Method for evaluating quality of biological signal and apparatus for estimating biological information

Abstract

A method for evaluating the quality of a biosignal and an apparatus for estimating bioinformation are provided. The method includes: receiving an input biosignal; setting a quality evaluation region in the biosignal; dividing the signal in the quality evaluation region into a plurality of sub-signals; extracting a typical waveform using the plurality of sub-signals; evaluating the quality of each sub-signal based on the typical waveform; and evaluating the quality of the signal in the quality evaluation region based on the quality evaluation results of the plurality of sub-signals.

Description

[0001] This application claims priority from Korean Patent Application No. 10-2021-0136593 filed on October 14, 2021, in the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference for all purposes. Technical Field

[0002] The disclosure relates to estimating biological information, and more particularly to a method of evaluating the quality of a biological signal and an apparatus for estimating biological information based on the quality evaluation. Background Art

[0003] Due to the aging population, rising medical costs, and a lack of medical personnel for specialized medical services, research on IT-medical convergence technology that combines IT technology with medical technology is being actively carried out. In particular, the monitoring of the health status of the human body is not limited to medical institutions, but is expanding to the field of mobile medical care that can monitor the health status of users anywhere and at any time in daily life at home or in the office. Typical examples of biosignals that indicate the health status of an individual include electrocardiogram (ECG) signals, photoplethysmography (PPG) signals, electromyography (EMG) signals, etc., and various biosignal sensors have been developed to measure these signals in daily life. In particular, the PPG sensor can estimate the blood pressure of the human body by analyzing the shape of the pulse wave that reflects the cardiovascular state, etc.

[0004] Research on PPG signals reveals that the entire PPG signal is the sum of propagating waves from the heart to the periphery of the body and reflected waves returning from the periphery. Information used for blood pressure estimation can be obtained by extracting various features associated with the propagating and reflected waves. However, if the quality of the biosignal deteriorates due to arrhythmias or motion noise in the heartbeat, the accuracy of the blood pressure estimate may decrease. Summary of the Invention

[0005] According to one aspect of the disclosure, a method for evaluating the quality of a biological signal may include: receiving a measured biological signal; setting a quality evaluation area in the measured biological signal; dividing the signal in the quality evaluation area into multiple sub-signals; extracting a typical waveform by using the multiple sub-signals; evaluating the quality of each sub-signal based on the typical waveform; and evaluating the quality of the signal in the quality evaluation area based on the quality evaluation results of the multiple sub-signals.

[0006] The step of setting the quality assessment area may include setting the quality assessment area based on a predetermined number of heartbeats or a predetermined unit of time period.

[0007] The dividing into the plurality of sub-signals may include dividing the signal of the quality assessment area into the sub-signals based on a unit of heartbeat.

[0008] The dividing into the plurality of sub-signals may include setting a reference point in each of the plurality of sub-signals. The extracting the typical waveform may include extracting the typical waveform representing the quality assessment area by overlapping the plurality of sub-signals based on the set reference point.

[0009] The step of setting the reference point may include setting one of a minimum point, a maximum point, a maximum slope point, and a tangent intersection point of each sub-signal as the reference point.

[0010] The extracting of the typical waveform may include overlapping the plurality of sub-signals after applying a predefined weight to each of the plurality of sub-signals.

[0011] The step of extracting the representative waveform may include adjusting weights to be applied in the current iteration based on quality evaluation results of the respective sub-signals in the previous iteration.

[0012] The extracting of the typical waveform may include overlapping the plurality of sub-signals after normalizing the plurality of sub-signals to have the same size.

[0013] The step of evaluating the quality of each of the multiple sub-signals may include: calculating the similarity between the typical waveform and each sub-signal, or the similarity between the Nth-order derivative signal of the typical waveform and the Nth-order derivative signal of each sub-signal, and evaluating the quality of each sub-signal based on the calculated similarity.

[0014] Evaluating the quality of each of the plurality of sub-signals may include calculating a similarity between the typical waveform and each of the plurality of sub-signals during a predetermined time interval starting from a reference point of each of the plurality of sub-signals.

[0015] The steps of extracting the typical waveform and evaluating the quality of each of the multiple sub-signals may include: repeatedly evaluating the quality at least a predetermined number of times, and until the similarity between the typical waveform in the current iteration and the typical waveform in the previous iteration is greater than or equal to a first predetermined threshold, or until the quality evaluation results of the multiple sub-signals in the current iteration and the quality evaluation results of the multiple sub-signals in the previous iteration are greater than or equal to a second predetermined threshold.

[0016] The step of evaluating the quality of the signal in the quality evaluation area may include calculating a statistical value of a quality evaluation result of each of the plurality of sub-signals, and evaluating the quality of the signal in the quality evaluation area based on the calculated statistical value.

[0017] According to another aspect of the disclosure, a device for estimating biological information may include: a sensor configured to measure a biological signal from an object; and a processor configured to: set a quality evaluation area in the measured biological signal; divide the signal in the quality evaluation area into multiple sub-signals; extract a typical waveform by using the multiple sub-signals; evaluate the quality of each of the multiple sub-signals based on the extracted typical waveform to evaluate the quality of the signal in the quality evaluation area; and estimate the biological information based on the quality evaluation.

[0018] The processor is further configured to set the quality assessment area based on a unit of a predetermined number of heartbeats or a predetermined period of time.

[0019] The processor is further configured to divide the signal of the quality assessment area into the plurality of sub-signals based on a unit of heartbeat.

