A method for measuring real-time blood glucose values ​​and control levels based on electrocardiograms and a computer program recorded on a recording medium for carrying out the method

Abstract

The present invention proposes a method for measuring real-time blood glucose levels and blood sugar management based on an electrocardiogram (ECG). The method includes the steps of acquiring an electrocardiogram (ECG) signal measured from a user, analyzing the ECG signal using a pre-trained first artificial intelligence (AI) to estimate the user's blood sugar level, analyzing the ECG signal using the AI ​​to determine whether the user has hyperglycemia or hypoglycemia, and determining whether the user needs guidance on blood glucose or diabetes based on the estimated blood glucose level and the determination result on whether the user has hyperglycemia or hypoglycemia. Thus, by simply measuring an ECG, a user can instantly check their blood glucose level and how well they are managing their blood glucose, thereby enabling early detection of hyperglycemia and diabetes or preventing complications associated with hyperglycemia or diabetes.

Description

[Technical Field]

[0001] The present invention relates to smart healthcare, and more particularly to a method for measuring real-time blood sugar values ​​and management levels based on an electrocardiogram (ECG), and a computer program recorded on a recording medium for executing the method. [Background technology]

[0002] An electrocardiogram (ECG) is a graphical record of the visual changes in electrical activity generated by the heart muscles. Briefly explaining the cardiac conduction system, the sinoatrial node (SA node) periodically generates electrical signals to induce cardiac contractions. The atrioventricular node (AV node) transmits the electrical signals generated by the SA node through the atria, after slightly delaying them. The electrical signals transmitted from the AV node are then distributed throughout the ventricles via the His bundle and Purkinje fibers.

[0003] The electrocardiogram (ECG) waveforms that can be seen during the cardiac impulse conduction process are as follows: The P wave is seen when the electrical signal generated by the sinoatrial node polarizes the atria, causing the valvular myocardium to contract, then depolarizes and relaxes again. The PQ wave is seen when the atrioventricular node delays the electrical signal to prevent the ventricles from immediately responding when the atria contract. The QRS complex is seen when the delayed electrical signal is transmitted by the AV node (Q), causing the ventricles to immediately polarize (R) and then immediately depolarize (S). The ST wave is seen during the resting period when the ventricles contract and blood moves around the body, preventing the electrical signal from stimulating the heart. The T wave is seen when the ventricles weakly polarize and then depolarize again, causing the ventricles and valvular myocardium to simultaneously relax. In some cases, a U wave due to repolarization of the intraventricular septum can also be seen.

[0004] The order of appearance of waveforms (P waves, PQ waves, QRS waves, ST waves, T waves, and U waves) that can be confirmed by such an electrocardiogram (ECG), as well as their respective shapes, sizes, and intervals, can vary in various forms depending on the health state. In other words, by analyzing the order of appearance, shapes, sizes, and intervals of waveforms included in an electrocardiogram (ECG), it is possible to infer the health state and even the various causes that cause such health state.

[0005] Meanwhile, artificial intelligence (AI) refers to technology that artificially embodies some or all of human learning, reasoning, and perception abilities through computer programs. In relation to AI, machine learning refers to learning that optimizes parameters based on given data using a model composed of multiple parameters.

[0006] Machine learning is divided into supervised learning, unsupervised learning, and reinforcement learning depending on the learning methodology, and is further divided into regression analysis, artificial neural networks (ANN), deep learning (DL), etc. depending on the learning algorithm.

[0007] Meanwhile, blood sugar refers to the glucose contained in the blood. Generally, blood sugar levels are maintained at a constant level through the interaction of insulin, glucagon, epinephrine, glucocorticoids, adrenocorticotrophic hormone, and thyroid hormone. Diabetes mellitus (DM) is a metabolic disease characterized by symptoms such as hyperglycemia due to insufficient insulin secretion or improper function of the secreted insulin.

[0008] If hyperglycemia persists for a long time or diabetes worsens, myocardial infarction, which occurs when the coronary artery becomes suddenly blocked, or cerebral infarction (stroke), which occurs when the cerebral artery becomes blocked or ruptured, can occur. Other complications include amblyopia, blindness, and renal function impairment.

[0009] According to various research results, if the value of glycated hemoglobin (HbA1c), which means blood pigment bound to glucose, is reduced by 1%, the risk of developing complications due to hyperglycemia or diabetes will decrease by approximately 20% to 30%. Therefore, various methods that can support thorough blood sugar management before complications due to high blood pressure or diabetes occur are needed. Summary of the Invention [Problem to be solved by the invention]

[0010] An object of the present invention is to propose a method that can measure the real-time value and control level of blood glucose based on an electrocardiogram (ECG).

[0011] Another object of the present invention is to provide a computer program recorded on a recording medium for executing a method for measuring real-time blood glucose values ​​and blood glucose control levels based on an electrocardiogram (ECG).

[0012] The technical problems of the present invention are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0013] To achieve the above technical objectives, the present invention proposes a method for measuring a real-time blood glucose value and a blood sugar management level based on an electrocardiogram (ECG). The method includes the steps of acquiring an electrocardiogram (ECG) signal measured from a user, analyzing the ECG signal using a first artificial intelligence (AI) that has been trained in advance to estimate the user's blood sugar value, analyzing the ECG signal using the AI ​​to determine whether the user has hyperglycemia or hypoglycemia, and determining whether the user needs guidance on blood glucose or diabetes based on the estimated blood glucose value and the determination result on whether the user has hyperglycemia or hypoglycemia.

[0014] If it is determined that the guidance is necessary after the step of determining whether the guidance is necessary, the method may further include a step of transmitting guidance information set based on the blood glucose value, the glycosylated hemoglobin (HbA1c) value, the determination result as to whether the blood glucose value is hyperglycemia or hypoglycemia, and the determination result as to whether the glycosylated hemoglobin (HbA1c) value is normal or abnormal to a user equipment (UE) pre-set corresponding to the user.

[0015] In addition, the step of determining whether the patient has hyperglycemia or hypoglycemia may involve analyzing the electrocardiogram (ECG) signal using a pre-trained second artificial intelligence (AI) to estimate the user's glycated hemoglobin (HbA1c) value, and then analyzing the electrocardiogram (ECG) signal using the second artificial intelligence (AI) to determine whether the glycated hemoglobin (HbA1c) is normal or abnormal.

[0016] More specifically, the step of determining whether the patient is hyperglycemic or hypoglycemic may include the steps of: extracting one or more feature information by disassembling the acquired electrocardiogram (ECG) signal based on one or more of amplitude, frequency, and time; dividing the extracted feature information into a plurality of subunits according to the chronological order in which the ECG signal is measured; inputting the divided subunits into the first artificial intelligence (AI) and the second artificial intelligence (AI), respectively, and acquiring a plurality of numerical values ​​and probability values ​​from the first artificial intelligence (AI) and the second artificial intelligence (AI); estimating the blood glucose value based on the numerical value and probability value acquired from the first artificial intelligence (AI) and determining whether the patient is hyperglycemic or hypoglycemic; and estimating the glycated hemoglobin (HbA1c) value based on the numerical value and probability value acquired from the second artificial intelligence (AI) and determining whether the glycated hemoglobin (HbA1c) is normal or abnormal.

