Apparatus and method for estimating biological information

Abstract

Provided are an apparatus and method for estimating bio-information. According to an embodiment of the present disclosure, the apparatus for estimating bio-information includes: a first sensor configured to measure a first pulse wave signal of a first wavelength and a second pulse wave signal of a second wavelength from a subject; a second sensor configured to measure at least one of a force or pressure applied to the subject; and a processor configured to: generate an oscillometric waveform envelope based on the first pulse wave signal of the first wavelength and at least one of the force or pressure applied to the subject; obtain a characteristic value from the oscillometric waveform envelope; predict a measured size of a blood vessel based on the second pulse wave signal of the second wavelength; correct the characteristic value based on the measured size of the blood vessel; and estimate the bio-information based on the corrected characteristic value.

Description

[0001] This application is based upon and claims the benefit of Korean Patent Application No. 10-2021-0035741, filed on March 19, 2021, in the Korean Intellectual Property Office, the disclosure of which is incorporated herein in its entirety by reference. Technical Field

[0002] The disclosure relates to an apparatus and method for estimating biological information, and more particularly, to a technique for estimating blood pressure based on oscillometry without using a cuff. Background Art

[0003] General techniques for extracting cardiovascular characteristics such as blood pressure, etc., without using a pressure cuff include a pulse wave analysis (PWA) method and a pulse wave velocity (PWV) method.

[0004] The pulse wave analysis (PWA) method extracts cardiovascular characteristics by analyzing the shape of photoplethysmography (PPG) signals or body surface pressure signals obtained from peripheral body sites (such as the fingertips and radial arteries). Blood ejected from the left ventricle causes reflections in large branching regions (such as the renal and iliac arteries), and these reflections influence the shape of the pulse wave or body pressure wave measured at the peripheral site. Therefore, by analyzing this shape, it is possible to infer arterial stiffness, arterial age, aortic pressure waveform, and other parameters.

[0005] The pulse wave velocity (PWV) method is a method for extracting cardiovascular characteristics (such as arterial stiffness and blood pressure) by measuring the pulse wave transit time. In this method, the ECG signal and PPG signal are measured at a peripheral part of the body. The speed at which blood from the heart reaches the peripheral part of the body is calculated by dividing the approximate length of the arm by the pulse transit time (PTT). The delay (PPT) between the R peak (left ventricular contraction interval) of the electrocardiogram (ECG) and the peak of the PPG signal of the finger or radial artery is measured. Summary of the Invention

[0006] According to one aspect of an example embodiment, an apparatus for estimating bio-information may include: a first sensor configured to measure a first pulse wave signal of a first wavelength and a second pulse wave signal of a second wavelength from a subject; a second sensor configured to measure at least one of a force or a pressure applied to the subject; and a processor configured to: generate an oscillometric waveform envelope based on the first pulse wave signal of the first wavelength and the at least one of the force or the pressure applied to the subject; obtain a characteristic value from the oscillometric waveform envelope; predict a measured size of a blood vessel based on the second pulse wave signal of the second wavelength; correct the characteristic value based on the measured size of the blood vessel; and estimate the bio-information based on the corrected characteristic value.

[0007] The first wavelength may be an infrared wavelength, and the second wavelength may be a green wavelength.

[0008] The processor may generate an oscillometric waveform envelope based on a difference between a peak and a valley of an alternating current (AC) component of the first pulse wave signal of the first wavelength and the at least one of force or pressure.

[0009] The processor may detect characteristic points from the oscillometric waveform envelope and obtain characteristic values ​​based on the characteristic points.

[0010] The characteristic point may include at least one of a peak point of the oscillometric waveform envelope, a front point before the peak point and corresponding to a predetermined ratio of the amplitude value of the peak point, and a rear point after the peak point and corresponding to a predetermined ratio of the amplitude value of the peak point.

[0011] The characteristic value may include at least one of a force value, a pressure value, and an amplitude value of the characteristic point.

[0012] The processor may extract a direct current (DC) component of the second pulse wave signal of the second wavelength, and predict the size of the measured blood vessel based on a DC component value corresponding to a force value or a pressure value of the characteristic point.

[0013] The processor may normalize a DC component of the second pulse wave signal of the second wavelength, and in response to a normalized DC component value corresponding to a force value or a pressure value of the characteristic point being less than a reference value, predict that the size of the measured blood vessel is smaller than the size of the target blood vessel; and in response to the normalized DC component value exceeding the reference value, predict that the size of the measured blood vessel is larger than the size of the target blood vessel.

[0014] The processor may increase the characteristic value based on predicting that the measured size of the blood vessel is smaller than the size of the target blood vessel; and decrease the characteristic value based on predicting that the measured size of the blood vessel is larger than the size of the target blood vessel.

[0015] The processor may determine a degree of increase or decrease of the characteristic value based on a difference between the normalized DC component value and a reference value.

[0016] The processor may estimate the bio-information based on the feature value by using the bio-information estimation model.

[0017] The biological information may include one or more of: blood pressure, vascular age, arterial stiffness, aortic pressure waveform, vascular compliance, pressure index, and fatigue level.

[0018] According to one aspect of an example embodiment, a method of estimating bio-information may include: measuring a first pulse wave signal of a first wavelength and a second pulse wave signal of a second wavelength from a subject; measuring at least one of a force or a pressure applied to the subject; generating an oscillometric waveform envelope based on the first pulse wave signal of the first wavelength and the at least one of the force or the pressure applied to the subject; obtaining a characteristic value from the oscillometric waveform envelope; predicting a measured size of a blood vessel based on the second pulse wave signal of the second wavelength; correcting the characteristic value based on the measured size of the blood vessel; and estimating the bio-information based on the corrected characteristic value.

[0019] The first wavelength may be an infrared wavelength, and the second wavelength may be a green wavelength.

