Method for estimating bio-information

Abstract

The present invention relates to a method for estimating bio-information. The present invention includes the steps of: applying bio-signals measured at a first location by a signal measuring device and externally measured and input bio-information to a bio-information estimation algorithm and thereby calibrating the bio-information estimation algorithm to be suitable for a user; additionally obtaining bio-signals of the user for a predetermined time at a location other than the first location using the signal measuring device; and applying the additionally obtained bio-signal to the bio-signal estimation algorithm and thereby generating an estimation value of additional bio-information corresponding to the predetermined time.

Description

Biometric information estimation method

[0001] The present invention relates to a biometric information estimation method, and more particularly, to a biometric information estimation method that calibrates a biometric information estimation algorithm at a first location, collects additional biometric information for a predetermined period of time at a location other than the first location, and generates an estimate value for the additional biometric information using the biometric information estimation algorithm, so that the biometric information estimate value during the observation period allocated to the predetermined period of time can be used for diagnosis.

[0002] Electrocardiogram (ECG) monitoring devices are widely used in the clinical diagnosis of heart disease and can be used to diagnose conditions such as myocardial infarction and pulmonary embolism. In particular, people with or suspected of having heart disease need to be able to detect or receive early warning of sudden cardiac abnormalities.

[0003] Electrocardiogram (ECG) devices attach electrodes to the body to detect the minute electrical signals generated by the heartbeat. However, conventional ECG devices suffer from the problem of being uncomfortable for the examiner to wear due to the size of the electrodes.

[0004] Meanwhile, wearable devices are being used in a variety of ways to detect biosignals such as blood pressure. Most conventional wearable devices are worn on the wrist. However, this type of wearable device has limitations, such as low reliability of biosignal data, as the wearable device does not come into contact with any part of the body other than the wearer.

[0005] To address the low reliability of biosignal data in conventional wearable devices, a ring-shaped sensing device is being developed that can improve the reliability of biosignal data. Conventional ring-shaped sensing devices may include an inner ring, an outer ring, and a top cover, and can be manufactured by assembling various components.

[0006] A ring-type sensing device can obtain a PPG signal (Photoplethysmography) from a user, derive blood vessel elasticity information using the characteristic values ​​of the PPG signal, and estimate blood pressure using the blood vessel elasticity information. Estimating blood pressure using the PPG signal in this way allows for simpler and easier blood pressure estimation compared to the conventional method using a cuff blood pressure monitor. However, since the method of estimating blood pressure using the PPG signal using the ring-type sensing device is not a direct measurement method like a cuff, there is a need to improve the accuracy of the measurement. The present invention proposes a method for estimating biometric information that improves the accuracy of the biometric information estimation value using the ring-type sensing device, and in particular, improves the accuracy for biometric signals collected over a predetermined period of time rather than at a specific point in time, so that it can be used as reliable biometric information.

[0007] The present invention is intended to solve the above-described problem, and provides a biometric information estimation method that calibrates a biometric information estimation algorithm at a first location, collects additional biometric information for a predetermined period of time at a location other than the first location, and generates an estimation value for the additional biometric information using the biometric information estimation algorithm, so that the biometric information estimation value during the observation period allocated to the predetermined period of time can be used for diagnosis.

[0008] In addition, the present invention aims to provide a biometric information estimation method that improves the accuracy of a biometric information estimation value by first calibrating a biometric information estimation algorithm at a first location, performing additional calibration again at the first location after a predetermined time using the additional biometric information, and correcting the biometric information estimation value by reflecting the user's biometric information change characteristics during the predetermined observation period.

[0009] A bio-information estimation method according to an embodiment of the present invention is characterized by including the steps of: applying a bio-signal measured by a signal measuring device at a first location and bio-information measured and input from the outside to a predetermined bio-information estimation algorithm to calibrate the bio-information estimation algorithm to suit the user; additionally acquiring a bio-signal of the user using the signal measuring device for a predetermined period of time at a location other than the first location; and applying the additionally acquired bio-signal to the bio-signal estimation algorithm to generate an estimate value of additional bio-information corresponding to the predetermined period of time.

[0010] Additionally, the method may include assigning a predetermined serial number to a user and matching the serial number with the signal measuring device.

[0011] In addition, the additional biometric information estimation value is generated at the first location, and the additional biometric information estimation value can be calculated after performing an additional calibration step of re-calibrating the biometric estimation algorithm using a biometric signal measured by a signal measuring device at the first location and biometric information measured and input from the outside.

[0012] Additionally, the estimated value of the additional biometric information may include a step of outputting it in an identifiable form.

[0013] Additionally, after the additional biometric information estimate is generated, the step of recovering, disinfecting, and charging the signal measuring device may be included.

[0014] Additionally, the first location may be a hospital that performs treatment for the user, and the period during which the user wears the signal measuring device at a location other than the first location to collect additional bio-signals may be set to at least one day.

[0015] Additionally, the biometric information may include blood pressure, blood sugar, or oxygen saturation.

[0016] Additionally, the biosignal may include at least one of the user's photoplethysmography signal (PPG signal), electrocardiogram (ECG), or electroencephalogram (EEG) signal.

[0017] Additionally, the signal measuring device may be a ring-shaped measuring device that can be worn by a user.

[0018] In addition, the additionally acquired bio-signal includes the bio-signal measured in at least two different states of the user, and includes a feature extraction step of deriving the user's unique bio-information change characteristics from the bio-signals in the different states, and the additional calibration step of the bio-information estimation algorithm can correct the bio-information estimation value by calibrating the bio-information estimation algorithm by reflecting the user's unique bio-information change characteristics extracted by the feature extraction step.

