Method of determining regularity of biosignal, device and method of estimating biological information

Abstract

A method of determining regularity of a biological signal, an apparatus and a method of estimating biological information are provided. The method of determining regularity of a biological signal can include acquiring a plurality of pulse waveforms of a biological signal, acquiring a plurality of slope waveforms corresponding to the plurality of pulse waveforms, binarizing the plurality of slope waveforms, acquiring synchronization information of the plurality of pulse waveforms based on binarizing the plurality of pulse waveforms, acquiring a synchronization rate of a reference interval based on the synchronization information, and determining whether the biological signal is regular or irregular based on the synchronization rate of the reference interval.

Description

[0001] This application claims priority to Korean Patent Application No. 10-2020-0116088, filed on September 10, 2020, with the Korean Intellectual Property Office, the entire disclosure of which is incorporated herein by reference. Technical Field

[0002] The exemplary embodiments of this disclosure relate to methods for determining the regularity of biological signals and techniques for estimating biological information by determining the regularity of biological signals. Background Technology

[0003] With an aging population, rising healthcare costs, and a shortage of medical personnel specializing in healthcare services, research into IT-healthcare convergence technologies, which combine information technology (IT) and medical technology, is actively underway. Specifically, health monitoring systems have extended care from hospitals to patients' homes and offices, allowing patients to monitor their health status in their daily lives. Examples of biosignals indicating an individual's health status include electrocardiogram (ECG) signals, photoplethysmography (PPG) signals, and electromyography (EMG) signals, and various biosignal sensors are being developed to measure biosignals in everyday life. For example, a PPG sensor can estimate a person's blood pressure by analyzing pulse waveforms, which reflect the condition of the cardiovascular system.

[0004] According to research on PPG biosignals, the waveform of a PPG signal can be the sum of a propagating wave from the heart to the periphery of the body and a reflected wave returning from the periphery. Furthermore, it is known that information for estimating blood pressure can be obtained by extracting various features associated with the propagating or reflected waves. However, if the quality of the biosignal is degraded due to arrhythmias or motion noise from the heartbeat, the accuracy of blood pressure estimation can decrease. Summary of the Invention

[0005] According to one aspect of an example embodiment, a method for determining the regularity of a biological signal may include: acquiring multiple pulse waveforms of the biological signal; acquiring multiple slope waveforms corresponding to the multiple pulse waveforms; binarizing the multiple slope waveforms; acquiring synchronization information of the multiple pulse waveforms based on the binarization of the multiple pulse waveforms; acquiring a synchronization rate of a reference interval based on the synchronization information; and determining whether the biological signal is regular or irregular based on the synchronization rate of the reference interval.

[0006] Biological signals may include at least one of the following signals: electrocardiogram (ECG) signal, photoplethysmography (PPG) signal, cardiac impact plethysmography (BCG) signal, electromyography (EMG) signal, impedance plethysmography (IPG) signal, pressure wave signal, or video volume plethysmography (VPG) signal.

[0007] The step of obtaining the plurality of slope waveforms may include: obtaining the plurality of slope waveforms by differentiating the plurality of pulse waveforms.

[0008] The step of binarizing the plurality of slope waveforms may include: binarizing the plurality of slope waveforms into a first value based on the slope value being positive at each time point, and binarizing the plurality of slope waveforms into a second value based on the slope value being negative at each time point.

[0009] The steps to obtain synchronization information may include: obtaining the absolute value of the average of the binarized values ​​at each time point as the synchronization information.

[0010] The steps to determine whether a biological signal is regular or irregular may include: determining that the biological signal is regular based on the synchronization rate of the reference interval being greater than or equal to a predetermined threshold.

[0011] The method may include: adjusting the reference interval based on the fact that the synchronization rate of the reference interval is less than a predetermined threshold; and obtaining another synchronization rate based on the adjusted reference interval.

[0012] The steps for adjusting the reference interval may include: adjusting the reference interval based on synchronization information so that a predetermined number of peak points are included in the reference interval.

[0013] The method may include: obtaining values ​​based on at least one of the type of biological signal, the type of biological information to be estimated, or user characteristic information, or setting a reference interval based on synchronization information.

[0014] According to one aspect of an example embodiment, an apparatus for estimating biological information may include: a sensor configured to measure a biological signal from an object; and a processor configured to: acquire synchronization information of the plurality of pulse waveforms based on a plurality of slope waveforms corresponding to a plurality of pulse waveforms constituting the biological signal; acquire a synchronization rate of a reference interval based on the acquired synchronization information; determine whether the biological signal is regular or irregular based on the synchronization rate of the reference interval; and estimate biological information using the biological signal based on the assumption that the biological signal is regular.

[0015] The processor can obtain the multiple slope waveforms corresponding to the multiple pulse waveforms by differentiating the multiple pulse waveforms of the biological signal.

[0016] The processor can binarize the slope waveform into a first value based on a positive slope value at each time point, and binarize the slope waveform into a second value based on a negative slope value at each time point.

[0017] The processor can obtain the absolute value of the average of the binarized values ​​at each time point as synchronization information.

[0018] The processor can obtain the average of the absolute values ​​within the reference interval from the acquired absolute values, and use this average as the synchronization rate of the reference interval.

[0019] The processor can determine that the biological signal is regular based on the synchronization rate of the reference interval being greater than or equal to a predetermined threshold.

[0020] The processor can adjust the reference interval based on the synchronization rate of the reference interval being less than a predetermined threshold; and obtain the synchronization rate.

