Blood pressure measurement device, mode setting device, and recording medium

Abstract

The blood pressure of a living body is measured more accurately than in the prior art. A blood pressure measurement device measures a first blood pressure of a subject living body. In a blood pressure measurement device, a body movement classification section classifies the movement direction of a predetermined region in the body surface of a subject organism. The blood pressure measurement device is communicably connected to the mode storage unit. In a pattern storage unit, (i) a plurality of blood pressure estimation patterns for estimating a first blood pressure according to a classification result of a movement direction and (i i) an evaluation result for each of the plurality of blood pressure estimation patterns according to the classification result of the movement direction are stored in advance. The mode selection unit selects a measurement mode from among the plurality of blood pressure estimation modes on the basis of each evaluation result of the plurality of blood pressure estimation modes. The blood pressure measurement unit calculates a first blood pressure based on the pulse parameter using the measurement mode.

Description

Technical Field

[0001] One aspect of the present disclosure is a blood pressure measuring device for measuring the blood pressure of a living being based on the pulse of the living being. This application claims priority to Japanese Patent Application No. 2019-1951 filed in Japan on January 9, 2019, the contents of which are incorporated herein by reference. Background Art

[0002] In recent years, various technologies for measuring biological information of a living organism (target organism) have been proposed. As an example, Patent Document 1 discloses a technology for measuring a predetermined type of biological information (e.g., pulse rate) of a target organism with high accuracy based on an image (photographic image) of the face of the target organism. Specifically, one purpose of the technology of Patent Document 1 is to measure the pulse rate with high accuracy even when the face of the target organism moves. Prior art literature Patent Literature

[0003] Patent Document 1: Japanese Patent Application Publication No. 2017-93760 Summary of the invention Technical Problems to be Solved by the Invention

[0004] However, Patent Document 1 does not particularly describe a specific method for measuring the blood pressure of a living body (another example of living body information) with high accuracy. An aspect of the present disclosure aims to measure the blood pressure of a living body with higher accuracy than conventional methods. Means of solving the problem

[0005] In order to solve the above-mentioned problem, a blood pressure measurement device according to one aspect of the present disclosure measures a first blood pressure of a living body based on a pulse of the living body, wherein the blood pressure measurement device comprises: a pulse acquisition unit for acquiring a pulse in a specified area on the body surface of the living body; a body movement detection unit for detecting a moving direction of the specified area; a body movement classification unit for classifying the moving direction; and a pulse parameter calculation unit for calculating a plurality of pulse parameters based on the pulse, wherein the blood pressure measurement device is communicatively connected to a pattern storage unit, wherein the pattern storage unit stores in advance the following patterns and results: (i) a plurality of blood pressure estimation patterns for estimating the first blood pressure based on the classification result of the moving direction, and (ii) an evaluation result of each of the plurality of blood pressure estimation patterns based on the classification result of the moving direction, wherein the blood pressure measurement device further comprises: a pattern selection unit for selecting a measurement pattern for calculating the first blood pressure from the plurality of blood pressure estimation patterns based on the evaluation result of each of the plurality of blood pressure estimation patterns; and a first blood pressure measurement unit for calculating the first blood pressure based on the plurality of pulse parameters using the measurement pattern.

[0006] In order to solve the above-mentioned problem, a mode setting device involved in one aspect of the present disclosure is communicatively connected to a blood pressure measurement device, wherein the blood pressure measurement device measures a first blood pressure of the living body based on the pulse of the living body, and the mode setting device is characterized in that it comprises: a second blood pressure measurement unit that measures the second blood pressure of the living body; a pulse acquisition unit that acquires the pulse in a specified area on the body surface of the living body; a body movement detection unit that detects the moving direction of the specified area; a body movement classification unit that classifies the moving direction; and a pulse parameter calculation unit that calculates a plurality of pulse parameters based on the pulse, wherein the mode setting device is communicatively connected to a mode storage unit, and the mode setting device further comprises: a mode creation unit that creates a plurality of blood pressure estimation modes for estimating the first blood pressure based on the plurality of pulse parameters and the second blood pressure according to the classification result of the moving direction, and stores the plurality of blood pressure estimation modes in the mode storage unit; and a mode evaluation unit that evaluates each of the plurality of blood pressure estimation modes stored in the mode storage unit according to the classification result of the moving direction, and stores the evaluation result in the mode storage unit.

[0007] In order to solve the above-mentioned problem, a blood pressure measurement method involved in one form of the present disclosure measures a first blood pressure of a living body based on the pulse of the living body, and the blood pressure measurement method is characterized in that it includes: a pulse acquisition step of acquiring a pulse in a specified area on the body surface of the living body; a body movement detection step of detecting the moving direction of the specified area; a body movement classification step of classifying the moving direction; and a pulse parameter calculation step of calculating a plurality of pulse parameters based on the pulse, wherein the blood pressure measurement device is communicatively connected to a mode storage unit, and the mode storage unit pre-stores the following modes and results: (i) a plurality of blood pressure estimation modes for estimating the first blood pressure based on the classification result of the moving direction, and (ii) an evaluation result of each of the plurality of blood pressure estimation modes based on the classification result of the moving direction, and the blood pressure measurement method further includes: a mode selection step of selecting a measurement mode for calculating the first blood pressure from the plurality of blood pressure estimation modes based on the evaluation result of each of the plurality of blood pressure estimation modes; and a first blood pressure measurement step of calculating the first blood pressure based on the plurality of pulse parameters using the measurement mode. Effects of the Invention

[0008] According to the blood pressure measuring device involved in one form of the present disclosure, the blood pressure of a living being can be measured with higher accuracy than before. The blood pressure measuring method involved in one form of the present disclosure also has the same effect. In addition, the mode setting device involved in one form of the present disclosure also has the same effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1This is a functional block diagram showing the configuration of the main parts of the blood pressure measurement device according to the first embodiment. Figure 2 This is a diagram for explaining an example of processing by the face image segmentation unit. Figure 3 This is a diagram for explaining another example of the processing of the face image segmentation unit. Figure 4 This is a diagram for explaining an example of a process of extracting the rear part of the measurement pattern. Figure 5 This is a diagram showing an example of a face direction template. Figure 6 It is shown Figure 1 A diagram showing an example of a process flow of a measurement pattern creation method in a blood pressure measurement device. Figure 7 It is shown Figure 1 A diagram showing an example of a process flow of a blood pressure measurement method in a blood pressure measurement device. DETAILED DESCRIPTION

[0010] [Implementation Method 1] The following describes the blood pressure measurement device 1 of the first embodiment. For the sake of convenience, the components having the same functions as the components described in the first embodiment are given the same reference numerals in the subsequent embodiments, and their descriptions are omitted. The same matters as those in the known technology are also appropriately omitted. In addition, for the sake of convenience, the device configuration shown in each figure is only an example. In addition, the numerical values ​​described below in the specification are also only an example.

[0011] (Overview of Blood Pressure Measurement Device 1) Figure 1 : is a functional block diagram showing the configuration of the main parts of the blood pressure measurement device 1. The blood pressure measurement device 1 measures the blood pressure (hereinafter, simply referred to as blood pressure) of the target organism H (organism) based on the pulse of the target organism H. Specifically, the blood pressure measurement device 1 measures the blood pressure using the blood pressure measurement mode (hereinafter, also simply referred to as "measurement mode") set in the mode setting device 100 described below. In addition, in this embodiment, the blood pressure estimation mode described later is also simply referred to as "estimation mode". In addition, sometimes the measurement mode and the estimation mode are collectively referred to as just "mode".