[0020] Generating the oscillometric waveform envelope may include generating the oscillometric waveform envelope based on a difference between a peak and a valley of an alternating current (AC) component of the first pulse wave signal of the first wavelength and at least one of a force or pressure applied to the subject.

[0021] The method may include: detecting characteristic points from an oscillometric waveform envelope; and obtaining characteristic values ​​based on the characteristic points.

[0022] The characteristic point may include at least one of a peak point of the oscillometric waveform envelope, a front point before the peak point and corresponding to a predetermined ratio of the amplitude value of the peak point, and a rear point after the peak point and corresponding to a predetermined ratio of the amplitude value of the peak point.

[0023] The characteristic value may include at least one of a force value, a pressure value, and an amplitude value of the characteristic point.

[0024] The method may include extracting a direct current (DC) component of a second pulse wave signal of a second wavelength; and predicting a size of a blood vessel based on a DC component value corresponding to a force value or a pressure value of a characteristic point.

[0025] The method may include: normalizing a DC component of a second pulse wave signal of a second wavelength; predicting that the size of the measured blood vessel is smaller than the size of a target blood vessel in response to a normalized DC component value corresponding to a force value or a pressure value of a characteristic point being smaller than a reference value; and predicting that the size of the measured blood vessel is larger than the size of the target blood vessel in response to the normalized DC component value exceeding the reference value.

[0026] The method may include increasing the characteristic value based on predicting that the measured size of the blood vessel is smaller than the size of the target blood vessel; and decreasing the characteristic value based on predicting that the measured size of the blood vessel is larger than the size of the target blood vessel.

[0027] The method may include determining a degree of increase or decrease of the characteristic value based on a difference between the normalized DC component value and a reference value.

[0028] The estimating of the biological information may include estimating the biological information based on the feature value by using a biological information estimation model.

[0029] According to one aspect of an example embodiment, an electronic device may include an apparatus for estimating bio-information and an output device configured to output a processing result of the apparatus for estimating bio-information. The apparatus for estimating bio-information may include: a first sensor configured to measure a first pulse wave signal having a first wavelength and a second pulse wave signal having a second wavelength from a subject; a second sensor configured to measure at least one of a force or pressure applied to the subject; and a processor configured to: generate an oscillometric waveform envelope based on the first pulse wave signal having the first wavelength and the at least one of the force or pressure applied to the subject; obtain a characteristic value from the oscillometric waveform envelope; predict a measured size of a blood vessel based on the second pulse wave signal having the second wavelength; correct the characteristic value based on the measured size of the blood vessel; and estimate the bio-information based on the corrected characteristic value.

[0030] The electronic device may include at least one of a wristwatch wearable device, an ear-worn device, and a mobile device.

[0031] The first wavelength may be an infrared wavelength, and the second wavelength may be a green wavelength.

[0032] The processor may detect characteristic points from the oscillometric waveform envelope and obtain characteristic values ​​based on the characteristic points.

[0033] The processor may extract a direct current (DC) component of the second pulse wave signal of the second wavelength, and predict the size of the measured blood vessel based on a DC component value corresponding to a force value or a pressure value of the characteristic point.

[0034] The processor may normalize a DC component of the second pulse wave signal of the second wavelength; in response to a normalized DC component value corresponding to a force value or a pressure value of the characteristic point being less than a reference value, predict that the size of the measured blood vessel is smaller than the size of the target blood vessel; and in response to the normalized DC component value exceeding the reference value, predict that the size of the measured blood vessel is larger than the size of the target blood vessel.

[0035] The processor may increase the characteristic value based on predicting that the measured size of the blood vessel is smaller than the size of the target blood vessel; and decrease the characteristic value based on predicting that the measured size of the blood vessel is larger than the size of the target blood vessel. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and other aspects, features and advantages of certain embodiments of the present disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0037] Figure 1 is a block diagram illustrating an apparatus for estimating bio-information according to an embodiment of the present disclosure;

[0038] Figure 2 is a diagram explaining the relationship between the DC component of the pulse wave signal having a green wavelength and tissue changes;

[0039] Figures 3A to 3D is a diagram explaining changes in characteristic values ​​associated with blood pressure according to the size of blood vessels of a subject having the same reference blood pressure and in a DC component of a pulse wave signal having a green wavelength;

[0040] Figure 4A is a diagram showing changes in blood vessel size according to various measurement positions;

[0041] Figure 4B is a diagram explaining an example of correcting a feature value according to a predicted blood vessel size;

[0042] Figures 5A to 5C is a diagram explaining an example of obtaining an oscillometric waveform envelope by using a pulse wave signal of an infrared wavelength;

[0043] Figure 6 is a block diagram illustrating an apparatus for estimating bio-information according to another embodiment of the present disclosure;

[0044] Figure 7 is a flowchart illustrating a method of estimating biological information according to an embodiment of the present disclosure;

[0045] Figure 8 is a block diagram illustrating an example of an electronic device including an apparatus for estimating biological information;

[0046] Figure 9 is shown as Figure 8 FIG. 1 is a diagram of a wristwatch wearable device as an example of an electronic device;

[0047] Figure 10 is shown as Figure 8 ; and

[0048] Figure 11 is shown as Figure 8 Schematic diagram of an ear-worn device that illustrates an example of an electronic device. DETAILED DESCRIPTION

[0049] Details of example embodiments are included in the following detailed description and accompanying drawings. The advantages and features of the present disclosure and methods of implementing the present disclosure will be more clearly understood from the following example embodiments described in detail with reference to the accompanying drawings. Throughout the drawings and detailed description, unless otherwise indicated, the same reference numerals will be understood to represent the same elements, features, and structures.

[0050] It will be understood that although the terms "first", "second" and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. In addition, unless the context clearly indicates otherwise, the singular form of a term is also intended to include the plural form of the term. It will also be understood that, unless explicitly described to the contrary, when an element is referred to as "comprising" another element, the element cannot exclude one or more other elements, but may further include one or more other elements. In the following description, terms such as "unit" and "module" indicate a unit for processing at least one function or operation, and they can be implemented using hardware, software or a combination thereof.