[0019] Additionally, the above different states may be states in which the user's heart rate or peripheral resistance is in different environments.

[0020] In addition, the signal measuring device can collect a user's optical volume change signal through the first sensor unit and detect the user's movement through the second sensor unit.

[0021] In addition, when a predetermined first pattern is measured for a specified time by the second sensor unit, it can be determined that the user is in the first state, and when a predetermined second pattern is measured for a specified time by the second sensor unit, it can be determined that the user is in the second state.

[0022] In addition, the feature extraction step performs pseudo-labeling for labeling bio-signals measured in different user states from the signal measurement device, and the additional calibration step of the bio-information estimation algorithm selects a high-quality signal that satisfies a predetermined standard among the pseudo-labeled bio-signals and utilizes it for calibration of the bio-information estimation algorithm.

[0023] In addition, the superior quality signal may include a first superior quality signal that satisfies a predetermined first criterion among the first measurement values ​​measured in the first state, and a second superior quality signal that satisfies a predetermined second criterion among the second measurement values ​​measured in the second state.

[0024] The biometric information estimation method according to the present invention comprises calibrating a biometric information estimation algorithm at a first location, collecting additional biometric information for a predetermined period of time at a location other than the first location, and generating an estimated value for the additional biometric information using the biometric information estimation algorithm, thereby enabling the biometric information estimation value during an observation period allocated to the predetermined period of time to be utilized for diagnosis. Since the observation period is not limited to the space and time of the first location, user convenience can be improved.

[0025] In addition, the present invention can provide an effect of improving the accuracy of a biometric information estimation value by first calibrating a biometric information estimation algorithm at a first location, performing additional calibration at the first location after a predetermined period of time, and calculating a biometric information estimation value by reflecting the user's unique biometric information change characteristics during the predetermined observation period.

[0026] Figure 1 is a drawing illustrating a signal measuring device employed in an embodiment of the present invention.

[0027] Figure 2 is an exploded perspective view of Figure 1.

[0028] Figure 3 is a diagram illustrating a process of a biometric information estimation method according to an embodiment of the present invention.

[0029] Figure 4 is a block diagram of a bio-information estimation system according to an embodiment of the present invention.

[0030] Figure 5 is a diagram illustrating a process in which a biometric information estimation value is calibrated by a first sensor unit, a second sensor unit, a state determination unit, a characteristic extraction unit, and a control unit.

[0031] Figure 6 is a drawing showing a process in which a state determination unit determines different states using a first sensor unit and a second sensor unit.

[0032] Figure 7 is a diagram showing the process of determining the sleep state by the state determination unit.

[0033] This specification clarifies the scope of the present invention and explains the principles of the invention and discloses embodiments thereof to enable those skilled in the art to practice the invention. The disclosed embodiments may be implemented in various forms.

[0034] Expressions such as “includes” or “may include” that may be used in various embodiments of the present invention indicate the existence of the disclosed function, operation, or component, etc., and do not limit one or more additional functions, operations, or components, etc. In addition, in various embodiments of the present invention, it should be understood that terms such as “includes” or “has” are intended to specify the existence of a feature, number, step, operation, component, part, or combination thereof described in the specification, and do not exclude in advance the possibility of the existence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0035] When a component is referred to as being "connected, coupled" to another component, it should be understood that while the component may be directly connected or coupled to the other component, there may also be a new component between the component and the other component. Conversely, when a component is referred to as being "directly connected" or "directly coupled" to another component, it should be understood that no new component exists between the component and the other component.

[0036] The terms "first," "second," etc., used herein may be used to describe various components, but the components should not be limited by the terms. The terms are used solely to distinguish one component from another.

[0037]

[0038] The present invention relates to a biometric information estimation method, and provides a biometric information estimation method that estimates biometric information using a biometric information estimation algorithm at a first location, and then corrects the estimated biometric information at the first location using biometric information collected for a predetermined period of time at a location other than the first location, thereby improving the accuracy of the biometric information estimation value. In particular, the present invention can allocate the predetermined period of time at a location other than the first location, and this predetermined period of time can be provided as an observation time for collecting biometric information of the user and observing signs of the user's biological activity, and since this observation time can be secured regardless of the first location, it can overcome spatial and temporal limitations, and thus can provide an effect that can be used for diagnosis, etc. in a completely new way compared to currently used biometric information acquisition methods.

[0039]

[0040] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the attached drawings. As illustrated in FIG. 1, a biometric information estimation method according to the present invention includes a step (100) of calibrating a biometric information estimation algorithm, a step (200) of additionally acquiring a user's biometric signal, and a step (300) of generating an estimated value of additional biometric information.

[0041]

[0042] The step (100) of calibrating a bio-information estimation algorithm is a step of applying a bio-signal measured by a signal measuring device (10) at a first location and bio-information measured and input from the outside to a predetermined bio-information estimation algorithm (20) as illustrated in FIG. 1, thereby calibrating the bio-information estimation algorithm to suit the user.

[0043] In the present invention, the bio-information may include the user's blood pressure, blood sugar, or oxygen saturation. For example, blood pressure may be measured by a conventional cuff blood pressure monitor. In addition, the bio-signal may include an electrocardiogram (ECG), an electroencephalogram (EEG), etc., in addition to the PPG signal obtained from the user. The signal measuring device (10) may collect at least one of the PPG signal, the ECG signal, and the EEG signal. The bio-information and bio-signal are not limited to those described above, and various types of information or signals may be used as long as they are information or signals that can be utilized for diagnosing a user's disease.

