Method for correcting non-invasive bio-information

Abstract

The present invention relates to a method of correcting non-invasive biological information measured by a non-invasive biological information measuring instrument, and more particularly, to a method of correcting non-invasive biological information measured by a non-invasive blood glucose measuring instrument using continuous biological information measured by a continuous blood glucose measuring instrument, and individualizing the non-invasive biological information for a user, and correcting inaccurate non-invasive biological information measured by a non-invasive blood glucose measuring instrument using continuous biological information measured by a continuous blood glucose measuring instrument for a user, thereby enabling accurate determination of a pattern of increase and decrease of biological information of a user from non-invasive biological information that is not yet accurate.

Description

Technical Field

[0001] This invention relates to a method for correcting non-invasive bioinformation measured by a non-invasive bioinformatics measuring instrument. More specifically, it relates to a method for correcting non-invasive bioinformation measured by a non-invasive bioinformatics measuring instrument by using continuous bioinformation measured by a continuous glucose meter to learn non-invasive bioinformation measured by a non-invasive bioinformatics measuring instrument, and for correcting non-invasive bioinformation for users in a personalized manner. Furthermore, it relates to a method for correcting non-invasive bioinformation measured by a non-invasive bioinformatics measuring instrument by using continuous bioinformation measured by a continuous glucose meter to correct non-invasive bioinformation for users in a personalized manner, thereby enabling the accurate determination of the increase or decrease pattern of a user's bioinformation from non-invasive bioinformation that is not yet certain. Background Technology

[0002] Diabetes is a common chronic disease in modern people. According to the International Diabetes Federation (IDF), there are 400 million people with diabetes worldwide.

[0003] Diabetes is caused by a variety of factors, including obesity, stress, poor dietary habits, and congenital heredity, resulting in an absolute or relative deficiency of insulin produced by the pancreas, which fails to correct the balance of sugar in the blood, leading to an absolute increase in the sugar content in the blood.

[0004] Blood usually contains a certain concentration of glucose, from which tissue cells obtain energy.

[0005] However, when glucose levels rise excessively, it cannot be properly stored in the liver, muscles, or fat cells and accumulates in the blood. As a result, the blood sugar levels of diabetic patients are maintained much higher than those of normal people. Furthermore, as excess blood sugar is directly excreted through tissues and excreted in urine, the body's tissues do not have enough sugar to meet their absolute needs, leading to abnormalities in various tissues.

[0006] The defining characteristic of diabetes is that it initially presents with almost no noticeable symptoms. However, as the disease progresses, specific symptoms such as polydipsia, polyphagia, polyuria, weight loss, general fatigue, itchy skin, and slow-healing wounds on the hands and feet appear. Further progression can lead to complications such as visual impairment, hypertension, kidney disease, stroke, periodontal disease, muscle spasms, neuralgia, and gangrene.

[0007] In order to diagnose such diabetes and manage it to prevent the development of complications, systematic blood glucose monitoring and treatment should be carried out in parallel.

[0008] Continuous blood glucose monitoring is necessary for the management of diabetes, leading to a sustained increase in demand for blood glucose measurement devices. Various studies have confirmed that the incidence of diabetic complications is significantly reduced when diabetic patients strictly regulate their blood glucose. Therefore, regular blood glucose monitoring is extremely important for diabetic patients in order to regulate their blood glucose levels.

[0009] For blood glucose management in diabetic patients, fingerprick method blood glucose meters are typically used. While these meters are helpful for blood glucose management, they only display the result at the moment of measurement, making it difficult to accurately track frequently changing blood glucose levels. Furthermore, fingerprick method blood glucose meters require multiple blood draws throughout the day to measure blood glucose, thus posing a significant burden on diabetic patients.

[0010] To overcome the limitations of such blood sampling blood glucose meters, a continuous glucose monitoring system (CGMS) has been developed that is inserted into the human body and measures blood glucose at intervals of several minutes. This system can easily handle the management of diabetic patients and emergency situations.

[0011] A continuous glucose meter (CGM) is a device that extracts intersitial fluid by means of a sensor partially inserted into a user's body and measures the user's blood glucose levels in real time from the extracted fluid. The CGM extracts the user's intersitial fluid using a sensor for a specified period, such as approximately 15 days, and periodically generates and provides the user with blood glucose biometrics from the extracted fluid.

[0012] However, even with continuous glucose monitoring, there are inconveniences such as having to replace the sensor and insert it into the body every week, 15 days, or month, and the need to use a separate blood sampling glucose meter to calibrate the measured blood glucose values ​​at each set time.

[0013] On the other hand, non-invasive blood glucose meters are currently being researched and developed that can measure blood glucose levels using portable devices without bleeding. Non-invasive blood glucose testing is harmless to the human body, painless, has no side effects, and offers excellent reproducibility, making it the dream blood glucose testing method for all diabetic patients.

[0014] Since 1990, research has been ongoing on non-invasive methods for measuring blood glucose, and approaches based on various principles are being explored.

[0015] Representative non-invasive blood glucose measurement methods currently under research and development can be broadly categorized into four principles. The earliest approach involved measuring subcutaneous blood glucose by attaching a consumable patch to the skin (Transdermal), but this method had limitations in accuracy and reproducibility due to its reliance on thin skin layers. Following this, an optical method was explored, using incident light and measuring and analyzing the spectrum of reflected light to determine blood glucose concentration (Optical), and extensive research continues in this area. On the other hand, methods are being explored that measure blood glucose by providing electrical stimulation and inducing electrochemical reactions (Electrochemical), or a method using ultrasound waves that penetrate deeply into the living body to measure blood glucose concentration (Ultrasound).

[0016] However, while non-invasive blood glucose meters have the advantage of being able to measure blood glucose painlessly from outside the skin or in contact with the skin, they are not as accurate as existing methods that measure blood glucose by directly drawing blood from the body or extracting body fluids. Furthermore, due to the differences in each user's body or physiological conditions, it is difficult to measure blood glucose accurately for all users in the same way. Summary of the Invention

[0017] Technical issues

[0018] The present invention aims to solve the problems existing in the existing non-invasive biometric information measurement methods mentioned above. The purpose of the present invention is to provide a method that can learn non-invasive biometric information measured by a non-invasive biometric instrument using continuous biometric information measured by a continuous biometric instrument, and to personalize the non-invasive biometric information for the user.

