Device for estimating biological information

Abstract

A device for estimating bioinformation is provided. The device for estimating bioinformation according to an embodiment of the present disclosure includes: a sensor configured to obtain a biosignal from a subject; and a processor configured to obtain a second-order differential signal of the biosignal and extract a forward wave component from the biosignal based on whether a first local minimum point of the second-order differential signal is stable.

Description

[0001] This application claims priority from Korean Patent Application No. 10-2020-0009152 filed on January 23, 2020, in the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference in its entirety for all purposes. Technical Field

[0002] The following description relates to an apparatus and method for non-invasively estimating biological information. Background Art

[0003] Recently, with the aging of the population, the surge in medical expenses, and the lack of medical personnel for specialized medical services, research on IT-medical fusion technology that combines IT technology and medical technology is being actively conducted. Specifically, the monitoring of the health status of the human body is not limited to medical institutions, but is expanding to the field of mobile healthcare that can monitor the health status of users anytime and anywhere 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. Specifically, a PPG sensor can estimate the blood pressure of a human body by analyzing the shape of a pulse wave that reflects the cardiovascular state, etc.

[0004] According to research on PPG signals, a complete PPG signal is a superposition of a propagating wave that leaves the heart and moves toward the distal parts of the body, and a reflected wave that returns from the distal parts. Furthermore, it is known that information used to estimate blood pressure can be obtained by extracting various features associated with the propagating or reflected waves. Summary of the Invention

[0005] In one general aspect, a device for estimating biological information is provided, the device comprising: a sensor configured to obtain a biological signal from an object; and a processor configured to obtain a second-order differential signal of the biological signal and extract a forward wave component from the biological signal based on whether a first local minimum point of the second-order differential signal is stable.

[0006] The sensor may include a pulse wave sensor having a light source configured to emit light onto the object and a detector configured to detect light reflected or scattered from the object.

[0007] The processor may detect an inflection point in a detection period of the second-order differential signal, and may determine whether the first local minimum point is stable based on the presence of the inflection point.

[0008] The detection period may include a time interval between a first local maximum point and a first local minimum point of the second-order differential signal.

[0009] The processor may detect, as the inflection point, a point at which the waveform of the second order differential signal changes from being downwardly convex to being upwardly convex in the detection period of the second order differential signal.

[0010] The processor can obtain a fourth-order differential signal of the biological signal, can detect a first point that satisfies the conditions that the amplitude at the first point is greater than 0 and the amplitude at the second point is less than 0 in the detection period of the fourth-order differential signal, and can detect a point corresponding to the first point from the second-order differential signal as an inflection point.

[0011] When it is determined that the first local minimum point is stable, the processor may extract the forward wave component based on the first local minimum point of the second-order differential signal.

[0012] The processor can extract at least one of the following items as the forward wave component: the amplitude of the biological signal corresponding to the time of the first local minimum point, and the amplitude of the biological signal corresponding to the internal division point between the time of the first local minimum point and the time of the second local maximum point of the second-order differential signal.

[0013] Upon determining that the first local minimum point is unstable, the processor may detect a maximum amplitude point in a contraction portion of the biosignal, and may extract the forward wave component based on the detected maximum amplitude point.

[0014] The processor may extract at least one of the following as the forward wave component: the amplitude of the maximum amplitude point, and the amplitude of the biosignal corresponding to an internal division point between the time of the inflection point detected in the detection period of the second-order differential signal and the time of the maximum amplitude point.

[0015] The processor may estimate bio-information based on the extracted forward wave component.

[0016] The biological information may include one or more of blood pressure, vascular age, arterial stiffness, aortic pressure waveform, stress index, and fatigue level.

[0017] In another general aspect, a method for estimating biological information is provided, the method comprising: obtaining a biological signal from an object; obtaining a second-order differential signal of the biological signal; determining whether a first local minimum point of the second-order differential signal is stable; and extracting a forward wave component from the biological signal based on the determination.

[0018] The step of determining whether the first local minimum point of the second order differential signal is stable may include: detecting an inflection point in a detection period of the second order differential signal; and determining whether the first local minimum point is stable based on the presence of the inflection point.

[0019] The detection period may include a time interval between a first local maximum point and a first local minimum point of the second-order differential signal.

[0020] The detecting of the inflection point may include detecting, as the inflection point, a point at which a waveform of the second order differential signal changes from being downwardly convex to being upwardly convex in a detection period of the second order differential signal.

[0021] The step of detecting an inflection point may include: obtaining a fourth-order differential signal of a biological signal; detecting a first point satisfying the conditions that the amplitude at the first point is greater than 0 and the amplitude at the second point is less than 0 in a detection period of the fourth-order differential signal; and detecting a point corresponding to the first point from the second-order differential signal as an inflection point.

[0022] The extracting of the progressive wave component may include extracting the progressive wave component based on a first local minimum point of the second-order differential signal in response to determining that the first local minimum point is stable.

