1110) (e.g., memory controller (1116)) may be included within other components (e.g., at least a portion of memory (1120), an interface (e.g., available for connection to at least one component of the electronic device (100)), a display (1140) and / or an image sensor (1150)).

[0211] The processor (1110) may cause other components of the electronic device (1100) to perform various operations by executing instructions stored in the memory (1120). The CPU (1111) (or central processing circuit) may be configured to control components of the processor (1110) based on the execution of instructions stored in the memory (1120) (e.g., volatile memory (1121) and / or non-volatile memory (1122)). The GPU (1112) (or graphics processing circuit) may be configured to execute parallel operations (e.g., rendering). The NPU (1113) (or neural processing circuit, or artificial intelligence (AI) chip) may be configured to execute operations for an artificial intelligence model (e.g., convolution computation). The ISP (1114) (or image signal processing circuit) may be configured to process a raw image acquired through the image sensor (1150) into a format suitable for a component within the electronic device (1100) or a component of the processor (1110). The display controller (1115) (or display control circuit, or display processing unit (DPU)) may be configured to process an image acquired from the CPU (1111), the GPU (1112), the ISP (1114), or the memory (1120) (e.g., the volatile memory (1121)) into a format suitable for the display (1140). The memory controller (1116) (or memory control circuit) may be configured to control reading data from the volatile memory (1121) and writing data to the volatile memory (1121). The storage controller (1117) (or storage control circuit) may be configured to control reading data from the nonvolatile memory (1122) and writing data to the nonvolatile memory (1122).The CP (1118) (communication processing circuit) may be configured to process data obtained from a component of the processor (1110) into a format suitable for transmission to another electronic device via the communication circuit (1160), or to process data obtained from another electronic device via the communication circuit (1160) into a format suitable for processing by the component of the processor (1110). For example, the communication circuit (1160) may include one or more communication circuits. The sensor interface (1119) (or sensing data processing circuit, sensor hub) may be configured to process data on the state of the electronic device (1100) and / or the state of the surroundings of the electronic device (1100), obtained via the sensor (1170), into a format suitable for the component of the processor (1110).

[0212] The memory (1120) may include one or more storage media (or one or more storage devices). For example, the memory (1120) may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory (e.g., non-volatile memory (1122)) such as a hard drive, flash memory, read-only memory (ROM), semi-permanent memory (e.g., volatile memory (1121)) such as random access memory (RAM), any other suitable type of storage (or storage assembly), or any combination thereof. The memory (1120) may include cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (1100). As a non-limiting example, the cache memory may be included within the processor (1110). The memory (1120) may be fixedly embedded within the electronic device (1100) or incorporated into one or more suitable types of components (e.g., a subscriber identity module (SIM) card and / or a secure digital (SD) card) that may be repeatedly inserted into and removed from the electronic device (1100).

[0213] For example, the memory (1120) may store one or more software applications, such as an operating system (or system) software application, a firmware software application, a driver software application, a plug-in (e.g., add-in, add-on, and / or applet) software application, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (1110). For example, the memory (1120) may store instructions callable by an application programming interface (API). For example, the memory (1120) may store instructions within a library.

[0214]

[0215] Referring to FIGS. 12A and 12B , an electronic device (1200) according to one embodiment (e.g., the electronic device (1101) of FIG. 11 ) may include a housing (1210) including a first side (or front side) (1210A), a second side (or back side) (1210B), and a side surface (1210C) surrounding a space between the first side (1210A) and the second side (1210B), and a fastening member (1250, 260) connected to at least a portion of the housing (1210) and configured to detachably fasten the electronic device (1200) to a body part (e.g., a wrist, an ankle, etc.) of a user. In another embodiment (not shown), the housing may also refer to a structure forming a portion of the first side (1210A), the second side (1210B), and the side surface (1210C) of FIG. 2A . In one embodiment, the first side (1210A) may be formed by a front plate (1201) that is at least partially substantially transparent (e.g., a glass plate or a polymer plate comprising various coating layers). The second side (1210B) may be formed by a substantially opaque back plate (1207). The back plate (1207) may be formed of, for example, coated or colored glass, ceramic, polymer, metal (e.g., aluminum, stainless steel (STS), or magnesium), or a combination of at least two of the foregoing materials. The side surface (1210C) may be formed by a side bezel structure (or “side member”) (1206) that is coupled to the front plate (1201) and the back plate (1207) and comprises a metal and / or a polymer. In some embodiments, the back plate (1207) and the side bezel structure (1206) may be formed integrally and comprise the same material (e.g., a metal material such as aluminum). The above-mentioned bonding member (1250, 260) can be formed of various materials and shapes.The integral and multiple unit links can be formed to be movable with each other by a combination of at least two of the above materials, such as woven fabric, leather, rubber, urethane, metal, ceramic, or a combination of at least two of the above materials.