[0012] In the following description, a blood pressure measuring device 1 is described as a non-contact blood pressure measuring device (a measuring device that can measure blood pressure without contacting a target organism H). In the first embodiment, the case where the target organism H is a human is exemplified. The blood pressure measuring device 1 measures blood pressure by treating a predetermined region on the body surface of the target organism H as a ROI (Region of In terest). In the following description, the case where the ROI is a face is exemplified. In addition, in this description, the face of the target organism H is also simply referred to as "face". The same applies to other notations.

[0013] The blood pressure measurement device 1 includes a mode setting device 100, a mode selection unit 60, a blood pressure measurement unit 160 (a first blood pressure measurement unit), and a blood pressure measurement result output unit 170. The mode setting device 100 includes a blood pressure acquisition unit 2 (a second blood pressure measurement unit), a pulse acquisition unit 10, a pulse parameter calculation unit 20, a body movement detection unit 21, a body movement classification unit 22, a pattern creation unit 30, a pattern evaluation unit 40, and a pattern storage unit 50.

[0014] exist Figure 1 In the example of FIG. 1 , the mode setting device 100 is provided inside the blood pressure measurement device 1. However, the mode setting device 100 may also be provided outside the blood pressure measurement device 1 (see Embodiment 2 described later).

[0015] The blood pressure acquisition unit 2 measures the blood pressure of the subject organism H. The blood pressure acquisition unit 2 is a contact-type blood pressure meter (e.g., a cuff blood pressure meter). The blood pressure (hereinafter, BPm) measured by the blood pressure acquisition unit 2 is used as test data (training data) in the mode setting device 100. That is, BPm is used to set the measurement mode in the mode selection unit 60. In addition, BPm is also used to set a plurality of estimation modes in the mode creation unit 30.

[0016] The blood pressure acquisition unit 2 outputs BPm to the pattern preparation unit 30 and the pattern evaluation unit 40 (more specifically, the pattern evaluation index calculation unit 42 described below). In addition, the final blood pressure measurement result (P described below) in the blood pressure measurement device 1 is also referred to as the first blood pressure. In addition, in order to distinguish it from the first blood pressure, BPm is also referred to as the second blood pressure. As described later, P is measured (calculated) by the blood pressure measurement unit 160. Therefore, BPm can also be expressed as training data for measuring P by the blood pressure measurement device 1.

[0017] (Pulse acquisition unit 10) The pulse acquisition unit 10 acquires the pulse in the ROI (eg, face) and includes an imaging unit 11 , a light source 12 , a light source adjustment unit 13 , a face image acquisition unit 14 , a face image segmentation unit 15 , a skin region extraction unit 16 , and a pulse calculation unit 17 .

[0018] The imaging unit 11 is a camera including an image sensor and a lens. As the image sensor, for example, a CMOS (Complementary Metal-Oxide Semiconductor) type or a CCD (Charge-Coupled Device) type image sensor may be used. The imaging unit 11 images the subject organism H several times at a predetermined frame rate (i.e., at each predetermined time interval), and outputs the image of the subject organism H that has been imaged (hereinafter, the subject organism image) to the face image acquisition unit 14. As an example, the frame rate is 300 fps (frames per second).

[0019] The imaging unit 11 may include a known color filter. The color filter preferably has optical characteristics suitable for observing the increase or decrease of the blood volume. Examples of suitable color filters include (i) RGBCy (Red, Blue, Green, Cyan), (ii) RGBIR (Red, Blue, Green, Infrared). In addition, the imaging unit 11 may be an RGB camera or an IR camera.

[0020] The light source 12 irradiates light to the target organism H when the imaging unit 11 is imaging the target organism H. The light source adjustment unit 13 adjusts the light source 12. As an example, the light source adjustment unit 13 preferably adjusts the light source so as to accurately calculate the pulse propagation time (a column of pulse parameters) between the regions used in the measurement mode selected by the mode selection unit 60.

[0021] Specifically, the light source adjustment unit 13 adjusts the light source 12 in such a manner that a pulse having a fixed signal quality in a corresponding area can be detected. "A pulse having a fixed signal quality" refers to, for example, a "pulse having a high SNR (Signal-to-Noise Ratio)". More specifically, the light source adjustment unit 13 adjusts at least one of (i) the light intensity of the light source 12, (ii) the spectrum of the light source 12, and (iii) the irradiation angle of the target organism H to the skin.

[0022] The light source 12 and the light source adjustment unit 13 are not necessarily provided in the pulse acquisition unit 10. When the light source 12 and the light source adjustment unit 13 are not provided, the imaging unit 11 may image the target living being H using only the ambient light.

[0023] The face image acquisition unit 14 extracts the face region of the target living being H from the image of the target living being captured by the imaging unit 11. The face image acquisition unit 14 acquires the image after the face region is extracted as a face image (an image reflecting the face of the target living being H). As an example, the face image acquisition unit 14 may perform face tracking on a moving image (a moving image composed of a plurality of images of the target living being) reflecting the target living being, and extract the face region at each predetermined frame interval of the moving image.

[0024] However, the face image acquisition unit 14 does not necessarily need to perform face tracking, and can also extract the face area. For example, (i) the face of the target organism H may be placed in a preset frame, and (ii) the image of the target organism may be captured by the image capture unit 11 while the face and the image capture unit 11 are fixed. In such a case, since the shaking of the face in the image of the target organism can be suppressed, face tracking is not required.

[0025] The face image segmentation unit 15 segments the face image extracted by the face image acquisition unit 14 into a plurality of regions (partial regions). In the following description, for convenience of explanation, the face image is also referred to as "IMG". Figure 2 This is a diagram for explaining an example of processing by the face image segmentation unit 15 . Figure 2 An example of IMG after segmentation by the face image segmentation unit 15 is shown. Figure 2 IMG is an example of a face image reflecting a face facing forward.

[0026] exist Figure 2 In the example, the face image segmentation unit 15 segments the IMG into 10 segments in the vertical direction and the horizontal direction (e.g., 10 equal segments each). That is, the face image segmentation unit 15 segments the IMG into 100 partial regions (partial regions 1 to 100). However, the segmentation method of the IMG by the face image segmentation unit 15 is not limited to Figure 2 For example, the sizes of the various partial areas do not necessarily need to be the same.

[0027] Before explaining other parts of the pulse acquisition unit 10, the operation of the body movement detection unit 21 will be described. The body movement detection unit 21 detects the body movement of the target organism H. Specifically, the body movement detection unit 21 detects the movement of the ROI (e.g., face). More specifically, the body movement detection unit 21 detects the movement direction of the ROI. As an example, the body movement detection unit 21 uses the result of face tracking by the face image acquisition unit 14 to detect the movement amount of each feature point (e.g., eyes, nose, mouth, or outline) of the face in the moving image.

[0028] Specifically, the body movement detection unit 21 detects the position change (movement amount) of each feature point at each predetermined frame interval. In other words, the body movement detection unit 21 detects "how much each feature point has moved in which direction" at each predetermined frame interval. The body movement detection unit 21 further detects the movement direction of the face based on the above movement amount. In addition, the body movement detection unit 21 further detects the orientation of the face at that moment based on the above movement amount.

[0029] As described later, a plurality of predetermined patterns are pre-set regarding the movement direction of the ROI (e.g., the orientation of the face) in the mode setting device 100. As described in detail below, the body motion classification unit 22 specifies which of the predetermined patterns the orientation of the face detected by the body motion detection unit 21 belongs to (corresponds to).

