Electronic device for managing movement and alarm of diabetic patient based on smart ring and method oepration thereof

Abstract

According to various embodiments, an electronic device for managing movement and alarms of a diabetic patient based on a smart ring comprises: at least one smart ring installed on the diabetic patient; memory; a communication interface; and a processor; The processor includes, through the at least one smart ring, at least one diabetic data from the diabetic patient, inputs the at least one diabetic data into a prediction model to determine diabetic patient prediction data, and if it is determined that the diabetic patient prediction data exceeds a preset first threshold value, determines that the diabetic patient requires attention, and is configured to transmit, through the communication interface, the diabetic patient prediction data determined to exceed the first threshold value and the first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, and the prediction model is learned based on a plurality of diabetic data obtained from a plurality of diabetic patients, a plurality of diabetic patient prediction data output from a plurality of diabetic patients, data determined that the plurality of diabetic patients are being managed normally, data determined that the plurality of diabetic patients require attention and need to be monitored, and data determined that the plurality of diabetic patients have a high probability of deterioration and require emergency measures.

Description

Technology Field

[0001] Various embodiments of the present invention relate to an electronic device for managing movement and alarms of diabetic patients based on a smart ring and a method for operating the same. Background Technology

[0002] Recently, modern society has seen significant changes in people's lifestyles due to urbanization and technological advancements. These changes have led to an increased incidence of adult diseases, including diabetes, and various studies and experiments have been conducted to treat them. In particular, recent research has highlighted the need for addressing the risks of diabetes, its prevention, and the management of diabetic foot after its onset.

[0003] However, conventionally, there is a problem in that blood sugar levels increase abnormally upon the onset of diabetes, necessitating a reduction, and that diabetes requires continuous management, including a balanced diet, consistent exercise, and weight control, rather than a complete cure.

[0004] In addition, while diabetic foot disease, which is one of the complications that occur when diabetes develops, can be prevented through proper management, there is a problem that if diabetic foot disease is left untreated, it may lead to infection, ulcers, and the need for amputation treatment.

[0005] Therefore, there is a need for technology to manage a user's feet so that the user can prevent and manage diabetic foot disease based on at least one biosignal data acquired from the user's external electronic device. Prior art literature

[0006] Korean Patent Publication No. 10-2458177 (Oct. 19, 2022) Korean Patent Publication No. 10-1964144 (March 26, 2019) The problem to be solved

[0007] Accordingly, the present embodiment may provide an electronic device and a method of operating the same, which inputs data acquired from a smart ring installed on a diabetic patient into a prediction model to check the patient's condition based on the determined prediction data, and provides data to an expert for rapid response while performing an alarm only in cases of caution and / or severe conditions. means of solving the problem

[0008] According to various embodiments, an electronic device for managing movement and alarms of a diabetic patient based on a smart ring comprises: at least one smart ring installed on the diabetic patient; memory; a communication interface; and a processor; The processor includes, through the at least one smart ring, at least one diabetic data from the diabetic patient, inputs the at least one diabetic data into a prediction model to determine diabetic patient prediction data, and if it is determined that the diabetic patient prediction data exceeds a preset first threshold value, determines that the diabetic patient requires attention, and is configured to transmit, through the communication interface, the diabetic patient prediction data determined to exceed the first threshold value and the first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, and the prediction model is learned based on a plurality of diabetic data obtained from a plurality of diabetic patients, a plurality of diabetic patient prediction data output from a plurality of diabetic patients, data determined that the plurality of diabetic patients are being managed normally, data determined that the plurality of diabetic patients require attention and need to be monitored, and data determined that the plurality of diabetic patients have a high probability of deterioration and require emergency measures.

[0009] According to various other embodiments, in a method for operating an electronic device for managing the movement and alarm of a diabetic patient based on a smart ring, the method comprises acquiring at least one diabetic data from the diabetic patient through at least one smart ring installed on the diabetic patient, inputting the at least one diabetic data into a prediction model through a processor to determine diabetic patient prediction data, determining through the processor that if the diabetic patient prediction data is determined to exceed a preset first threshold value, the diabetic patient requires attention, and transmitting, through a communication interface, the diabetic patient prediction data determined to exceed the first threshold value and first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, wherein the prediction model comprises a plurality of diabetic data acquired from a plurality of diabetic patients, a plurality of diabetic patient prediction data output from a plurality of diabetic patients, data determined to indicate that the plurality of diabetic patients are being managed normally, data determined to indicate that the plurality of diabetic patients require attention and observation of the progress, and data determined to indicate that the plurality of diabetic patients have a high probability of deterioration and require emergency measures. It is learned based on data. Effects of the invention

[0010] An electronic device according to one embodiment has the advantage of being able to easily determine diabetic patient prediction data by inputting at least one diabetic data obtained through a smart ring into a prediction model, easily predict the patient's condition by reviewing the diabetic patient prediction data, and, only when the patient's condition is determined to be in a critical and / or serious state based on the diabetic patient prediction data, transmit an alarm and / or the diabetic patient prediction data to the outside to perform a rapid response to the diabetic patient. Brief explanation of the drawing

[0011] FIG. 1 illustrates a block diagram of an electronic device and network according to various embodiments of the present invention. FIG. 2 is a flowchart illustrating a method of operation of an electronic device according to various embodiments of the present invention. Specific details for implementing the invention

[0012] Hereinafter, various embodiments of this document are described with reference to the accompanying drawings. The embodiments and the terms used therein are not intended to limit the technology described in this document to specific embodiments and should be understood to include various modifications, equivalents, and / or substitutions of said embodiments. In relation to the description of the drawings, similar reference numerals may be used for similar components. A singular expression may include a plural expression unless the context clearly indicates otherwise. In this document, expressions such as "A or B" or "at least one of A and / or B" may include all possible combinations of items listed together. Expressions such as "first," "second," "first," or "second" may modify said components regardless of order or importance and are used only to distinguish one component from another and do not limit said components. When it is mentioned that a certain (e.g., 1st) component is "(functionally or telecommunicationally) connected" or "connected" to another (e.g., 2nd) component, said certain component may be directly connected to said other component or connected through another component (e.g., 3rd component).

