Blood pressure measuring equipment

Abstract

A blood pressure measuring device is disclosed. The blood pressure measuring device includes: a pulse wave sensor configured to detect a pulse wave signal of an object; a pressure sensor configured to detect a contact pressure signal corresponding to a contact pressure between the object and the pulse wave sensor; and a processor configured to generate a pulse wave image based on the detected pulse wave signal of the object, generate a contact pressure image based on the detected contact pressure signal corresponding to the contact pressure between the object and the pulse wave sensor, and estimate the blood pressure of the object based on the generated pulse wave image, the generated contact pressure image, and a blood pressure estimation model.

Description

[0001] This application is based on and claims the benefit of priority from Korean Patent Application No. 10-2018-0138379 filed on November 12, 2018 in the Korean Intellectual Property Office, the disclosure of which is incorporated herein in its entirety by reference. Technical Field

[0002] The present disclosure relates to techniques for measuring blood pressure. Background Art

[0003] Currently, invasive and non-invasive methods are used to measure blood pressure. Invasive methods are often used to monitor high-risk patients in operating rooms or intensive care units. However, invasive methods involve complex preparations and procedures and can lead to complications such as tissue damage due to infection and vascular occlusion. In addition, invasive methods are mainly used in critically ill patients, and their use should be carefully managed.

[0004] Therefore, the non-invasive method is mainly used for general measurement, but the non-invasive method has reduced measurement accuracy compared with the invasive method. Summary of the invention

[0005] Provided are a blood pressure measuring device and a blood pressure measuring method.

[0006] Additional aspects will be set forth in part in the description which follows and, in part, will be apparent from the description, or may be learned by practice of the embodiments.

[0007] According to one aspect of the present disclosure, a blood pressure measuring device includes: a pulse wave sensor configured to detect a pulse wave signal of an object; a pressure sensor configured to detect a contact pressure signal corresponding to a contact pressure between the object and the pulse wave sensor; and a processor configured to: generate a pulse wave image based on the detected pulse wave signal of the object, generate a contact pressure image based on the detected contact pressure signal corresponding to the contact pressure between the object and the pressure sensor; and estimate the blood pressure of the object based on the generated pulse wave image, the generated contact pressure image and a blood pressure estimation model.

[0008] The pulse wave signal may be a photoplethysmographic signal.

[0009] The pulse wave sensor can detect multiple pulse wave signals of different wavelengths.

[0010] The pressure sensor may detect a contact force signal and a contact area signal corresponding to a contact force and a contact area between the object and the pulse wave sensor, respectively, and obtain a contact pressure signal based on the contact force signal and the contact area signal.

[0011] The processor may generate the pulse wave image by converting the pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

[0012] The processor may generate a contact pressure image by converting the detected contact pressure signal into a gradient image.

[0013] The processor may process the pulse wave image and the contact pressure image to have the same time domain scale.

[0014] The blood pressure estimation model can be a convolutional neural network based model.

[0015] The blood pressure estimation model is generated by machine learning based on training data, and the training data may include pulse wave image data, contact pressure image data, and blood pressure data corresponding thereto.

[0016] The blood pressure measurement apparatus may further include: a contact image sensor configured to obtain a plurality of contact images of the subject in a time frame.

[0017] The processor may convert the plurality of contact images obtained at the time frames into a single contact image representing changes in the contact images over the time frames, and estimate the blood pressure of the subject based on the single contact image.

[0018] The processor may perform n-order differentiation on the detected pulse wave signal to obtain an n-order differential pulse wave signal, convert the obtained n-order differential pulse wave signal into an image to generate an n-order differential pulse wave image, and estimate the blood pressure of the subject based on the generated n-order differential pulse wave image. n may be a natural number.

[0019] The processor may generate guide information instructing the user to increase or decrease the contact pressure between the object and the pressure sensor based on the detected contact pressure signal, and provide the generated guide information to the user via the output device.

[0020] According to one aspect of the present disclosure, a blood pressure measurement method includes: detecting a pulse wave signal of an object; detecting a contact pressure signal corresponding to a contact pressure between the object and a pulse wave sensor; generating a pulse wave image based on the detected pulse wave signal; generating a contact pressure image based on the detected contact pressure signal; and estimating the blood pressure of the object based on the generated pulse wave image, the generated contact pressure image and a blood pressure estimation model.

[0021] The pulse wave signal may be a photoplethysmographic signal.

[0022] The step of detecting the pulse wave signal may include detecting a plurality of pulse wave signals of different wavelengths.

[0023] The step of detecting a contact pressure signal may include: detecting a contact force signal corresponding to a contact force between the object and the pulse wave sensor; detecting a contact area signal corresponding to a contact area between the object and the pulse wave sensor; and obtaining a contact pressure signal based on the contact force signal and the contact area signal.

[0024] The generating of the pulse wave image may include generating the pulse wave image by converting the detected pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

[0025] The generating of the contact pressure image may include generating the contact pressure image by converting the detected contact pressure signal into a gradient image.

[0026] The blood pressure measurement method may include generating a pulse wave image and a contact pressure image to have the same time domain scale.

[0027] The blood pressure estimation model can be a convolutional neural network based model.

[0028] The blood pressure estimation model may be generated through machine learning based on training data; and the training data may include pulse wave image data, contact pressure image data, and blood pressure data.

[0029] The blood pressure measurement method may include: obtaining multiple contact images of an object in a time frame; converting the multiple contact images obtained in the time frame into a single contact image representing changes in the contact images over the time frame, wherein the step of estimating blood pressure also includes: estimating the blood pressure of the object based on the single contact image.

[0030] The blood pressure measurement method may include: performing n-th order differentiation on the detected pulse wave signal to obtain an n-th order differential pulse wave signal; and converting the obtained n-th order differential pulse wave signal into an image to generate an n-th order differential pulse wave image, and the step of estimating the blood pressure may include: estimating the blood pressure of the subject based on the generated n-th order differential pulse wave image.

[0031] The blood pressure measurement method may include: generating guide information for instructing a user to increase or decrease a contact pressure between an object and a pulse wave sensor based on the detected contact pressure signal; and providing the generated guide information to the user.

[0032] A blood pressure measuring device may include: a pulse wave sensor configured to detect a pulse wave signal of an object; a force sensor configured to detect a contact force signal corresponding to a contact force between the object and the pulse wave sensor; an area sensor configured to detect a contact area signal corresponding to a contact area between the object and the pulse wave sensor; and a processor that may generate a pulse wave image based on the detected pulse wave signal of the object, generate a contact force image based on the detected contact force signal corresponding to the contact force between the object and the pulse wave sensor, generate a contact area image based on the detected contact area signal corresponding to the contact area between the object and the pulse wave sensor, and estimate the blood pressure of the object based on the generated pulse wave image, the generated contact force image, the generated contact area image, and a blood pressure estimation model.

[0033] The processor may generate the pulse wave image by converting the pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

[0034] The processor may generate a contact force image by converting the detected contact force signal into a gradient image, and may generate a contact area image by converting the detected contact area signal into a gradient image.

[0035] The blood pressure estimation model can be a convolutional neural network based model.

[0036] The blood pressure estimation model may be generated by machine learning based on training data, and the training data may include pulse wave image data, contact force image data, contact area image data, and blood pressure data.

[0037] According to one aspect of the present disclosure, a blood pressure measurement device may include: a cuff configured to be worn by a subject; a pressure sensor configured to detect a cuff pressure signal corresponding to the pressure between the cuff and the subject; and a processor configured to: obtain an alternating current (AC) component signal and a direct current (DC) component signal based on the cuff pressure signal, generate an AC component image based on the AC component signal, generate a DC component image based on the DC component signal, and estimate the subject's blood pressure based on the generated AC component image, the generated DC component image, and a blood pressure estimation model.

[0038] The processor may generate an AC component image by converting the AC component signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

[0039] The processor may generate a DC component image by converting the DC component signal into a gradient image.

[0040] The blood pressure estimation model can be a convolutional neural network based model.

[0041] The blood pressure estimation model may be generated by machine learning based on training data, and the training data may include AC component image data, DC component image data, and blood pressure data.

[0042] According to one aspect of the present disclosure, a blood pressure measurement method includes: detecting a cuff pressure signal corresponding to the pressure between the cuff and the object based on a cuff being placed on an object; extracting an alternating current (AC) component signal and a direct current (DC) component signal based on the cuff pressure signal; generating an AC component image based on the extracted AC component signal; generating a DC component image based on the extracted DC component signal; and estimating the object's blood pressure based on the generated AC component image, the generated DC component image and a blood pressure estimation model.

[0043] The generating of the AC component image may include generating the AC component image by converting the AC component signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

[0044] The generating of the DC component image may include generating the DC component image by converting a DC component signal into a gradient image.