[0021] The processor can determine a representative pulse waveform among the plurality of pulse waveforms based on the regularity of the biological signal; and extract features from the determined representative pulse waveform that will be used for biological information estimation.

[0022] The processor can extract features by searching for intervals in a representative pulse waveform that correspond to a reference interval.

[0023] The processor can detect one or more minima from a representative pulse waveform; and extract at least one of the time and amplitude of the biosignal corresponding to the detected minima as a feature.

[0024] The processor can use the irregularity of biological signals to control the output interface to guide the remeasurement of biological signals or terminate the estimation of biological signals.

[0025] The processor can, based on the fact that the biosignals measured during the first time period are irregular, control the sensor to increase the measurement time and measure the biosignals during the second time period; and determine whether the biosignals measured during the second time period are regular or irregular.

[0026] Biometric information may include one or more of the following: blood pressure, arrhythmia, vascular age, skin elasticity, skin age, arterial stiffness, aortic pressure waveform, stress index, and fatigue level.

[0027] According to one aspect of an example embodiment, a method for estimating biological information may include: measuring a biological signal from an object; decomposing the biological signal into a plurality of pulse waveforms; acquiring synchronization information of the plurality of pulse waveforms based on slope waveforms corresponding to the plurality of pulse waveforms; acquiring a synchronization rate of a reference interval based on the synchronization information; determining whether the biological signal is regular or irregular based on the synchronization rate of the reference interval; and estimating biological information using the biological signal based on the determination that the biological signal is regular.

[0028] The method may include binarizing the plurality of slope waveforms at each time point in the reference interval.

[0029] The steps to obtain synchronization information may include: obtaining the absolute value of the average of the binarized values ​​at each time point as the synchronization information.

[0030] The steps to obtain the synchronization rate of the reference interval may include: obtaining the average of the absolute values ​​within the reference interval from the obtained absolute values, as the synchronization rate of the reference interval.

[0031] The steps for estimating biological information may include: determining a representative pulse waveform among the plurality of pulse waveforms based on the regularity of the biological signal, and extracting features from the determined representative pulse waveform that will be used for biological information estimation.

[0032] The steps for extracting features may include: extracting features by searching for intervals of representative pulse waveforms that correspond to reference intervals.

[0033] The method may include at least one of the following: based on determining that the biological signal is regular, increasing the biological signal measurement time, guiding the remeasurement of the biological signal, or terminating the biological information estimation.

[0034] Other features and aspects will become clear from the following detailed description, drawings, and claims. Attached Figure Description

[0035] The above and other aspects will become clearer from the following description of exemplary embodiments taken in conjunction with the accompanying drawings, in which:

[0036] Figure 1 This is a block diagram illustrating an apparatus for determining the regularity of biological signals according to an example embodiment;

[0037] Figure 2 This is a flowchart illustrating a method for determining the regularity of biological signals according to an example embodiment;

[0038] Figures 3A to 3F It is a graph used to describe each operation that determines the regularity of biological signals;

[0039] Figure 4 This is a flowchart illustrating a method for determining the regularity of biological signals according to another example embodiment;

[0040] Figure 5A and Figure 5B It is a graph used to describe the method of adjusting the reference interval;

[0041] Figure 6 This is a block diagram illustrating an apparatus for estimating biological information according to an example embodiment;

[0042] Figure 7 This is a block diagram illustrating an apparatus for estimating biological information according to another example embodiment;

[0043] Figure 8 This is a flowchart illustrating a method for estimating biological information according to an example embodiment;

[0044] Figure 9 This is a flowchart illustrating a method for estimating biological information according to another example embodiment;

[0045] Figure 10 This is a block diagram illustrating a wearable device according to an example embodiment; and

[0046] Figure 11 This is a block diagram illustrating a smart device according to another example embodiment.

[0047] Throughout the accompanying drawings and detailed embodiments, unless otherwise described, the same reference numerals will be understood to denote the same elements, features, and structures. For clarity, illustration, and convenience, the relative dimensions and depictions of these elements, features, and structures may be exaggerated. Detailed Implementation

[0048] Details of exemplary embodiments are provided in the following detailed description with reference to the accompanying drawings. The disclosure will be more readily understood by referring to the following detailed description and drawings of the exemplary embodiments. However, the disclosure may be implemented in many different forms and should not be construed as limited to the exemplary embodiments set forth herein. Rather, these exemplary embodiments are provided so that the disclosure will be thorough and complete, fully conveying the concept of this disclosure to those skilled in the art, and the disclosure will be defined only by the appended claims. Throughout the specification, the same reference numerals denote the same elements.

[0049] It will be understood that although the terms “first,” “second,” etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. Furthermore, unless the context clearly indicates otherwise, the singular form of a term is intended to include the plural form as well. In the specification, unless explicitly stated otherwise, the word “comprising” and its variations (such as “including”) will be understood to indicate that the stated element is included but not excluded any other element. Terms (such as “unit” and “module”) mean a unit that performs at least one function or operation, and a unit may be implemented using hardware, software, or a combination of hardware and software.

[0050] Figure 1 This is a block diagram illustrating an apparatus for determining the regularity of biological signals according to an example embodiment.

[0051] Reference Figure 1 The device 100 for determining the regularity of biological signals includes a sensor 110 and a processor 120.