[0044] In the present embodiment, the signal measuring device (10) may be a ring-shaped measuring device that measures the user's bio-signals. In addition, the first location may be, for example, a hospital including a clinic or public health center that treats patients. That is, when the user visits a hospital to receive a diagnosis, the user may collect bio-signals using the signal measuring device (10) according to the doctor's decision. For example, when measuring blood pressure, blood pressure (biological information) may be obtained using a cuff blood pressure monitor, a PPG signal may be obtained from the signal measuring device (10), and the bio-information estimation algorithm (20) may be calibrated to fit the user by applying the obtained signal to a predetermined bio-information estimation algorithm.

[0045] In addition, according to the present embodiment, in the step (100) of calibrating the biometric information estimation algorithm, a step of assigning a predetermined serial number to the user and matching the serial number with the signal measuring device (10) may be included. By individually matching and distributing the signal measuring device (10) to the user, it is possible to efficiently manage that the biometric information acquired from the signal measuring device (10) is acquired from the specific user. As illustrated in FIG. 2, the present invention can go through a login process in an application or on the web, and for example, in a first location, a hospital, a user can be assigned a serial number as a patient and each patient can be matched with a ring-type signal measuring device (10).

[0046]

[0047] The step (200) of additionally acquiring the user's bio-signal is a step of additionally acquiring the user's bio-signal using the signal measuring device (10) for a predetermined period of time at a location other than the first location. According to the present embodiment, the location other than the first location may be a location distinct from the location where the first calibration step is performed. For example, if the first location is a hospital, the location other than the first location may include accommodations, homes, etc. other than the hospital. However, if the first location is a hospital, the location other than the first location may be a hospital room. That is, the first location may be a treatment room, and the location other than the first location may be an inpatient ward, and the patient's bio-signal may be additionally acquired continuously or discontinuously for a predetermined period of time. In addition, as illustrated in FIG. 2, according to the present embodiment, the predetermined period of time may be set to at least one day. For example, the user may wear the signal measuring device (10) and allow the signal measuring device (10) to acquire his / her bio-information for at least one day outside the hospital.

[0048]

[0049] The step (300) of generating an estimated value of the additional bio-information is a step of applying the additionally acquired bio-signal to the bio-signal estimation algorithm (20), as illustrated in FIG. 1, to generate an estimated value of the additional bio-information corresponding to the predetermined period. The additional bio-information may be provided to the bio-information estimation algorithm (20) at a first location. Of course, the location where the additional bio-information is provided to the bio-information estimation algorithm (20) is not limited to the first location. After the first calibration as described above, the bio-information estimation algorithm (20) may be provided with the additional bio-information and may produce an estimated value of the bio-information corresponding thereto.

[0050] In the present embodiment, the biometric estimation algorithm may further include an additional calibration step (400). That is, after a predetermined period of time for additionally acquiring the biometric signal has elapsed, the biometric estimation algorithm (20) may be recalibrated using the biometric signal measured by the signal measurement device (10) and the biometric information measured and input from the outside. For example, after the first calibration is performed at the first location, additional biometric information may be collected at a location other than the first location, and then additional calibration may be performed again at the first location. The additional calibration is a calibration performed separately in time from the first calibration performed at the first location, and may be selectively performed as a secondary calibration as illustrated in FIG. 1. After the biometric estimation algorithm (20) is calibrated for the second time, the additionally acquired biometric signal may be applied to produce a biometric information estimation value. The additional calibration step (400) can be performed substantially identically to the first calibration.

[0051] Meanwhile, when secondary calibration is performed, the user's unique biometric information can be reflected and calibrated. During this process, the biometric estimation algorithm is calibrated to reflect the user's unique characteristics, resulting in more accurate biometric estimates. The process of reflecting the user's unique biometric information is described later.

[0052] As illustrated in FIG. 3, additional calibration reflecting unique characteristics may include a user status determination step (501) and a feature extraction step (502). The status determination step (501) is a step for determining different user statuses from bio-signals measured in at least two different user statuses. The different statuses may be states in which the user's heart rate or peripheral resistance is in different environments.

[0053] In addition, according to an embodiment of the present invention, a feature extraction step (502) for deriving a user's unique bio-information change characteristic from the bio-signals acquired in the above mutual state may be included. Accordingly, the additional calibration step (400) of the bio-information estimation algorithm may be performed substantially in the same manner as the first calibration, or the bio-information estimation algorithm may be calibrated by reflecting the user's state and unique bio-information change characteristic extracted by the state determination step (501) and the feature extraction step, thereby more precisely correcting the bio-information estimation value.

[0054]

[0055] As illustrated in FIG. 2, according to the present embodiment, once the biometric information estimate is calculated, the step (600) of outputting the estimate in an identifiable form may be further included. The identifiable form may be in the form of a report. The report may be provided online on a website or output externally.

[0056] Additionally, according to an embodiment of the present invention, after an estimated value for additional biometric information is generated, a step (700) of recovering, disinfecting, and charging the signal measuring device (10) may be performed. For example, when a user revisits the hospital and an estimated value for additional biometric information is generated through additional calibration, the signal measuring device (10) provided to the user may be recovered, disinfected, and charged for storage, and may be provided to other users in the future.

[0057]

[0058] The above-described bio-information estimation method can be implemented as a system specifically including a signal measuring device (10), a bio-information estimation algorithm (20), a feature extraction unit (30), a status determination unit (40), a display unit (50), and a control unit (50). Each component is described in detail below.

[0059]

[0060] The signal measuring device (10) is provided to measure the user's bio-signal. According to the present embodiment, the signal measuring device (10) may include a first sensor unit (11) that collects the user's photoplethysmography signal (PPG signal). Using the PPG signal, it is possible to analyze characteristics related to the user's bio-information, such as PTT (Pulse Transit Time) and HRV (Heart rate variation), and thereby, it can be used to derive an estimated value of bio-information related to heart rate (HR), blood pressure, etc. According to the present embodiment, the bio-information may include blood pressure, blood sugar, or oxygen saturation, and these bio-information can be estimated by applying a bio-signal obtained from the user to a bio-information estimation algorithm (20).