[0017] In this case, the step of extracting the feature information may involve extracting the feature information by decomposing the electrocardiogram (ECG) signal using one of a wavelet transform, an ensemble empirical mode decomposition (EEMD), a triadic motif field (TMF), and a triadic motif difference field (TMDF).

[0018] According to one embodiment, the step of dividing into a plurality of subunits may involve moving a window of a predetermined size along a time axis, and dividing the feature information acquired from the electrocardiogram (ECG) signal into a plurality of subunits having a size corresponding to the window.

[0019] Meanwhile, the step of obtaining the plurality of numerical values ​​and probability values ​​may be performed by inputting feature vectors for the plurality of divided subunits into a multiple linear regression model and a classification model of the first artificial intelligence (AI) and the second artificial intelligence (AI), respectively, to obtain the plurality of numerical values ​​and probability values.

[0020] The step of determining whether the value is normal or abnormal may include removing outliers included in the values ​​obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a predetermined validated range, estimating the blood glucose value using a soft voting result based on the average value of the values ​​obtained from the first artificial intelligence (AI) from which the outliers have been removed, and estimating the glycated hemoglobin (HbA1c) value using a soft voting result based on the average value of the values ​​obtained from the second artificial intelligence (AI) from which the outliers have been removed.

[0021] In addition, the step of determining whether the blood sugar is normal or abnormal can involve removing outliers included in the probability values ​​obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on the valid range, determining whether the blood sugar is hyperglycemia or hypoglycemia using a hard voting result based on a majority vote of the probability values ​​obtained from the first artificial intelligence (AI) from which the outliers have been removed, and determining whether the glycated hemoglobin (HbA1c) is normal or abnormal using a hard voting result based on a majority vote of the probability values ​​obtained from the second artificial intelligence (AI) from which the outliers have been removed.

[0022] To achieve the above technical objectives, the present invention proposes a computer program recorded on a recording medium for executing a method for measuring a real-time blood glucose level and management level based on an electrocardiogram (ECG). The computer program can be coupled to a computing device including a memory, a transceiver, an input / output device, and a processor for processing instructions resident in the memory. The computer program may be recorded on a recording medium to cause the processor to execute the following steps: acquire an electrocardiogram (ECG) signal measured from a user via the transceiver or the input / output device; analyze the ECG signal using a first artificial intelligence (AI) that has been previously trained to estimate the user's blood glucose level, analyze the ECG signal using the AI ​​to determine whether the user has hyperglycemia or hypoglycemia; and determine whether the user needs guidance on blood glucose or diabetes based on the estimated blood glucose level and the determination result of hyperglycemia or hypoglycemia.

[0023] Further details of the embodiments are included in the detailed description and accompanying drawings. [Effects of the Invention]

[0024] According to an embodiment of the present invention, a user can instantly check their blood glucose level and how well they have managed their blood glucose by simply measuring their electrocardiogram (ECG), which can result in early detection of hyperglycemia and diabetes or prevention of complications caused by hyperglycemia or diabetes.

[0025] The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be apparent to those skilled in the art to which the present invention pertains from the claims. [Brief explanation of the drawings]

[0026] [Figure 1] FIG. 2 is an exemplary diagram illustrating a blood glucose management means according to an embodiment of the present invention. [Figure 2] 1 is an exemplary diagram illustrating a blood glucose management system according to an embodiment of the present invention; [Figure 3] FIG. 2 is a logical configuration diagram of a blood glucose management server according to an embodiment of the present invention. [Figure 4] 1 is an exemplary diagram illustrating a learning process of artificial intelligence (AI) according to an embodiment of the present invention. [Figure 5] 1 is an exemplary diagram illustrating a method for canceling an electrocardiogram (ECG) signal according to an embodiment of the present invention. [Figure 6] 10A and 10B are exemplary diagrams illustrating a process of dividing into a plurality of partial units according to some embodiments of the present invention; [Figure 7] 10A and 10B are exemplary diagrams illustrating a process of dividing into a plurality of partial units according to some embodiments of the present invention; [Figure 8] 1 is an exemplary diagram illustrating an analysis process using artificial intelligence (AI) according to some embodiments of the present invention. FIG. [Figure 9] 1 is an exemplary diagram illustrating a process of interpreting an artificial intelligence (AI) analysis result according to an embodiment of the present invention. [Figure 10] 1 is an exemplary diagram illustrating a process of interpreting an artificial intelligence (AI) analysis result according to an embodiment of the present invention. [Figure 11] FIG. 2 is a hardware configuration diagram of a blood glucose management server according to an embodiment of the present invention. [Figure 12] 1 is a flowchart illustrating a method for measuring a real-time blood glucose value and a blood glucose control level according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0027] It should be noted that the technical terms used herein are merely used to describe specific embodiments and are not intended to limit the present invention. Furthermore, unless otherwise defined herein, technical terms used herein should be interpreted in a way that is commonly understood by a person of ordinary skill in the art to which the present invention pertains, and should not be interpreted in an overly comprehensive or overly narrow sense. Furthermore, if a technical term used herein is incorrect and cannot accurately express the concept of the present invention, it should be understood by substituting a technical term that can be correctly understood by a person skilled in the art. Furthermore, general terms used herein should be interpreted according to their predefined meanings or the context, and should not be interpreted in an overly narrow sense.

[0028] Furthermore, as used herein, singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as "comprise" or "have" should not be interpreted as necessarily including all of the components or steps described in the specification, but should be interpreted as not including some of the components or steps, or as possibly including additional components or steps.

[0029] Furthermore, terms including ordinal numbers such as "first" and "second" used in this specification may be used to describe various components, but the components should not be limited to these terms. These terms are used only to distinguish one component from another. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component, without departing from the scope of the present invention.

[0030] When a component is said to be "coupled" or "connected" to another component, it may be directly coupled or connected to the other component, but there may be other components in between. On the other hand, when a component is said to be "directly coupled" or "directly connected" to another component, it should be understood that there are no other components in between.

[0031] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings. Identical or similar elements will be given the same reference numerals regardless of the drawing numbers, and redundant description thereof will be omitted. Furthermore, in the description of the present invention, if it is determined that a detailed description of related known technology may obscure the gist of the present invention, such a detailed description will be omitted. It should be noted that the accompanying drawings are merely provided to facilitate understanding of the concept of the present invention, and the concept of the present invention should not be construed as being limited by the accompanying drawings. The concept of the present invention should be construed as extending to all modifications, equivalents, or alternatives other than those shown in the accompanying drawings.

