Measurement apparatus, measurement system, and measurement method

Abstract

To provide a measuring device capable of calculating biological information in a non-contact manner by reflecting the influence of exercise.SOLUTION: The measurement device includes an imaging unit configured to image a living body to acquire an image, a signal acquisition unit configured to acquire a biological signal which is a value related to the living body calculated from the image, an input unit configured to receive information related to exercise performed by the living body before the imaging unit acquires the image as exercise information, and a biological information calculation unit configured to calculate biological information related to a blood vessel or a blood flow from the biological signal using reference information selected from a plurality of pieces of reference information based on the exercise information.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a measurement device, a measurement system, and a measurement method. [Background technology]

[0002] Patent Document 1 discloses a technology for acquiring optical information about a living organism by photographing the living organism with a camera, and acquiring the living organism's pulse rate, blood pressure, respiratory rate, etc. by analyzing the living organism's feature amounts calculated from the optical information. Specifically, in the technology disclosed in Patent Document 1, the living organism's pulse rate, blood pressure, respiratory rate, etc. are acquired by analyzing the living organism's feature amounts using artificial intelligence or machine learning. In the technology disclosed in Patent Document 1, the living organism's feature amounts include feature amounts related to the living organism's pulse wave, feature amounts related to the living organism's blood pressure, feature amounts related to the living organism's age, feature amounts related to the living organism's movement, etc. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2017 / 188099 Summary of the Invention [Problem to be solved by the invention]

[0004] During exercise, the body must pump a large amount of blood, increasing blood flow and raising blood pressure. It is believed that blood vessels dilate during exercise, facilitating blood flow. Even when resting after exercise, blood vessels do not immediately return to their normal state; they remain dilated for a while, potentially causing lower blood pressure than usual, leading to phenomena such as post-exercise hypotension and exercise-related collapse. Furthermore, these phenomena manifest differently depending on whether or not a subject regularly engages in intense exercise. Habitual exercisers tend to have lower heart rates and blood pressure even when not exercising. Thus, exercise significantly impacts the state of blood vessels and blood flow. Based on data measured by the inventors, for example, a tendency for hypotension was particularly pronounced in track and field athletes, whose sports place a greater strain on the heart than ball games. Some subjects even experienced hypotension more than 30 minutes after exercise. Due to these phenomena, machine learning models and regression equations created using vascular data measured at rest or from subjects who do not regularly exercise can sometimes reduce the accuracy of vital signs related to blood vessels and blood flow. Therefore, it is desirable to incorporate the exercise state prior to measurement into vital sign calculations. Contact-type devices like smartwatches can monitor exercise using acceleration sensors, but this puts a strain on the wearer.On the other hand, camera-based devices, which eliminate the burden of wearing a device, make it difficult to monitor exercise.

[0005] Patent Document 1 does not mention the effects of exercise on blood pressure, etc., and does not clearly state a method for taking into account factors resulting from exercise-induced changes in vascular status when estimating blood pressure, etc. Therefore, the technology disclosed in Patent Document 1 cannot reflect the effects of exercise on blood pressure, etc., due to changes in vascular status. Furthermore, the technology disclosed in Patent Document 1 outputs a comprehensive health assessment by combining blood pressure values ​​measured with a cuff sphygmomanometer, pulse waves, and exercise status. However, wearing a cuff sphygmomanometer is a burden for the user. Therefore, one aspect of the present disclosure aims to provide a measurement device, measurement system, and measurement method that can calculate biological information non-contact while reflecting the effects of exercise. [Means for solving the problem]

[0006] A measuring device according to one embodiment of the present disclosure includes an imaging unit that captures an image of a living body by capturing an image, a signal acquisition unit that acquires a biosignal, which is a value related to the living body calculated from the image, an input unit to which information related to the exercise performed by the living body before the imaging unit acquired the image is input as exercise information, and a bioinformation calculation unit that calculates bioinformation related to blood vessels or blood flow from the biosignal using reference information selected from a plurality of reference information based on the exercise information.