[0045] The blood pressure estimation model can be a convolutional neural network based model.

[0046] The blood pressure estimation model may be generated by machine learning based on training data, and the training data may include AC component image data, DC component image data, and blood pressure data. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other aspects, features and advantages of certain embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings, in which:

[0048] Figure 1 is a block diagram showing an example of a blood pressure measurement apparatus according to an embodiment;

[0049] Figure 2 is a block diagram showing an example of a processor according to an embodiment;

[0050] Figure 3 is a diagram showing an example of generating a pulse wave image according to an embodiment;

[0051] Figure 4 is a diagram showing an example of generating a contact pressure image according to an embodiment;

[0052] Figure 5 is a block diagram showing another example of a processor according to an embodiment;

[0053] Figure 6 is a block diagram showing an example of a pulse wave sensor according to an embodiment;

[0054] Figure 7 is a block diagram showing another example of a pulse wave sensor according to the embodiment;

[0055] Figure 8 is a block diagram showing another example of a pulse wave sensor according to the embodiment;

[0056] Fig. 9 is a block diagram showing another example of the blood pressure measurement apparatus according to the embodiment;

[0057] Fig.10 is a block diagram showing an example of a processor according to an embodiment;

[0058] Fig.11 and Fig.12 is a diagram illustrating an example of converting a plurality of contact images over time into a single contact image according to an embodiment;

[0059] Fig.13 is a block diagram showing another example of a processor according to an embodiment;

[0060] Fig.14 is a block diagram showing another example of the blood pressure measurement apparatus according to the embodiment;

[0061] Fig.15 is a flowchart showing an example of a blood pressure measurement method according to an embodiment;

[0062] Fig.16 is a flowchart showing another example of the blood pressure measurement method according to the embodiment;

[0063] Fig.17 is a flowchart showing another example of the blood pressure measurement method according to the embodiment;

[0064] Fig.18 is a flowchart showing another example of the blood pressure measurement method according to the embodiment;

[0065] Fig.19 is a flowchart showing another example of the blood pressure measurement method according to the embodiment;

[0066] Fig. 20 is a block diagram showing another example of the blood pressure measurement apparatus according to the embodiment;

[0067] Fig.21 is a block diagram showing an example of a processor according to an embodiment;

[0068] Fig. 22 is a flowchart showing another example of the blood pressure measurement method according to the embodiment;

[0069] Fig.23is a block diagram showing another example of the blood pressure measurement apparatus according to the embodiment;

[0070] Fig.24 is a block diagram showing an example of a processor according to an embodiment; and

[0071] Fig.25 is a flowchart showing another example of the blood pressure measurement method according to the embodiment.

[0072] Throughout the drawings and detailed description, unless otherwise described, the same drawing reference numerals may represent the same elements, features, and structures. The relative sizes and depictions of these elements may be exaggerated for clarity, illustration, and convenience. DETAILED DESCRIPTION

[0073] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. It should be noted that although the same reference symbols are shown in other drawings, the same reference symbols may represent the same elements, features and structures wherever they are used. In the following description, the detailed description of the known functions and configurations contained herein may be omitted to avoid blurring the subject matter of the present disclosure.

[0074] Unless a specified order is clearly stated in the context of the present disclosure, the process steps described herein may be performed differently from the specified order. That is, each step may be performed in the specified order, substantially simultaneously, in reverse order, or in a different order.

[0075] Furthermore, the terms used throughout this specification are defined in consideration of the functions of the exemplary embodiments, and may vary according to the purpose of a user or manager, precedents, etc. Therefore, the definition of the terms should be made based on the overall context.

[0076] It will be understood that although the terms "first", "second", etc. may be used to describe various elements herein, these elements may not be limited by these terms. These terms may be used to distinguish one element from another element. Unless otherwise expressly stated, any reference to a term in the singular may include a term in the plural form. In the present disclosure, it should be understood that terms such as "including", "having", etc. may indicate the presence of features, quantities, steps, actions, components, parts, or combinations thereof disclosed in the specification, and may not exclude the possibility that one or more other features, quantities, steps, actions, components, parts, or combinations thereof may be present or may be added.

[0077] In addition, the components described in the specification can be distinguished according to the functions mainly performed by the components. That is, two or more components can be integrated into a single component. In addition, a single component can be divided into two or more components. In addition, in addition to the main function of each component, each component can additionally perform some or all of the functions performed by another component. Some or all of the main functions of each component can be performed by another component. Each component can be implemented in hardware, software, or a combination of the two.

[0078] Figure 1 is a block diagram showing an example of a blood pressure measurement apparatus according to an embodiment. Figure 1 The blood pressure measurement device 100 is a device for non-invasively measuring the blood pressure of an object, and may be embedded in an electronic device or may be enclosed in a housing to be provided as a separate device. Examples of electronic devices may include cellular phones, smart phones, tablet personal computers (PCs), laptop computers, personal digital assistants (PDAs), portable multimedia players (PMPs), navigation devices, MP3 players, digital cameras, wearable devices, etc.; and examples of wearable devices may include watch-type wearable devices, wristband-type wearable devices, ring-type wearable devices, belt-type wearable devices, necklace-type wearable devices, ankle-band-type wearable devices, thigh-band-type wearable devices, forearm-band-type wearable devices, etc. However, the electronic device is not limited to the above examples, and the wearable device is not limited thereto.

[0079] Reference Figure 1 , the blood pressure measurement device 100 includes a pulse wave sensor 110 , a pressure sensor 120 , and a processor 130 .

[0080] The pulse wave sensor 110 may detect a pulse wave signal of a subject. In one embodiment, the pulse wave sensor 110 may detect at least one pulse wave signal for different wavelengths. That is, the pulse wave sensor 110 may detect a pulse wave signal of a single wavelength, or may detect a plurality of pulse wave signals of different wavelengths. In this case, the pulse wave signal may be a photoplethysmography (PPG) signal.

[0081] For example, based on an object contacting the pulse wave sensor 110, the pulse wave sensor 110 may emit light to the object and may detect light reflected by the object to detect at least one pulse wave signal. In this case, the light emitted to the object may be visible light or near infrared light.

[0082] The pressure sensor 120 may detect a contact pressure signal corresponding to the contact pressure between the object and the pulse wave sensor 110. In one embodiment, the pressure sensor 120 may detect a contact force signal corresponding to the contact force between the object and the pulse wave sensor 110, and may obtain the contact pressure signal by dividing the contact force signal by a predetermined area. The predetermined area may be pre-stored in the blood pressure measurement device 100 as a default value. In another embodiment, the pressure sensor 120 may detect a contact force signal and a contact area signal corresponding to the contact force and the contact area between the object and the pulse wave sensor 110, respectively, and may obtain the contact pressure signal by dividing the measured contact force signal by the measured contact area signal. To this end, the pressure sensor 120 may include a force sensor, a barometer sensor, an acceleration sensor, a piezoelectric film, a load cell, a radar, a strain gauge, a contact area sensor, and the like.

[0083] The processor 130 may control the overall operation of the blood pressure measurement apparatus 100 .

[0084] Based on the object contacting the pulse wave sensor 110 , the processor 130 may control the pulse wave sensor 110 to detect a pulse wave signal of the object, and may control the pressure sensor 120 to detect a contact pressure signal corresponding to a contact pressure between the object and the pulse wave sensor 110 .

[0085] In addition, the processor 130 may estimate the blood pressure of the subject based on the pulse wave signal and the contact pressure signal. For example, the processor 130 may convert each of the pulse wave signal and the contact pressure signal into an image to generate a pulse wave image and a contact pressure image, and may estimate the blood pressure of the subject by using the generated pulse wave image and the contact pressure image.

[0086] In the following, reference will be made to Figures 2 to 5 Embodiments of the processor 130 are described in detail.

[0087] Figure 2 is a block diagram illustrating an example of a processor according to an embodiment. Figure 2 The processor 200 may be Figure 1 An example of a processor 130 .

[0088] Reference Figure 2 , the processor 200 includes a pulse wave image generator 210 , a contact pressure image generator 220 , a guide information generator 230 , and a blood pressure estimator 240 .

[0089] The pulse wave image generator 210 may convert the pulse wave signal into an image by performing frequency domain conversion to generate a pulse wave image. The pulse wave signal may be a periodic signal having a shape containing important information. In one embodiment, the pulse wave image generator 210 may generate a pulse wave image by converting the pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Wille distribution. In this case, the generated pulse wave image may be represented in the time domain and the frequency domain. That is, the horizontal axis of the pulse wave image represents the time domain reflecting the physical characteristics about time; the vertical axis of the pulse wave image represents the frequency domain reflecting the physical characteristics about frequency. However, the pulse wave image is not limited thereto, and the horizontal axis may represent the frequency domain reflecting the physical characteristics about frequency, and the vertical axis may represent the time domain reflecting the physical characteristics about time.