[0023] The step of extracting the forward wave component may include: in response to determining that the first local minimum point is stable, extracting at least one of the following items as the forward wave component: the amplitude of the biological signal corresponding to the time of the first local minimum point, and the amplitude of the biological signal corresponding to the internal division point between the time of the first local minimum point and the time of the second local maximum point of the second-order differential signal.

[0024] The extracting of the progressive wave component may include extracting a maximum amplitude point in a contraction portion of the biosignal in response to determining that the first local minimum point is unstable; and extracting the progressive wave component based on the detected maximum amplitude point.

[0025] The step of extracting the forward wave component based on the detected maximum amplitude point may include: extracting at least one of the following items as the forward wave component: the amplitude of the maximum amplitude point, and the amplitude of the biological signal corresponding to the internal division point between the time of the inflection point detected in the detection period of the second-order differential signal and the time of the maximum amplitude point.

[0026] Furthermore, the method of estimating biological information may further include estimating the biological information based on the extracted forward wave component.

[0027] In another general aspect, a method for estimating a user's bio-information is provided, the method comprising: obtaining a bio-signal of the user; obtaining a second-order differential signal of the bio-signal; determining whether there is an inflection point in the interval between a first local maximum point and a first local minimum point of the second-order differential signal where the waveform of the second-order differential signal changes from a downward convex to an upward convex; based on determining that there is no inflection point in the interval, using the first local minimum point of the second-order differential signal to extract a forward wave component from the bio-signal, or based on determining that there is an inflection point in the interval, using the maximum amplitude point in the contraction part of the bio-signal to extract the forward wave component; and estimating the bio-information based on the forward wave component. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1is a block diagram illustrating an apparatus for estimating bio-information according to an embodiment of the present disclosure.

[0029] Figure 2 is a block diagram illustrating an apparatus for estimating bio-information according to another embodiment of the present disclosure.

[0030] Figure 3 It shows that according to Figure 1 and Figure 2 A block diagram of a processor of an embodiment.

[0031] Figures 4A to 4D is a diagram explaining an example of extracting a progressive wave component from a biological signal.

[0032] Figure 5 is a flowchart illustrating a method of estimating biological information according to an embodiment of the present disclosure.

[0033] Figure 6 is a diagram illustrating a wearable device according to an embodiment of the present disclosure.

[0034] Figure 7 is a diagram illustrating a smart device according to an embodiment of the present disclosure.

[0035] 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 sizes and depictions of these elements may be exaggerated for clarity, illustration, and convenience. DETAILED DESCRIPTION

[0036] Details of other embodiments are included in the following detailed description and drawings. The advantages and features of the present invention and the methods of implementing the present invention will be more clearly understood from the embodiments described in detail below with reference to the accompanying drawings. Throughout the drawings and detailed description, unless otherwise specified, the same reference numerals will be understood to represent the same elements, features, and structures.

[0037] It will be understood that although the terms first, second, etc. can be used to describe various elements here, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. Unless otherwise explicitly stated, any reference to the singular may include the plural. In addition, unless explicitly described to the contrary, expressions such as "comprise" or "include" will be understood to indicate that the elements stated are included but do not exclude any other elements. In addition, terms such as "component" or "module" should be understood as units for performing at least one function or operation, and the units can be implemented as hardware, software, or a combination thereof.

[0038] Hereinafter, embodiments of an apparatus and method for estimating bio-information will be described in detail with reference to the accompanying drawings.

[0039] Figure 1 is a block diagram illustrating an apparatus for estimating bio-information according to an embodiment of the present disclosure. The apparatus 100 for estimating bio-information may be embedded in a terminal (such as a smart phone, a tablet PC, a desktop computer, a laptop computer, etc.), or may be manufactured as an independent hardware device. In this case, if the apparatus 100 for estimating bio-information is manufactured as an independent hardware device, the device may be a wearable device worn on an object OBJ to allow a user to easily measure bio-information while carrying the device. Examples of wearable devices may include watch-type wearable devices, bracelet-type wearable devices, wristband-type wearable devices, ring-type wearable devices, glasses-type wearable devices, headband-type wearable devices, etc., but the wearable device is not limited thereto and may be modified for various purposes (such as fixed-type devices used in medical institutions for measuring and analyzing bio-information).

[0040] Reference Figure 1 , an apparatus 100 for estimating bio-information includes a sensor 110 and a processor 120 .

[0041] like Figure 1 As shown in , the sensor 110 may obtain a biosignal from the object OBJ and may transmit the obtained biosignal to the processor 120. In this case, the biosignal may include a photoplethysmography (PPG) signal (hereinafter referred to as a "pulse wave signal"). However, the biosignal is not limited thereto and may include various biosignals that can be modeled by the sum of multiple waveform components (such as an electrocardiogram (ECG) signal, a photoplethysmography (PPG) signal, an electromyogram (EMG) signal, etc.).