[0007] A measurement system according to one embodiment of the present disclosure includes an imaging unit that captures an image of a living body and acquires the image; a signal acquisition unit that acquires a biosignal, which is a value related to the living body calculated from the image; an input unit to which information related to the exercise performed by the living body before the imaging unit acquired the image is input as exercise information; and a bioinformation calculation unit that calculates bioinformation related to blood vessels or blood flow from the biosignal using reference information selected from a plurality of reference information based on the exercise information.

[0008] A measurement method according to one embodiment of the present disclosure includes the steps of: capturing an image of a living body to obtain an image; obtaining a biosignal, which is a value related to the living body calculated from the image; inputting information related to the exercise performed by the living body before the image was obtained as exercise information; and calculating bioinformation related to blood vessels or blood flow from the biosignal using reference information selected from a plurality of reference information based on the exercise information. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of how the measurement device is used. [Figure 2] 1 is a block diagram showing an example of the configuration of a measurement device according to a first embodiment. [Figure 3] FIG. 10 is a schematic diagram illustrating an example of an input screen displayed to a user. [Figure 4] 4 is a flowchart showing an example of the operation of the measurement device according to the first embodiment. [Figure 5] FIG. 10 is a block diagram showing an example of the configuration of a measurement device according to a second embodiment. [Figure 6] 10 is a flowchart showing an example of the operation of the measurement device according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] (First embodiment) The first embodiment will be described with reference to Figures 1 to 4. In the drawings, the same or similar elements are given the same reference numerals, and redundant explanations will be omitted.

[0011] 1 is a diagram showing an example of a usage mode of the measurement device 100. As shown in the example of FIG.

[0012] The measuring device 100 measures time-series changes in the condition of the surface or interior of the skin of a living body 102 from images acquired by an imaging unit 101, thereby acquiring biological information. For example, the measuring device 100 may be a personal computer (PC), smartphone, tablet device, a dedicated terminal for measuring biological information, or a monitoring robot equipped with the imaging unit 101. When an organism is irradiated with illumination or natural light, the measuring device 100 measures the condition of the interior of the skin, such as biological information that is a vital sign related to blood vessels or blood flow, such as blood pressure, pulse rate, and blood oxygen saturation, by measuring light transmitted through or reflected from the skin. In this embodiment, blood pressure is used as an example of a vital sign, but it is not limited to blood pressure as long as it is a vital sign related to blood vessels or blood flow. While the measuring device 100 is not shown in FIG. 1 as being held in the hand, this is not a limitation, and it also includes cases where the measuring device 100 is held in the hand while taking images, for example, a smartphone or tablet.

[0013] The imaging unit 101 captures an image of the living body 102. In the present disclosure, a still image or a video cut out from continuous or discontinuous actual recording that reflects the state of blood vessels of the living body 102 captured by the imaging unit 101 is referred to as an image.

[0014] The imaging unit 101 is installed in a position where it can capture an image of an exposed part of the body surface of the living body 102. The exposed part of the body surface of the living body 102 is the forehead, cheeks, fingertips, wrist, palm, etc. of the living body 102. For example, the imaging unit 101 is installed in a PC, a smartphone, a tablet, a display, a mirror, a washbasin, etc.

[0015] The imaging unit 101 is a camera including a CCD (Charged Coupled Device) or CMOS (Complementary Metal Oxide Semiconductor) image sensor and a lens. The imaging unit 101 may be configured with a camera image sensor including RGB filters. For example, the imaging unit 101 includes color filters in an RGB Bayer array to detect minute changes in the skin of the living body 102. Alternatively, the imaging unit 101 may include color filters such as RGBCy and RGBIR. Color filters such as RGBCy and RGBIR are suitable for observing increases and decreases in blood volume indicated by reflected light of light that has passed through the inside of the skin.

[0016] FIG. 2 is a block diagram showing an example of the configuration of the measurement device 100. As shown in FIG.

[0017] The measuring device 100 includes an imaging unit 101, an input unit 201, an output unit 202, a storage unit 203, and a control unit 204. The imaging unit 101, the input unit 201, the output unit 202, and the storage unit 203 are electrically connected to the control unit 204.