[0019] Another objective of this invention is to provide a non-invasive bioinformatics correction method that can use continuous bioinformatics measured by a continuous bioinformatics measuring instrument to personalize the non-invasive bioinformatics measured by the non-invasive bioinformatics measuring instrument for the user, thereby accurately determining the increase or decrease pattern of the user's bioinformatics from the non-invasive bioinformatics.

[0020] Another objective of this invention is to provide a method for correcting non-invasive biometric information that compares non-invasive biometric information corresponding to input event information with continuous biometric information, and for learning continuous biometric information corresponding to the non-invasive biometric information at the time of the event in a personalized manner for the user, so that even if there is no continuous biometric information, the user's biometric information can be accurately determined by using only event information and non-invasive biometric information.

[0021] Another objective of this invention is to provide a method for correcting non-invasive biometric information that can compare non-invasive biometric information corresponding to input event information with continuous biometric information, and after the user learns the continuous biometric information corresponding to the non-invasive biometric information at the time of the event in a personalized manner, use only event information and non-invasive biometric information to judge or predict the user's biometric information, and provide the user with an alarm in case of an emergency.

[0022] Technical solution

[0023] To achieve the objectives of this invention, one embodiment of the non-invasive biometric correction method includes: measuring continuous biometric information of a user by means of a continuous biometric measuring device in which a portion of a sensor is inserted into the user's body and measures the user's biometric information for a specified period; measuring non-invasive biometric information of the user for a specified period by means of the non-invasive biometric measuring device in which the user's biometric information is measured non-invasively; and comparing the non-invasive biometric information measured for the specified period with the continuous biometric information, and learning the continuous biometric information corresponding to the non-invasive biometric information for the user in a personalized manner.

[0024] Preferably, in a non-invasive bio-information correction method according to an embodiment of the present invention, when additional non-invasive bio-information of the user is acquired by a non-invasive bio-information measuring device after a specified period, the step of determining the continuous bio-information learned in accordance with the additional non-invasive bio-information to correct the additional non-invasive bio-information is performed.

[0025] In one embodiment of the non-invasive bio-information correction method of the present invention, the increase / decrease pattern of non-invasive bio-information is compared with the increase / decrease pattern of continuous bio-information, and the increase / decrease pattern of continuous bio-information corresponding to the increase / decrease pattern of non-invasive bio-information is learned for the user in a personalized manner; the increase / decrease pattern of continuous bio-information learned in accordance with the increase / decrease pattern of the added non-invasive bio-information is determined by the added non-invasive bio-information, and the increase / decrease pattern of the added non-invasive bio-information is corrected based on the determined increase / decrease pattern of continuous bio-information.

[0026] Preferably, the non-invasive biometric correction method of an embodiment of the present invention further includes the steps of: acquiring event information of an event occurring to the user within a specified period, comparing the non-invasive biometric information corresponding to the event information with continuous biometric information, and learning the continuous biometric information corresponding to the non-invasive biometric information at the time of the event for the user in a personalized manner.

[0027] Among them, the event information is the event input entered through the interface screen.

[0028] Preferably, the non-invasive biometric correction method of an embodiment of the present invention further includes: the step of acquiring occurrence condition information of an event that occurs simultaneously with the user when acquiring event information, and comparing the non-invasive biometric information corresponding to the event information and occurrence condition information with continuous biometric information, and using the occurrence condition information to learn the continuous biometric information corresponding to the non-invasive biometric information at the time of the event for the user in a personalized manner.

[0029] Among them, the occurrence condition information is at least one of the following: seasonal information, time information, location information, position information, temperature information, and humidity information.

[0030] The occurrence condition information is entered through the displayed occurrence condition input interface.

[0031] In the non-invasive biometric correction method, the user's continuous biometric information is measured by multiple continuous biometric measurement devices over multiple specified periods; the non-invasive biometric information measured over multiple specified periods is compared with the continuous biometric information, and the user's corresponding continuous biometric information is learned in a personalized manner over multiple specified periods.

[0032] The multiple specified periods are set at intervals from each other. For example, the multiple specified periods are set at the same time interval, or, for example, the multiple specified periods are set at intervals based on at least one of environmental conditions, seasonal conditions, user physical conditions, and user physiological conditions.

[0033] Preferably, the non-invasive biometric information correction method of an embodiment of the present invention further includes the step of: when subsequent event information occurring in the user and additional non-invasive biometric information of the user are obtained after a specified period, determining the continuous biometric information learned in accordance with the subsequent event information and the additional non-invasive biometric information to correct the additional non-invasive biometric information.

[0034] Preferably, in another embodiment of the present invention, the method for correcting non-invasive biometric information further includes: when subsequent event information occurring to the user, subsequent event occurrence condition information, and additional non-invasive biometric information of the user are obtained after a specified period, determining continuous biometric information learned in accordance with the subsequent event information, subsequent event occurrence condition information, and additional non-invasive biometric information to correct the additional non-invasive biometric information.

[0035] In the non-invasive bio-information correction method of the present invention, the increase / decrease pattern of non-invasive bio-information is compared with the increase / decrease pattern of continuous bio-information, and the increase / decrease pattern of continuous bio-information corresponding to the increase / decrease pattern of non-invasive bio-information is learned for the user in a personalized manner; the increase / decrease pattern of the added non-invasive bio-information and the increase / decrease pattern of continuous bio-information learned in accordance with the added event information are judged by the added non-invasive bio-information to correct the increase / decrease pattern of the added non-invasive bio-information.

[0036] Another embodiment of the non-invasive biometric correction method of the present invention includes: measuring continuous biometric information of a user by means of a continuous biometric measuring device in which a portion of a sensor is inserted into the user's body and measures the user's biometric information for a specified period; measuring non-invasive biometric information of the user for a specified period by means of the non-invasive biometric measuring device in which the user's biometric information is measured non-invasively; acquiring event information of events occurring to the user during the period of measuring continuous biometric information; comparing the increase / decrease pattern of event information and non-invasive biometric information with the increase / decrease pattern of continuous biometric information, and learning an increase / decrease pattern of continuous biometric information corresponding to the increase / decrease pattern of event information and non-invasive biometric information for the user in a personalized manner; acquiring additional non-invasive biometric information of the user and additional event information occurring to the user by means of the non-invasive biometric measuring device after the specified period; and judging the increase / decrease pattern of additional non-invasive biometric information determined by the additional non-invasive biometric information and the increase / decrease pattern of continuous biometric information learned in accordance with the additional event information to correct the increase / decrease pattern of additional non-invasive biometric information.