[0013] In this document, "configured to" may be used interchangeably with, depending on the context, for example, hardware- or software-wise, "suitable for," "capable of," "modified to," "made to," "capable of," or "designed to." In some cases, the expression "device configured to" may mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase "processor configured to perform A, B, and C" may mean a dedicated processor for performing the corresponding operations (e.g., an embedded processor), or a general-purpose processor capable of performing the corresponding operations by executing one or more software programs stored in a memory device (e.g., a CPU or application processor).

[0014] An electronic device according to various embodiments of the present document may include, for example, at least one of a smartphone, a tablet PC, a desktop PC, a laptop PC, a netbook computer, a workstation, and a server.

[0015] Referring to FIG. 1, an electronic device (101) within a network environment (100) in various embodiments is described. The electronic device (101) may include a bus (110), a processor (120), a memory (130), an input / output interface (140), a display (150), a communication interface (160), and a smart ring (170). In some embodiments, the electronic device (101) may omit at least one of the components or additionally include other components. The bus (110) may include a circuit that connects the components (110-170) to each other and transmits communication (e.g., control messages or data) between the components. The processor (120) may include one or more of a central processing unit, an application processor, or a communication processor (CP). The processor (120) may, for example, perform operations or data processing regarding the control and / or communication of at least one other component of the electronic device (101).

[0016] The memory (130) may include volatile and / or non-volatile memory. The memory (130) may store instructions or data related to at least one other component of the electronic device (101), for example. According to one embodiment, the memory (130) may store software and / or a program (140).

[0017] The input / output interface (140) can, for example, transmit commands or data input from a patient or other external device to other component(s) of the electronic device (101), or output commands or data received from other component(s) of the electronic device (101) to the patient or other external device.

[0018] The display (150) may include, for example, a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display, a microelectromechanical system (MEMS) display, or an electronic paper display. The display (150) may display various content (e.g., text, images, videos, icons, and / or symbols, etc.) to a patient, for example. The display (150) may include a touch screen and may receive touch, gesture, proximity, or hovering input using, for example, an electronic pen or a part of the patient's body. The communication interface (160) may establish communication between, for example, the electronic device (101) and an external device (e.g., a first external electronic device (102), a second external electronic device (104), or a server (108)). For example, the communication interface (160) can be connected to a network (162) via wireless or wired communication to communicate with an external device (e.g., a second external electronic device (104) or a server (108)).

[0019] Wireless communication may include cellular communication using at least one of, for example, LTE, LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM (Global System for Mobile Communications). According to one embodiment, wireless communication may include at least one of, for example, WiFi (wireless fidelity), Bluetooth, Bluetooth Low Energy (BLE), Zigbee, NFC (near field communication), Magnetic Secure Transmission, Radio Frequency (RF), or Body Area Network (BAN). According to one embodiment, wireless communication may include GNSS. GNSS may be, for example, GPS (Global Positioning System), Glonass (Global Navigation Satellite System), Beidou Navigation Satellite System (hereinafter "Beidou"), or Galileo, the European global satellite-based navigation system. Hereinafter, in this document, "GPS" may be used interchangeably with "GNSS". Wired communication may include at least one of, for example, USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).The network (162) may include at least one of a telecommunications network, for example, a computer network (e.g., LAN or WAN), the Internet, or a telephone network.

[0020] Each of the first and second external electronic devices (102, 104, 106) may be the same or a different type of device as the electronic device (101). According to various embodiments, all or part of the operations performed on the electronic device (101) may be performed on one or more other electronic devices (e.g., electronic devices (102, 104, 106), or a server (108). According to one embodiment, when the electronic device (101) needs to perform a function or service automatically or upon request, the electronic device (101) may request at least some of the associated functions from another device (e.g., electronic devices (102, 104, 106), or a server (108)) instead of performing the function or service itself or additionally. The other electronic device (e.g., electronic devices (102, 104, 106), or a server (108)) may perform the requested function or additional functions and transmit the result to the electronic device (101). The electronic device (101) may provide the requested function or service by processing the received result as is or additionally. For this purpose, for example, cloud computing, distributed computing, or client-server computing technologies may be used.

[0021] The smart ring (170) is a smart ring inserted into the finger of at least one diabetic patient and can acquire health and activity data by acquiring and processing accelerometer signals and PPG (photoplethysmography) signals. This allows the PPG installed in the smart ring (170) to acquire biometric data such as heart rate (HR), heart rate variability (HRV), and blood oxygen saturation (SpO₂) by measuring changes in reflected / transmitted light caused by changes in blood flow within the blood vessels using LEDs and optical sensors. However, PPG is very sensitive to the movement of the finger / wrist, so there is a problem with severe motion artifacts (noise). Since the accelerometer (IMU) signal directly measures the user's movement, there was a problem that it was essential to operate to detect and correct contamination of the PPG signal (when / what kind of movement). Therefore, the smart ring (170) can be configured to enable accurate biometric signal extraction by combining PPG and 3-axis accelerometer (sometimes gyroscope). Additionally, the smart ring (170) is equipped with a red / infrared (IR) LED and a photodetector (photodiode), and can be frequently used in portable rings because the fingers are rich in blood vessels, which is advantageous for PPG. Additionally, the smart ring (170) is highly susceptible to signal quality depending on the sensor position (where the LED / PD is placed on the inner surface), and in some models, multiple paths (different tissue depths) can be measured through asymmetric placement. Additionally, the smart ring (170) is equipped with a 3-axis accelerometer and is used for detecting movement / classifying / determining the state (stopping, walking, rapid acceleration, etc.) of at least one patient, and the sampling rate is typically in the range of 25-200 Hz depending on the application.Additionally, the smart ring (170) can mark (masking) "sections of severe movement" by looking at the magnitude and frequency content of the acceleration signal based on acceleration-based artifact detection, and can precisely determine it using a simple threshold, variance-based, or machine learning (classifier), and remove PPG noise by regression using acceleration (or multiple axes) as a reference input based on acceleration-based regression (Adaptive noise cancellation) (adaptive filters such as LMS, RLS, etc.). By modeling and removing the correlation between movement and PPG, it can be widely used in both research and commercial applications. Additionally, the smart ring (170) can preserve the basic heart rate band and reduce non-periodic noise using wavelet transform and bandpass filtering (e.g., HR is in the 0.5-4 Hz band), and can separate signal components by including PPG and reference (acceleration) together. In addition, the smart ring (170) has the advantage that although the output of the upper data is large, the output is performed by the electronic device (101), so it does not cause a major problem.