[0018] The imaging unit 101 captures an image of the living body 102, which is the user, to obtain an image 211, and transmits the obtained image 211 to the control unit 204. For example, the imaging unit 101 captures an image of the living body 102 at 30 to 60 fps (frames per second) to obtain the image 211. The image 211 includes an image of the body surface of the living body 102.

[0019] Exercise information 210 is input to the input unit 201. In this embodiment, the exercise information 210 is information about the exercise performed by the living body 102 before the imaging unit 101 acquires the image 211. Furthermore, the input unit 201 accepts input of information necessary for the measuring device 100 in addition to the user's exercise information 210. For example, the input unit 201 is a keyboard, a mouse, a touch panel, or the like.

[0020] The output unit 202 outputs an image 211, a report 212 in which the control unit 204 summarizes the biometric information according to the user's needs, a message to the user, the date and time, etc. For example, the output unit 202 is configured to include a display, a speaker, etc.

[0021] The control unit 204 executes various processes in accordance with the programs and data stored in the storage unit 203. The control unit 204 is configured by a processor such as a CPU (Central Processing Unit) or a GPU (Graphic Processing Unit).

[0022] The control unit 204 includes a signal acquisition unit 205 , a biological information calculation unit 206 , and a model selection unit 207 .

[0023] The signal acquiring unit 205 acquires a biosignal 216 from the image 211. The biosignal 216 is a value related to the living body 102 calculated from the image 211. Specifically, the signal acquiring unit 205 acquires the biosignal 216 from a signal such as an RGB pixel value included in the image 211. For example, in this embodiment, the biosignal 216 is data representing the state of the living body, such as a vascular volume pulse wave. Since the pulse wave reflects the state of the blood vessels and blood flow, bioinformation can be obtained from the pulse wave. The pulse wave is not limited to a volume pulse wave, and other signals or indicators, such as a pressure pulse wave or pulse wave velocity, may be used as long as they are biosignals that reflect the state of the blood vessels or blood flow.

[0024] In this embodiment, the image 211 is a face image. Generally, the position of a region of interest in a face image can be extracted using a face detection algorithm such as pattern recognition or machine learning, and the biosignal 216 is calculated using pixel values ​​or time-series data of pixel values ​​in the extracted region of interest.

[0025] The biological information calculation unit 206 calculates biological information relating to blood vessels or blood flow from the biological signal 216. In this embodiment, the biological information is, for example, blood pressure.

[0026] The model selection unit 207 selects an appropriate model from among the blood pressure calculation models stored in the model storage unit 215 based on the exercise information 210 received by the input unit 201. In the present disclosure, a model includes a machine learning model, a regression equation, a mathematical formula, or a table for calculating biological information. Note that feature quantities generated from the exercise information 210 can be used in the model. For example, the following features included in the exercise information 210 can be used: "type of exercise, intensity, or load, such as the intensity of exercise or the burden on the body," "exercise duration, load, amount, or number of repetitions," and "exercise end time or the elapsed time from the end of exercise to measurement by the measurement device 100," which are described below. For example, a polynomial consisting of the exercise information 210 and coefficients to be multiplied by each may be created, or in the case of a machine learning model using a decision tree, the exercise information 210 may be used as a branching condition.

[0027] Furthermore, rather than using the exercise information 210 as a feature directly, a new feature may be generated. For example, a feature may be created by summarizing multiple pieces of exercise information 210 using principal component analysis. Here, the definition of "model" also includes a correction formula for the value of a feature. For example, a correction formula for correcting the value of a feature can be created using the "type, intensity, or load of exercise, i.e., the intensity of exercise or the burden on the organism," "exercise duration or load, amount, or number of times," and "exercise end time or the elapsed time from the end of exercise to measurement by the measuring device 100," which will be described later. Information on which model was selected by the model selection unit 207 is output as the determination result 217.

[0028] The biometric information calculation unit 206 receives the determination result 217 and calculates the biometric information using the model selected based on the determination result 217.

[0029] The output unit 202 receives a report 212 created by the control unit 204 from the biometric information and outputs it as needed. The report 212 is the biometric information itself or biometric information that has been processed or edited according to the user's needs, and specifically includes the value of the biometric information itself, a graph of the progress of the biometric information, analysis results, evaluation, or summary of the biometric information, a log or progress of the user's exercise information, etc. The procedures for such processing or editing are stored in advance in the storage unit 203.