[0042] For example, the sensor 110 may include a PPG sensor for measuring a PPG signal. The PPG sensor may include a light source for emitting light onto a subject, and a detector for measuring the PPG signal by detecting light emitted from the subject when the light emitted by the light source is scattered or reflected from the subject's body tissue. In this case, the light source may include at least one of a light emitting diode (LED), a laser diode (LD), and a phosphor, but is not limited thereto. The detector may include a photodiode.

[0043] Upon receiving a control signal from processor 120, sensor 110 can drive the PPG sensor to obtain a pulse wave signal from a subject. In this case, the subject can be a body part that is in contact with or adjacent to the PPG sensor, and can be a body part where pulse waves can be easily measured using photoplethysmography. For example, the subject can be an area on the wrist adjacent to the radial artery, and can include the upper portion of the wrist where veins or capillaries are located. When measuring the pulse wave in the area of ​​skin where the radial artery passes, the measurement can be relatively less affected by external factors that can cause errors in the measurement, such as the thickness of skin tissue in the wrist, etc. However, the skin area is not limited thereto and can be a distal part of the body where blood vessels are densely located, such as fingers, toes, etc.

[0044] Upon receiving a request from the user to estimate biometric information, processor 120 may generate a control signal for controlling sensor 110 and transmit the control signal to sensor 110. Furthermore, processor 120 may receive biometric signals from sensor 110 and estimate biometric information by analyzing the received biometric signals. In this case, biometric information may include, but is not limited to, blood pressure, vascular age, arterial stiffness, aortic pressure waveform, stress index, fatigue level, and the like.

[0045] Upon receiving the biosignal from the sensor 110 , the processor 120 may perform pre-processing such as filtering for removing noise, amplifying the biosignal, converting the signal into a digital signal, etc.

[0046] The processor 120 may extract features required for estimating bio-information by analyzing the waveform of the received bio-signal. For example, the processor 120 may obtain individual pulse waveform components constituting the waveform of the bio-signal and obtain features by using the obtained pulse waveform components or by appropriately combining the pulse waveform components with other additional information.

[0047] As will be referred to below Figure 3 As described in detail, the processor can obtain each pulse waveform component by analyzing the second-order differential signal of the biosignal. The processor 120 can obtain the time of the first local minimum point of the second-order differential signal and / or the amplitude of the biosignal corresponding to the time as a progressive wave component, and can obtain a feature by using the obtained progressive wave component.

[0048] However, due to noise in the measurement of the biosignal, non-ideal contact conditions of the human body, abnormal conditions of the subject, etc., a biosignal with a non-ideal waveform shape may be generated. In the biosignal obtained in these cases, the first local minimum point may not be detected at the position where the first local minimum point is originally expected to be detected from the second-order differential signal, or the first local minimum point may not be clearly detected. In order to stably extract features even in these cases, the processor 120 can determine whether the waveform of the biosignal (specifically, the first local minimum point of the second-order differential signal) is stable and can adaptively obtain the forward wave component based on this determination.

[0049] Figure 2 is a block diagram illustrating an apparatus for estimating bio-information according to another embodiment of the present disclosure.

[0050] Reference Figure 2 , the apparatus 200 for estimating biological information includes a sensor 110 , a processor 120 , an output interface 210 , a storage device 220 , and a communication interface 230 .

[0051] The sensor 110 may measure a biosignal from a subject, and the processor 120 may estimate bioinformation by using the biosignal measured by the sensor 110 .

[0052] The output interface 210 may output the bio-signal information measured by the sensor 110 and various processing results of the processor 120, and may provide the output information to the user. The output interface 210 may provide information through various visual methods / non-visual methods using a display module, a speaker, a tactile device, etc. installed in the apparatus 200 for estimating bio-information.

[0053] For example, once the user's blood pressure is estimated, the output interface 210 may output the estimated blood pressure by using various visual methods (such as by changing the color, line thickness, font, etc.) based on whether the estimated blood pressure value falls within the normal range or falls outside the normal range. Alternatively, the output interface 210 may output the estimated blood pressure by voice, or may output the estimated blood pressure using a non-visual method by providing different vibrations or tactile sensations according to abnormal blood pressure levels. In addition, when comparing the measured blood pressure with the previous measurement history, if it is determined that the measured blood pressure is abnormal, the output interface 210 may warn the user, or may provide guidance information about the user's behavior (such as food information that the user should pay attention to, information for making an appointment for a hospital appointment, etc.).

[0054] The storage device 220 may store various reference information required for estimating biometric information, obtained biometric signals, detected characteristic points, extracted features, biometric information estimation results, etc. In this case, the various reference information required for estimating biometric information may include user information (such as the user's age, gender, occupation, current health status, etc.), information about a biometric information estimation model, etc., but the reference information is not limited thereto.

[0055] For example, the storage device 220 may include at least one of the following storage media: flash memory, hard disk memory, multimedia card micro memory, card-type memory (for example, SD memory, XD memory, etc.), 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., but not limited to these.