[0023] FIG. 2 is a flowchart illustrating a method of operation of an electronic device according to various embodiments of the present invention.

[0025] In operation 201, an electronic device (101) (e.g., the processor (120) of FIG. 1) can obtain at least one diabetic data from a diabetic patient through at least one smart ring (170).

[0026] According to one embodiment, at least one diabetic data may include heart rate data, photoplethysmography (PPG) data, acceleration data and velocity data according to the movement of the diabetic patient, and body temperature data for the diabetic patient through a smart ring (170). Specifically, the heart rate data may consist of real-time HR (e.g., 78 bpm) data, time-series HR trend data (e.g., average value at 5-second intervals), and HRV (Heart Rate Variability) data according to minute changes in the time interval between consecutive beats. Additionally, the heart rate data may be output as a decrease in HRV, as autonomic neuropathy is one of the complications of diabetes, and may be used for the possibility of early diagnosis of diabetic autonomic neuropathy (DAN) through HRV analysis, and the HR pattern may change according to blood glucose fluctuations. In addition, photoplethysmography (PPG) data can be composed of data measured by a photodiode regarding changes in the amount of light passing through or reflected from blood vessels based on an LED light source (red, infrared, etc.), and can be used to evaluate vascular elasticity through pulse wave velocity (PWV), evaluate peripheral vascular resistance through waveform characteristics (rise time, reflected wave ratio, etc.), and utilize the red / infrared reflection ratio through blood oxygen saturation (SpO₂). Furthermore, photoplethysmography data can be characterized by reduced peripheral vascular circulation and decreased vascular elasticity, and can estimate the state of peripheral circulation and the degree of vascular aging through PPG waveform analysis, and long-term PPG trends can be used as an indirect indicator of blood glucose control status (e.g., blood flow stability).In addition, acceleration data can be used as real-time acceleration time-series data for the 3-axis accelerometer within the smart ring to detect fine finger movements, and can be used for activity indices, movement / walking patterns, and as feature values ​​for classifying stationary, walking, and sleep states. Furthermore, acceleration data can be used to directly influence blood glucose control as a measure of activity level, and can be used to estimate daily activity levels, sedentary lifestyle time, and sleep time based on acceleration. Additionally, motion data can be used to remove motion artifacts in PPG. Furthermore, velocity data can be calculated by integrating acceleration data or derived from stride × walking cycle based on step detection when walking is detected. It can be calculated as instantaneous movement speed and / or average speed, walking speed, and activity-specific speed profiles, and can be used to classify activity levels (walking, running, etc.). In addition, speed data is known as an indicator of muscle strength and metabolic health, and can be used to evaluate the decline in exercise capacity of diabetic patients or the degree of improvement after blood sugar control, and can also be applied to detect abnormal gait patterns caused by chronic complications (peripheral neuropathy). In addition, body temperature data can be measured by placing an infrared temperature sensor or a thermocouple sensor on the inner surface of the ring to measure skin temperature, and can be used as skin temperature time series data, average / maximum / minimum temperature data, and body temperature rise / fall pattern data. Furthermore, body temperature data can be used as measurement data for diabetic patients who may show a decrease in skin temperature due to reduced peripheral blood flow, and can be used as data to evaluate autonomic nervous system abnormalities and circulatory disorders through nighttime body temperature pattern analysis, and can be used for long-term metabolic rate changes and early detection of infection. Subsequently, the electronic device (101) can preprocess heart rate data, photoplethysmography data, acceleration data, speed data, and body temperature data and input them into a prediction model.

[0027] According to another embodiment, the electronic device (101) can calculate activity data of a diabetic patient based on acceleration data and velocity data, and can calculate biometric data of a diabetic patient based on body temperature data, heart rate data, and photoplethysmography data, and the activity data and biometric data can be input into a prediction model. Specifically, the electronic device (101) can measure finger movement, vibration, steps, and physical activity patterns in three axes based on acceleration data, and can integrate acceleration based on velocity data or be used for movement speed calculated from stride and walking cycle when walking is detected. Subsequently, the electronic device (101) can calculate the number of steps using a periodic acceleration pattern based on step detection, and can distinguish between 'walking / running / stopping / sleeping' by inputting acceleration RMS, variance, and FFT spectrum into an ML classifier (KNN, RF, CNN, etc.) based on activity recognition, and can calculate the MET (Metabolic Equivalent of Task) value using speed, weight, HR, etc. based on energy expenditure, and can calculate the acceleration mean square value (RMS) or rate of change based on the movement intensity index. Subsequently, the electronic device (101) can calculate activity data of a diabetic patient including the measured pattern, variance, rate of change, etc. Additionally, the electronic device (101) can estimate skin temperature and core body temperature based on body temperature data, estimate HR, HRV and heart rhythm based on heart rate data, and can be used for pulse wave shape, blood flow volume, SpO2, and vascular elasticity based on PPG data.Subsequently, the electronic device (101) can perform acceleration-based corrected PPG noise removal, perform body temperature sensor collaboration, and detect peak intervals between body temperatures through HR / HRV extraction. Subsequently, the electronic device (101) can produce biometric data including noise-removed PPG, body temperature sensor collaboration, and peak interval detection. Subsequently, the electronic device (101) can input the generated activity data and biometric data into a prediction model.