[0030] The storage unit 203 is a recording medium capable of recording various data, programs, etc., and is configured from a hard disk, an SSD (Solid State Drive), a semiconductor memory, etc. The storage unit 203 includes a measurement information storage unit 213, a biological information storage unit 214, and a model storage unit 215. Note that while Fig. 2 illustrates an example of a configuration in which the storage unit 203 is provided in the measuring device 100, the storage unit 203 may also be configured from a server connected to the measuring device 100 via a network. For example, the network may be the Internet or a LAN (Local Area Network).

[0031] The measurement information storage unit 213 stores pre-stored programs necessary for measuring biological information, information registered by the user, etc. The measurement information storage unit 213 stores, for example, a calculation formula for converting the image 211 into a pulse wave, a signal processing algorithm for reducing noise in the pulse wave, measurement conditions such as the measurement time required to calculate the biological information, a biological signal 216, and analysis results of the biological signal 216. For example, the user is the living body 102, or the administrator of the measuring device 100, or the manufacturer of the measuring device 100.

[0032] The biometric information storage unit 214 stores information related to the living body 102, such as input data, measured data, and information on calculated results. The biometric information storage unit 214 stores necessary information, such as an image 211, exercise information 210, biometric information calculated from the image 211, a report 212, a biometric signal 216, and analysis results of the biometric signal 216.

[0033] The model storage unit 215 stores multiple pieces of reference information. The multiple pieces of reference information according to this embodiment indicate multiple models used to calculate biological information. Specifically, the model storage unit 215 stores multiple models, pre-stored programs related to the models, information related to the models registered by the user, and the like. Multiple models are stored and can be selected by the model selection unit 207. The stored contents can also be changed by the user.

[0034] 3 is a schematic diagram showing an example of an input screen shown to the user. In this embodiment, the user inputs exercise information 210 from the input unit 201.

[0035] The exercise information 210 to be input mainly includes "the type of exercise, intensity or load, such as the intensity of the exercise or the burden on the living body," "the duration or load, amount and number of times of exercise," and "the end time of exercise (the time when exercise is finished) or the elapsed time from the end of exercise to measurement by the measuring device 100." The elapsed time from the end of exercise to measurement by the measuring device 100 is the elapsed time from the end of exercise to the time when the imaging unit 101 images the living body 102.

[0036] During exercise, blood vessels expand to pump large amounts of blood into the body, but this state can continue even after exercise, causing changes in vascular status. The degree and duration of this change vary depending on the type of exercise, and it has been reported that vascular status does not return to normal for several hours after intense or prolonged exercise. The manifestation of this change can also vary depending on whether the exercise is high-intensity or habitually involves exercise that places strain on the heart. Therefore, machine learning models created using vascular data measured during non-exercise periods or vascular data from subjects who do not habitually exercise may have poor accuracy in calculating post-exercise biometric information when vascular status changes. Therefore, it is desirable to use data from the exercise information 210 and select and use an appropriate model that takes into account the changes in vascular status caused by exercise.

[0037] Therefore, it is desirable that the input exercise information 210 includes all three pieces of information: "type of exercise, intensity, or load, such as the intensity of exercise or the burden on the organism," "exercise duration or load, amount, and number of times," and "end time of exercise or the time from the end of exercise to measurement by the measuring device 100." Although any one of these pieces of information can improve the accuracy of calculation of biological information, having all three pieces of information can further improve the accuracy of calculation. Note that "type of exercise, intensity, or load" and "exercise duration or load, amount, and number of times" may be combined into a single comprehensive index by multiplying the two together. Examples of comprehensive indexes include "METs" or "total load," which will be described later.