[0056] Upon receiving a control signal including access information for the external device 250 from the processor 120, the communication interface 230 may access the communication network using a communication technology to connect to the external device 250. When connected to the external device 250, the communication interface 230 may receive various information related to the estimation of biological information from the external device 250, and may transmit the biological signals measured by the sensor 110, the biological information estimated by the processor 120, and the like to the external device 250. In this case, examples of the external device 250 may include other devices for estimating biological information, a cuff pressure meter for measuring cuff blood pressure, a smartphone, a tablet PC, a desktop computer, a laptop computer, and the like, but the external device 250 is not limited thereto.

[0057] In this case, examples of communication technologies may include: 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, and mobile communication. However, this is merely exemplary and is not intended to be limiting.

[0058] Figure 3 It shows that according to Figure 1 and Figure 2 A block diagram of a processor of an embodiment. Figures 4A to 4D : are diagrams explaining an example of extracting a forward wave component from a biological signal.

[0059] Reference Figure 3 , the processor 300 includes a stability determiner 310 , a feature obtainer 320 , and a bio-information estimator 330 .

[0060] Figure 4Ais a diagram illustrating the waveform of a pulse wave signal 40 composed of a superposition of five component pulses 41, 42, 43, 44, and 45. By appropriately combining the time information and amplitude information associated with each of the component pulses 41, 42, 43, 44, and 45 of the pulse wave signal 40, a feature highly correlated with blood pressure can be obtained. Typically, pulses up to the third component pulse are primarily used for estimating blood pressure; specifically, the first component pulse waveform component can be extracted as a component associated with the advancing wave. In some cases, depending on the individual, pulses after the third pulse may not be observed and may be difficult to detect due to noise or may have a low correlation with blood pressure estimation.

[0061] In an ideal biological signal, such as Figure 4A As shown in , an upwardly convex shape can be clearly shown at each time point of the pulse waveform components. However, due to noise in the measurement of the biosignal, abnormal contact between the subject and the sensor 110, or abnormal characteristics of the user's subject (e.g., abnormal vascular structure, etc.), a non-ideal waveform shape may be generated. Alternatively, when measuring the biosignal from a portion of the capillary blood vessels rather than the artery, the high-frequency components mostly disappear and only the low-frequency components remain, thereby generating a smooth waveform of the biosignal.

[0062] In order to stably obtain features from the biosignal measured under these circumstances, the stability determiner 310 may determine whether the waveform of the biosignal is stable. For example, in order to adaptively obtain the forward wave component based on the stability of the waveform of the biosignal, the stability determiner 310 may obtain a second-order differential signal of the biosignal measured by the sensor 110 and determine whether the first local minimum point of the second-order differential signal related to the forward wave component is stable.

[0063] For example, the stability determiner 310 may detect an inflection point during a detection period of the second-order differential signal and determine whether the first local minimum point is stable based on the presence of the inflection point. In this case, the detection period may include a time interval between the first local maximum point and the first local minimum point of the second-order differential signal and may be adjusted by considering device performance, speed, etc.

[0064] When detecting an inflection point during the detection period of the second-order differential signal, if no inflection point exists, the stability determiner 310 may determine that the first local minimum is stable. Conversely, if an inflection point exists during the detection period, the stability determiner 310 may determine that the first local minimum is unstable. In this case, the inflection point may be a point at which the waveform of the second-order differential signal changes from being convex downward to being convex upward during the detection period of the second-order differential signal.

[0065] The stability determiner 310 may obtain a fourth-order differential signal by, for example, performing fourth-order differentiation on the biosignal, and may detect an inflection point using the fourth-order differential signal. The stability determiner 310 may detect a first point in a detection period of the fourth-order differential signal, and the stability determiner 310 may detect a point corresponding to the first point t from the second-order differential signal as an inflection point, the first point satisfying a condition that the amplitude at the first point t is greater than 0 and the amplitude at a second point t+1 subsequent to the first point t is less than 0.

[0066] The feature obtainer 320 may adaptively obtain a progressive wave component based on the determination of the stability determiner 310 and may obtain a feature by using the obtained progressive wave component.

[0067] Figure 4B is a diagram illustrating a case where the stability determiner 310 determines that the first local minimum point is stable (ie, a case where an inflection point is not detected in the detection period of the second-order differential signal).

[0068] In response to determining that the first local minimum point is stable, the feature obtainer 320 may obtain a forward wave component based on the first local minimum point MP of the second-order differential signal. For example, the feature obtainer 320 may detect the first local minimum point MP of the second-order differential signal and obtain the amplitude P1 of the biosignal corresponding to the time T1 of the first local minimum point as the forward wave component. In another example, the feature obtainer 320 may obtain an internal dividing point between the time of the first local minimum point and the time of the second local maximum point of the second-order differential signal and obtain the amplitude of the biosignal corresponding to the internal dividing point as the forward wave component. In this case, the feature obtainer 320 may apply a weight to each of the time of the first local minimum point and the time of the second local maximum point. However, the feature is not limited to this, and the feature obtainer 320 may obtain the following values ​​as the forward wave component: a value having a predetermined ratio with the amplitude P1 at the first local minimum point MP, a value having a predetermined ratio with the time T1 at the first local minimum point MP, or an amplitude at a time point obtained by adding a predetermined value to time T1 or subtracting a predetermined value from time T1.