[0061] According to an embodiment of the present invention, the signal measuring device (10) can obtain an electrocardiogram (ECG), an electroencephalogram (EEG), etc. from the user in addition to the PPG signal in order to estimate bio-information. The signal measuring device (10) can collect at least one of a PPG signal, an ECG signal, and an EEG signal, but the user's bio-signals collected from the signal measuring device (10) are not limited thereto.

[0062] Additionally, according to the present embodiment, the signal measuring device (10) may include a second sensor unit (12) for detecting the user's movement. The second sensor unit (12) may be an acceleration sensor that measures the magnitude and amount of change in acceleration that occurs according to the movement pattern of the user's finger.

[0063] According to the present embodiment, the signal measuring device (10) may be provided in a wearable device that can be worn by a user. For example, the signal collection unit (10) may be implemented as a device in the form of a ring, band, or watch that can be worn on a finger, wrist, or ankle, or may be provided by being installed on clothing. That is, it may be implemented in various forms such as a ring type, a wristwatch type, a bracelet type, an anklet type, a wrist band type, an ankle band type, a hair band type, or a glasses type. Hereinafter, the signal measuring device (10) will be described in the case where it is a ring type that can be worn on a user's finger.

[0064] As shown in FIGS. 4 and 5, the signal collection device (10) may include an external electrode (101), an internal electrode (102), an insulation unit (103), a top cover (104), and a plurality of sensors (105).

[0065] The external electrode (101) may have an arc shape with an open section. The external electrode may be composed of a conductor and may function as an electrode for measuring an electrocardiogram (ECG) by coming into contact with the user's body. The external electrode (101) may form the exterior of a ring-shaped signal collection device (10).

[0066] The inner electrode (102) may have a ring shape and may be formed with a plurality of openings (106) to install a plurality of sensors (105). The inner electrode (102) may be formed of a conductor and may function as an electrode for measuring an electrocardiogram. In addition, the inner electrode (102) may form the inner ring of a ring and the inner electrode (102) may come into contact with a user's finger.

[0067] An insulating unit (103) may be placed between the external electrode (101) and the internal electrode (102). The insulating unit (103) may enable electrical insulation between the external electrode (101) and the internal electrode (102).

[0068] The top cover (104) may have an arc shape so as to close a portion of the external electrode (101), and may be formed with the same curvature as the external electrode (101) to form a ring together with the external electrode. The top cover (104) may be coupled to a portion of the portion between the external electrodes (101) to form the exterior of the ring-shaped signal collection device (10).

[0069] A plurality of sensors (105) may be arranged to protrude inwardly from the inner surface of the inner electrode (102) and come into contact with the user's finger. The plurality of sensors (105) may be arranged in each of the openings (106) of the inner electrode (102). The plurality of sensors (105) may be first sensor units (11) that collect PPG signals (photoplethysmograms) from the user at different locations. In addition, the signal collection device (10) may have a second sensor unit (12) arranged between the outer electrode (101) and the inner electrode (102). The second sensor unit (12) may be an acceleration sensor arranged between the outer electrode (101) and the inner electrode (102) to detect the user's movement. According to an embodiment of the present invention, the signal collection device (10) may be equipped with a separate sensor that collects electrocardiogram (ECG) signals and electroencephalogram (EEG) signals.

[0070]

[0071] The above bio-information estimation algorithm (20) is provided to estimate bio-information using the bio-signal. The above bio-information estimation algorithm (20) may be generated in a predetermined manner and embedded in a predetermined memory or control unit, etc.

[0072] The biometric information estimation algorithm (20) may be algorithmized to extract biometric information by extracting features from the user's biometric signal. Specifically, the biometric information estimation algorithm (20) may be algorithmized to extract a predetermined characteristic point from the user's biometric information and estimate the biometric information by using the extracted characteristic point and comparing it with the actually measured biometric information. For example, if the biometric information to be estimated is a blood pressure value, the algorithm may be algorithmized to extract a predetermined characteristic point from the user's PPG signal and compare it with the actually measured blood pressure value to estimate the blood pressure value. Hereinafter, the biometric information estimation algorithm (20) will be described using blood pressure estimation as an example. Of course, the biometric information estimation algorithm (20) may be provided as an algorithm for estimating blood sugar, oxygen saturation, etc.

[0073] The characteristic points of the PPG signal can be extracted from a specific point in time or a periodic signal. The specific point in time or the periodic signal can be selected from a biosignal that is continuously or intermittently repeatedly measured. If the characteristic points are periodic signals, a predetermined representative feature can be selectively extracted and used from the periodic signal. There can be one or more pieces of information about the characteristic points obtained through the characteristic points or periodic signals, and these can be combined and applied to estimate a predetermined blood pressure value. This bioinformation estimation algorithm (20) can be obtained by retrospectively analyzing the waveform of the PPG signal. The PPG signal can be analyzed by applying various methods such as linear regression analysis, multiple regression analysis, and nonlinear regression analysis. There is a predetermined relationship between the waveform of the PPG signal and the actual blood pressure value, and by analyzing this relationship, an algorithm for estimating a blood pressure value from the PPG signal can be secured.