[0038] FIG. 3 illustrates input items for obtaining these three pieces of information. "METs of today's exercise" is an item that represents a comprehensive index that combines "type, intensity, or load of exercise" and "type of exercise performed today and duration or load, volume, and number of repetitions." Furthermore, "type of exercise performed today and duration or load, volume, and number of repetitions" is an item that represents the duration of exercise. Finally, "time elapsed from today's exercise to measurement or end time of exercise" is an item that represents the end time of exercise or the time elapsed from the end of exercise to measurement by the measuring device 100. Furthermore, because it is desirable to collect information such as whether the subject habitually engages in high-intensity exercise or exercise that places a strain on the heart in order to improve the calculation accuracy of biometric information, an input item for "exercise habits" is provided in FIG. 3 . Because FIG. 3 is merely an example, calculation accuracy can be improved even if information on all items is not necessarily obtained. However, calculation accuracy can be further improved if all of this information is available.

[0039] "METs" in Figure 3 indicates the intensity of activity by how many times more energy is consumed compared to when the resting state is set to 1. METs are widely used and are calculated by multiplying the value of the unit of exercise intensity called MET (Metabolic Equivalent) by the duration of exercise (s), giving "MET·hours."

[0040] Although the "type of exercise performed today" is exemplified as running and lifting in Figure 3, it is not limited to this. For example, if used at a gym, the name of a training machine such as a treadmill may also be used.

[0041] For "each exercise duration or load, volume, and number of repetitions," enter the duration for running, or the number of repetitions for weight training, where repetition is important. As shown in Figure 3, it is preferable to enter data for each type of exercise, but if this is not possible, it is acceptable to enter the duration of all exercises. However, since each type of exercise places different strains on the body, it is preferable to enter data. Note that if it is possible to enter an index that combines the intensity and volume of exercise using indices such as METs or total load, these can be used in place of the exercise duration and volume items, so these items are not necessarily required.

[0042] The above two items are not limited to the examples shown in Figure 3 and can be appropriately selected depending on the type of exercise. For example, exercise intensity can be expressed by heart rate, or in the case of strength training, an index such as RM (Repetition Maximum) can be used, or a comprehensive index combining multiple items such as total load can be used. Furthermore, exercise intensity can be an absolute value, or it can be based on the physical ability of the living body 102, such as the Rate of Perceived Exertion.

[0043] Regarding "the end time of today's exercise or the elapsed time from the end of exercise to the measurement," if the measurement device 100 has a clock function, the end time of exercise can be used to calculate the elapsed time from the end of exercise to the measurement by the measurement device 100, so there is no need to input the elapsed time from the end of exercise to the measurement. Note that although the "elapsed time from the end of exercise to the measurement" is input in minutes in the figure, it can also be input in hours or seconds.

[0044] "Exercise habits" is an input item that allows for obtaining such information, since measurements by the inventor have revealed that the manifestation of blood flow or vascular modulation after exercise varies depending on whether the exercise is intense or cardio-intensive, such as in a track and field club, and on the frequency of such exercise. Note that in Figure 3, the number of times per week that a person participates in club activities is entered, but this notation is not necessarily limited to this, and other notations may be used as long as the above-mentioned information can be obtained.

[0045] Although the accuracy of calculation of biological information can be improved without inputting the "exercise habits" item, inputting the information can further improve the accuracy of calculation.

[0046] Although only exercise is input in Figure 3, this is not a limitation, and any activity that involves stress on the body or heart is not limited to exercise. For example, items for inputting activities such as eating, sleeping, climbing stairs, and conversation may be provided. Also, although all items are input in Figure 3, this is not a limitation, and items that cannot be input can be left blank on the input screen.

[0047] FIG. 4 is a flowchart showing an example of the operation of the measurement device 100 according to this embodiment.

[0048] In step S401, the user inputs the exercise information 210. As a result, the input unit 201 accepts the exercise information 210 input by the user.

[0049] In step S402, the imaging unit 101 acquires an image 211. For the sake of explanation, in this embodiment, the kinetic information 210 is input first in step S401, but this is not limiting. The image 211 does not necessarily have to be acquired after the input unit 201 accepts the kinetic information, as long as the kinetic information 210 can be used to improve the accuracy of the calculation of the biometric information. For example, if a dialogue such as "May I calculate the biometric information using this image?" is held between the user and the measurement device 100 after the image 211 is acquired, the kinetic information 210 may be input during that dialogue. Furthermore, if the user realizes that they forgot to input the kinetic information 210 after the image 211 is acquired, the user may be able to re-input it later. For example, the system may be provided with a function such as a recalculation mode or a high-accuracy mode, in which the user first briefly inputs the kinetic information 210, and then recalculates the biometric information to further improve accuracy if the user feels that the calculated biometric information is abnormal.

