Blood glucose management system using continuous blood glucose monitoring device and extended reality glasses and blood glucose management method using the same

Abstract

A blood glucose management system is disclosed, comprising a user terminal configured to capture an image of food, a processor, and an information providing device configured to provide the processor with blood glucose time-series information of a user prior to ingestion of the food. The processor is configured to execute a step of generating blood glucose trend prediction information of the user after ingestion of the food, based on data related to the food captured by the user terminal and the blood glucose time-series information. The user terminal is configured to display the blood glucose trend prediction information.

Description

BLOOD GLUCOSE MANAGEMENT SYSTEM USING CONTINUOUS BLOOD GLUCOSE MONITORING DEVICE AND EXTENDED REALITY GLASSES AND BLOOD GLUCOSE MANAGEMENT METHOD USING THE SAME

[0001] This application claims priority based on Korean Patent Application No. 10-2025-0002156 filed on January 07, 2025, and Korean Patent Application No. 10-2024-0118060 filed on August 30, 2024, the disclosures of which are incorporated herein by reference in their entirety.

[0002] The present invention relates to blood glucose management technology, and more particularly, to a technology using a continuous blood glucose monitoring device and extended reality glasses.

[0003] A continuous glucose monitoring (CGM) device is a technology that measures changes in a user's blood glucose level in real time and is widely used to help diabetic patients effectively manage their blood glucose. The CGM device continuously collects blood glucose data by attaching a sensor to the skin and transmits the data to a smartphone or a separate receiving device, thereby providing the user with blood glucose values and trends. This technology has the advantages of being less invasive and enabling continuous monitoring compared to the conventional blood sampling method, thus significantly improving the quality of life of diabetic patients.

[0004] However, most existing CGM technologies require checking the data through a smartphone or a specific display device, which has the disadvantage that the process of checking blood glucose information is cumbersome. The user has to take out the device periodically to check the screen, and therefore, it is often difficult to quickly check blood glucose information. In particular, in situations where it is difficult to use hands freely, such as during exercise, driving, or outdoor activities, it is even more inconvenient to check the blood glucose level. Such inconvenience can impair the efficiency of blood glucose management and may act as a factor that weakens the user's willingness for continuous blood glucose management.

[0005] The present invention aims to provide nutritional information (e.g., food name, calories) to the user by recognizing in real time information about food captured by the user using AR / VR glasses, and to provide personalized blood glucose prediction and health management suggestions in metaverse video based on the nutritional information of the food and blood glucose information obtained by a CGMS used by the user.

[0006] According to one aspect of the present invention, a user-customized blood glucose management method using AR / VR glasses and a CGMS may be provided. The blood glucose management method may include: a step in which a user wears AR / VR glasses provided according to one embodiment of the present invention and looks at food; a step in which a camera embedded in the AR / VR glasses captures the food in the line of sight; a step in which image recognition software embedded in the AR / VR glasses recognizes the food present in the captured image; a step in which the AR / VR glasses generate food information including the name and calories of the recognized food and display the generated food information to the user through a video display provided in the AR / VR glasses; a step in which the AR / VR glasses receive in real time the blood glucose information of the user measured by the CGMS used by the user; a step in which the AR / VR glasses predict the expected blood glucose change upon intake of the recognized food based on the received blood glucose information and the generated food information; a step in which the AR / VR glasses determine or acquire an appropriate blood glucose management method for the user based on the predicted blood glucose change; and a step in which the AR / VR glasses provide customized suggestions (e.g., walking for 30 minutes, cycling for 10 minutes, maintaining fasting for 2 hours, etc.) suitable for the user's condition as visual content in the metaverse on the video display of the glasses.

[0007] <AR / VR Glasses-Based User-Customized Blood Glucose Management Method>

[0008] According to one aspect of the present invention, the personalized blood glucose management system may include a personalized AI (artificial intelligence) health agent that continuously monitors the user's health in a metaverse environment and provides real-time information through augmented reality (AR).

[0009] The health agent may be a device selected from among AR / VR glasses, eyeglass camera, Bluetooth bidirectional audio headset, digital watch, wireless weight scale, and bio-wearable measuring device, or a device combining two or more thereof.

[0010] For example, AR / VR glasses may be used as the health agent. The AR / VR glasses may monitor the user's condition in conjunction with a CGMS used by the user. Also, the AR / VR glasses may provide visual feedback such as calories, ingredients, nutrient information of the food captured by the AR / VR glasses, and exercise recommendations to the user.

[0011] The health agent, in a specific operation mode among multiple operation modes provided by the health agent, may monitor and analyze the user's health condition, habits, environment, and behavior in real time for 24 hours without user intervention, and may provide graphics and information overlaid on the real world through AR / VR functions to induce healthy choices. It may help users make healthier choices in daily life and provide real-time information for achieving personalized health improvements.

[0012] When using the AR / VR glasses as the health agent, the user can wear the AR / VR glasses and receive real-time health-related information by overlaying additional graphics on information visible in the real world. For example, when a user about to eat looks at food through the eyeglass camera, calorie and nutrient content of the visible food may be overlaid in real time on the AR screen, and expected blood glucose changes or exercise recommendations may be immediately provided. Also, by analyzing health data collected from various sensors including the CGMS, personalized feedback based on the user's activities or surrounding environment can be provided to assist in long-term health improvement. This provides advantageous effects over conventional health management systems, which require users to manually search for or record information and fail to provide real-time necessary information or integrated health management due to unintegrated data collected from various devices.

[0013] Specifically, the camera provided in the AR / VR glasses may capture the user's surrounding environment in real time, and visual information may be provided through the AR / VR glasses or augmented reality function. The visual information may include, for example, food information, environmental information, and habit correction information.

[0014] For example, a scenario in which the AR / VR glasses provide the food information is as follows. That is, when the user enters a restaurant and selects a menu, if a food image is recognized through the camera, the calorie, nutritional components, GI (GL) index, and expected blood glucose changes of the food may be displayed in real time on the screen of the AR / VR glasses. To aid food selection, exercise amounts required after intake and exercise recommendations may also be provided as AR graphics.

[0015] For example, a scenario in which the AR / VR glasses provide the environmental information is as follows. That is, when the user exercises in a park, the exercise intensity and consumed calories may be monitored in real time, and appropriate exercise duration and intensity may be recommended through the screen of the AR / VR glasses.

[0016] For example, a scenario in which the AR / VR glasses provide the habit correction information is as follows. That is, if the user repeats a bad habit for a certain period, continuous warnings and feedback may be provided through graphics generated and displayed by the AR / VR glasses, and real-time guidance may be provided to replace the habit with a healthy one.

[0017] As described above, by using AR / VR glasses, first, real-time visual feedback may be provided to induce health improvement for the user; second, convenience may be increased by allowing direct confirmation of information and reflection in behavior in the real world; third, an integrated management function may be provided by compiling various health information on a single screen; fourth, a personalized guide for real-time support of health-related decisions such as food selection and exercise recommendation may be provided; and fifth, long-term health improvement may be achieved by providing personalized health feedback based on the user's environment.

[0018] According to one aspect of the present invention, when the blood glucose management system uses AR / VR glasses as the personalized AI health agent, the blood glucose management system may include the following components.

[0019] That is, according to one aspect of the present invention, the blood glucose management system may include VR / AR glasses; a bio-wearable measuring device; and a wireless weight scale. The bio-wearable measuring device may include one or more of a digital watch and a CGMS. The VR / AR glasses may include the function of a Bluetooth bidirectional audio headset. The Bluetooth bidirectional audio headset may support voice feedback and user command input functions. The bio-wearable measuring device may provide body activity and health data monitoring functions. The wireless weight scale may provide weight and other body data measurement functions.

[0020] <Metaverse-Based User-Customized Blood Glucose Management Method>

[0021] According to one aspect of the present invention, the personalized blood glucose management system may provide a metaverse, which is an immersive digital space combining virtual reality (VR) and augmented reality (AR). For this purpose, the personalized blood glucose management system may include a bio-wearable device, a metaverse platform providing device, a data processing and connection device, and virtual reality / augmented reality equipment. The virtual reality / augmented reality equipment may be the above-described AR / VR glasses.

[0022] The bio-wearable device may include a CGMS. The bio-wearable device may transmit its measured wearable data to the cloud or to the VR / AR device via Bluetooth or Wi-Fi. The wearable data may include CGMS measurement data.

[0023] The metaverse platform providing device may be a remote server, the virtual reality / augmented reality equipment, or a system device including the server and the virtual reality / augmented reality equipment. The metaverse platform providing device may utilize AI (artificial intelligence) algorithms for analysis of healthcare data such as CGMS data and food information. The wearable data may be integrated with the metaverse platform via a RESTful API

[0024] The metaverse platform providing device may provide a dashboard where patient data is visually represented. The dashboard may be provided and displayed on the virtual reality / augmented reality equipment. Real-time incoming biometric data may be displayed on the metaverse dashboard. For example, the user's continuous glucose data may be graphically represented in real time within the virtual environment. Furthermore, by visualizing changes in the user's blood glucose, personalized guidance may be provided in real time to assist health-related decisions such as food selection and exercise recommendations.

[0025] The wearable data may be encrypted using, for example, AES or RSA, to protect the user's sensitive data.

[0026] In the metaverse, the dashboard may refer to an interface that helps the user or manager intuitively grasp and manage various information in the virtual environment. Like a real-world dashboard, it plays a role in visually expressing important data or indicators. In one embodiment of the present invention, CGMS-related data, data about captured food, food recommendation information, and exercise recommendation information may be displayed on the metaverse dashboard.

[0027] <User-Customized Blood Glucose Management Method Based on Individual Food Glycemic Index (GI)>

[0028] According to one aspect of the present invention, the personalized blood glucose management system may learn (i.e., may be trained with) the individual food glycemic index (GI) of a patient and recommend personalized eating habits according to the current blood glucose and health condition. This system can be applied to meal planning, nutrition management, and health maintenance for people needing blood glucose management, including diabetic patients.

[0029] The glycemic index (GI) is an indicator that quantifies how fast and how high a food raises blood glucose levels after digestion and absorption. The reference GI may be based on glucose or white bread, and the reference GI may be set, for example, at 100. The blood glucose response of food may be relatively scored compared to this reference.