[0037] Event information and additional event information are entered through the event input interface.

[0038] Preferably, another embodiment of the non-invasive biometric correction method of the present invention further includes: acquiring the occurrence condition information of the event occurring to the user at the same time as acquiring event information; comparing the increase / decrease pattern of non-invasive biometric information corresponding to the event information and occurrence condition information with the increase / decrease pattern of continuous biometric information, and using the occurrence condition information to learn the increase / decrease pattern of continuous biometric information corresponding to the increase / decrease pattern of non-invasive biometric information at the time of the event for the user in a personalized manner.

[0039] The conditions for an event to occur, or the conditions for adding an event to occur, are entered through the displayed conditions input interface.

[0040] Preferably, another embodiment of the non-invasive bio-information correction method of the present invention further includes: a step of judging the rate of increase or decrease based on the increase or decrease pattern of the corrected additional non-invasive bio-information; and a step of providing an alarm to the user when the judged rate of increase or decrease exceeds a critical rate of change.

[0041] Preferably, another embodiment of the non-invasive bio-information correction method of the present invention further includes: a step of predicting the subsequent rate of increase or decrease based on the increase or decrease pattern of the corrected additional non-invasive bio-information; and a step of providing an alarm to the user when the predicted rate of increase or decrease exceeds a critical rate of change.

[0042] The effects of the invention

[0043] The non-invasive bio-information correction method of the present invention has the following effects.

[0044] First, in the non-invasive bioinformation correction method of the present invention, the non-invasive bioinformation measured by the non-invasive bioinformation measuring instrument is learned by using accurate continuous bioinformation measured by the continuous bioinformation measuring instrument, so that even if each user's physical and physiological conditions are different, the non-invasive bioinformation can be corrected in a personalized manner for the user.

[0045] Secondly, in the non-invasive bioinformation correction method of the present invention, the non-invasive bioinformation measured by the non-invasive bioinformation measuring instrument is corrected for the user in a personalized manner using the continuous bioinformation measured by the continuous bioinformation measuring instrument, thereby enabling the accurate determination of the increase or decrease pattern of the user's bioinformation from the still inaccurate non-invasive bioinformation.

[0046] Third, in the non-invasive biometric information correction method of the present invention, the non-invasive biometric information corresponding to the input event information is compared with the continuous biometric information, and the continuous biometric information corresponding to the non-invasive biometric information at the time of the event is learned in a personalized manner for the user, so that even if there is no subsequent continuous biometric information, the user's biometric information can be accurately judged using only the event information and the non-invasive biometric information.

[0047] The method for correcting non-invasive biometric information according to the present invention compares non-invasive biometric information and continuous biometric information based on input event information, and personalizes and learns the continuous biometric information corresponding to the non-invasive biometric information. When an event occurs, even without continuous biometric information, the user's biometric information can be accurately determined using only event information and non-invasive biometric information.

[0048] Fourth, in the non-invasive biometric correction method of the present invention, non-invasive biometric information corresponding to the input event information is compared with continuous biometric information, and continuous biometric information corresponding to the non-invasive biometric information at the time of the event is learned in a personalized manner for the user, so that the user's biometric information can be judged or predicted using only event information and non-invasive biometric information, and an alarm can be provided to the user in case of an emergency. Attached Figure Description

[0049] Figure 1 This is a diagram illustrating a non-invasive bio-information correction system according to an embodiment of the present invention.

[0050] Figure 2 This is a diagram illustrating a non-invasive bio-information correction system according to another embodiment of the present invention.

[0051] Figure 3 This is a functional block diagram illustrating the non-invasive bio-information correction device of the present invention.

[0052] Figure 4 This is a diagram illustrating the operation of the learning unit of the present invention.

[0053] Figure 5 This is a diagram illustrating the operation of the correction section of the present invention.

[0054] Figure 6 This is a flowchart illustrating a non-invasive bio-information correction method according to an embodiment of the present invention.

[0055] Figure 7 This is a flowchart illustrating a non-invasive bio-information correction method according to another embodiment of the present invention.

[0056] Figure 8 An example is shown of non-invasive blood glucose information measured by a non-invasive bioinformatics instrument and an example of continuous blood glucose information measured by a continuous bioinformatics instrument.

[0057] Figure 9 Instructions are provided regarding the prescribed period for wearing the continuous biometric measurement device on the body.

[0058] Figure 10 An example of the interface screen for inputting event information in this invention will be described.

[0059] Figure 11 An example of event information input via an interface screen is described.

[0060] Figure 12 This is a diagram illustrating an example of displaying measured blood glucose information using only a non-invasive bioinformatics device after the removal of a continuous bioinformatics device.

[0061] Figure 13 This is a flowchart illustrating an example of providing alerts to users based on patterns of increasing or decreasing blood glucose information.

[0062] Figure 14 This is a flowchart illustrating an example of providing alerts to users based on the rate of subsequent increases or decreases in blood glucose information.

[0063] Figure 15 This shows an example of an alert message provided to the user. Detailed Implementation

[0064] It should be noted that the technical terms used in this invention are only for illustrating specific embodiments and are not intended to limit the invention. Furthermore, unless specifically defined differently in this invention, the technical terms used in this invention should be interpreted as meaning commonly understood by one of ordinary skill in the art, and should not be interpreted as overly inclusive or excessively narrow. Moreover, when the technical terms used in this invention are incorrect terms that fail to accurately express the spirit of the invention, they should be replaced with technical terms that can be correctly understood by one of ordinary skill in the art.

[0065] Furthermore, unless the context explicitly defines otherwise, singular expressions used in this invention include plural expressions. In this invention, terms such as “consisting of” or “comprising” should not be construed as necessarily including all of the multiple constituent elements or steps described in this invention, but should be interpreted as potentially excluding some constituent elements or steps, or potentially including additional constituent elements or steps.

[0066] Furthermore, it should be noted that the accompanying drawings are only for the purpose of facilitating the understanding of the concept of the present invention, and should not be construed as limiting the concept of the present invention to the drawings.

[0067] Figure 1 This is a diagram illustrating a non-invasive bio-information correction system according to an embodiment of the present invention. Figure 2 This is a diagram illustrating a non-invasive bio-information correction system according to another embodiment of the present invention.