[0052] Sensor 110 can acquire biosignals for regularity determination. In this case, the biosignal can be a biosignal that is continuously measured over a predetermined time period and exhibits multiple repetitive pulse waveforms. However, the biosignal does not necessarily have to be a biosignal acquired continuously over a predetermined time period, and can be multiple biosignals having a single pulse waveform measured at different time points. Furthermore, the biosignals do not need to be of the same type. The biosignal can include, but is not limited to, at least one of: ECG signal, PPG signal, cardiac impaction recording (BCG) signal, EMG signal, impedance volumetric recording (IPG) signal, pressure wave signal, and video volumetric recording (VPG) signal. Additionally, the biosignal to be processed for regularity determination can include various signals measured from the user's body parts, or can include signals obtained by differentiating the measured signal (e.g., second-order differential signals).

[0053] For example, sensor 110 may include various sensors that measure the aforementioned biological signals. Sensor 110 may measure biological signals from various parts of the user's body. Sensor 110 may transmit the measured biological signals, or biological signals obtained by, for example, performing a second-order derivative on the measured biological signals, to processor 120.

[0054] For example, sensor 110 may include a PPG sensor. The PPG sensor may include one or more light sources and one or more detectors, the light sources being configured to emit light onto a user's body part, and the detectors being configured to detect light reflected or scattered from the body part. The light source may include a light-emitting diode (LED), a laser diode, a phosphor, etc. The light source 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. Furthermore, 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.

[0055] In another example, sensor 110 can receive biosignals from an external device using wired or wireless communication technologies. The external device may include a smart device or wearable device equipped with a biosignal measurement sensor or biosignal measurement functionality. Wired or wireless communication technologies may include, but are not limited to: Bluetooth communication, Bluetooth Low Energy (BLE) communication, Near Field Communication (NFC), Wireless Local Area Network (WLAN) communication, ZigBee communication, Infrared Data Association (IrDA) communication, Wi-Fi Direct (WFD) communication, Ultra Wideband (UWB) communication, Ant+ communication, Wi-Fi communication, Radio Frequency Identification (RFID) communication, 3G communication, 4G communication, and / or 5G communication.

[0056] Processor 120 can be electrically connected to sensor 110 to control sensor 110. Based on the biological signals received from sensor 110, processor 120 can determine the regularity of the biological signals. Processor 120 can determine the regularity based on the slope of the biological signals. Processor 120 can determine the regularity of the biological signals so that various features for biological information estimation can be extracted from the biological signals. Processor 120 can extract corresponding intervals of signal increase or decrease from the slope waveform of the biological signals and can determine whether there is a regularity within those intervals.

[0057] In the following text, reference will be made to Figures 2 to 5B Various example embodiments of methods for determining the regularity of biological signals are described.

[0058] Figure 2 This is a flowchart illustrating a method for determining the regularity of biological signals according to an example embodiment. Figures 3A to 3F It is a graph used to describe each operation that determines the regularity of biological signals.

[0059] Reference Figure 2 The device 100 for determining the regularity of biological signals can acquire multiple pulse waveforms from the biological signals to be used for regularity analysis (operation 211). For example, the biological signal can be filtered and decomposed into multiple pulse waveforms. For example, the waveforms of the biological signal can be averaged as a whole in units of a predetermined number of bits to obtain multiple pulse waveforms, or the waveforms of the biological signal can be decomposed into multiple waveforms by gating based on feature points of a reference signal (e.g., the R wave of an ECG signal). However, these are merely examples. Figure 3A The diagram shows 15 pulse waveforms superimposed on each other. Here, the pulse waveforms are superimposed based on a predefined reference point. For example, the reference point could be the starting point of each pulse waveform. However, the embodiment is not limited to this.

[0060] Based on the acquisition of multiple pulse waveforms, device 100 can acquire the slope waveform of each pulse waveform (operation 212). For example, device 100 for determining regularity can acquire the slope waveform by differentiating each pulse waveform. Figure 3B The diagram shows the slope waveforms obtained by differentiating 15 pulse waveforms and superimposing them on each other.

[0061] Based on the acquired slope waveforms, device 100 can binarize each slope waveform to extract information about the increase and decrease of the pulse waveform (operation 213). For example, regardless of the slope value at each time point, the slope waveform is binarized to +1 based on a positive slope value, and to -1 based on a negative slope value. In one example, based on a positive slope value of any slope waveform among the plurality of slope waveforms at any time point, the slope value of that arbitrary slope waveform at that arbitrary time point is binarized to a first value (e.g., +1), and based on a negative slope value of any slope waveform among the plurality of slope waveforms at any time point, the slope value of that arbitrary slope waveform at that arbitrary time point is binarized to a second value (e.g., -1). For example, in Figure 3B In the process, because all pulse waveforms in the interval between time indices 0 and 18 have slope values ​​less than 0, all waveforms are converted to -1. Furthermore, because some pulse waveforms in the interval between time indices 18 and 20 have slope values ​​less than 0, these waveforms are converted to -1. Additionally, because the remaining pulse waveforms in the interval between time indices 18 and 20 have slope values ​​greater than 0, these remaining waveforms are converted to +1. Figure 3C The binarized values ​​of each slope waveform obtained in this way at each time point are shown.

[0062] Based on the binarization of the slope waveform, device 100 can obtain synchronization information for each pulse waveform based on the binarization result of each superimposed pulse waveform (operation 214). For example, all binarized values ​​at a specific time point can be summed and divided by the number of pulse waveforms to obtain an average value, and then the absolute value of this average value can be obtained to obtain synchronization information. In this way, the absolute value of the average value at all time points can be obtained. The absolute value of the average of the binarized values ​​can be called the absolute value of the average. Based on all pulse waveforms that increase or decrease in the same direction, the absolute value of the average is 1. In this case, in order to apply more weight to the case where all pulse waves increase or decrease in the same direction (e.g., the absolute value of the average is 1), the absolute value of the average value obtained at each time point can be increased to the power of M. In this case, M can be an integer greater than or equal to 2. Figure 3D The diagram illustrates the synchronization information obtained by raising the absolute value of the average of the binarized values ​​at each time point to a second power.