[0030] Figure 3 2 is a diagram for explaining another example of the processing of the face image segmentation unit 15. The face image segmentation unit 15 can segment the IMG further based on the result of the pattern classification by the body movement classification unit 22. Figure 3 The IMGA of FIG. 1 is another example of a face image showing a face facing forward. The body motion classification unit 22 determines whether the face direction in the IMGA corresponds to the face direction described later. Figure 5 of “Pattern 1”.

[0031] exist Figure 3 In the example, the segmentation method of IMGA is different from Figure 2 The example is the same. But for the sake of illustration, Figure 3 In the example, IMGA is divided into 25 parts (partial areas A1 to A25). Figure 3 In the figure, for the sake of simplicity of illustration, only a part of A1 to A25 is shown with reference numerals. This also applies to the partial areas B1 to B25 (partial areas of IMGB) described below.

[0032] Figure 3 IMGB in FIG. 1 is an example of a face image facing downward to the right. Hereinafter, the time when IMGA is captured is referred to as time A, and the time when IMGB is captured is referred to as time B. In this example, time B is a time after time A. The body motion classification unit 22 determines that the direction of the face in IMG2 corresponds to Figure 5 "Pattern 7".

[0033] The face image segmentation unit 15 segments a face image of another pattern (e.g., face image of pattern 7, i.e., IMGB) based on the segmentation result of the face image of a certain pattern (e.g., face image of pattern 1, i.e., IMGA). Specifically, the face image segmentation unit 15 segments IMGB so that each sub-region (B1 to B25) of IMGB corresponds to each sub-region (A1 to A25) of IMGA. Figure 3In the example of , B1 and B25 correspond to A1 and A25 respectively.

[0034] By dividing the face image in this way, approximately the same part can be displayed by (i) a certain partial area at time A (before the body movement of the subject organism H occurs) and (ii) a partial area corresponding to the certain partial area at time B (after the body movement of the subject organism H occurs). Figure 3 In the example of , A12 and B12 are partial areas of one eye (eg, left eye) of the object creature H. In addition, A18 and B18 are partial areas of the mouth of the object creature H.

[0035] The skin region extraction unit 16 extracts a skin region (at least a portion of the skin is reflected) from each partial region. The skin region can also be expressed as a region where the skin is not completely covered by a covering (eg, hair). Figure 2 In the example shown in FIG. 1 , the skin area is displayed as an area without a texture in each partial area. Figure 2 In the example of , the skin region extraction unit 16 extracts 52 (52 positions) skin regions from 100 partial regions.

[0036] The pulse calculation unit 17 calculates the pulse (more strictly speaking, the pulse signal) for each skin area extracted by the skin area extraction unit 16. As a method for calculating the pulse in the pulse calculation unit 17, a known method (for example, a method using independent component analysis) may be applied. The pulse calculation unit 17 supplies the calculated pulse to the pulse parameter calculation unit 20.

[0037] The pulse parameter calculation unit 20 calculates the pulse parameter based on the pulse of each skin area obtained from the pulse calculation unit 17. In this specification, "pulse parameter" generally refers to explanatory variables (also called independent variables) used in the measurement (calculation) of blood pressure in the measurement mode.

[0038] In the first embodiment, the case where the pulse transit time (PTT) between the skin regions is used as a pulse parameter is illustrated. In this case, the pulse parameter calculation unit 20 calculates the PTT based on the pulse of each skin region using a known method. In addition, the PTT between region A (an arbitrary skin region) and region B (another skin region with region A) is also expressed as PTT (AB). For example, Figure 2 The PTT between regions 23 and 24 is expressed as PTT (23-24).

[0039] exist Figure 2In the example of , the pulse parameter calculation unit 20 selects a combination of any two skin regions from the 52 skin regions. That is, the pulse parameter calculation unit 20 selects a total of 52 C2=1326 combinations. Then, the pulse parameter calculation unit 20 calculates PTT for each combination. In this way, the pulse parameter calculation unit 20 calculates 1326 types of PTT, namely, PTT (23-24) to PTT (96-97). The pulse parameter calculation unit 20 supplies each calculated PTT (pulse parameter) to each of the pattern preparation unit 30, the evaluation predicted blood pressure calculation unit 41, and the blood pressure measurement unit 160.

[0040] (Pattern creation unit 30) The pattern creation unit 30 creates a blood pressure estimation pattern (estimation pattern). The estimation pattern refers to a calculation pattern for estimating the blood pressure (P) of the subject organism H. Specifically, the pattern creation unit 30 creates the estimation pattern by using (i) the pulse parameter (PTT) calculated by the pulse parameter calculation unit 20 and (ii) the blood pressure (BPm) of the subject organism H acquired by the blood pressure acquisition unit 2 as test data.

[0041] In addition, if Figure 1 As shown, the pattern creation unit 30 includes a first pattern creation unit 300-1, a second pattern creation unit 300-2, ..., and an N-th pattern creation unit 300-N. N is the number of classification patterns preset for the orientation of the face. N is an arbitrary integer greater than 2. The k-th pattern creation unit 300-k creates an estimated pattern based on pattern k. k is an integer satisfying 1≦k≦N. In this way, the pattern creation unit 30 can create estimated patterns for each pattern according to the orientation of the face.

[0042] In this specification, for convenience, the first mode creation unit 300-1 to the Nth mode creation unit 300-N are collectively referred to as the mode creation unit 30. The description of the mode creation unit 30 is applicable to any kth mode creation unit 300-k. By the same token, in this specification, the first mode evaluation predicted blood pressure calculation unit 410-1 to the Nth mode evaluation predicted blood pressure calculation unit 410-N described later are collectively referred to as the evaluation predicted blood pressure calculation unit 41. In addition, the first mode evaluation index calculation unit 420-1 to the Nth mode evaluation index calculation unit 420-N described later are collectively referred to as the mode evaluation index calculation unit 42. In addition, the first mode selection unit 600-1 to the Nth mode selection unit 600-N described later are collectively referred to as the mode selection unit 60.

[0043] (An example of a method for creating an estimation pattern) The velocity v of the pulse propagating in the blood vessel is expressed by the Moens-Korteg formula, that is, the following formula.

[0044] [Number 1]

[0045] In formula (1), E is the elastic modulus of the blood vessel, a is the blood vessel wall pressure, R is the blood vessel diameter, and ρ is the blood density.

[0046] It is known that the elastic modulus E of a blood vessel changes exponentially with respect to the blood pressure P. Therefore, when the elastic modulus E of a blood vessel in P=O is set to EO, E is expressed as the following formula.

[0047] [Number 2] E=E0e γP …(2)

[0048] γ is a constant that depends on the vessel.

[0049] In addition, the length L of the vascular passage is expressed by the following formula.

[0050] [Number 3] LvT…(3)

[0051] T is the pulse transit time (PTT) and L is the length of the vascular access.

[0052] Therefore, from formulas (1) to (3)

[0053] [Number 4]

[0054] The above formula (number 4).

[0055] As shown in formula (4), when L is fixed, T has a correlation with P. Therefore, the pattern creation unit 30 creates a plurality of estimation patterns of P using the PTT calculated by the pulse parameter calculation unit 20 .

[0056] First, the pattern creation unit 30 creates an estimation pattern M1 of complexity 1. The "complexity" in this specification means the number of explanatory variables in the estimation pattern (eg, the number of PTTs used in the estimation pattern). In the following example, in the estimation pattern M1, one PTT is used as an explanatory variable.

