Method for measuring real-time value and degree of management of blood glucose based on electrocardiogram, and computer program stored in storage medium for executing method

Abstract

The invention discloses a method for measuring the real-time value and management degree of blood glucose on the basis of electrocardiogram (ECG). The method may include the steps of: acquiring an electrocardiogram (ECG) signal measured with a user as a subject; a blood glucose estimation unit that estimates a blood glucose value of the user by analyzing the electrocardiogram (ECG) signal using a first artificial intelligence (AI) learned in advance, and determines whether the user is hyperglycemia or hypoglycemia by analyzing the electrocardiogram (ECG) signal using the artificial intelligence (AI); and determining whether the user needs to be reminded about blood glucose or glycosuria on the basis of the inferred blood glucose value and the determination result of whether the blood glucose value is hyperglycemia or hypoglycemia. Therefore, the user can immediately confirm the blood glucose value and the good management degree of the blood glucose only by simply measuring the electrocardiogram (ECG), and as a result, the hyperglycemia and the glycosuria can be found at an early stage or the complication caused by the hyperglycemia or the glycosuria can be prevented.

Description

Technical Field

[0001] The present invention discloses a smart health care, more specifically,

[0002] A method for measuring blood sugar based on electrocardiogram (ECG) is presented.

[0003] sugar) real-time value and management method and storage for executing the method

[0004] Computer program for a medium. Background Art

[0005] An electrocardiogram (ECG) records the electrical activity of the heart muscle in a graph.

[0006] The following is a brief description of the conduction system of the heart.

[0007] The sinoatrial node (SA Node) regularly generates electrical signals to induce heart contraction.

[0008] Atrioventricular Node (AV Node) in the sinoatrial node (SA Node)

[0009] The electrical signal arrives through the atrium and is then transmitted with a slight delay.

[0010] The electrical signal from the AV node passes through the bundle of His and the Purkinje fibers.

[0011] Purkinje fibers spread throughout the ventricle.

[0012] The following are the electrocardiogram (ECG) waves that can be observed along the conduction process of the heart.

[0013] The electrical signal generated by the sinoatrial node (SA Node) polarizes the atrium and causes the myocardium of the valve to

[0014] P can be observed in the process of atrial re-depolarization after contraction, which allows the valve myocardium to relax again.

[0015] The atrioventricular node (AV Node) is formed to prevent the ventricles from immediately reacting when the atria contract.

[0016] Therefore, the PQ wave can be observed in the process of delaying the electrical signal.

[0017] (AV Node) The delayed signal arrives (Q) and the ventricle polarizes (R) and then depolarizes

[0018] The QRS complex can be observed during the process of ventricular contraction.

[0019] During the rest period, when the blood in the chamber moves to all parts of the body and the electrical signals do not stimulate the heart

[0020] ST waves can be observed. Moreover, after the ventricles are repolarized to a weaker degree,

[0021] The T wave (T) is observed during the simultaneous relaxation of the ventricular and valvular myocardium.

[0022] In addition, U waves due to repolarization of the intraventricular septum are also observed in some cases.

[0023] As mentioned above, the order of appearance, shape, size, and interval of the multiple waveforms (P wave, PQ wave, QRS wave, ST wave, T wave, and U wave) observed by the electrocardiogram (ECG) can change into various forms depending on the health status. In other words, by analyzing the order of appearance, shape, size, and interval of the multiple waveforms included in the electrocardiogram (ECG), the health status can be inferred, and further, the various causes leading to the health status can be inferred.

[0024] On the other hand, artificial intelligence (AI) refers to the technology that uses computer programs to artificially realize part or all of human learning ability, reasoning ability, and perception ability. Regarding artificial intelligence (AI), machine learning refers to the learning that uses a model composed of multiple parameters to optimize the parameters with given data.

[0025] As mentioned above, machine learning is divided into supervised learning, unsupervised learning, and reinforcement learning according to the learning methodology. Moreover, machine learning is divided into regression analysis, artificial neural network (ANN), deep learning (DL), etc. according to the learning algorithm.

[0026] On the other hand, blood sugar refers to the glucose contained in the blood. Generally speaking, blood sugar is maintained at a certain value by the interaction of insulin, glucagon, epinephrine, glucocorticoid, adrenocorticotrophic hormone and thyroid hormone. Moreover, diabetes mellitus (DM) is a metabolic disease in which symptoms such as high blood sugar appear due to insufficient secretion of insulin or inability of the secreted insulin to function normally.

[0027] If high blood sugar persists for a long time or diabetes becomes severe, myocardial infarction due to acute blockage of coronary arteries or cerebral infarction (stroke) due to blockage or rupture of cerebral arteries may occur. In addition, complications such as decreased vision (amblyopia), blindness (caecitas), and decreased kidney function (renal function impairment) may also be induced.

[0028] According to various research results, if the value of glycated hemoglobin (HbA1c), which means hemoglobin bound to glucose, decreases by 1%, the risk of complications caused by high blood sugar or diabetes will decrease by about 20% to 30%. Therefore, it is necessary to develop various tools to thoroughly manage blood sugar before complications caused by diseases such as high blood pressure and diabetes occur. Summary of the invention

[0029] Technical issues

[0030] An object of the present invention is to provide a method for measuring the real-time value and management level of blood sugar based on an electrocardiogram (ECG).

[0031] Another object of the present invention is to provide a computer program stored in a storage medium for executing a method for measuring a real-time value of blood sugar and a degree of management based on an electrocardiogram (ECG).

[0032] The technical problems of the present invention are not limited to the technical problems mentioned above, and ordinary technicians in the technical field to which the present invention belongs can clearly understand other technical problems not mentioned above from the following records.

[0033] Technical Solution

[0034] In order to solve the above-mentioned technical problems, the present invention discloses a method for measuring the real-time value and management level of blood sugar based on an electrocardiogram (ECG). The method may include the following steps: obtaining an electrocardiogram (ECG) signal for measuring a user as an object; using a pre-learned first artificial intelligence (AI) to analyze the ECG signal to infer the blood sugar value of the user, using the artificial intelligence (AI) to analyze the ECG signal to determine whether the user has high blood sugar or low blood sugar; and determining whether the user needs a reminder about blood sugar or diabetes based on the inferred blood sugar value and the result of the determination of whether it is high blood sugar or low blood sugar.

[0035] The method may further include the following step after the step of determining whether a reminder is needed: if it is determined that the reminder is needed, transmitting reminder information set based on the blood sugar value, the glycosylated hemoglobin (HbA1c) value, whether it is high blood sugar or low blood sugar, and whether the glycosylated hemoglobin (HbA1c) is normal to a pre-set user equipment (UE) corresponding to the user.

[0036] Moreover, in the step of determining whether it is hyperglycemia or hypoglycemia, the pre-learned second artificial intelligence (AI) is used to analyze the electrocardiogram (ECG) signal to infer the user's glycated hemoglobin (HbA1c) value, and the second artificial intelligence (AI) is used to analyze the electrocardiogram (ECG) signal to further determine whether the glycated hemoglobin (HbA1c) is normal or not.