[0069] Figure 4C is a diagram illustrating a case where the stability determiner 310 determines that the first local minimum point is unstable (ie, a case where an inflection point is detected in the detection period).

[0070] The stability determiner 310 may be configured to determine the stability of the second-order differential signal ( Figure 4CThe inflection point IP is detected during a detection period (e.g., a period between the time Ta of the first local maximum point and the time Tb of the first local minimum point) of the second-order differential signal, and if the inflection point IP exists, the stability determiner 310 may determine that the first local minimum point is unstable. In other words, under normal circumstances, the first local minimum point appears at a point detected as the inflection point IP, but if the first local minimum point is not clearly detected at the point, the point is converted into an inflection point, and the first local minimum point is subsequently detected, the stability determiner 310 may determine that the first local minimum point actually detected from the second-order differential signal is unstable.

[0071] When the inflection point IP is detected, the feature obtainer 320 may detect the maximum amplitude point Pmax in the contraction portion of the biosignal and may obtain the forward wave component based on the maximum amplitude point Pmax, rather than using the first local minimum point actually detected from the second-order differential signal as the forward wave component. In this case, the contraction portion may represent the interval from the start point of the biosignal to the dicrotic notch point.

[0072] For example, Figure 4C As shown in , the feature acquirer 320 can obtain the amplitude value at the maximum amplitude point Pmax of the biological signal as the forward wave component. Figure 4D As shown in , the feature obtainer 320 may obtain an internal segmentation point between the time Tip of the detected inflection point IP and the time Tmax of the maximum amplitude point Pmax, and may obtain the amplitude Psys corresponding to the time Tsys of the internal segmentation point as a forward wave component. In this case, a predefined weight may be applied to each of the time Tip of the inflection point IP and the time Tmax of the maximum amplitude point Pmax. However, the feature is not limited to this, and the feature obtainer 320 may obtain the following values ​​as the forward wave component: a value having a predetermined ratio with the amplitude at the maximum amplitude point Pmax, a value having a predetermined ratio with the time Tmax of the maximum amplitude point Pmax, or an amplitude at a time point obtained by adding a predetermined value to the time Tmax or subtracting a predetermined value from the time Tmax.

[0073] After adaptively obtaining the forward wave component, the feature obtainer 320 can obtain features for estimating biometric information using the forward wave component. For example, the feature obtainer 320 can obtain the forward wave component (i.e., the amplitude value itself or a value obtained by processing the amplitude value) as a feature. For example, the feature obtainer 320 can process the forward wave component based on the type of biometric information, abnormal conditions of the user, etc., using various methods, including adding a predetermined value to the amplitude value, subtracting a predetermined value from the amplitude value, multiplying the amplitude value by a predetermined value, or dividing the amplitude value by a predetermined value.

[0074] Optionally, the feature obtainer 320 may extract various additional information from the biosignal and obtain features by appropriately combining the extracted additional information with the forward wave component. For example, by using a second-order differential signal, the feature obtainer 320 may obtain the amplitude value corresponding to the time of the second local minimum point and the time of the third local minimum point of the biosignal, the maximum amplitude value of the contraction portion of the biosignal, the total area or partial area of ​​the biosignal, and the like as additional information.

[0075] Once the feature obtainer 320 extracts the features, the biometric information estimator 330 may estimate the biometric information using the extracted features. The biometric information estimator 330 may estimate the biometric information from the extracted features by applying a predetermined biometric information estimation model. In this case, the biometric information estimation model may be expressed in the form of a linear function or a nonlinear function that defines the correlation between the features and the biometric information (e.g., blood pressure).

[0076] Figure 5 is a flowchart illustrating a method of estimating biological information according to an embodiment of the present disclosure.

[0077] Figure 5 The method is an example of a method of estimating bio-information performed by the apparatuses 100 and 200 for estimating bio-information.

[0078] Upon receiving the request for estimating bio-information, the apparatuses 100 and 200 for estimating bio-information may measure a bio-signal from an object of a user in 510 .

[0079] Apparatuses 100 and 200 for estimating biometric information may provide interfaces for various user interactions and may receive requests for estimating biometric information from users via these interfaces. Alternatively, apparatuses 100 and 200 for estimating biometric information may receive requests for estimating biometric information from external devices. In this case, the request for estimating biometric information from the external device may include a request for biometric information estimation results. If the external device includes a biometric information estimation algorithm, the request for estimating biometric information may also include a request for feature information. The external device may be a smartphone, tablet PC, or the like that can be carried by the user.