[0090] The contact pressure image generator 220 may generate a contact pressure image by converting the contact pressure signal into an image. The contact pressure signal may be a non-periodic signal having an intensity containing important information. In one embodiment, the contact pressure image generator 220 may generate a contact pressure image by converting the contact pressure signal into a gradient image. In this case, the generated contact pressure image may be represented in the time domain. That is, one axis (e.g., the horizontal axis or the vertical axis) of the contact pressure image may represent a time domain reflecting a physical property with respect to time.

[0091] Based on the measured contact pressure signal, the guide information generator 230 may generate guide information for instructing the user to increase or decrease the contact pressure between the object and the pulse wave sensor to measure the blood pressure. Then, the guide information generator 230 may provide the generated guide information to the user via an output device. For example, the guide information generator 230 may compare the measured contact pressure signal with a linearly increasing or decreasing target pressure signal; in response to the measured contact pressure signal being greater than the target pressure signal, the guide information generator 230 may generate guide information for instructing the user to reduce the contact pressure, and in response to the measured contact pressure signal being less than the target pressure signal, the guide information generator 230 may generate guide information for instructing the user to increase the contact pressure. Then, the guide information generator 230 may provide the generated guide information to the user via an output device. In this case, examples of the output device may include various output devices such as a visual output device, an audio output device, a tactile output device, and the like.

[0092] The blood pressure estimator 240 may estimate the blood pressure of the subject based on the pulse wave image and the contact pressure image. In this case, the blood pressure estimator 240 may use a pre-generated blood pressure estimation model. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the pulse wave image data, the contact pressure image data, and the blood pressure data corresponding thereto as training data, and may be stored in the internal memory or the external memory of the processor 200.

[0093] In one embodiment, before estimating the blood pressure, the blood pressure estimator 240 may process the pulse wave image and the contact pressure image so that the pulse wave image and the contact pressure image may have the same size. For example, the blood pressure estimator 240 may process the pulse wave image and the contact pressure image so that the pulse wave image and the contact pressure image may have the same time domain scale.

[0094] Figure 3 is a diagram illustrating an example of generating a pulse wave image according to an embodiment. Figure 3 is an example of generating a pulse wave image by converting a PPG signal using wavelet transform.

[0095] Reference Figure 2 and Figure 3 , the pulse wave image generator 210 may transform the pulse wave signal 310 using wavelet transform to generate a pulse wave image 320. The pulse wave signal 310 is a periodic signal having a shape containing important information. In the pulse wave signal 310, physical characteristics regarding time and physical characteristics regarding frequency may be important factors for estimating blood pressure. Therefore, the pulse wave image generator 210 may generate the pulse wave image 320 by performing frequency domain conversion such as wavelet transform so that the physical characteristics regarding time and physical characteristics regarding frequency of the pulse wave signal 310 may be represented. In this case, the shape of the envelope or the combination of a plurality of high frequency components forming the shape of the pulse wave signal 310 may be reflected in the generated pulse wave image 320.

[0096] like Figure 3 As shown in , the horizontal axis of the pulse wave image 320 represents the time domain reflecting the physical characteristics regarding time, and the vertical axis of the pulse wave image 320 represents the frequency domain reflecting the physical characteristics regarding frequency.

[0097] Figure 4 is a diagram illustrating an example of generating a contact pressure image according to an embodiment. Figure 4 An example of generating a contact pressure image by converting a contact pressure signal into a gradient image is shown.

[0098] Reference Figure 2 and Figure 4, the contact pressure image generator 220 may convert the contact pressure signal 410 into a gradient image to generate the contact pressure image 420. The contact pressure signal 410 may be a non-periodic signal having an intensity containing important information, and the physical characteristics of the contact pressure signal 410 with respect to time may be a relatively important factor in estimating the blood pressure. Therefore, the contact pressure image generator 220 may generate the contact pressure image 420 by converting the contact pressure signal 410 into a gradient image so that the physical characteristics of the contact pressure signal 410 with respect to time (e.g., signal intensity over time) may be well represented.

[0099] like Figure 4 As shown in , the horizontal axis of the contact pressure image 420 represents the time domain reflecting the physical characteristics with respect to time.

[0100] Figure 5 is a block diagram showing another example of the processor according to the embodiment. Figure 5 The processor 500 may be Figure 1 Another example of processor 130.

[0101] Reference Figure 5 , the processor 500 includes a pulse wave image generator 510, a contact pressure image generator 520, a guide information generator 530, a differentiator 540, a differential image generator 550, and a blood pressure estimator 560. Here, the pulse wave image generator 510, the contact pressure image generator 520, and the guide information generator 530 may be connected to Figure 2 The pulse wave image generator 210, the contact pressure image generator 220, and the guide information generator 230 are substantially similar, and thus a detailed description thereof may be omitted.

[0102] The differentiator 540 may perform n-th order differentiation on the pulse wave signal to obtain an n-th order differentiated pulse wave signal, where n may be a natural number greater than 0.

[0103] The differential image generator 550 may convert the obtained n-order differential pulse wave signal into an image to generate an n-order differential pulse wave image. The pulse wave signal may be a periodic signal having a shape containing important information, and thus the n-order differential pulse wave signal may also be a periodic signal having a shape containing important information. The differential image generator 550 may convert the n-order differential pulse wave signal into an image by performing frequency domain conversion on the n-order differential pulse wave signal to generate an n-order differential pulse wave image. In one embodiment, the differential image generator 550 may convert the n-order differential pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Wille distribution to generate an n-order differential pulse wave image. The generated n-order differential pulse wave image may be represented in the time domain and the frequency domain. That is, the horizontal axis of the n-order differential pulse wave image represents the time domain reflecting the physical characteristics regarding time; and the vertical axis of the n-order differential pulse wave image represents the frequency domain reflecting the physical characteristics regarding frequency. However, the n-order differential pulse wave image is not limited thereto, and its horizontal axis may be the frequency domain reflecting physical characteristics regarding frequency, and its vertical axis may be the time domain reflecting physical characteristics regarding time.

[0104] The blood pressure estimator 560 may estimate the blood pressure of the subject based on the pulse wave image, the contact pressure image, and the n-order differential pulse wave image. In this case, the blood pressure estimator 560 may use a pre-generated blood pressure estimation model. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the pulse wave image data, the contact pressure image data, the n-order differential pulse wave image data, and the blood pressure data corresponding thereto as training data, and may be stored in the internal memory or the external memory of the processor 500.

[0105] In one embodiment, before estimating the blood pressure, the blood pressure estimator 560 may process the pulse wave image, the contact pressure image, and the n-order differential pulse wave image so that the pulse wave image, the contact pressure image, and the n-order differential pulse wave image may have the same size. For example, the blood pressure estimator 560 may process the pulse wave image, the contact pressure image, and the n-order differential pulse wave image so that the pulse wave image, the contact pressure image, and the n-order differential pulse wave image may have the same time domain scale.

[0106] Figure 6 is a block diagram illustrating an example of a pulse wave sensor. Figure 6 An example of measuring two or more pulse wave signals of different wavelengths is shown; and Figure 6 The pulse wave sensor 600 may be Figure 1 An example of the pulse wave sensor 110 is shown.

[0107] Reference Figure 6The pulse wave sensor 600 may be formed as an array of pulse wave sensors for measuring a plurality of pulse wave signals of different wavelengths. Figure 6 As shown in FIG. 6 , the pulse wave sensor 600 includes a first pulse wave sensor 610 and a second pulse wave sensor 620. However, this is merely an example for convenience of explanation, and the number of pulse wave sensors included in the array is not particularly limited.

[0108] The first pulse wave sensor 610 includes a first light source 611 that emits light of a first wavelength to a subject and a first light detector 612 that detects a first pulse wave signal by detecting light of the first wavelength emitted by the first light source 611 and reflected by the subject.

[0109] The second pulse wave sensor 620 includes a second light source 621 that emits light of a second wavelength to the subject and a second light detector 622 that detects a second pulse wave signal by detecting light of the second wavelength emitted by the second light source 621 and reflected by the subject.

[0110] In one embodiment, the first light source 611 and the second light source 621 may include a light emitting diode (LED), an organic light emitting diode (OLED), a quantum dot light emitting diode (QLED), a laser diode, a phosphor, etc., but are not limited thereto. In addition, the first light detector 612 and the second light detector 622 may include a photodiode, a phototransistor (PTR), a charge coupled device (CCD), a complementary metal oxide semiconductor (CMOS), etc., but are not limited thereto.