[0051] Hereinafter, example embodiments of an apparatus and method for estimating bio-information will be described in detail with reference to the accompanying drawings.

[0052] Various exemplary embodiments of the apparatus for estimating biometric information, which will be described below, may be installed in a terminal (such as a smartphone, a tablet personal computer (PC), a desktop computer, a laptop computer, etc.) or a wearable device, etc. In this case, examples of the wearable device may include a wristwatch-type wearable device, a bracelet-type wearable device, a wristband-type wearable device, a ring-type wearable device, a glasses-type wearable device, a headband-type wearable device, etc., but the wearable device is not limited thereto.

[0053] Figure 1 is a block diagram illustrating an apparatus for estimating bio-information according to an embodiment of the present disclosure.

[0054] Reference Figure 1 , an apparatus 100 for estimating bio-information includes a first sensor 110 , a second sensor 120 , and a processor 130 .

[0055] The first sensor 110 measures a PPG signal (hereinafter referred to as a "pulse wave signal") from a subject. For example, the first sensor 110 may measure a pulse wave signal having a first wavelength (e.g., an infrared wavelength) and a second wavelength (e.g., a green wavelength) that are different from each other. In this case, the subject may be an area of ​​the human body that can contact the first sensor 110, and may be a body part where the pulse wave can be easily measured using PPG. For example, the subject may be a finger where blood vessels are densely distributed, but the subject is not limited thereto and may be an area on the wrist adjacent to the radial artery, or a peripheral part of the body where veins or capillaries are located (such as the upper part of the wrist, toes, etc.).

[0056] The first sensor 110 may include, for example, an infrared light source configured to emit light of an infrared wavelength onto an object, and a green light source configured to emit light of a green wavelength onto an object. Furthermore, the first sensor 110 may include a light receiver disposed at a predetermined distance from the light source and configured to acquire a pulse wave signal of a green wavelength and a pulse wave signal of an infrared wavelength by detecting light scattered or reflected from the object. The light source may include, but is not limited to, a light emitting diode (LED), a laser diode (LD), a phosphor, or the like. Furthermore, the light receiver may include a photodiode, a photodiode array, a complementary metal oxide semiconductor (CMOS) image sensor, a charge coupled device (CCD) image sensor, or the like.

[0057] As the subject contacts first sensor 110 and increases or decreases the pressing force to cause a change in pulse wave amplitude, second sensor 120 can measure the force / pressure applied to the subject. Here, "force / pressure" refers to at least one of force and pressure. Second sensor 120 can include a single force sensor including a strain gauge, or can include a force sensor array, a pressure sensor, a balloon-type pressure sensor, a pressure sensor combined with a force sensor and an area sensor, or the like.

[0058] The processor 130 may be electrically connected to the first sensor 110 and the second sensor 120. The processor 130 may control the first sensor 110 and the second sensor 120 to estimate blood pressure, and may receive a pulse wave signal and force / pressure data from the first sensor 110 and the second sensor 120.

[0059] Processor 130 may pre-process the received pulse wave signal. For example, processor 130 may reduce noise (such as motion noise) by using a noise reduction method (such as filtering, smoothing, etc.). For example, processor 130 may perform bandpass filtering on the pulse wave signal using a cutoff frequency of 1 Hz to 10 Hz.

[0060] Processor 130 can estimate biometric information using the received pulse wave signal of the first wavelength, force / pressure, and pulse wave signal of the second wavelength. In this case, the biometric information may include, but is not limited to, blood pressure, vascular age, arterial stiffness, aortic pressure waveform, vascular compliance, pressure index, fatigue level, skin age, and skin elasticity. For ease of explanation, the following description uses blood pressure as an example.

[0061] Processor 130 may generate an oscillometric waveform envelope based on a pulse wave signal of a first wavelength (e.g., an infrared wavelength) and force / pressure, and may estimate blood pressure using the generated oscillometric waveform envelope. Processor 130 may obtain characteristic values ​​associated with blood pressure from the oscillometric waveform envelope of the infrared wavelength, and may obtain an estimated blood pressure value by inputting the obtained characteristic values ​​into a predefined blood pressure estimation model. The blood pressure estimation model may be a model for converting characteristic values ​​measured from the size of a target blood vessel of an object (such as a finger) into blood pressure in the upper arm artery. In this case, based on the object contacting first sensor 110, the actual measured blood vessel size may differ from the size of the target blood vessel depending on the contact position. Therefore, processor 130 may predict the actual measured blood vessel size using a pulse wave signal of a second wavelength (e.g., a green wavelength), and may correct the characteristic values ​​extracted from the oscillometric waveform envelope of the first wavelength so that the characteristic values ​​correspond to the size of the target blood vessel.

[0062] In the following, reference will be made to Figures 2 to 5C Describe an example of estimating blood pressure.

[0063] Figure 2 is a diagram explaining the relationship between a direct current (DC) component of a pulse wave signal having a green wavelength and tissue changes.

[0064] exist Figure 2 In the graph, the X-axis indicates the force / pressure applied to the subject, and the Y-axis indicates the normalized DC component 21 of the pulse wave signal with a green wavelength. The DC component 21 of the pulse wave signal with a green wavelength increases as the force / pressure applied to the subject increases, demonstrating a specific correlation between DC component 21 and changes in the subject's tissue / blood vessels. Specifically, it can be seen that tissue changes are small at point P1, where DC component 21 is relatively low, and large at point P2, where DC component 21 is relatively high. Therefore, tissue changes can be estimated using DC component 21 of the pulse wave signal with a green wavelength, and blood vessel size can be indirectly predicted based on the estimated tissue changes. For example, if tissue changes are small, they can be predicted from relatively small blood vessels (where pressure is relatively low), while if tissue changes are large, they can be predicted from relatively large blood vessels (where pressure is relatively high). As described above, the size of a blood vessel measured at a measurement position of a subject can be predicted by using a DC component of a pulse wave signal having a green wavelength, and blood pressure can be estimated by using the predicted blood vessel size information, thereby improving accuracy.