[0032] As described above, if hyperglycemia persists for a long time or diabetes worsens, myocardial infarction, which occurs when coronary arteries are suddenly blocked, or stroke, which occurs when cerebral arteries are blocked or ruptured, may occur, and other complications such as decreased vision, blindness, and decreased kidney function may also occur. Therefore, various measures that can support thorough blood sugar control before complications due to high blood pressure or diabetes occur are currently needed.

[0033] In order to meet such demands, the present invention proposes a means for measuring the real-time value and control level of blood glucose based on an electrocardiogram (ECG).

[0034] FIG. 1 is an exemplary diagram for explaining a blood sugar management means according to one embodiment of the present invention.

[0035] As shown in FIG. 1, a blood glucose management means according to an embodiment of the present invention measures a user's electrocardiogram (ECG) 10 using an electrocardiogram reader (ECG reader) 100, analyzes the measured user's electrocardiogram (ECG) 10 using artificial intelligence (AI), estimates the user's blood sugar level, glycated hemoglobin (HbA1c) level, etc., and provides the user with a guide 20 for blood glucose or diabetes based on the estimated results.

[0036] Therefore, according to one embodiment of the present invention, a user can instantly check their blood glucose level and how well they have managed their blood glucose by simply measuring an electrocardiogram (ECG) 10, which can result in early detection of hyperglycemia and diabetes or prevention of complications caused by hyperglycemia or diabetes.

[0037] Hereinafter, an apparatus and method for realizing the above-mentioned features will be described in detail.

[0038] FIG. 2 is an exemplary diagram illustrating a blood glucose management system according to an embodiment of the present invention.

[0039] As shown in FIG. 2, a blood glucose management system according to one embodiment of the present invention may include one or more electrocardiographs 100a, 100b, ..., 100n; 100, one or more user devices 200a, 200b, ..., 200n; 200, and a blood glucose management server 300.

[0040] The components of the exercise recommendation system according to one embodiment of the present invention merely indicate functionally separated components, and therefore, two or more components may be integrated and implemented in an actual physical environment, or a single component may be implemented separately from each other in an actual physical environment.

[0041] To explain each component, the electrocardiograph 100 is a device capable of measuring and recording a user's electrocardiogram (ECG) 10 .

[0042] Specifically, the electrocardiograph 100 induces electric potential changes due to electrical activity in the myocardium through electrodes in contact with the user's body, amplifies the induced electric potential changes, and records them as a waveform.

[0043] The electrocardiogram 100 according to an embodiment of the present invention may generate an electrocardiogram (ECG) using any one of standard limb leads, unipolar limb leads, and precordial leads, but the lead type of the electrocardiogram 10 of the electrocardiogram 100 is not limited thereto. The electrocardiogram 100 may include electrodes for 1 lead, 6 leads, or 12 leads, but the number of leads of the electrocardiogram 100 is not limited thereto. The electrocardiogram 100 may be of any one of a watch type 100a, a portable type 100b, and a Holter type 100n, but the type of the electrocardiogram 100 is not limited thereto.

[0044] The electrocardiogram (ECG) signal (i.e., the recorded waveform signal) measured by the electrocardiograph 100 can be directly transmitted to the server 300 by the network function of the electrocardiograph 100 itself, or can be input to the blood glucose management server 300 via a third means. For example, the third means can be any one of a removable medium, a user device 200, and a data input action by a user, but is not limited thereto.

[0045] Next, the user device 200 can output guidance information 20 about blood glucose or diabetes determined by the blood glucose management server 300.

[0046] Specifically, the user device 200 can receive guidance information 20 about blood glucose or diabetes from the blood glucose management server 300. Then, the user device 200 can output the received guidance information 20 about blood glucose or diabetes.

[0047] In this case, the blood glucose or diabetes guide 20 information may directly include the blood glucose value, the glycosylated hemoglobin (HbA1c) value, the determination result of whether the blood glucose or hypoglycemia is high or low, or the determination result of whether the glycosylated hemoglobin (HbA1c) is normal or abnormal, or may include indirect cautions, recommendations, or warnings based on the blood glucose value, the glycosylated hemoglobin (HbA1c) value, the determination result of whether the blood glucose or hypoglycemia is high or low, or the determination result of whether the glycosylated hemoglobin (HbA1c) is normal or abnormal. In addition, the blood glucose or diabetes guide 20 information may include one or more of guidance on measures that the user should take immediately in relation to blood glucose or diabetes and guidance to support the user's diabetes management.

[0048] The user device 200 according to an embodiment of the present invention is not limited to a user equipment (UE) defined by 3GPP (3rd Generation Partnership Project) or a mobile station (MS) defined by IEEE (Institute of Electrical and Electronics Engineers), but may be any device that can transmit and receive data to and from the blood glucose management server 300 and perform calculations based on the transmitted and received data.

[0049] For example, the user device 200 may be any one of, but is not limited to, a fixed computing device such as a desktop PC 200c, a workstation, or a server, or a mobile computing device such as a smartphone 200a, a laptop PC 200b, a tablet PC, a phablet, a portable multimedia player (PMP), a personal digital assistant (PDA), or an e-book reader.

[0050] As a next configuration, the blood glucose management server 300 can estimate the user's blood glucose level, glycated hemoglobin level, etc. based on the electrocardiogram (ECG) 10 measured by the electrocardiograph 100, and transmit guidance information 20 about blood glucose or diabetes to the user device 200 based on the estimated results.

[0051] Specific components and operations of the blood glucose management server 300 will be described later with reference to FIGS.

[0052] The one or more electrocardiographs 100, one or more user devices 200, and blood glucose management server 300 constituting the above-described blood glucose management system can transmit and receive data via a network that directly connects the devices to each other and is a combination of one or more of a secure line, a shared wired communication network, and a mobile communication network.

[0053] For example, the shared wired communication network may include, but is not limited to, Ethernet, x Digital Subscriber Line (xDSL), Hybrid Fiber Coax (HFC), and Fiber To The Home (FTTH). Also, the mobile communication network may include, but is not limited to, Code Division Multiple Access (CDMA), Wideband CDMA (WCDMA), High Speed ​​Packet Access (HSPA), Long Term Evolution (LTE), and 5th generation mobile telecommunications.

[0054] The components of the blood glucose management server 300 having the above-mentioned features will be specifically described below.

[0055] Figure 3 is a logical block diagram of a blood glucose management server according to an embodiment of the present invention. Figure 4 is an exemplary diagram illustrating an artificial intelligence (AI) learning process according to an embodiment of the present invention. Figure 5 is an exemplary diagram illustrating a method for canceling an electrocardiogram (ECG) signal according to an embodiment of the present invention. Figures 6 and 7 are exemplary diagrams illustrating a process of dividing into a plurality of subunits according to some embodiments of the present invention. Figure 8 is an exemplary diagram illustrating a process of analyzing using artificial intelligence (AI) according to some embodiments of the present invention. And Figures 9 and 10 are exemplary diagrams illustrating a process of interpreting the results of artificial intelligence (AI) analysis according to an embodiment of the present invention.