[0074] In addition, the bio-information estimation algorithm (20) can be derived by being trained using a machine learning or deep learning method. For example, an artificial neural network (ANN), a recurrent neural network (RNN), etc. can be used. In the case of an algorithm for estimating blood pressure, various hidden layers can be used to derive a blood pressure estimation value, and various trained learning models can be used to estimate a blood pressure value using the PPG signal. Meanwhile, the bio-information estimation algorithm (20) can be implemented to provide an estimated blood pressure value according to physical characteristics by using the user's basic physical information such as age, gender, weight, and height together with the PPG signal in order to improve the accuracy of estimation.

[0075]

[0076] The control unit (50) is provided to calibrate the bio-information estimation algorithm (20) using the bio-signal measured from the signal measuring device (10) and bio-information input from the outside. According to the present embodiment, the control unit (50) can perform calibration at a first time point and perform additional calibration at a second time point after a predetermined time interval from the first time point. The calibration performed at the first time point and the second time point can be performed at substantially the same location. When performing the calibration at the second time point, the control unit can use the user's bio-signal collected continuously or discontinuously for at least a part of the time from the first time point to the second time point for calibration. According to the present embodiment, the interval between the first time point and the second time point can be set in units of days or weeks. Of course, if the first time point and the second time point have a predetermined time interval, the interval therebetween can also be set in units of hours. However, the calibration at the second point in time by the control unit (50) is optional. That is, the calibration at the second point in time can be omitted.

[0077] The first and second calibrations can be performed as follows. For example, if a doctor at a hospital determines that a 24-hour blood pressure measurement test (Ambulatory Blood Pressure Monitoring: 24H ABPM) is necessary for diagnosing a patient's hypertension, etc., the patient's blood pressure is measured at the first time point at the first location, which is the hospital, and the patient's PPG signal is collected to primarily calibrate the bio-information estimation algorithm (20, in this case, an algorithm for estimating blood pressure). The bio-information estimation algorithm (20) is primarily calibrated and fitted to the user. The signal measuring device (10) can be provided in the form of a wearable device, such as a ring type, a band type, a watch type, etc., and the patient can collect bio-information through the signal measuring device (10) for a predetermined period of time at a location other than the first location (the patient's home, lodging, etc., hereinafter referred to as a "second location") until the patient returns home and revisits the hospital. The above signal measurement device (10) may be worn continuously, or may collect the user's bio-signals continuously or discontinuously for at least a portion of the time. In either case, bio-signals may be accumulated over a predetermined period of time to accumulate data.

[0078] A doctor may determine to collect bio-information from a patient from the signal measurement device (10) on a daily or weekly basis, such as 24 hours, 48 ​​hours, or a week, and the patient or user may collect bio-signals from the signal measurement device (10) at a second location during such a set period and revisit the hospital. When the patient revisits the hospital, the control unit (50) may calculate a bio-information estimation value for the additionally acquired bio-signals. Optionally, a second calibration may be performed using the bio-signals received from the signal measurement device (10) at the second time point and the bio-information measured and input from the outside. After the second calibration is completed, the additionally acquired bio-information may be applied to the bio-information estimation algorithm (20) to derive a bio-information estimation value. Meanwhile, when performing the second calibration, the user's status and unique characteristics extracted from the additionally acquired bio-signals may be applied to additional calibration of the bio-information estimation algorithm (20). This will be discussed later.

[0079] The physician can optionally confirm and add additional information, such as bedtime and wake-up time, once additional calibration is completed and biometric information estimates for the additionally acquired biometric signals are calculated, and output a report on the biometric information, which can be provided to the patient.

[0080] In this way, the control unit (50) can perform a first calibration of the bio-information estimation algorithm (20) at the first location during the initial diagnosis, and estimate bio-information for additional bio-signals acquired at locations other than the first location during a predetermined period of time. At this time, when calculating a bio-information estimation value for the additionally acquired bio-signals, a second calibration can be further performed, and when performing the second calibration, the bio-signals measured by the signal measuring device and the bio-information measured and input from the outside can be used, and further, the user's unique bio-information change characteristics can be reflected in the additionally acquired bio-signals to improve the accuracy of the estimated bio-information provided by the bio-information estimation algorithm (20).

[0081] Here, the first calibration may be a calibration performed at a first time point and a first location, and the second calibration may be a calibration performed at a second time point and a first location. A predetermined period of time for acquiring additional biometric information may be set between the first time point and the second time point, and a process for extracting user-specific biometric information characteristics and determining user status from biometric signals acquired during the period will be described.

[0082]

[0083] According to the present embodiment, the system may include a feature extraction unit (30) that derives a user's unique bio-information change characteristic from the bio-signals measured in at least two different states of the user between the first time point and the second time point. The control unit (50) may apply the user's unique bio-information change characteristic extracted by the feature extraction unit (30) to additional calibration of the bio-information estimation algorithm (20). For example, the control unit (50) may calibrate the bio-information estimation algorithm (20) for blood pressure by applying the user's unique blood pressure change characteristic extracted by the bio-information feature extraction unit (30), and may reflect the user's unique characteristic during calibration by applying a high-quality signal extracted by the feature extraction unit (30) according to the user's state determined by the state determination unit (40). Specifically, according to the present embodiment, in order to derive the user's unique blood pressure change characteristics, the characteristic extraction unit (30) can derive the user's unique blood pressure change characteristics from the user's bio-signals measured in different states of the user.

[0084]

[0085] The above-described feature extraction unit (30) may perform pseudo-labeling to derive the user's unique bio-information change characteristics. That is, the feature extraction unit (30) may perform pseudo-labeling to label bio-signals measured from the signal measurement device (10) in different states of the user, and may select high-quality signals that satisfy predetermined criteria among the pseudo-labeled bio-signals. As described below, the pseudo-labeled and selected high-quality signals may be used again for calibration, and this series of processes may be referred to as pseudo-calibration.