[0063] Based on the obtained synchronization information, device 100 can use the absolute value of the average at each time point to obtain the average synchronization rate of the reference interval (operation 215). For example, referring to... Figure 3EThe average synchronization rate of the reference interval L1 can be obtained by averaging the absolute values ​​of the average values ​​within the reference interval L1 (e.g., from 0 to time point T). In this case, the reference interval can be set to a value obtained in advance through preprocessing based on the type of biosignal, the type of biological information to be estimated, user characteristic information, etc. Optionally, the device 100 for determining regularity can set the reference interval by using the absolute value of the average value at each time point before obtaining the average synchronization rate. For example, as described below, the reference interval can be set to include a preset number of peak points based on the absolute value of the average value at each time point.

[0064] Based on the obtained synchronization rate, device 100 can determine whether the average synchronization rate of the reference interval is greater than or equal to a preset threshold (operation 216). If the average synchronization rate of the reference interval is greater than or equal to the preset threshold (operation 216 - Yes), device 100 can determine that there is regularity within the reference interval (operation 217). In other words, device 100 can determine that the biological signal is regular. Optionally, if the average synchronization rate of the reference interval is less than the preset threshold (operation 216 - No), device 100 can determine that there is no regularity within the reference interval (operation 218). In other words, device 100 can determine that the biological signal is irregular. For example, Figure 3F This is a graph showing the average synchronization rate from the starting point 0 to each time index, obtained by gradually increasing the time index. (See reference...) Figure 3F ,exist Figure 3E The average synchronization rate of the reference interval (0-100) set in the data is 0.69. If the average synchronization rate of 0.69 in the reference interval (0-100) is greater than or equal to the threshold, it can be determined that there is a regularity within the reference interval; otherwise, it can be determined that there is no regularity within the reference interval (0-100).

[0065] Figure 4 This is a flowchart illustrating a method for determining the regularity of biological signals according to another example embodiment. Figure 5A and Figure 5B It is a graph used to describe the method of adjusting the reference interval.

[0066] Reference Figure 4 The device 100 for determining the regularity of biological signals can acquire multiple pulse waveforms (operation 411) that will be used to analyze the regularity of biological signals.

[0067] Based on the acquisition of multiple pulse waveforms, the device 100 can differentiate each pulse waveform to obtain the slope waveform of each pulse waveform (operation 412).

[0068] Based on the acquired slope waveform, the device 100 can binarize each slope waveform in order to extract the increase and decrease information of the corresponding pulse waveform (operation 413).

[0069] Based on the binarization of the slope waveform, device 100 can obtain synchronization information for each pulse waveform based on the binarization result of each superimposed pulse waveform (operation 414). For example, the binarized values ​​at each time point can be summed and divided by the number of pulse waveforms to obtain an average value, and then the absolute value of the average value at each time point can be obtained.

[0070] Based on the acquired synchronization information, device 100 can use the absolute value of the average at each time point to obtain the average synchronization rate of the first reference interval (operation 415). Initially, the first reference interval can be set using values ​​pre-obtained based on the type of biosignal, the type of bioinformation to be estimated, user characteristic information, and / or the absolute value of the average at each time point obtained in operation 414.

[0071] Based on the obtained average synchronization rate, device 100 can determine whether the average synchronization rate is greater than or equal to a preset threshold (operation 416). Based on the average synchronization rate of the first reference interval being greater than or equal to the preset threshold (operation 416 - Yes), device 100 can determine that there is regularity in the first reference interval (operation 417). In other words, device 100 can determine that the biosignal is regular.

[0072] Optionally, based on the average synchronization rate being less than a preset threshold (operation 416 - No), device 100 may determine whether the adjustment count for the reference interval has been satisfied (operation 418). Based on the determination that the adjustment count for the reference interval has not been satisfied (operation 418 - No), device 100 may adjust the first reference interval to a second reference interval (operation 419). In this case, the adjustment count can be preset.

[0073] For example, such as Figure 3F As shown, assuming the first reference interval is 0 to 100 and the average synchronization rate of the first reference interval (0-100) is 0.69, device 100 can determine that there is no regularity in the first reference interval (0-100) based on a preset threshold of 0.8. Device 100, used to determine regularity, can adjust the reference interval so that the absolute value of the average value obtained in operation 414 is greater than or equal to... Figure 5A The preset threshold T1 shown is used to set the time interval from 0 to 80 as the second reference interval L2. For example, the device 100 for determining regularity may set the second reference interval as the interval (0-80), in which the number of peak points in the second reference interval whose absolute value of the average value obtained in operation 414 is greater than or equal to the threshold T1 satisfies a preset number (e.g., 5).

[0074] Based on the setting of a second reference interval, device 100 can acquire the average synchronization rate of the second reference interval (operation 415), and based on the fact that the average synchronization rate of the second reference interval is greater than or equal to a threshold (operation 416 - Yes), device 100 can determine that regularity exists in the second reference interval (operation 417). In other words, device 100 can determine that the biological signal is regular. Optionally, based on the fact that the average synchronization rate of the second reference interval is less than a threshold (operation 416 - No), device 100 can determine whether the adjustment number has been met (operation 418), and based on the fact that the adjustment number has been met (operation 418 - Yes), device 100 can avoid adjusting the reference interval and can determine that there is no regularity in the second reference interval. In other words, device 100 can determine that the biological signal is irregular. (Refer to...) Figure 5B Based on the average synchronization rate of 0.85 and the threshold of 0.8 in the second reference interval 0-80 as described above, the device 100 can determine that the biosignal is regular in the second reference interval.