[0056] As shown in FIG. 3, a blood glucose management server 300 according to an embodiment of the present invention may include a communication unit 305, an input / output unit 310, an artificial intelligence learning unit 315, an electrocardiogram release unit 320, a blood glucose analysis unit 325, and a guidance determination unit 330.

[0057] The components of the blood glucose management server 300 according to one embodiment of the present invention merely indicate functionally separated components, and therefore, two or more components may be implemented in an integrated manner in an actual physical environment, or one component may be implemented in a separated manner in an actual physical environment.

[0058] To explain each component, the communication unit 305 can send and receive data to and from the electrocardiograph 100 and the user device 200.

[0059] Specifically, the communication unit 305 can receive an electrocardiogram (ECG) 10 signal from the electrocardiograph 100. The communication unit 305 can also transmit information about blood glucose or diabetes guidance 20 to the user device 200.

[0060] The next component, the input / output unit 310, can receive commands from an administrator through a user interface (UI) or output calculation results.

[0061] Specifically, the input / output unit 310 may receive an input of a conversion method for extracting feature information from the signal of the electrocardiogram (ECG) 10. The input / output unit 310 may receive an input of a validated range, which is a criterion for dividing the feature information into a plurality of subunits. The input / output unit 310 may receive an input of an exercise dictionary in which the cardiac pump status, oxygen intake, and activity metabolic rate are matched with the type of exercise, exercise intensity, and exercise duration.

[0062] The input / output unit 310 can receive an input of a blood glucose value that serves as a criterion for determining whether the patient is hyperglycemic or hypoglycemic. The input / output unit 310 can also receive an input of a glycated hemoglobin (HbA1c) value that serves as a criterion for determining whether the patient is glycated or abnormal.

[0063] The input / output unit 310 can also output a signal of the user's electrocardiogram (ECG) 10. The input / output unit 310 can also output information about blood sugar or diabetes 20 to be provided to the user.

[0064] As the next configuration, the artificial intelligence learning unit 315 can train the first artificial intelligence (AI) and the second artificial intelligence (AI) by machine learning based on the signal of the electrocardiogram (ECG) 10.

[0065] Specifically, the first artificial intelligence (AI) is an AI for estimating the user's blood glucose level and determining whether the user has hyperglycemia or hypoglycemia, and the second artificial intelligence (AI) is an AI for estimating the user's glycosylated hemoglobin (HbA1c) level and determining whether the user's glycosylated hemoglobin (HbA1c) is normal or abnormal.

[0066] 4, the first AI may include a multiple linear regression model for estimating a user's blood glucose level and a classification model for determining whether the user has hyperglycemia or hypoglycemia, and the second AI may include a multiple linear regression model for estimating a user's glycated hemoglobin (HbA1c) level and a classification model for determining whether the glycated hemoglobin (HbA1c) level is normal or abnormal.

[0067] The artificial intelligence (AI) learning unit 315 may set arbitrary weights and biases for the first AI multiple linear regression model based on a data set of blood glucose levels and feature vectors of initial partial signals segmented from an input electrocardiogram (ECG) 10 signal for supervised training. The AI ​​learning unit 315 may input feature vectors of subsequently segmented partial signals for supervised training to the first AI multiple linear regression model to which arbitrary weights and biases have been set, and obtain a result value. The AI ​​learning unit 315 may calculate a loss function between the feature vectors of subsequently segmented partial signals, the blood glucose levels constituting the data set, and the result value obtained from the multiple linear regression model. The AI ​​learning unit 315 may then train the first AI multiple linear regression model by updating the weights and biases to minimize an error due to the loss function.

[0068] The artificial intelligence learning unit 315 may set arbitrary weights and biases for a first artificial intelligence (AI) classification model based on feature vectors of initial partial signals segmented from an electrocardiogram (ECG) 10 signal input for supervised learning and a dataset of hyperglycemia or hypoglycemia classification results. The artificial intelligence learning unit 315 may input feature vectors of subsequently segmented partial signals for supervised learning to the first artificial intelligence (AI) classification model to which arbitrary weights and biases have been set, and obtain a result value. The artificial intelligence learning unit 315 may calculate a loss function between the feature vectors of subsequently segmented partial signals, the classification results for whether the signal is hyperglycemia or hypoglycemia constituting the dataset, and the result value obtained from the classification model. The artificial intelligence learning unit 315 may then train the first artificial intelligence (AI) classification model by updating the weights and biases to minimize an error due to the loss function.

[0069] The artificial intelligence learning unit 315 may set arbitrary weights and biases for the second AI multiple linear regression model based on a dataset of glycosylated hemoglobin (HbA1c) values ​​and feature vectors of initial partial signals segmented from an electrocardiogram (ECG) 10 signal input for supervised learning. The artificial intelligence learning unit 315 may input the feature vectors of subsequently segmented partial signals for supervised learning to the second AI multiple linear regression model to which arbitrary weights and biases have been set, and obtain a result value. The artificial intelligence learning unit 315 may calculate a loss function between the feature vectors of the subsequently segmented partial signals, the glycosylated hemoglobin (HbA1c) values ​​constituting the dataset, and the result value obtained from the multiple linear regression model. The artificial intelligence learning unit 315 may then train the second AI multiple linear regression model by updating the weights and biases to minimize an error due to the loss function.

[0070] The artificial intelligence learning unit 315 may set arbitrary weights and biases based on the feature vectors of initial partial signals segmented from the electrocardiogram (ECG) 10 signal input for supervised learning and the dataset of classification results for normality or abnormality for the second artificial intelligence (AI) classification model. The artificial intelligence learning unit 315 may input the feature vectors of subsequently segmented partial signals for supervised learning to the second artificial intelligence (AI) classification model to which arbitrary weights and biases are set, and obtain result values. The artificial intelligence learning unit 315 may calculate a loss function between the feature vectors of subsequently segmented partial signals, the classification results for normality or abnormality constituting the dataset, and the result value obtained from the classification model. The artificial intelligence learning unit 315 may train the second artificial intelligence (AI) classification model by updating the weights and biases to minimize the error due to the loss function.

[0071] In this case, the loss function used in training the first artificial intelligence (AI) or the second artificial intelligence (AI) may be, but is not limited to, the mean squared error (MSE), and may also be substituted with the root mean squared error (RMSE), cross entropy error (CEE), binary cross entropy error (BCEE), categorical cross entropy error (CCEE), or focal loss.

[0072] Furthermore, the AI ​​learning unit 315 may update the weights and biases by gradient descent, but is not limited thereto.

[0073] Referring to FIG. 3, the next configuration will be described. The electrocardiogram canceller 320 can cancel the signal of the electrocardiogram (ECG) 10 measured by the electrocardiograph 100.

[0074] Specifically, the ECG release unit 320 can acquire an ECG 10 signal measured on the user. That is, the ECG release unit 320 can directly receive the ECG 10 signal from the ECG monitor 100 via the communication unit 305 or can directly receive the ECG 10 signal via the input / output unit 310.