[0111] Figure 7 is a block diagram showing another example of a pulse wave sensor. Figure 7 An example of detecting two or more pulse wave signals of different wavelengths is shown; and Figure 7 The pulse wave sensor 700 may be Figure 1 An example of the pulse wave sensor 110 is shown.

[0112] Reference Figure 7 , the pulse wave sensor 700 includes a light source unit 710 and a light detector 720, and the light source unit 710 includes a first light source 711 and a second light source 712. Figure 7 An example is shown in which the light source part 710 includes two light sources 711 and 712 , but this is merely an example for convenience of explanation, and the number of light sources is not particularly limited.

[0113] The first light source 711 may emit light of a first wavelength to the object, and the second light source 712 may emit light of a second wavelength to the object. In this case, the first wavelength and the second wavelength may be different from each other.

[0114] The light detector 720 may detect a first pulse wave signal by detecting light of a first wavelength emitted by the first light source 711 and reflected by the object, and may detect a second pulse wave signal by detecting light of a second wavelength emitted by the second light source 712 and reflected by the object.

[0115] For example, the first light source 711 and the second light source 712 may be driven in a time-division manner under the control of the processor to sequentially emit light to the object. In this case, the light source driving conditions (such as emission time, driving order, current intensity, pulse duration, etc.) of the first light source 711 and the second light source 712 may be preset. The processor may control the driving of each of the light sources 711 and 712 by referring to the preset light source driving conditions.

[0116] The light detector 720 may detect the first pulse wave signal and the second pulse wave signal by sequentially detecting the first wavelength of light and the second wavelength of light sequentially emitted by the first light source 711 and the second light source 712 and reflected by the object.

[0117] Figure 8 is a block diagram showing another example of a pulse wave sensor. Figure 8 An example of detecting two or more pulse wave signals of different wavelengths is shown; and Figure 8 The pulse wave sensor 800 may be Figure 1 An example of the pulse wave sensor 110 is shown.

[0118] Reference Figure 8 , the pulse wave sensor 800 includes a light source 810 and a light detector unit 820. The light detector unit 820 includes a first light detector 821 and a second light detector 822. Figure 8 An example is shown in which the photodetector section 820 includes two photodetectors 821 and 822 , but this is merely an example for convenience of explanation, and the number of photodetectors is not particularly limited.

[0119] The light source 810 may emit light of a predetermined wavelength range toward the object. In this case, the light source 810 as a single light source may emit light in a wide wavelength range including a visible light range.

[0120] The light detector part 820 may detect a plurality of pulse wave signals by detecting light within a predetermined wavelength range reflected by an object. To this end, the first light detector 821 and the second light detector 822 included in the light detector part 820 may have different response characteristics.

[0121] For example, the first light detector 821 and the second light detector 822 may have different measurement ranges to respond to different wavelengths of light among the light beams reflected by the object. Alternatively, a filter may be mounted on the front surface of any one of the first light detector 821 and the second light detector 822, or different filters may be mounted on the front surfaces of the two light detectors 821 and 822 to respond to different wavelengths of light. In addition, the first light detector 821 and the second light detector 822 may be placed at different distances from the light source 810. In this case, the light detector of the light detectors 821 and 822 placed at a relatively short distance from the light source 810 may detect light in a short wavelength range; the other light detector placed at a relatively long distance from the light source 810 may detect light in a long wavelength range.

[0122] Reference above Figures 6 to 8 An embodiment of a pulse wave sensor for detecting a plurality of pulse wave signals of different wavelengths is described in more detail, which is merely an example, and the pulse wave sensor is not limited thereto. That is, there may be various numbers and arrangements of light sources and light detectors, and their numbers and arrangements may vary according to the purpose of use of the pulse wave sensor, the size and shape of an electronic device in which the pulse wave sensor is installed, and the like.

[0123] Fig. 9 is a block diagram showing another example of the blood pressure measurement apparatus according to the embodiment. Fig. 9 The blood pressure measurement apparatus 900 is an apparatus for non-invasively measuring the blood pressure of a subject, and may be embedded in an electronic device or may be enclosed in a housing to be provided as a separate apparatus.

[0124] Reference Fig. 9 , the blood pressure measurement device 900 includes a pulse wave sensor 910, a pressure sensor 920, a contact image sensor 930, and a processor 940. Here, the pulse wave sensor 910 and the pressure sensor 920 may be connected to Figure 1 The pulse wave sensor 110 and the pressure sensor 120 are substantially similar, and thus a detailed description thereof may be omitted.

[0125] The contact image sensor 930 may obtain a plurality of contact images of an object over time (i.e., obtain a plurality of contact images in time sequence). For example, the contact image sensor 930 may obtain a plurality of contact images at a plurality of times periodically or non-periodically, thereby obtaining a plurality of contact images over time. To this end, the contact image sensor 930 may include a touch sensor, a fingerprint sensor, etc. For example, the contact image sensor 930 may obtain a contact image at each time by drawing an outline based on a sensor value of a touch sensor or a fingerprint sensor at each time.

[0126] The processor 940 may control the overall operation of the blood pressure measurement device 900 .

[0127] Once the object contacts the pulse wave sensor 910, the processor 940 can control the pulse wave sensor 910 to detect the pulse wave signal of the object; can control the pressure sensor 920 to detect a contact pressure signal corresponding to the contact pressure between the object and the pulse wave sensor 910; and can control the contact image sensor 930 to obtain multiple contact images over time.

[0128] In addition, the processor 940 may estimate the blood pressure of the subject based on the detected pulse wave signal, the detected contact pressure signal, and the multiple contact images obtained over time. For example, the processor 940 may convert each of the pulse wave signal and the contact pressure signal into an image to generate a pulse wave image and a contact pressure image, may convert the multiple contact images over time into a single contact image representing the change of the contact images over time, and may estimate the blood pressure of the subject by using the pulse wave image, the contact pressure image, and the single contact image.

[0129] In the following, reference will be made to Figures 10 to 13 An embodiment of processor 940 is described in detail.

[0130] Fig.10 is a block diagram illustrating an example of a processor according to an embodiment. Fig.10 The processor 1000 may be Fig. 9 An example of a processor 940 .

[0131] Reference Fig.10 , the processor 1000 includes a pulse wave image generator 1010, a contact pressure image generator 1020, a guide information generator 1030, an image converter 1040, and a blood pressure estimator 1050. Here, the pulse wave image generator 1010, the contact pressure image generator 1020, and the guide information generator 1030 may be connected to Figure 2 The pulse wave image generator 210, the contact pressure image generator 220, and the guide information generator 230 are substantially similar, and thus a detailed description thereof may be omitted.

[0132] The image converter 1040 may convert the multiple contact images over time into a single contact image representing the change of the contact images over time. For example, the image converter 1040 may convert the multiple contact images over time into a single contact image by dividing the contact image at each time into a plurality of parts, arranging the plurality of parts in a predetermined arrangement order to generate an arrangement image of the contact image at each time, and arranging the generated arrangement image of the plurality of contact images in a time series order.

[0133] The blood pressure estimator 1050 may estimate the blood pressure of the subject based on the pulse wave image, the contact pressure image, and the single contact image. In this case, the blood pressure estimator 1050 may use a pre-generated blood pressure estimation model. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the pulse wave image data, the contact pressure image data, the single contact image data, and the blood pressure data corresponding thereto as training data, and may be stored in the internal memory or the external memory of the processor 1000.

[0134] In one embodiment, before estimating the blood pressure, the blood pressure estimator 1050 may process the pulse wave image, the contact pressure image, and the single contact image so that the pulse wave image, the contact pressure image, and the single contact image may have the same size. For example, the blood pressure estimator 1050 may process the pulse wave image, the contact pressure image, and the single contact image so that the pulse wave image, the contact pressure image, and the single contact image may have the same time domain scale.

[0135] Fig.11 and Fig.12 is a diagram illustrating an example of converting a plurality of contact images over time into a single contact image according to an embodiment.

[0136] Reference Figures 10 to 12 , the image converter 1040 may convert the plurality of contact images 1111 and 1112 over time into a single contact image 1130 representing the change of the contact images over time. In the illustrated example, the image converter 1040 may divide the first contact image 1111 into a plurality of parts (such as 1, 2, etc.), and may sequentially arrange the plurality of parts in a predetermined arrangement order (for example, from top to bottom) to generate an arrangement image 1121 of the first contact image 1111. In addition, the image converter 1040 may divide the second contact image 1112 into a plurality of parts, and may sequentially arrange the plurality of parts in a predetermined arrangement order (for example, from top to bottom) to generate an arrangement image 1122 of the second contact image 1112. In this way, the image converter 1040 may generate an arrangement image of all contact images over time, and may arrange the generated arrangement images 1121 and 1122 in a time series order to generate a single contact image 1130.