[0020] The processor may be further configured to set a reference point in each of the plurality of sub-signals, and extract the representative waveform representing the quality assessment region by overlapping the plurality of sub-signals based on the set reference point.

[0021] The processor may also be configured to calculate a similarity between the typical waveform and each of the multiple sub-signals, or a similarity between an N-order derivative signal of the typical waveform and an N-order derivative signal of each of the multiple sub-signals, and evaluate the quality of each of the multiple sub-signals based on the calculated similarity.

[0022] The processor may also be configured to repeatedly evaluate the quality at least a predetermined number of times, and until the similarity between the typical waveform in the current iteration and the typical waveform in the previous iteration is greater than or equal to a first predetermined threshold, or until the quality evaluation results of the multiple sub-signals in the current iteration and the quality evaluation results of the multiple sub-signals in the previous iteration are greater than or equal to a second predetermined threshold.

[0023] The processor may be further configured to calculate a statistical value of a quality evaluation result of each of the plurality of sub-signals, and evaluate the quality of the signal in the quality evaluation area based on the calculated statistical value.

[0024] According to another aspect of the disclosure, an electronic device may include: a main body and an apparatus for estimating blood pressure disposed in the main body, the apparatus for estimating blood pressure including: a PPG sensor configured to measure a photoplethysmography signal from a subject; and a processor configured to: set a quality evaluation area in the PPG signal; divide the signal of the quality evaluation area into a plurality of sub-signals; extract a typical waveform by using the plurality of sub-signals; evaluate the quality of each of the plurality of sub-signals based on the extracted typical waveform to evaluate the quality of the signal in the quality evaluation area; and estimate blood pressure based on the quality evaluation.

[0025] According to another aspect of the present disclosure, a method for evaluating the quality of a biological signal may include: receiving a biological signal based on a first measurement; dividing the biological signal into multiple sub-signals; generating a typical waveform by superimposing the multiple sub-signals; evaluating the quality of the measured biological signal by comparing the multiple sub-signals with the typical waveform; estimating biological information based on the measured biosignal based on the quality of the measured biosignal being higher than a predetermined threshold; and performing a second measurement within a duration greater than the first measurement based on the quality of the measured biosignal being lower than or equal to the predetermined threshold, and performing quality evaluation on the second measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a block diagram of an apparatus for estimating bio-information according to an embodiment.

[0027] Figure 2 is a flowchart of a method of evaluating the quality of a biosignal according to an embodiment.

[0028] Figures 3A to 6B : are diagrams explaining a process of evaluating the quality of a biosignal according to an embodiment.

[0029] Figure 7 is a flowchart of a method of evaluating the quality of a biosignal according to an embodiment.

[0030] Figure 8 is a block diagram illustrating an apparatus for estimating bio-information according to an embodiment.

[0031] Figure 9 is a flowchart of a method of estimating biological information according to an embodiment.

[0032] Figure 10 is a flowchart of a method of estimating biological information according to an embodiment.

[0033] Figure 11 is a diagram of a wrist wearable electronic device for estimating bio-information according to an embodiment.

[0034] Figure 12 is a diagram of a mobile electronic device for estimating bio-information according to an embodiment.

[0035] Figure 13 is a diagram of an ear wearable electronic device for estimating bio-information according to an embodiment.

[0036] Throughout the drawings and detailed description, unless otherwise described, the same drawing reference numerals will be understood to refer to the same elements, features, and structures. The relative size and depiction of these elements may be exaggerated for clarity, illustration, and convenience. DETAILED DESCRIPTION

[0037] Details of example embodiments are included in the following detailed description and accompanying drawings. Advantages and features of the present disclosure and methods for achieving the advantages and features of the present disclosure will be more clearly understood based on the following example embodiments described in detail with reference to the accompanying drawings. Throughout the drawings and detailed description, unless otherwise described, the same reference numerals will be understood to refer to the same elements, features, and structures.

[0038] It should be understood that although the terms first, second, etc. can be used here to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish an element from another element. In addition, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In the specification, unless clearly described to the contrary, the words "comprise" and "include" and variants (such as, "have", "composed of", "have" or "composed of") will be understood to imply the elements included in the statement but do not exclude any other elements. Terms (such as, "unit" and "module") represent the unit for processing at least one function or operation, and they can be implemented by using hardware, software or a combination of hardware and software.

[0039] Figure 1 is a block diagram illustrating an apparatus for estimating bio-information according to an embodiment.

[0040] Reference Figure 1 The apparatus 100 for estimating bio-information may include a sensor 110 and a processor 120 (or more than one processor). The sensor 110 and the processor 120 may be integrally formed with each other in a single hardware device, or may be separately formed in two or more hardware devices.

[0041] The sensor 110 can obtain a periodic biosignal (i.e., a biosignal having a plurality of repetitive pulse waveforms) by continuously measuring the biosignal from the subject over a predetermined period of time. In this case, the biosignal may be, for example, an electrocardiogram (ECG), a photoplethysmography (PPG), a ballistocardiogram (BCG), an electromyogram (EMG), an impedance plethysmography (IPG), a pressure wave, and a video plethysmography (VPG), but is not limited thereto.

[0042] For example, the sensor 110 may include a PPG sensor for acquiring a PPG signal from an object, and the PPG sensor may include one or more light sources for emitting light onto the user's object and one or more detectors for detecting light reflected or scattered from the object. The light source may include a light emitting diode (LED), a laser diode (LD), a phosphor, etc., and may be formed as a single light source or an array of two or more light sources. Each light source may emit light of a different wavelength. In addition, the detector may include a photodiode, a phototransistor, a complementary metal oxide semiconductor (CMOS) image sensor, a charge coupled device (CCD) image sensor, etc., and may be formed as a single detector or an array of two or more detectors.