[0068] The non-invasive bioinformation correction system of the present invention includes a continuous bioinformation measuring instrument 10 and a non-invasive bioinformation measuring instrument 30. It can correct non-invasive bioinformation through a separate user terminal 50, or it can directly correct non-invasive bioinformation through the non-invasive bioinformation measuring instrument 30 without a separate user terminal 50.

[0069] Although described below as a continuous bioinformatics measuring device 10 and a non-invasive bioinformatics measuring device 30 measuring a user's blood glucose respectively, depending on the field of application of the present invention, devices capable of measuring a variety of bioinformatics can be used as the continuous bioinformatics measuring device 10 and the non-invasive bioinformatics measuring device 30.

[0070] First, refer to Figure 1 The system for calibrating non-invasive bioinformation using user terminal 50 is described. The continuous bioinformation measuring device 10 is equipped with a sensor, which is a device that is inserted into and attached to the user's body and can extract body fluids within a specified period to measure the user's blood glucose information. The non-invasive bioinformation measuring device 30 is a device that can measure the user's blood glucose information in a non-invasive manner by contacting or separating it from the user's skin while the user is wearing it.

[0071] User terminal 50 communicates with continuous bioinformatics measurement device 10 wirelessly or via wired means, and periodically or upon request receives continuous blood glucose information of the user from continuous bioinformatics measurement device 10. User terminal 50 also communicates with non-invasive bioinformatics measurement device 30 wirelessly or via wired means, and periodically or upon request receives non-invasive blood glucose information of the user from non-invasive bioinformatics measurement device 30.

[0072] Preferably, the user can input information about events occurring to the user into the user terminal 50 within a specified period after attaching the continuous bioinformatics measuring instrument 10. The user terminal 50 displays an interface screen for inputting event information, allowing the user to input information about events that will occur to the user in the future or events that have occurred previously. According to the field of application of this invention, multiple sensors for sensing events occurring to the user may also be included. For example, the user terminal 50 can determine events occurring to the user using activity sensors, position sensors, etc., and automatically input the determined events upon user confirmation.

[0073] Here, an event is defined as something that can affect a user's blood sugar. For example, it could be an event that raises blood sugar, such as eating breakfast, lunch, dinner, or snacks, or an event that lowers blood sugar, such as exercising, working, or studying. To more accurately determine the impact of an event on a user's blood sugar, detailed event information such as the type and amount of food consumed, or detailed event information such as the type and duration of exercise, can be entered together.

[0074] Preferably, when an event occurs, the user can further input information about the conditions under which the event occurred into the user terminal 50. An interface screen is displayed on the user terminal 50, allowing the user to input the event occurrence condition information. According to the field of application of this invention, multiple sensors for sensing the occurrence conditions of the event occurring to the user may also be included. For example, the user terminal 50 can determine the event occurrence condition information through a position sensor, temperature sensor, humidity sensor, etc., or obtain the occurrence condition information through a network. The event occurrence condition information can be automatically input with user confirmation.

[0075] User terminal 50 includes: a storage mechanism capable of storing continuous blood glucose information, non-invasive blood glucose information, event information, and occurrence condition information for a specified period; and a processor mechanism capable of using a learning model stored in the storage mechanism to learn, for the user, continuous blood glucose information corresponding to the non-invasive blood glucose information in a personalized manner from the continuous blood glucose information, non-invasive blood glucose information, event information, and occurrence condition information.

[0076] User terminal 50 can receive continuous blood glucose information from continuous bioinformatics meter 10 and non-invasive blood glucose information from non-invasive bioinformatics meter 30, and compare the received non-invasive blood glucose information with the continuous blood glucose information within a specified period, and learn the continuous blood glucose information corresponding to the non-invasive blood glucose information for the user's personalized needs.

[0077] Preferably, in addition to continuous blood glucose information and non-invasive blood glucose information, the user terminal 50 can also receive information about events occurring to the user and the occurrence conditions information of the events within a specified period, and compare the non-invasive blood glucose information and continuous blood glucose information corresponding to the event information and occurrence conditions information, and use the occurrence conditions information to learn the continuous blood glucose information corresponding to the non-invasive blood glucose information at the time of the event for the user in a personalized way.

[0078] That is, by using the continuous bioinformatics measuring instrument 10 and the user terminal 50, the continuous bioinformatics measuring instrument 10 can continuously measure the user's blood glucose information within a specified period, such as 1 week, 15 days, or 1 month, and the user terminal 50 can use the continuous blood glucose information measured within the specified period to learn continuous blood glucose information corresponding to non-invasive blood glucose information for the user in a personalized way.

[0079] The continuous bioinformatics measuring device 10 is removed after being attached to the user's body for a specified period, and the user's blood glucose information is determined only by the non-invasive bioinformatics measuring device 30. When the non-invasive blood glucose information is received using a calibration model generated from the learning results, the user terminal 50 applies the non-invasive blood glucose information, event information, and event occurrence condition information to the calibration model to correct the non-invasive blood glucose information measured by the non-invasive bioinformatics measuring device 30.

[0080] This overcomes the shortcomings of previous methods that used only non-invasive bioinformatics instruments to measure blood glucose information, such as inaccurate blood glucose data or different blood glucose values ​​for each user. It enables non-invasive bioinformatics to accurately measure blood glucose information for each user in a personalized way, or at least accurately determine the user's blood glucose increase or decrease pattern.

[0081] The following is for reference. Figure 2 The following describes a system for calibrating non-invasive biometrics without the medium of a user terminal 50. A continuous biometrics meter 10 is inserted into and attached to the user's body by a portion of a sensor and extracts bodily fluids within a specified period to measure the user's blood glucose information. A non-invasive biometrics meter 30 measures the user's blood glucose information non-invasively while the user is wearing the device within a specified period.

[0082] The continuous bioinformatics measuring device 10 and the non-invasive bioinformatics measuring device 30 are connected wirelessly or via wired means. The non-invasive bioinformatics measuring device 30 receives continuous blood glucose information from the user, which is measured periodically or upon request, from the continuous bioinformatics measuring device 10.

[0083] Preferably, the user can input information about events occurring to the user into the non-invasive bioinformatics measuring device 30 within a predetermined period of time after attaching the continuous bioinformatics measuring device 10. The non-invasive bioinformatics measuring device 30 displays an interface screen for inputting event information, allowing the user to input information about events that will occur to the user in the future or events that have occurred previously. According to the field of application of the present invention, multiple sensors for sensing events occurring to the user may also be included. For example, the non-invasive bioinformatics measuring device 30 can determine events occurring to the user using activity sensors, position sensors, etc., and automatically input the determined events upon user confirmation.