[0028] In operation 203, the electronic device (101) (e.g., the processor (120) of FIG. 1) can determine diabetic patient prediction data by inputting at least one diabetic data into a prediction model.

[0029] According to one embodiment, the prediction model may be trained based on a plurality of diabetic data obtained from a plurality of diabetic users, a plurality of diabetic patient prediction data output from a plurality of diabetic users, data determined to indicate that a plurality of diabetic users are being managed normally, data determined to indicate that a plurality of diabetic users require attention and follow-up observation, and data determined to indicate that a plurality of diabetic users have a high probability of deterioration and require emergency measures. Additionally, the prediction model may be further trained with a plurality of activity data and a plurality of biological data, a plurality of biological prognosis data, and a plurality of body movement data. Specifically, the prediction model for determining diabetic patient prediction data may be driven by an AI neural network model trained through unsupervised learning on basic data. The prediction model may be configured to increase the ease of data collection and to have various data output values. The prediction model has a structure that outputs image data from text data, and at least one of BigScience’s bloom and T0pp, EleutherAI’s GPT series, Tsinghua UNIV’s GLM series, GOOGLE’s UL and T5 series, and META AI’s OPT series may be utilized. According to one embodiment, the prediction model can be implemented using a plurality of Cloud Foundation models, utilizing the structure of Microsoft’s Chat GPT, Google’s BARD series, and NVIDIA’s translation service-based Transformer model. For example, the prediction model can be trained as a multimodal-based model based on at least one of text data, image data, and audio data to implement various image renderings.In one embodiment, compared to conventional deep learning methods, this can reduce the amount of labeled training data per task, and once established, various training can be performed with a small amount of training data, making data collection and labeling easier and improving accuracy. Additionally, the electronic device (101) can be used as a training process for a prediction model to output state prediction data by obtaining a result value (output data) using a prediction model to which arbitrary weights are assigned, comparing the obtained result value with the labeled data of the training data, and performing backpropagation according to the error to optimize the weights. Specifically, training of the prediction model refers to a process of training the prediction model based on training data and labeled data or unlabeled data so that the prediction model can determine output data for the input data. That is, the prediction model forms rules and makes judgments regarding the data. According to one embodiment, the electronic device (101) may use a plurality of learning algorithms among a plurality of learning algorithms that calculate predicted values. For example, an ensemble method can be used in a prediction model, and better prediction performance can be obtained compared to using learning algorithms separately. Training a prediction model may mean adjusting the weights of the model. According to one embodiment, various methods such as supervised learning, unsupervised learning, reinforcement learning, imitation learning, and federated learning may be used as learning methods.

[0030] Although not illustrated, the electronic device (101) may include an evaluation step for evaluating the performance of the prediction model during the learning process of the prediction model. In the evaluation step, the prediction model may be evaluated using an evaluation data set. The evaluation of the prediction model may be a step of evaluating the prediction model learned by the learning step and making predictions for new data using the prediction model. Specifically, the evaluation step may be a step of measuring whether the learned prediction model is capable of generalization for new data.

[0031] Furthermore, the prediction model is a type of artificial neural network specialized for learning patterns in time-series or sequential data, utilizing a Long Short-Term Memory (LSTM) structure. It is primarily an improved version of the Recurrent Neural Network (RNN). While RNNs predict the future based on past information, they suffer from the Gradient Vanishing problem, which makes learning difficult in long sequences and hinders the processing of long-term dependencies. However, the prediction model (LSTM) can learn long-term dependencies by introducing a special gate structure to control the flow of information and solve this problem. The prediction model can operate by selectively remembering and forgetting information using three gates: an Input Gate, a Forget Gate, and an Output Gate. These gates can perform the following actions at each stage. First, the Input Gate determines how much newly input information to accept; the Forget Gate determines how much previously stored information to forget; and the Output Gate determines the amount of information to be passed from the current state to the next. Based on the three gates at the top, the prediction model learns and adjusts on its own whether past information is needed for current predictions, and learns whether information at the beginning of a sentence is needed at the end of a sentence.Furthermore, the predictive model (LSTM) is a natural language processing tool utilized in sentence generation, translation, and sentiment analysis. It possesses strengths particularly in machine translation, such as its ability to grasp the context of an entire sentence. It can recognize specific words or phrases by processing speech data as a time series, and it can be used to predict future stock prices by learning past fluctuation patterns. It can also be applied to behavior prediction or scene classification by learning changes between frames over time in videos, and it can be used for long-term predictions—for example, the probability of disease onset—by analyzing a user's past medical history and treatment records. Additionally, the predictive model (LSTM) has the advantage of effectively remembering and utilizing long historical data. However, the predictive model (LSTM) has high computational costs, and training times can become lengthy as the amount of data increases. Consequently, other sequential models, such as the Gated Recurrent Unit (GRU) or Transformer model, have emerged and can be selectively used in various situations to overcome these limitations.

[0032] According to another embodiment, the electronic device (101) can analyze biological prognosis data based on biological data based on a prediction model, analyze physical movement data based on activity data based on the prediction model, and determine diabetic patient prediction data based on biological prognosis data and physical movement data.