[0086] Specifically, the feature extraction unit (30) performs pseudo-labeling to label PPG signals measured in different user states in order to derive the user's unique blood pressure change characteristics, and selects high-quality signals that satisfy predetermined criteria among the pseudo-labeled PPG signals. As described below, the pseudo-labeled and selected high-quality signals can be used again for calibration. In this process, the bio-information estimation algorithm (20) is calibrated while reflecting the user's unique blood pressure change characteristics, so that a bio-information estimation value that is more suitable for the user can be produced.

[0087] Here, the different states above mean cases where the factors affecting the user's blood pressure are different. Generally, blood pressure is calculated as 'cardiac output × peripheral resistance', and cardiac output is defined as 'stroke volume × heart rate'. Therefore, different states of stroke volume, heart rate, or peripheral resistance as factors affecting blood pressure can be treated as different states for extracting blood pressure change characteristics. For example, immediately after waking up, the sympathetic nervous system is activated, cardiac output increases, and blood vessels constrict, increasing resistance. In addition, during the day when people are actively working, cardiac output increases and the degree of blood vessel constriction becomes greater. On the other hand, in a situation where one has sufficiently rested (generally just before going to bed), the parasympathetic nervous system is activated, cardiac output decreases, blood vessels dilate, and resistance decreases.

[0088] Specifically, the user's unique state change characteristics in the first and second states can be applied to the bio-information estimation algorithm (20) by using the bio-signals measured from the signal measuring device (10) in the first state and the blood pressure value measured at that point in time, and the bio-signals measured from the signal measuring device (10) in the second state different from the first state and the blood pressure value measured at that point in time. Of course, as described above, the unique state change characteristics can be applied to the bio-information estimation algorithm based on a high-quality signal. For example, if the user's systolic blood pressure measured in the first state is 120 mmHg in the first measurement and 124 mmHg in the second measurement, and the user's systolic blood pressure measured in the second state is 140 mmHg in the first measurement and 138 mmHg in the second measurement, it is possible to extract blood pressure change information according to the change in the bio-signals, for example, the PPG signal, from the first state to the second state. At this time, the average of the measurements in the first state and the average of the measurements in the second state can be used to extract the state of change. This blood pressure change information is unique to the user and can provide the effect of enabling more accurate blood pressure correction tailored to the individual.

[0089] The more bio-signals collected in different environments and conditions, the more precisely the user's unique blood pressure characteristics can be extracted, and the more precisely the unique blood pressure change characteristics are extracted, the more accurate the bio-information estimation algorithm (20) that reflects the characteristics increases.

[0090]

[0091] According to the present embodiment, the feature extraction unit (30) can select a high-quality signal that satisfies a predetermined standard among the bio-signals measured in the different states of the user and utilize it for calibration. Specifically, a first high-quality signal that satisfies a predetermined standard among the first measurement values ​​measured in the first state can be selected, and a second high-quality signal that satisfies a predetermined second standard among the second measurement values ​​measured in the second state can be selected and applied to calibration. In the present embodiment, for example, the first state can be a resting state, and the second state can be an active state.

[0092] In the first state, the first measurement value may be a measurement value that satisfies a predetermined criterion among measurement values ​​measured multiple times in the first state, or an average value of measurement values ​​that satisfies a predetermined criterion may be used. The biosignal may be measured continuously or intermittently (discontinuously) in the first state. For example, when measured intermittently in the first state, the measurement may be performed at a predetermined time interval, for example, an interval of 10 to 30 minutes, and a first high-quality signal that satisfies a predetermined first criterion among the measurement values ​​in the first state may be applied to calibration. The first criterion may be selected as the first high-quality signal when the difference between the SBP (systolic blood pressure) and DBP (diastolic blood pressure) values ​​obtained through the PPG signal is within a predetermined error range that is set in advance.

[0093] The second measurement value in the second state, like the second measurement value in the first state, may be a measurement value that satisfies a predetermined criterion among measurement values ​​measured multiple times in the second state, or an average value of measurement values ​​that satisfies a predetermined criterion may be used. The bio-signal may be measured continuously or intermittently (discontinuously) in the second state. For example, when the bio-signal is measured intermittently in the first state, it may be measured at a predetermined time interval, for example, an interval of 10 to 30 minutes, and a second high-quality signal that satisfies a predetermined second criterion among the measurement values ​​in the second state may be applied to calibration. The second criterion may be selected as the second high-quality signal when the difference between the SBP (systolic blood pressure) and DBP (diastolic blood pressure) values ​​obtained through the PPG signal is within a predetermined error range that is set in advance.

[0094] This process can be defined as Pseudo Calibration because it reuses signals of superior quality that satisfy a certain standard among the measured values ​​in different states to calibrate the estimated values.

[0095] Furthermore, the feature extraction unit (30) can obtain a signal from which noise components have been removed for the first and second measurement values, extract feature points for periodic waveforms, and combine them to extract the user's unique features for cardiac output, heart rate, and vascular resistance. Through this process, the feature extraction unit (30) can select the first high-quality signal and the second high-quality signal from the signal from which noise has been removed, more accurately extract unique blood pressure change features in different states, and calibrate the bio-information estimation algorithm (20) to derive a more accurate estimated blood pressure value.

[0096]

[0097] According to an embodiment of the present invention, the status determination unit (40) is provided to receive the bio-signal measured from the second sensor unit (12) and determine the user's status.

[0098] As illustrated in FIG. 8, the state determination unit (40) can determine that the user is in the first state when a predetermined first pattern is measured for a specified time by the second sensor unit (12), and can determine that the user is in the second state when a predetermined second pattern is measured for a specified time by the second sensor unit (12). At this time, the first state may be a resting state, and the second state may be an active state. Alternatively, when a predetermined third pattern is measured by the second sensor unit (12), the user may be determined to be in the third state, for example, a sleeping state.