[0065] Figures 3A to 3D Graphs explaining changes in characteristic values ​​associated with blood pressure according to the size of blood vessels of a subject having the same reference blood pressure and in the DC component of a pulse wave signal having a green wavelength.

[0066] Figure 3A and Figure 3C The figure shows an oscillometric waveform envelope IR generated using infrared pulse wave signals and force / pressure measurements from large and small blood vessels of a subject with the same reference blood pressure (e.g., cuff blood pressure). It can be seen that when characteristic points 31 and 33 associated with blood pressure are extracted from the oscillometric waveform envelope IR based on the same criteria for different blood vessel sizes, the force / pressure values ​​a and a' at each characteristic point 31 and 33 can differ. In this case, when the force / pressure values ​​a and a' at each characteristic point 31 and 33, which serve as feature values ​​for estimating blood pressure, are applied to a blood pressure estimation model, the estimated blood pressure values ​​differ despite the same reference blood pressure, potentially leading to errors depending on the size of the measured blood vessel.

[0067] Figure 3B and Figure 3D The normalized DC component G of the pulse wave signal having a green wavelength measured from relatively large blood vessels and relatively small blood vessels of a subject having the same reference blood pressure is shown. Figure 3B and Figure 3D In the figure, points 32 and 34 correspond to Figure 3A and Figure 3C The characteristic points 31 and 33 are extracted from the oscilloscope waveform envelope IR. It can be seen that the changes in the DC components b and b' between each point 32 and point 34 correspond to the changes in the force / pressure values ​​a and a' between each characteristic point 31 and characteristic point 33. Figure 2 As shown in , the intensity of the DC component has a specific correlation with the change in tissue / blood vessel size according to the change in force / pressure, so that by using the DC component of the target vessel and the DC component of the measured vessel, the relative size of the measured vessel can be predicted, and the characteristic value can be corrected based on the predicted vessel size.

[0068] Figure 4A is a diagram showing changes in blood vessel size according to various measurement positions. Figure 4B : is a diagram explaining an example of correcting a feature value according to a predicted blood vessel size. Figure 4A and Figure 4B When a relatively large-sized blood vessel A is set as a target blood vessel for estimating blood pressure from a finger, a blood pressure estimation model may be defined to convert feature values ​​extracted from the oscillometric waveform envelope of the target blood vessel A into blood pressure in the upper arm artery T. As shown herein, when pulse wave signals are measured from blood vessels B, C, and D having relatively smaller sizes than the target blood vessel A of the finger, the feature values ​​extracted from the oscillometric waveform envelopes of the relatively smaller-sized blood vessels may be corrected and then applied to the blood pressure estimation model.

[0069] Based on the infrared wavelength pulse wave signal and force / pressure being measured from the subject, the processor 130 may generate an oscillometric waveform envelope based on the difference between peaks and valleys of an alternating current (AC) component of the measured infrared wavelength pulse wave signal and force / pressure.

[0070] Figures 5A to 5C is a diagram explaining an example of obtaining an oscillometric waveform envelope by using a pulse wave signal of an infrared wavelength, wherein Figure 5A shows the AC component of the pulse wave signal with infrared wavelength, Figure 5B Shows force / pressure, Figure 5C Shows the oscilloscope waveform envelope.

[0071] Reference Figures 5A to 5C The processor 130 may extract a peak-to-peak point by subtracting an amplitude value of a negative (-) point (such as a valley amplitude value in3) from an amplitude value of a positive (+) point (such as a peak amplitude value in2) of the pulse wave envelope in1 at each measurement time point of the pulse wave signal, and may obtain an oscillometric waveform envelope (OW) by plotting the peak-to-peak amplitude at a corresponding time point against a force / pressure value at each measurement time point and by performing, for example, polynomial curve fitting.

[0072] The processor 130 may detect characteristic points from the obtained oscillometric waveform envelope OW, and may obtain at least one of a force / pressure value, an amplitude value, and the like of the detected characteristic points as characteristic values. For example, the processor 130 may detect a peak point, a first point located in an interval before the peak point and corresponding to an amplitude value having a first ratio (e.g., 0.5 to 0.7) relative to the amplitude value MA of the peak point, and / or a second point located in an interval after the peak point and corresponding to an amplitude value having a second ratio (e.g., 0.5 to 0.7) relative to the amplitude value MA of the peak point from the oscillometric waveform envelope OW, and the processor 130 may obtain the force / pressure values ​​MP, DP, and SP at the detected peak point, the first point, and / or the second point as characteristic values ​​of mean arterial pressure (MAP), diastolic pressure (DBP), and systolic pressure (SBP), respectively.

[0073] Based on a green-wavelength pulse wave signal obtained from the subject, processor 130 may extract a DC component from the green-wavelength pulse wave signal using, for example, a bandpass filter, a low-pass filter, or the like. Furthermore, processor 130 may normalize the DC component value at each time point. For example, by dividing the DC component value at each time point by a maximum value, processor 130 may normalize the DC component value so that the DC component value at each time point is within a range of 0 to 1. However, this example is not limited thereto, and other normalization methods may also be used to normalize the DC component value.

[0074] Processor 130 may predict the size of the measured blood vessel based on the normalized DC component value. For example, processor 130 may compare the DC component value corresponding to the force / pressure value of a characteristic point extracted from the oscillometric waveform envelope with a reference value. If the DC component value is less than the reference value, processor 130 may predict that the measured blood vessel size is relatively smaller than the target vessel size; if the DC component value is equal to the reference value, processor 130 may predict that the measured blood vessel size is equal to the target vessel size; and if the DC component value exceeds the reference value, processor 130 may predict that the measured blood vessel size is relatively larger than the target vessel size. In this case, a reference value may be defined for each user and may be, for example, the DC component value of a pulse wave signal having a green wavelength, which corresponds to the force / pressure value of a characteristic point extracted from the oscillometric waveform envelope having an infrared wavelength measured from the target vessel of the subject at the calibration time. The reference value may be determined individually for each of the characteristic values ​​MAP, DBP, and SBP, and the processor 130 may correct each of the characteristic values ​​MAP, DBP, and SBP by individually comparing the DC component value corresponding to the force / pressure values ​​MP, DP, and SP of each characteristic point with the reference value.