[0080] Then, the apparatuses 100 and 200 for estimating bio-information may obtain a second-order differential signal of the bio-signal in 520 , and may determine whether the second-order differential signal (specifically, a first local minimum point of the second-order differential signal) is stable in 530 .

[0081] For example, the apparatuses 100 and 200 for estimating bio-information may detect an inflection point during the detection period of the second-order differential signal. If no inflection point exists, the apparatuses 100 and 200 for estimating bio-information may determine that the first local minimum is stable. Conversely, if an inflection point exists, the apparatuses 100 and 200 for estimating bio-information may determine that the first local minimum is unstable. In this case, the inflection point may be a point at which the waveform of the second-order differential signal changes from being convex downward to being convex upward during the detection period of the second-order differential signal.

[0082] Then, when it is determined that the first local minimum point is stable in 530 , the apparatuses 100 and 200 for estimating bio-information may extract a forward wave component based on the first local minimum point of the second-order differential signal in 540 .

[0083] For example, the bio-information estimation apparatuses 100 and 200 may obtain the amplitude P1 of the bio-signal corresponding to the time T1 of the first local minimum point as the forward wave component. Alternatively, the bio-information estimation apparatuses 100 and 200 may obtain the amplitude corresponding to the inner dividing point between the time of the first local minimum point and the time of the second local maximum point of the second-order differential signal as the forward wave component. In this case, a weight may be applied to each of the time of the first local minimum point and the time of the second local maximum point.

[0084] In contrast, when it is determined in 530 that the first local minimum point is unstable, the apparatuses 100 and 200 for estimating bio-information may detect a maximum amplitude point in a contraction portion of the bio-signal and may extract a forward wave component based on the detected maximum amplitude point in 550 .

[0085] For example, the apparatuses 100 and 200 for estimating biological information may obtain the amplitude value at the maximum amplitude point as the forward wave component. Alternatively, the apparatuses 100 and 200 for estimating biological information may obtain the amplitude at the inner dividing point between the time of the inflection point detected in 530 and the time of the maximum amplitude point as the forward wave component. In this case, a predefined weight may be applied to each of the time of the inflection point and the time of the maximum amplitude point, but is not limited thereto.

[0086] Next, the apparatuses 100 and 200 for estimating biological information may estimate biological information based on the obtained progressive wave component in 560. For example, the apparatuses 100 and 200 for estimating biological information may obtain the obtained progressive wave component (i.e., the amplitude value itself, a value obtained by processing the amplitude value, a value obtained by extracting additional information from the second-order differential signal and appropriately combining the extracted additional information with the progressive wave component, etc.) as a feature. Furthermore, the apparatuses 100 and 200 for estimating biological information may estimate biological information by applying a biological information estimation model based on the obtained features.

[0087] After estimating biometric information, the devices 100 and 200 for estimating biometric information can provide the user with the estimated result. In this case, the devices 100 and 200 for estimating biometric information can provide the user with the estimated biometric information using various visual and non-visual methods. Furthermore, the devices 100 and 200 for estimating biometric information can determine the user's health status based on the estimated biometric information and provide the user with a warning or response action based on this determination.

[0088] Figure 6 1 is a diagram illustrating a wearable device according to an embodiment of the present disclosure. The aforementioned embodiments of the apparatuses 100 and 200 for estimating bio-information may be installed in a Figure 6 In the smart watch or smart band type wearable device worn on the wrist as shown in, but not limited to.

[0089] Reference Figure 6 , the wearable device 600 includes a main body 610 and a band 630 .

[0090] The body 610 may be formed in various shapes and may include modules mounted inside or outside the body 610 to perform the aforementioned function of estimating biometric information and various other functions. A battery may be embedded in the body 610 or in the band 630 to power the various modules of the wearable device 600.

[0091] The strap 630 may be connected to the main body 610. The strap 630 may be flexible so as to bend around the user's wrist. The strap 630 may be bendable to allow it to be removed from the user's wrist, or may be formed as a non-detachable strap. Air may be injected into the strap 630, or an air bag may be included in the strap 630, so that the strap 630 has elasticity that changes according to the pressure applied to the wrist, and the strap 630 may transmit the change in wrist pressure to the main body 610.

[0092] The body 610 may include a sensor 620 for measuring biosignals. The sensor 620 may be mounted on the rear surface of the body 610 that contacts the upper portion of the user's wrist and may include a light source for emitting light onto the skin of the wrist and a detector for detecting light scattered or reflected from an object. The sensor 620 may also include a contact pressure sensor for measuring contact pressure applied by an object.

[0093] The processor may be installed in the body 610. The processor may be electrically connected to each module installed in the wearable device 600 to control the operation of each module. In addition, the processor may estimate biological information by using the biological signal measured by the sensor 620.