[0057] In the following description, one PTT calculated by the pulse parameter calculation unit 20 is displayed as PTT1. PTT1 is the PTT between any two skin areas. The pattern creation unit 30 performs regression analysis using the least square method on PTT1 and BPm. The pattern creation unit 30 creates an estimated pattern M1 as a result of the regression analysis. Each PTT calculated by the pulse parameter calculation unit 20 and the BPm acquired by the blood pressure acquisition unit 2 are examples of test data.

[0058] As an example, consider the estimation mode M1 through BP1=α1×PTT1+α2…(5) In the case of a linear model (calculation model represented by a linear function) represented by BP1, α1 and α2 are constants. In this case, the model creation unit 30 calculates α1 and α2 by performing regression analysis (i.e., creates an estimated model M1).

[0059] For convenience, Figure 2 Each of the 1329 types of PTT in the example is referred to as PTT1-1 to PTT1-1326. The pattern creation unit 30 uses PTT1-1 to PTT1-1326 to create the same number of estimated patterns M1 as the PTT. For convenience, each of these estimated patterns M1 is referred to as M1-1 to M1-1326.

[0060] Next, the pulse parameter calculation unit 20 creates an estimation pattern M2 of complexity 2. In the estimation pattern M2, two PTTs are used as explanatory variables. In the following description, two different PTTs calculated by the pulse parameter calculation unit 20 are shown as PTT1 and PTT2.

[0061] The model creation unit 30 performs regression analysis using the least square method on (i) PTT1 and PTT2 and (ii) BPm. The model creation unit 30 creates an estimation model M2 as a result of the regression analysis.

[0062] As an example, consider the estimation mode M2 ​​through BP2=β1×PTT1+β2×PTT2+β3…(6) In the case of a linear model represented by , BP2 is the predicted blood pressure, and β1 to β3 are constants. In this case, the model generator 30 calculates β1 to β3 by performing regression analysis.

[0063] exist Figure 2 In the example, the pattern generation unit 30 uses PTT1-1 to PTT1-1326 to generate an estimated pattern M2 that is more than the PTT. In this example, there are 878475 combinations of PTT1 and PTT2 (i.e., 1326 C2). Therefore, the pattern creation unit 30 calculates 878,475 estimated patterns M2.

[0064] In the same manner, the model generating unit 30 generates an estimation model M3 of complexity 3, an estimation model M4 of complexity 4, ..., and an estimation model Mz of complexity z. z represents the upper limit of complexity. z is determined based on the following Figure 6The calculation results in each process of the flowchart may be different. The model creation unit 30 supplies each created estimation model to the model evaluation unit 40 (more specifically, the evaluation predicted blood pressure calculation unit 41).

[0065] As described above, the first pattern generator 300-1 generates an estimated pattern (hereinafter referred to as the first pattern) based on pattern 1. The second pattern generator 300-2 to the N-th pattern generator 300-N are similar. That is, the k-th pattern generator 300-k generates an estimated pattern (hereinafter referred to as the k-th pattern) based on pattern k.

[0066] In this way, the pattern generation unit 30 generates the first pattern to the Nth pattern. Hereinafter, the first pattern to the Nth pattern are collectively referred to as a pattern group. Figure 1 In the example of , the pattern creation unit 30 supplies the created pattern group to the pattern evaluation unit 40 and the pattern storage unit 50 respectively.

[0067] (Pattern Evaluation Unit 40) The mode evaluation unit 40 evaluates each estimation mode created by the mode creation unit 30 and outputs the evaluation result. Specifically, the mode evaluation unit 40 outputs the PI described below as the evaluation result. Figure 1 In the example of , the pattern evaluating unit 40 directly obtains the pattern group from the pattern creating unit 30. However, the pattern evaluating unit 40 may obtain the pattern group created by the pattern creating unit 30 and stored in the pattern storing unit 50 in advance.

[0068] The mode evaluation unit 40 includes a predicted blood pressure calculation unit for evaluation 41 and a mode evaluation index calculation unit 42. The predicted blood pressure calculation unit for evaluation 41 includes a first mode evaluation predicted blood pressure calculation unit 410-1, a second mode evaluation predicted blood pressure calculation unit 410-2, ..., and an Nth mode evaluation predicted blood pressure calculation unit 410-N. In addition, the mode evaluation index calculation unit 42 includes a first mode evaluation index calculation unit 420-1, a second mode evaluation index calculation unit 420-2, ..., and an Nth mode evaluation index calculation unit 420-N.

[0069] The kth mode evaluation predicted blood pressure calculation unit 410-k and the kth mode evaluation index calculation unit 420-k are functional units corresponding to the kth mode, respectively. The kth mode evaluation predicted blood pressure calculation unit 410-k and the kth mode evaluation index calculation unit 420-k are collectively referred to as the "kth mode evaluation unit".

[0070] The predicted blood pressure calculation unit 41 for evaluation calculates the predicted blood pressure (hereinafter, BPe) in the estimation pattern prepared by the pattern preparation unit 30. Specifically, the predicted blood pressure calculation unit 41 for evaluation calculates BPe by applying (specifically, substituting) PTT calculated as test data by the pulse parameter calculation unit to the estimation pattern.

[0071] The mode evaluation index calculation unit 42 calculates the evaluation index (hereinafter, PI) of the above-mentioned estimated mode. The mode evaluation index calculation unit 42 can also calculate PI based on BPe and BPm. As an example, the mode evaluation index calculation unit 42 calculates the mean square error (MSE) between BPe and BPm as PI. The mode evaluation index calculation unit 42 calculates the PI of each estimated mode in sequence from the estimated mode with small complexity. Then, the mode evaluation index calculation unit 42 supplies the calculated PI to the mode storage unit 50.

[0072] As described above, the predicted blood pressure calculation unit 410-1 for first mode evaluation calculates the predicted blood pressure in the first mode (predicted blood pressure for the first mode). The same is true for the predicted blood pressure calculation unit 410-2 for second mode evaluation to the predicted blood pressure calculation unit 410-N for N-th mode evaluation. That is, the predicted blood pressure calculation unit 410-k for k-th mode evaluation calculates the predicted blood pressure for the k-th mode (hereinafter, BPek). In this way, the predicted blood pressure calculation unit 41 for evaluation calculates BPe1 to BPeN. hereinafter, BPe1 to BPe N are collectively referred to as the predicted blood pressure group. The predicted blood pressure calculation unit 41 for evaluation supplies the calculated predicted blood pressure group to the mode evaluation index calculation unit 42.

[0073] Next, the first mode evaluation index calculation unit 420-1 calculates each PI in the first mode (first mode evaluation index group). The same is true for the second mode evaluation index calculation unit 420-2 to the Nth mode evaluation index calculation unit 420-N. That is, the kth mode evaluation index calculation unit 420-k calculates the kth mode evaluation index group (hereinafter, PIk). Hereinafter, PI1 to Pik are collectively referred to as evaluation index groups. The mode evaluation index calculation unit 42 associates the calculated evaluation index groups with the mode groups and supplies them to the mode storage unit 50.

[0074] (Pattern Storage Unit 50) The pattern storage unit 50 stores (saves) the pattern group created by the pattern creation unit 30. In addition, the pattern storage unit 50 stores the evaluation index group calculated by the pattern evaluation index calculation unit 42. The pattern storage unit 50 may be a known storage device.