[0075] If the measured blood vessel size is predicted to be relatively smaller than the target blood vessel size, processor 130 may increase the feature value extracted from the oscillometric waveform envelope of the infrared wavelength used to estimate blood pressure. Conversely, if the measured blood vessel size is predicted to be relatively larger than the target blood vessel size, processor 130 may decrease the feature value. Processor 130 may determine the degree of increase or decrease in the feature value based on the difference between the DC component value corresponding to the force / pressure value of the characteristic point extracted from the oscillometric waveform envelope and a reference value, and may reflect the determined degree of increase or decrease in the feature value.

[0076] For example, suppose Figure 3A Shows the target blood vessel. Figure 3C The situation of the measured blood vessel is shown, then the DC component value b' of point 34 corresponding to the force / pressure value a' of the characteristic point 33 in the measured blood vessel is smaller than the reference value b of point 32 corresponding to the force / pressure value a of the characteristic point 31 in the target blood vessel, so that the processor 130 can predict that the size of the measured blood vessel is relatively smaller than the target blood vessel; and based on the difference between the DC component value b' and the reference value b or according to a predetermined standard, the processor 130 can increase the characteristic value a' obtained from the measured blood vessel by the difference adjustment value to obtain a corrected characteristic value.

[0077] Processor 130 can estimate blood pressure by applying the corrected eigenvalues ​​to a blood pressure estimation model. Equation 1 below is an example of a blood pressure estimation model defined as a simple linear function. However, the blood pressure estimation model is not limited thereto and can be predefined using various methods, such as linear / nonlinear regression analysis, neural networks, deep learning, etc.

[0078] [Equation 1]

[0079] y=ax+b

[0080] In Equation 1, "y" represents the estimated blood pressure value, "x" represents the corrected eigenvalue, "a" represents the adjustment coefficient of the predefined eigenvalue, and "b" is an offset value and may be, for example, the cuff blood pressure obtained at the calibration time. In this case, "a" and / or "b" may be defined for each of MAP, DBP, and SBP, and by applying the corrected eigenvalues ​​MAP, DBP, and SBP to each blood pressure estimation model, MAP, DBP, and SBP can be independently estimated.

[0081] Figure 6 is a block diagram illustrating an apparatus for estimating bio-information according to another embodiment of the present disclosure.

[0082] Reference Figure 6 The apparatus 600 for estimating biometric information includes a first sensor 110, a second sensor 120, a processor 130, a storage device 610, an output interface 620, and a communication interface 630. The first sensor 110, the second sensor 120, and the processor 130 are described in detail above, and thus descriptions of the first sensor 110, the second sensor 120, and the processor 130 will be omitted below.

[0083] The storage device 610 stores data related to biometric information estimation. For example, the storage device 610 may store data including pulse wave signals, force / pressure, oscillometric waveform envelopes, feature values ​​before and after correction, estimated biometric information values, and the like measured and processed by the first sensor 110, the second sensor 120, and the processor 130. Furthermore, the storage device 610 may store data including user characteristic information (such as the user's gender, age, and health status), reference blood pressure, biometric information estimation models, reference values, and the like, but the data is not limited thereto.

[0084] The storage device 610 may include at least one storage medium selected from a flash memory, a hard disk memory, a multimedia card memory, a micro card memory (e.g., a secure digital (SD) memory, an extreme digital (XD) memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk, but is not limited thereto.

[0085] The output interface 620 can output data related to the estimated biometric information. For example, the output interface 620 can output data including pulse wave signals, force / pressure, oscillometric waveform envelopes, characteristic values, estimated biometric information values, and the like measured and processed by the first sensor 110, the second sensor 120, and the processor 130. The output interface 620 can output data to the user through various visual and non-visual methods using a display, an audio output module, a tactile module, and the like.

[0086] The communication interface 630 can communicate with an external device using a wired communication technology or a wireless communication technology under the control of the processor 130, and can transmit and receive various data to and from the external device. For example, the communication interface 630 can transmit the bio-information estimation result to the external device and can receive various reference information for estimating blood pressure from the external device. In this case, the external device may include an information processing device (such as a cuff pressure gauge, a smartphone, a tablet PC, a desktop computer, a laptop computer, etc.).

[0087] In this case, the communication technology may include Bluetooth communication, Bluetooth Low Energy (BLE) communication, near field communication (NFC), wireless local area network (WLAN) communication, Zigbee communication, infrared data association (IrDA) communication, wireless fidelity (Wi-Fi) direct (WFD) communication, ultra-wideband (UWB) communication, Ant+ communication, Wi-Fi communication, radio frequency identification (RFID) communication, 3G communication, 4G communication, 5G communication, etc. However, the aforementioned communication technologies are merely examples and are not intended to be limiting.

[0088] Figure 7 is a flowchart illustrating a method of estimating biological information according to an embodiment of the present disclosure.

[0089] Figure 7 The method is based on Figure 1 or Figure 6 An example of a method of estimating bio-information performed by the apparatus for estimating bio-information of an embodiment, which is described above in detail, will thus be briefly described below.

[0090] In operation 711, based on the subject contacting the first sensor, the apparatus for estimating bio-information may measure a pulse wave signal of a first wavelength and a pulse wave signal of a second wavelength from the subject using the first sensor. In this case, the first wavelength may be an infrared wavelength, and the second wavelength may be a green wavelength.