[0030] Foods that raise blood glucose slowly, such as vegetables, whole grains, and some fruits, may have low GI values of 55 or less. Foods that moderately raise blood glucose, such as brown rice and corn, may have medium GI values of about 56 to 60. Foods that rapidly raise blood glucose, such as white rice, sugar, and potatoes, may have high GI values of 70 or more.

[0031] The individual GI (i.e., patient-specific GI) may refer to a personalized blood glucose response to a specific food. Even for the same food, blood glucose responses can differ among individuals.

[0032] In the present invention, by learning a patient's eating habits and health patterns, a personalized meal guide suitable for the individual patient may be provided. Initially, the guide may be provided based on known food GI values, and an individualized food GI model may be generated based on actual post-meal blood glucose response data from the patient. Subsequently, meal recommendations may be adjusted according to the patient's health status, and the system may be advanced by analyzing the patient's adherence to the recommended habits, ultimately proposing optimal dietary habits.

[0033] Conventional systems provide general guidance based on known food GI values without considering post-meal blood glucose changes, failing to reflect individual differences. Additionally, they have difficulty enabling continuous dietary habit improvement due to a lack of reflection of actual patient adherence.

[0034] In contrast, the present invention initially provides a meal guide based on known food GI values, then generates a personalized food GI model by continuously learning the patient's post-meal blood glucose responses and dietary patterns. Based on this model, personalized meal recommendations suited to the patient's health status may be provided, and the system may be refined by analyzing adherence to the recommended guide. Over time, this allows the proposal of more suitable personalized dietary habits for the patient.

[0035] According to one aspect of the present invention, the personalized blood glucose management system may provide a dietary recommendation method comprising: a step of providing the user with an initial meal guide based on the known GI value of the food and the meal amount; a step of monitoring post-meal blood glucose changes through the CGMS and collecting the patient's eating habit data; a step of learning (i.e., training a model with) a personalized food GI model based on the post-meal blood glucose change and the eating habit data; a step of recommending a personalized meal suitable for the patient's current health status based on the learned model; and a step of analyzing the patient's actual adherence and providing an updated meal guide to the user based on the analyzed actual adherence.

[0036] To this end, at least one processor included in the personalized blood glucose management system may execute instructions to perform the functions of: a sensor and transmitter for real-time monitoring of the patient's blood glucose; a data processing module for processing the collected blood glucose and eating habit data and learning the personalized food GI model; a meal recommendation module for recommending a personalized meal based on the learned model; and an adherence analysis module for analyzing the patient's adherence and improving the system.

[0037] According to one aspect of the present invention, a blood glucose management system 3 may be provided, comprising: a user terminal 20 configured to capture an image of food 700; a processor 9; and an information providing device configured to provide the processor with time-series blood glucose information 361 of the user before consumption of the food. In this case, the processor is configured to execute: a step S140 of determining a user-customized GI corrected to the user by the GI of the food captured by the user terminal; and a step S170 of generating blood glucose trend prediction information 372 of the user after consuming the food, based on the blood glucose time-series information and the user-customized GI. The user terminal is configured to display the blood glucose trend prediction information.

[0038] In this case, the information providing device may be a device included in a CGMS (continuous glucose monitoring system) that is configured to measure the user's blood glucose.

[0039] In this case, the information providing device may be configured to provide postprandial blood glucose time-series information 362 of the user after consuming the food. The processor may be further configured to execute a step S360 of correcting the user-customized GI based on the difference between the postprandial blood glucose time-series information and the blood glucose trend prediction information.

[0040] In this case, in the step of correcting the user-customized GI, if the blood glucose value of the user included in the postprandial blood glucose time-series information is less than the blood glucose value of the user included in the blood glucose trend prediction information during a predetermined time period after the user has consumed the food, the user-customized GI may be updated by decreasing it.

[0041] In this case, in the step of correcting the user-customized GI, if the blood glucose value of the user included in the postprandial blood glucose time-series information is greater than the blood glucose value of the user included in the blood glucose trend prediction information during a predetermined time period after the user has consumed the food, the user-customized GI may be updated by increasing it.

[0042] In this case, the user terminal may be extended reality glasses 400 including a capturing device. The step in which the extended reality glasses capture the food may include: a step S111 in which the user wears the extended reality glasses and gazes at the food; a step S112 in which the user inputs a predetermined voice command to the extended reality glasses; and a step S113 in which the extended reality glasses capture the food in response to the voice command.

[0043] In this case, the processor may be further configured to execute: between the step of determining the user-customized GI and the step of generating the blood glucose trend prediction information of the user, a step S150 of requesting the blood glucose time-series information from the information providing device or a first network system N1 including the information providing device, and a step S160 of receiving the blood glucose time-series information from the information providing device or the first network system.

[0044] In this case, the processor may be further configured to execute: between the time point when the user finishes consuming the food and the step of correcting the user-customized GI, a step S340 of requesting postprandial blood glucose time-series information from the information providing device or a first network system N1 including the information providing device, and a step S350 of receiving the postprandial blood glucose time-series information from the information providing device or the first network system.

[0045] In this case, the processor may be included in the user terminal, and the user terminal may be configured to obtain the blood glucose time-series information by wired or proximity-based wireless communication with the information providing device.

[0046] In this case, the blood glucose management system may further include a service server 300. The processor may be included in the service server, and the server may be configured to obtain the blood glucose time-series information from a first network system N1 including the information providing device.

[0047] In this case, the step of correcting and updating the user-customized GI may include: a step of correcting and updating a correction coefficient related to the user based on the difference between the postprandial blood glucose time-series information and the blood glucose trend prediction information; and a step of correcting the user-customized GI by multiplying the updated correction coefficient by the GI of the food.

[0048] In this case, the blood glucose management system may further include a second user terminal 600 configured to measure time-series information of the user's amount of exercise. The information providing device may be configured to provide postprandial blood glucose time-series information 362 of the user after the user has consumed the food. The processor may be further configured to execute: a step S360 of requesting the time-series information of the user's amount of exercise from the second user terminal or a second network system N2 including the second user terminal after the user has consumed the food; a step S370 of receiving the time-series information of the user's amount of exercise from the second user terminal or the second network system; and a step S380 of correcting the user-customized GI based on the blood glucose trend prediction information, the postprandial blood glucose time-series information, and the time-series information of the user's amount of exercise.

[0049] According to another aspect of the present invention, a blood glucose management method may be provided, comprising: a step in which extended reality glasses worn by a user capture food; a step in which a service server determines a user-customized GI corrected to the user by the GI of the captured food and obtains blood glucose time-series information of the user measured before the user consumes the food; a step in which the service server generates blood glucose trend prediction information of the user after consuming the food based on the blood glucose time-series information and the user-customized GI; and a step in which the extended reality glasses display the blood glucose trend prediction information.

[0050] In this case, the blood glucose management method may further include a step in which the service server corrects and updates the user-customized GI based on the difference between the postprandial blood glucose time-series information and the blood glucose trend prediction information after the step of generating the blood glucose trend prediction information of the user.

[0051] According to another aspect of the present invention, a blood glucose management method may be provided, comprising: a step in which extended reality glasses worn by a user capture food; a step in which the extended reality glasses determine a user-customized GI corrected to the user by the GI of the captured food and obtain blood glucose time-series information of the user measured before the user consumes the food; a step in which the extended reality glasses generate blood glucose trend prediction information of the user after consuming the food based on the blood glucose time-series information and the user-customized GI; and a step in which the extended reality glasses display the blood glucose trend prediction information.

[0052] In this case, the blood glucose management method may further include a step in which the extended reality glasses correct and update the user-customized GI based on the difference between the postprandial blood glucose time-series information and the blood glucose trend prediction information after the step of generating the blood glucose trend prediction information of the user.

[0053] According to one aspect of the present invention, a biometric data management system may be provided, comprising: extended reality glasses configured to capture food; a processor; and an information providing device configured to provide the processor with biometric data of the user measured before the user consumes the food. The processor is configured to execute a step of generating personalized information relating to one or more of the user's current blood glucose information, the user's blood glucose time-series information, the user's blood glucose prediction information, recommended food information for the user, recommended exercise information for the user, restaurant information for the user, fitness facility information for the user, and information regarding the purchase of bio-wearable devices for the user, upon identifying the food captured by the user terminal. The user terminal is configured to display the generated personalized information.

[0054] In this case, the personalized information may be generated or obtained based on the user's biometric data and the information regarding the captured food.

[0055] In this case, the user's biometric data may be the user's blood glucose time-series information, and the bio-wearable device may be a CGM device.

[0056] In this case, the bio-wearable device may be one or more selected from a smartwatch and fitness band configured to measure heart rate, blood pressure, oxygen saturation, ECG, and sleep patterns; a blood glucose meter configured to measure continuous blood glucose levels; an ECG and heart rate meter configured to measure ECG and heart rate; a blood pressure monitor configured to measure blood pressure; an oximeter configured to measure blood oxygen saturation; a wearable thermometer configured to measure body temperature in real time; an electromyograph configured to measure muscle activity and neural signals; a wearable EEG configured to measure brain wave activity; a smart ring configured to measure heart rate and activity levels; a wearable muscle and posture monitor configured to monitor posture and muscle activity; smart clothing embedded with sensors configured to monitor heart rate and respiration; a wearable respiratory monitor configured to measure respiration and lung capacity; a skin sensor configured to measure body temperature and sweat composition; and a wearable ultrasound device configured to diagnose tissue images and heart conditions using ultrasound.

[0057] In this case, the information providing device may be the bio-wearable device itself or another user device that communicates with the bio-wearable device.

[0058] According to another aspect of the present invention, a biometric data management system may be provided, comprising: a processor configured to generate personalized information; extended reality glasses configured to capture food and display the generated personalized information; and an information providing device configured to provide the processor with the user's biometric data. The processor is configured to generate integrated data by integrating at least one of the user's biometric data, data related to food consumed by the user, data related to exercise performed by the user, and data related to drugs ingested by the user, and a model comprising one or more of an LLM and an LMM learns the integrated data. The processor analyzes the user's health status using the food-related data captured by the extended reality glasses and the learned model, and generates the personalized information including at least one of a personalized diet, exercise plan, and medication schedule for the user based on the analyzed data.