[0075] Figure 6 This is a block diagram illustrating a device for estimating biological information according to an example embodiment.

[0076] Reference Figure 6 The device 600 for estimating biological information includes a sensor 610 and a processor 620.

[0077] Sensor 610 can measure biosignals from a user. For example, sensor 610 may include a light source and a detector, and uses the light source and detector to measure PPG signals from the body part based on the contact between the sensor and the user's body part and changes in the contact pressure between the sensor and the user's body part. However, biosignals are not limited to PPG signals and may include ECG signals, BCG signals, IPG signals, VPG signals, etc.

[0078] The processor 620 can receive biological signals from the sensor 610 and use the received biological signals to estimate biological information. In this case, the biological information includes, but is not limited to: blood pressure, arrhythmia, vascular age, skin elasticity, skin age, arterial stiffness, aortic pressure waveform, stress index, and fatigue level.

[0079] The processor 620 can remove noise (such as motion noise) by using various noise removal techniques (such as filtering or smoothing of biological signals). For example, based on the fact that the biological signal is a PPG signal, bandpass filtering with a cutoff frequency of 1 Hz to 10 Hz can be performed.

[0080] Processor 620 can acquire biological signals and obtain multiple pulse waveforms by dividing the waveforms of the biological signals. Furthermore, processor 620 can determine the regularity of the biological signals based on the acquired multiple pulse waveforms. The process for determining the regularity of biological signals has been described above; therefore, it will be briefly described below.

[0081] For example, processor 620 can obtain a slope waveform by differentiating each pulse waveform and determine regularity based on the slope waveform of each pulse waveform. Processor 620 can binarize each slope waveform to extract information on the increase and decrease of the pulse waveform, sum all binarized values ​​at each time point, divide the sum by the number of pulse waveforms to obtain an average value, and obtain the absolute value of the average value to obtain the synchronization information of the pulse waveform. At this point, regardless of the slope value at each time point, the slope waveform is binarized as +1 if the slope value is positive, and as -1 if the slope value is negative. Furthermore, the average synchronization rate of the reference interval can be obtained using the absolute value of the average value at each time point.

[0082] Based on the fact that the average synchronization rate of the reference interval obtained as described above is greater than or equal to a predetermined threshold, the processor 620 can determine that the biological signal is regular in the reference interval and can use the biological signal to estimate biological information.

[0083] Based on the regularity of biological signals, processor 620 can extract one or more features for use in biological information estimation. Processor 620 can identify one of multiple pulse waveforms as a representative waveform and extract features by searching a reference interval of the identified representative waveform. For example, a pulse waveform (e.g., a first pulse waveform) can be identified as a representative waveform based on the time index of the biological signal measurement. However, the embodiments are not limited to this. Furthermore, two or more pulse waveforms can be identified as representative waveforms, and features can be extracted from each pulse waveform based on the existence of two or more representative waveforms.

[0084] For example, processor 620 may extract the amplitude and / or time of the component pulse waveforms constituting a biological signal (such as component pulse waveforms associated with propagating and reflected waves) as features. In this case, a reference interval of a biological signal is determined to be regular in order to extract the time at the minimum point of the component pulse waveform of the biological signal, and processor 620 may extract the amplitude of the biological signal corresponding to the time extracted at that minimum point as a feature. However, embodiments are not limited to this, and the shape of the biological signal waveform, the time and / or amplitude of the maximum point in the contraction interval of the biological signal, the time and / or amplitude of the minimum point of the biological signal, the entire or partial region of the biological signal waveform, or the time elapsed of the biological signal may be extracted as features.

[0085] The processor 620 can combine one or more of the acquired features and estimate biological information using a predefined bioinformatics estimation model. Various techniques (such as linear functional equations, nonlinear regression analysis, neural networks, deep learning, etc.) can be used to predefine the bioinformatics estimation model.

[0086] Based on the determination that the biological signal does not exhibit regularity within the reference interval, the processor 620 can control the output interface to guide the user to remeasure the biological signal or terminate the biological information estimation.

[0087] Based on the measurement of biological signals by sensor 610 within a first time period (e.g., 40 seconds), processor 620 can determine the regularity of the measured biological signals. If the measured biological signals are not regular, processor 620 can control sensor 610 to increase the measurement time and further measure the biological signals within a consecutive second time period (e.g., 20 seconds) following the first time period. Processor 620 can then redetermine the regularity based on the biological signals measured within the first and second time periods.

[0088] Furthermore, processor 620 can determine the risk of arrhythmia based on the regularity determination results of biological signals. For example, processor 620 can determine the number of times a reference interval is determined to be irregular, compared to the total number of times regularity of a reference interval is determined within a predetermined time period, and each time regularity is determined, processor 620 can determine a regular interval. Based on the satisfaction of preset criteria (such as the rate of change of regular intervals being greater than or equal to a threshold, or the continuous repetition of irregularity during a specific period of day (e.g., during nighttime sleep), processor 620 can determine the risk of arrhythmia.

[0089] Figure 7 This is a block diagram illustrating a device for estimating biological information according to another example embodiment.

[0090] Reference Figure 7 The device 700 for estimating biological information may include a sensor 610, a processor 620, an output interface 710, a storage device 720, and a communication interface 730. Figure 6 The configuration of sensor 610 and processor 620 is described in the example embodiments.