[0043] The processor 120 may control the sensor 110 and may evaluate the quality of the biosignal received from the sensor 110. The processor 120 may evaluate the quality of the biosignal measured by the sensor 110 by using the received biosignal itself, the biosignal filtered by a low-pass filter, a high-pass filter, a band-pass filter, etc., or the biosignal obtained by N-th order differentiation / integration of the received biosignal, etc., where N is a positive integer.

[0044] Hereinafter, reference will be made to Figures 2 to 7 Various examples of determining the quality of a biosignal are described.

[0045] Figure 2 is a flowchart of a method of evaluating the quality of a biosignal according to an embodiment. Figures 3A to 6B : are diagrams explaining each process of evaluating the quality of a biosignal according to an embodiment.

[0046] Reference Figure 2 In operation 211 , the processor 120 may set a quality assessment region in which quality assessment is to be performed in the biosignal. Figure 3A The quality assessment area 31 is shown to be set in units of 15 heartbeats, and the quality assessment area 31 may be set in units of a predetermined number of heartbeats or a predetermined period (for example, a period of 15 seconds (SEC)).

[0047] When a continuous biosignal measured by the sensor 110 is input in real time, or when the input of the measured biosignal is completed, the processor 120 may check the beat count or elapsed time starting from a predetermined time point (e.g., a measurement start point or a point after a predetermined time has elapsed), and when a set number of beats or a set time has elapsed, the processor 120 may set an area from the predetermined time point to the current time point as a quality assessment area. The quality assessment area may be set by sliding over time, and operations 212 to 215 to be described below may be performed for each set quality assessment area. In this case, the quality assessment areas 31a and 31b may be as shown in FIG. Figure 3B Slide to overlap each other as shown, or can be as Figure 3C The slides shown are so as not to overlap each other.

[0048] Then, in operation 212, the processor 120 may divide the signal of the set quality evaluation area into a plurality of sub-signals. Figure 4A As shown, the processor 120 may divide the signal 41 of the quality assessment area into sub-signals 41-1, 41-2, and 41-3. In addition, the processor 120 may set a reference point in each of the divided sub-signals. For example, Figure 4B As shown, the processor 120 can set the initial minimum point 42a, the maximum point 42b, the maximum slope point 42c, the tangent intersection point 42d which is the intersection of the tangent at the initial minimum point and the tangent at the maximum slope point, etc. as reference points, but the reference points are not limited thereto.

[0049] Subsequently, in operation 213, the processor 120 may extract a typical waveform by using the divided sub-signals. For example, the processor 120 may extract one typical waveform representing the quality assessment area by overlapping the sub-signals based on the reference points set for the sub-signals in operation 212. Figure 5A , the processor 120 can process the sub-signals B1, B2, B N-1 , and B N Predetermined weights W1, W2, W N-1 and W N Applied to each sub-signal B1, B2, B N-1 and B N To obtain the typical waveform 51. In this case, the weights may be values ​​that are equally defined for the respective sub-signals, or may be values ​​that include at least some differently defined values. Figure 5B , the processor 120 can process each sub-signal B1, B2, B N-1 and B N The amplitudes of the sub-signals B1, B2, B N-1and B N , and then overlapping the sub-signals to obtain the typical waveform 51. In this way, if an abnormally large noise signal is detected as a sub-signal, the influence of the corresponding noise heartbeat can be reduced.

[0050] Next, in operation 214, the processor 120 may evaluate the quality of each sub-signal by using the typical waveform extracted in operation 213. For example, Figure 6A As shown, the processor 120 can calculate the typical waveform 61 and each sub-signal B1, B2, B N-1 and B N The similarity between the N-order derivative signal of the typical waveform 61 and each sub-signal B1, B2, B N-1 and B N The similarity between the N-order derivative signals of the sub-signals B1, B2, B N-1 and B N Here, the N-order derivative signal may be a first-order derivative signal or a second-order derivative signal, but is not limited thereto. The processor 120 may obtain the similarity value itself or a value obtained by using a predetermined model as the quality value of each sub-signal. In this case, the similarity may be calculated by various methods such as correlation coefficient, mean square error (MSE), root mean square error (RMSE), etc.

[0051] That is, the similarity evaluation in this embodiment includes all of the following: similarity evaluation based on the original signal and similarity evaluation based on the N-order derivative signal (such as, the first-order derivative signal or the second-order derivative signal), and it should be understood that, unless specifically distinguished, the similarity evaluation includes not only the similarity based on the original signal, but also the similarity based on the N-order derivative signal.

[0052] In the case of dividing the sub-signals into units of heartbeats, each sub-signal may have a different duration due to different heartbeats, and therefore, the latter part of each sub-signal waveform may have a different shape. Therefore, the processor 120 may calculate the similarity between the typical waveform during a predetermined period of the sub-signal and each sub-signal. For example, referring to Figure 6B , instead of the length of the typical waveform 61 and the sub-signal B i Instead of normalizing the lengths of the sub-signals to the same size, the processor 120 may calculate the similarity between the typical waveform and the waveform in a predetermined region CD excluding the rear portion of the waveform. For example, the processor 120 may determine as the similarity calculation region an interval corresponding to 10% to 70% of the duration of the typical waveform, an interval corresponding to 75% of the average or median value of the duration of the sub-signals, or the like.