[0059] According to one aspect of the present invention, a blood glucose management system may be provided, comprising: a user terminal configured to collect lifestyle information of the user including information about at least one of food, exercise, medication, sleep, and stress; an information providing device configured to acquire the blood glucose time-series information of the user; and a processor configured to execute a step of generating personalized service information including at least some or all of explanation data about the user's current health status, explanation data about the user's predicted future health status, and information about actions the user must take to improve health based on the user's lifestyle information and the blood glucose time-series information. The user terminal is configured to output the personalized service information to the user.

[0060] In this case, the information about food included in the lifestyle information may include information about food that the user is going to consume or has consumed, including at least some of food items, recipes, processed foods, and ingredients designated by the user, and consumption schedule.

[0061] In this case, the information about exercise included in the lifestyle information may include at least some of the type of exercise to be performed or that was performed by the user, exercise intensity, exercise time, exercise structure, and exercise schedule.

[0062] In this case, the information about medication included in the lifestyle information may include at least some of the type of drug to be ingested or that was ingested by the user, intake schedule, and dosage.

[0063] In this case, the information about sleep included in the lifestyle information may include at least some data about the user's recent sleep time and sleep stages.

[0064] In this case, the information about stress included in the lifestyle information may include time-series data of the user's stress index.

[0065] Information regarding at least one of food, exercise, medication, sleep, and stress may be collected by the user terminal. For this purpose, the user terminal may include a user input interface that allows the user to directly input information regarding at least one of food, exercise, medication, sleep, and stress. Alternatively, the user terminal may include a sensor configured to directly detect at least one of food, exercise, medication, sleep, and stress.

[0066] For example, the user terminal may be a smartwatch including a sensor configured to directly detect information regarding at least one of exercise, sleep, and stress. Alternatively, the user terminal may be extended reality glasses including a capture sensor configured to capture food and medications presented for food intake and medication. Alternatively, the user terminal may refer to a user terminal system composed of a group of devices including the smartwatch and the extended reality glasses.

[0067] In this case, the explanation data about the user's current health status, the explanation data about the user's predicted future health status, and the information about actions the user must take to improve health may be generated in the form of voice data, audio data, and / or visualized data. The personalized service information may also be generated in the form of voice data, audio data, and / or visualized data.

[0068] In this case, the user terminal may include a speaker and / or display device to output the personalized service information to the user.

[0069] In this case, the blood glucose management system may further include a storage storing a database including the user's lifestyle information and the blood glucose time-series information, and the user terminal may be configured to receive an inquiry from the user.

[0070] The storage may be included in the user terminal, the information providing device, a device including the processor, or another independent server accessible by the processor.

[0071] The user terminal may collect the lifestyle information of the user multiple times and store the collected lifestyle information in the storage. Also, the information providing device may collect the blood glucose time-series information of the user multiple times and store the collected blood glucose time-series information in the storage.

[0072] The user terminal may include a user interface for inputting an inquiry, such as a microphone, keyboard, mouse, or touch panel.

[0073] In this case, the step of generating the personalized service information may include: a step of preparing personal information obtained by retrieving some of the lifestyle information and some of the blood glucose time-series information related to the user's inquiry from the database; a step of preparing augmented information by combining the personal information with predetermined medical information; and a step of generating the personalized service information using the augmented information.

[0074] For example, if the user's inquiry is "I had a hamburger, French fries, and 500 mL of cola for lunch and I'm planning to take a walk. Can you suggest an appropriate walking schedule?", the database may be searched for a time segment in the past when the user consumed a similar meal (hamburger, French fries, and cola) near lunchtime, and the user's postprandial blood glucose change may be retrieved and prepared as the personal information. Then, the retrieved blood glucose change data and predefined general medical or exercise physiology information may be combined to prepare the augmented information. For example, the user's blood glucose elevation trend and blood glucose prediction result after consuming the meal may be determined from the personal information, and appropriate reference data included in the medical or exercise physiology information for correcting the blood glucose prediction result to a desirable level may be combined with the personal information to generate the augmented information.

[0075] In this case, the personalized service information may include the user's blood glucose trend prediction information. The step of generating the personalized service information may include a step of generating the user's blood glucose trend prediction information using the user's lifestyle information, the blood glucose time-series information, and diabetes-related chronic disease indicators related to the user.

[0076] In this case, the diabetes-related chronic disease indicators may include one or more of GI index, GL index, TIR, TAR, TBR, Glucose Variability, Mean Glucose, SD, GRI, Hyperglycemia risk, Hypoglycemia risk, AGP, AUC, MAGE, GMI, Lability Index, Low Blood Glucose Index, High Blood Glucose Index, Glucose Variability and Energy Expenditure, and Postprandial Glucose Response.

[0077] Among the diabetes-related chronic disease indicators, GI (Glycemic Index), GL (Glycemic Load), Postprandial Glucose Response, AUC (Area Under the Curve), and MAGE (Mean Amplitude of Glycemic Excursion) are indicators highly correlated with specific foods or ingredients. GI directly represents the rate at which a specific food raises blood glucose, GL indicates the degree of blood glucose increase considering the amount of intake, Postprandial Glucose Response shows short-term blood glucose changes after consumption of a specific food, AUC shows the magnitude and duration of blood glucose changes after food intake, and MAGE indicates the amplitude of blood glucose fluctuation related to meals.

[0078] Among the diabetes-related chronic disease indicators, indicators that are not directly correlated with specific foods or ingredients include TIR (Time in Range), TAR (Time Above Range), TBR (Time Below Range), Mean Glucose, SD (Standard Deviation), GMI (Glucose Management Indicator), AGP (Ambulatory Glucose Profile), and Glucose Variability and Energy Expenditure. TIR is an indicator that measures the time blood glucose stays within a target range (e.g., 70-180 mg / dL) and is used to evaluate overall blood glucose control. TAR and TBR evaluate the time blood glucose stays above or below the target range, respectively. Mean Glucose is the average of all blood glucose values over a day or a specific period. SD represents the overall magnitude of blood glucose variability. GMI is an indicator that evaluates long-term blood glucose control similarly to HbA1c. AGP is a profile that visually represents long-term blood glucose patterns. Glucose Variability and Energy Expenditure are indicators mainly related to exercise, metabolic state, and overall lifestyle.

[0079] In this case, the step of generating the user's blood glucose trend prediction information may include: a step of correcting the diabetes-related chronic disease indicators related to the user based on at least some of the user's lifestyle information and the blood glucose time-series information; and a step of generating the user's blood glucose trend prediction information using the corrected diabetes-related chronic disease indicators, the user's lifestyle information, and the blood glucose time-series information.

[0080] In this case, the user terminal may be configured to capture food 700, the blood glucose time-series information acquired by the information providing device may be the user's blood glucose time-series information measured before consuming the food, and the user's blood glucose trend prediction information may be the predicted blood glucose time-series information of the user after consuming the food.

[0081] In this case, the step of generating the personalized service information may include: a step of determining a user-customized index that is a corrected value of at least one of the GI index, GL index, Postprandial Glucose Response, AUC, and MAGE of the food for the user; and a step of generating the user's blood glucose trend prediction information after consuming the food based on the blood glucose time-series information and the user-customized index.

[0082] In this case, the step of generating the personalized service information may include: a step of determining a user-customized GI corrected to the user by the GI of the food; and a step of generating the user's blood glucose trend prediction information after consuming the food based on the blood glucose time-series information and the user-customized GI.

[0083] In this case, the information providing device may be configured to provide postprandial blood glucose time-series information of the user after ingestion of the food, and the processor may be further configured to execute: a step of correcting the user-customized GI based on a difference between the postprandial blood glucose time-series information and the blood glucose trend prediction information.

[0084] In this case, in the step of correcting the user-customized GI, if the blood glucose value of the user included in the postprandial blood glucose time-series information during a predetermined time interval after ingestion of the food is less than the blood glucose value of the user included in the blood glucose trend prediction information, the user-customized GI may be updated by decreasing the value.

[0085] In this case, in the step of correcting the user-customized GI, if the blood glucose value of the user included in the postprandial blood glucose time-series information during a predetermined time interval after ingestion of the food is greater than the blood glucose value of the user included in the blood glucose trend prediction information, the user-customized GI may be updated by increasing the value.

[0086] In this case, the user terminal may be extended reality glasses including an image capturing device, and the step of the extended reality glasses capturing an image of the food may comprise: a step of the user wearing the extended reality glasses and gazing at the food; a step of the user inputting a predetermined voice command into the extended reality glasses; and a step of the extended reality glasses capturing an image of the food in response to the voice command.

[0087] In this case, the step of correcting and updating the user-customized GI may comprise: a step of correcting and updating a correction coefficient related to the user based on a difference between the postprandial blood glucose time-series information and the blood glucose trend prediction information; and a step of correcting the user-customized GI by multiplying the GI of the food by the updated correction coefficient related to the user.

[0088] The blood glucose management system may further comprise a second user terminal configured to measure time-series information on the user's physical activity. In this case, the information providing device is configured to provide postprandial blood glucose time-series information after the user has ingested the food, and the processor is further configured to execute, after the user ingests the food: a step of requesting time-series information on the user's physical activity from the second user terminal or from a second network system (N2) including the second user terminal; a step of receiving the time-series information on the user's physical activity from the second user terminal or the second network system; and a step of correcting the user-customized GI based on the blood glucose trend prediction information, the postprandial blood glucose time-series information, and the time-series information on the user's physical activity.

[0089] According to another aspect of the present invention, a blood glucose management method may be provided, comprising: a step in which a user terminal collects lifestyle information of the user including information about at least one of food, exercise, medication, sleep, and stress; a step in which an information providing device acquires the blood glucose time-series information of the user; a step in which a processor generates personalized service information including at least some or all of explanation data about the user's current health status, explanation data about the user's predicted future health status, and information about actions the user must take to improve health based on the lifestyle information and blood glucose time-series information; and a step in which the user terminal outputs the personalized service information to the user.

[0090] In this case, the step of generating the personalized service information may include: a step in which the user terminal receives an inquiry from the user; a step in which personal information is prepared by retrieving some of the lifestyle information and some of the blood glucose time-series information related to the user's inquiry from a database including the user's lifestyle information and blood glucose time-series information; a step in which augmented information is prepared by combining the personal information with predetermined medical information; and a step in which the personalized service information is generated using the augmented information.