[0037] More specifically, the step of determining whether it is hyperglycemia or hypoglycemia may include the following steps: decomposing the acquired electrocardiogram (ECG) signal based on one or more of amplitude, frequency and time to extract one or more feature information; dividing the extracted feature information into a plurality of local units according to the order of the timing at which the electrocardiogram (ECG) signal is measured; inputting the divided plurality of local units into the first artificial intelligence (AI) and the second artificial intelligence (AI), respectively, and obtaining a plurality of numerical values ​​and a plurality of probability values ​​from the first artificial intelligence (AI) and the second artificial intelligence; and inferring the blood sugar value based on the plurality of numerical values ​​and the plurality of probability values ​​obtained from the first artificial intelligence (AI) and determining whether it is hyperglycemia or hypoglycemia, and inferring the glycosylated hemoglobin (HbA1c) value based on the plurality of numerical values ​​and the plurality of probability values ​​obtained from the second artificial intelligence (AI) and determining whether the glycosylated hemoglobin (HbA1c) is normal or not.

[0038] In this case, in the step of extracting feature information, one of wavelet transform, ensemble empirical mode decomposition (EEMD), ternary motif field (Triadic Motif Field, TMF) and ternary motif difference field (Triadic Motif Difference Field, TMDF) can be used to decompose the electrocardiogram (ECG) signal and extract the feature information.

[0039] According to one embodiment of the present invention, in the step of dividing into a plurality of local units, a grid (window) of a preset size can be moved along the time axis and feature information obtained from the electrocardiogram (ECG) signal can be divided into a plurality of local units having a size corresponding to the grid.

[0040] On the other hand, in the step of obtaining multiple numerical values ​​and multiple probability values, the feature vectors of the multiple segmented local units can be respectively input into the multiple linear regression model and classification model of the first artificial intelligence (AI) and the second artificial intelligence (AI) to obtain the multiple numerical values ​​and multiple probability values.

[0041] In the step of judging whether it is normal or not, outliers included in the multiple values ​​taken from the first artificial intelligence (AI) and the second artificial intelligence (AI) are eliminated based on a preset valid range, and the blood sugar value is judged using a soft voting result based on the average value of the multiple values ​​taken from the first artificial intelligence (AI) from which the outliers are eliminated, and the glycated hemoglobin (HbA1c) value is inferred using a soft voting result based on the average value of the multiple values ​​taken from the second artificial intelligence (AI) from which the outliers are eliminated.

[0042] Moreover, in the step of judging whether it is normal or not, the abnormal values ​​contained in the multiple probability values ​​taken from the first artificial intelligence (AI) and the second artificial intelligence (AI) are eliminated based on the effective range, and whether it is hyperglycemia or hypoglycemia is judged by using the hard voting result based on the majority decision of the multiple probability values ​​taken from the first artificial intelligence (AI) from which the abnormal values ​​are eliminated, and whether the glycated hemoglobin (HbA1c) is normal or not is judged by using the hard voting result based on the majority decision of the multiple probability values ​​taken from the second artificial intelligence (AI) from which the abnormal values ​​are eliminated.

[0043] In order to achieve the above-mentioned technical problem, the present invention provides a computer program stored in a storage medium for executing a method for measuring the real-time value of blood sugar and the degree of management based on an electrocardiogram (ECG). The computer program can be combined with the following computing device, which includes a memory, a transceiver, an input / output device, and a processor for processing commands resident in the memory. Moreover, the computer program can be a computer program stored in a storage medium for executing the following steps: the processor obtains an electrocardiogram (ECG) signal measured with a user as an object through the transceiver or the input / output device; the processor analyzes the electrocardiogram (ECG) signal using a pre-learned first artificial intelligence (AI) to infer the blood sugar value of the user, and uses the artificial intelligence (AI) to analyze the electrocardiogram (ECG) signal to determine whether the user has high blood sugar or low blood sugar; and the processor determines whether the user needs a reminder about blood sugar or diabetes based on the inferred blood sugar value and the result of the judgment of whether it is high blood sugar or low blood sugar.

[0044] Details of other embodiments are included in the following detailed description and drawings.

[0045] Effects of the Invention

[0046] According to various embodiments of the present invention, a user can immediately check the user's blood sugar level and the degree of blood sugar management simply by measuring an electrocardiogram (ECG). As a result, hyperglycemia and diabetes can be detected early or complications caused by hyperglycemia or diabetes can be prevented.

[0047] The effects of the present invention are not limited to the effects mentioned above, and a person skilled in the art to which the present invention belongs can clearly understand other effects not mentioned above from the description of the scope of protection claimed in the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is an illustrative diagram for explaining a blood sugar management device according to an embodiment of the present invention.

[0049] Figure 2 This is an illustrative diagram for explaining a blood sugar management system according to an embodiment of the present invention.

[0050] Figure 3 It is a logical configuration diagram of a blood sugar management server according to an embodiment of the present invention.

[0051] Figure 4 This is an exemplary diagram for explaining the learning process of artificial intelligence (AI) according to an embodiment of the present invention.

[0052] Figure 5 FIG. 1 is an exemplary diagram for explaining a method of removing an electrocardiogram (ECG) signal according to an embodiment of the present invention.

[0053] Figure 6 and Figure 7 is an exemplary diagram for explaining a process of segmenting into multiple local units according to some embodiments of the present invention.

[0054] Figure 8 The present invention is a diagram for explaining the process of using artificial intelligence (AI) analysis according to some embodiments of the present invention.

[0055] Fig. 9 and Fig.10 is an exemplary diagram for explaining a process of interpreting an artificial intelligence (AI) analysis result according to an embodiment of the present invention.

[0056] Fig.11 FIG. 4 is a hardware configuration diagram of a blood sugar management server according to an embodiment of the present invention.

[0057] Fig.12 This is a flowchart for explaining a method for measuring a real-time blood sugar value and a management level according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The technical terms used in this specification are only for describing specific embodiments and are not intended to limit the present invention. Furthermore, unless a different definition is specifically given in this specification, the technical terms used in this specification should be interpreted as the meanings commonly understood by ordinary technicians in the technical field to which the present invention belongs, and should not be interpreted as overly general or overly narrowed. Furthermore, when a technical term used in this specification is an erroneous term that cannot correctly express the spirit of the present invention, it should be replaced with a technical term that can be correctly understood by ordinary technicians in the technical field to which the present invention belongs. Furthermore, the general terms used in the present invention should be interpreted according to the content defined in the dictionary or according to the context of the article, and should not be interpreted as overly narrowed.

[0059] Furthermore, unless it can be clearly distinguished in the context of the sentence, the singular expressions used in this specification also include the plural. In this application, the terms such as "including" or "having" should not be interpreted as necessarily including all the multiple elements or steps recorded in the specification, and may not include some of the elements or steps, or may further include other elements or steps.

[0060] Furthermore, the terms used in this specification that include ordinal numbers such as "first" and "second" may be used to describe various elements, but the elements shall not be limited to the terms. The purpose of using the terms is only to distinguish one element from other elements. For example, the first element may be named the second element without departing from the scope of the claims of the present invention, and similarly, the second element may be named the first element.

[0061] When an element is recorded as being "connected" or "accessed" to another element, it can be understood as being directly connected to or accessed to the other element, but it can also be understood as other elements being present in between. Conversely, when an element is recorded as being "directly connected" or "directly accessed" to another element, it should be understood as other elements not being present in between.