[0053] Then, in operation 215, the processor 120 may evaluate the quality of the signal in the quality assessment area based on the quality assessment results of each sub-signal. For example, the processor 120 may calculate statistical values ​​(such as mean, standard deviation, variance, coefficient of variation, etc.) of the quality values ​​of each sub-signal, and may evaluate the quality of the signal in the quality assessment area based on the calculated statistical values. For example, the processor 120 may determine the calculated statistical value itself or a value obtained by applying a predefined model as the signal quality value in the corresponding quality assessment area. In addition, if the signal quality value in the quality assessment area exceeds a predefined reference value, the processor 120 may determine that the quality is good, and if not, the processor 120 may determine that the quality is poor. Upon completing the quality assessment of the signal in the current quality assessment area, the processor 120 may proceed to operation 711 for setting a quality assessment area to evaluate the quality of the signal in the subsequent quality assessment area.

[0054] Figure 7 is a flowchart of a method of evaluating the quality of a biosignal according to an embodiment.

[0055] Reference Figure 7 In operation 711, the processor 120 may set a quality assessment area in the biosignal where quality assessment is to be performed. The quality assessment area may be set in units of a predetermined number of heartbeats or in units of a predetermined time period. When the biosignal is input in real time or when the input of the measured biosignal is completed, the processor 120 may check the beat count or elapsed time starting from a predetermined time point (e.g., a measurement start point or a point after a predetermined time has elapsed), and when the set number of beats or the set time has elapsed, the processor 120 may set the area from the predetermined time point to the current time point as the quality assessment area.

[0056] Then, the processor 120 may divide the signal of the set quality evaluation area into a plurality of sub-signals in operation 712. The processor 120 may divide the signal of the quality evaluation area into sub-signals in units of heartbeats and may set a reference point in each of the divided sub-signals.

[0057] Subsequently, in operation 713, the processor 120 may extract a typical waveform using the divided sub-signals. In this case, the processor 120 may extract a typical waveform by overlapping the sub-signals based on a reference point set for each sub-signal, and may overlap the sub-signals by first applying a predefined weight (e.g., a fixed value (e.g., 1) defined identically for each sub-signal, or a value including at least some differently defined values) to each sub-signal. In addition, the processor 120 may overlap the sub-signals after normalizing their amplitudes to the same magnitude.

[0058] Next, in operation 714, the processor 120 may evaluate the quality of each sub-signal using the representative waveform extracted in operation 713. For example, the processor 120 may calculate the similarity between the representative waveform and each sub-signal, and may evaluate the quality of each sub-signal based on the calculated similarity. For example, the processor 120 may obtain the similarity value of each sub-signal itself or a value obtained by using a predetermined model as the quality value of each sub-signal. In this case, the processor 120 may calculate the similarity between the representative waveform and each sub-signal during a predetermined period of the sub-signal. For example, the processor 120 may calculate the similarity between the representative waveform and each sub-signal during a predetermined time interval starting from the reference point of each of the multiple sub-signals.

[0059] Then, in operation 715, the processor 120 may determine whether the number of iterations for extracting a typical waveform is satisfied. For example, if the number of the current iteration is less than a predefined reference value, the processor 120 may determine to execute the next iteration for extracting a typical waveform. In another example, the processor 120 may calculate the similarity between the typical waveform extracted in the current iteration and the typical waveform extracted in the previous iteration, and if the calculated similarity is less than a predetermined threshold, the processor 120 may determine to execute the next iteration for extracting a typical waveform. In another example, if the difference between the quality evaluation results of each sub-signal in the current iteration and the quality evaluation results of each sub-signal in the previous iteration (for example, the difference between the statistical value (e.g., average, median, etc.) of the quality evaluation results of the sub-signals in the current iteration and the statistical value of the quality evaluation results of the sub-signals in the previous iteration) exceeds a predetermined threshold, the processor 120 may determine to execute the next iteration. However, the determination is not limited to this.

[0060] Subsequently, when it is determined in operation 715 that the next iteration is to be performed, the processor 120 may adjust the weights to be applied to the respective sub-signals in the next iteration in operation 716, and may perform operations 713 and 714 again. For example, based on the quality evaluation results of the respective sub-signals calculated in the current iteration of operation 714, the processor 120 may adjust the weights of the respective sub-signals. For example, the processor 120 may set the quality values ​​of the respective sub-signals in the current iteration as the weights of the respective sub-signals. However, the present disclosure is not limited thereto.

[0061] Next, in operation 717, based on the quality evaluation results of each sub-signal, the processor 120 may evaluate the quality of the signal in the quality evaluation area. For example, the processor 120 may calculate statistical values ​​(such as the mean, standard deviation, variance, coefficient of variation, etc.) of the quality values ​​of each sub-signal, and may evaluate the quality of the signal in the quality evaluation area based on the calculated statistical values. For example, the processor 120 may determine the calculated statistical value itself or a value obtained by applying a predefined model as the signal quality value in the corresponding quality evaluation area. In addition, if the signal quality value in the quality evaluation area exceeds a predefined threshold, the processor 120 may determine that the quality is good; if not, the processor 120 may determine that the quality is poor.

[0062] Return to reference Figure 1 The processor 120 may estimate bio-information based on the quality evaluation result of the bio-signal. In this case, the bio-information may include, but is not limited to, blood pressure, arrhythmia, vascular age, skin elasticity, skin age, arterial hardness, aortic pressure waveform, stress index, fatigue level, etc.