[0091] In this case, the personalized service information may include the user's blood glucose trend prediction information, and the step of generating the personalized service information may include a step of generating the blood glucose trend prediction information of the user using the lifestyle information, the blood glucose time-series information, and the diabetes-related chronic disease indicators related to the user.

[0092] According to the present invention, the user's health condition can be monitored in real time using AR / VR glasses and a CGMS used by the user, and optimal advice related to food intake can be provided to the user.

[0093] According to the present invention, a technology can be provided that allows the user to visually confirm nutritional information such as the name and calories of food in real time when the user wears AR / VR glasses and looks at the food.

[0094] According to the present invention, the current blood glucose condition of the user can be monitored in real time through the CGMS, and a technology for predicting and managing changes in blood glucose before and after food intake can be provided.

[0095] According to the present invention, based on the blood glucose condition of the user measured by the CGMS and the food intake information captured by the AR / VR glasses, a technology can be provided that supports the user's health management by offering personalized exercise and behavioral suggestions (e.g., walking for 30 minutes, maintaining fasting for 2 hours) in metaverse video format.

[0096] FIG. 1 is a conceptual diagram illustrating a continuous blood glucose monitoring system according to an embodiment of the present disclosure.

[0097] FIGS. 2A, 2B, 2C, and 2D are diagrams illustrating an applicator according to an embodiment of the present disclosure.

[0098] FIGS. 3A and 3B illustrate environments in which a personalized blood glucose management system according to an embodiment of the present disclosure is used.

[0099] FIG. 4 illustrates the configuration of a personalized blood glucose management system provided according to one aspect of the present invention and a blood glucose management method using the same.

[0100] FIG. 5 is a flowchart illustrating a blood glucose management method for generating a user-customized GI for a specific food according to an embodiment of the present invention.

[0101] FIG. 6A, FIG. 6B, and FIG. 6C are for explaining the difference between first blood glucose trend prediction information and first postprandial blood glucose time-series information used in an embodiment of the present invention.

[0102] FIG. 7A is provided to aid understanding of a process for updating a user-customized GI for a specific food according to an embodiment of the present invention.

[0103] FIG. 7B is provided to aid understanding of a process for updating a user-customized GI for a specific food according to another embodiment of the present invention.

[0104] FIG. 8 illustrates the configuration of a personalized blood glucose management system and a blood glucose management method using the same according to another aspect of the present invention.

[0105] FIG. 9 illustrates the configuration of a personalized blood glucose management system and a blood glucose management method using the same according to still another aspect of the present invention.

[0106] FIGS. 10A and 10B illustrate specific methods in which a user terminal captures food according to an embodiment of the present invention.

[0107] FIG. 11 illustrates the configuration of a first network system and a second network system used in an embodiment of the present invention.

[0108] FIGS. 12A and 12B illustrate a process of updating a user-customized GI according to an embodiment of the present invention.

[0109] FIGS. 13A and 13B illustrates a process of updating a user-customized GI according to another embodiment of the present invention.

[0110] FIG. 14 illustrates a process of updating a user-customized GI according to still another embodiment of the present invention.

[0111] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the present invention is not limited to the embodiments described in this specification and can be implemented in various other forms. The terminology used in this specification is for the purpose of understanding the embodiments and is not intended to limit the scope of the present invention. Also, singular forms used below are intended to include plural forms unless the context clearly indicates otherwise.

[0112] FIG. 1 is a conceptual diagram illustrating a continuous blood glucose monitoring system according to an embodiment of the present disclosure.

[0113] Referring to FIG. 1, the continuous blood glucose monitoring system according to an embodiment of the present disclosure may include transmitter 110 and mobile device 200.

[0114] Transmitter 110 is attached to the body of user 1, and when attached, one end of the sensor of transmitter 110 may be inserted into the skin to periodically measure blood glucose from the body fluid.

[0115] mobile device 200 may be an electronic device that receives blood glucose information from transmitter 110 and displays the received blood glucose information to the user. For example, mobile device 200 may be an electronic device capable of communicating with transmitter 110, such as a dedicated receiver, smartphone, tablet PC, laptop, medical device, or wearable device. Of course, mobile device 200 is not limited thereto and may include various electronic devices having communication capability and capable of installing programs or applications.

[0116] Transmitter 110 may transmit the periodically measured blood glucose information to mobile device 200 either upon request from mobile device 200 or at preset times. Transmitter 110 and mobile device 200 may be connected via a wired or wireless communication method for data transmission.

[0117] For example, in a wired communication connection, transmitter 110 and mobile device 200 may be connected via at least one communication method among USB (Universal Serial Bus), serial port, Ethernet, or HDMI (High-Definition Multimedia Interface).

[0118] For example, in a wireless communication connection, transmitter 110 and mobile device 200 may be connected via at least one communication method among Bluetooth, Bluetooth Low Energy, infrared communication (IrDA: Infrared Data Association), UWB (Ultra WideBand), WiFi Direct, or NFC (Near Field Communication).

[0119] Here, transmitter 110 may be attached to a part of the body via applicator 100.

[0120] FIGS. 2A, 2B, 2C, and 2D are diagrams illustrating applicator 100 according to an embodiment of the present disclosure.

[0121] FIG. 2A shows a state in which cap 130 is mounted on upper housing 120.

[0122] FIG. 2B shows a state in which cap 130 is detached from upper housing 120.

[0123] Referring to FIG. 2A, applicator 100 may include upper housing 120, a button inserted into and press-fitted to the outer circumferential surface of upper housing 120, and cap 130 which is detachable from upper housing 120.

[0124] Referring to FIG. 2B, when cap 130 of applicator 100 is detached from upper housing 120, a portion of lower housing 140 may be exposed. By detaching cap 130, applicator 100 may become ready for use by the user.

[0125] Transmitter 110 may be provided inside applicator 100. For example, applicator 100 may have a shape with one open surface, and transmitter 110 may be installed in applicator 100 through the open surface. Applicator 100 may operate to discharge transmitter 110 to the outside in response to user operation so that transmitter 110 is attached to a specific body part of user 1.

[0126] When attaching transmitter 110 to a body part (e.g., skin 2) using applicator 100, applicator 100 may include a needle (not shown), a first elastic member (not shown), and a second elastic member (not shown) to insert one end of the sensor of transmitter 110 into the skin. For example, the needle may be formed to surround one end of the sensor. The first elastic member may push the needle and one end of the sensor together into the skin. The second elastic member may pull the needle back from the skin after the sensor end is inserted.

[0127] Specifically, by releasing the compression of the first elastic member arranged in a compressed state inside applicator 100, the needle and the sensor end may be inserted into the skin simultaneously. After insertion, the compression of the second elastic member (not shown) is released to retract only the needle from the skin. In this way, the user may safely and easily attach transmitter 110 to the skin using applicator 100.

[0128] FIG. 2C is a diagram for explaining the operation of attaching the transmitter to skin 2 using the applicator.

[0129] FIG. 2C is a diagram for explaining the operation of separating the applicator from skin 2 after attaching the transmitter.

[0130] Referring to FIG. 2C and FIG. 2D, when attaching transmitter 110 to the body in more detail, the open surface (e.g., lower housing 140) of applicator 100 may be brought into close contact with a specific area of skin 2 with cap 130 removed. In this state, if applicator 100 is activated, transmitter 110 discharged from applicator 100 may be attached to skin 2.

[0131] On the bottom of transmitter 110, one end of the sensor may be disposed and exposed. As applicator 100 is activated, the sensor end may be inserted into skin 2 through a needle provided in applicator 100. Accordingly, transmitter 110 may be attached to skin 2 with the sensor end inserted into it.

[0132] On the skin-contact surface of transmitter 110, an adhesive material (e.g., adhesive tape) may be provided so that transmitter 110 is fixed to skin 2. Therefore, after activating applicator 100, when applicator 100 is separated from skin 2, transmitter 110 may remain attached to skin 2 by the adhesive force of the adhesive material.

[0133] When power is applied to transmitter 110 in the attached state on skin 2, transmitter 110 may be connected to mobile device 200 via a predetermined communication method for data communication. For example, transmitter 110 may transmit the measured blood glucose information to mobile device 200 via a predetermined communication method.

[0134] Although the transmitter 110 of the present disclosure may measure various biometric information such as lactate, ketone, oxygen saturation, carbon dioxide level, heart rate, or blood pressure in addition to blood glucose, the following description assumes that transmitter 110 measures blood glucose as an example of biometric information.

[0135] FIGS. 3A and 3B illustrate an environment in which a personalized blood glucose management system provided according to an embodiment of the present disclosure is used.

[0136] Medical device 10 may be configured to perform bidirectional communication with mobile device 200 using a wireless communication protocol. The wireless communication protocol may be any one of the various wireless communication methods described above, but is not limited thereto.

[0137] mobile device 200 may provide predetermined information or commands to medical device 10.

[0138] As shown in FIG. 3A, mobile device 200 may communicate with service server 300 connected to metropolitan network 500 via wireless mobile communication base station 510.

[0139] Alternatively, as shown in FIG. 3B, mobile device 200 may communicate with service server 300 connected to metropolitan network 500 via WiFi access point 520.

[0140] mobile device 200 may provide information obtained from medical device 10 or information related to medical device 10 to service server 300.

[0141] Although FIGS. 3A and 3B show only one medical device 10 being connected to mobile device 200, multiple medical devices 10 may be communicatively connected to a single mobile device 200.

[0142] In one embodiment, medical device 10 may be transmitter 110 of FIG. 1.

[0143] FIG. 4 illustrates the configuration of a personalized blood glucose management system 3 and a blood glucose management method using the same, according to one aspect of the present invention.

[0144] The blood glucose management system 3 may include an information providing device 800, a user terminal 20, and a processor 9.

[0145] The information providing device 800 may be any one of the devices constituting a CGMS including a CGM device 10 that measures the user's blood glucose. For example, the information providing device 800 may be the CGM device 10 or the mobile device 200. In FIG. 4, for convenience of explanation, an example in which the information providing device 800 is the CGM device 10 is presented. However, the information providing device 800 may alternatively be the mobile device 200, and the mobile device 200 may acquire the user's blood glucose time-series information from the CGM device 10.