[0137] Fig.13 is a block diagram showing another example of the processor according to the embodiment. Fig.13 The processor 1300 may be Fig. 9 An example of a processor 940 .

[0138] Reference Fig.13, the processor 1300 includes a pulse wave image generator 1310, a contact pressure image generator 1320, a guide information generator 1330, an image converter 1340, a differentiator 1350, a differential image generator 1360, and a blood pressure estimator 1370. Here, the pulse wave image generator 1310, the contact pressure image generator 1320, the guide information generator 1330, and the image converter 1340 may be respectively connected to Fig.10 The pulse wave image generator 1010, the contact pressure image generator 1020, the guide information generator 1030 and the image converter 1040 are substantially similar, so their detailed description may be omitted. In addition, the differentiator 1350 and the differential image generator 1360 may be similar to Figure 5 The differentiator 540 and the differential image generator 550 are substantially similar, and thus a detailed description thereof may be omitted.

[0139] The blood pressure estimator 1370 may estimate the blood pressure of the subject based on the pulse wave image, the contact pressure image, the single contact image, and the n-order differential pulse wave image. In this case, the blood pressure estimator 1370 may use a pre-generated blood pressure estimation model. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using pulse wave image data, contact pressure image data, single contact image data, n-order differential pulse wave image data, and blood pressure data corresponding thereto as training data, and may be stored in an internal memory or an external memory of the processor 1300.

[0140] In one embodiment, before estimating the blood pressure, the blood pressure estimator 1370 may process the pulse wave image, the contact pressure image, the single contact image, and the n-order differential pulse wave image so that the pulse wave image, the contact pressure image, the single contact image, and the n-order differential pulse wave image may have the same size. For example, the blood pressure estimator 1370 may process the pulse wave image, the contact pressure image, the single contact image, and the n-order differential pulse wave image so that the pulse wave image, the contact pressure image, the single contact image, and the n-order differential pulse wave image may have the same time domain scale.

[0141] Fig.14 is a block diagram showing another example of the blood pressure measurement apparatus according to the embodiment. Fig.14 The blood pressure measurement apparatus 1400 is an apparatus for non-invasively measuring the blood pressure of a subject, and may be embedded in an electronic device or may be enclosed in a housing to be provided as a separate device.

[0142] Reference Fig.14, the blood pressure measurement device 1400 includes a pulse wave sensor 1410, a pressure sensor 1420, a processor 1430, an input interface 1440, a memory 1450, a communication interface 1460, and an output interface 1470. Here, the pulse wave sensor 1410, the pressure sensor 1420, and the processor 1430 may be respectively connected to Figure 1 The pulse wave sensor 110, the pressure sensor 120, and the processor 130 are substantially similar, and thus a detailed description thereof may be omitted.

[0143] The input interface 1440 may receive input of various operation signals based on user input. In one embodiment, the input interface 1440 may include a keyboard, a dome switch, a touch pad (e.g., a static pressure touch pad, a capacitive touch pad, etc.), a scroll wheel, a jog switch, a hardware (H / W) button, etc. In particular, a touch pad forming a layer structure with a display may be referred to as a touch screen.

[0144] The memory 1450 may store programs or commands for the operation of the blood pressure measurement device 1400, and may store data input to and output from the blood pressure measurement device 1400. In addition, the memory 1450 may store a pulse wave signal, a contact pressure signal, a pulse wave image, a contact pressure image, a blood pressure estimation model, and the like.

[0145] The memory 1450 may include at least one of the following storage media: a flash memory, a hard disk memory, a multimedia card micro memory, a card-type 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, an optical disk, etc. In addition, the blood pressure measurement device 1400 may communicate with an external storage medium (such as a network storage, etc.) that performs a storage function of the memory 1450 on the Internet.

[0146] The communication interface 1460 may perform communication with an external device. For example, the communication interface 1460 may transmit data input to the blood pressure measurement apparatus 1400, data stored in the blood pressure measurement apparatus 1400, or data processed by the blood pressure measurement apparatus 1400, etc. to an external device, or may receive various data for estimating the blood pressure of a subject from an external device.

[0147] In this case, the external device may be a medical device that uses data input to the blood pressure measurement apparatus 1400, data stored in the blood pressure measurement apparatus 1400, or data processed by the blood pressure measurement apparatus 1400, a printer that prints out the results, or a display that displays the results. In addition, the external device may be a digital television (TV), a desktop computer, a cellular phone, a smart phone, a tablet PC, a laptop computer, a PDA, a PMP, a navigation device, an MP3 player, a digital camera, a wearable device, etc., but is not limited thereto.

[0148] The communication interface 1460 may communicate with an external device by using 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) communication, ultra-wideband (UWB) communication, Ant+ communication, Wi-Fi direct (WFD) communication, radio frequency identification (RFID) communication, third generation (3G) communication, fourth generation (4G) communication, fifth generation (5G) communication, etc. However, this is merely exemplary and is not intended to be limiting.

[0149] The output interface 1470 may output data input to the blood pressure measurement device 1400, data stored in the blood pressure measurement device 1400, data processed by the blood pressure measurement device 1400, etc. In one embodiment, the output interface 1470 may output data input to the blood pressure measurement device 1400, data stored in the blood pressure measurement device 1400, data processed by the blood pressure measurement device 1400, etc. by using at least one of an acoustic method, a visual method, and a tactile method. To this end, the output interface 1470 may include a speaker, a display, a vibrator, etc.

[0150] Fig.15 is a flowchart illustrating an example of a blood pressure measurement method according to an embodiment. Fig.15 Blood pressure measurement can be done by Figure 1 The blood pressure measurement device 100 performs.

[0151] Reference Fig.15 In operation 1510, the blood pressure measurement device may detect a pulse wave signal of the subject. In one embodiment, the blood pressure measurement device may detect at least one pulse wave signal of different wavelengths. For example, based on the object contacting the pulse wave sensor, the blood pressure measurement device may detect at least one pulse wave signal of different wavelengths by detecting light reflected by the object.

[0152] In operation 1520, the blood pressure measurement device may detect a contact pressure signal corresponding to the contact pressure between the object and the pulse wave sensor. In one embodiment, the blood pressure measurement device may detect a contact force signal corresponding to the contact force between the object and the pulse wave sensor, and may obtain the contact pressure signal by dividing the detected contact force signal by a predetermined area. The predetermined area may be pre-stored in the blood pressure measurement device as a default value. In one embodiment, the blood pressure measurement device may detect a contact force signal and a contact area signal corresponding to the contact force and the contact area between the object and the pulse wave sensor, respectively, and may obtain the contact pressure signal by dividing the measured contact force signal by the measured contact area signal.

[0153] In operation 1530, the blood pressure measurement apparatus may convert the pulse wave signal into an image by performing frequency domain conversion to generate a pulse wave image. In one embodiment, the blood pressure measurement apparatus may generate a pulse wave image by converting the pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Wille distribution.

[0154] In operation 1540, the blood pressure measurement apparatus may convert the contact pressure signal into an image to generate a contact pressure image. In one embodiment, the blood pressure measurement apparatus may generate the contact pressure image by converting the contact pressure signal into a gradient image.

[0155] In operation 1550, the blood pressure measurement device may estimate the blood pressure of the subject by using the pulse wave image, the contact pressure image, and the blood pressure estimation model. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the pulse wave image data, the contact pressure image data, and the blood pressure data corresponding thereto as training data.

[0156] Fig.16 is a flowchart showing another example of the blood pressure measurement method according to the embodiment. Fig.16 Blood pressure measurement can be done by Figure 1 The blood pressure measurement device 100 performs. Fig.16 Operations 1610, 1620, 1640, 1650, and 1670 may be respectively Fig.15 Operations 1510, 1520, 1530, 1540, and 1550 are substantially similar, so a description thereof may be briefly made below.

[0157] Reference Fig.16 , the blood pressure measurement apparatus may detect a pulse wave signal of the subject in operation 1610 , and may detect a contact pressure signal corresponding to a contact pressure between the subject and the pulse wave sensor in operation 1620 .

[0158] In operation 1630, based on the detected contact pressure signal, the blood pressure measurement device may generate guidance information instructing the user to increase or decrease the contact pressure between the object and the pulse wave sensor to measure the blood pressure, and may provide the generated guidance information to the user via an output device. For example, the blood pressure measurement device may compare the detected contact pressure signal with a linearly increasing or decreasing target pressure signal; in response to the measured contact pressure signal being greater than the target pressure signal, the blood pressure measurement device may generate guidance information instructing the user to reduce the contact pressure, and in response to the measured contact pressure signal being less than the target pressure signal, the blood pressure measurement device may generate guidance information instructing the user to increase the contact pressure. Then, the blood pressure measurement device may provide the generated guidance information to the user via an output device.