[0063] For example, the processor 120 may estimate the biological information by using the signal in the quality assessment region having a good quality assessment result. In this case, if there are a plurality of quality assessment regions having good quality assessment results, the processor 120 may select, for example, any one quality assessment region in the order of the quality values ​​of the respective quality assessment regions, or may select two or more quality assessment regions, and may use the signals of the respective quality assessment regions.

[0064] The processor 120 may extract one or more features from the typical waveform extracted from the corresponding quality assessment region. For example, the processor 120 may extract the amplitude and / or time values ​​associated with the propagating wave and the reflected wave, the shape of the waveform, the time and / or amplitude value at the maximum point during the contraction phase of the waveform, the time and / or amplitude value at the minimum point, the entire or partial area of ​​the waveform, the elapsed time, etc. as features. However, these are merely examples.

[0065] The processor 120 may estimate the bioinformation by combining one or two or more extracted features and using a predefined bioinformation estimation model. The bioinformation estimation model may be predefined using various methods such as linear function equations, nonlinear regression analysis, neural networks, deep learning, etc.

[0066] In another example, if there is no quality evaluation region of the input biosignal having a good quality evaluation result, the processor 120 may guide the user to re-measure the biosignal, or may terminate estimating the biosignal.

[0067] In another example, by controlling the sensor 110 to measure the biosignal for a first period (e.g., 40 seconds), the processor 120 may evaluate the quality of the signal input from the sensor 110, and if there is no quality evaluation area with good signal quality, the processor 120 may increase the measurement time to control the sensor 110 to continuously further measure the biosignal for a second period (e.g., 20 seconds) after the first period. Based on the biosignal measured during the first period and / or the second period, the processor 620 may perform quality evaluation again.

[0068] Figure 8 is a block diagram of an apparatus for estimating bio-information according to an embodiment.

[0069] Reference Figure 8 , the apparatus 800 for estimating biological information may include a sensor 810, a processor 820, an output interface 830, a storage device 840, and a communication interface 850. In this case, the above reference Figures 1 to 7 Various embodiments of the sensor 810 and the processor 820 are described so that their description will be omitted.

[0070] The output interface 830 can provide the user with the processing results of the processor 820. For example, the output interface 830 can display the estimated biological information value of the processor 820 on a display. In this case, if the estimated blood pressure value falls outside the normal range, the output interface 830 can provide a warning message to the user by changing the color, line thickness, etc. or displaying the abnormal value together with the normal range, so that the user can easily identify the abnormal value. In addition, regardless of whether there is a visual display of the value, the output interface 830 can use an audio output module (such as a speaker) or a tactile module to provide the estimated biological information value to the user in a non-visual manner through voice, vibration, touch, etc.

[0071] In addition, the output interface 830 can display the quality evaluation process performed by the processor 820, the quality evaluation result, etc. in a visual manner (such as a graph). In addition, if the quality of the biosignal is poor based on the quality evaluation result, the output interface 830 can guide the user to re-measure the biosignal, additionally measure the biosignal, or terminate the estimation of the biosignal.

[0072] The storage device 840 may store information related to estimated biometric information. For example, the storage device 840 may store biometric signals acquired by the sensor 810 and processing results (e.g., quality assessment results and estimated biometric information values) by the processor 820. Furthermore, the storage device 840 may store information such as a biometric information estimation model, units of quality assessment regions, thresholds used for quality assessment, and user characteristic information. In this case, the user characteristic information may include the user's age, gender, and health status.

[0073] The storage device 840 may include at least one storage medium selected from the group consisting of a flash memory, a hard disk memory, a multimedia card micro memory, a card-type memory (e.g., an SD memory, an XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk, but is not limited thereto.

[0074] The communication interface 850 can communicate with external devices to send and receive various data related to estimated biometric information. The external device may include an information processing device (such as a smartphone, tablet PC, desktop computer, laptop computer, etc.). For example, the communication interface 850 can send the biometric information estimation results to an external device (such as a user's smartphone, etc.), allowing the user to use a relatively high-performance device to manage and monitor the component analysis results. In addition, if the external device includes a sensor for measuring biometric signals, the communication interface 850 can receive the biometric signals from the external device for quality assessment.

[0075] The communication interface 850 can communicate with external devices by using various wired or wireless communication technologies, such as Bluetooth communication, Bluetooth Low Energy (BLE) communication, near field communication (NFC), WLAN communication, ZigBee communication, infrared data association (IrDA) communication, Wi-Fi Direct (WFD) communication, ultra-wideband (UWB) communication, ANT+ communication, WIFI communication, radio frequency identification (RFID) communication, 3G, 4G and 5G communication, etc. However, this is merely exemplary and is not intended to be limiting.

[0076] Figure 9 is a flowchart of a method of estimating biological information according to an embodiment.

[0077] Figure 9 The method can be based on Figure 1 or Figure 8 An example of a method of estimating bio-information performed by the apparatus 100 or 800 for estimating bio-information of an embodiment of the present invention will be briefly described below to avoid redundancy.

[0078] Reference Figure 9 , the apparatus for estimating bio-information may first measure a bio-signal of a subject from a user using a sensor in operation 911, and may evaluate the quality of the measured bio-signal in operation 912. The method of evaluating the quality of the bio-signal is described above in detail.

[0079] Then, if the quality of the biosignal is good in operation 913, the apparatus for estimating bioinformation may extract one or more features from the good quality signal in the quality evaluation area, and may estimate the bioinformation by using the extracted features in operation 914. If the quality of the biosignal is poor in operation 913, the apparatus for estimating bioinformation may terminate estimating the bioinformation or may guide the user to remeasure the biosignal in operation 915.