[0146] In one embodiment, where the information providing device 800 is the CGM device 10, the user terminal 20 may be the mobile device 200 or the AR / VR glasses 400.

[0147] In another embodiment, where the information providing device 800 is the mobile device 200, the user terminal 20 may be the mobile device 200 itself or the AR / VR glasses 400.

[0148] FIGS. 4 through 7 focus on the example where the user terminal 20 is the AR / VR glasses 400.

[0149] The processor 9 may be included in the user terminal 20 or in the service server 300.

[0150] In the embodiment where the processor 9 is included in the user terminal 20, communication between the information providing device 800 and the processor 9 can be regarded as communication between the information providing device 800 and the user terminal 20. In this case, the steps S100, S140, and S170 shown in FIG. 4 may be considered as steps executed by the processor 9, and also as steps executed by the user terminal 20.

[0151] In the embodiment where the processor 9 is included in the service server 300, communication between the information providing device 800 and the processor 9 can be regarded as communication between the information providing device 800 and the service server 300. In this case, the steps S100, S140, and S170 shown in FIG. 4 may be considered as steps executed by the processor 9, and also as steps executed by the service server 300.

[0152] Hereinafter, in this specification, stating that the processor 9 executes a specific step may mean that the device 20 (user terminal) or 300 (server) including the processor 9 reads and executes an instruction for performing the specific step. The instruction may be recorded in a storage or memory accessible by the device 20 or 300 including the processor 9.

[0153] In step S100, the processor 9 may initialize or update the user-customized GI of a first food 700 for a first user. A specific method for this is described later in FIGS. 5 and 9.

[0154] In step S110, the user terminal 20 may generate a captured image, which is an image obtained by capturing the food 700. In this specification, the captured image refers to both still images and video.

[0155] In step S120, the user terminal 20 may, and generate food information for the first food. For example, if the first food is a fried egg, the user terminal 20 may include information representing the fried egg in the first food information.

[0156] In step S130, the user terminal 20 may transmit the first food information and a predetermined trigger to the processor 9. In this case, meta-information about the first food information may be transmitted together. The meta-information may include various types of information, for example, information representing the first food, the time of capture, the place where the first food was captured, and identification information of the first user intending to consume the food.

[0157] The trigger may refer to a request message that instructs the processor 9 to execute step S140 described later.

[0158] In step S140, the processor 9 may determine the user-customized GI of the first food for the first user as specified by the meta-information.

[0159] For example, in one embodiment, the user-customized GI of the first food may be a standard GI typically assigned to the food. Alternatively, in another embodiment, the user-customized GI may be a GI value modified from the standard GI to reflect the characteristics of the first user. A specific method for determining the modified value is described in detail in FIGS. 5, 7, and 9.

[0160] In step S150, the processor 9 may request blood glucose time-series information of the first user measured before consuming the first food.

[0161] In the embodiment where the processor 9 is included in the service server 300, the request target of the processor 9 for the blood glucose time-series information may be a first network system N1 including the information providing device 800. The first network system N1 may also be referred to as CGMS. The CGMS may be regarded as a kind of network system consisting of one or more devices including the CGM device 10, mobile device 200, AR / VR glasses 400, wireless mobile communication base station 510, WiFi access point 520, and MAN 500. In one embodiment, the information providing device 800 may be any one of the CGM device 10, mobile device 200, or AR / VR glasses 400.

[0162] In the embodiment where the processor 9 is included in the user terminal 20, the request target of the processor 9 for the blood glucose time-series information may be the information providing device 800. In this case, the processor 9 may access the information providing device 800 using a proximity communication means such as WiFi, WiFi-Direct, Bluetooth, NFC, or wired communication via an access point. In one embodiment, the information providing device 800 may be the CGM device 10.

[0163] That is, the processor 9 may request the blood glucose time-series information from the information providing device 800 or the first network system N1 including the information providing device 800.

[0164] In step S160, the processor 9 may receive first blood glucose time-series information of the first user from the information providing device 800 or from the first network system N1 including the information providing device 800.

[0165] In this case, the first blood glucose time-series information may be the blood glucose time-series information of the first user collected before consuming the food 700. Here, blood glucose time-series information may refer to a set of multiple time-tagged blood glucose values measured from the first user.

[0166] In step S170, the processor 9 may generate first blood glucose trend prediction information of the first user after consuming the first food based on the received first blood glucose time-series information and the determined user-customized GI of the first food.

[0167] In a preferred embodiment, the first blood glucose trend prediction information may be time-series data of predicted blood glucose levels.

[0168] That is, after the first user consumes the food 700, how the first user's blood glucose changes over time may be determined in consideration of both the blood glucose time-series information collected before food intake and the determined user-customized GI of the food. The determined result is considered the first blood glucose trend prediction information of the first user.

[0169] The processor 9 may utilize an artificial intelligence model, namely, a blood glucose prediction model, to generate the first blood glucose trend prediction information of the first user.

[0170] An artificial intelligence model, throughout the specification, refers to a set of machine learning algorithms using a layered algorithm structure based on a deep neural network in machine learning technology and cognitive science. For example, the artificial intelligence model may include an input layer receiving an input signal or input data from an external source, an output layer outputting an output signal or input output data in response to the input data, and at least one hidden layer positioned between the input layer and the output layer to receive a signal from the input layer, extract characteristics from the receive signal, and transmit the same to the output layer. The output layer receives a signal or data from the hidden layer and outputs the same to the outside.

[0171] The blood glucose prediction model may be trained using at least one of logging data and data generated using a generative artificial intelligence model. Here, the logging data may refer to the blood glucose time-series information of the first user collected by the transmitter 110 of FIG. 1 or the medical device 10 and GI(s) of various foods. User-customized GI of the various food may be used for training. The generative artificial intelligence model may refer to an artificial intelligence model able to generate or apply text, documents, pictures, or images. Therefore, data generated using the generative artificial intelligence model may refer to data generated using the generative artificial intelligence model in order to train the object specifying model. Accordingly, by using the generative artificial intelligence model, the processor 9 may obtain blood glucose time-series information that are typically difficult to acquire or not usually available as logging data by using the generative artificial intelligence model and train the blood glucose prediction model using the same.

[0172] In step S180, the processor 9 may provide the generated first blood glucose trend prediction information of the first user to the user terminal 20.

[0173] In step S190, the user terminal 20 may display the first blood glucose trend prediction information on a metaverse dashboard.

[0174] To this end, the user terminal 20 may be configured to provide the metaverse to the first user.

[0175] The blood glucose management method illustrated in FIG. 4 may be provided before the first user consumes the food 700. If the first blood glucose trend prediction information displayed to the first user by the user terminal 20 in step S190 includes negative information for the first user's health, the first user may confirm this and replace the food 700 with another type of food and re-execute the blood glucose management method illustrated in FIG. 4. In other words, the first blood glucose trend prediction information displayed to the first user by the user terminal 20 may serve as a motivation to induce a specific action by the first user.

[0176] In one embodiment, if the food 700 includes a plurality of food items, the blood glucose management method illustrated in FIG. 4 may be executed individually and simultaneously for each of the food items. As a result, first blood glucose trend prediction information may be generated for each possible combination of the plurality of food items and displayed on the user terminal 20.

[0177] Even if the blood glucose management method illustrated in FIG. 4 is executed individually and simultaneously for each food item, steps commonly applicable to each food item may be executed only once. For example, if the food 700 includes both a first food and a second food, steps S120, S130, and S140 may be executed independently for the first food and the second food. Also, steps S170 and S190 may be executed independently for each possible combination of the first and second food (e.g., first food only, second food only, and combination of first and second food). However, steps S150 and S160, which provide information to the processor 9, are not dependent on the number of food items included in the food 700, so they may be executed only once.

[0178] For example, if the food 700 includes both a first food and a second food, the metaverse dashboard may display the first blood glucose trend prediction information (Case 1) for the case in which the first user consumes only the first food, the first blood glucose trend prediction information (Case 2) for the case in which the first user consumes only the second food, and the first blood glucose trend prediction information (Case 3) for the case in which the first user consumes both the first and second foods.

[0179] Then, the first user may select the case that does not include negative information for the first user's health among the first blood glucose trend prediction information of Case 1, Case 2, and Case 3, and consume the food corresponding to the selected combination.

[0180] For example, if it is predicted that blood glucose will drop below the reference level before the next meal when consuming only one of the first or second food, and if it is predicted that blood glucose will remain above the reference level before the next meal when consuming both the first and second food, the first user may choose to consume both the first and second foods.

[0181] As another example, if it is predicted that the blood glucose rise trend after the meal is within an acceptable range when consuming only one of the first or second food, and if it is predicted that the blood glucose rise trend is at a health-risking level when consuming both, the first user may choose to consume only one of the first or second foods.

[0182] The food 700 photographed by the user terminal 20 may be the actual food or food set provided to the first user, but it may also be a food menu provided to the first user. The food menu may include multiple food items presented in the form of text and / or sample food images. The user terminal 20 or a server supporting the user terminal 20 may be programmed to analyze the plurality of food menu items presented in the food menu.

[0183] If the food analysis capability of the user terminal 20 is limited, instead of steps S120 and S130, the user terminal 20 may transmit the captured image to the processor 9, and the processor 9 may analyze the captured image, identify the foods included in the image, and generate information for each food item on behalf of the user terminal 20.

[0184] As described above, the blood glucose management method illustrated in FIG. 4 may be provided before the first user consumes the food 700. In contrast, FIG. 5 illustrates a blood glucose management method that is provided after the first user has consumed the food 700.

[0185] FIG. 5 is a flowchart illustrating a blood glucose management method for generating a user-specific glycemic index (GI) for a specific food item according to an embodiment of the present invention.

[0186] In step S310, the first user may consume the food 700. This may be an action that occurs after step S170 of FIG. 4.

[0187] In step S320, the user terminal 20 may confirm that the first user has consumed the food 700. This may be achieved, for example, by the first user providing a consumption completion input through a user interface provided by the user terminal 20.

[0188] At this time, if the food 700 includes both a first food and a second food, information about which of the first and second foods were actually consumed by the first user may be provided by the user to the processor 9. That is, the processor 9 may be provided with information regarding the food actually consumed by the first user as realistically as possible.

[0189] In step S330, the user terminal 20 may transmit to the processor 9 information that an event of food 700 consumption completion has occurred.