[0033] Specifically, the electronic device (101) can calculate predictive data for a diabetic patient based on bio-signal data collected through the smart ring (170). The bio-signal data may include the diabetic patient's heart rate data, photoplethysmography (PPG) data, body temperature data, and acceleration and velocity data based on movement. Additionally, the electronic device (101) can calculate activity data based on the user's daily movement distance, number of steps, activity intensity, and duration of rest by analyzing the acceleration and velocity data. At this time, the activity data can be used as basic data for generating physical movement data, including the user's exercise frequency, energy consumption, sleep patterns, and gait balance. Additionally, the electronic device (101) can calculate bio-data based on body temperature data, heart rate data, and photoplethysmography data. The biometric data may include derived indicators such as heart rate (HR), heart rate variability (HRV), blood flow volume, amplitude and waveform distortion of the pulse wave, and changes in skin temperature, and the biometric data may reflect the user's autonomic nervous system activity, peripheral vascular elasticity, metabolic rate, and circulatory system function. Additionally, the electronic device (101) can analyze prognostic information for diabetic patients by inputting the calculated activity data and biometric data into a prediction model. Subsequently, the prediction model may include a machine learning or deep learning-based prediction algorithm and can predict diabetic complications, risk of blood glucose fluctuation, and the possibility of reduced peripheral blood flow by analyzing the temporal change pattern of the input biometric data and the correlation with the activity volume. For example, the electronic device (101) can determine a decline in peripheral vascular circulation function or an autonomic nervous system abnormality if a pattern is detected in which the heart rate variability decreases below a certain level and, at the same time, the amplitude of the photoplethysmography data decreases.Additionally, if the nighttime drop in body temperature of the electronic device (101) decreases or a state of significantly low activity persists, the risk of metabolic rate decline or blood sugar fluctuation may be assessed as high. Furthermore, the electronic device (101) can calculate bio-prognosis data based on bio-data analyzed through a prediction model, and the bio-prognosis data, as data for predicting future changes in the health status of a diabetic patient, may include a Glycemic Variability Index, a risk of vascular function decline, a score for the likelihood of neuropathy, and a lifestyle risk index. Additionally, the electronic device (101) can calculate physical movement data by analyzing activity data based on the prediction model, and the physical movement data may include indicators such as the patient's exercise intensity, balance, gait pattern, and inactivity time. The electronic device (101) can determine comprehensive prediction data for a diabetic patient by comparing and combining the bio-prognosis data and the physical movement data. At this time, the comprehensive prediction data can be displayed as blood sugar control risk, vascular health index, or nervous system abnormality alert information, and can be transmitted to the user's health management system or cloud server to be utilized for continuous monitoring and feedback.

[0034] In operation 205, the electronic device (101) (e.g., the processor (120) of FIG. 1) can determine whether the diabetic patient prediction data has exceeded a preset first threshold value. According to one embodiment, the electronic device (101) can output bio-prognosis data and body movement data from the diabetic patient prediction data. Subsequently, the electronic device (101) can calculate the bio-prognosis data as -100% to 100% based on the value determined to be normal in the bio-data for the diabetic patient. Additionally, the electronic device (101) can determine whether activity occurs within 30 minutes from that point, excluding data confirmed as sleep, based on the point of non-movement in the body movement data. Subsequently, the electronic device (101) can compare the value in the calculated bio-data with the time value until the next activity based on the point of non-movement confirmed as not being in a sleep state, with a preset first threshold value. Additionally, the first threshold value is based on normal data in the bio-data. It is possible to determine whether the threshold has been exceeded and whether movement occurred within 30 minutes from the point in time when biological movement was judged to have ended in a non-sleep state in the body movement data, and at least one case exceeding this threshold can be set as the threshold value. Additionally, the first threshold value is the threshold value of the biological data according to the administrator's settings. The range can be changed to 22.5 minutes to 37.5 minutes, and the end point of the body movement data can be changed to 22.5 minutes to 37.5 minutes. Afterwards, the electronic device (101) can determine the excess range of the diabetic patient prediction data based on the set first threshold value.

[0035] In operation 207, the electronic device (101) (e.g., the processor (120) of FIG. 1) may determine that the diabetic user is in a normal state if it determines that the diabetic patient prediction data does not exceed a first threshold value. According to one embodiment, if the electronic device (101) determines that the value of the bio-data is 2.4% and the next movement time of the body movement data is 8.4 minutes, the first threshold value (e.g., bio-data It can be determined that the entire body movement data (30 minutes) has not exceeded the threshold value, and that the diabetic patient prediction data has not exceeded the first threshold value. Afterwards, the electronic device (101) can determine that the diabetic patient is in a normal state and can return to operation 201 and repeat the process until the diabetic patient exceeds the first threshold value.

[0036] Meanwhile, in operation 205, if the electronic device (101) (e.g., the processor (120) of FIG. 1) determines that the diabetic patient prediction data has exceeded a first threshold value, in operation 209, the electronic device (101) (e.g., the processor (120) of FIG. 1) may determine whether the diabetic patient prediction data has exceeded a second threshold value set to be greater than the first threshold value. According to one embodiment, if the electronic device (101) determines that the value of the bio-data is 12.4% and the next movement time of the body movement data is 29.1 minutes, the first threshold value (e.g., bio-data In the body movement data (30 minutes), it can be determined that the body movement data has not exceeded the threshold but the biometric data has exceeded it, and it can be determined that the diabetic patient prediction data has exceeded the first threshold. Subsequently, the electronic device (101) can determine whether it exceeds a second threshold value that is set to be greater than the first threshold value. In addition, the second threshold value is based on normal data in the biometric data. It is possible to determine whether the threshold has been exceeded and whether movement occurred within 60 minutes from the point in time when biological movement was judged to have ended in a non-sleep state in the body movement data, and at least one case exceeding this threshold can be set as the threshold value. Additionally, the second threshold value [is] the threshold value of the biological data according to the administrator's settings. The range can be changed to 45 minutes to 75 minutes, and the end point of the body movement data can be changed to 45 minutes to 75 minutes. Afterwards, the electronic device (101) can determine the excess range of the diabetic patient prediction data based on the set second threshold value.

[0037] In operation 211, if the electronic device (101) (e.g., the processor (120) of FIG. 1) determines that the diabetic patient prediction data has exceeded a first threshold but has not exceeded a second threshold, it may determine that the diabetic user requires caution. According to one embodiment, if the electronic device (101) determines that the value of the bio-data is 12.4% and the next movement time of the body movement data is 29.1 minutes, the first threshold (e.g., bio-data ..., regarding physical movement data (30 minutes), it can be determined that the physical movement data did not exceed the threshold but the biometric data exceeded it, and it can be determined that the diabetic patient prediction data exceeded the first threshold, but the second threshold (e.g., biometric data It can be determined that the total of the body movement data (60 minutes) has not been exceeded, and that the diabetic patient prediction data has not been exceeded. Afterwards, the electronic device (101) can determine that the diabetic patient requires caution.