[0084] Preferably, when an event occurs, the user can further input information about the conditions under which the event occurred into the non-invasive bioinformatics measuring device 30. The non-invasive bioinformatics measuring device 30 displays an interface screen allowing the user to input the event occurrence condition information. According to the field of application of this invention, it may also include multiple sensors for sensing the occurrence conditions of the event occurring to the user. For example, the non-invasive bioinformatics measuring device 30 can determine the event occurrence condition information through position sensors, temperature sensors, humidity sensors, etc., or obtain the occurrence condition information through a network. The event occurrence condition information can be automatically input with user confirmation.

[0085] The non-invasive bioinformatics measuring device 30 includes: a storage mechanism capable of storing continuous blood glucose information, non-invasive blood glucose information, event information, and occurrence condition information for a specified period; and a processor mechanism capable of using a learning model stored in the storage mechanism to learn, for the user, continuous blood glucose information corresponding to the non-invasive blood glucose information in a personalized manner from the continuous blood glucose information, non-invasive blood glucose information, event information, and occurrence condition information.

[0086] The non-invasive bioinformatics measuring device 30 can compare continuous blood glucose information received from the continuous bioinformatics measuring device 10 with non-invasive blood glucose information, and learn continuous blood glucose information corresponding to non-invasive blood glucose information for the user in a personalized way.

[0087] Preferably, the non-invasive bioinformatics measuring device 30 can compare non-invasive blood glucose information and continuous blood glucose information corresponding to event information and occurrence condition information, and use the occurrence condition information to learn continuous blood glucose information corresponding to the non-invasive blood glucose information at the time of the event for the user in a personalized manner.

[0088] That is, by using the continuous bioinformatics measurement device 10 together with the non-invasive bioinformatics measurement device 30, the continuous bioinformatics measurement device 10 can continuously measure the user's continuous blood glucose information for a specified period, such as 1 week, 15 days, or 1 month, and the non-invasive bioinformatics measurement device 30 can use the continuous blood glucose information measured within the specified period to learn the continuous blood glucose information corresponding to the non-invasive blood glucose information for the user in a personalized way.

[0089] The continuous bioinformatics measuring device 10 is removed after being attached to the user's body for a specified period, and the user's blood glucose information is measured only using the non-invasive bioinformatics measuring device 30. When non-invasive blood glucose information is obtained using a calibration model generated from the learning results, the non-invasive bioinformatics measuring device 30 applies the non-invasive blood glucose information, event information, and event occurrence condition information to the calibration model to correct the non-invasive blood glucose information.

[0090] This overcomes the shortcomings of previous methods that relied solely on non-invasive bioinformatics devices to measure blood glucose information, such as inaccurate results or inconsistent blood glucose values ​​for each user. It enables the use of non-invasive bioinformatics to accurately measure blood glucose information in a personalized manner for each user, or at least accurately determine the user's blood glucose fluctuation patterns.

[0091] Figure 3 This is a functional block diagram illustrating the non-invasive bio-information correction device of the present invention. Figure 3 The non-invasive bio-information correction device described in the text is in Figure 1 In this case, it can be implemented as a user terminal, and Figure 2 In certain situations, it can be implemented as a non-invasive bioinformatics measurement instrument.

[0092] refer to Figure 3 More specifically, the communication unit 110 communicates with and sends / receives data to an external terminal. Here, when the non-invasive biometric correction device is implemented as a user terminal, the communication unit 110 sends / receives data with the continuous biometric measuring instrument and the non-invasive biometric measuring instrument; when the non-invasive biometric correction device is implemented within the non-invasive biometric measuring instrument, the communication unit 110 sends / receives data with the continuous biometric measuring instrument. The communication unit 110 can send / receive data with the external terminal via wired or wireless means, such as using Bluetooth, NFC (Near Field Communication), infrared communication, Wi-Fi communication, or USB cable communication.

[0093] A continuous bioinformatics measurement device is attached to the user's body and continuously measures the user's blood glucose information for a specified period. A non-invasive bioinformatics measurement device is also worn by the user to measure non-invasive blood glucose information. The storage unit 130 stores the measured continuous blood glucose information and non-invasive blood glucose information. The learning unit 120 applies the continuous blood glucose information measured by the continuous bioinformatics measurement device and the non-invasive blood glucose information measured by the non-invasive bioinformatics measurement device within the specified period to a learning model and learns the corresponding continuous blood glucose information for the user, tailored to the specific needs of the user.

[0094] Preferably, during the period of continuous blood glucose information measurement within a specified period, event information occurring to the user or event occurrence condition information at the time of the event can be acquired, and the acquired continuous blood glucose information, non-invasive blood glucose information, event information, and event occurrence condition information are stored in the storage unit 130. When the learning unit 120 uses the continuous blood glucose information to learn continuous blood glucose information corresponding to the non-invasive blood glucose information for the user in a personalized manner, the non-invasive blood glucose information and continuous blood glucose information corresponding to the event information and occurrence condition information can be compared using the continuous blood glucose information, non-invasive blood glucose information, event information, and event occurrence condition information stored in the storage unit 130, and the continuous blood glucose information corresponding to the non-invasive blood glucose information at the time of the event can be learned in a personalized manner for the user using the occurrence condition information.

[0095] That is, the learning unit 120 uses a training dataset consisting of continuous blood glucose information, non-invasive blood glucose information, event information that occurs during the period of continuous blood glucose measurement, and event occurrence condition information. It learns continuous blood glucose information corresponding to non-invasive blood glucose information at the time of event occurrence based on the occurrence condition information for the user, and generates a correction model for correcting non-invasive blood glucose information from the learning results.

[0096] Here, the learning unit 120 can utilize various learning model algorithms to perform learning, such as Generalized Linear Models (GLM), Decision Trees, Random Forests, Gradient Boosting Machines (GBM), and Deep Learning. According to the field to which this invention applies, various learning model algorithms can be used when learning continuous blood glucose information corresponding to non-invasive blood glucose information for personalized user needs, and this falls within the scope of this invention.

[0097] Here, event information can be directly input by the user through the event input interface screen output to the user interface unit 150, and event occurrence condition information can be directly input by the user through the occurrence condition input interface screen output to the user interface unit 150.