[0190] In step S340, in response to step S330, the processor 9 may request blood glucose time-series information from the information providing device 800 or from a first network system N1 including the information providing device 800.

[0191] In step S350, the processor 9 may receive post-ingestion blood glucose time-series information from the information providing device 800 or the first network system N1 including the information providing device 800.

[0192] The post-ingestion blood glucose time-series information may include the continuous blood glucose information of the first user collected by the CGM device 10 during the time interval after the first user consumed the food 700.

[0193] In step S360, the processor 9 may update the user-specific GI for the first food for the first user based on the difference between the first blood glucose trend prediction information generated in step S170 of FIG. 4 and the post-ingestion blood glucose time-series information.

[0194] At this time, if the food 700 includes both the first and second foods, the first blood glucose trend prediction information generated in step S170 of FIG. 4 may include various consumption cases. Accordingly, if the information acquired in step S330 includes the combination of foods that the first user actually consumed, the corresponding first blood glucose trend prediction information may be used in step S360. For example, if the first user consumed only the first food, the processor may use the first blood glucose trend prediction information (Case 1) corresponding to Case 1 among the three aforementioned cases.

[0195] According to an embodiment, the processor 9 may utilize an artificial intelligence model, namely, a GI user-customization model, to update the user-customized GI.

[0196] The GI user-customization model may be trained by using information on the consumed food, the first blood glucose trend prediction information generated in step S170 of FIG. 4, and the continuous blood glucose information of the first user collected by the CGM device 10 during the time interval before / after the first user consumed the food 700 (i.e., the post-ingestion blood glucose time-series information). The training of the GI user-customization model may be performed by using information obtained by repeating the process in FIG. 5.

[0197] In one embodiment, step S360 corresponds to step S100 of FIG. 4.

[0198] FIG. 6A, FIG. 6B, and FIG. 6C illustrate the difference between the first blood glucose trend prediction information and the first post-ingestion blood glucose time-series information mentioned in step S360 of FIG. 5.

[0199] In FIG. 6A, FIG. 6B, and FIG. 6C, the horizontal axis represents time, and the vertical axis represents the blood glucose value of the first user.

[0200] In FIG. 6A, FIG. 6B, and FIG. 6C, reference numeral 361 denotes the first blood glucose time-series information 361, which is the actual blood glucose information of the first user before ingesting the food 700, reference numeral 362 denotes the first post-ingestion blood glucose time-series information 362, which is the actual blood glucose information of the first user after ingesting the food 700, and reference numeral 372 denotes the first blood glucose trend prediction information 372 of the first user generated by the processor 9 in step S170 of FIG. 4. The first blood glucose trend prediction information 372 of the first user is not actual blood glucose information after ingesting the food 700, but rather information predicted by the processor 9.

[0201] FIG. 6A illustrates a case where the first post-ingestion blood glucose time-series information 362 and the first blood glucose trend prediction information 372 substantially match during a determination period from a predetermined first time point t01 to a second time point t02 after the ingestion time point t0 of the first food. In this case, there is no need to update the already set user-specific GI for the first food. Here, the term "substantially match" may mean that the difference between the integral value of the data representing the first post-ingestion blood glucose time-series information 362 and the integral value of the data representing the first blood glucose trend prediction information 372 is substantially zero during the determination period.

[0202] FIG. 6B illustrates a case where the first post-ingestion blood glucose time-series information 362 has a substantially greater value than the first blood glucose trend prediction information 372 during a determination period from a predetermined first time point t01 to a second time point t02 after the ingestion time point t0 of the first food. In this case, it may be determined that the already set user-specific GI for the first food has been set to a somewhat lower value for the first user. Accordingly, the already set user-specific GI for the first food may be corrected and updated to a higher value. Here, the term "substantially greater value" may mean that the integral value of the data representing the first post-ingestion blood glucose time-series information 362 is greater than the integral value of the data representing the first blood glucose trend prediction information 372 during the determination period.

[0203] FIG. 6C illustrates a case where the first post-ingestion blood glucose time-series information 362 has a substantially smaller value than the first blood glucose trend prediction information 372 during a determination period from a predetermined first time point t01 to a second time point t02 after the ingestion time point t0 of the first food. In this case, it may be determined that the already set user-specific GI for the first food has been set to a somewhat higher value for the first user. Accordingly, the already set user-specific GI for the first food may be corrected and updated to a lower value. Here, the term "substantially smaller value" may mean that the integral value of the data representing the first post-ingestion blood glucose time-series information 362 is smaller than the integral value of the data representing the first blood glucose trend prediction information 372 during the determination period.

[0204] The updated value may be used the next time the blood glucose management method presented in FIG. 4 is executed again. Step S100 presented in FIG. 4 refers to this update process.

[0205] FIG. 6A, FIG. 6B, and FIG. 6C conceptualize and illustrate the first blood glucose time-series information 361, the first post-ingestion blood glucose time-series information 362, and the first blood glucose trend prediction information 372 to aid in understanding the present invention. In reality, these pieces of information may vary over time with a shorter cycle than that shown in FIG. 6A, FIG. 6B, and FIG. 6C.

[0206] FIG. 7A is provided to aid in understanding the process of updating a user-specific GI for a particular food according to an embodiment of the present invention.

[0207] Processor 9 may access a storage or memory in which a table TB1 storing values related to user-specific GIs for each food and user is stored.

[0208] Each column of table TB1 shown in FIG. 7A represents a different food, and each row represents a different user.

[0209] Hereinafter, the description will be based on food 1 and the first user shown in table TB1.

[0210] When the first user is newly registered in table TB1, the user-specific GI for food 1 may be initialized to a reference GI. The reference GI refers to a GI that is generally recognized. GIs may be defined per food.

[0211] For the sake of explanation in FIG. 7A, a specific food is presented as representing a specific ingredient. However, in actual implementation examples, a specific food may be defined as a specific dish made by mixing various ingredients. Since there are various ways to define a specific food, the present invention is not necessarily limited by the specific definition of "food".

[0212] In FIG. 7A, at t = t0, the user-specific GI for food 1 is initialized to a value of 58, which is the same as the reference GI. This corresponds to the "initialization" presented in step S100 of FIG. 4.

[0213] In FIG. 7A, t = t1 may refer to the time immediately after the blood glucose management method shown in FIGS. 4 and 5 is executed once. At this time, by step S360 of FIG. 5, the user-specific GI for food 1, which was set at t = t0, may be corrected and updated to a new value. That is, at t = t1, the user-specific GI for food 1 is updated from 58 to 60.

[0214] In FIG. 7A, t = t2 may refer to the time immediately after the blood glucose management method shown in FIGS. 4 and 5 is executed again. At this time, by step S360 of FIG. 5, the user-specific GI for food 1, which was set at t = t1, may be corrected and updated to a new value. That is, at t = t2, the user-specific GI for food 1 is updated from 60 to 59.

[0215] Each user may have a different sensitivity to nutrients (e.g., carbohydrates) that affect blood glucose. These nutrients may commonly act on all foods (dishes, ingredients). Therefore, if the user-specific GI for food 1 is updated, the user-specific GIs for other foods may also be updated based on that.

[0216] FIG. 7B is provided to aid in understanding the process of updating a user-specific GI for a particular food according to another embodiment of the present invention.

[0217] Processor 9 may access a storage or memory in which a table TB1 storing correction coefficients for user-specific GIs per food and per user is stored.

[0218] Each row of table TB1 shown in FIG. 7B represents a different user.

[0219] Hereinafter, the description will be based on the first user shown in table TB1.

[0220] When the first user is newly registered in table TB1, the correction coefficient for the first user may be initialized to 100%.

[0221] In FIG. 7B, at t = t0, the correction coefficient for the first user is initialized to 100%. This corresponds to the "initialization" presented in step S100 of FIG. 4.

[0222] In FIG. 7B, t = t1 may refer to the time immediately after the blood glucose management method shown in FIGS. 4 and 5 is executed once. At this time, by step S360 of FIG. 5, the correction coefficient for the first user, which was set at t = t0, may be corrected and updated to a new value. That is, at t = t1, the correction coefficient for the first user is updated from 100% to 91%.

[0223] In FIG. 7B, t = t2 may refer to the time immediately after the blood glucose management method shown in FIGS. 4 and 5 is executed again. At this time, by step S360 of FIG. 5, the correction coefficient for the first user, which was set at t = t1, may be corrected and updated to a new value. That is, at t = t2, the correction coefficient for the first user is updated from 91% to 93%.

[0224] At each decision point of processor 9, the user-specific GI for a specific food for the first user may be determined by multiplying the reference GI for that food by the correction coefficient for the first user. Therefore, at t = t0, the user-specific GI for food 1 is determined as 58, which is the value obtained by multiplying the reference GI for food 1 (58) by 100%; at t = t1, it is determined as 52.8, which is the value obtained by multiplying 58 by 91%; and at t = t2, it is determined as 53.9, which is the value obtained by multiplying 58 by 93%.

[0225] FIG. 8 illustrates the configuration of a personalized blood glucose management system and a method of managing blood glucose using the same according to another aspect of the present invention.

[0226] Steps S100, S110, S120, S130, S140, S150, S160, and S170 shown in FIG. 8 are the same as those described in FIG. 4.

[0227] In step S210, the processor (9) may generate a first type of exercise and schedule that can affect (i.e., change) the previously generated first blood glucose trend prediction information.

[0228] In step S220, the processor (9) may provide the generated first type of exercise and schedule to the user terminal (20).

[0229] In step S230, the user terminal (20) may display the first type of exercise and schedule on a metaverse dashboard.

[0230] The blood glucose management method shown in FIG. 8 may be executed in combination with the method shown in FIG. 4.

[0231] According to an embodiment, the user terminal 20 or the server 300 may store in a database a list of various exercises and information of each exercise, for example, effectiveness such as information on calorie consumption per unit time or according to unit count. According to an embodiment, in step 210, the processor 9 may choose one of the exercises and calculate an amount of exercise, such as an amount of time or counts for the exercise, to reduce the predicted blood glucose level or trend to a predetermined level. The processor 9 may choose one of the exercises from the database based on a preset preference of the user with respect to the exercises.