[0062] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. The same or similar elements are given the same figure mark without being affected by the graphic symbols, and repeated descriptions thereof are omitted. Moreover, when describing the present invention below, if it is considered that the specific description of the relevant known technology may confuse the main purpose of the present invention, its detailed description will be omitted. Moreover, the purpose of the drawings is only to make the spirit of the present invention easy to understand, and the drawings cannot be interpreted as limiting the spirit of the present invention. The spirit of the present invention should be extended to all changes, equivalents and even substitutes in addition to the drawings.

[0063] As mentioned above, if high blood sugar levels persist for a long time or diabetes becomes severe, myocardial infarction due to acute blockage of coronary arteries or stroke due to blockage or rupture of cerebral arteries may occur, in addition to complications such as decreased vision, blindness, and decreased kidney function. Therefore, various means are needed to support thorough management of blood sugar levels before complications caused by diseases such as hypertension and diabetes occur.

[0064] In order to meet this demand, the present invention proposes a tool that can measure the real-time value and management level of blood sugar based on electrocardiogram (ECG).

[0065] Figure 1 This is an illustrative diagram for explaining a blood sugar management device according to an embodiment of the present invention.

[0066] like Figure 1 As shown, the blood sugar management device according to one embodiment of the present invention uses an electrocardiograph (ECG reader, 100) to measure the user's ECG. Fig.10 (ECG), using artificial intelligence (AI) to analyze the user's measured ECG Fig.10 The user's blood sugar level, glycated hemoglobin (HbA1c) level, etc. can be inferred by ECG, and a guide 20 about blood sugar or diabetes can be provided to the user based on the inferred results.

[0067] Therefore, according to one embodiment of the present invention, the user only needs to measure the ECG Fig.10 (ECG) can immediately confirm the user's blood sugar level and the degree of blood sugar management. As a result, high blood sugar and diabetes can be detected early or complications caused by high blood sugar or diabetes can be prevented.

[0068] The following describes in detail a number of devices and methods for implementing the aforementioned features.

[0069] Figure 2 This is an illustrative diagram for explaining a blood sugar management system according to an embodiment of the present invention.

[0070] like Figure 2 As shown, a blood glucose management system of one embodiment of the present invention may include one or more electrocardiographs 100 (including a watch type 100a, a portable type 100b, ..., a dynamic (holter) type 100n), one or more user devices 200 (including a smart phone 200a, a laptop computer 200b, ..., 200n) and a blood glucose management server 300.

[0071] As described above, the multiple elements of the blood glucose management system of one embodiment of the present invention merely illustrate multiple elements that are functionally distinguished, so that two or more elements can be implemented in an integrated manner in an actual physical environment or one element can be implemented separately in an actual physical environment.

[0072] The following describes each element. The electrocardiograph 100 is a device that can measure and record the user's electrocardiogram. Fig.10 (ECG) device.

[0073] Specifically, the electrocardiograph 100 can induce electric potential changes based on myocardial electrical activity by electrodes in contact with the user and amplify the induced electric potential changes and record them in the form of a waveform.

[0074] The electrocardiograph 100 of one embodiment of the present invention can induce an electrocardiogram (ECG) according to one of standard limb leads, unipolar limb leads, and precordial leads. Fig.10 The ECG induction method is not limited thereto. The electrocardiograph 100 may have electrodes for a single lead, 6 leads, or 12 leads, but the number of leads of the electrocardiograph 100 is not limited thereto. Furthermore, the electrocardiograph 100 may have a watch type 100a, a portable type 100b, and a holter type 100n, but the type of the electrocardiograph 100 is not limited thereto.

[0075] The electrocardiogram (ECG) signal (i.e., the recorded waveform signal) measured by the electrocardiograph 100 can be directly transmitted to the blood glucose management server 300 through the network function of the electrocardiograph 100 itself or input into the blood glucose management server 300 via a third tool. For example, the third tool can be any one of a removable media, a user device 200, and a data input behavior of the user, but is not limited thereto.

[0076] As a next element, the user device 200 can output reminder information 20 related to blood sugar or diabetes determined by the blood sugar management server 300.

[0077] Specifically, the user device 200 can receive reminder information 20 about blood sugar or diabetes from the blood sugar management server 300. Also, the user device 200 can output the received reminder information 20 about blood sugar or diabetes.

[0078] In this case, the reminder 20 information about blood sugar or diabetes may directly include the blood sugar value, glycosylated hemoglobin (HbA1c) value, whether it is a result of high blood sugar or low blood sugar, or whether the glycosylated hemoglobin (HbA1c) value is normal or not, or include indirect precautions, advice or warnings caused by the blood sugar value, glycosylated hemoglobin (HbA1c) value, whether it is a result of high blood sugar or low blood sugar, or whether the glycosylated hemoglobin (HbA1c) value is normal or not. In addition, the reminder 20 information about blood sugar or diabetes may include one or more of a reminder about the measures that the user needs to take immediately regarding blood sugar or diabetes and a reminder for supporting the user in managing diabetes.

[0079] The user device 200 of one embodiment of the present invention is not limited to the user equipment (UE) specified in the 3rd Generation Partnership Project (3GPP) or the mobile station (MS) specified in the Institute of Electrical and Electronics Engineers (IEEE). Any device can be permitted by the present invention as long as it can send and receive data with the blood glucose management server 300 and perform calculations based on the sent and received data.

[0080] As an example, the user device 100 can be a fixed computing device such as a desktop computer 200n, a workstation or a server, or a mobile computing device such as a smart phone 200a, a laptop computer 200b, a tablet computer, a phablet, a portable multimedia player (PMP), a personal digital assistant (PDA) or an e-book reader, but is not limited thereto.

[0081] As the next element, the blood sugar management server 300 uses the electrocardiograph 100 to measure the Fig.10 The user's blood sugar level, glycated hemoglobin level, etc. can be inferred based on the ECG, and reminder information about blood sugar or diabetes can be transmitted to the user device 200 based on the inferred result.

[0082] The specific elements and operations of the blood sugar management server 300 described above will be described later in conjunction with Figures 3 to 12 Please explain.

[0083] As described above, one or more electrocardiographs 100, one or more user devices 200, and a blood glucose management server 300 constituting the blood glucose management system can send and receive data using a network composed of one or more of a secure line that directly connects multiple devices, a public wired communication network, or a mobile communication network.

[0084] For example, the public wired communication network may include Ethernet, x Digital Subscriber Line (xDSL), Hybrid Fiber Coax (HFC), Fiber To The Home (FTTH), but are not limited thereto. Furthermore, the mobile communication network may include Code Division Multiple Access (CDMA), Wideband CDMA (WCDMA), High Speed ​​Packet Access (HSPA), Long Term Evolution (LTE), and 5th generation mobile telecommunication, but are not limited thereto.

[0085] The elements of the blood sugar management server 300 having the above-mentioned features will be described in detail below.