[0216] According to one embodiment, the electronic device (1200) may include at least one of a display (1220, see FIG. 13), an audio module (1205, 208), a sensor module (1211), a key input device (1202, 203, 204), and a connector hole (1209). In some embodiments, the electronic device (1200) may omit at least one of the components (e.g., the key input device (1202, 203, 204), the connector hole (1209), or the sensor module (1211)) or may additionally include other components.

[0217] The display (1220) may be exposed, for example, through a significant portion of the front plate (1201). The shape of the display (1220) may correspond to the shape of the front plate (1201), and may be in various shapes such as circular, oval, or polygonal. The display (1220) may be coupled to or disposed adjacent to a touch detection circuit, a pressure sensor capable of measuring the intensity (pressure) of a touch, and / or a fingerprint sensor.

[0218] The audio module (1205, 208) may include a microphone hole (1205) and a speaker hole (1208). The microphone hole (1205) may have a microphone positioned therein for acquiring external sounds, and in some embodiments, multiple microphones may be positioned therein to detect the direction of sounds. The speaker hole (1208) may be used as an external speaker and a receiver for calls. In some embodiments, the speaker hole (1208) and the microphone hole (1205) may be implemented as a single hole, or a speaker may be included without the speaker hole (1208) (e.g., a piezo speaker).

[0219] The sensor module (1211) can generate an electric signal or data value corresponding to the internal operating state of the electronic device (1200) or the external environmental state. The sensor module (1211) can include, for example, a biometric sensor module (1211) (e.g., an HRM sensor) disposed on the second surface (1210B) of the housing (1210). The electronic device (1200) can further include at least one of a non-illustrated sensor module, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0220] The key input devices (1202, 203, 204) may include a wheel key (1202) disposed on a first side (1210A) of the housing (1210) and rotatable in at least one direction, and / or a side key button (1203, 204) disposed on a side surface (1210C) of the housing (1210). The wheel key may have a shape corresponding to the shape of the front plate (1202). In other embodiments, the electronic device (1200) may not include some or all of the above-mentioned key input devices (1202, 203, 204), and the key input devices (1202, 203, 204) that are not included may be implemented in another form, such as a soft key, on the display (1220). The connector hole (1209) may include another connector hole (not shown) that may accommodate a connector (e.g., a USB connector) for transmitting and receiving power and / or data with an external electronic device, and may accommodate a connector for transmitting and receiving audio signals with the external electronic device. The electronic device (1200) may further include, for example, a connector cover (not shown) that covers at least a portion of the connector hole (1209) and blocks the inflow of external foreign substances into the connector hole.

[0221] The fastening member (1250, 260) can be detachably fastened to at least a portion of the housing (1210) using a locking member (1251, 261). The fastening member (1250, 260) can include one or more of a fixing member (1252), a fixing member fastening hole (1253), a band guide member (1254), and a band fastening ring (1255).

[0222] The fixing member (1252) may be configured to fix the housing (1210) and the fastening members (1250, 260) to a part of the user's body (e.g., wrist, ankle, etc.). The fastening member fastening hole (1253) may correspond to the fastening member (1252) to fasten the housing (1210) and the fastening members (1250, 260) to a part of the user's body. The band guide member (1254) may be configured to limit the range of motion of the fastening member (1252) when the fastening member (1252) is fastened to the fastening member fastening hole (1253), thereby allowing the fastening members (1250, 260) to be fastened in close contact with a part of the user's body. The band fixing ring (1255) may limit the range of motion of the fastening members (1250, 260) when the fastening member (1252) and the fastening member fastening hole (1253) are fastened.