[0099] In addition, the state determination unit (40) can determine whether the user is wearing the signal measurement device (10) based on the size or shape of the signal measured by the second sensor unit (12). Furthermore, the state determination unit (40) can determine whether the user is sleeping or active based on the bio-signal. The sleep or activity status can be considered as different environments corresponding to the different conditions of the states.

[0100] According to the present embodiment, the second sensor unit (12) may be an acceleration sensor that detects the movement of a finger, and the second sensor unit (12) may measure the movement acceleration of the user's finger continuously / intermittently or periodically / aperiodically. The state determination unit (40) may determine the user's state using the ACC signal information measured by the acceleration sensor. The state determination unit (40) may be provided in the signal measurement device (10) or in various electronic devices such as a mobile device, a wearable device, a PC, etc. that can receive a bio-signal from the signal measurement device. In addition, the bio-information estimation algorithm (20) or the feature extraction unit (30) may also be provided in the signal measurement device (10) or in various electronic devices such as a mobile device, a wearable device, a PC, etc. that can receive a bio-signal from the signal measurement device (10).

[0101] Specifically, when the state determination unit (40) determines that the user is wearing the ring (10) through the first sensor unit (11), and a first pattern is measured from the second sensor unit (12) for a specified period of time, the state can be determined as a first state in which the user is resting for a specified period of time. Here, the first pattern may be a regular pattern, and the first pattern may be a stable pattern. Specifically, the first pattern may be a regular pattern in which a specific pattern is repeated. That is, when the state determination unit (40) determines that the user is wearing the ring (10) through the first sensor unit (11), and a stable first pattern is measured from the second sensor unit (12), the state determination unit (40) determines that the user is resting. When the state determination unit (40) determines that the user is resting, the user can be set to be in the first state.

[0102] In addition, the state determination unit (40) determines that the user has worn the ring (10) for a specified period of time through the first sensor unit (11), and when a second pattern is measured from the second sensor unit (12), it can determine that the user is in a second state in which the user is active for a specified period of time. At this time, the second pattern may be an irregular pattern, and the second pattern may be an unstable pattern. The state determination unit (40) determines that the user is active when the second sensor unit (12) measures the unstable second pattern when it determines that the user has worn the ring-type signal measurement device (10) through the first sensor unit (11). When the state determination unit (40) determines that the user is active, the user can be set to be in the second state.

[0103] In the embodiments of the present invention, the first pattern is described as being a regular pattern and the second pattern is described as being an irregular pattern, but this is not limited thereto. The first pattern may be composed of various patterns as long as it can measure whether the user is resting, and the second pattern may be composed of various patterns as long as it can measure whether the user is active.

[0104] Additionally, the first pattern capable of measuring whether the user is resting and the second pattern capable of measuring whether the user is active may be derived from patterns occurring in the user's previous activity and previous rest data.

[0105] According to an embodiment of the present invention, the state determination unit (40) can determine whether the user is sleeping based on the number of times the first state is determined to be resting. Specifically, as illustrated in FIG. 9, the state determination unit (40) can determine that the user is sleeping when the number of times the first state is determined to be resting exceeds a predetermined reference number for a certain period of time. The sleeping state can be defined as the third state.

[0106] According to an embodiment of the present invention, a case where a user transitions from a resting state to an active state cannot be determined as a sleep state, but a case where the user continues to remain in a resting state can be determined as a sleep state. For example, when a user transitions from a resting state to an active state, the first sensor unit (11) may measure a stable first pattern and then measure an unstable second pattern. In this case, the state determination unit (40) may determine that the user has transitioned to an active state that is not sleeping or resting.

[0107] When a user continues to remain in a resting state and enters a sleeping state, the first sensor unit (11) can continuously measure the first stable pattern. In this case, the state determination unit (40) can determine that the user is in a sleeping state.

[0108] At this time, the state determination unit (40) determines that the user is sleeping when the number of times the third state is determined to be resting for a certain period of time is greater than or equal to a specified standard number. More specifically, the state determination unit (40) determines that the user is sleeping when the number of times the third state is determined to be resting for a certain period of time (a specified period of time) is greater than or equal to a specified standard value, thereby improving the accuracy of determining whether or not the user is sleeping. That is, the state determination unit (40) can determine whether or not the third state is sleeping through the number of repetitions of a short unit of time determined to be resting for a certain period of time.

[0109] According to an embodiment of the present invention, the state determination unit (40) can calculate the reference number based on statistical values ​​of the second state measured over a specified period of time. Specifically, the state determination unit (40) can calculate the reference number of the second state based on the user's previous sleep data to determine whether or not the user is asleep.

[0110] According to an embodiment of the present invention, the second sensor unit (12) can measure the movement patterns of the user's fingers that occur when the user is in a sleeping state and when the user is in a state of alternating activity and rest. The second sensor unit (12) can apply the measured values ​​of the second state, when the user is in a sleeping state and when the user is in a state of alternating activity and rest, to statistical values.

[0111] In addition, the state determination unit (40) according to an embodiment of the present invention can calculate statistical values ​​by accumulating signals measured by the second sensor unit (12) over a specified period of time. Specifically, the state determination unit (40) can calculate and produce statistical values ​​for the second state when the user is in a sleeping state and when the user is in a state of repeating activity and rest.