[0086] Figure 3 It is a logical configuration diagram of a blood sugar management server according to an embodiment of the present invention. Figure 4 This is an exemplary diagram for explaining the learning process of artificial intelligence (AI) according to an embodiment of the present invention. Figure 5 FIG. 1 is an exemplary diagram for explaining a method of removing an electrocardiogram (ECG) signal according to an embodiment of the present invention. Figure 6 and Figure 7 is an exemplary diagram for explaining a process of segmenting into multiple local units according to some embodiments of the present invention. Figure 8 is an illustrative diagram for illustrating the process of using artificial intelligence (AI) analysis in some embodiments of the present invention. Fig. 9 and Fig.10 is an exemplary diagram for explaining a process of interpreting an artificial intelligence (AI) analysis result according to an embodiment of the present invention.

[0087] like Figure 3As shown, the blood glucose management server 300 of one embodiment of the present invention may include a communication unit 305, an input and output unit 310, an artificial intelligence learning unit 315, an electrocardiogram release unit 320, a blood glucose analysis unit 325 and a reminder determination unit 330.

[0088] As described above, the multiple elements of the blood glucose management server 300 of one embodiment of the present invention merely illustrate multiple elements that are functionally distinguished, so that two or more elements can be implemented in an integrated manner in an actual physical environment or one element can be implemented separately in an actual physical environment.

[0089] Each element is described below. The communication unit 305 can transmit and receive data with the electrocardiograph 100 and the user device 200.

[0090] Specifically, the communication unit 305 can receive the electrocardiograph 100. Fig.10 Furthermore, the communication unit 305 can transmit reminder information 20 about blood sugar or diabetes to the user device 200 .

[0091] As the next element, the input-output unit 310 can receive input of a command from a manager or output a calculation result through a user interface (UI).

[0092] Specifically, the input-output unit 310 can receive the Fig.10 The input / output unit 310 can receive an input of a transformation method for extracting feature information from an ECG signal. The input / output unit 310 can receive an input of a window size as a basis for dividing feature information into a plurality of local units. The input / output unit 310 can receive an input of a valid range as a basis for removing outliers from a plurality of probability values ​​obtained from artificial intelligence (AI).

[0093] The input / output unit 310 can receive an input of a blood sugar value as a criterion for determining whether the blood sugar level is high or low, and an input / output unit 310 can receive an input of a glycated hemoglobin (HbA1c) value as a criterion for determining whether the glycated hemoglobin (HbA1c) level is normal or not.

[0094] Furthermore, the input / output unit 310 can output the user's ECG. Fig.10 The input-output unit 310 can also output reminder information 20 about blood sugar or diabetes to be provided to the user.

[0095] As the next element, the artificial intelligence learning unit 315 can use electrocardiogram Fig.10The first artificial intelligence (AI) and the second artificial intelligence (AI) perform machine learning based on the (ECG) signal.

[0096] Specifically, the first AI is an AI for inferring the blood sugar value of the user and determining whether the user has high blood sugar or low blood sugar. Moreover, the second AI is an AI for inferring the glycated hemoglobin (HbA1c) value of the user and determining whether the glycated hemoglobin (HbA1c) of the user is normal or not.

[0097] See also Figure 4 , the first AI may include a multiple linear regression model for inferring the user's blood sugar value and a classification model for determining whether it is high blood sugar or low blood sugar. Moreover, the second AI may include a multiple linear regression model for inferring the user's glycosylated hemoglobin (HbA1c) value and a classification model for determining whether the glycosylated hemoglobin (HbA1c) is normal or not.

[0098] The artificial intelligence learning unit 315 can set any weight and bias based on the multiple linear regression model of the first artificial intelligence (AI) and the following dataset, which is obtained from the ECG input for supervised training. Fig.10 The artificial intelligence learning unit 315 can obtain the result value after inputting the feature vector of the segmented signal subsequently segmented for supervised learning into the multiple linear regression model of the first artificial intelligence (AI) with arbitrary weights and bias items. The artificial intelligence learning unit 315 can calculate the loss function between the blood glucose value of the data set composed of the feature vector of the segmented signal subsequently segmented and the result value taken from the multiple linear regression model. Moreover, the artificial intelligence learning unit 315 updates the weights and bias items so as to minimize the error caused by the loss function and allow the multiple linear regression model of the first artificial intelligence (AI) to learn.

[0099] The artificial intelligence learning unit 315 can set any weight and bias item based on the classification model of the first artificial intelligence (AI) and the following data set, which is obtained from the ECG input for supervised learning. Fig.10The artificial intelligence learning unit 315 can obtain the result value after inputting the feature vector of the segmented signal subsequently segmented for supervised learning into the classification model of the first artificial intelligence (AI) with arbitrary weights and bias items. The artificial intelligence learning unit 315 can calculate the loss function between the classification result of hyperglycemia or hypoglycemia of the data set composed of the feature vector of the segmented signal subsequently segmented and the result value taken from the classification model. Moreover, the artificial intelligence learning unit 315 updates the weights and bias items so as to minimize the error caused by the loss function and allow the classification model of the first artificial intelligence (AI) to learn.

[0100] The artificial intelligence learning unit 315 can set any weight and bias term based on the multiple linear regression model of the second artificial intelligence (AI) and the following data set, which is obtained from the ECG input for supervised learning. Fig.10 The artificial intelligence learning unit 315 can obtain the result value after inputting the feature vector of the segmented signal subsequently segmented for supervised learning into the multiple linear regression model of the second artificial intelligence (AI) with arbitrary weights and bias items. The artificial intelligence learning unit 315 can calculate the loss function between the glycated hemoglobin (HbA1c) value of the data set composed of the feature vector of the segmented signal subsequently segmented and the result value taken from the multiple linear regression model. Moreover, the artificial intelligence learning unit 315 updates the weights and bias items so as to minimize the error caused by the loss function and allow the multiple linear regression model of the second artificial intelligence (AI) to learn.

[0101] Furthermore, the artificial intelligence learning unit 315 can set any weight and bias item based on the classification model of the second artificial intelligence (AI) and the following dataset, which is obtained from the ECG input for supervised learning. Fig.10 The artificial intelligence learning unit 315 can obtain the result value after inputting the feature vector of the segmented signal subsequently segmented for supervised learning into the classification model of the second artificial intelligence (AI) with arbitrary weights and bias items. The artificial intelligence learning unit 315 can calculate the loss function between the classification result of the normal or not of the data set composed of the feature vector of the segmented signal subsequently segmented and the result value taken from the classification model. Moreover, the artificial intelligence learning unit 315 updates the weights and bias items so as to minimize the error caused by the loss function and allow the classification model of the second artificial intelligence (AI) to learn.

[0102] In this case, the loss function used in the learning of the first artificial intelligence (AI) or the second artificial intelligence (AI) may be mean square error (MSE), but is not limited thereto, and may also be replaced by root mean square error (RMSE), cross entropy error (CEE), binary cross entropy error (BCEE), categorical cross entropy error (CCEE) or focal loss.

[0103] Furthermore, although the artificial intelligence learning unit 315 can update the weights and bias items according to the gradient descent method, it is not limited thereto.

[0104] Recombination Figure 3 The following elements are described: the electrocardiogram release unit 320 can release the electrocardiogram measured by the electrocardiograph 100. Fig.10 (ECG) signal.