[0159] The blood pressure measurement apparatus may convert the pulse wave signal into an image by performing frequency domain conversion to generate a pulse wave image in operation 1640 , and may convert the contact pressure signal into an image to generate a contact pressure image in operation 1650 .

[0160] The blood pressure measurement apparatus may process the pulse wave image and the contact pressure image so that they may have the same size in operation 1660. For example, the blood pressure measurement apparatus may process the pulse wave image and the contact pressure image so that they may have the same time domain scale.

[0161] The blood pressure measurement apparatus may estimate the blood pressure of the subject by using the pulse wave image, the contact pressure image, and the blood pressure estimation model in operation 1670 .

[0162] Fig.17 is a flowchart showing another example of the blood pressure measurement method according to the embodiment. Fig.17 Blood pressure measurement can be done by Figure 1 The blood pressure measurement device 100 performs. Fig.17 Operations 1710, 1720, 1730, and 1740 may be respectively Fig.15 Operations 1510, 1520, 1530, and 1540 are substantially similar, so a description thereof may be briefly made below.

[0163] Reference Fig.17 , the blood pressure measurement apparatus may detect a pulse wave signal of the subject in operation 1710 , and may detect a contact pressure signal corresponding to a contact pressure between the subject and the pulse wave sensor in operation 1720 .

[0164] The blood pressure measurement apparatus may convert the pulse wave signal into an image by performing frequency domain conversion to generate a pulse wave image in operation 1730 , and may convert the contact pressure signal into an image to generate a contact pressure image in operation 1740 .

[0165] The blood pressure measurement apparatus may perform n-th order differentiation on the pulse wave signal to obtain an n-th order differentiated pulse wave signal in operation 1750 , where n may be a natural number greater than 0.

[0166] The blood pressure measurement apparatus may convert the obtained n-order differential pulse wave signal into an image by performing frequency domain conversion to generate an n-order differential pulse wave image in operation 1760. In one embodiment, the blood pressure measurement apparatus may generate an n-order differential pulse wave image by converting the n-order differential pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

[0167] The blood pressure measurement device may estimate the blood pressure of the subject by using the pulse wave image, the contact pressure image, and the n-order differential pulse wave image and the blood pressure estimation model in operation 1770. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the pulse wave image data, the contact pressure image data, the n-order differential pulse wave image data, and the blood pressure data corresponding thereto as training data.

[0168] Fig.18 is a flowchart showing another example of the blood pressure measurement method according to the embodiment. Fig.18 Blood pressure measurement can be done by Fig. 9 The blood pressure measurement device 900 performs. Fig.18 Operations 1810, 1820, 1830 and 1840 may be respectively Fig.15 Operations 1510, 1520, 1530, and 1540 are substantially similar, so a description thereof may be briefly made below.

[0169] Reference Fig.18 The blood pressure measurement apparatus may detect a pulse wave signal of the subject in operation 1810 , and may detect a contact pressure signal corresponding to a contact pressure between the subject and the pulse wave sensor in operation 1820 .

[0170] The blood pressure measurement apparatus may convert the pulse wave signal into an image by performing frequency domain conversion to generate a pulse wave image in operation 1830 , and may convert the contact pressure signal into an image to generate a contact pressure image in operation 1840 .

[0171] The blood pressure measurement device may obtain a plurality of contact images over time in operation 1850 .

[0172] The blood pressure measurement device may convert the multiple contact images over time into a single contact image representing the change of the contact images over time in operation 1860. For example, the blood pressure measurement device may convert the multiple contact images over time into a single contact image by dividing each contact image into a plurality of parts, arranging the plurality of parts in a predetermined arrangement order to generate an arrangement image of each contact image, and arranging the generated arrangement images of the plurality of contact images in a time series order.

[0173] The blood pressure measurement device may estimate the blood pressure of the subject by using the pulse wave image, the contact pressure image, the single contact image, and the blood pressure estimation model in operation 1870. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the pulse wave image data, the contact pressure image data, the single contact image data, and the blood pressure data corresponding thereto as training data.

[0174] Fig.19 is a flowchart showing another example of the blood pressure measurement method according to the embodiment. Fig.19 Blood pressure measurement can be done by Fig. 9 The blood pressure measurement device 900 performs. Fig.19 Operations 1910, 1920, 1930, 1940, 1950, and 1960 may be respectively Fig.18 The operations 1810, 1820, 1830, 1840, 1850 and 1860 are substantially similar, and Fig.19 Operations 1970 and 1980 can be respectively Fig.17 Operations 1750 and 1760 are substantially similar, so a description thereof may be briefly made below.

[0175] Reference Fig.19 , the blood pressure measurement apparatus may detect a pulse wave signal of the subject in operation 1910 , and may detect a contact pressure signal corresponding to a contact pressure between the subject and the pulse wave sensor in operation 1920 .

[0176] The blood pressure measurement apparatus may convert the pulse wave signal into an image by performing frequency domain conversion to generate a pulse wave image in operation 1930 , and may convert the contact pressure signal into an image to generate a contact pressure image in operation 1940 .

[0177] The blood pressure measurement apparatus may obtain a plurality of contact images over time in operation 1950 , and may convert the plurality of contact images over time into a single contact image representing a change of the contact images over time in operation 1960 .

[0178] The blood pressure measurement apparatus may perform n-th order differentiation on the pulse wave signal to obtain an n-th order differential pulse wave signal in operation 1970 , and may convert the obtained n-th order differential pulse wave signal into an image by performing frequency domain conversion in operation 1980 to generate an n-th order differential pulse wave image.

[0179] The blood pressure measurement device may estimate the blood pressure of the subject by using the pulse wave image, the contact pressure image, the single contact image, the n-order differential pulse wave image, and the blood pressure estimation model in operation 1990. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and by using the pulse wave image data, the contact pressure image data, the single contact image data, the n-order differential pulse wave image data, and the blood pressure data corresponding thereto as training data.

[0180] Fig. 20 is a block diagram showing another example of the blood pressure measurement apparatus according to the embodiment. Fig. 20 The blood pressure measurement apparatus 2000 is an apparatus for non-invasively measuring the blood pressure of a subject, and may be embedded in an electronic device or may be enclosed in a housing to be provided as a separate apparatus.

[0181] Reference Fig. 20 , the blood pressure measurement device 2000 includes a pulse wave sensor 2010, a force sensor 2020, an area sensor 2030, and a processor 2040. Here, the pulse wave sensor 2010 may be connected to Figure 1 The pulse wave sensor 110 is substantially similar, and thus a detailed description thereof may be omitted.

[0182] The force sensor 2020 may detect a contact force signal corresponding to a contact force between the object and the pulse wave sensor 2010. To this end, the force sensor 2020 may include a piezoelectric film, a load sensor, a radar, a strain gauge, or the like.

[0183] The area sensor 2030 may detect a contact area signal corresponding to a contact area between the object and the pulse wave sensor 2010. To this end, the area sensor 2030 may include a contact area sensor (eg, a touch sensor, etc.).

[0184] The processor 2040 may control the overall operation of the blood pressure measurement apparatus 2000 .

[0185] Based on the object contacting the pulse wave sensor 2010, the processor 2040 can control the pulse wave sensor 2010 to detect the pulse wave signal of the object, can control the force sensor 2020 to detect the contact force signal corresponding to the contact force between the object and the pulse wave sensor 2010, and can control the area sensor 2030 to detect the contact area signal corresponding to the contact area between the object and the pulse wave sensor 2010.

[0186] In addition, the processor 2040 may estimate the blood pressure of the subject based on the detected pulse wave signal, the detected contact force signal, and the detected contact area signal. For example, the processor 2040 may convert each of the pulse wave signal, the contact force signal, and the contact area signal into an image to generate a pulse wave image, a contact force image, and a contact area image, respectively, and may estimate the blood pressure of the subject by using the generated pulse wave image, contact force image, and contact area image.

[0187] Fig.21 is a block diagram illustrating an example of a processor according to an embodiment. Fig.21 The processor 2100 may be Fig. 20 An example of processor 2040 .

[0188] Reference Fig.21 , the processor 2100 includes a pulse wave image generator 2110, a contact force image generator 2120, a contact area image generator 2130, a guide information generator 2140, and a blood pressure estimator 2150. Here, the pulse wave image generator 2110 may be connected to Figure 2 The pulse wave image generator 210 is substantially similar, and thus a detailed description thereof may be omitted.

[0189] The contact force image generator 2120 can generate a contact force image by converting a contact force signal into an image. The contact force signal can be a non-periodic signal having an intensity that contains important information. In one embodiment, the contact force image generator 2120 can generate a contact force image by converting a contact force signal into a gradient image. In this case, the generated contact force image can be represented in the time domain. That is, one axis (e.g., the horizontal axis or the vertical axis) of the contact force image can represent a time domain that reflects physical properties with respect to time.