[0094] For example, the wearable device 600 worn on the wrist measures a biosignal from the capillary portion on the upper part of the wrist, thereby acquiring a biosignal mainly having a low-frequency component. Therefore, in order to stably obtain features even in various situations where unstable biosignals may be generated, the processor can adaptively detect the forward wave component. For example, as described above, based on the presence of an inflection point in the detection period of the second-order differential signal, the processor can determine whether the waveform of the biosignal is stable (i.e., whether the first local minimum point of the second-order differential signal, which is generally related to the forward wave component, is stable). In addition, based on the determination of stability, the processor can obtain the forward wave component by using the first local minimum point of the second-order differential signal, the maximum amplitude point of the biosignal, and the like.

[0095] In the case where the processor includes a contact pressure sensor, the processor may monitor the contact state of the object based on the contact pressure between the wrist and the sensor 620, and may provide guidance information about the contact position and / or contact state to the user through the display.

[0096] In addition, the main body 610 may include a storage device that stores the processing results of the processor and various information. In this case, the various information may include reference information related to the estimated biometric information and information associated with the function of the wearable device 600.

[0097] In addition, the main body 610 may further include a controller 640 that receives a user's control command and sends the received control command to the processor. The controller 640 may include a power button for inputting a command for turning on / off the wearable device 600.

[0098] The display may be mounted on the front surface of the main body 610 and may include a touch panel for receiving touch input. The display may receive touch input from the user, transmit the received touch input to the processor, and display the results of the processor's processing. For example, the display may display estimated biometric information values ​​and warning / alarm information.

[0099] In addition, a communication interface configured to communicate with an external device (such as a user's mobile terminal) may be installed in the main body 610. The communication interface can transmit the biometric information estimation result to the external device (e.g., the user's smartphone) to display the result to the user. However, the communication interface is not limited to this and can transmit and receive various necessary information.

[0100] Figure 7 1 is a diagram illustrating a smart device according to an embodiment of the present disclosure. In this case, the smart device may be a smartphone, a tablet PC, etc., and may include the aforementioned apparatuses 100 and 200 for estimating biometric information.

[0101] Reference Figure 7, the smart device 700 includes a main body 710 and a sensor 730 mounted on one surface of the main body 710. In this case, the sensor 730 may include a pulse wave sensor including at least one light source 731 and a detector 732. Figure 7 As shown in , the sensor 730 may be mounted on the rear surface of the body 710 , but is not limited thereto and may be configured to be combined with a fingerprint sensor or a touch panel mounted on the front surface of the body 710 .

[0102] In addition, a display may be installed on the front surface of the body 710. The display may visually display the bio-information estimation result, etc. The display may include a touch panel, and may receive various information input through the touch panel and transmit the received information to the processor.

[0103] Furthermore, an image sensor 720 may be mounted in the body 710. When a user's finger approaches the sensor 730 to measure a pulse wave signal, the image sensor 720 may capture an image of the finger and transmit the captured image to the processor. In this case, the processor may identify the relative position of the finger relative to the actual position of the sensor 730 based on the image of the finger and may provide the user with the relative position of the finger through a display, thereby guiding the measurement of the pulse wave signal with improved accuracy.

[0104] As described above, the processor can estimate bio-information based on the bio-signal measured by sensor 730. In this case, as described above, the processor can perform second-order differentiation on the bio-signal, detect an inflection point within a predetermined period of the second-order differential signal, and adaptively obtain the forward wave component required for estimating the bio-information based on this detection. In this case, when measuring the bio-signal from the user's finger using sensor 730 mounted on the rear surface of smart device 700, the processor can be configured to first detect a local minimum point and then detect an inflection point, but is not limited thereto.

[0105] The present invention 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.

[0106] 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 across multiple networked computer systems so that computer-readable code can be written to and executed from the computer-readable recording media in a decentralized manner. The functional programs, codes, and code segments required to implement the present invention can be easily derived by a person skilled in the art to which the present invention pertains.

[0107] The present invention 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 essential features of the present disclosure. Therefore, it will be apparent that the above embodiments are illustrative in all respects and are not intended to limit the present disclosure.

Claims

1. A device for estimating biological information, the device comprising: a sensor configured to obtain a biosignal from a subject; and The processor is configured to: Obtaining the second-order differential signal of the biological signal; determining whether the first local minimum point of the second-order differential signal is stable; and Based on determining that the first local minimum point of the second-order differential signal is stable, the first local minimum point of the second-order differential signal is used to extract the forward wave component from the biological signal, or based on determining that the first local minimum point of the second-order differential signal is unstable, the maximum amplitude point in the contraction part of the biological signal is used to extract the forward wave component from the biological signal.

2. The device according to claim 1, wherein The sensor includes a pulse wave sensor having a light source configured to emit light onto an object and a detector configured to detect light reflected or scattered from the object.

3. The device according to claim 1, wherein The processor is further configured to: determine whether an inflection point exists in a detection period of the second-order differential signal; and determine whether the first local minimum point is stable based on whether the inflection point exists in the detection period of the second-order differential signal.