[0075] (Mode Selection Unit 60) The mode selection unit 60 includes a first mode selection unit 600-1, a second mode selection unit 600-2, ..., and an N-th mode selection unit 600-N. The k-th mode selection unit 600-k is a functional unit corresponding to the k-th mode. Figure 7 As shown, the mode selection unit 60 operates to measure (calculate) the blood pressure (P) in the blood pressure measurement unit 160 after the processing by the mode setting device 100 is completed.

[0076] The mode selection unit 60 selects at least one measurement mode from a plurality of estimated modes stored in the mode storage unit 50 based on the evaluation result (i.e., each PI stored in the mode storage unit 50) by the mode evaluation unit 40 (more specifically, the mode evaluation index calculation unit 42). The measurement mode refers to a calculation mode for measuring the blood pressure (P) in the blood pressure measurement unit 160.

[0077] First, the mode selection unit 60 selects at least one measurement mode candidate (mode candidate) from a plurality of estimation modes. As an example, the mode selection unit 60 extracts "an estimation mode in which PI (e.g., MSE) becomes less than a predetermined threshold value" from a plurality of estimation modes as a measurement mode candidate. Then, the mode selection unit 60 selects at least one measurement mode from the measurement mode candidates.

[0078] As an example, consider a case where a measurement mode is selected by the selection unit 60. In this case, the mode selection unit 60 may select the estimation mode with the smallest PI as the measurement mode among the measurement mode candidates. Alternatively, the mode selection unit 60 may select the estimation mode with the smallest complexity as the measurement mode among the measurement mode candidates.

[0079] Alternatively, the mode selection unit 60 may select a plurality of measurement modes. For example, the mode selection unit 60 may select, as a measurement mode, "a measurement mode candidate in which the SNR in the entire partial area used in the measurement mode candidate is greater than or equal to a predetermined value" from among a plurality of measurement mode candidates.

[0080] Figure 4 FIG. 1 is a diagram for explaining an example of a process for extracting measurement mode candidates. Figure 4 In the example of , the standard deviation of the error of the estimated pattern is used as the PI (also refer to the modified example described later). In this case, the pattern evaluation index calculation unit 42 calculates the standard deviation of the error between BP e (predicted blood pressure) and BP m (test data) as the PI. Figure 4 The graph shows the distribution of PI (standard deviation of error) calculated by the mode evaluation index calculation unit 42.

[0081] exist Figure 4In the example, the predetermined threshold is set to a value such as "8 mmHg" (blood pressure threshold). This value is set based on the specifications of the non-blood pressure meter. In this case, the mode selection unit 60 extracts the estimated mode in which the PI is less than 8 mmHg as a measurement mode candidate. Figure 4 In the example of , the mode selection unit 60 extracts M2 to M4 as measurement mode candidates from the estimated modes M1 to M4 (complexity levels 1 to 4).

[0082] As described above, the first mode selection unit 600-1 selects at least one measurement mode candidate from the first mode (a measurement mode candidate within the first mode). Then, the first mode selection unit 600-1 selects at least one measurement mode candidate from the measurement mode candidates within the first mode (a measurement mode candidate within the first mode). The same is true for the second mode selection unit 600-2 to the Nth mode selection unit 600-N.

[0083] That is, the k-th mode selection unit 600-k selects at least one k-th mode intra-measurement mode candidate from the k-th mode. Then, the k-th mode selection unit 600-k specifies at least one k-th mode intra-measurement mode from the k-th mode intra-measurement mode candidates. The k-th mode intra-measurement mode refers to a calculation mode for measuring blood pressure (P) in the blood pressure measurement unit 160 in the case of pattern k.

[0084] However, consider a case where a pulse with a fixed signal quality (high-precision pulse) cannot be obtained from a part of the skin area. Examples of such a skin area include (i) a skin area covered by a cover or (ii) a skin area with a shadow. Therefore, from the perspective of improving the accuracy of blood pressure measurement, it is preferable to consider the existence of such a skin area.

[0085] Therefore, the pulse calculation unit 17 first calculates the pulse in each skin area. Then, the pulse calculation unit 17 can classify each skin area into (i) an area where a pulse with a fixed signal quality can be obtained (hereinafter, a quality-suitable area) and (ii) other areas (hereinafter, a quality-unsuitable area). The quality-unsuitable area can also be expressed as an area where a pulse with a fixed signal quality cannot be obtained. For example, the classification can also be performed based on the SNR (an example of signal quality) of each pulse. Alternatively, the classification can also be performed based on the pixel value of each skin area.

[0086] Then, the mode selection unit 60 may extract only the mode using only the quality appropriate region from the plurality of estimation modes as the measurement mode candidate. This can more effectively prevent the accuracy of the measurement result (blood pressure P described later) from being reduced.

[0087] (An Example of Processing by the Body Movement Classification Unit 22) In the body movement classification unit 22, N types of prescribed patterns are pre-set regarding the orientation (direction) of the face of the target organism H. Hereinafter, a data set is referred to as a face direction template, and the data set is a data set showing the N types of prescribed patterns. The body movement classification unit 22 uses the face direction template to classify the direction of the face detected by the body movement detection unit 21. That is, the body movement classification unit 22 specifies which pattern in the face direction template the face direction detected by the body movement detection unit 21 (hereinafter, the detection direction) should be.

[0088] Figure 5 is an example of a face direction template. Figure 5 In the example, N = 9. Figure 5 In the example, as Pattern 1: front side; Pattern 2: right; Pattern 3: top right; Pattern 4: top; Pattern 5: top left; Pattern 6: left; Pattern 7: bottom left; Pattern 8: bottom; Pattern 9: bottom right; Nine different face directions are specified. In this case, the body movement classification unit 22 can classify the detection direction into nine types from pattern 1 to pattern 9. In addition, "pattern k" can also be called "kth pattern". The body movement classification unit 22 outputs a classification number (pattern number) specific to itself at each specified time.

[0089] The classification numbers in the above examples are marked to indicate the transition (change) of the orientation of the face between two specified moments (e.g., between moments A and B). As an example, the orientation of the face at moment A is pattern 1. In this case, patterns 1 to 9 can also be expressed as patterns of the direction of movement of the face between moments A and B. In addition, if it is pattern 1 at moment B, it means that the orientation of the face has not changed. In this way, the pattern of the orientation of the face can also be said to be a pattern of the direction of movement of the face.

[0090] As an example, consider the case where the detection direction at time A is the front (pattern 1). As a first example, the detection direction at time B is the left (pattern 6). In this case, the body movement classification unit 22 changes the classification number to "pattern 1→6" ( Figure 5 arrow example).

[0091] As a second example, consider a case where the detection direction at time C (a time later than time B) is the front (pattern 1), and the detection direction at time D (a time later than time C) is the upper right (pattern 3). In this case, the body movement classification unit 22 changes the classification number to "pattern 1→6→1→3".

[0092] In addition, the body movement classification unit 22 can set the pattern transition between two predetermined moments as the classification object. In the case of the second example described above, first, the classification of the pattern transition is changed from "pattern 1→6" to "pattern 6→1". Next, the classification of the pattern transition is changed from "pattern 6→1" to "pattern 1→3".

[0093] In addition, the body motion classification unit 22 can perform pattern classification based on the movement amount calculated by the body motion detection unit 21. As an example, the body motion classification unit 22 can also perform pattern classification based on the result of comparing the movement amount with a predetermined threshold value. In addition, in the judgment process of pattern classification, instead of the movement amount, a time average value of the movement amount (hereinafter, the movement amount average value) can also be used. The time average value of the movement amount can also be, for example, the average value of the movement amount in the measurement time of each measurement data for pattern creation.