[0080] Figure 10 is a flowchart of a method of estimating biological information according to an embodiment.

[0081] Figure 10 The method can be based on Figure 1 or Figure 8 An example of a method of estimating bio-information performed by the apparatus 100 or 800 for estimating bio-information of an embodiment of the present invention will be briefly described below to avoid redundancy.

[0082] Reference Figure 10 , the apparatus for estimating bio-information may first measure a bio-signal of a subject from a user using a sensor in operation 1011, and may evaluate the quality of the measured bio-signal in operation 1012. The method of evaluating the quality of the bio-signal is described above in detail.

[0083] Then, if the quality of the biosignal is poor in operation 1013, the apparatus for estimating bioinformation may determine whether to additionally measure the biosignal in operation 1014. If additional measurement is required, the apparatus for estimating bioinformation may increase the measurement time in operation 1015 and may proceed to operation 1011 to continuously additionally measure the biosignal for the increased period. If it is determined in operation 1014 that additional measurement is not required, the apparatus for estimating bioinformation may terminate estimating the bioinformation in operation 1017 or may guide the user to remeasure the biosignal.

[0084] If the quality of the biosignal is good in operation 1013, the apparatus for estimating bioinformation may estimate the bioinformation by using the biosignal in operation 1016. In this case, the apparatus for estimating bioinformation may extract features from the good quality signal in the quality evaluation region and estimate the bioinformation by using the extracted features and a bioinformation estimation model.

[0085] Figures 11 to 13 is a diagram showing a method including Figure 1 or Figure 8 A block diagram of various structures of an electronic device of the apparatus 100 or 800 for estimating bio-information.

[0086] The electronic device may include, for example, various types of wearable devices (e.g., smart watches, smart bands, smart glasses, smart headphones, smart rings, smart patches, and smart necklaces), as well as mobile devices (such as smart phones, tablet PCs, etc.), or home appliances or various Internet of Things (IoT) devices based on Internet of Things (IoT) technology (e.g., home IoT devices, etc.).

[0087] The electronic device may include a sensor device, a processor, an input device, a communication module, a camera module, an output device, a storage device, and a power supply module. All components of the electronic device may be integrally mounted in a specific device, or may be distributed in two or more devices. The sensor device may include a sensor (e.g., a PPG sensor) of the apparatus 100 and 800 for estimating biometric information, and may also include additional sensors (such as a gyroscope sensor, a global positioning system (GPS), etc.).

[0088] The processor can execute a program stored in a storage device to control components connected to the processor, and can perform various data processing or calculations including estimation of biological information (e.g., blood pressure). For example, the processor can evaluate the quality of a PPG signal measured by a PPG sensor of a sensor device, and can estimate blood pressure based on the evaluation result. Various embodiments of evaluating quality and estimating blood pressure have been described above, so a detailed description thereof will be omitted. The processor may include a main processor (e.g., a central processing unit (CPU) or an application processor (AP)) and an auxiliary processor (e.g., a graphics processing unit (GPU), an image signal processor (ISP), a sensor hub processor, or a communication processor (CP)) that can operate independently of the main processor or in conjunction with the main processor.

[0089] The input device may receive commands and / or data to be used by each component of the electronic device from a user, etc. The input device may include, for example, a microphone, a mouse, a keyboard, or a digital pen (eg, a stylus, etc.).

[0090] The communication module can support the establishment of direct (e.g., wired) communication channels and / or wireless communication channels between an electronic device and other electronic devices, servers, or sensor devices within a network environment, as well as the execution of communication via the established communication channels. The communication module may include one or more communication processors, which may operate independently of the processor and support direct communication and / or wireless communication. The communication module may include a wireless communication module (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module, etc.) and / or a wired communication module (e.g., a local area network (LAN) communication module, a power line communication (PLC) module, etc.). These various types of communication modules may be integrated into a single chip, or may be implemented separately as multiple chips. The wireless communication module may identify and authenticate the electronic device in the communication network by using user information (e.g., an international mobile subscriber identity (IMSI)), etc.) stored in a user identification module.

[0091] A camera module can capture still images or moving images. A camera module may include a lens assembly having one or more lenses, an image sensor, an image signal processor, and / or a flash. The lens assembly included in the camera module may collect light emitted from an object to be imaged.

[0092] The output device may visually / non-visually output data generated or processed by the electronic device. The output device may include a sound output device, a display device, an audio module, and / or a haptic module.

[0093] The sound output device can output sound signals to the outside of the electronic device. The sound output device may include a speaker and / or a receiver. The speaker can be used for general purposes (such as playing multimedia or playing records), and the receiver can be used for incoming calls. The receiver can be implemented separately from the speaker or as part of the speaker.

[0094] The display device can visually provide information to the outside of the electronic device. The display device may include, for example, a display, a holographic device, or a projector, and a control circuit for controlling the device. The display device may include a touch circuit suitable for detecting a touch and / or a sensor circuit suitable for measuring the strength of the force caused by the touch (e.g., a pressure sensor, etc.).

[0095] The audio module can convert sound into an electrical signal, or vice versa. The audio module can obtain sound via an input device, or can output sound via a sound output device and / or a speaker and / or earphone of another electronic device directly or wirelessly connected to the electronic device.

[0096] The haptic module may convert the electrical signal into mechanical stimulation (eg, vibration, motion, etc.) or electrical stimulation that can be recognized by the user through tactile or kinesthetic sense. The haptic module may include, for example, a motor, a piezoelectric element, and / or an electrical stimulator.