[0038] In operation 213, an electronic device (101) (e.g., processor (120) of FIG. 1) can transmit, through a communication interface (e.g., communication interface (160) of FIG. 1), data predicting a diabetic patient that has been determined to have exceeded a first threshold value, and first guideline data stored in memory (e.g., memory (130) of FIG. 1) based on the data predicting a diabetic patient that has exceeded the first threshold value, to an external electronic device (102, 104, 106) of a diabetic patient. According to one embodiment, the electronic device (101) can transmit, through a communication interface (e.g., communication interface (160) of FIG. 1), first guideline data consisting of data predicting a diabetic patient that has exceeded the first threshold value, a state requiring attention, and a guide regarding recovery methods and / or outpatient treatment in the case of a state requiring attention, to an external electronic device (102, 104, 106) of a diabetic patient. Afterward, the diabetic patient can check the alarm and / or diabetic patient prediction data generated from the diabetic patient's external electronic device (102, 104, 106) and determine whether to perform outpatient treatment and / or recovery at the hospital based on the first guideline data.

[0039] Meanwhile, in operation 209, if the electronic device (101) (e.g., the processor (120) of FIG. 1) determines that the diabetic patient prediction data exceeds a first threshold and a second threshold, in operation 215, the electronic device (101) (e.g., the processor (120) of FIG. 1) may determine that the diabetic user is likely to worsen and that urgent measures are required. According to one embodiment, if the electronic device (101) determines that the value of the bio-data is 16.9% and the next movement time of the body movement data is 67.8 minutes, the first threshold (e.g., bio-data , it can be determined that the total has been exceeded in the body movement data (30 minutes), and it can be determined that the diabetic patient prediction data has exceeded the first threshold, and the second threshold (e.g., biometric data In the body movement data (60 minutes), it can be determined that the biometric data has not exceeded the threshold, but the body movement data has exceeded the threshold, and it can be determined that the diabetic patient prediction data has exceeded the second threshold. Subsequently, if the diabetic patient prediction data has exceeded the second threshold, the electronic device (101) can determine that the diabetic patient is in an emergency state.

[0040] In operation 217, an electronic device (101) (e.g., processor (120) of FIG. 1) can transmit, via a communication interface (e.g., communication interface (160) of FIG. 1), second guideline data stored in memory (e.g., memory (130) of FIG. 1) based on diabetic patient prediction data determined to have exceeded a first threshold and a second threshold, and diabetic patient prediction data exceeding the second threshold, to an external electronic device (102, 104, 106) of a diabetic user and an external electronic device (102, 104, 106) of a specialist of the user. According to one embodiment, an electronic device (101) can transmit second guideline data, which consists of prediction data of a diabetic patient exceeding a second threshold, a severe condition, and a guide on emergency measures and / or inpatient treatment in the case of a severe condition, to an external electronic device (102, 104, 106) of a diabetic user through a communication interface (e.g., communication interface (160) of FIG. 1). Subsequently, the diabetic user can check the external electronic device (102, 104, 106) of the diabetic user and determine whether to perform inpatient treatment and / or recovery at a hospital based on the second guideline data, and a diabetic specialist can prepare in advance for hospitalization and treatment progress methods for the user.

[0042] Additionally, the electronic device (101) is a wearable sensor device for non-invasively measuring the biosignals and activity levels of a diabetic patient based on a smart ring (170), and may have a plurality of sensor modules and communication modules embedded inside a ring-shaped housing. Additionally, the electronic device (101) may include a photoplethysmography (PPG) module for detecting the user's blood flow and heart rate-related biosignals based on the smart ring (170). The PPG module includes a red or infrared LED emitter and a light sensor (photodiode) that receives reflected light, and can acquire blood flow fluctuation signals by detecting changes in the amount of light reflected from the user's finger blood vessels. Additionally, the electronic device (101) may include a 3-axis accelerometer for measuring the user's movements based on the smart ring (170). Additionally, the acceleration sensor can determine the user's walking, movement, and stationary state using acceleration data measured at a sampling frequency of 10 Hz to 50 Hz, and can be utilized for calculating activity levels. Additionally, the electronic device (101) may be equipped with a body temperature sensor based on the smart ring (170) to detect changes in the user's skin temperature, and the sensor can measure the skin surface temperature at intervals of 0.2 Hz (5-second cycle) to calculate the average temperature and fluctuation values. Additionally, the electronic device (101) may be equipped with a Bluetooth Low Energy (BLE) communication chip based on the smart ring (170) to synchronize collected data with a smartphone or an external electronic device (101). The electronic device (101) may be equipped with a vibration motor or a mini LED display inside the ring based on the smart ring (170) to output vibration or visual signals when the user's biological state or system alarm occurs.

[0043] Additionally, the electronic device (101) according to the present embodiment can process biosignal data obtained from the smart ring (170). Specifically, the electronic device (101) can calculate activity levels based on acceleration signals of 10 to 50 Hz collected from an acceleration sensor, calculate average temperature and short-term fluctuations using temperature data collected from a body temperature sensor at a 0.2 Hz cycle, and estimate heart rate (HR), heart rate variability (HRV), and oxygen saturation (SpO₂) by analyzing photocirculatory signals obtained from a PPG sensor at a 200 Hz cycle. The biosignal data obtained in this way can be utilized for analyzing the patient's condition after undergoing time synchronization and noise filtering processes. Subsequently, if the activity level measured over the past 30 minutes to 1 hour remains '0', the electronic device (101) can generate an "activity needed" alarm, determining that the patient is in an inactive state for a long time. Here, the alarm can be used for warning purposes to improve the habit of sitting for long periods and to promote blood circulation. Additionally, the electronic device (101) can allow the patient to input the meal time via a smartphone application, or the system can automatically estimate the time of the meal through PPG signal patterns and changes in acceleration. Subsequently, if no movement is detected within a certain time (e.g., 30 minutes to 1 hour) from the time of the meal, the electronic device (101) can output a “light activity recommended after meal” alarm to prevent a rapid increase in blood sugar after the meal. Additionally, the electronic device (101) can generate an alarm if the body temperature (T) or heart rate (HR) shows a fluctuation of more than ±10% compared to the individual’s baseline value, determining it to be in a “caution” state. For example, the electronic device (101) can determine that a rapid rise in body temperature or an abnormally low heart rate indicates a physiological abnormality such as infection, circulatory disorder, or accumulated fatigue.Afterward, the electronic device (101) can display a notification message through a smartphone application and provide a physical notification by driving a ring's vibration motor or LED, and if the patient ignores the alarm or does not respond, the system can intermittently re-alarm according to a set cycle, which can be individually adjusted according to the patient's settings.