[0232] According to an embodiment, the processor 9 may utilize an artificial intelligence model, namely, an exercise recommendation model, to choose and calculate the amount of exercise. The exercise recommendation model may be trained using the continuous blood glucose information of the first user collected by the CGM device 10 before / during / after the exercise and information on the exercise. The processor 9 may utilize the exercise recommendation model to identify the most efficient type of exercise in terms of time and counts and recommend the same.

[0233] FIG. 9 illustrates the configuration of a personalized blood glucose management system provided according to another aspect of the present invention and a blood glucose management method using the same.

[0234] The blood glucose management method shown in FIG. 9 may be executed in combination with the method shown in FIG. 5.

[0235] Steps S310, S320, S330, S340, and S350 shown in FIG. 9 are the same as those presented in FIG. 5.

[0236] In step S410, processor 9 may request time-series data of the physical activity (exercise amount) of the first user.

[0237] In an embodiment in which processor 9 is included in service server 300, the target from which processor 9 requests the first user's time-series activity data may be a second network system N2 that includes a second user terminal 600. The second network system N2 may be considered a type of network system composed of one or more devices selected from the group consisting of the second user terminal 600, mobile device 200, wireless mobile communication base station 510, WiFi access point 520, and MAN 500. The second user terminal 600 may comprises a sensor that detects and calculates physical activities and biological status of the user, such as walk distances, activity time, heart rate, calory consumption. The user terminal 600 may a wearable device such as a smart watch, a smart ring.

[0238] In another embodiment in which processor 9 is included in user terminal 20, the target from which processor 9 requests the time-series activity data may be the second user terminal 600. In this case, processor 9 may access the second user terminal 600 directly using a short-range communication method such as WiFi-Direct, Bluetooth, NFC, or wired communication.

[0239] That is, processor 9 may request the time-series activity data from the second user terminal 600 or from the second network system N2 including the second user terminal 600.

[0240] In step S420, processor 9 may receive first activity time-series data related to the physical activity of the first user from the second user terminal 600 or from the second network system N2 including the second user terminal 600.

[0241] The first activity time-series data may relate to the physical activity of the first user after the user has ingested food 700.

[0242] The second user terminal 600 may be, for example, a smart watch or smartphone capable of collecting various physical activity information. However, the present invention is not limited to such examples.

[0243] In step S430, processor 9 may update the user-specific GI for the first user and the first food item based on the first blood glucose trend prediction information, the first postprandial blood glucose time-series data, and the first physical activity time-series data.

[0244] In step S430, the process 9 may utilize the GI user-customization model to update the user-customized GI, as similarly described in reference to FIG. 5. The GI user-customization model may be trained by using information on the consumed food, the first blood glucose trend prediction information generated in step S170 of FIG. 4, the continuous blood glucose information of the first user collected by the CGM device 10 during the time interval after the first user consumed the food 700 (i.e., the post-ingestion blood glucose time-series information), and the first activity time-series data. The training of the GI user-customization model may be performed by using information obtained by repeating the process in FIG. 9.

[0245] In one embodiment, step S380 corresponds to step S100 of FIG. 4.

[0246] FIG. 10 illustrates a specific example of how user terminal 20 captures an image of food 700.

[0247] FIG. 10A illustrates a case in which the user terminal 20 is a mobile device 200 such as a smartphone. In this case, the first user may operate the mobile device 200 by hand to capture an image of the food 700.

[0248] FIG. 10B illustrates a case in which the user terminal 20 is AR / VR glasses 400. In this case, the first user may capture an image of the food 700 by (S111) wearing the AR / VR glasses 400 and gazing at the food 700, (S112) issuing a voice command to trigger the capture, and (S113) having the AR / VR glasses 400 perform the capture in response to the voice command.

[0249] FIG. 11 illustrates the configuration of the aforementioned first network system (N1) and second network system (N2). The first network system (N1) and second network system (N2) may be configured to include one or more of the following: a WiFi Direct-enabled device, a Metropolitan Area Network (500), a Bluetooth-enabled device (530), AR / VR glasses (400), a mobile device (200), a wireless mobile communication base station (510), and a WiFi access point (520). The network entities that may be included in the first network system (N1) and the second network system (N2) are not limited to those listed above.

[0250] Any of the components described above may be included in the first network system (N1), as long as the structure can support a communication connection between the information providing device (800) and the processor (9).

[0251] Likewise, any of the components described above may be included in the second network system (N2), as long as the structure can support a communication connection between the second user terminal (600) and the processor (9).

[0252] FIG. 12 illustrates a process for updating a user-specific GI according to an embodiment of the present invention.

[0253] In one embodiment, in FIG. 12A, the horizontal axis represents time, and GI_user1 represents the user-specific GI of the first user. GI_user1 may represent the user-specific GI of the first user for a particular food item. As shown in FIG. 12A, at the first time point (t1), second time point (t2), and third time point (t3), the user-specific GI of the first user (GI_user1) may be updated to values G1, G2, and G3, respectively, based on one or more of the blood glucose time-series data (361), postprandial blood glucose time-series data (362), and blood glucose trend prediction data (372). Once updated, each value may be maintained until the next update time point.

[0254] In another embodiment, in FIG. 12B, the horizontal axis also represents time, and GI_cal%_user1 may represent a correction rate of the GI value for the first user to be used in generating the user-specific GI. As shown in FIG. 12B, at time points t1, t2, and t3, the GI correction rate for the first user may be updated to values Gcal%_1, Gcal%_2, and Gcal%_3, respectively, based on one or more of the blood glucose time-series data (361), postprandial blood glucose time-series data (362), and blood glucose trend prediction data (372). Once updated, each value may be maintained until the next update time point.

[0255] In this case, the user-specific GI of the first user for a particular food may be determined and used as a value obtained by multiplying the standard GI of the particular food by the GI correction rate (GI_cal%_user1) of the first user. The GI correction rate (GI_cal%_user1) of the first user may, for example, range from 70% to 130%. This is merely an example and the present invention is not limited thereto.

[0256] The GI correction rate of the user may also be referred to as a GI correction parameter of the user.

[0257] FIG. 13 illustrates a process of updating a user-specific GI according to another embodiment of the present invention.

[0258] The process shown in FIG. 13 corresponds to the process shown in FIG. 12A.

[0259] Referring to FIG. 13A, in Step 1, at the first time point t1, the user-specific GI (GI_user1) of the first user is determined as G1. In Step 2, at the second time point t2, the user-specific GI (GI_user1) of the first user is determined as G2 based on one or more of the blood glucose time-series information (361), postprandial blood glucose time-series information (362), and blood glucose trend prediction information (372). However, in the present embodiment, the value G2 is not used as-is; instead, it is corrected and updated through Step 3 before being used. In Step 3, at the second time point t2, the user-specific GI (GI_user1) of the first user is updated as a weighted sum of the generated G2 and the past confirmed value G1. The weight for G1 may be denoted as wp and the weight for G2 may be denoted as wc.

[0260] FIG. 13B illustrates that the above-described process related to FIG. 13A may likewise be performed at the third time point t3, which follows the second time point.

[0261] Referring to FIG. 13B, in Step 1, at the second time point t2, the user-specific GI (GI_user1) of the first user is determined as G2. In Step 2, at the third time point t3, the user-specific GI (GI_user1) of the first user is determined as G3 based on one or more of the blood glucose time-series information (361), postprandial blood glucose time-series information (362), and blood glucose trend prediction information (372). However, in the present embodiment, the value G3 is not used as-is; instead, it is corrected and updated through Step 3 before being used. In Step 3, at the third time point t3, the user-specific GI (GI_user1) of the first user is updated as a weighted sum of the generated G3 and the previously confirmed value G2. The weight for G2 may be denoted as wp and the weight for G3 may be denoted as wc.

[0262] As such, in one embodiment of the present invention, the processor may determine the current user-specific GI using a predetermined determination routine. The determination routine may be, for example, a routine for calculating the user-specific GI using one or more of the aforementioned blood glucose time-series information (361), postprandial blood glucose time-series information (362), and blood glucose trend prediction information (372). The processor may retrieve the previous user-specific GI generated earlier from a memory or storage using the determination routine. The processor may then update the current user-specific GI as a result of a weighted sum operation of the current user-specific GI and the previous user-specific GI. The processor may generate the blood glucose trend prediction information after the intake of the specific food based on the updated current user-specific GI.

[0263] FIG. 14 illustrates a process of updating a user-specific GI according to another embodiment of the present invention.

[0264] The process shown in FIG. 14 corresponds to the process shown in FIG. 12B.

[0265] Referring to FIG. 14, in Step 1, at the first time point t1, the GI value correction ratio (GIcal%_user1) of the first user for a specific food is determined as Gcal%1. In Step 2, at the second time point t2, the GI value correction ratio (GIcal%_user1) of the first user is determined as Gcal%2 based on one or more of the blood glucose time-series information (361), postprandial blood glucose time-series information (362), and blood glucose trend prediction information (372). However, in the present embodiment, the value Gcal%2 is not used as-is; instead, it is corrected and updated through Step 3 before being used. In Step 3, at the second time point t2, the GI value correction ratio (GIcal%_user1) of the first user is updated as a weighted sum of the generated Gcal%2 and the previously confirmed value Gcal%1. The weight for Gcal%1 may be denoted as wp and the weight for Gcal%2 may be denoted as wc.

[0266] As such, in one embodiment of the present invention, the processor may determine a current user GI correction ratio using a predetermined determination routine. The determination routine may be a routine for calculating a user's GI correction ratio using one or more of the blood glucose time-series information (361), postprandial blood glucose time-series information (362), and blood glucose trend prediction information (372) as described above. The processor may retrieve a previously generated user GI correction ratio from memory or storage using the determination routine. The processor may then update the current user GI correction ratio by performing a weighted sum calculation of the current user GI correction ratio and the previously generated user GI correction ratio. The processor may generate a user-specific GI for a specific food by multiplying the updated current user GI correction ratio by a standard GI of the specific food. The processor may generate blood glucose trend prediction information after intake of the specific food using the generated user-specific GI.

[0267] The AR / VR glasses described above in this specification may also be referred to as extended reality (XR) glasses. Extended reality (XR) glasses are wearable display devices designed to implement augmented reality (AR), virtual reality (VR), or mixed reality (MR) that lies between the two. The XR glasses may include a display module, optical system, camera and sensors, processor and computing unit, input and control system, battery and power management unit, audio system, and network connectivity and communication unit.