[0091] Also, in operation 712 , the apparatus for estimating bio-information may measure force / pressure applied to the first sensor by the object based on the object being in contact with the first sensor, by using the second sensor.

[0092] In operation 713, the apparatus for estimating bio-information may obtain an oscillometric waveform envelope based on the pulse wave signal of the first wavelength and the force / pressure. For example, the apparatus for estimating bio-information may obtain an oscillometric waveform envelope based on the difference between the peak and the valley of the AC component of the pulse wave signal having an infrared wavelength and the force / pressure.

[0093] In operation 714, the apparatus for estimating bio-information may obtain a characteristic value from the oscillometric waveform envelope. For example, the apparatus for estimating bio-information may detect at least one of a peak point of the oscillometric waveform envelope, a first point before the peak point having an amplitude value corresponding to a first predetermined ratio of the amplitude value of the peak point, and a second point after the peak point having an amplitude value corresponding to a second predetermined ratio of the amplitude value of the peak point as characteristic points, and may obtain force / pressure values ​​of the detected characteristic points as characteristic values. In an example embodiment, the first predetermined ratio and the second predetermined ratio may be the same or different.

[0094] In operation 715, the apparatus for estimating bio-information may predict the size of the measured blood vessel based on the pulse wave signal of the second wavelength. For example, the apparatus for estimating bio-information may extract a DC component from the pulse wave signal of the second wavelength and may normalize the DC component. Furthermore, by comparing the DC component value corresponding to the force / pressure value of the characteristic point extracted in operation 714 with a reference value, the apparatus for estimating bio-information may predict the size of the measured blood vessel relative to the target blood vessel.

[0095] In operation 716, the apparatus for estimating bio-information may correct the feature value obtained in operation 714 based on the predicted size of the blood vessel. For example, based on the difference between the DC component value corresponding to the force / pressure of the characteristic point extracted in operation 714 and a reference value, the apparatus for estimating bio-information may determine the degree of increase or decrease in the DC component value, and may obtain a corrected feature value by reflecting the determined degree of increase or decrease in the feature value.

[0096] In operation 717 , the apparatus for estimating bio-information may estimate bio-information by using the corrected eigenvalues.

[0097] Figure 8 is a block diagram illustrating an example of an electronic device including an apparatus for estimating biological information. Figure 9 is shown as Figure 8 Schematic diagram of a wristwatch wearable device as an example of an electronic device. Figure 10 is shown as Figure 8 FIG. 1 is a diagram of a mobile device that is an example of an electronic device. Figure 11 is shown as Figure 8 Schematic diagram of an ear-worn device that illustrates an example of an electronic device.

[0098] Reference Figure 8 The electronic device 800 may include a sensor module 810, a processor 820, an input device 830, a communication module 840, a camera module 850, an output device 860, a storage device 870, and a power supply module 880. All components of the electronic device 800 may be integrally mounted in a specific device or distributed across two or more devices. The components of the apparatuses 100 and 600 for estimating biometric information described above may be integrated into the components of the electronic device 800 or may be provided separately.

[0099] The sensor module 810 may include a first sensor and a second sensor. The first sensor may include a light source and a light receiver. In this case, the light source may include a green wavelength light source and an infrared wavelength light source. Based on the object contacting the first sensor, the first sensor may obtain a green wavelength pulse wave signal and an infrared wavelength pulse wave signal from the object. The second sensor may be arranged at the upper end or lower end of the first sensor and may measure the force / pressure applied between the object and the first sensor. The sensor module 810 may include various sensors for performing other functions (such as a gyroscope sensor, a global positioning system (GPS), etc.).

[0100] The processor 820 may execute a program stored in the storage device 870 to control components connected to the processor 820, and the processor 820 may perform various data processing or calculations. The processor 820 may include a main processor (such as a central processing unit (CPU) or an application processor (AP)), and an auxiliary processor (such as a graphics processing unit (GPU), an image signal processor (ISP), a sensor hub processor, or a communication processor (CP)) that can operate independently of the main processor or in conjunction with the main processor.

[0101] Based on the user's request to estimate biometric information, the processor 820 can send a control signal to the sensor module 810, and can estimate the biometric information by using the infrared wavelength pulse wave signal, green wavelength pulse wave signal and force / pressure received from the sensor module 810 using the aforementioned method.

[0102] The input device 830 may receive commands and / or data from a user or the like to be used by each component of the electronic device 800. The input device 830 may include, for example, a microphone, a mouse, a keyboard, or a digital pen (eg, a stylus pen, etc.).

[0103] The communication module 840 can support the establishment of a direct (e.g., wired) communication channel and / or a wireless communication channel between the electronic device 800 and another electronic device, server, or sensor module 810 within the network environment, as well as communication via the established communication channel. The communication module 840 may include one or more communication processors that can operate independently of the processor 820 and support direct communication and / or wireless communication. The communication module 840 may include a wireless communication module (such as a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module, etc.) and / or a wired communication module (such as a local area network (LAN) communication module, a power line communication (PLC) module, etc.). These various types of communication modules can be integrated into a single chip or can be implemented separately as multiple chips. The wireless communication module can identify and authenticate the electronic device 800 in the communication network by using user information (e.g., an international mobile subscriber identity (IMSI), etc.) stored in the user identification module.

[0104] The camera module 850 can capture still images or moving images. The camera module 850 may include a lens assembly having one or more lenses, an image sensor, an image signal processor, and / or a flash. The lens assembly included in the camera module 850 may collect light emitted from an object to be imaged.

[0105] The output device 860 may visually / non-visually output data generated or processed by the electronic device 800. The output device 860 may include a sound output device, a display device, an audio module, and / or a haptic module.

[0106] The sound output device can output sound signals to the outside of the electronic device 800. The sound output device may include a speaker and / or a receiver. The speaker can be used for general purposes (such as playing multimedia), and the receiver can be used for incoming calls. The receiver can be implemented separately from the speaker or as part of the speaker.