[0091] Output interface 710 can provide the processing results of processor 620 to a user. For example, output interface 710 may include a display that can show the biometric estimates of processor 620. In this case, if the biometric estimate is outside the normal range, a warning message can be provided to the user by adjusting the color or thickness of the line to make it easily identifiable, or by displaying the normal range together. In addition, output interface 710 may include a speaker or haptic module that can provide the biometric estimate to the user in a non-visual manner (such as voice, vibration, and touch) together with or independently of the visual display.

[0092] Furthermore, the output interface 710 can visually display the results of the regularity determination processing performed by the processor 620 as graphics or the like. Additionally, based on the determination that the biological signal lacks regularity, the output interface 710 can guide the user to remeasure the biological signal, or output information indicating that the biological information estimation has been terminated.

[0093] Storage device 720 can store information related to bioinformatics estimation. For example, storage device 720 can store biosignals acquired by sensor 610, processing results from processor 620 (such as results for determining regularity and bioinformatics estimates). Furthermore, storage device 720 can store bioinformatics estimation models, reference intervals, the number of times the reference intervals are adjusted, criteria used to adjust the reference intervals, thresholds used to determine regularity, user characteristic information, etc. In this case, user characteristic information may include the user's age, gender, health status, etc.

[0094] Storage device 720 may include, but is not limited to, at least one type of storage medium (such as flash memory, hard disk, multimedia microcard, card memory (e.g., Secure Digital (SD) or Extreme Digital (XD) memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc.).

[0095] The communication interface 730 can communicate with external devices to send and receive various data related to bioinformatics estimation. External devices may include information processing devices (such as smartphones, tablet PCs, desktop computers, laptop computers, etc.). For example, bioinformatics estimation results can be sent to external devices (such as the user's smartphone), allowing the user to manage and monitor the component analysis results via a relatively high-performance device.

[0096] The communication interface 730 can communicate with external devices using various wired or wireless communication technologies. Examples of such communication technologies include: Bluetooth, BLE, NFC, WLAN, ZigBee, IrDA, WFD, UWB, Ant+, Wi-Fi, RFID, 3G, 4G, and / or 5G. However, the foregoing technologies are merely examples and are not intended to be limiting.

[0097] Figure 8 This is a flowchart illustrating a method for estimating biological information according to an example embodiment.

[0098] Figure 8 The method can correspond to, according to Figure 6 or Figure 7 The method performed by device 600 or 700 for estimating biological information in an example embodiment will be briefly described below to avoid redundancy.

[0099] Reference Figure 8 The device for estimating biological information can measure biological signals from the user via sensors (operation 811) and determine the regularity of the measured biological signals (operation 812). In other words, the device can determine whether the biological signals are regular or irregular. The method for determining the regularity of biological signals has been described in detail above.

[0100] Based on the determination of regularity (operation 813 - Yes), the device can extract features from the biosignal (operation 814) and use the extracted features to estimate bioinformation (operation 816). For example, features related to the propagation and reflection waveforms (such as the time and amplitude of the minimum point of the pulse waveform component of the biosignal) can be extracted by searching a reference interval of the biosignal determined to be regular. Based on the determination of the absence of regularity (operation 813 - No), the device can terminate the bioinformation estimation or control the output to guide the user to remeasure the biosignal (operation 815).

[0101] Figure 9 This is a flowchart illustrating a method for estimating biological information according to another example embodiment.

[0102] Figure 9 The method can correspond to, according to Figure 6 or Figure 7 The method performed by device 600 or 700 for estimating biological information in an example embodiment will be briefly described to avoid redundancy.

[0103] Reference Figure 9The device for estimating biological information can measure biological signals from the user via sensors (operation 911) and determine the regularity of the measured biological signals (operation 912). In other words, the device can determine whether the biological signals are regular or irregular. The method for determining the regularity of biological signals has been described in detail above.

[0104] Based on the determination that no regularity exists (Operation 913 - No), the device can determine whether further measurement is needed (Operation 914), and based on the determination that further measurement is needed (Operation 914 - Yes), the device can increase the measurement time (Operation 915), and the process returns to Operation 911. Based on the determination that no further measurement is needed (Operation 914 - No), the device can terminate the bioinformatics estimation or controllable output interface to guide the user to remeasure (Operation 917).

[0105] Based on the determination of regularity (operation 913 - yes), the device can extract features from the biological signal (operation 916) and use the extracted features to estimate biological information (operation 918). In this case, the device for estimating biological information can extract features related to the propagation waveform and the reflection waveform (e.g., taking the time and amplitude of the minimum point of the pulse waveform component of the biological signal as an example) by searching a reference interval of the biological signal determined to be regular.

[0106] Figure 10 A wearable device is shown. The above-described example embodiments of devices 100, 600, and 700 for estimating biometric information can be embedded in a wearable device.

[0107] Reference Figure 10 The wearable device 1000 includes a main body 1010 and a strap 1030.

[0108] The strap 1030 can be attached to both ends of the body 1010 and is made of a flexible material to conform to the user's wrist. The strap 1030 may include a first strap and a second strap that are separate from each other. One end of each of the first strap and the second strap can be attached to a corresponding end of the body 1010, and the first strap and the second strap can be fastened to each other via a fastening device. In this case, the fastening device may be formed as a magnetic fastening device, a Velcro fastening device, a pin fastening device, but is not limited to these. In addition, the strap 1030 may be formed as an integrated part (such as a strip). In this case, air may be injected into the strap 1030, or an airbag may be included in the strap 1030, so that the strap 1030 can be elastic according to changes in pressure applied to the wrist, and changes in wrist pressure can be transmitted to the body 1010.