[0050] In step S403, the signal acquisition unit 205 acquires a biosignal 216 from the image 211 acquired by the imaging unit 101. For example, a pulse wave is calculated from RGB pixel values ​​of a region of interest in the image 211 using a calculation formula stored in advance in the storage unit 203. In this case, the biosignal 216 is time-series data such as a pulse wave. It is desirable to appropriately determine a means for acquiring the biosignal 216 depending on the vital sign to be measured. For example, the pulse wave may be acquired as a time change in a value calculated by substituting the brightness value of the image 211 into a predetermined formula, or may be acquired as a pulse wave converted into absorbance or the like, or may be acquired by extracting a biosignal using independent component analysis or the like. For example, in calculating blood pressure, a volume pulse wave can be obtained using a conversion formula using absorbance by utilizing the fact that hemoglobin concentration correlates with the degree of light absorption by blood vessels, and blood pressure can be calculated from the state of the volume pulse wave.

[0051] In step S404, the control unit 204 stores the biosignal 216 in the measurement information storage unit 213 or the bioinformation storage unit 214. While the biosignal 216 is stored for various reasons, such as allowing a new analysis to be performed using the biosignal 216 at a later date, recalculation using an updated model, and use as a log, it is not necessarily stored. The server may collect exercise information and calculated bioinformation for multiple users from the measurement device 100. For example, the server may be connected to the measurement device 100 via a network. The server may then update multiple models based on the collected exercise information and bioinformation. In this case, the control unit 204 acquires the updated models from the server and stores the acquired models in the model storage unit 215.

[0052] In step S405, the model selection unit 207 selects an optimal model from among the models stored in the model storage unit 215 based on the exercise information 210 received in step S401. The criteria or formula for judgment are stored in advance in the model storage unit 215. For example, if METs is 7 or more and the subject has been exercising up until 30 minutes before the measurement, a model that takes post-exercise hypotension into consideration may be selected.

[0053] In step S406, the biological information calculation unit 206 calculates biological information from the biological signal 216 using the model selected by the model selection unit 207. That is, the biological information calculation unit 206 calculates biological information from the biological signal 216 using reference information selected from the plurality of pieces of reference information stored in the storage unit 203 based on the motion information 210.

[0054] In step S407, the control unit 204 creates a report 212, which is information to be displayed to the user, based on the biometric information as needed, and outputs it to the output unit 202. The output unit 202 outputs the report 212 to the user as needed.

[0055] In step S408, the control unit 204 stores the bio-information and exercise information 210 in the storage unit 203 as necessary.

[0056] In this way, the measuring device 100 according to this embodiment is capable of performing non-contact measurement using only a camera, without using a cuff sphygmomanometer, a contact-type acceleration sensor, etc. Therefore, the measuring device 100 according to this embodiment can reduce the burden on the user compared to when using a cuff sphygmomanometer, a contact-type acceleration sensor, etc.

[0057] Furthermore, the measuring device 100 according to this embodiment calculates biological information related to blood vessels and blood flow by incorporating information about the exercise the user performed before measurement. This allows the measuring device 100 according to this embodiment to accurately calculate biological information in a non-contact manner, taking into account the effects of exercise on blood vessels and blood flow.

[0058] Second Embodiment The second embodiment will be described with reference to Figures 5 and 6. In the drawings, the same or equivalent elements are denoted by the same reference numerals, and redundant explanations will be omitted.

[0059] Fig. 5 is a block diagram showing an example of the configuration of a measurement device 500 according to this embodiment. The measurement device 500 shown in Fig. 5 differs from the measurement device 100 shown in Fig. 2 in that the measurement device 500 includes a biological information calculation unit 506, a correction information selection unit 507, and a correction information storage unit 515 shown in Fig. 5 instead of the biological information calculation unit 206, the model selection unit 207, and the model storage unit 215 shown in Fig. 2.