[0190] The contact area image generator 2130 can generate a contact area image by converting the contact area signal into an image. The contact area signal can be a non-periodic signal with an intensity containing important information. In one embodiment, the contact area image generator 2130 can generate a contact area image by converting the contact area signal into a gradient image. In this case, the generated contact area image can be represented in the time domain. That is, one axis (e.g., the horizontal axis or the vertical axis) of the contact area image can represent the time domain reflecting the physical characteristics with respect to time.

[0191] The guide information generator 2140 may obtain a contact pressure signal based on the detected contact force signal and the detected contact area signal; based on the obtained contact pressure signal, the guide information generator 2140 may generate guide information instructing the user to increase or decrease the contact pressure between the object and the pulse wave sensor to measure the blood pressure, and may provide the generated guide information to the user via an output device. For example, the guide information generator 230 may obtain the contact pressure signal by dividing the contact force signal by the contact area signal. In addition, the guide information generator 2140 may compare the obtained contact pressure signal with a linearly increasing or decreasing target pressure signal; in response to the obtained contact pressure signal being greater than the target pressure signal, the guide information generator 2140 may generate guide information instructing the user to reduce the contact pressure, and in response to the measured contact pressure signal being less than the target pressure signal, the guide information generator 2140 may generate guide information instructing the user to increase the contact pressure. Then, the guide information generator 2140 may provide the generated guide information to the user via an output device. In this case, examples of the output device may include various output devices such as a visual output device, an audio output device, a tactile output device, and the like.

[0192] The blood pressure estimator 2150 may estimate the blood pressure of the subject based on the pulse wave image, the contact force image, and the contact area image. In this case, the blood pressure estimator 2150 may use a pre-generated blood pressure estimation model. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using pulse wave image data, contact force image data, contact area image data, and blood pressure data corresponding thereto as training data, and may be stored in an internal memory or an external memory of the processor 2100.

[0193] In one embodiment, before estimating the blood pressure, the blood pressure estimator 2150 may process the pulse wave image, the contact force image, and the contact area image so that the pulse wave image, the contact force image, and the contact area image may have the same size. For example, the blood pressure estimator 2150 may process the pulse wave image, the contact force image, and the contact area image so that the pulse wave image, the contact force image, and the contact area image may have the same time domain scale.

[0194] Fig. 22 is a flowchart showing another example of the blood pressure measurement method according to the embodiment. Fig. 22 Blood pressure measurement can be done by Fig. 20 The blood pressure measurement device 2000 performs. Fig. 22 Operations 2210 and 2240 may be respectively Fig.15 Operations 1510 and 1530 are substantially similar, so a description thereof may be briefly made below.

[0195] Reference Fig. 22The blood pressure measurement device may detect a pulse wave signal of the object in operation 2210, may detect a contact force signal corresponding to a contact force between the object and the pulse wave sensor in operation 2220, and may detect a contact area signal corresponding to a contact area between the object and the pulse wave sensor in operation 2230.

[0196] The blood pressure measurement apparatus may convert the pulse wave signal into an image by performing frequency domain conversion to generate a pulse wave image in operation 2240 .

[0197] The blood pressure measurement apparatus may convert the contact force signal into an image to generate a contact force image in operation 2250. In one embodiment, the blood pressure measurement apparatus may generate a contact area image by converting the contact force signal into a gradient image.

[0198] The blood pressure measurement apparatus may convert the contact area signal into an image to generate a contact area image in operation 2260. In one embodiment, the blood pressure measurement apparatus may generate the contact area image by converting the contact area signal into a gradient image.

[0199] The blood pressure measurement device may estimate the blood pressure of the subject based on the pulse wave image, the contact force image, the contact area image, and the blood pressure estimation model in operation 2270. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the pulse wave image data, the contact force image data, the contact area image data, and the blood pressure data corresponding thereto as training data.

[0200] although Figures 1 to 22 This is an example of estimating blood pressure using a pulse wave signal, a contact pressure signal, an n-order differential pulse wave signal, a contact image over time, a contact force signal, and / or a contact area signal, but estimating blood pressure is not limited thereto. That is, blood pressure can also be estimated by using a non-periodic signal reflecting the physical characteristics of the user (such as the temperature of the object or the measurement environment), etc.

[0201] Fig.23 is a block diagram showing another example of the blood pressure measurement apparatus according to the embodiment.

[0202] Reference Fig.23 , the blood pressure measurement device 2300 includes a cuff 2310 , a pressure sensor 2320 , a signal extractor 2330 and a processor 2340 .

[0203] The cuff 2310 (e.g., a blood pressure cuff) can be wrapped around the subject to apply pressure to the subject. Specifically, the cuff 2310 is placed around the subject's upper arm and is inflated to a pressure higher than the systolic pressure according to a predetermined control signal to tighten blood vessels near the upper arm, and then the pressure applied to the subject is gradually reduced.

[0204] The pressure sensor 2320 can detect the cuff pressure signal.

[0205] The signal extractor 2330 may extract an alternating current (AC) component signal and a direct current (DC) component signal from the measured cuff pressure signal. To this end, the signal extractor 2330 may include various filters (such as a high-pass filter, a low-pass filter, etc.).

[0206] The processor 2340 may control the overall operation of the blood pressure measurement device 2300 .

[0207] Based on the cuff 2310 being placed around the object, the processor 2340 may control the cuff 2310 to apply pressure to the object, and may control the pressure sensor 2320 to detect the cuff pressure signal. In addition, the processor 2340 may control the signal extractor 2330 to extract the AC component signal and the DC component signal from the detected cuff pressure signal.

[0208] The processor 2340 may estimate the blood pressure of the subject based on the extracted AC component signal and DC component signal. For example, the processor 2340 may convert each of the AC component signal and the DC component signal into an image to generate an AC component image and a DC component image, and may estimate the blood pressure of the subject by using the generated AC component image and the DC component image.

[0209] In the following, reference will be made to Fig.24 Processor 2340 is described in detail.

[0210] Fig.24 is a block diagram illustrating an example of a processor according to an embodiment. Fig.24 The processor 2400 may be Fig.23 An example of a processor 2340.

[0211] Reference Fig.24 , the processor 2400 includes an AC component image generator 2410, a DC component image generator 2420 and a blood pressure estimator 2430.

[0212] The AC component image generator 2410 may convert the AC component signal into an image by performing frequency domain conversion to generate an AC component image. The AC component signal may be a periodic signal having a shape containing important information. In one embodiment, the AC component image generator 2410 may generate an AC component image by converting the AC component signal into an image using at least one of a wavelet transform, a short-time Fourier transform, and a Wigner-Wille distribution. In this case, the generated AC component image may be represented in the time domain and the frequency domain. That is, the horizontal axis of the AC component image represents the time domain reflecting the physical characteristics of time; and the vertical axis of the AC component image represents the frequency domain reflecting the physical characteristics of frequency. However, the AC component image is not limited thereto, and the horizontal axis may represent the frequency domain reflecting the physical characteristics of frequency, and the vertical axis may represent the time domain reflecting the physical characteristics of time.

[0213] The DC component image generator 2420 can generate a DC component image by converting a DC component signal into an image. The DC component signal can be a non-periodic signal having an intensity containing important information. In one embodiment, the DC component image generator 2420 can generate a DC component image by converting a DC component signal into a gradient image. In this case, the generated DC component image can be represented in the time domain. That is, one axis (e.g., the horizontal axis or the vertical axis) of the DC component image can represent the time domain reflecting the physical characteristics about time.

[0214] The blood pressure estimator 2430 may estimate the blood pressure of the subject based on the AC component image and the DC component image. In this case, the blood pressure estimator 2430 may use a pre-generated blood pressure estimation model. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the AC component image data, the DC component image data, and the blood pressure data corresponding thereto as training data, and may be stored in an internal memory or an external memory of the processor 2400.

[0215] Fig.25 is a flowchart showing another example of the blood pressure measurement method according to the embodiment. Fig.25 Blood pressure measurement can be done by Fig.23 The blood pressure measurement device 2300 performs.

[0216] Reference Fig.25 In operation 2510 , the blood pressure measurement device may detect a cuff pressure signal based on placement of the cuff around the subject.

[0217] In operation 2520 , the blood pressure measurement apparatus may extract an AC component signal and a DC component signal from the measured cuff pressure signal.

[0218] In operation 2530, the blood pressure measurement apparatus may convert the AC component signal into an image by performing frequency domain conversion to generate an AC component image. In one embodiment, the blood pressure measurement apparatus may generate an AC component image by converting the AC component signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

[0219] In operation 2540, the blood pressure measurement apparatus may generate a DC component image by converting the DC component signal into an image. In one embodiment, the blood pressure measurement apparatus may generate a DC component image by converting the DC component signal into a gradient image.