[0223]

[0224] Referring to FIG. 13, an electronic device (1301) (e.g., the electronic device (1101) of FIG. 11 or the electronic device (1200) of FIG. 12) may include a side bezel structure (1310), a wheel key (1320), a front plate (1201), a display (1220), a first antenna (1350), a second antenna (1355), a support member (1360) (e.g., a bracket), a battery (1370), a printed circuit board (1380), a sealing member (1390), a rear plate (1393), and a fastening member (1395, 397). At least one of the components of the electronic device (1301) may be the same as or similar to at least one of the components of the electronic device (1200) of FIG. 1 or FIG. 2, and a redundant description thereof will be omitted below. The support member (1360) may be disposed inside the electronic device (1301) and connected to the side bezel structure (1310), or may be formed integrally with the side bezel structure (1310). The support member (1360) may be formed of, for example, a metallic material and / or a non-metallic (e.g., polymer) material. The support member (1360) may have a display (1220) coupled to one surface and a printed circuit board (1380) coupled to the other surface. A processor, a memory, and / or an interface may be mounted on the printed circuit board (1380). The processor may include, for example, one or more of a central processing unit, an application processor, a graphic processing unit (GPU), a sensor processor, or a communication processor.

[0225] The memory may include, for example, volatile memory or non-volatile memory. The interface may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, and / or an audio interface. The interface may electrically or physically connect the electronic device (1301) to an external electronic device, for example, and may include a USB connector, an SD card / MMC connector, or an audio connector.

[0226] The battery (1370) is a device for supplying power to at least one component of the electronic device (1301), and may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell. At least a portion of the battery (1370) may be disposed substantially on the same plane as, for example, the printed circuit board (1380). The battery (1370) may be disposed integrally within the electronic device (1200), or may be disposed detachably from the electronic device (1200).

[0227] The first antenna (1350) may be positioned between the display (1220) and the support member (1360). The first antenna (1350) may include, for example, a near field communication (NFC) antenna, a wireless charging antenna, and / or a magnetic secure transmission (MST) antenna. The first antenna (1350) may, for example, perform short-range communication with an external device, wirelessly transmit and receive power required for charging, and transmit a magnetic-based signal including a short-range communication signal or payment data. In another embodiment, the antenna structure may be formed by a portion or a combination of the side bezel structure (1310) and / or the support member (1360).

[0228] The second antenna (1355) may be positioned between the printed circuit board (1380) and the back plate (1393). The second antenna (1355) may include, for example, a near field communication (NFC) antenna, a wireless charging antenna, and / or a magnetic secure transmission (MST) antenna. The second antenna (1355) may, for example, perform short-range communication with an external device, wirelessly transmit and receive power required for charging, and transmit a magnetic-based signal including a short-range communication signal or payment data. In another embodiment, the antenna structure may be formed by a portion or a combination of the side bezel structure (1310) and / or the back plate (1393).

[0229] A sealing member (1390) may be positioned between the side bezel structure (1310) and the rear plate (1393). The sealing member (1390) may be configured to block moisture and foreign substances from entering the space surrounded by the side bezel structure (1310) and the rear plate (1393) from the outside.

[0230]

[0231] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0232] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions.

[0233] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0234]

[0235]

Claims

1. In electronic devices, At least one sensor; Memory that stores instructions; and Contains at least one processor, The above instructions, when executed by the at least one processor, cause the electronic device to: Obtaining a user's biosignal using at least one sensor, Recognize at least one of the user's exercise status or exercise type based on sensor data acquired using at least one sensor, Determine a weight to be applied to bio-data corresponding to the bio-signal based on at least one of the above exercise state or the above exercise type, Applying the determined weight to the above biometric data, Based on at least one of the above exercise state or the above exercise type, the weighted biometric data is normalized using a specified normalization method to obtain preprocessed biometric data, Removing noise related to the movement of the electronic device from the preprocessed biometric data, An electronic device that obtains user's biometric information based on biometric data from which the above noise has been removed.

2. In claim 1, wherein at least one sensor comprises a photoplethysmogram (PPG) sensor, The biosignal includes at least one signal representing the user's heart rate measured using the PPG sensor, An electronic device wherein the biometric information includes information related to the heart rate.