4. The device according to claim 3, wherein The detection period includes a time interval between a first local maximum point and a first local minimum point of the second-order differential signal.

5. The apparatus according to claim 3, wherein The processor detects, as an inflection point, a point at which the waveform of the second order differential signal changes from being downwardly convex to being upwardly convex in a detection period of the second order differential signal.

6. The device according to claim 5, wherein The processor obtains a fourth-order differential signal of the biological signal, detects a first point that satisfies the conditions that the amplitude at the first point is greater than 0 and the amplitude at the second point is less than 0 in the detection period of the fourth-order differential signal, and detects a point corresponding to the first point from the second-order differential signal as an inflection point.

7. The apparatus according to any one of claims 1 to 6, wherein: When determining that the first local minimum point is stable, the processor extracts at least one of the following items as a forward wave component: the amplitude of the biological signal corresponding to the time of the first local minimum point, and the amplitude of the biological signal corresponding to the internal division point between the time of the first local minimum point and the time of the second local maximum point of the second-order differential signal.

8. The apparatus according to any one of claims 1 to 6, wherein: When determining that the first local minimum point is unstable, the processor extracts at least one of the following items as the forward wave component: the amplitude of the maximum amplitude point, and the amplitude of the biological signal corresponding to the internal division point between the time of the inflection point detected in the detection period of the second-order differential signal and the time of the maximum amplitude point.

9. The apparatus according to any one of claims 1 to 6, wherein: The processor estimates biological information based on the extracted forward wave component.

10. The apparatus according to claim 9, wherein The biological information includes one or more of blood pressure, vascular age, arterial stiffness, aortic pressure waveform, stress index, and fatigue level.

11. A computer-readable storage medium storing a program, which, when executed by a processor, causes the processor to perform a method for estimating biological information, the method comprising: obtaining a biological signal from a subject; Obtaining the second-order differential signal of the biological signal; Determine whether the first local minimum point of the second-order differential signal is stable; and Based on determining that the first local minimum point of the second-order differential signal is stable, the first local minimum point of the second-order differential signal is used to extract the forward wave component, or based on determining that the first local minimum point of the second-order differential signal is unstable, the maximum amplitude point in the contraction part of the biological signal is used to extract the forward wave component from the biological signal.

12. The computer-readable storage medium of claim 11, wherein: The steps of determining whether the first local minimum point of the second-order differential signal is stable include: determining whether an inflection point exists in a detection period of the second-order differential signal; and Whether the first local minimum point is stable is determined based on whether an inflection point exists in a detection period of the second-order differential signal.

13. The computer-readable storage medium of claim 12, wherein: The detection period includes a time interval between a first local maximum point and a first local minimum point of the second-order differential signal.

14. The computer-readable storage medium of claim 12, wherein: The step of detecting the inflection point includes detecting, as the inflection point, a point at which the waveform of the second-order differential signal changes from being downwardly convex to being upwardly convex in a detection period of the second-order differential signal.

15. The computer-readable storage medium of claim 14, wherein: The steps to detect the inflection point include: Obtaining the fourth-order differential signal of the biological signal; detecting a first point satisfying a condition that the amplitude at the first point is greater than 0 and the amplitude at the second point is less than 0 in a detection period of the fourth-order differential signal; and A point corresponding to the first point is detected from the second-order differential signal as an inflection point.

16. The computer-readable storage medium according to any one of claims 11 to 15, wherein: The steps to extract the forward wave component include: In response to determining that the first local minimum point is stable, at least one of the following items is extracted as a forward wave component: the amplitude of the biological signal corresponding to the time of the first local minimum point, and the amplitude of the biological signal corresponding to the internal division point between the time of the first local minimum point and the time of the second local maximum point of the second-order differential signal.

17. The computer-readable storage medium according to any one of claims 11 to 15, wherein: The steps to extract the forward wave component include: In response to determining that the first local minimum point is unstable, at least one of the following items is extracted as a forward wave component: the amplitude of the maximum amplitude point, and the amplitude of the biological signal corresponding to an internal division point between the time of the inflection point detected in the detection period of the second-order differential signal and the time of the maximum amplitude point.

18. The computer-readable storage medium according to any one of claims 11 to 15, the method further comprising: Biometric information is estimated based on the extracted forward wave component.

19. A computer-readable storage medium storing a program, which, when executed by a processor, causes the processor to execute a method for estimating biometric information of a user, the method comprising: Obtaining the user's biological signals; Obtaining the second-order differential signal of the biological signal; determining whether there is an inflection point where the waveform of the second-order differential signal changes from being downwardly convex to being upwardly convex in an interval between a first local maximum point and a first local minimum point of the second-order differential signal; extracting a forward wave component from the biosignal using a first local minimum point of a second-order differential signal based on a determination that an inflection point does not exist in the interval, or extracting a forward wave component using a maximum amplitude point in a contraction portion of the biosignal based on a determination that an inflection point exists in the interval; as well as The biological information is estimated based on the forward wave component.

Images