[0075] As shown in FIG. 5, the electrocardiogram extraction unit 320 can extract one or more feature information F1, F2, ..., Fn by decomposing the acquired electrocardiogram (ECG) 10 signal based on one or more of amplitude, frequency, and time.

[0076] For example, the ECG cancellation unit 320 may extract feature information F1, F2, ..., Fn by decomposing the ECG 10 signal using one of a wavelet transform, an ensemble empirical mode decomposition (EEMD), a triadic motif field (TMF), and a triadic motif difference field (TMDF), but the manner in which the ECG cancellation unit 320 cancels the ECG 10 signal is not limited thereto.

[0077] Next, the electrocardiogram release unit 320 can divide the extracted feature information F1, F2, ..., Fn into multiple segmentation units based on the chronological order in which the electrocardiogram (ECG) signal was measured by the user.

[0078] 6, the ECG release unit 320 can divide each piece of feature information F1, F2, ..., Fn into a plurality of separate partial units S1, S2, S3, ... by discretely dividing the pieces of feature information F1, F2, ..., Fn into a predetermined size without overlapping areas. In this case, the size for discretely dividing the pieces of feature information F1, F2, ..., Fn may be a predetermined value preset by the input / output unit 310, but is not limited thereto and may be a randomized value.

[0079] 7, the ECG release unit 320 may divide each piece of feature information F1, F2, ..., Fn into a plurality of partial units S1, S2, S3, ..., each having a size corresponding to the window, by cutting the piece of feature information F1, F2, ..., Fn while sliding the window along the time axis. In this case, the size of the window for cutting each piece of feature information F1, F2, ..., Fn may be a constant value preset by the input / output unit 310.

[0080] Meanwhile, the signal of the electrocardiogram (ECG) 10 may contain noise generated due to the user's behavior during the measurement process, etc. Therefore, the ECG canceller 320 can remove noise contained in the divided subunits S1, S2, S3, ...

[0081] Specifically, the ECG removal unit 320 may identify displacements of keypoints included in each of the divided subunits S1, S2, S3, .... The ECG removal unit 320 may generate a normal distribution of displacements of the identified keypoints. The ECG removal unit 320 may then remove noise by selectively removing only partial signals having keypoints included in a predetermined noise range from the generated normal distribution. In this case, the method of identifying keypoints from the divided subunits S1, S2, S3, ... may be, but is not limited to, based on a predetermined keypoint extraction criterion.

[0082] Referring to Figure 3, the next configuration will be described. The blood glucose analysis unit 325 uses a first artificial intelligence (AI) previously learned by the artificial intelligence learning unit 315 to analyze the signal of the electrocardiogram (ECG) 10 to estimate the user's blood glucose value, and can also use the artificial intelligence (AI) to analyze the signal of the electrocardiogram (ECG) 10 to determine whether the user has hyperglycemia or hypoglycemia.

[0083] In addition, the blood glucose analysis unit 325 can use a second artificial intelligence (AI) previously trained by the artificial intelligence learning unit 315 to analyze the electrocardiogram (ECG) 10 signal to additionally estimate the user's glycated hemoglobin (HbA1c) value, and can use the artificial intelligence (AI) to analyze the electrocardiogram (ECG) 10 signal to additionally determine whether the glycated hemoglobin (HbA1c) is normal or abnormal.

[0084] Preferentially, the blood glucose analysis unit 325 can input the multiple partial units S1, S2, S3, ... divided by the electrocardiogram release unit 320 to the first artificial intelligence (AI) and the second artificial intelligence (AI), respectively, and obtain multiple numerical values ​​V1, V2, V3, ..., Vn and probability values ​​P1, P2, P3, ..., Pn from the first artificial intelligence (AI) and the second artificial intelligence (AI).

[0085] Specifically, the blood glucose analyzer 325 can identify feature vectors for the plurality of subunits S1, S2, S3, . . . divided by the electrocardiogram release unit 320.

[0086] 8, the blood glucose analysis unit 325 can input the identified feature vector to a multiple linear regression model and a classification model of a first artificial intelligence (AI), and can also input the identified feature vector to a multiple linear regression model and a classification model of a second artificial intelligence (AI).

[0087] The blood glucose analysis unit 325 can obtain multiple values ​​V1, V2, V3, ..., Vn for estimating blood glucose levels from the multiple linear regression model of the first artificial intelligence (AI). The blood glucose analysis unit 325 can obtain multiple probability values ​​P1, P2, P3, ..., Pn for determining whether blood glucose is hyperglycemia or hypoglycemia from the classification model of the first artificial intelligence (AI). The blood glucose analysis unit 325 can obtain multiple values ​​V1, V2, V3, ..., Vn for estimating glycated hemoglobin (HbA1c) levels from the multiple linear regression model of the second artificial intelligence (AI). The blood glucose analysis unit 325 can obtain multiple probability values ​​P1, P2, P3, ..., Pn for determining whether glycated hemoglobin (HbA1c) is normal or abnormal from the classification model of the second artificial intelligence (AI).

[0088] The blood glucose analyzer 325 can then estimate the user's blood glucose level based on the value and probability value obtained from the first artificial intelligence (AI) and determine whether the user has hyperglycemia or hypoglycemia. The blood glucose analyzer 325 can then estimate the user's glycated hemoglobin (HbA1c) level based on the value and probability value obtained from the second artificial intelligence (AI) and determine whether the glycated hemoglobin (HbA1c) is normal or abnormal.

[0089] As shown in FIG. 9, the blood glucose analyzer 325 can remove outliers contained in the values ​​V1, V2, V3, ..., Vn obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a pre-set validated range.

[0090] The blood glucose analysis unit 325 can estimate the user's blood glucose value using soft voting results based on the average value of values ​​V1, V2, ..., Vm from which outliers have been removed among values ​​V1, V2, ..., Vn obtained from the first artificial intelligence (AI).

[0091] The blood glucose analysis unit 325 can estimate the user's glycated hemoglobin (HbA1c) value using the softboarding result based on the average value of the values ​​V1, V2, ..., Vm from which outliers have been removed among the values ​​V1, V2, V3, ..., Vn obtained from the second artificial intelligence (AI).

[0092] As shown in FIG. 10, the blood glucose analysis unit 325 can remove outliers included in the probability values ​​P1, P2, P3, ..., Pn obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a preset valid range.

[0093] The blood glucose analysis unit 325 can determine whether the user has hypoglycemia or hyperglycemia using the hard voting result based on a majority vote of the probability values ​​P1, P2, P3, ..., Pm from which outliers have been removed among the probability values ​​P1, P2, P3, ..., Pn obtained from the first artificial intelligence (AI).

[0094] The blood glucose analysis unit 325 can determine whether glycated hemoglobin (HbA1c) is normal or abnormal using the hard voting results based on a majority vote of the probability values ​​P1, P2, ..., Pm from which outliers have been removed among the probability values ​​P1, P2, P3, ..., Pn obtained from the second artificial intelligence (AI).