[0094] (Blood Pressure Measurement Unit 160 and Blood Pressure Measurement Result Output Unit 170) The blood pressure measurement unit 160 measures the blood pressure (P) using the measurement mode selected by the mode selection unit 60. Specifically, the blood pressure measurement unit 160 calculates P by applying the pulse parameter (e.g., PTT) calculated by the pulse parameter calculation unit 20 to the measurement mode. In this way, the blood pressure measurement unit 160 calculates the first blood pressure (P) based on the pulse parameter by using the measurement mode.

[0095] As described above, the mode selection unit 60 selects the measurement mode corresponding to the pattern k (k-th mode measurement mode). As a result, the blood pressure measurement unit 160 calculates P using the measurement mode suitable for the orientation of the face of the subject organism H.

[0096] The blood pressure measurement result output unit 170 obtains P measured by the blood pressure measurement unit 160. Then, the blood pressure measurement result output unit 170 outputs the P as the blood pressure measurement result. The blood pressure measurement result output unit 170 may also present P in any notification form. As an example, the blood pressure measurement result output unit 170 may also be a display. In this case, the blood pressure measurement result output unit 170 can visually present the blood pressure measurement result to the subject organism H by displaying a numerical value showing P.

[0097] (How to create a measurement mode) Figure 61 is a flowchart showing an example of the process flow of the blood pressure measurement device 1. Figure 6 , an example of a method for creating (setting) a measurement mode by the blood pressure measurement device 1 (more specifically, the mode setting device 100). This method may also be referred to as a measurement mode creation method (or a measurement mode setting method).

[0098] First, the imaging unit 11 captures a target living being image (S1). The face image acquisition unit 14 acquires a face image (IMG) from the target living being image (S2). The face image acquisition unit 14 performs face tracking on IMG.

[0099] Next, the body motion detection unit 21 detects the orientation of the face (the direction in which the face moves) using the result of the face tracking in S3 (S4, body motion detection process). The body motion classification unit 22 classifies the orientation of the face detected in S4 (S5, body motion classification process). For example, the body motion classification unit 22 classifies the orientation of the face into any one of the above-mentioned patterns 1 to 9 (pattern k).

[0100] Next, the face image segmentation unit 15 segments the IMG into a plurality of partial regions based on the patterns classified in S5 (S6). The skin region extraction unit 16 extracts the skin region from the plurality of partial regions (S7). The pulse calculation unit 17 calculates the pulse (pulse signal) for each skin region (S8, pulse acquisition process). Next, the pulse parameter calculation unit 20 uses the pulse to calculate the PTT (pulse propagation time) between each skin region (S9, pulse parameter calculation process).

[0101] Each of the processes described below is performed for each pattern (pattern k) classified in S5. After S9, the mode setting device 100 confirms whether an estimated pattern (kth pattern) of pattern k for the subject organism H whose blood pressure is currently to be measured already exists (S10). In other words, the mode setting device 100 confirms whether an estimated pattern based on the orientation of the face exists. If the above-mentioned estimated pattern does not exist at the current moment (No in S10), the blood pressure acquisition unit 2 acquires the blood pressure (BPm) of the subject organism H (S11, second blood pressure measurement process).

[0102] Next, the pattern creation unit 30 (more specifically, the k-th pattern creation unit 300-k) uses the test data to create a plurality of estimated patterns (k-th patterns) in pattern k. Specifically, the pattern creation unit 30 uses PTT and BPm to create a plurality of estimated patterns of a predetermined complexity (S12, pattern creation process). When S12 is performed for the first time (the first loop process), the pattern creation unit 30 creates a plurality of estimated patterns of complexity 1 (a plurality of M1). As described above, the pattern creation unit 30 stores the estimated patterns (e.g., each M1) created by itself in the pattern storage unit 50.

[0103] The BPm used in S12 is the blood pressure measured by the blood pressure acquisition unit 2 simultaneously with the capturing of the target biological image (S1). That is, the second blood pressure measurement step is performed once in advance simultaneously with S1 before S11.

[0104] Next, the predicted blood pressure calculation unit for evaluation 41 (more specifically, the k-th mode predicted blood pressure calculation unit for evaluation 410-k) calculates the predicted blood pressure (BPe, more specifically, BPek) in each M1 created in S12 using the test data. More specifically, the predicted blood pressure calculation unit for evaluation 41 calculates BPe by applying PTT to each M1 (S13).

[0105] Next, the mode evaluation index calculation unit 42 (more specifically, the k-th mode evaluation index calculation unit 420-k) calculates the evaluation index (PI, more specifically PIk) of the estimated mode. Specifically, the mode evaluation index calculation unit 42 calculates the mean square error (MSE) between BPe and BPem as the PI (S14). As described above, the mode evaluation index calculation unit 42 stores each PI calculated by itself in the mode storage unit 50. S13 and S14 are collectively referred to as the mode evaluation process. In addition, before starting S13, the mode evaluation unit 40 can also read each estimated mode (k-th mode) from the mode storage unit 50.

[0106] Next, when the estimated modes with the minimum PI (e.g., MSE) in each complexity are plotted against each other, the mode evaluation unit 40 determines whether the minimum value of MSE is obtained (S15). In other words, the mode evaluation unit 40 determines whether the minimum MSE in the complexity calculated in the previous S14 is greater than the minimum MSE in the complexity calculated in S14 in the previous loop processing.

[0107] In addition, when S16 is performed for the first time (the first loop process), there is no minimum MSE in the complexity calculated in S14 in the previous loop process (i.e., comparison with the minimum MSE in the complexity calculated in the previous step S14). Therefore, when S15 is performed for the first time, it is judged as No in S15.

[0108] When the minimum value of MSE cannot be obtained (in other words, when the minimum MSE in the complexity calculated in the previous S14 is smaller than the minimum MSE in the complexity calculated in S14 in the previous loop processing) (No in S15), the pattern creation unit 30 increases the complexity of the estimated pattern to 1 (S16). In the case of the above example, the pattern creation unit 30 adds the complexity count from 1 to 2. Then, it returns to S12. Thereafter, until it becomes "Yes" in S15, the processing of S1 to S15 is repeated. In this way, the above z (the upper limit value of the complexity) is consistent with the number of repetitions of the processing of S12 to S15.

[0109] On the other hand, when a minimum value of MSE is obtained (in other words, the minimum MSE in the complexity calculated in the previous S14 is greater than the minimum MSE in the complexity calculated in the previous S14) (yes in S15), the pattern evaluation unit 40 determines whether the minimum value of the MSE is greater than a specified threshold (S17).

[0110] When the minimum value of MSE is greater than the threshold value (if S17 is yes), the process of creating the kth mode is terminated. This is because it is considered that in this case, even if the complexity is increased in the future, there is no room for creating an estimated mode, and the estimated mode can obtain a PI (e.g., MSE) that is better than the current situation. On the other hand, when the minimum value of MSE is less than the threshold value (if S17 is no), return to S16. This is because it is considered that in such a case, by increasing the complexity, there is room for creating an estimated mode, and the estimated mode can obtain a PI that is better than the current situation.

[0111] If S10 is "Yes" (if the k-th pattern already exists), the process is terminated directly (ie, S11 to S17 are not performed). This is because in such a case, it is not necessary to create the k-th pattern.

[0112] For each of patterns 1 to N (e.g. patterns 1 to 9), execute Figure 6 By processing the mode setting device 100, it is possible to create the first mode to the Nth mode (mode group).