[0098] According to the field to which this invention applies, an event determination unit 160 can determine an event occurring to a user. The event determination unit 160 can determine an event occurring to a user based on information received from an activity sensor and a position sensor. Preferably, when the event determination unit 160 determines that an event has occurred, it outputs information about the determined event to the user interface unit 150, and when it receives confirmation from the user, it confirms that the event has occurred to the user.

[0099] The occurrence condition determination unit 170, corresponding to the field to which this invention is applied, can determine the occurrence condition information of an event when it occurs. The occurrence condition determination unit 170 can determine the occurrence condition information based on information received from a position sensor, activity sensor, temperature sensor, humidity sensor, etc., or seasonal information, location information, temperature information, humidity information, etc., obtained through a network. Preferably, when the occurrence condition determination unit 170 determines the occurrence condition information of an event, it outputs the determined occurrence condition information to the user interface unit 150, and confirms the occurrence condition information of the event upon receiving confirmation from the user.

[0100] A continuous bioinformatics analyzer is used to generate a personalized calibration model for non-invasive blood glucose information, which is then removed from the user's body after the calibration model is generated. The calibration unit 140 applies the non-invasive blood glucose information measured by the non-invasive bioinformatics analyzer to the calibration model to calibrate the non-invasive blood glucose information. Preferably, when acquiring event information, event occurrence condition information, and non-invasive blood glucose information after removing the continuous bioinformatics analyzer, the calibration unit 140 applies the event information, event occurrence condition information, and non-invasive bioinformatics to the calibration model to calibrate the non-invasive blood glucose information.

[0101] The alarm unit 180 determines the rate of increase or decrease of non-invasive blood glucose information based on the corrected non-invasive blood glucose information. When the rate of increase or decrease of non-invasive blood glucose information exceeds the critical rate of change, an alarm is provided to the user. Alternatively, the alarm unit predicts the subsequent rate of increase or decrease of non-invasive blood glucose information from the corrected non-invasive blood glucose information. When the subsequent rate of increase or decrease of non-invasive blood glucose information exceeds the critical rate of change, an alarm is provided to the user.

[0102] Figure 4 This is a diagram illustrating the operation of the learning unit of the present invention. Figure 5 This is a diagram illustrating the operation of the correction section of the present invention.

[0103] First refer to Figure 4The operation of the learning unit is described as follows: when continuous blood glucose information and non-invasive blood glucose information are input into the learning unit 120, the learning unit 120 applies the continuous blood glucose information at the same time as the non-invasive blood glucose information to the learning model algorithm to learn the continuous blood glucose information corresponding to the non-invasive blood glucose information in a personalized way for the user, and generates a correction model for the non-invasive blood glucose information as the learning result.

[0104] Preferably, in addition to continuous blood glucose information and non-invasive blood glucose information, event information and occurrence condition information when the event occurs can be further input into the learning unit 120. The learning unit 120 applies the continuous blood glucose information, non-invasive blood glucose information, event information and occurrence condition information when the event occurs to the learning model algorithm to learn the continuous blood glucose information corresponding to the non-invasive blood glucose information when the event occurs in a personalized way for the user using the occurrence condition information, and generates a correction model for correcting the non-invasive blood glucose information as the learning result.

[0105] On the other hand, reference Figure 5 The operation of the calibration unit is described. After the continuous bioinformatics measuring device is removed from the body, the user's blood glucose information is measured using only a non-invasive bioinformatics measuring device. The calibration unit 140 can also apply the additional non-invasive blood glucose information obtained after the continuous bioinformatics measuring device is removed to the calibration model to correct the additional non-invasive blood glucose information.

[0106] Preferably, in addition to non-invasive blood glucose information, the calibration unit 140 can also be further input with additional event information and additional occurrence condition information when the additional event occurs. The calibration unit 140 can apply the non-invasive blood glucose information, event information and occurrence condition information when the event occurs to the calibration model to correct the additional non-invasive blood glucose information.

[0107] Figure 6 This is a flowchart illustrating a non-invasive bio-information correction method according to an embodiment of the present invention.

[0108] refer to Figure 6 To describe it more specifically, when continuous blood glucose information is measured by a continuous bioinformatics measuring instrument within a specified period, continuous blood glucose information is received and acquired (S111); when non-invasive blood glucose information is measured by a non-invasive bioinformatics measuring instrument within a specified period, non-invasive blood glucose information is acquired (S113).

[0109] The continuous bioinformatics measuring device is attached to the body for a specified period to measure continuous blood glucose information, and is removed from the body after the specified period. The continuous blood glucose information measured during the specified period and the non-invasive blood glucose information measured at the same time as the continuous blood glucose information during the specified period are applied to the learning model algorithm to learn for the user's personalization, and a correction model is generated from the learning results (S115).

[0110] The method involves comparing non-invasive blood glucose data measured at the same time with continuous blood glucose data to extract features from the non-invasive blood glucose data. The corresponding continuous blood glucose data is then learned to generate a calibration model. Alternatively, the non-invasive and continuous blood glucose data measured at the same time can be applied to the input nodes of an artificial neural network model to calculate the weights of hidden nodes using linear regression to generate a calibration model. Since the learning method based on features extracted from machine learning and the learning method based on artificial neural network models are widely known, a detailed description of them will be omitted.

[0111] According to the field to which this invention applies, in addition to generating a correction model based on continuous bioinformation corresponding to non-invasive blood glucose information learned by the user in a personalized manner, a correction model can also be generated from non-invasive blood glucose information based on the user's personalized learning of the increase and decrease patterns of continuous blood glucose information corresponding to the increase and decrease patterns of non-invasive blood glucose information. The correction model for the increase and decrease pattern is based solely on non-invasive blood glucose information to correct whether the user's blood glucose is in an increasing or decreasing pattern, and therefore can be more accurate than correcting the user's blood glucose value using non-invasive blood glucose information.

[0112] Refer again Figure 6 The description is as follows: when additional non-invasive blood glucose information is obtained from the non-invasive bioinformatics instrument after the continuous bioinformatics instrument is removed from the body (S117), the additional non-invasive blood glucose information is applied to the calibration model to correct the non-invasive blood glucose information (S119).

[0113] Figure 7 This is a flowchart illustrating a non-invasive bio-information correction method according to another embodiment of the present invention.

[0114] Figure 7 The non-invasive bioinformation correction method of another embodiment of the present invention described herein relates to a method for learning non-invasive blood glucose information in a personalized manner for a user, in addition to using continuous blood glucose information acquired within a specified period, and also utilizing event information or event occurrence condition information that occurred within the specified period.