3. In claim 1, The above instructions, when executed by the at least one processor, cause the electronic device to: An electronic device that recognizes at least one of a plurality of specified movement states or a plurality of specified movement types based on the above sensor data.

4. In claim 1, An electronic device, wherein the above-mentioned normalization method comprises at least one of a normalization method based on a sigmoid function, a normalization method based on a z-score, or a method that does not perform normalization.

5. In claim 1, The above instructions, when executed by the at least one processor, cause the electronic device to: Before applying the weight to the biometric data, the biometric data corresponding to the acquired biometric signal is first normalized, An electronic device that applies the weight to the first normalized biometric data.

6. In claim 1, The above instructions, when executed by the at least one processor, cause the electronic device to: An electronic device that performs adaptive noise cancelling (ANC) on the preprocessed biometric data based at least in part on the sensor data.

7. In claim 1, The above instructions, when executed by the at least one processor, cause the electronic device to: Acquiring raw biosignals using at least one sensor, An electronic device that extracts biometric data from raw data corresponding to the raw biometric signal based on a filter corresponding to a specified frequency band.

8. In claim 1, The at least one sensor comprises a biosensor including light receiving units configured to acquire a plurality of biosignals corresponding to a plurality of channels, The above instructions, when executed by the at least one processor, cause the electronic device to: Based on the light received using the plurality of light receiving units of the above biosensor, a plurality of biosignals corresponding to the plurality of channels are acquired, Determine a weight matrix including weight values ​​for a plurality of bio-data corresponding to each of the plurality of bio-signals, An electronic device that obtains biometric data to which the weights have been applied by applying the weight values ​​to the biometric data and then summing them based on the weight matrix.

9. In claim 1, Including more displays, The above instructions, when executed by the at least one processor, cause the electronic device to: An electronic device that provides a user interface (UI) including information related to at least one of the exercise state or the exercise type and the biometric information through the display.

10. In claim 1, The above instructions, when executed by the at least one processor, cause the electronic device to: An electronic device that determines the above weights using a model learned based on artificial intelligence.

11. A method for obtaining biometric information of an electronic device, An operation of acquiring a user's biosignal using at least one sensor of the electronic device; An action of recognizing at least one of the user's exercise status or exercise type based on sensor data acquired using at least one sensor; An operation of determining a weight to be applied to bio-data corresponding to the bio-signal based on at least one of the exercise state or the exercise type; An action of applying the determined weight to the above biometric data; An operation of obtaining a preprocessed biosignal by normalizing the weighted biodata using a specified normalization method based on at least one of the above exercise states or exercise types; An operation of removing noise related to the movement of the electronic device from the preprocessed biometric data; and A method comprising an action of obtaining biometric information of a user based on biometric data from which the above noise has been removed.

12. In claim 11, An action that recognizes at least one of the above movement states or movement types, A method comprising an action of recognizing at least one movement state or movement type among a plurality of specified movement states or a plurality of specified movement types based on the above sensor data.

13. In claim 11, A method wherein the above-mentioned normalization method comprises at least one of a normalization method based on a sigmoid function, a normalization method based on a z-score, or a method that does not perform normalization.

14. In claim 11, An operation of first normalizing the biometric data corresponding to the acquired biometric signal before applying the weight to the biometric data is included. A method wherein the operation of applying the weight includes an operation of applying the weight to the first normalized biometric data.

15. In a non-transitory storage medium that stores instructions, The above instructions, when executed by at least one processor of an electronic device, cause the electronic device to: Obtaining a user's biosignal using at least one sensor of the electronic device, Recognize at least one of the user's exercise status or exercise type based on sensor data acquired using at least one sensor, Determine a weight to be applied to bio-data corresponding to the bio-signal based on at least one of the above exercise state or the above exercise type, Applying the determined weight to the above biometric data, Based on at least one of the above exercise state or the above exercise type, the weighted biometric data is normalized using a specified normalization method to obtain preprocessed biometric data, Removing noise related to the movement of the electronic device from the preprocessed biometric data, A storage medium for obtaining user's biometric information based on biometric data from which the above noise has been removed.

Images