[0095] 3, the guidance determination unit 330 can determine whether the user needs guidance about blood glucose or diabetes based on the blood glucose value estimated through the blood glucose analysis unit 325 and the determination result on whether the blood glucose is high or low. The guidance determination unit 330 can also determine whether the user needs guidance about blood glucose or diabetes by additionally considering the blood glucose value estimated through the blood glucose analysis unit 325 and the determination result on whether the blood glucose value is high or low.

[0096] Specifically, the guidance determination unit 330 can primarily determine whether the user has hyperglycemia or hypoglycemia based on the blood glucose value estimated by the multiple linear regression model of the first artificial intelligence (AI). The guidance determination unit 330 can secondarily determine whether the primary determination result and the classification result by the classification model of the first artificial intelligence (AI) are identical to each other. Then, the guidance determination unit 330 can determine whether the user needs guidance about blood glucose based on the secondary determination result.

[0097] For example, if the blood glucose level estimated by the first AI's multiple linear regression model is 65 mg / dL or less and classified as hypoglycemia by the first AI's classification model, the guidance determination unit 330 may determine that the user needs guidance regarding blood glucose. Conversely, if the blood glucose level estimated by the first AI's multiple linear regression model is 95 mg / dL or more and classified as hyperglycemia by the first AI's classification model, the guidance determination unit 330 may determine that the user needs guidance regarding blood glucose.

[0098] The guidance determination unit 330 can primarily determine whether the glycosylated hemoglobin (HbA1c) is normal or abnormal based on the glycosylated hemoglobin (HbA1c) value estimated by the multiple linear regression model of the second artificial intelligence (AI). The guidance determination unit 330 can secondarily determine whether the primary determination result and the classification result by the classification model of the second artificial intelligence (AI) are identical to each other. Then, the guidance determination unit 330 can determine whether the user needs guidance on diabetes management based on the secondary determination result.

[0099] For example, if the glycated hemoglobin (HbA1c) value estimated by the multiple linear regression model of the second artificial intelligence (AI) is 5.7% or higher and is classified as abnormal by the classification model of the second artificial intelligence (AI), the guidance determination unit 330 can determine that the user needs guidance on diabetes management.

[0100] On the other hand, if the primary judgment based on the numerical values ​​of the multiple linear regression model and the results classified according to the probability values ​​of the classification model are different from each other, the artificial intelligence learning unit 315 may also readjust the weights and biases set in the multiple linear regression models or classification models of the first artificial intelligence (AI) and the second artificial intelligence (AI), respectively, so that the matching rate between the primary judgment based on the numerical values ​​of the multiple linear regression model and the results classified according to the probability values ​​of the classification model is within a predetermined validated range.

[0101] Next, if the guidance determination unit 330 determines that the user needs guidance regarding blood glucose or diabetes, it can set guidance information regarding blood glucose or diabetes based on the user's blood glucose value, glycosylated hemoglobin (HbA1c) value, the determination result as to whether the user is hyperglycemic or hypoglycemic, and the determination result as to whether the glycosylated hemoglobin (HbA1c) is normal or abnormal.

[0102] In this case, the guidance 20 information regarding blood glucose or diabetes may directly include the blood glucose value, the glycated hemoglobin (HbA1c) value, the judgment result as to whether the blood glucose value is high or low, or the judgment result as to whether the glycated hemoglobin (HbA1c) is normal or abnormal, or may include indirect precautions, recommendations, or warnings based on the blood glucose value, the glycated hemoglobin (HbA1c) value, the judgment result as to whether the blood glucose value is high or low, or the judgment result as to whether the glycated hemoglobin (HbA1c) is normal or abnormal.

[0103] In addition, the blood sugar or diabetes guidance information 20 may include one or more of guidance regarding measures that the user must take immediately in relation to blood sugar or diabetes and guidance to assist the user in managing their diabetes.

[0104] For example, the guidance determination unit 330 may set guidance on measures that the user should take immediately based on the user's blood glucose level and whether the blood glucose level is high or low. Also, the guidance determination unit 330 may set guidance to support the user's diabetes management based on the user's glycosylated hemoglobin (HbA1c) level and whether the level is normal or abnormal.

[0105] The guidance determination unit 330 may identify a pre-set human weight corresponding to the gender and age of the user. The guidance determination unit 330 may determine a distance weight corresponding to the distance value from the location of the user device (UE) 200 to the medical institution located at the shortest distance. The guidance determination unit 330 may determine a tone of sentence for composing the guidance 20 for blood glucose or diabetes based on the identified human weight and the determined distance weight. Then, the guidance determination unit 330 may compose the guidance 20 information for blood glucose or diabetes according to the determined tone of sentence.

[0106] The guidance determination unit 330 may transmit the set blood glucose or diabetes guidance information to a user equipment (UE) 200 that is set in advance in correspondence with the user.

[0107] Hereinafter, the hardware for realizing the logical components of the blood glucose management server 300 having the above-mentioned features will be described in more detail.

[0108] FIG. 11 is a hardware configuration diagram of a blood glucose management server according to an embodiment of the present invention.

[0109] As shown in FIG. 11, a blood glucose management server 300 according to an embodiment of the present invention may include a processor 350, a memory 355, a transceiver 360, an input / output device 365, a data bus 370, and a storage 375.

[0110] Specifically, the processor 350 can implement the operations and functions of the blood glucose management server 300 based on commands from software 380a that implements a method for measuring real-time blood glucose values ​​and management levels and resides in the memory 355.

[0111] The memory 355 may be loaded with software 380b stored in the storage 375, which implements a method for measuring the real-time blood glucose level and the degree of control.

[0112] The transceiver 360 may transmit data to and receive data from one or more of the electrocardiograph 100 and the user equipment (UE) 200 .

[0113] The input / output device 365 can receive input of signals required for the operation of the blood glucose management server 300 or output calculation results to the outside, according to instructions from the processor 350.

[0114] The data bus 370 is connected to the processor 350, the memory 355, the transceiver 360, the input / output device 365, and the storage 375, respectively, and can serve as a communication path for transmitting signals between the respective components.

[0115] The storage 375 may store an application programming interface (API), library files, resource files, etc., required for executing software 380a implementing a method for measuring real-time blood glucose values ​​and management levels according to various embodiments of the present invention. The storage 375 may store software 380b implementing a method for measuring real-time blood glucose values ​​and management levels according to various embodiments of the present invention. The storage 375 may also include a database 385 for storing AI learning data, various setting values, etc.