[0107] The display device can visually provide information to the outside of the electronic device 800. The display device may include, for example, a display, a holographic device, or a projector, and a control circuit for controlling the device. The display device may include a touch circuit suitable for detecting a touch and / or a sensor circuit suitable for measuring the strength of the force caused by the touch (e.g., a pressure sensor, etc.).

[0108] The audio module can convert sound into an electrical signal and vice versa. The audio module can obtain sound via an input device, or can output sound via a sound output device and / or a speaker and / or earphone of another electronic device directly or wirelessly connected to the electronic device 800.

[0109] The haptic module may convert the electrical signal into mechanical stimulation (eg, vibration, motion, etc.) or electrical stimulation that can be recognized by the user through tactile or kinesthetic sense. The haptic module may include, for example, a motor, a piezoelectric element, and / or an electrical stimulator.

[0110] The storage device 870 may store driving conditions for driving the sensor module 810 and various data for other components of the electronic device 800. The various data may include, for example, software and input data and / or output data for commands related to the software. The storage device 870 may include volatile memory and / or non-volatile memory.

[0111] The power module 880 may manage the power supplied to the electronic device 800. The power module 880 may be implemented as part of a power management integrated circuit (PMIC). The power module 880 may include a battery including a non-rechargeable primary battery, a rechargeable secondary battery, and / or a fuel cell.

[0112] Figures 9 to 11 It shows Figure 8 1 is a diagram of an example of a structure of an electronic device 800.

[0113] Reference Figure 9 The electronic device 800 may be implemented as a wristwatch wearable device 900 and may include a main body and a wristband. A display is provided on the front surface of the main body and may display various application screens including time information, received message information, etc. A sensor module 910 may be provided on the rear surface of the main body to measure a pulse wave signal and force / pressure for estimating bio-information.

[0114] Reference Figure 10 , the electronic device 800 may be implemented as a mobile device 1000 such as a smart phone.

[0115] Mobile device 1000 may include a housing and a display panel. The housing may form the exterior of mobile device 1000. The housing has a first surface on which the display panel and cover glass are sequentially disposed. The display panel may be exposed to the outside through the cover glass. A sensor module 1010, a camera module, and / or an infrared sensor, etc. may be disposed on a second surface of the housing. Based on a user transmitting a request for estimating biometric information by executing an application installed in mobile device 1000, etc., mobile device 1000 may estimate biometric information using sensor module 1010 and may provide the estimated biometric information value to the user as an image and / or sound.

[0116] Reference Figure 11 , the electronic device 800 can be implemented as an ear-worn device 1100.

[0117] The ear-worn device 1100 may include a main body and an ear strap. A user may wear the ear-worn device 1100 by hanging the ear strap on the user's auricle. The ear strap may be omitted depending on the type of ear-worn device 1100. The main body may be inserted into the external auditory canal. The sensor module 1110 may be installed in the main body. The ear-worn device 1100 may provide the blood pressure estimation result to the user as sound, or may transmit the estimation result to an external device (such as a mobile device, tablet PC, personal computer, etc.) via a communication module provided in the main body.

[0118] The exemplary embodiments of the present disclosure may be implemented by codes stored on a non-transitory computer-readable medium and executed by a processor. The computer-readable medium may be any type of recording device that stores data in a computer-readable manner.

[0119] Examples of computer-readable 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 media can be distributed across multiple networked computer systems so that computer-readable code can be written to and executed from the computer-readable media in a decentralized manner. Functional programs, codes, and code segments for implementing the exemplary embodiments of the present disclosure can be derived by a programmer of ordinary skill in the art to which the present disclosure pertains.

[0120] The present disclosure has been described herein with respect to example embodiments. However, it will be apparent to those skilled in the art that various changes and modifications may be made without departing from the scope of the present disclosure. Therefore, it will be apparent that the embodiments described above 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 first sensor configured to measure a first pulse wave signal of a first wavelength and a second pulse wave signal of a second wavelength from a subject; a second sensor configured to measure at least one of a force and a pressure applied to the object; as well as The processor is configured to: generating an oscillometric waveform envelope based on the first pulse wave signal of the first wavelength and the at least one of the force and pressure applied to the subject; Obtain characteristic values ​​from the oscilloscope waveform envelope; predicting a measured size of the blood vessel based on a second pulse wave signal of a second wavelength; Correcting the characteristic value based on the measured size of the blood vessel; and Estimate biological information based on the corrected eigenvalues, The processor is further configured to: normalizing a DC component of a second pulse wave signal of a second wavelength; In response to a normalized DC component value corresponding to the at least one of the force value and the pressure value of the characteristic point being smaller than a reference value, predicting that the size of the measured blood vessel is smaller than the size of the target blood vessel; and In response to the normalized DC component value exceeding the reference value, predicting that the size of the measured blood vessel is larger than the size of the target blood vessel, The processor is further configured to: increasing the feature value based on predicting that the measured blood vessel size is smaller than the target blood vessel size; and The feature value is reduced based on the prediction that the size of the measured blood vessel is larger than the size of the target blood vessel.

2. The device according to claim 1, wherein The first wavelength is an infrared wavelength and the second wavelength is a green wavelength.

3. The device according to claim 1, wherein The processor is configured to generate an oscillometric waveform envelope based on a difference between a peak and a valley of an AC component of the first pulse wave signal of the first wavelength and the at least one of force and pressure.

4. The apparatus according to claim 1, wherein The processor is also configured to: Detecting characteristic points from the oscilloscope waveform envelope; and The characteristic values ​​are obtained based on the characteristic points.

5. The device according to claim 4, wherein The characteristic point includes at least one of a peak point of the oscillometric waveform envelope, a first point before the peak point and having an amplitude value corresponding to a first predetermined ratio of the amplitude value of the peak point, and a second point after the peak point and having an amplitude value corresponding to a second predetermined ratio of the amplitude value of the peak point.

6. The device according to claim 4, wherein The characteristic value includes at least one of a force value, a pressure value, and an amplitude value of a characteristic point.