[0045] An electronic device (101) according to one embodiment has the advantage of being able to easily determine diabetic patient prediction data by inputting at least one diabetic data obtained through a smart ring (170) into a prediction model, easily predict the patient's condition by reviewing the diabetic patient prediction data, and, only when the patient's condition is determined to be in a critical and / or serious state based on the diabetic patient prediction data, transmit an alarm and / or the diabetic patient prediction data to the outside to perform a rapid response to the diabetic patient.

[0047] According to various embodiments, an electronic device for managing movement and alarms of a diabetic patient based on a smart ring comprises: at least one smart ring installed on the diabetic patient; memory; a communication interface; and a processor; The processor includes, through the at least one smart ring, at least one diabetic data from the diabetic patient, inputs the at least one diabetic data into a prediction model to determine diabetic patient prediction data, and if it is determined that the diabetic patient prediction data exceeds a preset first threshold value, determines that the diabetic patient requires attention, and is configured to transmit, through the communication interface, the diabetic patient prediction data determined to exceed the first threshold value and the first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, and the prediction model is learned based on a plurality of diabetic data obtained from a plurality of diabetic patients, a plurality of diabetic patient prediction data output from a plurality of diabetic patients, data determined that the plurality of diabetic patients are being managed normally, data determined that the plurality of diabetic patients require attention and need to be monitored, and data determined that the plurality of diabetic patients have a high probability of deterioration and require emergency measures.

[0048] According to various embodiments, the at least one diabetic data includes, through the smart ring, heart rate data, photoplethysmography (PPG) data, acceleration data and velocity data according to the movement of the diabetic patient, and body temperature data for the diabetic patient.

[0049] According to various embodiments, the processor calculates activity data of the diabetic patient based on the acceleration data and the velocity data, calculates biometric data for the diabetic patient based on the body temperature data, the heart rate data, and photoplethysmography data, and is configured to input the activity data and the biometric data into the prediction model, and the prediction model further learns a plurality of activity data and a plurality of biometric data.

[0050] According to various embodiments, the processor analyzes biological prognosis data based on biological data based on the prediction model, analyzes body movement data based on activity data based on the prediction model, and is configured to determine the diabetic patient prediction data based on the biological prognosis data and the body movement data, and the prediction model further learns a plurality of biological prognosis data and a plurality of body movement data.

[0051] According to various embodiments, the processor is configured to determine that the diabetic patient is in a normal state if it determines that the diabetic patient prediction data does not exceed the first threshold value, determine that the diabetic patient requires caution if it determines that the diabetic patient prediction data exceeds the first threshold value but does not exceed a second threshold value set to be greater than the first threshold value, and determine that the diabetic patient requires urgent action if it determines that the diabetic patient prediction data exceeds both the first threshold value and the second threshold value.

[0052] According to various embodiments, the processor is configured to transmit, through the communication interface, the diabetic patient prediction data determined to have exceeded the first threshold value and the first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, and through the communication interface, the diabetic patient prediction data determined to have exceeded the first threshold value and the second threshold value and the second guideline data stored in the memory based on the diabetic patient prediction data exceeding the second threshold value to an external electronic device of the diabetic patient and an external electronic device of the patient's specialist.

[0053] According to various other embodiments, in a method for operating an electronic device for managing the movement and alarm of a diabetic patient based on a smart ring, the method comprises acquiring at least one diabetic data from the diabetic patient through at least one smart ring installed on the diabetic patient, inputting the at least one diabetic data into a prediction model through a processor to determine diabetic patient prediction data, determining through the processor that if the diabetic patient prediction data is determined to exceed a preset first threshold value, the diabetic patient requires attention, and transmitting, through a communication interface, the diabetic patient prediction data determined to exceed the first threshold value and first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, wherein the prediction model comprises a plurality of diabetic data acquired from a plurality of diabetic patients, a plurality of diabetic patient prediction data output from a plurality of diabetic patients, data determined to indicate that the plurality of diabetic patients are being managed normally, data determined to indicate that the plurality of diabetic patients require attention and observation of the progress, and data determined to indicate that the plurality of diabetic patients have a high probability of deterioration and require emergency measures. It is learned based on data.

[0055] As used in this document, the terms “module” or “part” include a unit composed of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. “Module” or “part” may be a component formed integrally or a minimum unit or part thereof that performs one or more functions. “Module” or “part” may be implemented mechanically or electronically and may include, for example, an application-specific integrated circuit (ASIC) chip, field-programmable gate arrays (FPGAs), or programmable logic device known or to be developed that performs certain operations, and may be executed by a processor (120). At least part of the device (e.g., modules or functions thereof) or method (e.g., operations) according to various embodiments may be implemented as instructions stored in a computer-readable storage medium (e.g., memory (130)) in the form of a program module. When the above instruction is executed by a processor (e.g., processor (120)), the processor may perform a function corresponding to the above instruction. Computer-readable recording media may include a hard disk, a floppy disk, a magnetic medium (e.g., magnetic tape), an optical recording medium (e.g., CD-ROM, DVD, magneto-optical medium (e.g., floptical disk), built-in memory, etc. Instructions may include code generated by a compiler or code that can be executed by an interpreter. A module or program module according to various embodiments may include at least one of the aforementioned components, some of which may be omitted, or additionally include other components. Operations performed by a module, program module, or other components according to various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations may be added.