[0116] According to one embodiment of the present invention, the software 380a, 380b for implementing the method for measuring the real-time blood glucose value and management level, which is resident in the memory 355 or stored in the storage 375, may be a computer program recorded on a recording medium to cause the processor 350 to execute the steps of acquiring an electrocardiogram (ECG) 10 signal measured for a user via the transceiver 360 or the input / output device 365, the processor 350 analyzing the ECG signal using a first artificial intelligence (AI) that has been previously trained, estimating the user's blood glucose value, and analyzing the ECG 10 signal using the AI ​​to determine whether the user has hyperglycemia or hypoglycemia, and the processor 350 determining whether the user needs blood glucose or diabetes guidance 20 based on the estimated blood glucose value and the determination result of hyperglycemia or hypoglycemia.

[0117] More specifically, the processor 350 may include, but is not limited to, one or more of a central processing unit (CPU), an application-specific integrated circuit (ASIC), a chipset, and a logic circuit.

[0118] The memory 355 may include, but is not limited to, one or more of a read-only memory (ROM), a random access memory (RAM), a flash memory, and a memory card.

[0119] The input / output device 365 may include, but is not limited to, one or more of input devices such as a button, a switch, a keyboard, a mouse, a joystick, and a touch screen, and output devices such as a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), an active matrix organic light emitting diode (AMOLED), a printer, and a plotter.

[0120] When the embodiments described herein are implemented using software, the methods described above may be implemented as modules (processes, functions, etc.) that perform the respective functions described above. Each module may reside in memory 355 and be executed by processor 350. Memory 355 may be internal or external to processor 350 and may be coupled to processor 350 via various known means.

[0121] 9 may be implemented by various means (e.g., hardware, firmware, software, or a combination thereof). When implemented by hardware, an embodiment of the present invention may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, etc.

[0122] Furthermore, when embodied in firmware or software, an embodiment of the present invention may be embodied in the form of modules, procedures, functions, etc. that perform the above-described functions or operations and recorded on a recording medium that can be read by various computer means. Here, the recording medium may include program instructions, data files, data structures, etc., alone or in combination.

[0123] The program instructions recorded on the recording medium may be specially designed and constructed for the present invention, or may be of the type well known and available to those of ordinary skill in the computer software art. For example, recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as compact disk read-only memories (CD-ROMs) and digital video disks (DVDs), magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions, such as read-only memories (ROMs), random access memories (RAMs), flash memories, etc.

[0124] Examples of program instructions include not only machine code, such as produced by a compiler, but also high-level language code that is executable by a computer via an interpreter, etc. Such hardware devices may be configured to act as one or more software modules to perform the operations of the present invention, and vice versa.

[0125] The operation of the blood glucose management server 300 as described above will now be described in detail.

[0126] FIG. 12 is a flowchart illustrating a method for measuring a real-time blood glucose value and a blood glucose control level according to an embodiment of the present invention.

[0127] As shown in FIG. 12, a blood glucose management server 300 according to an embodiment of the present invention can acquire an electrocardiogram (ECG) 10 signal measured from a user (S100).

[0128] Specifically, the blood glucose management server 300 can receive an electrocardiogram (ECG) 10 signal directly from the electrocardiograph 100, or can receive a signal directly from the user or other person.

[0129] Next, the blood glucose management server 300 can extract one or more pieces of feature information F1, F2, ..., Fn by disassembling the electrocardiogram (ECG) 10 signal based on one or more of amplitude, frequency, and time (S200).

[0130] For example, the blood glucose management server 300 can extract feature information F1, F2, ..., Fn by decomposing the electrocardiogram (ECG) 10 signal using one of wavelet transform, ensemble empirical mode decomposition (EEMD), tripartite motif field (TMF), and tripartite motif difference field (TMDF), but is not limited to these.

[0131] Next, the blood glucose management server 300 can divide the extracted feature information F1, F2, ..., Fn into multiple subunits according to the chronological order in which the electrocardiogram (ECG) signal was measured by the user (S300).

[0132] According to one embodiment, the blood glucose management server 300 can divide each piece of feature information F1, F2, ..., Fn into a plurality of discrete subunits S1, S2, S3, ..., which are separated from each other, by cutting each piece of feature information F1, F2, ..., Fn into discrete pieces of a certain size without overlapping areas. According to another embodiment, the blood glucose management server 300 can divide each piece of feature information F1, F2, ..., Fn into a plurality of discrete pieces S1, S2, S3, ..., which have a size corresponding to the window, by cutting each piece of feature information F1, F2, ..., Fn while sliding the window along the time axis.

[0133] Next, the blood glucose management server 300 can analyze the signal of the electrocardiogram (ECG) 10 using a first artificial intelligence (AI) that has been trained in advance to estimate the user's blood glucose value and determine whether the user has hyperglycemia or hypoglycemia. In addition, the blood glucose management server 300 can analyze the signal of the electrocardiogram (ECG) 10 using a second artificial intelligence (AI) that has been trained in advance to additionally estimate the user's glycosylated hemoglobin (HbA1c) value and additionally determine whether the glycosylated hemoglobin (HbA1c) is normal or abnormal (S400).

[0134] Specifically, the blood glucose management server 300 inputs multiple partial units S1, S2, S3, ... to a first artificial intelligence (AI) and a second artificial intelligence (AI), respectively, and can obtain multiple numerical values ​​V1, V2, V3, ..., Vn and probability values ​​P1, P2, P3, ..., Pn from the first artificial intelligence (AI) and the second artificial intelligence (AI).

[0135] Next, the blood glucose management server 300 estimates the user's blood glucose value based on the value and probability value obtained from the first artificial intelligence (AI) and can determine whether the user has hyperglycemia or hypoglycemia.The blood glucose management server 300 then estimates the user's glycosylated hemoglobin (HbA1c) value based on the value and probability value obtained from the second artificial intelligence (AI) and can determine whether the glycosylated hemoglobin (HbA1c) is normal or abnormal (S500).

[0136] Specifically, the blood glucose management server 300 can remove outliers contained in the values ​​V1, V2, V3, ..., Vn obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a preset valid range.

[0137] The blood glucose management server 300 can estimate the user's blood glucose value using a softboarding result based on the average value of the values ​​V1, V2, ..., Vm from which outliers have been removed among the values ​​V1, V2, V3, ..., Vn obtained from the first artificial intelligence (AI), and can estimate the user's glycated hemoglobin (HbA1c) value using a softboarding result based on the average value of the values ​​V1, V2, ..., Vm from which outliers have been removed among the values ​​V1, V2, V3, ..., Vn obtained from the second artificial intelligence (AI).

[0138] The blood glucose management server 300 can remove outliers included in the probability values ​​P1, P2, P3, ..., Pn obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a preset valid range.

[0139] The blood glucose management server 300 can determine whether the user has hypoglycemia or hyperglycemia using the hard boarding result based on a majority vote of the probability values ​​P1, P2, ..., Pm obtained from the first artificial intelligence (AI) with outliers removed from among the probability values ​​P1, P2, ..., Pn, and can determine whether the user has hypoglycemia or hyperglycemia using the hard boarding result based on a majority vote of the probability values ​​P1, P2, ..., Pm obtained from the second artificial intelligence (AI) with outliers removed from among the probability values ​​P1, P2, ..., Pm.