[0105] Specifically, the electrocardiogram release unit 320 can obtain the electrocardiogram measured by the user. Fig.10 That is, the electrocardiogram release unit 320 can directly receive the electrocardiogram (ECG) signal from the electrocardiograph 100 through the communication unit 305. Fig.10 (ECG) signal or directly receive the ECG signal through the input and output unit 310 Fig.10 (ECG) signal input.

[0106] like Figure 5 As shown, the electrocardiogram decomposition unit 320 can decompose the acquired electrocardiogram based on one or more of amplitude, frequency and time. Fig.10 (ECG) signal and extract one or more feature information F1, F2, ..., Fn.

[0107] For example, the ECG decomposition unit 320 can decompose the ECG using one of wavelet transform, EEMD, TMF and TMDF. Fig.10(ECG) signal and then extracts feature information F1, F2, ..., Fn, but the ECG release unit 320 releases the ECG signal. Fig.10 The form of the (ECG) signal is not limited thereto.

[0108] Next, the ECG decomposition unit 320 can divide the extracted feature information F1, F2, . . . , Fn into a plurality of segmentation units according to the timing sequence from the user's measurement to the ECG signal.

[0109] Basically, if Figure 6 As shown, the electrocardiogram decompression unit 320 cuts each feature information F1, F2, ..., Fn individually (discretely) at a certain size without overlapping areas, and can be divided into a plurality of mutually separated local units S1, S2, S3, .... In this case, the size for individually cutting each feature information F1, F2, ..., Fn can be a certain value preset by the input and output unit 310, but it is not limited to this and can be a random value.

[0110] Differently, if Figure 7 As shown, the electrocardiogram removal unit 320 cuts each feature information F1, F2, ..., Fn while sliding the grid (window) along the time axis and can be divided into a plurality of local units S1, S2, S3, ... having a size corresponding to the grid. In this case, the size of the grid used to cut each feature information F1, F2, ..., Fn can be a certain value pre-set by the input and output unit 310.

[0111] On the other hand, ECG Fig.10 The (ECG) signal may contain noises generated during the measurement process due to factors such as the user's actions. Therefore, the ECG removal unit 320 can remove the noises contained in the divided multiple local units S1, S2, S3, ...

[0112] Specifically, the electrocardiogram release unit 320 can identify the displacement of the key points contained in each of the segmented multiple local units S1, S2, S3, ... The electrocardiogram release unit 320 can generate a normal distribution of multiple displacements of the identified multiple feature points. Moreover, the electrocardiogram release unit 320 can selectively remove only the segmented signal having the feature points contained in the preset noise range in the generated normal distribution to remove the noise. In this case, the method of identifying the feature points from the segmented multiple local units S1, S2, S3, ... can be based on a preset feature point extraction benchmark, but is not limited to this.

[0113] Recombination Figure 3 The following elements are described: the blood sugar analysis unit 325 can analyze the electrocardiogram using the first artificial intelligence (AI) pre-learned by the artificial intelligence learning unit 315. Fig.10 (ECG) signals to infer the user's blood sugar level and use artificial intelligence (AI) to analyze the ECG Fig.10 (ECG) signal to determine whether the user has high or low blood sugar.

[0114] Furthermore, the blood sugar analysis unit 325 can analyze the electrocardiogram using the second artificial intelligence (AI) pre-learned by the artificial intelligence learning unit 315. Fig.10 (ECG) signal to further infer the user's glycosylated hemoglobin (HbA1c) value and use artificial intelligence (AI) to analyze the ECG Fig.10 (ECG) signal to determine whether glycosylated hemoglobin (HbA1c) is normal or not.

[0115] First, the blood glucose analysis unit 325 can input the multiple local units S1, S2, S3, ... divided by the electrocardiogram release unit 320 into the first artificial intelligence (AI) and the second artificial intelligence (AI), and then obtain multiple numerical values ​​V1, V2, V3, ..., Vn and multiple probability values ​​P1, P2, P3, ..., Pn from the first artificial intelligence (AI) and the second artificial intelligence (AI).

[0116] Specifically, the blood sugar analyzing unit 325 can identify feature vectors of the plurality of local units S1 , S2 , S3 , . . . divided by the electrocardiogram decomposing unit 320 .

[0117] like Figure 8As shown, the blood glucose analysis unit 325 can input the identified feature vectors into the multiple linear regression model and classification model of the first artificial intelligence (AI). Moreover, the blood glucose analysis unit 325 can input the identified feature vectors into the multiple linear regression model and classification model of the second artificial intelligence (AI).

[0118] Moreover, the blood sugar analysis unit 325 can obtain multiple values ​​V1, V2, V3, ..., Vn for inferring blood sugar values ​​from the multiple linear regression model of the first artificial intelligence (AI). The blood sugar analysis unit 325 can obtain multiple probability values ​​P1, P2, P3, ..., Pn for judging whether it is hyperglycemia or hypoglycemia from the classification model of the first artificial intelligence (AI). The blood sugar analysis unit 325 can obtain multiple values ​​V1, V2, V3, ..., Vn for inferring glycated hemoglobin (HbA1c) values ​​from the multiple linear regression model of the second artificial intelligence (AI). The blood sugar analysis unit 325 can obtain multiple probability values ​​P1, P2, P3, ..., Pn for judging whether glycated hemoglobin (HbA1c) is normal or not from the classification model of the second artificial intelligence (AI).

[0119] Next, the blood sugar analysis unit 325 can infer the user's blood sugar value based on the multiple values ​​and multiple probability values ​​obtained from the first artificial intelligence (AI) and determine whether the user has high blood sugar or low blood sugar. In addition, the blood sugar analysis unit 325 can infer the user's glycosylated hemoglobin (HbA1c) value based on the multiple values ​​and multiple probability values ​​obtained from the second artificial intelligence (AI) and determine whether the glycosylated hemoglobin (HbA1c) is normal.

[0120] like Fig. 9 As shown, the blood glucose analysis unit 325 can remove outliers contained in multiple values ​​V1, V2, V3, ..., Vn obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a preset valid range.

[0121] The blood glucose analysis unit 325 can infer the user's blood glucose value by using a soft voting result based on the average value of multiple values ​​V1, V2, ..., Vm from which abnormal values ​​are removed among multiple values ​​V1, V2, V3, ..., Vn taken from the first artificial intelligence (AI).

[0122] The blood glucose analysis unit 325 can infer the user's glycated hemoglobin (HbA1c) value using a soft voting result based on the average value of multiple values ​​V1, V2, ..., Vm from which abnormal values ​​have been removed from multiple values ​​V1, V2, V3, ..., Vn taken from the second artificial intelligence (AI).

[0123] like Fig.10 As shown, the blood glucose analysis unit 325 can remove abnormal values ​​contained in multiple probability values ​​P1, P2, P3, ..., Pn taken from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a preset effective range.

[0124] The blood glucose analysis unit 325 can determine whether the user has hypoglycemia or hyperglycemia by using a hard voting result based on a majority decision of multiple probability values ​​P1, P2, ..., Pm from which abnormal values ​​have been removed among multiple probability values ​​P1, P2, P3, ..., Pn taken from the first artificial intelligence (AI).

[0125] The blood glucose analysis unit 325 can determine whether glycated hemoglobin (HbA1c) is normal or not by using a hard voting result based on a majority decision of multiple probability values ​​P1, P2, ..., Pm from which abnormal values ​​have been removed among multiple probability values ​​P1, P2, P3, ..., Pn taken from the second artificial intelligence (AI).