[0109] A battery that powers the wearable device 1000 can be embedded in the main body 1010 or the strap 1030.

[0110] Sensor 1020 is mounted on one side of body 1010. Sensor 1020 may include, for example, a light source and a detector.

[0111] The processor can be installed inside the main body 1010 and electrically connected to the components of the wearable device 1000. The processor can control the sensor 1020, and based on the biosignals received from the sensor 1020, the processor can determine the regularity of the biosignals. Based on determining that the biosignals are regular, the processor can estimate biological information based on the biosignals.

[0112] In addition, a storage device may be included within the main body 1010 to store reference information for bioinformatics estimation and information processed by various components.

[0113] Furthermore, the controller 1040 may be mounted on one side of the main body 1010 to receive control commands from the user and send the received control commands to the processor. The controller 1040 may include a power button for inputting commands to turn the wearable device 1000 on / off.

[0114] Furthermore, a display may be disposed on the front surface of the main body 1010 to output information, and the display may include a touchscreen capable of receiving touch input. The display may receive touch input from the user, send the received touch input to the processor, and display the processing results of the processor.

[0115] Furthermore, a communication interface for communicating with external devices can be installed in the main body 1010. The communication interface can send bioinformatics estimation results to external devices (such as a user's smartphone).

[0116] Figure 11 The diagram illustrates a smart device. This smart device may include a smartphone, tablet PC, etc. The smart device may include the functions of the aforementioned devices 100, 600, and 700 for estimating biological information.

[0117] Reference Figure 11 The smart device 1100 may include a sensor 1130 mounted on a surface of the body 1110. As shown, the sensor 1130 may include one or more light sources 1131 and one or more detectors 1132.

[0118] Furthermore, a display may be disposed on the front surface of the main body 1110. The display can visually output bioinformation estimation results, health status assessment results, etc. The display may include a touch screen, which receives information input via the touch screen and sends the received information to the processor.

[0119] The main body 1110 may include an image sensor 1120 as shown. The image sensor 1120 is capable of capturing various images, and for example, can acquire a fingerprint image of a finger when the finger touches the sensor 1130.

[0120] The processor can be installed in the main body 1110 and electrically connected to various components to control their operation. The processor can control the sensor 1130, and based on biological signals received from the sensor 1130, the processor can determine the regularity of the biological signals. Based on the determination of the regularity of the biological signals, the processor can estimate biological information based on the biological signals.

[0121] Example embodiments may be implemented using computer-readable code stored in a non-transitory computer-readable medium and executed by a processor. The code and code segments constituting a computer program can be inferred by a computer programmer in the art. Computer-readable media include all types of recording media that store computer-readable data. Examples of computer-readable media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. Furthermore, computer-readable media may be implemented in the form of a carrier wave (such as internet transmission). Moreover, computer-readable media may be distributed across networked computer systems, wherein computer-readable code can be stored and executed in a distributed manner.

[0122] Numerous examples have been described above. However, it will be understood that various modifications can be made. For example, suitable results may be achieved if the described techniques are performed in a different order and / or if components in the described system, architecture, apparatus, or circuit are combined in a different manner and / or replaced or supplemented by other components or their equivalents. Therefore, other embodiments are within the scope of the claims.

Claims

1. A method for determining the regularity of biological signals, the method comprising: Acquire multiple pulse waveforms of biological signals; Multiple slope waveforms corresponding to the multiple pulse waveforms are obtained by differentiating the multiple pulse waveforms; Binarize the multiple slope waveforms; Synchronization information of the multiple pulse waveforms is obtained by binarizing the multiple slope waveforms; The synchronization rate of the reference interval is obtained based on synchronization information; and The synchronization rate within a reference interval is used to determine whether a biological signal is regular or irregular. The steps for obtaining synchronization information include: obtaining the absolute value of the average of the binarized values ​​at each time point as the synchronization information.

2. The method according to claim 1, wherein, Biological signals include at least one of the following signals: electrocardiogram signal, photoplethysmography signal, cardiac impact recording signal, electromyography signal, impedance volume recording signal, pressure wave signal, and video volume recording signal.

3. The method according to claim 1 or 2, wherein, The step of binarizing the plurality of slope waveforms includes: based on the fact that the slope value of any slope waveform at any time point is positive, binarizing the slope value of the arbitrary slope waveform at any time point into a first value; and based on the fact that the slope value of any slope waveform at any time point is negative, binarizing the slope value of the arbitrary slope waveform at any time point into a second value.

4. The method according to claim 1, wherein, The steps to obtain the synchronization rate include: obtaining the average of the absolute values ​​within the reference interval from the obtained absolute values, and using this average as the synchronization rate of the reference interval.

5. The method according to claim 1 or 2, wherein, The steps to determine whether a biological signal is regular or irregular include: determining that the biological signal is regular based on the synchronization rate of the reference interval being greater than or equal to a predetermined threshold; and determining that the biological signal is irregular based on the synchronization rate of the reference interval being less than a predetermined threshold.

6. The method according to claim 1 or 2, further comprising: If the synchronization rate of the reference interval is less than a predetermined threshold, adjust the reference interval. and Another synchronization rate is obtained by adjusting the reference interval.

7. The method according to claim 6, wherein, The steps for adjusting the reference interval include: adjusting the reference interval based on synchronization information so that a predetermined number of peak points are included in the reference interval.

8. The method according to claim 1 or 2, further comprising: The value is obtained based on at least one of the type of biological signal, the type of biological information to be estimated, and user characteristic information, or the reference interval is set based on synchronization information.