[0268] The display module may be a transparent display that overlays digital information (virtual images) without blocking the user's view. Graphics may be overlaid on the physical world or projected onto transparent lenses or a viewing window using micro-projectors.

[0269] The optical system may include an optical waveguide that adjusts light through lenses to present virtual images at a specific focal length, and reflective or holographic lenses that naturally deliver virtual content to the user's eyes.

[0270] The camera and sensors may include: external cameras that recognize the real environment and overlay virtual objects or track the user's gaze; depth sensors that scan 3D space and detect the distance and shape of objects; IMU (Inertial Measurement Unit) components such as accelerometers, gyroscopes, and compasses that track head movements and positions; and eye-tracking sensors that detect eye movements.

[0271] The processor and computing unit may include a chipset such as a SoC (System on Chip) for data processing and graphics rendering, and an AI processor that analyzes user and environmental data to support natural interactions.

[0272] The input and control system may include: a voice control system for voice input commands; touchpads or buttons on the side of the device for physical control; and a gesture recognition module for detecting hand or body movements to execute commands.

[0273] The battery and power management unit may include a compact battery optimized for lightweight and extended use.

[0274] The audio system may include a microphone for voice command input.

[0275] The network connectivity and communication unit may include Wi-Fi, Bluetooth modules, and 5G / 4G LTE communication modules for linking with CGMS devices, smartphones, or cloud servers and enabling real-time data transmission and high-speed internet.

[0276] The XR glasses provided according to one embodiment of the present invention may be designed to integrate various functions to maximize user convenience and immersion. These glasses may be equipped with wireless communication features such as Bluetooth and Wi-Fi to easily connect to other devices, and support voice input and output through a microphone and speaker. They may offer intuitive user interfaces through touch, motion detection, vibration, and haptic technology. They may also have high-resolution built-in cameras to recognize or capture environments and objects, and visualize extended reality content in real time through the display.

[0277] According to one embodiment of the present invention, the XR glasses may provide current CGM values and trend information via voice or screen simply by the user wearing the XR glasses and looking at the CGM device.

[0278] The XR glasses may notify the user through voice, screen, vibration, or other means when an alarm condition or predictive alert occurs.

[0279] The XR glasses may offer personalized guidance and recommendations based on current CGM data and health information, when the user gazes at food, exercise, or medication for a certain period or provides additional touch or voice input.

[0280] The XR glasses may also recommend meals or exercise before meals or at certain times, even without user input, and provide guidance via voice or screen while allowing the user to choose a rejection option.

[0281] When the user issues a voice command such as "Tell me my current blood glucose," the XR glasses may provide the current CGM information (value, trend, comments, etc.) via voice.

[0282] When the user inputs food or exercise-related information, the XR glasses may integrate the input with the current CGM data to deliver personalized guidance via voice.

[0283] The XR glasses may initially provide blood glucose change predictions, GI and GL indices for food, exercise, sleep, and medication based on general data, then gradually personalize the information by learning from stored data.

[0284] The XR glasses may automatically perform calibration when a blood glucose measurement by blood sampling is taken while wearing the CGM device, if the value meets certain calibration criteria.

[0285] The XR glasses may provide information such as recommended foods, exercises, nearby restaurants, gyms, and contact information through the display.

[0286] They may also allow the user to easily configure key functions such as alarm thresholds and times.

[0287] Alarm importance can be gradually increased and delivered to the user via vibration, voice, and visual cues.

[0288] In one embodiment, the notification may be provided in the form of vibration, voice, image, or text. User terminal 20 may include a vibration module such as a haptic actuator. The haptic actuator may include a vibration motor, an eccentric rotating mass (ERM) actuator, or a linear resonant actuator (LRA). The vibration module may generate different vibrations depending on the notification, by changing the strength, pattern, and / or length of the vibration. For example, as the acquired blood glucose level or the magnitude of the change exceeds a predetermined value, electronic device 200 may modify the notification to make it more prominent. For example, the vibration module may generate stronger vibration.

[0289] The user may check battery life, sensor status, etc., periodically or immediately upon receiving an alarm.

[0290] If the sensor's lifespan is about to end, the XR glasses may automatically prompt the user to purchase a replacement and proceed with the purchase upon user approval.

[0291] The XR glasses may judge and deliver useful health-related information to the user in real time through the built-in camera.

[0292] The XR glasses may support efficient health management without a smartphone and enhance user adherence to health management.

[0293] The present invention may also include various advanced technologies for user health management. For example, technologies that search past similar images based on the currently input image (food, exercise, etc.), match related blood glucose information, and provide predictive results; intuitive data visualization that overlays blood glucose graphs (actual and predicted) and health-related information such as food, exercise, sleep, and medication on the display; personalized blood glucose modeling and prediction algorithms to offer user-tailored health information; and shape recognition and motion technologies that recognize user behavior and environment to deliver more sophisticated services.

[0294] Using the above-described embodiments of the present invention, those skilled in the art may make various modifications and changes without departing from the essential characteristics of the present invention. The contents of each claim in the claims may be combined with other claims not in a citation relationship, to the extent that such combination can be understood through this specification.

Claims

1.A blood glucose management system comprising:a user terminal configured to collect lifestyle information of a user, the lifestyle information including information regarding at least one of food intake, exercise, medication, sleep, and stress;an information providing device configured to acquire blood glucose time-series information of the user; anda processor configured to generate personalized service information including at least some or all of: description data regarding a current health state of the user, description data regarding a predicted future health state of the user, and information regarding actions to be performed by the user for enhancement of the user's health, based on the lifestyle information and the blood glucose time-series information of the user;wherein the user terminal is configured to output the personalized service information to the user.2.The blood glucose management system of claim 1,further comprising a storage storing a database including the lifestyle information and the blood glucose time-series information of the user,wherein the user terminal is configured to receive a query from the user, andwherein the generating of the personalized service information comprises:preparing personal information obtained by retrieving, from the database, a portion of the lifestyle information and a portion of the blood glucose time-series information associated with the query;preparing augmented information by combining predetermined medical information with the personal information; andgenerating the personalized service information using the augmented information.3.The blood glucose management system of claim 1,wherein the personalized service information includes blood glucose trend prediction information of the user, andwherein the generating of the personalized service information comprises generating the blood glucose trend prediction information of the user using the lifestyle information, the blood glucose time-series information, and a diabetes-related chronic disease index related to the user.4.The blood glucose management system of claim 3,wherein the diabetes-related chronic disease index is any one of: a glycemic index (GI), a glycemic load (GL), time in range (TIR), time above range (TAR), time below range (TBR), glucose variability, mean glucose, standard deviation (SD), glucose risk index (GRI), hyperglycemia risk, hypoglycemia risk, ambulatory glucose profile (AGP), area under the curve (AUC), mean amplitude of glycemic excursions (MAGE), glucose management indicator (GMI), lability index, low blood glucose index, high blood glucose index, glucose variability and energy expenditure, and postprandial glucose response.5.The blood glucose management system of claim 3,wherein the generating of the blood glucose trend prediction information comprises:correcting the diabetes-related chronic disease index based on at least part of the lifestyle information and the blood glucose time-series information of the user; andgenerating the blood glucose trend prediction information using the lifestyle information, the blood glucose time-series information, and the corrected diabetes-related chronic disease index of the user.6.The blood glucose management system of claim 4,wherein the user terminal is configured to capture an image of food,wherein the blood glucose time-series information acquired by the information providing device is blood glucose time-series information of the user before the user ingests the food, andwherein the blood glucose trend prediction information of the user is predicted blood glucose time-series information of the user after ingestion of the food.7.The blood glucose management system of claim 6,wherein the generating of the personalized service information comprises:determining a user-customized index, which is a value obtained by correcting, for the user, at least one of the GI, GL, postprandial glucose response, AUC, and MAGE for the food; andgenerating the blood glucose trend prediction information of the user after ingestion of the food, based on the blood glucose time-series information and the user-customized index.8.The blood glucose management system of claim 6,wherein the generating of the personalized service information comprises:determining a user-customized GI by correcting the GI of the food for the user; andgenerating the blood glucose trend prediction information of the user after ingestion of the food, based on the blood glucose time-series information and the user-customized GI.9.The blood glucose management system of claim 8,wherein the information providing device is a device included in a continuous glucose monitoring system (CGMS) configured to measure blood glucose of the user.10.The blood glucose management system of claim 8,wherein the information providing device is configured to provide postprandial blood glucose time-series information of the user after ingestion of the food, andwherein the processor is further configured to execute:a step of correcting the user-customized GI based on a difference between the postprandial blood glucose time-series information and the blood glucose trend prediction information.11.The blood glucose management system of claim 8,wherein the processor is further configured to execute, between a step of determining the user-customized GI and a step of generating the blood glucose trend prediction information of the user:a step of requesting the blood glucose time-series information from the information providing device or from a first network system (N1) including the information providing device; anda step of receiving the blood glucose time-series information from the information providing device or the first network system.12.The blood glucose management system of claim 8,wherein the processor is further configured to execute, between a time point after the user completes ingestion of the food and a step of correcting the user-customized GI:a step of requesting postprandial blood glucose time-series information from the information providing device or from a first network system (N1) including the information providing device; anda step of receiving the postprandial blood glucose time-series information from the information providing device or the first network system.13.The blood glucose management system of claim 8,wherein the processor is included in the user terminal,and the user terminal is configured to acquire the blood glucose time-series information by wired or short-range wireless communication with the information providing device.14.The blood glucose management system of claim 8,further comprising a service server,wherein the processor is included in the service server,and the server is configured to acquire the blood glucose time-series information from a first network system (N1) including the information providing device.15.A blood glucose management method comprising:a step of a user terminal collecting lifestyle information of a user including information related to at least one of food, exercise, medication, sleep, and stress;a step of an information providing device acquiring blood glucose time-series information of the user;a step of a processor generating personalized service information including at least a portion or all of descriptive data about a current health status of the user, descriptive data about a predicted future health status of the user, and information on actions to be performed by the user for improving the user's health, based on the lifestyle information and the blood glucose time-series information of the user; anda step of the user terminal outputting the personalized service information to the user.

Images