[0126] Recombination Figure 3 To illustrate the following elements, the reminder determination unit 330 can determine whether the user needs a reminder about blood sugar or diabetes based on the blood sugar value estimated by the blood sugar analysis unit 325 and the judgment result of whether it is high blood sugar or low blood sugar. Moreover, the reminder determination unit 330 can also determine whether the user needs a reminder about blood sugar or diabetes after further considering the glycated hemoglobin (HbA1c) value estimated by the blood sugar analysis unit 325 and the judgment result of whether the glycated hemoglobin (HbA1c) is normal or not.

[0127] Specifically, the reminder determination unit 330 can make a first judgment on whether the user has high blood sugar or low blood sugar based on the blood sugar value inferred by the multiple linear regression model using the first artificial intelligence (AI). The reminder determination unit 330 can make a second judgment on whether the first judgment result and the result classified by the classification model of the first artificial intelligence (AI) are the same. Moreover, the reminder determination unit 330 can determine whether the user needs a reminder about blood sugar based on the second judgment result.

[0128] For example, if the blood glucose value inferred by the multiple linear regression model of the first artificial intelligence (AI) is below 65 mg / dl and is classified as hypoglycemia by the classification model of the first artificial intelligence (AI), the reminder determination unit 330 may determine that the user needs a reminder about blood glucose. Differently, if the blood glucose value inferred by the multiple linear regression model of the first artificial intelligence (AI) is above 95 mg / dl and is classified as hyperglycemia by the classification model of the first artificial intelligence (AI), the reminder determination unit 330 may determine that the user needs a reminder about blood glucose.

[0129] The reminder determination unit 330 can make a first judgment on whether the glycated hemoglobin (HbA1c) is normal or not based on the glycated hemoglobin (HbA1c) value inferred by the multiple linear regression model using the second artificial intelligence (AI). The reminder determination unit 330 can make a second judgment on whether the first judgment result and the result classified by the classification model of the second artificial intelligence (AI) are the same. Moreover, the reminder determination unit 330 can determine whether the user needs a reminder about diabetes management based on the second judgment result.

[0130] For example, if the glycated hemoglobin (HbA1c) value inferred by the multiple linear regression model of the second artificial intelligence (AI) is above 5.7% and is classified as abnormal by the classification model of the second artificial intelligence (AI), the reminder determination unit 330 can determine that the user needs a reminder about diabetes management.

[0131] On the other hand, when the first judgment based on the numerical value of the multiple linear regression model and the result of classification by the probability value of the classification model are different, the artificial intelligence learning unit 315 can also readjust the weights and bias items set for the multiple linear regression models or classification models of the first artificial intelligence (AI) and the second artificial intelligence (AI) so that the matching rate of the first judgment based on the numerical value of the multiple linear regression model and the result of classification by the probability value of the classification model is within a pre-set valid range.

[0132] Next, when the user is determined to need a reminder about blood sugar or diabetes, the reminder determination unit 330 can set reminder information about blood sugar or diabetes based on the user's blood sugar value, glycosylated hemoglobin (HbA1c) value, whether it is a result of high blood sugar or low blood sugar, and whether glycosylated hemoglobin (HbA1c) is normal.

[0133] In this case, the reminder 20 information about blood sugar or diabetes may directly include the blood sugar value, glycosylated hemoglobin (HbA1c) value, whether it is a result of high blood sugar or low blood sugar, or whether the glycosylated hemoglobin (HbA1c) is normal or not, or may include indirect precautions, advices or warnings caused by the blood sugar value, glycosylated hemoglobin (HbA1c) value, whether it is a result of high blood sugar or low blood sugar, or whether the glycosylated hemoglobin (HbA1c) is normal or not.

[0134] Furthermore, the reminder information 20 regarding blood sugar or diabetes may include one or more of a reminder regarding the user's need to take immediate action regarding blood sugar or diabetes and a reminder for supporting the user in managing diabetes.

[0135] For example, the reminder determination unit 330 can set a reminder about the action that the user needs to take immediately based on the user's blood sugar value and whether it is high blood sugar or low blood sugar. In addition, the reminder determination unit 330 can set a reminder for supporting the user in managing diabetes based on the user's glycated hemoglobin (HbA1c) value and whether it is normal.

[0136] The reminder determination unit 330 can identify a pre-set human weight corresponding to the gender and age of the user. The reminder determination unit 330 can determine a distance weight corresponding to a distance value of a medical institution closest to the user device 200 (UE). The reminder determination unit 330 can determine a tone of sentence constituting a reminder 20 about blood sugar or diabetes based on the identified human weight and the determined distance weight. Moreover, the reminder determination unit 330 can compose the reminder 20 information about blood sugar or diabetes according to the determined tone of sentence.

[0137] Furthermore, the reminder determination unit 330 can transmit the set reminder information about blood sugar or diabetes to the user device 200 (UE) which is preset corresponding to the user.

[0138] The hardware for realizing the logical elements of the blood sugar management server 300 having the above-mentioned features will be described in more detail below.

[0139] Fig.11 FIG. 4 is a hardware configuration diagram of a blood sugar management server according to an embodiment of the present invention.

[0140] like Fig.11 As shown, the 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 an auxiliary storage 375 .

[0141] Specifically, the processor 350 can realize the operation and function of the blood sugar management server 300 based on the instructions of the software 380 a resident in the memory 355 and realizing the method of measuring the real-time value of blood sugar and the degree of management.

[0142] The software 380 b stored in the auxiliary memory 375 and realizing a method of measuring a real-time value of blood sugar and a management level can be resident (loaded) in the memory 355 .

[0143] The transceiver 360 can transmit and receive data with one or more of the electrocardiograph 100 and the user equipment (UE) 200 .

[0144] The input / output device 365 can receive input of signals required for the operation of the blood sugar management server 300 or output calculation results to the outside according to the command of the processor 350.

[0145] The data bus 370 is connected to the processor 350 , the memory 355 , the transceiver 360 , the input / output device 365 , and the auxiliary memory 375 , respectively, and can function as a mobile channel for transmitting signals between the various elements.

[0146] The auxiliary memory 375 can store an application programming interface (API), a library file, and a resource file required for executing the software 380a that implements the method of measuring the real-time value of blood glucose and the degree of management according to various embodiments of the present invention. The auxiliary memory 375 can store the software 380b that implements the method of measuring the real-time value of blood glucose and the degree of management according to various embodiments of the present invention. In addition, the auxiliary memory 375 may include a database 385 for storing learning data of artificial intelligence (AI) and various setting values.

[0147] According to an embodiment of the present invention, the software 380a, 380b for implementing the method for measuring the real-time value of blood sugar and the degree of management resident in the memory 355 or stored in the auxiliary memory 375 may be a computer program stored in the storage medium for executing the following steps: the processor 350 obtains the electrocardiogram (ECG) of the user as the object through the transceiver 360 or the input / output device 365; Fig.10 (ECG) signal; the processor 350 uses the pre-learned first artificial intelligence (AI) to analyze the electrocardiogram (ECG) signal to infer the user's blood sugar value, and uses the artificial intelligence (AI) to analyze the ECG signal Fig.10 (ECG) signal to determine whether the user has high blood sugar or low blood sugar; and the processor 350 determines whether the user needs a reminder about blood sugar or diabetes based on the inferred blood sugar value and the determination result of whether it is high blood sugar or low blood sugar 20.