[0220] In operation 2550, the blood pressure measurement device may estimate the blood pressure of the subject by using the AC component image, the DC component image, and a blood pressure estimation model. The blood pressure estimation model may be a model pre-generated by machine learning based on a convolutional neural network and using the AC component image data, the DC component image data, and the blood pressure data corresponding thereto as training data.

[0221] The present disclosure may be implemented as a computer-readable code stored on a non-transitory computer-readable medium. A computer-readable medium may be any type of recording device in which data is stored in a computer-readable manner. Examples of computer-readable media may include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and carrier wave (e.g., data transmission over the Internet). The computer-readable medium may be distributed via a plurality of computer systems connected to a network so that the computer-readable code is written to the computer-readable medium in a decentralized manner and executed from the computer-readable medium. Functional programs, codes, and code segments for implementing the present disclosure may be derived by those of ordinary skill in the art.

[0222] The present disclosure has been described herein with respect to preferred embodiments. However, it will be apparent to those skilled in the art that various changes and modifications may be made without departing from the scope of the present disclosure. Therefore, it is clear that the above embodiments are illustrative in all aspects and are not intended to limit the present disclosure.

Claims

1. A blood pressure measuring device, comprising: a pulse wave sensor configured to detect a pulse wave signal of a subject; a pressure sensor configured to detect a contact pressure signal corresponding to a contact pressure between the object and the pulse wave sensor; as well as a processor configured to: generate a pulse wave image based on a detected pulse wave signal of the object; generate a contact pressure image based on a detected contact pressure signal corresponding to a contact pressure between the object and the pulse wave sensor, The blood pressure measurement device further comprises: a contact image sensor configured to obtain a plurality of contact images of the object over time, The processor is further configured to: converting the plurality of contact images obtained over time into a single contact image representing changes in the contact images over time, and estimating the blood pressure of the subject based on the generated pulse wave image, the generated contact pressure image, and the single contact image, Wherein, the processor is configured to: divide the contact image at each time into multiple parts, arrange the multiple parts in a predetermined arrangement order to generate an arrangement image of the contact image at each time, and arrange the generated arrangement image of the multiple contact images in a time series order to convert the multiple contact images over time into the single contact image.

2. The blood pressure measuring device according to claim 1, wherein: The pulse wave signal is a photoplethysmographic signal.

3. The blood pressure measuring device according to claim 1, wherein: The pulse wave sensor is also configured to: Detect multiple pulse wave signals of different wavelengths.

4. The blood pressure measuring device according to claim 1, wherein: The pressure sensor is also configured to: detecting a contact force signal and a contact area signal corresponding to a contact force and a contact area, respectively, between the object and the pulse wave sensor; and A contact pressure signal is obtained based on the contact force signal and the contact area signal.

5. The blood pressure measuring device according to claim 1, wherein: The processor is also configured to: The pulse wave image is generated by converting the pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

6. The blood pressure measuring device according to claim 1, wherein: The processor is also configured to: A contact pressure image is generated by converting the detected contact pressure signal into a gradient image.

7. The blood pressure measuring device according to claim 1, wherein: The processor is also configured to: The pulse wave image and the contact pressure image are processed so that the pulse wave image and the contact pressure image have the same time domain scale.

8. The blood pressure measuring device according to claim 1, in, The processor is configured to estimate the blood pressure of the subject based on the generated pulse wave image, the generated contact pressure image, the single contact image, and a blood pressure estimation model, Among them, the blood pressure estimation model is a model based on convolutional neural network.

9. The blood pressure measuring device according to claim 8, wherein: A blood pressure estimation model is generated by machine learning based on training data; and The training data includes pulse wave image data, contact pressure image data, single contact image data, and blood pressure data corresponding to the pulse wave image data, the single contact image data, and the contact pressure image data.

10. The blood pressure measurement device according to claim 1, wherein: The processor is also configured to: performing n-th order differentiation on the detected pulse wave signal to obtain an n-th order differentiated pulse wave signal; converting the obtained n-order differential pulse wave signal into an image to generate an n-order differential pulse wave image; and estimating the blood pressure of the subject based on the pulse wave image, the contact pressure image, the single contact image, and the generated n-order differential pulse wave image, Wherein, n is a natural number greater than 0.

11. The blood pressure measuring device according to claim 1, wherein: The processor is also configured to: generating guidance information instructing a user to increase or decrease the contact pressure between the object and the pulse wave sensor based on the detected contact pressure signal; and The generated guidance information is provided to the user via the output device.

12. A computer-readable storage medium storing a program, wherein: When the program is executed by a processor, the processor is caused to perform a process, the process comprising: detecting a pulse wave signal of a subject; detecting a contact pressure signal corresponding to a contact pressure between the object and the pulse wave sensor; generating a pulse wave image based on the detected pulse wave signal; generating a contact pressure image based on the detected contact pressure signal; obtaining a plurality of contact images of the object over time; converting the plurality of contact images obtained over time into a single contact image representing changes in the contact images over time; and estimating the blood pressure of the subject based on the generated pulse wave image, the generated contact pressure image, the single contact image, and a blood pressure estimation model, Among them, the process of converting the multiple contact images obtained over time into a single contact image representing the change of the contact images over time includes: dividing the contact image at each time into multiple parts, arranging the multiple parts in a predetermined arrangement order to generate an arrangement image of the contact image at each time, and arranging the generated arrangement image of the multiple contact images in a time series order.

13. The computer-readable storage medium of claim 12, wherein: The pulse wave signal is a photoplethysmographic signal.

14. The computer-readable storage medium of claim 12, wherein: The step of detecting the pulse wave signal also includes: Detect multiple pulse wave signals of different wavelengths.

15. The computer-readable storage medium of claim 12, wherein: The step of detecting the contact pressure signal also includes: detecting a contact force signal corresponding to a contact force between the object and the pulse wave sensor; detecting a contact area signal corresponding to a contact area between the subject and the pulse wave sensor; and A contact pressure signal is obtained based on the contact force signal and the contact area signal.

16. The computer-readable storage medium of claim 12, wherein: The step of generating a pulse wave image also includes: A pulse wave image is generated by converting the detected pulse wave signal into an image using at least one of wavelet transform, short-time Fourier transform, and Wigner-Ville distribution.

17. The computer-readable storage medium of claim 12, wherein: The step of generating a contact pressure image further includes: A contact pressure image is generated by converting the detected contact pressure signal into a gradient image.

18. The computer-readable storage medium of claim 12, wherein: The processing also includes: The pulse wave image and the contact pressure image are processed so that the pulse wave image and the contact pressure image have the same time domain scale.

19. The computer-readable storage medium of claim 12, wherein: The blood pressure estimation model is based on a convolutional neural network.

20. The computer-readable storage medium of claim 12, wherein: A blood pressure estimation model is generated by machine learning based on training data; and The training data includes pulse wave image data, contact pressure image data, single contact image data, and blood pressure data corresponding to the pulse wave image data, the single contact image data, and the contact pressure image data.

21. The computer-readable storage medium of claim 12, wherein: The processing also includes: performing n-th order differentiation on the detected pulse wave signal to obtain an n-th order differentiated pulse wave signal; and The obtained n-order differential pulse wave signal is converted into an image to generate an n-order differential pulse wave image, The step of estimating the blood pressure further comprises: estimating the blood pressure of the subject based on the pulse wave image, the contact pressure image, the single contact image and the generated n-order differential pulse wave image, and Wherein, n is a natural number greater than 0.

22. The computer-readable storage medium of claim 12, wherein: The processing also includes: generating, based on the detected contact pressure signal, guide information for instructing a user to increase or decrease the contact pressure between the object and the pulse wave sensor; and The generated guidance information is provided to the user.

23. A computer-readable storage medium storing a program, wherein: When the program is executed by a processor, the processor is caused to perform the following processing: obtaining a pulse wave image corresponding to a pulse wave of the subject detected by the sensor; obtaining a contact pressure image corresponding to the contact pressure between the sensor and the object; obtaining a plurality of contact images of the object over time; converting the plurality of contact images obtained over time into a single contact image representing changes in the contact images over time; inputting the pulse wave image, the single contact image and the contact pressure image into the model; as well as Identify the subject’s blood pressure based on the output of the model, Among them, the process of converting the multiple contact images obtained over time into a single contact image representing the change of the contact images over time includes: dividing the contact image at each time into multiple parts, arranging the multiple parts in a predetermined arrangement order to generate an arrangement image of the contact image at each time, and arranging the generated arrangement image of the multiple contact images in a time series order.

Images