[0060] The measuring device 100 shown in the first embodiment selects a model based on the motion information 210 received by the input unit 201, but the measuring device 500 according to the present embodiment does not select a model, but instead calculates pre-correction bioinformation related to blood vessels or blood flow from the biosignal 216 using a predetermined model, and corrects the pre-correction bioinformation using the correction information selected based on the motion information 210 to calculate the bioinformation.

[0061] A plurality of pieces of reference information are stored in the correction information storage unit 515. The plurality of pieces of reference information according to this embodiment indicates a plurality of pieces of correction information used to correct the pre-correction biometric information. That is, the correction information storage unit 515 stores a plurality of pieces of correction information.

[0062] The correction information selection unit 507 selects correction information from the plurality of pieces of correction information stored in the correction information storage unit 515 based on the motion information 210. In other words, the correction information selection unit 507 selects appropriate correction information according to the motion information 210 from the plurality of pieces of correction information.

[0063] The correction information includes, for example, a correction formula, correction conditions, a table for correction, etc. Rules, conditions, criteria, formulas, etc. used to select the correction information are stored in the correction information storage unit 515 in advance.

[0064] The server may collect exercise information and calculated biological information for multiple users from the measurement device 500. The server may then update multiple pieces of correction information based on the collected exercise information and collected biological information. In this case, the control unit 204 obtains the updated pieces of correction information from the server and stores the obtained pieces of correction information in the correction information storage unit 515.

[0065] Alternatively, the server may collect the exercise information and the calculated biological information in association with information identifying the user. The server may then update the correction information for each user based on the collected exercise information and the collected biological information. The control unit 204 acquires the correction information from the server in association with the information identifying the user, and stores the acquired correction information in association with the information identifying the user in the correction information storage unit 515.

[0066] The biological information calculation unit 506 according to this embodiment calculates pre-correction biological information from the biological signal 216 and corrects the pre-correction biological information using the selected correction information, thereby calculating biological information.

[0067] For example, if the exercise information 210 indicates that METs is 7 or more and that the person had been exercising until 30 minutes before the measurement, the correction information selection unit 507 selects correction information indicating a correction formula using these numerical values ​​indicated by the exercise information 210. Then, the biological information calculation unit 506 calculates the biological information by correcting the pre-correction biological information using the correction formula indicated by the selected correction information.

[0068] For example, if multiple correction formulas are created in advance by measuring blood pressure over time for each user after exercise and stored in the correction information storage unit 515, the correction information selection unit 507 can select a correction formula from the multiple correction formulas based on the exercise information 210. Alternatively, instead of a formula, a correspondence table indicating correction values ​​to be used depending on the content of the exercise information may be stored in the correction information storage unit 515. In this case, the correction information selection unit 507 selects a correction value to be used based on the exercise information 210 by referring to the correspondence table stored in the correction information storage unit 515. Then, the biological information calculation unit 506 corrects the uncorrected biological information using the selected correction value.

[0069] 6 is a flowchart showing an example of the operation of the measurement device 500 according to this embodiment. Note that detailed explanations of steps similar to the steps illustrated in FIG.

[0070] In step S605, the biological information calculation unit 506 calculates the pre-correction biological information from the biological signal 216. Specifically, the biological information calculation unit 506 calculates the pre-correction biological information using a predetermined model.

[0071] In step S606, the correction information selection unit 507 selects correction information according to the exercise information 210. Specifically, the correction information selection unit 507 determines the correction information to be used from the correction information stored in the correction information storage unit 515 based on the exercise information 210.

[0072] In step S607, the biometric information calculation unit 506 corrects the pre-correction biometric information calculated in step S605 using the selected correction information, thereby calculating the biometric information to be output by the output unit 202. The subsequent processing is the same as the processing exemplified in Fig. 4, and therefore will not be described.

[0073] In this way, the measuring device 500 according to this embodiment corrects biological information related to blood vessels and blood flow by reflecting information about the exercise the user performed before measurement. As a result, the measuring device 500 according to this embodiment corrects biological information taking into account the effects of exercise on blood vessels and blood flow, and can accurately calculate biological information in a non-contact manner.