[0097] The storage device may store driving conditions required to drive the sensor device and various data required by other components of the electronic device. The various data may include, for example, software and input data and / or output data for commands associated therewith. The storage device may include volatile memory and / or non-volatile memory.

[0098] The power module can manage the power supplied to the electronic device. The power module can be implemented as, for example, at least a portion of a power management integrated circuit (PMIC). The power module can include a battery, which can include a non-rechargeable primary battery, a rechargeable secondary battery, and / or a fuel cell.

[0099] Reference Figure 11 According to an embodiment, the electronic device may be implemented as a wristwatch wearable device 1100 and may include a main body and a wristband. A display is provided on the front surface of the main body and may display various application screens including time information, received message information, etc. A sensor device 1110 may be provided on the rear surface of the main body.

[0100] Reference Figure 12 According to an embodiment, the electronic device may be implemented as a mobile device 1200 such as a smart phone.

[0101] Mobile device 1200 may include a housing and a display panel. The housing may form the exterior of mobile device 1200. The housing has a first surface, on which the display panel and cover glass may be sequentially disposed, with the display panel exposed to the outside through the cover glass. Sensor device 1110, a camera module, and / or an infrared sensor, etc. may be disposed on a second surface of the housing. A processor and various other components may be disposed within the housing.

[0102] Reference Figure 13 According to an embodiment, the electronic device may be implemented as an ear-worn device 1300 .

[0103] The ear-worn device 1300 may include a main body and an earband. A user may wear the ear-worn device 1300 by hanging the earband on the auricle. Depending on the shape of the ear-worn device 1300, the earband may be omitted. The main body may be placed in the external auditory canal. The sensor device 1310 may be installed in the main body. In addition, a processor may be provided in the main body, and blood pressure may be estimated by using the pulse wave signal measured by the sensor device 1310. Alternatively, the ear-worn device 1300 may estimate blood pressure by interacting with an external device. For example, the pulse wave signal measured by the sensor device 1310 of the ear-worn device 1300 may be transmitted to an external device (e.g., a mobile device, a tablet PC, etc.) via a communication module provided in the main body, so that the processor of the external device can estimate the blood pressure, and the estimated blood pressure value may be output via a sound output module provided in the main body of the ear-worn device 1300.

[0104] The present disclosure can be implemented as computer-readable codes written on a computer-readable recording medium. The computer-readable recording medium may be any type of recording device that stores data in a computer-readable manner.

[0105] Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and carrier wave (e.g., data transmission via the Internet). Computer-readable recording media can be distributed on multiple computer systems connected to a network so that computer-readable code is written therein and executed therefrom in a decentralized manner. A programmer having ordinary skills in the field to which the present disclosure pertains can easily derive the functional programs, codes, and code segments required to implement the present disclosure.

[0106] The present disclosure has been described herein with respect to preferred embodiments. However, it will be apparent to those skilled in the art that various changes and modifications may be made without changing the technical concepts and basic features of the present disclosure. Therefore, it is clear that the above-described embodiments are illustrative in all respects and are not intended to limit the present disclosure.

Claims

1. A method for evaluating the quality of a biological signal, the method comprising: receiving a measured biological signal; setting a quality assessment region in the measured biological signal; dividing the signal of the quality assessment area into a plurality of sub-signals; extracting a representative waveform by using the plurality of sub-signals; evaluating the quality of each sub-signal based on the typical waveform; and evaluating the quality of the signal in the quality evaluation area based on the quality evaluation results of the plurality of sub-signals, The step of extracting the typical waveform includes: obtaining the typical waveform by applying a weight predetermined for each sub-signal to each sub-signal, The steps of extracting the typical waveform and evaluating the quality of each sub-signal include: repeatedly evaluating the quality at least a predetermined number of times, and until the similarity between the typical waveform in the current iteration and the typical waveform in the previous iteration is greater than or equal to a first predetermined threshold, or until the quality evaluation results of the multiple sub-signals in the current iteration and the quality evaluation results of the multiple sub-signals in the previous iteration are greater than or equal to a second predetermined threshold, and The weights to be applied in the current iteration are adjusted based on quality evaluation results of the respective sub-signals in the previous iteration.

2. The method according to claim 1, wherein The step of setting the quality assessment area includes setting the quality assessment area based on a predetermined number of heartbeats or a predetermined unit of time period.

3. The method according to claim 1, wherein The step of dividing into the plurality of sub-signals includes dividing the signal of the quality assessment area into the plurality of sub-signals based on a unit of heartbeat.

4. The method according to claim 1, wherein The step of dividing into the plurality of sub-signals comprises: setting a reference point in each of the plurality of sub-signals, The step of extracting the typical waveform includes extracting the typical waveform representing the quality assessment area by overlapping the multiple sub-signals based on a set reference point.

5. The method according to claim 4, wherein The step of setting the reference point includes setting one of a minimum point, a maximum point, a maximum slope point, and a tangent intersection point of each of the plurality of sub-signals as a reference point.

6. The method according to claim 4, wherein: The step of extracting the typical waveform includes overlapping the plurality of sub-signals after applying a predefined weight to each of the plurality of sub-signals.

7. The method according to claim 4, wherein: The step of extracting the typical waveform includes overlapping the plurality of sub-signals after normalizing the plurality of sub-signals to have the same size.