[0115] refer to Figure 7The description includes receiving and acquiring continuous blood glucose information when continuous blood glucose information is measured by a continuous bioinformatics measuring device within a specified period (S131); and acquiring non-invasive blood glucose information when non-invasive blood glucose information is measured by a non-invasive bioinformatics measuring device within a specified period (S132).

[0116] When an event occurs within the specified period, information about the event and the conditions under which the event occurred are obtained (S133). Here, the event information includes everything that can affect the user's biometric information, such as the type and duration of exercise, food intake, type and amount of food intake, the level of stress experienced by the user, and the user's physical condition (sleep time and quality, illness, etc.).

[0117] On the other hand, when an event occurs, the information on the conditions under which the event occurs can include the season, weather, time, location, position, temperature, humidity, etc.

[0118] Such event information and event occurrence conditions can be directly input by the user through the interface screen, but can also be automatically determined by using information obtained through various sensors or through the network.

[0119] In addition to continuous blood glucose information measured within a specified period and non-invasive blood glucose information measured at the same time as the continuous blood glucose information within the specified period, event information and event occurrence condition information are further applied to the learning model algorithm to learn for the user's personalization, and a correction model is generated from the learning results (S134).

[0120] The method involves comparing continuous blood glucose data measured at the same time as the non-invasive blood glucose measurement within the event information and event occurrence condition information to extract features from the non-invasive blood glucose information. The corresponding continuous blood glucose information is then learned to generate a calibration model. Alternatively, the event information, event occurrence condition information, and the non-invasive and continuous blood glucose data measured at the same time can be applied to the input nodes of an artificial neural network model to calculate the weights of hidden nodes using linear regression to generate a calibration model. Since the learning method based on features extracted from machine learning and the learning method based on artificial neural network models are widely known, a detailed description of them will be omitted.

[0121] In the field to which this invention is applied, in addition to generating a calibration model by using event occurrence conditions to learn continuous bio-information corresponding to the non-invasive bio-information at the time of the event in a personalized manner for the user, a calibration model can also be generated by using event occurrence conditions to learn continuous blood glucose information increase / decrease patterns corresponding to the increase / decrease patterns of non-invasive blood glucose information in a personalized manner for the user in a personalized manner.

[0122] Refer again Figure 7 After the continuous bioinformatics measuring device is removed from the body, additional non-invasive blood glucose information is acquired by the non-invasive bioinformatics measuring device (S135). When event information and event occurrence condition information that occurred to the user are acquired (S137), the additional non-invasive blood glucose information, event information and event occurrence condition information are applied to the calibration model to correct the non-invasive blood glucose information (S139).

[0123] Figure 8 An example is shown of non-invasive blood glucose information measured by a non-invasive bioinformatics instrument and an example of continuous blood glucose information measured by a continuous bioinformatics instrument.

[0124] like Figure 8 As shown in (a), regarding non-invasive blood glucose information measured by non-invasive bioinformatics measuring instruments, due to various reasons such as inaccurate measurement principles or difficulty in setting non-invasive bioinformatics measuring instruments for individual users, the blood glucose levels do not rise in the same way when the actual user's blood glucose rises or fall in the same way when blood glucose falls. Instead, meaningless values ​​of blood glucose levels that rise and fall repeatedly, such as noise or background noise, may be obtained.

[0125] Unlike this, such as Figure 8 As shown in (b), the continuous blood glucose information measured by the continuous bioinformatics meter can guarantee accuracy to some extent by measuring continuous blood glucose information that rises in the same way when the user's blood glucose rises and falls in the same way when blood glucose falls.

[0126] In this way, non-invasive blood glucose information can be personalized for users by using continuous blood glucose information measured by a continuous bioinformatics instrument over a specified period.

[0127] This continuous bioinformatics measurement device can be inserted and attached to the user's body for a specified period to measure continuous blood glucose information, and uses the continuous blood glucose information acquired over the specified period to personalize the non-invasive blood glucose information measured by the non-invasive bioinformatics measurement device for the user.

[0128] Figure 9 Instructions are provided regarding the prescribed period for wearing the continuous biometric measurement device on the body.

[0129] refer to Figure 9 (a) As described, the continuous bioinformatics measurement device can be inserted into a specified time period among the user's body time periods T1, T2, and T3.

[0130] Here, T1, T2, and T3 can be worn on the user's body during the use of the continuous bioinformatics measurement device, for example, for 1 week, 15 days, or 1 month.

[0131] However, even if the continuous bioinformatics analyzer has a one-month lifespan, it can be worn on the user's body for shorter periods (T1, T2, T3) as needed. Here, the period during which the continuous bioinformatics analyzer is worn to measure continuous blood glucose information can be set as the time for completing the calibration model. That is, even if the continuous bioinformatics analyzer has a one-month lifespan, it can be removed after 10 days when a calibration model with the required accuracy is generated from continuous blood glucose information measured over 10 days.

[0132] In this invention, multiple continuous bioinformatics instruments can be used to measure continuous blood glucose information over multiple specified periods, and a more accurate calibration model can be generated from the continuous blood glucose information measured over multiple specified periods.

[0133] Multiple continuous biometric sensors can be inserted and attached to measure continuous blood glucose information at predetermined intervals, which can be set to be spaced out from each other, such as... Figure 9 As shown in (b), multiple specified periods T1, T2, T3, and T4 are set at equal time intervals, or as follows: Figure 9 As shown in (c), the multiple specified periods T1, T2, T3, T4 can be set separately by at least one of the following: environmental conditions, seasonal conditions, user physical conditions, and user physiological conditions, with different intervals between them.

[0134] Figure 10 An example of the interface screen for inputting event information in this invention will be described.

[0135] like Figure 10 As shown in (a), an input interface screen for inputting event information is activated on the display of the user terminal. The user can input the event type, detailed type, event details, etc. through the input interface screen.

[0136] like Figure 10 As shown in (b), when the non-invasive bioinformatics measuring instrument is equipped with a display unit, the input interface screen for inputting event information is activated on the display unit, and the user can input the event type, detailed type, event details, etc. through the input interface screen.

[0137] Figure 11An example of event information input via an interface screen is described.

[0138] like Figure 11 As shown, when an event occurring within a specified period and the conditions under which that event occurred are entered by the user through the input interface, an event icon E is displayed, indicating the event information and its occurrence conditions over time. Selecting an event icon activates detailed information about the corresponding event and its occurrence conditions.