[0074] The processes performed in the above embodiments are not limited to the processing modes exemplified in the above embodiments. The above-described functional blocks may be implemented using either a logic circuit (hardware) formed on an integrated circuit or software using a CPU. The processes performed in the above embodiments may be executed by multiple computers. For example, some of the processes executed by each functional block of the measurement device 100 may be executed by another computer, or all of the processes may be shared and executed by multiple computers. That is, a measurement system including multiple computers may be configured to include an imaging unit 101, an input unit 201, an output unit 202, a memory unit 203, a signal acquisition unit 205, a biometric information calculation unit 506, and a model selection unit 207. Alternatively, a measurement system including multiple computers may be configured to include an imaging unit 101, an input unit 201, an output unit 202, a memory unit 503, a signal acquisition unit 205, a biometric information calculation unit 506, and a correction information selection unit 507.

[0075] The present disclosure is not limited to the above-described embodiments, and may be replaced with a configuration that is substantially the same as the configuration shown in the above-described embodiments, a configuration that achieves the same effect, or a configuration that can achieve the same purpose. The present disclosure also includes within its technical scope embodiments obtained by appropriately combining the technical means disclosed in different embodiments. Furthermore, new technical features can be formed by combining the technical means disclosed in each embodiment. [Explanation of symbols]

[0076] 100 Measuring device, 101 Imaging unit, 102 Living body, 201 Input unit, 202 Output unit, 203 Memory unit, 204 Control unit, 205 Signal acquisition unit, 206 Living body information calculation unit, 207 Model selection unit, 210 Exercise information, 211 Image, 212 Report, 213 Measurement information memory unit, 214 Living body information memory unit, 215 Model memory unit, 216 Living body signal, 217 Determination result, 500 Measuring device, 503 Memory unit, 506 Living body information calculation unit, 507 Correction information selection unit, 515 Correction information memory unit

Claims

1. an imaging unit that captures an image of a living body; a signal acquisition unit that acquires a biological signal that is a value related to the living body calculated from the image; an input unit to which information about an exercise performed by the living body before the imaging unit acquires the image is input as exercise information; a biological information calculation unit that calculates biological information related to blood vessels or blood flow from the biological signal using reference information selected from a plurality of reference information based on the motion information; Equipped with Measuring equipment.

2. The exercise information includes at least one selected from the group consisting of (i) at least one selected from the group consisting of type, intensity, and load, (ii) at least one selected from the group consisting of duration, number of times, and amount of exercise, and (iii) at least one of the time the exercise ended and the elapsed time from the end of the exercise until the imaging unit images the living body. The measuring device according to claim 1 .

3. the plurality of reference information indicates a plurality of models; a storage unit that stores the plurality of models; a model selection unit that selects a model that is the selected reference information from the plurality of models; Furthermore, The biological information calculation unit calculates the biological information from the biological signal using the model.

3. The measuring device according to claim 1 or 2.

4. The model uses features generated from the motion information. The measuring device according to claim 3 .

5. The model includes a correction formula for the value of the feature amount.

5. The measuring device according to claim 4.

6. the plurality of pieces of reference information indicate a plurality of pieces of correction information, a storage unit that stores the plurality of pieces of correction information; a correction information selection unit that selects correction information that is the selected reference information from the plurality of correction information; Further preparation, The biological information calculation unit calculates pre-correction biological information related to blood vessels or blood flow from the biological signal, and calculates the biological information by correcting the pre-correction biological information using the correction information.

3. The measuring device according to claim 1 or 2.

7. an imaging unit that captures an image of a living body; a signal acquisition unit that acquires a biological signal that is a value related to the living body calculated from the image; an input unit to which information about an exercise performed by the living body before the imaging unit acquires the image is input as exercise information; a biological information calculation unit that calculates biological information related to blood vessels or blood flow from the biological signal using reference information selected from a plurality of reference information based on the motion information; Equipped with Measurement system.

8. A step of capturing an image of a living body; acquiring a biological signal, which is a value related to the living body calculated from the image; inputting information about the exercise performed by the living body before the image was acquired as exercise information; calculating biological information relating to blood vessels or blood flow from the biological signal using reference information selected from a plurality of pieces of reference information based on the motion information; Contains Measurement method.

Images