[0148] More specifically, the processor 350 may include one or more of a central processing unit (CPU), an application-specific integrated circuit (ASIC), a chipset, and a logic circuit, but is not limited thereto.

[0149] The memory 355 may include one or more of a read-only memory (ROM), a random access memory (RAM), a flash memory, and a memory card, but is not limited thereto.

[0150] The input / output device 365 may include one or more input devices such as buttons, switches, keyboards, mice, joysticks, and touch screens, and output devices such as liquid crystal displays (LCDs), light emitting diodes (LEDs), organic LEDs (OLEDs), active matrix OLEDs (AMOLEDs), printers, and plotters, but is not limited thereto.

[0151] If the embodiments included in this specification are implemented in software, the methods can be implemented by multiple modules (processes, functions, etc.) each performing the functions described. Each module can reside in the memory 355 and be executed by the processor 350. The memory 355 can exist inside or outside the processor 350 and can be connected to the processor 350 by various well-known means.

[0152] Fig.11 The elements shown can be implemented by various tools (such as hardware, firmware, software or a combination thereof). If implemented by hardware, an embodiment of the present invention can 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.

[0153] Furthermore, if implemented in firmware or software, an embodiment of the present invention can be implemented in the form of modules, steps, functions, etc. that perform the multiple functions or actions described above and stored in a readable storage medium through various computer tools. Here, the storage medium can contain program commands, data files, data structures, etc. alone or in combination.

[0154] The program commands recorded in the storage medium may be specially designed for the present invention or may be known and usable by ordinary technicians in the computer software industry. For example, the storage medium includes magnetic media such as hard disks, floppy disks and tapes; optical recording media such as compact disk read only memory (CD-ROM) and digital video disks (DVD); magneto-optical media such as floptical disks; and special hardware devices such as read-only memory (ROM), random access memory (RAM), and flash memory that store and execute program commands.

[0155] Program commands may include machine language codes produced by a compiler, or high-level language codes executed by a computer using tools such as an interpreter. The hardware device can be operated by one or more software to perform the actions of the present invention, and vice versa.

[0156] Next, the operation of the blood sugar management server 300 described above will be described in detail.

[0157] Fig.12 This is a flowchart for explaining a method for measuring a real-time blood sugar value and a management level according to an embodiment of the present invention.

[0158] like Fig.12 As shown, the blood sugar management server 300 of one embodiment of the present invention can obtain the electrocardiogram (ECG) of the user as the object. Fig.10 (ECG) signal (step S100).

[0159] Specifically, the blood sugar management server 300 can directly receive the electrocardiograph from the electrocardiograph 100. Fig.10 (ECG) signals or can directly receive signal input from a user or other person.

[0160] Next, the blood sugar management server 300 can decompose the ECG based on one or more of amplitude, frequency and time. Fig.10 (ECG) signal to extract one or more feature information F1, F2, ..., Fn (step S200).

[0161] For example, the blood sugar management server 300 can use one of wavelet transform, ensemble empirical mode decomposition (EEMD), ternary motif field (TMF) and ternary motif difference field (TMDF) to decompose the ECG. Fig.10 (ECG) signal and then extract characteristic information F1, F2, ..., Fn, but not limited to this.

[0162] Next, the blood sugar management server 300 can divide the extracted feature information F1, F2, ..., Fn into a plurality of local units according to the timing sequence from the user's measurement to the electrocardiogram (ECG) signal (step S300).

[0163] According to one embodiment, the blood sugar management server 300 can cut each feature information F1, F2, ..., Fn individually (discretely) at a certain size without overlapping areas, and can be divided into a plurality of local units S1, S2, S3, ... separated from each other. According to another embodiment, the blood sugar management server 300 can cut each feature information F1, F2, ..., Fn while sliding a grid (window) along the time axis, and can be divided into a plurality of local units S1, S2, S3, ... having a size corresponding to the grid.

[0164] Next, the blood sugar management server 300 can use the first artificial intelligence (AI) learned in advance to analyze the ECG. Fig.10 (ECG) signal to infer the user's blood sugar value and determine whether the user has high blood sugar or low blood sugar. In addition, the blood sugar management server 300 can use the pre-learned second artificial intelligence (AI) to analyze the ECG signal. Fig.10 (ECG) signal to further infer the user's glycated hemoglobin (HbA1c) value and further determine whether the glycated hemoglobin (HbA1c) is normal (step S400).

[0165] Specifically, the blood glucose management server 300 can input multiple local units S1, S2, S3,... into the first artificial intelligence (AI) and the second artificial intelligence (AI) respectively, and then obtain multiple numerical values ​​V1, V2, V3,..., Vn and multiple probability values ​​P1, P2, P3,..., Pn from the first artificial intelligence (AI) and the second artificial intelligence (AI).

[0166] Next, the blood sugar management server 300 can infer the user's blood sugar value based on the multiple values ​​and multiple probability values ​​obtained from the first artificial intelligence (AI) and determine whether the user has high blood sugar or low blood sugar. In addition, the blood sugar management server 300 can infer the user's glycosylated hemoglobin (HbA1c) value based on the multiple values ​​and multiple probability values ​​obtained from the second artificial intelligence (AI) and determine whether the glycosylated hemoglobin (HbA1c) is normal (step S500).

[0167] Specifically, the blood sugar management server 300 can remove abnormal values ​​included in the multiple values ​​V1, V2, V3, ..., Vn obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on the preset effective range.

[0168] The blood glucose management server 300 can infer the user's blood glucose value by using a soft voting result based on the average value of multiple values ​​V1, V2, ..., Vm from which abnormal values ​​have been removed among multiple values ​​V1, V2, V3, ..., Vn taken from the first artificial intelligence (AI), and can infer the user's glycated hemoglobin (HbA1c) value by using a soft voting result based on the average value of multiple values ​​V1, V2, ..., Vm from which abnormal values ​​have been removed among multiple values ​​V1, V2, V3, ..., Vn taken from the second artificial intelligence (AI).

[0169] The blood sugar management server 300 can remove abnormal values ​​included in the plurality of probability values ​​P1, P2, P3, ..., Pn obtained from the first artificial intelligence (AI) and the second artificial intelligence (AI) based on a preset effective range.

[0170] Moreover, the blood sugar management server 300 can determine whether the user has hypoglycemia or hyperglycemia by using a hard voting result based on a majority decision of multiple probability values ​​P1, P2, ..., Pm taken from a first artificial intelligence (AI) with abnormal values ​​removed, and can determine whether glycated hemoglobin (HbA1c) is normal by using a hard voting result based on a majority decision of multiple probability values ​​P1, P2, P3, ..., Pm taken from a second artificial intelligence (AI) with abnormal values ​​removed.

[0171] Next, the blood sugar management server 300 can set reminder information about blood sugar or diabetes based on the user's blood sugar value, glycosylated hemoglobin (HbA1c) value, whether it is a result of high blood sugar or low blood sugar, and whether glycosylated hemoglobin (HbA1c) is normal (step S600).