[0139] Figure 12 This is a diagram illustrating an example of displaying measured blood glucose information using only a non-invasive bioinformatics device after the removal of a continuous bioinformatics device.

[0140] After removing the continuous bioinformatics analyzer, the user only uses a non-invasive bioinformatics analyzer to receive measured blood glucose information, such as... Figure 12 As shown in (a), the blood glucose information R is displayed when subsequent input event information, subsequent event occurrence condition information, and subsequent non-invasive blood glucose information are applied to the calibration model for calibration.

[0141] like Figure 12 As shown in (b), information about the increase or decrease pattern of the user's blood glucose is displayed, which is determined by applying blood glucose information that is subsequently input, the occurrence conditions of subsequent events, and subsequent non-invasive blood glucose information to the calibration model.

[0142] Figure 13 This is a flowchart illustrating an example of providing alerts to users based on patterns of increasing or decreasing blood glucose information.

[0143] refer to Figure 13 To provide a more specific description, additional non-invasive blood glucose information, additional event information, and additional event occurrence condition information are applied to the calibration model to determine the increase or decrease pattern of the user's blood glucose information (S151), and the increase or decrease rate is determined from the determined increase or decrease pattern (S153).

[0144] Determine whether the determined rate of increase or decrease is greater than the critical rate of change (S155). If the determined rate of increase or decrease is greater than the critical rate of change, generate an alarm message and provide it to the user (S157).

[0145] Figure 14 This is a flowchart illustrating an example of providing alerts to users based on the rate of subsequent increases or decreases in blood glucose information.

[0146] refer to Figure 14To describe it more specifically, additional non-invasive blood glucose information, additional event information, and information on the occurrence conditions of the additional events are applied to the calibration model to determine the increase or decrease pattern of the user's blood glucose information (S171), and the expected subsequent rate of increase or decrease is determined based on the determined increase or decrease pattern (S173). Here, the expected subsequent rate of increase or decrease can be determined based on the expected increase or decrease pattern to be seen subsequently, which is determined based on the increase or decrease pattern determined according to the user's personalized learning.

[0147] Determine whether the determined subsequent increase or decrease rate is greater than the critical rate of change (S175). If the determined subsequent increase or decrease rate is greater than the critical rate of change, generate an alarm message and provide it to the user (S177).

[0148] Figure 15 This shows an example of an alert message provided to the user.

[0149] like Figure 15 As shown in (a), along with the blood glucose correction information R, the event icon E indicating an event occurring to the user and the alarm icon A indicating an alarm message are displayed in chronological order of the events. Selecting alarm icon A2 activates a specific alarm message.

[0150] like Figure 15 As shown in (b), along with information about the user's blood glucose fluctuation patterns, event icons E (indicating an event occurring to the user) and alarm icons A (indicating an alarm message) are displayed in chronological order of the events. Selecting alarm icon A1 activates a specific alarm message.

[0151] On the other hand, the embodiments of the present invention described above can be written as programs that can be executed on a computer, and can be implemented in a general-purpose digital computer that runs the program using a computer-readable recording medium.

[0152] The computer-readable recording media include magnetic storage media (e.g., ROM, floppy disk, hard disk, etc.), optical reading media (e.g., CD-ROM, DVD, etc.), and storage media such as carrier waves (e.g., transmission over the Internet).

[0153] While the invention has been described with reference to embodiments shown in the accompanying drawings, these are merely exemplary, and those skilled in the art will understand that various modifications and equivalent embodiments can be implemented. Therefore, the true scope of protection of the invention should be defined by the technical concept of the appended claims.

Claims

1. A method of non-invasive bio-information correction, characterized by, include: The step of measuring a user's continuous biometrics using a continuous biometrics measuring device, the continuous biometrics measuring device including a sensor configured to be at least partially inserted into the user's body and to measure the user's continuous biometrics over a specified period; The steps of measuring a user's non-invasive biometric information by means of a non-invasive biometric measuring device that measures the user's non-invasive biometric information during the specified period; While measuring continuous biometric information, event information and occurrence condition information of events occurring to the user are acquired; By comparing the increase / decrease patterns of non-invasive biological information based on event information and occurrence condition information with the increase / decrease patterns of continuous biological information, the system learns the increase / decrease patterns of continuous biological information corresponding to the increase / decrease patterns of non-invasive biological information in each event that matches the occurrence condition information, in order to generate personalized models for users. Acquire additional non-invasive biometric information of users, as well as additional event information and additional occurrence condition information of additional events that occur in users after a personalized model is generated for them; as well as The additional non-invasive bioinformation is corrected based on a personalized model that applies the additional non-invasive bioinformation, the additional event information, and the additional occurrence condition information.

2. The non-invasive bio-information correction method according to claim 1, characterized in that, The continuous biological information increase and decrease pattern is learned in accordance with the increase and decrease pattern of the additional non-invasive biological information, so as to correct the increase and decrease pattern of the additional non-invasive biological information.

3. The non-invasive bio-information correction method according to claim 1, characterized in that, The event information is entered through the event input interface.

4. The non-invasive bio-information correction method according to claim 1, characterized in that, The occurrence condition information is at least one of the following: seasonal information, time information, location information, position information, temperature information, and humidity information.

5. The non-invasive bio-information correction method according to claim 4, characterized in that, The occurrence condition information is input through the displayed occurrence condition input interface.

6. The non-invasive bio-information correction method according to claim 1, characterized in that, The user's continuous biometrics are measured over multiple specified periods using multiple continuous biometric measurement devices, including the aforementioned continuous biometric measurement device.

7. The non-invasive bio-information correction method according to claim 6, characterized in that, The multiple specified periods are set at intervals from each other.

8. The non-invasive bio-information correction method according to claim 7, characterized in that, The multiple specified periods are set apart by the same time interval.

9. The non-invasive bio-information correction method according to claim 7, characterized in that, The multiple specified periods are set at intervals based on at least one of the following: environmental conditions, seasonal conditions, user physical conditions, and user physiological conditions.

10. The non-invasive bio-information correction method according to claim 1, characterized in that, The addition and subtraction patterns of the supplementary non-invasive biological information and the addition and subtraction patterns of the continuous biological information learned in accordance with the supplementary event information are determined in order to correct the addition and subtraction patterns of the supplementary non-invasive biological information.

Images