9. An apparatus for estimating biological information, the apparatus comprising: The sensor is configured to measure biological signals from the object; and The processor is configured as follows: The synchronization information of the multiple pulse waveforms is obtained based on multiple slope waveforms corresponding to multiple pulse waveforms that constitute biological signals. The synchronization rate of the reference interval is obtained based on the acquired synchronization information; The synchronization rate within a reference interval is used to determine whether a biological signal is regular or irregular; and Based on the premise that biological signals are regular, biological signals are used to estimate biological information. The processor is further configured to: obtain the multiple slope waveforms corresponding to the multiple pulse waveforms by differentiating the multiple pulse waveforms of the biological signal. The processor is further configured to: binarize the plurality of slope waveforms and obtain the absolute value of the average of the binarized values ​​at each time point as synchronization information.

10. The device according to claim 9, wherein, The processor is also configured to: binarize the slope value of the arbitrary slope waveform at any time point to a first value based on the positive slope value of the arbitrary slope waveform at any time point, and binarize the slope value of the arbitrary slope waveform at any time point to a second value based on the negative slope value of the arbitrary slope waveform at any time point.

11. The device according to claim 9, wherein, The processor is also configured to: obtain the average of the absolute values ​​within the reference interval from the acquired absolute values, as the synchronization rate of the reference interval.

12. The device according to claim 9, wherein, The processor is also configured to: determine that the biological signal is regular based on the synchronization rate of the reference interval being greater than or equal to a predetermined threshold; and determine that the biological signal is irregular based on the synchronization rate of the reference interval being less than a predetermined threshold.

13. The device according to claim 9, wherein, The processor is also configured as follows: If the synchronization rate of the reference interval is less than a predetermined threshold, adjust the reference interval; and Another synchronization rate is obtained based on the adjusted reference interval.

14. The device according to claim 9, wherein, The processor is also configured as follows: Based on the premise that the biological signals are regular, a representative pulse waveform is determined among the multiple pulse waveforms; and Features that will be used for bioinformatics estimation are extracted from a defined representative pulse waveform.

15. The device according to claim 14, wherein, The processor is also configured to extract features by searching a reference interval of a representative pulse waveform.

16. The device according to claim 14, wherein, The processor is also configured as follows: Detect one or more minimum points from a representative pulse waveform; and At least one of the time and amplitude of the biosignal corresponding to the minimum point of detection is extracted as a feature.

17. The device according to claim 9, wherein, The processor is also configured to: based on the determination that the biological signal is irregular, control the output interface to guide the remeasurement of the biological signal or terminate the estimation of biological information.

18. The device according to claim 9, wherein, The processor is also configured as follows: Based on the irregularity of the biosignals measured in the first time period, the sensor is controlled to increase the measurement time to measure the biosignals in the second time period; and To determine whether the biosignals measured in the first and second time periods are regular or irregular.

19. The device according to claim 9, wherein, Biometric information includes one or more of the following: blood pressure, arrhythmia, vascular age, skin elasticity, skin age, arterial stiffness, aortic pressure waveform, stress index, and fatigue level.

20. A method for estimating biological information, the method comprising: Measuring biological signals from objects; Decompose biological signals into multiple pulse waveforms; Multiple slope waveforms corresponding to the multiple pulse waveforms are obtained by differentiating the multiple pulse waveforms; The synchronization information of the multiple pulse waveforms is obtained based on the multiple slope waveforms corresponding to the multiple pulse waveforms; The synchronization rate of the reference interval is obtained based on synchronization information; The synchronization rate of the reference interval is used to determine whether a biological signal is regular or irregular. and Based on the premise that biological signals are regular, biological signals are used to estimate biological information. The method further includes: binarizing the plurality of slope waveforms at each time point. The steps for obtaining synchronization information include: obtaining the absolute value of the average of the binarized values ​​at each time point as the synchronization information.

21. The method according to claim 20, wherein, The steps to obtain the synchronization rate of the reference interval include: obtaining the average of the absolute values ​​within the reference interval from the obtained absolute values, and using this average as the synchronization rate of the reference interval.

22. The method according to claim 20 or 21, wherein, The steps for estimating biological information include: determining a representative pulse waveform among the plurality of pulse waveforms based on the determination that the biological signal is regular, and extracting features from the determined representative pulse waveform that will be used for biological information estimation.

23. The method according to claim 22, wherein, The steps for feature extraction include: extracting features by searching a reference interval of a representative pulse waveform.

24. The method according to claim 20 or 21, further comprising: Based on the determination that biological signals are irregular, perform at least one of the following: increase the biological signal measurement time, guide the remeasurement of biological signals, and terminate the biological information estimation.

25. A method for estimating biological information, the method comprising: Multiple slope waveforms corresponding to multiple pulse waveforms of biological signals are obtained by differentiating multiple pulse waveforms of biological signals. Based on the multiple slope waveforms corresponding to multiple pulse waveforms of the biological signal, the synchronization information of multiple pulse waveforms of the biological signal is obtained. The synchronization rate of the reference interval is obtained based on the synchronization information; The synchronization rate of the reference interval is used to determine whether a biological signal is regular or irregular. and Based on the premise that biological signals are regular, biological signals are used to estimate biological information. The method further includes: binarizing the plurality of slope waveforms at each time point. The steps for obtaining synchronization information include: obtaining the absolute value of the average of the binarized values ​​at each time point as the synchronization information.

26. A computer-readable storage medium storing a program, which, when executed by a processor, causes the processor to perform the method of any one of claims 1 to 8 and 20 to 25.

Images