8. The method according to claim 1, wherein The step of evaluating the quality of each of the multiple sub-signals includes: calculating the similarity between the typical waveform and each sub-signal, or the similarity between the N-th order derivative signal of the typical waveform and the N-th order derivative signal of each sub-signal, and evaluating the quality of each sub-signal based on the calculated similarity, where N is a positive integer.

9. The method according to claim 8, wherein The step of evaluating the quality of each of the plurality of sub-signals includes calculating a similarity between the representative waveform and each of the plurality of sub-signals during a predetermined time interval starting from a reference point of each of the plurality of sub-signals.

10. The method according to any one of claims 1 to 9, wherein The step of evaluating the quality of the signal in the quality evaluation area includes calculating a statistical value of a quality evaluation result of each of the plurality of sub-signals, and evaluating the quality of the signal in the quality evaluation area based on the calculated statistical value.

11. A device for estimating biological information, the device comprising: a sensor configured to measure a biological signal from a subject; and The processor is configured to: setting a quality assessment region in the measured biological signal; dividing the signal of the quality assessment area into a plurality of sub-signals; extracting a representative waveform by using the plurality of sub-signals; evaluating the quality of each of the plurality of sub-signals based on the extracted typical waveform to evaluate the quality of the signal in a quality evaluation area; and Estimating biological information based on quality assessment, The processor is further configured to obtain the typical waveform by applying a weight predetermined for each sub-signal to each sub-signal. The processor is further configured to: repeatedly evaluate the quality of each of the multiple sub-signals at least a predetermined number of times, and until the similarity between the typical waveform in the current iteration and the typical waveform in the previous iteration is greater than or equal to a first predetermined threshold, or until the quality evaluation results of the multiple sub-signals in the current iteration and the quality evaluation results of the multiple sub-signals in the previous iteration are greater than or equal to a second predetermined threshold, and The weights to be applied in the current iteration are adjusted based on quality evaluation results of the respective sub-signals in the previous iteration.

12. The apparatus according to claim 11, wherein The processor is further configured to set the quality assessment area based on a unit of a predetermined number of heartbeats or a predetermined period of time.

13. The apparatus according to claim 11, wherein The processor is further configured to divide the signal of the quality assessment area into the plurality of sub-signals based on a unit of heartbeat.

14. The apparatus according to claim 11, wherein The processor is further configured to set a reference point in each of the plurality of sub-signals, and extract the representative waveform representing the quality assessment region by overlapping the plurality of sub-signals based on the set reference point.

15. The apparatus according to claim 11, wherein The processor is further configured to calculate a similarity between the typical waveform and each of the multiple sub-signals, or a similarity between an N-order derivative signal of the typical waveform and an N-order derivative signal of each of the multiple sub-signals, and to evaluate a quality of each of the multiple sub-signals based on the calculated similarity, where N is a positive integer.

16. The apparatus according to claim 11, wherein The processor is further configured to calculate a statistical value of a quality evaluation result of each of the plurality of sub-signals, and evaluate the quality of the signal in the quality evaluation area based on the calculated statistical value.

17. An electronic device comprising: a subject and a device for estimating blood pressure disposed in the subject, Among them, devices used to estimate blood pressure include: a photoplethysmography (PPG) sensor configured to measure a PPG signal from a subject; and The processor is configured to: Setting a quality assessment region in the PPG signal; dividing the signal of the quality assessment area into a plurality of sub-signals; extracting a representative waveform by using the plurality of sub-signals; evaluating the quality of each of the plurality of sub-signals based on the extracted typical waveform to evaluate the quality of the signal in a quality evaluation area; and Estimate blood pressure based on quality assessment, The processor is further configured to obtain the typical waveform by applying a weight predetermined for each sub-signal to each sub-signal. The processor is further configured to: repeatedly evaluate the quality of each of the multiple sub-signals at least a predetermined number of times, and until the similarity between the typical waveform in the current iteration and the typical waveform in the previous iteration is greater than or equal to a first predetermined threshold, or until the quality evaluation results of the multiple sub-signals in the current iteration and the quality evaluation results of the multiple sub-signals in the previous iteration are greater than or equal to a second predetermined threshold, and The weights to be applied in the current iteration are adjusted based on quality evaluation results of the respective sub-signals in the previous iteration.

18. A method for evaluating the quality of a biological signal, the method comprising: receiving a first biosignal based on the first measurement; Divide the biological signal into multiple sub-signals; extracting a representative waveform by using the plurality of sub-signals; evaluating the quality of each of the plurality of sub-signals based on the extracted typical waveform to evaluate the quality of the first biosignal; estimating bio-information based on the first bio-signal based on a quality of the first bio-signal being higher than a predetermined threshold; and performing a second measurement within a second period after the first period of the first measurement based on the quality of the first biosignal being lower than or equal to the predetermined threshold, and performing a quality evaluation on the second biosignal based on the second measurement, The step of extracting the typical waveform includes: obtaining the typical waveform by applying a weight predetermined for each sub-signal to each sub-signal, The steps of extracting the typical waveform and evaluating the quality of each of the multiple sub-signals include: repeatedly evaluating the quality at least a predetermined number of times, and until the similarity between the typical waveform in the current iteration and the typical waveform in the previous iteration is greater than or equal to a first predetermined threshold, or until the quality evaluation results of the multiple sub-signals in the current iteration and the quality evaluation results of the multiple sub-signals in the previous iteration are greater than or equal to a second predetermined threshold, and The weights to be applied in the current iteration are adjusted based on quality evaluation results of the respective sub-signals in the previous iteration.

Images