[0172] Specifically, the blood sugar management server 300 can also determine whether the user needs a reminder about blood sugar based on the blood sugar value and the judgment result of whether it is high blood sugar or low blood sugar, and determine whether the user needs a reminder about diabetes based on the glycated hemoglobin (HbA1c) value and the judgment result of whether the glycated hemoglobin (HbA1c) is normal or not.

[0173] Furthermore, the reminder information 20 about blood sugar or diabetes may directly include the blood sugar value, glycosylated hemoglobin (HbA1c) value, whether it is a result of high blood sugar or low blood sugar, or whether the glycosylated hemoglobin (HbA1c) value is normal or not, or may include indirect precautions, advices, or warnings caused by the blood sugar value, glycosylated hemoglobin (HbA1c) value, whether it is a result of high blood sugar or low blood sugar, or whether the glycosylated hemoglobin (HbA1c) value is normal or not. Furthermore, the reminder information 20 about blood sugar or diabetes may include one or more of a reminder about the measures that the user needs to take immediately regarding blood sugar or diabetes and a reminder for supporting the user in managing diabetes.

[0174] Finally, the blood sugar management server 300 can transmit the set reminder information 20 about blood sugar or diabetes to the user device 200 (UE) preset corresponding to the user (step S700).

[0175] As mentioned above, this specification and the accompanying drawings disclose the preferred embodiments of the present invention. However, in addition to the embodiments disclosed herein, multiple variations based on the technical spirit of the present invention can also be implemented, which is self-evident to a person of ordinary skill in the technical field to which the present invention belongs. Moreover, although specific terms are used in this specification and the accompanying drawings, these terms are used in a general sense only to facilitate the description of the technical content of the present invention and to help understand the present invention, and are not intended to limit the scope of the present invention. Therefore, the detailed descriptions above cannot be interpreted as restrictive in all aspects and can only be regarded as illustrative. The scope of the present invention should be selected based on a reasonable interpretation of the scope of the invention claims, and all changes within the equivalent range of the present invention are included in the scope of the present invention.

Claims

1. A method for measuring the real-time value of blood sugar and the degree of management, characterized in that: The following steps are involved: Acquiring an electrocardiogram signal measured with the user as an object; Analyzing the electrocardiogram signal using a pre-learned first artificial intelligence to infer the blood sugar value of the user, and analyzing the electrocardiogram signal using the artificial intelligence to determine whether the user has high blood sugar or low blood sugar; as well as Whether the user needs a reminder about blood sugar or diabetes is determined based on the inferred blood sugar value and the result of the judgment of whether it is high blood sugar or low blood sugar.

2. The method for measuring the real-time value of blood sugar and the degree of management according to claim 1, characterized in that: In the step of determining whether it is hyperglycemia or hypoglycemia, the pre-learned second artificial intelligence is used to analyze the electrocardiogram signal to infer the user's glycosylated hemoglobin value, and the second artificial intelligence is used to analyze the electrocardiogram signal to determine whether the glycosylated hemoglobin is normal or not.

3. The method for measuring the real-time value of blood sugar and the degree of management according to claim 2, characterized in that: The step of determining whether it is hyperglycemia or hypoglycemia comprises the following steps: Decomposing the acquired electrocardiogram signal based on one or more of amplitude, frequency and time to extract one or more feature information; Dividing the extracted characteristic information into a plurality of local units according to the timing of measuring the electrocardiogram signal; Input the divided local units to the first artificial intelligence and the second artificial intelligence respectively, and obtain a plurality of numerical values ​​and a plurality of probability values ​​from the first artificial intelligence and the second artificial intelligence; as well as Based on the multiple numerical values ​​and multiple probability values ​​obtained from the first artificial intelligence, the blood glucose value is inferred and whether it is hyperglycemia or hypoglycemia is determined. Based on the multiple numerical values ​​and multiple probability values ​​obtained from the second artificial intelligence, the glycated hemoglobin value is inferred and whether the glycated hemoglobin is normal is determined.

4. The method for measuring the real-time value of blood sugar and the degree of management according to claim 3, characterized in that: In the step of extracting characteristic information, the electrocardiogram signal is decomposed and the characteristic information is extracted by using any one of wavelet transform, set empirical mode decomposition, ternary motif field and ternary motif difference field.

5. The method for measuring the real-time value of blood sugar and the degree of management according to claim 3, characterized in that: In the step of dividing into a plurality of local units, a grid of a preset size is moved along the time axis and the feature information obtained from the electrocardiogram signal is divided into a plurality of local units having a size corresponding to the grid.

6. The method for measuring the real-time value of blood sugar and the degree of management according to claim 3, characterized in that: In the step of obtaining multiple numerical values ​​and multiple probability values, the feature vectors of the multiple segmented local units are respectively input into the multiple linear regression model and the classification model of the first artificial intelligence and the second artificial intelligence to obtain the multiple numerical values ​​and multiple probability values.

7. The method for measuring the real-time value of blood sugar and the degree of management according to claim 3, characterized in that: In the step of judging whether it is normal or not, the abnormal values ​​contained in the multiple values ​​taken from the first artificial intelligence and the second artificial intelligence are eliminated based on the preset effective range, and the blood sugar value is judged using the soft voting result based on the average value of the multiple values ​​taken from the first artificial intelligence from which the abnormal values ​​are eliminated, and the glycated hemoglobin value is inferred using the soft voting result based on the average value of the multiple values ​​taken from the second artificial intelligence from which the abnormal values ​​are eliminated.

8. The method for measuring the real-time value of blood sugar and the degree of management according to claim 3, characterized in that: In the step of judging whether it is normal or not, the abnormal values ​​contained in the multiple probability values ​​taken from the first artificial intelligence and the second artificial intelligence are eliminated based on the effective range, and whether it is hyperglycemia or hypoglycemia is judged by using the hard voting result based on the majority decision of the multiple probability values ​​taken from the first artificial intelligence from which the abnormal values ​​are eliminated, and whether the glycated hemoglobin is normal or not is judged by using the hard voting result based on the majority decision of the multiple probability values ​​taken from the second artificial intelligence from which the abnormal values ​​are eliminated.

9. The method for measuring the real-time value of blood sugar and the degree of management according to claim 3, characterized in that: After the step of determining whether a reminder is needed, the following steps are also included: If it is determined that the reminder is needed, the reminder information set based on the blood sugar value, the glycosylated hemoglobin value, whether it is high blood sugar or low blood sugar, and whether the glycosylated hemoglobin is normal or not is transmitted to the pre-set user device corresponding to the user.

10. A computer program stored in a storage medium in combination with a computing device comprising a memory, a transceiver, an input / output device and a processor for processing commands resident in the memory for executing the following steps: The processor acquires an electrocardiogram signal measuring the user as an object through the transceiver or the input / output device; The processor uses the pre-learned first artificial intelligence to analyze the electrocardiogram signal to infer the blood sugar value of the user, and uses the artificial intelligence to analyze the electrocardiogram signal to determine whether the user has high blood sugar or low blood sugar; and The processor determines whether the user needs a reminder about blood sugar or diabetes based on the inferred blood sugar value and the result of the judgment of whether it is high blood sugar or low blood sugar.

Images