[0112] For example, the state determination unit (40) may set a designated period of 24 hours prior to the sleep determination time, and accumulate signals measured by the second sensor unit (12) to calculate statistical values. In addition, the state determination unit (40) may set a designated period of 24 hours prior to the sleep determination time, and calculate statistical values ​​of the second state when the user is in a sleeping state and when the user is in a state of repeating activity and rest.

[0113] The number of criteria required to determine whether a user is asleep may vary depending on the user's lifestyle. Therefore, to increase the accuracy of sleep determination, the number of criteria required to determine sleep must be optimized for each user. The state determination unit (40) according to an embodiment of the present invention can calculate the number of criteria for determining whether sleep is present based on the statistical values ​​of the second state measured over a specified period, thereby enabling the user to determine whether sleep is present in an optimized manner.

[0114] In addition, according to an embodiment of the present invention, by optimizing the determination of whether or not sleep is present for each user, the accuracy of calibration of blood pressure estimation values ​​according to the user's condition can be further improved.

[0115]

[0116] In this way, the bio-information estimation device according to an embodiment of the present invention collects bio-signals for a predetermined period of time at a location other than the first location, and estimates a bio-information estimation value by applying additionally acquired bio-signals collected during the period to a bio-information estimation algorithm, thereby enabling the bio-information estimation value during the observation period allocated to the predetermined time to be utilized for diagnosis, thereby improving the accuracy of diagnosis.

[0117] The present invention collects bio-signals by distributing the ring-shaped signal measuring device to a patient or the like, thereby providing the effect of easily acquiring bio-signals without being restricted by space and time by simply wearing the ring.

[0118] The present invention can optionally perform a second calibration after a first calibration for user fitting is performed, and in particular, in the second calibration, a bio-information estimation value is calculated by reflecting the user's unique bio-information change characteristics from the user's bio-signals collected during a predetermined observation period, thereby providing an effect of improving the accuracy of the bio-information estimation value.

[0119]

[0120] While the present invention has been described with reference to the embodiments illustrated in the drawings, these are merely exemplary, and those skilled in the art will appreciate that various modifications and variations of the embodiments are possible. Therefore, the true scope of technical protection of the present invention should be determined by the technical spirit of the appended claims.

Claims

1. A step of applying a bio-signal measured by a signal measuring device at a first location and bio-information measured and input from the outside to a predetermined bio-information estimation algorithm to calibrate the bio-information estimation algorithm to suit the user; A step of additionally acquiring the user's bio-signal using the signal measuring device for a predetermined period of time at a location other than the first location; and A bioinformation estimation method characterized by comprising a step of applying the additionally acquired biosignal to the biosignal estimation algorithm to generate an estimated value of additional bioinformation corresponding to the predetermined period.

2. In paragraph 1, A biometric information estimation method characterized by including a step of assigning a predetermined serial number to a user and matching the serial number with the signal measuring device.

3. In paragraph 1, The above additional biometric information estimate is generated at the first location, A biometric information estimation method characterized in that the above additional biometric information estimation value is calculated after performing an additional calibration step of re-calibrating the biometric estimation algorithm using the biometric signal measured by the signal measuring device at the first location and the biometric information measured and input from the outside.

4. In paragraph 1, A biometric information estimation method characterized by including a step of outputting the estimated value of the above additional biometric information in an identifiable form.

5. In paragraph 1, A biometric information estimation method characterized by including the steps of recovering, disinfecting, and charging the signal measuring device after the additional biometric information estimation value is generated.

6. In paragraph 1, The above first location may be a hospital that provides medical treatment to the user; A bio-information estimation method characterized in that the user wears the signal measuring device in a location other than the first location to collect additional bio-signals for at least one day.

7. In paragraph 1, A method for estimating biometric information, characterized in that the biometric information includes blood pressure, blood sugar, or oxygen saturation.

8. In paragraph 1, A bio-information estimation method characterized in that the bio-signal includes at least one of a user's photoplethysmography signal (PPG signal), electrocardiogram (ECG), or electroencephalogram (EEG) signal.

9. In paragraph 1, A biometric information estimation method characterized in that the signal measuring device is a ring-shaped measuring device that can be worn by a user.

10. In paragraph 3, The additionally acquired bio-signals include bio-signals measured in at least two different states of the user, and include a feature extraction step of deriving unique bio-information change characteristics of the user from the bio-signals in the different states. A biometric information estimation method characterized in that the additional calibration step of the biometric information estimation algorithm corrects the biometric information estimation value by calibrating the biometric information estimation algorithm by reflecting the user's unique biometric information change characteristics extracted by the characteristic extraction step.

11. In paragraph 10, A bio-information estimation method characterized in that the above different states are states in which the user's heart rate or peripheral resistance is in different environments.

12. In paragraph 9, A bio-information estimation method characterized in that the signal measuring device collects a user's optical volume change signal through a first sensor unit and detects the user's movement through a second sensor unit.

13. In paragraph 7, A biometric information estimation method characterized in that when a predetermined first pattern is measured for a specified time by the second sensor unit, the user is determined to be in a first state, and when a predetermined second pattern is measured for a specified time by the second sensor unit, the user is determined to be in a second state.

14. In paragraph 10, The above feature extraction step performs pseudo-labeling, which labels bio-signals measured in different user states from the signal measurement device, A bioinformation estimation method characterized in that the additional calibration step of the bioinformation estimation algorithm selects a high-quality signal that satisfies a predetermined standard among the biosignals labeled with the water and uses it for calibration of the bioinformation estimation algorithm.

15. In paragraph 14, A bioinformation estimation method characterized in that the above-mentioned superior quality signal includes a first superior quality signal that satisfies a predetermined first criterion among the first measurement values ​​measured in the first state, and a second superior quality signal that satisfies a predetermined second criterion among the second measurement values ​​measured in the second state.

Images