7. The apparatus according to claim 6, wherein The processor is also configured to: extracting a DC component of a second pulse wave signal of a second wavelength; and The measured size of the blood vessel is predicted based on the DC component value corresponding to the at least one of the force value and the pressure value of the characteristic point.

8. The apparatus according to claim 1, wherein The processor is also configured to: Based on the difference between the normalized DC component value and the reference value, the degree of increase or decrease of the characteristic value is determined.

9. The apparatus according to any one of claims 1 to 8, wherein: The processor is also configured to: The biological information is estimated based on the corrected eigenvalues ​​by using a biological information estimation model.

10. The apparatus according to any one of claims 1 to 8, wherein: The biological information includes one or more of: blood pressure, vascular age, arterial stiffness, aortic pressure waveform, vascular compliance, pressure index, and fatigue level.

11. A method for estimating biological information, the method comprising: measuring, by the first sensor, a first pulse wave signal of a first wavelength and a second pulse wave signal of a second wavelength from the subject; measuring, by a second sensor, at least one of a force and a pressure applied to the object; generating an oscillometric waveform envelope based on the first pulse wave signal of the first wavelength and the at least one of the force and pressure applied to the subject; Obtain characteristic values ​​from the oscilloscope waveform envelope; predicting a measured size of the blood vessel based on a second pulse wave signal of a second wavelength; Correcting the characteristic value based on the measured size of the blood vessel; as well as Estimate biological information based on the corrected eigenvalues, The method further comprises: normalizing a DC component of a second pulse wave signal of a second wavelength; In response to a normalized DC component value corresponding to the at least one of the force value and the pressure value of the characteristic point being smaller than a reference value, predicting that the size of the measured blood vessel is smaller than the size of the target blood vessel; and In response to the normalized DC component value exceeding the reference value, predicting that the size of the measured blood vessel is larger than the size of the target blood vessel, The method further comprises: increasing the feature value based on predicting that the measured blood vessel size is smaller than the target blood vessel size; and The feature value is reduced based on the prediction that the size of the measured blood vessel is larger than the size of the target blood vessel.

12. The method according to claim 11, wherein The first wavelength is an infrared wavelength and the second wavelength is a green wavelength.

13. The method according to claim 11, wherein Generating the oscillometric waveform envelope includes generating the oscillometric waveform envelope based on a difference between a peak and a valley of an AC component of the first pulse wave signal of the first wavelength and the at least one of a force and a pressure applied to the subject.

14. The method according to claim 11, wherein The method further comprises: Detecting characteristic points from the oscilloscope waveform envelope; and The characteristic values ​​are obtained based on the characteristic points.

15. The method according to claim 14, wherein The characteristic point includes at least one of a peak point of the oscillometric waveform envelope, a first point before the peak point and having an amplitude value corresponding to a first predetermined ratio of the amplitude value of the peak point, and a second point after the peak point and having an amplitude value corresponding to a second predetermined ratio of the amplitude value of the peak point.

16. The method according to claim 14, wherein The characteristic value includes at least one of a force value, a pressure value, and an amplitude value of a characteristic point.

17. The method according to claim 16, wherein: The method further comprises: extracting a DC component of a second pulse wave signal of a second wavelength; and The measured size of the blood vessel is predicted based on the DC component value corresponding to the at least one of the force value and the pressure value of the characteristic point.

18. The method according to claim 11, wherein The method further comprises: The degree of increase or decrease of the characteristic value is determined based on the difference between the normalized DC component value and the reference value.

19. The method according to any one of claims 11 to 18, wherein: The step of estimating the biological information includes estimating the biological information based on the corrected feature values ​​by using a biological information estimation model.

20. An electronic device comprising an apparatus for estimating biological information and an output device configured to output a processing result of the apparatus for estimating biological information, in, Equipment used to estimate biological information includes: a first sensor configured to measure a first pulse wave signal of a first wavelength and a second pulse wave signal of a second wavelength from a subject; a second sensor configured to measure at least one of a force and a pressure applied to the object; and The processor is configured to: generating an oscillometric waveform envelope based on the first pulse wave signal of the first wavelength and the at least one of the force and pressure applied to the subject; Obtain characteristic values ​​from the oscilloscope waveform envelope; predicting a measured size of the blood vessel based on a second pulse wave signal of a second wavelength; Correcting the characteristic value based on the measured size of the blood vessel; and Estimate biological information based on the corrected eigenvalues, The processor is further configured to: normalizing a DC component of a second pulse wave signal of a second wavelength; In response to a normalized DC component value corresponding to the at least one of the force value and the pressure value of the characteristic point being smaller than a reference value, predicting that the size of the measured blood vessel is smaller than the size of the target blood vessel; and In response to the normalized DC component value exceeding the reference value, predicting that the size of the measured blood vessel is larger than the size of the target blood vessel, The processor is further configured to: increasing the feature value based on predicting that the measured blood vessel size is smaller than the target blood vessel size; and The feature value is reduced based on the prediction that the size of the measured blood vessel is larger than the size of the target blood vessel.

21. The electronic device according to claim 20, wherein: The electronic device includes at least one of a wristwatch wearable device, an ear-worn device, and a mobile device.

22. The electronic device according to claim 20, wherein: The first wavelength is an infrared wavelength and the second wavelength is a green wavelength.

23. The electronic device according to claim 20, wherein: The processor is also configured to: Detecting characteristic points from the oscilloscope waveform envelope; and The characteristic values ​​are obtained based on the characteristic points.

24. The electronic device according to claim 23, wherein: The processor is also configured to: extracting a DC component of a second pulse wave signal of a second wavelength; and The measured size of the blood vessel is predicted based on the DC component value corresponding to the at least one of the force value and the pressure value of the characteristic point.

25. A computer-readable medium storing codes, which, when executed by a processor, causes the processor to perform the method according to any one of claims 11 to 19.

Images