[0113] (Blood pressure measurement method) Figure 7 FIG. 2 is a flowchart showing another example of the process flow of the blood pressure measurement device 1. Figure 7 Detailed Description of the Invention An example of a method for measuring blood pressure using the blood pressure measurement device 1 (blood pressure measurement method) is shown. Figure 7 The various processing Figure 6 After the entire processing of is completed. That is, Figure 7Before starting each process, (i) the pattern group created by the pattern setting device 100 and (ii) the evaluation index group calculated by the pattern setting device 100 are stored in the pattern storage unit 50 in advance.

[0114] Figure 7 S21 to S32, S21 to S29 are respectively Figure 6 Therefore, in the following, only S30 to S32 and the associated processing are described. In addition, the processing after S30 is performed for each pattern (pattern k) classified in S25. Figure 7 In the example, the second blood pressure measurement process is performed simultaneously with S21.

[0115] After S29, the mode selection unit 60 (more specifically, the k-th mode selection unit 600-k) reads each estimated mode (k-th mode) from the mode storage unit 50. In addition, the mode selection unit 60 reads each PI from the mode storage unit 50. As described above, the mode selection unit 60 selects a predetermined measurement mode (k-th mode within measurement mode) from a plurality of k-th modes based on each PI. In this way, the mode selection unit 60 selects a predetermined measurement mode from a plurality of estimated modes according to the orientation of the face (S30, mode selection process).

[0116] Next, the blood pressure measurement unit 160 calculates the blood pressure (P) using the measurement mode selected in S30 (S31, first blood pressure measurement step). Finally, the blood pressure measurement result output unit 170 outputs the P as the blood pressure measurement result (S32). With the completion of S32, the blood pressure measurement by the blood pressure measurement device 1 ends.

[0117] (Effect) As described above, the measuring device of Patent Document 1 is configured to measure the pulse rate with high accuracy even when the body of the subject organism H moves (more specifically, when the face of the subject organism H moves). However, Patent Document 1 does not particularly describe a specific method for measuring the blood pressure (P) with high accuracy in response to the body movement of the subject organism H. Thus, P cannot be measured with high accuracy in the prior art.

[0118] In contrast, in the blood pressure measurement device 1, a plurality of types of estimation modes corresponding to the orientation of the face (i.e., corresponding to body movement) are pre-set by the mode setting device 100. Then, the blood pressure measurement device 1 can measure (calculate) the blood pressure (P) using the estimation mode stored in the mode storage unit 50. In other words, P can be measured in consideration of the body movement of the subject organism H. Thus, even when there is body movement of the user, it is possible to measure with higher accuracy than before.

[0119] [Implementation Method 2] (1) The target organism H is not limited to a human being, and the target organism H may be any object to which the blood pressure measurement method according to one aspect of the present disclosure is applicable. For example, the target organism H may be an animal such as a dog or a rabbit.

[0120] (2) ROI is not limited to the face. ROI can be any part of the body surface of a living being whose pulse can be obtained. Other examples of ROI include the neck, chest, and palm.

[0121] However, the ROI is preferably the face. When IMG (face image) is used, the burden on the subject H during the blood pressure measurement can be reduced. That is, it is easy to measure the blood pressure of the subject H in a natural state (relaxed state).

[0122] (3) The body movement detection unit 21 does not necessarily detect body movement based on image analysis (e.g., face tracking results). For example, the body movement detection unit 21 may be a contact-type sensor that can detect body movement. The sensor may be configured to give the subject H a sense of restraint as little as possible. In this way, the blood pressure measurement device 1 may be a contact-type blood pressure measurement device.

[0123] In addition, the body motion detection unit 21 may further detect at least one of (i) the speed of the body motion and (ii) the acceleration of the body motion based on the size (displacement) of the body motion. In this case, the body motion classification unit 22 may further classify the body motion pattern based on at least one of (i) the speed of the body motion and (ii) the acceleration of the body motion based on the size of the body motion. In this case, the pattern creation unit 30 creates an estimated pattern based on the classification.

[0124] (4) The pulse parameter is not limited to PTT. For example, the pulse parameter calculation unit 20 calculates the waveform feature of the pulse in each skin area as the waveform parameter. Examples of the waveform feature include (i) the amplitude of the pulse and (ii) the time difference between each pulse pulse. In addition, the pulse parameter calculation unit 20 may combine PTT and the waveform feature to set the pulse parameter.

[0125] (5) The estimated model is not limited to the linear model. The model creation unit 30 may create a nonlinear model (a calculation model expressed by a nonlinear function) by performing regression analysis.

[0126] (6) The evaluation index (PI) of the estimated model is not limited to the mean square error of BPe and BPm. For example, (i) the mean square error of BPe and BPm, or (ii) the standard deviation of the mean square error of BPe and BPm can be used as the PI. Furthermore, the PI can be a parameter calculated based on BPe and BPm, and is not limited to a parameter associated with the error. For example, (i) the completion degree of freedom adjustment determination index and (ii) AIC (Akaike's information Criteria) can be used as the PI.

[0127] (7) The mode storage unit 50 may be connected to the blood pressure measurement device 1 in a communicable manner. For example, the mode storage unit 50 may be a server device provided outside the blood pressure measurement device 1. In this way, the mode storage unit 50 does not necessarily need to be provided inside the blood pressure measurement device 1. Similarly, the mode storage unit 50 does not necessarily need to be provided inside the mode setting device 100.

[0128] In addition, the mode storage unit 50 may be omitted. In this case, the mode selection unit 60 may directly obtain each measurement mode from the mode creation unit 30. Similarly, the mode selection unit 60 may directly obtain each PI from the mode evaluation unit 40. However, in order to speed up the measurement of P by the blood pressure measurement device 1, it is preferable to provide the mode storage unit 50.

[0129] (8) The mode setting device 100 may further include a measurement data classification unit. The measurement data classification unit is a functional unit that (i) extracts pulses for each of a plurality of data measurement times from the pulses acquired by the pulse acquisition unit 10 and (ii) classifies the extracted pulses. As an example, the function of the measurement data classification unit may be given to the mode creation unit 30.

[0130] As an example, the plurality of data measurement times are four types of time, namely, "5 seconds", "10 seconds", "20 seconds", and "30 seconds". The pulse parameter calculation unit 20 calculates the plurality of pulse parameters using the pulses classified by the measurement data classification unit. That is, the pulse parameter calculation unit 20 calculates the plurality of pulse parameters (i) for each pattern classification of the body movement classification unit 22 and (ii) for each pulse classification of the measurement data classification unit.

[0131] In the present case, the pulse parameter calculation 20 calculates four types of pulse parameters in pattern k, namely, "the pulse parameter when the data measurement time is 5 seconds", "the pulse parameter when the data measurement time is 10 seconds", "the pulse parameter when the data measurement time is 20 seconds", and "the pulse parameter when the data measurement time is 30 seconds".

[0132] Then, the pattern creation unit 30 creates each estimation pattern using each pulse parameter calculated by the pulse parameter calculation unit 20. According to this configuration, an estimation pattern can be created at each of the multiple types of data measurement time. Therefore, the blood pressure measurement device 1 can further consider the length of time when body movement occurs and select a measurement mode suitable for blood pressure measurement. As a result, the accuracy of blood pressure measurement can be further improved.

[0133] (9) The mode setting device 100 may be connected to the blood pressure measurement device 1 in a communicable manner. For example, the mode setting device 100 may be provided in a server device outside the blood pressure measurement device 1. In this way, the mode setting device 100 does not necessarily need to be provided inside the blood pressure measurement device 1.