[0140] Next, the blood glucose management server 300 can set guidance information about blood glucose or diabetes based on the user's blood glucose value, glycosylated hemoglobin (HbA1c) value, the judgment result on whether the user has hyperglycemia or hypoglycemia, and the judgment result on whether the glycosylated hemoglobin (HbA1c) is normal or abnormal (S600).

[0141] Specifically, the blood glucose management server 300 determines whether the user needs guidance about blood glucose based on the blood glucose value and the determination result of whether the blood glucose is high or low, and can also determine whether the user needs guidance about diabetes based on the glycated hemoglobin (HbA1c) value and the determination result of whether the glycated hemoglobin (HbA1c) is normal or abnormal.

[0142] The blood glucose or diabetes guide 20 information may directly include the blood glucose value, glycosylated hemoglobin (HbA1c) value, the determination result of whether the blood glucose or hypoglycemia is high or low, or the determination result of whether the glycosylated hemoglobin (HbA1c) is normal or abnormal, or may include indirect cautions, recommendations, or warnings based on the blood glucose value, glycosylated hemoglobin (HbA1c) value, the determination result of whether the blood glucose or hypoglycemia is high or low, or the determination result of whether the glycosylated hemoglobin (HbA1c) is normal or abnormal. The blood glucose or diabetes guide 20 information may include one or more of guidance on measures that the user should take immediately regarding blood glucose or diabetes and guidance to support the user's diabetes management.

[0143] Finally, the blood glucose management server 300 can transmit the set blood glucose or diabetes guide information 20 to a user equipment (UE) 200 set in advance corresponding to the user (S700).

[0144] As described above, the present specification and drawings have disclosed preferred embodiments of the present invention. However, it will be obvious to those skilled in the art to which the present invention pertains that other modifications based on the technical concept of the present invention are possible in addition to the disclosed embodiments. Furthermore, although specific terms are used in the present specification and drawings, these are used in general terms merely to facilitate the description of the present invention and to facilitate understanding of the invention, and are not intended to limit the scope of the present invention. Therefore, the above detailed description should not be construed as limiting in all respects, but should be considered as illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included within the scope of the present invention.

Claims

1. acquiring an electrocardiogram (ECG) signal measured from a user; analyzing the ECG signal using a first artificial intelligence (AI) that has been trained in advance to estimate the blood sugar value of the user, and analyzing the ECG signal using the first artificial intelligence (AI) to determine whether the user has hyperglycemia or hypoglycemia; and determining whether the user needs guidance on blood glucose or diabetes based on the estimated blood glucose value and the determination result on whether the user has hyperglycemia or hypoglycemia.

2. 2. The method of claim 1, wherein the determining whether the user has hyperglycemia or hypoglycemia comprises: analyzing the ECG signal using a pre-trained second artificial intelligence (AI) to estimate the user's glycated hemoglobin (HbA1c) value; and analyzing the ECG signal using the second artificial intelligence (AI) to determine whether the glycated hemoglobin (HbA1c) is normal or abnormal.

3. The step of determining whether the blood sugar level is hyperglycemia or hypoglycemia includes: extracting one or more feature information by disassembling the acquired electrocardiogram (ECG) signal based on one or more of amplitude, frequency, and time; Dividing the extracted feature information into a plurality of subunits according to the time series of the ECG signal measurements; inputting the divided subunits into the first artificial intelligence (AI) and the second artificial intelligence (AI), respectively, and obtaining a plurality of numerical values ​​and probability values ​​from the first artificial intelligence (AI) and the second artificial intelligence; estimating the blood glucose value based on the value and probability value obtained from the first artificial intelligence (AI) and determining whether the blood glucose is hyperglycemic or hypoglycemic, and estimating the glycated hemoglobin (HbA1c) value based on the value and probability value obtained from the second artificial intelligence (AI) and determining whether the glycated hemoglobin (HbA1c) is normal or abnormal.

4. 4. The method of claim 3, wherein the extracting the feature information comprises extracting the feature information by decomposing the ECG signal using one of a wavelet transform, an ensemble empirical mode decomposition (EEMD), a triadic motif field (TMF), and a triadic motif difference field (TMDF).

5. 4. The method of claim 3, wherein the dividing into a plurality of subunits comprises moving a window of a predetermined size along a time axis, and dividing the feature information acquired from the electrocardiogram (ECG) signal into a plurality of subunits having a size corresponding to the window.

6. 4. The method of claim 3, wherein the step of obtaining the plurality of numerical values ​​and probability values ​​includes inputting feature vectors for the divided subunits into a multiple linear regression model and a classification model of the first artificial intelligence (AI) and the second artificial intelligence (AI), respectively, to obtain the plurality of numerical values ​​and probability values.

7. 4. The method of claim 3, wherein the determining whether the blood glucose is normal or abnormal includes removing outliers included in the values ​​obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a predetermined validated range, estimating the blood glucose value using a soft voting result based on an average value of the values ​​obtained from the first artificial intelligence (AI) from which the outliers have been removed, and estimating the glycosylated hemoglobin (HbA1c) value using a soft voting result based on an average value of the values ​​obtained from the second artificial intelligence (AI) from which the outliers have been removed.

8. 4. The method of claim 3, wherein the determining whether the blood glucose is normal or abnormal includes removing outliers included in the probability values ​​obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a preset valid range, determining whether the blood glucose is hyperglycemic or hypoglycemic using a result of hard voting based on a majority vote of the probability values ​​obtained from the first artificial intelligence (AI) from which the outliers have been removed, and determining whether the glycated hemoglobin (HbA1c) is normal or abnormal using a result of hard voting based on a majority vote of the probability values ​​obtained from the second artificial intelligence (AI) from which the outliers have been removed.

9. 4. The method of claim 3, further comprising the step of transmitting, when it is determined that the guidance is necessary after the step of determining whether the guidance is necessary, guidance information set based on the blood glucose value, the glycosylated hemoglobin (HbA1c) value, the determination result on whether the blood glucose value is hyperglycemic or hypoglycemic, and the determination result on whether the glycosylated hemoglobin (HbA1c) is normal or abnormal, to a user equipment (UE) preset corresponding to the user.

10. A memory; a transceiver; an input / output device; a processor for processing instructions resident in the memory; acquiring, by the processor, an electrocardiogram (ECG) signal measured from a user via the transceiver or input / output device; The processor analyzes the electrocardiogram (ECG) signal using a first artificial intelligence (AI) that has been pre-trained to estimate the blood glucose level of the user, and analyzes the electrocardiogram (ECG) signal using the first artificial intelligence (AI) to determine whether the user has hyperglycemia or hypoglycemia; A computer program recorded on a recording medium, causing the processor to execute a step of determining whether the user needs guidance on blood glucose or diabetes based on the estimated blood glucose value and the determination result on whether the user has hyperglycemia or hypoglycemia.

Images