[0134] [Implementation Method 3] The control block of the blood pressure measuring device 1 (especially, the pulse acquisition unit 10, the pulse parameter calculation unit 20, the body movement detection unit 21, the body movement classification unit 22, the pattern creation unit 30, the pattern evaluation unit 40, the pattern selection unit 60 and the blood pressure measurement unit 160) can be implemented by a logic circuit (hardware) formed on an integrated circuit (IC chip) or the like, or can be implemented by software.

[0135] In the latter case, the blood pressure measuring device 1 is provided with a computer that executes the commands of the software that implements each function, that is, the program. The computer is provided with, for example, at least one processor (control device), and at least one computer-readable recording medium that records the above-mentioned program. Then, in the above-mentioned computer, the above-mentioned program is read from the above-mentioned recording medium by the above-mentioned processor and executed, thereby achieving the purpose of one form of the present disclosure. As the above-mentioned processor, for example, a CPU (Central processing Unit) can be used. As the above-mentioned recording medium, "non-temporary tangible media" such as ROM (Read Only Memory) can be used, such as tapes, disks, cards, semiconductor memories, programmable logic circuits, etc. In addition, it is also possible to have a RAM (Rand om Access Memory) for expanding the program. In addition, the above-mentioned program can also be supplied to the above-mentioned computer via any transmission medium (communication network, broadcast wave, etc.) that can transmit the program. The blood pressure measuring device 1 can also be implemented by a well-known information processing device (for example: a smart phone, a tablet notebook, or a personal computer). In addition, one form of the present disclosure can be implemented in the form of a data signal embedded in a carrier that embodies the above-mentioned program through electronic transmission.

[0136] [Additional matters] One form of the present disclosure is not limited to the above-mentioned embodiments, and various changes can be made within the scope indicated by the claims. The embodiments obtained by appropriately combining the technical solutions disclosed in different embodiments are also included in the technical scope of one form of the present disclosure. Moreover, new technical features can be formed by combining the technical means disclosed in each embodiment.

Claims

1. A blood pressure measuring device for measuring a first blood pressure of a living body based on the pulse of the living body, wherein: The blood pressure measuring device comprises: A pulse acquisition unit that acquires a pulse in a face region on the body surface of the living body; A body motion detection unit, detecting the orientation of the face; a body movement classification unit that classifies the orientation of the face; and The pulse parameter calculation unit calculates a plurality of pulse parameters based on the pulse. The blood pressure measuring device is communicatively connected to the mode storage unit. The pattern storage unit stores in advance a plurality of blood pressure estimation patterns corresponding to the orientations of the face classified by the body movement classification unit, and an evaluation index based on the predicted blood pressure and the measured blood pressure of the subject organism. The above-mentioned blood pressure measuring device also has a first blood pressure measuring unit, which selects a specified measurement mode from the above-mentioned multiple blood pressure estimation modes corresponding to the orientation of the above-mentioned face based on the above-mentioned predicted blood pressure read from the above-mentioned pattern storage unit and the above-mentioned evaluation index of the measured blood pressure of the above-mentioned target organism, and uses the above-mentioned specified measurement mode to calculate the above-mentioned first blood pressure based on the above-mentioned multiple pulse wave parameters.

2. A mode setting device, which is communicatively connected to a blood pressure measuring device, wherein the blood pressure measuring device measures a first blood pressure of the living body based on the pulse of the living body, wherein the mode setting device is characterized in that: The above-mentioned mode setting device comprises: a second blood pressure measuring unit for measuring a second blood pressure of the biological subject; A pulse acquisition unit that acquires a pulse in a face region on the body surface of the living body; A body motion detection unit, detecting the orientation of the face; a body movement classification unit for classifying the orientation of the face; as well as The pulse parameter calculation unit calculates a plurality of pulse parameters based on the pulse. The mode setting device is communicatively connected to the mode storage unit. The mode setting device further comprises: The pattern creation unit creates a plurality of blood pressure estimation patterns for estimating the first blood pressure according to the orientation of the face classified by the body movement classification unit, based on the plurality of pulse parameters and the second blood pressure, and stores the plurality of blood pressure estimation patterns in the pattern storage unit.

3. A mode setting device connected to a blood pressure measuring device in a communicable manner, wherein the blood pressure measuring device measures a first blood pressure of the living body based on the pulse of the living body, wherein the mode setting device is characterized in that: The above-mentioned mode setting device comprises: a second blood pressure measuring unit for measuring a second blood pressure of the biological subject; A pulse acquisition unit that acquires a pulse in a predetermined area on the body surface of the living body; A body motion detection unit, detecting a moving direction of the above-mentioned specified area; a body movement classification unit, which classifies the movement direction; and The pulse parameter calculation unit calculates a plurality of pulse parameters based on the pulse. The mode setting device is communicatively connected to the mode storage unit. The mode setting device further comprises: a pattern generating unit that generates a blood pressure estimation pattern for estimating the first blood pressure based on the plurality of pulse parameters and the second blood pressure according to the classification result of the moving direction, and stores the blood pressure estimation pattern in the pattern storing unit; The mode setting device further includes a mode evaluation unit configured to store, in the mode storage unit, an evaluation result of each of the plurality of blood pressure estimation modes stored in the mode storage unit based on a result of the classification of the movement direction.

4. The mode setting device according to claim 3, characterized in that: Let N be an integer greater than 2, The body movement classification unit classifies the movement direction into N patterns from a first pattern to an Nth pattern, Let k be an integer greater than 1 and less than N, The blood pressure estimation mode based on the k-th pattern is referred to as the k-th mode. The pattern generator has a k-th pattern generator, which generates a plurality of k-th patterns for estimating the first blood pressure based on the plurality of pulse parameters and the second blood pressure, and stores the plurality of k-th patterns in the pattern storage unit. The pattern evaluation unit includes a k-th pattern evaluation unit that evaluates each of the plurality of k-th patterns stored in the pattern storage unit and stores the evaluation result in the pattern storage unit.

5. A recording medium storing a blood pressure measurement program for executing a blood pressure measurement method using a blood pressure measurement device, wherein the blood pressure measurement device measures a first blood pressure of the living body based on the pulse of the living body, wherein the recording medium is characterized in that: The above blood pressure measurement program causes the computer to execute: A pulse acquisition step of acquiring a pulse in a face region on the body surface of the living body; A body motion detection step, detecting the orientation of the face; a body movement classification step of classifying the orientation of the face; and The pulse parameter calculation step calculates a plurality of pulse parameters based on the pulse. The blood pressure measuring device is communicatively connected to the mode storage unit. The pattern storage unit stores in advance a plurality of blood pressure estimation patterns corresponding to the orientation of the face and an evaluation index based on the predicted blood pressure and the measured blood pressure of the subject organism. The blood pressure measurement program also enables the computer to execute a first blood pressure measurement process. In the first blood pressure measurement process, based on the predicted blood pressure and the evaluation index of the measured blood pressure of the target organism, a specified measurement mode is selected from the multiple blood pressure estimation modes corresponding to the orientation of the face, and the first blood pressure is calculated based on the multiple pulse wave parameters using the specified measurement mode.

6. The recording medium storing the blood pressure measurement program according to claim 5, characterized in that: The model storage department stores in advance: the plurality of blood pressure estimation modes corresponding to the orientation of the face; and The evaluation result of each of the plurality of blood pressure estimation modes corresponding to the orientation of the face.

Images