[0056] Furthermore, the embodiments disclosed in this document are presented for the purpose of explaining and understanding the disclosed technical content and are not intended to limit the scope of this disclosure. Accordingly, the scope of this disclosure should be interpreted to include all modifications or various other embodiments based on the technical concept of this disclosure.

[0058] This study was conducted with funding from the Ministry of Health and Welfare and supported by the Korea Health Information Service's Medical Data-Centric Hospital Support Project.

[0059] This specification is based on the following private information.

[0060] Project ID: 1415188707

[0061] Assignment No.: P0025898

[0062] Ministry Name: Ministry of Trade, Industry and Energy

[0063] Project Management (Specialized) Agency Name: Korea Institute for Industrial Technology Promotion

[0064] Research Project Name: Development of Regional Innovation Clusters (R&D)

[0065] Research Project Title: Development of Customized Health Promotion Management Services

[0066] Research Period: August 1, 2023 – December 31, 2025

Claims

Claim 1 An electronic device for managing movement and alarms of a diabetic patient based on a smart ring, comprising: at least one smart ring installed on the diabetic patient; memory; a communication interface; and a processor; An electronic device comprising: a processor that acquires at least one diabetic data from a diabetic patient through at least one smart ring, inputs the at least one diabetic data into a prediction model to determine diabetic patient prediction data, determines that the diabetic patient requires attention if it is determined that the diabetic patient prediction data exceeds a preset first threshold value, and is configured to transmit, through the communication interface, the diabetic patient prediction data determined to exceed the first threshold value and the diabetic patient prediction data exceeding the first threshold value, and a first guideline data previously stored in the memory, to an external electronic device of the diabetic patient, and the prediction model is learned based on a plurality of diabetic data acquired from a plurality of diabetic patients, a plurality of diabetic patient prediction data output from a plurality of diabetic patients, data determined that the plurality of diabetic patients are being managed normally, data determined that the plurality of diabetic patients require attention and need follow-up observation, and data determined that the plurality of diabetic patients have a high probability of deterioration and require emergency measures. Claim 2 An electronic device according to claim 1, wherein the at least one diabetic data includes, through the smart ring, heart rate data, photoplethysmography (PPG) data, acceleration data and velocity data according to the movement of the diabetic patient, and body temperature data of the diabetic patient. Claim 3 An electronic device according to claim 2, wherein the processor calculates activity data of the diabetic patient based on the acceleration data and the velocity data, calculates biometric data for the diabetic patient based on the body temperature data, the heart rate data, and photoplethysmography data, and is configured to input the activity data and the biometric data into the prediction model, and the prediction model is further trained on a plurality of activity data and a plurality of biometric data. Claim 4 An electronic device according to claim 3, wherein the processor analyzes bio-prognosis data based on the bio-data based on the prediction model, analyzes body movement data based on the activity data based on the prediction model, and is configured to determine the diabetic patient prediction data based on the bio-prognosis data and the body movement data, and the prediction model further learns a plurality of bio-prognosis data and a plurality of body movement data. Claim 5 An electronic device according to claim 1, wherein the processor determines that the diabetic patient is in a normal state if it determines that the diabetic patient prediction data does not exceed the first threshold value, determines that the diabetic patient requires caution if it determines that the diabetic patient prediction data exceeds the first threshold value but does not exceed a second threshold value set to be greater than the first threshold value, and determines that the diabetic patient requires urgent action if it determines that the diabetic patient prediction data exceeds both the first threshold value and the second threshold value. Claim 6 An electronic device according to claim 5, wherein the processor is configured to transmit, through the communication interface, the diabetic patient prediction data determined to have exceeded the first threshold value and the first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, and through the communication interface, the diabetic patient prediction data determined to have exceeded the first threshold value and the second threshold value and the second guideline data stored in the memory based on the diabetic patient prediction data exceeding the second threshold value to an external electronic device of the diabetic patient and an external electronic device of the patient's specialist. Claim 7 A method for operating an electronic device for managing the movement and alarm of a diabetic patient based on a smart ring, wherein the method comprises acquiring at least one diabetic data from the diabetic patient through at least one smart ring installed on the diabetic patient, determining diabetic patient prediction data by inputting the at least one diabetic data into a prediction model through a processor, determining that the diabetic patient requires attention if the diabetic patient prediction data is determined to exceed a preset first threshold value through the processor, and transmitting, through a communication interface, the diabetic patient prediction data determined to exceed the first threshold value and first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, wherein the prediction model is configured based on a plurality of diabetic data acquired from a plurality of diabetic patients, a plurality of diabetic patient prediction data output from a plurality of diabetic patients, data determined to indicate that the plurality of diabetic patients are being managed normally, data determined to indicate that the plurality of diabetic patients require attention and observation of their progress, and data determined to indicate that the plurality of diabetic patients have a high probability of deterioration and require emergency measures. Learning method. Claim 8 In claim 7, the method comprises, through the smart ring, at least one diabetic data including heart rate data, photoplethysmography (PPG) data for the diabetic patient, acceleration data and velocity data according to the movement of the diabetic patient, and body temperature data for the diabetic patient. Claim 9 In claim 8, the method comprises calculating activity data of the diabetic patient based on the acceleration data and the velocity data, calculating biometric data of the diabetic patient based on the body temperature data, the heart rate data, and photoplethysmography data, and setting the activity data and the biometric data to be input into the prediction model, wherein the prediction model is further trained on a plurality of activity data and a plurality of biometric data. Claim 10 In claim 9, the method is configured to analyze biological prognostic data based on biological data based on the prediction model, analyze physical movement data based on activity data based on the prediction model, and determine the diabetic patient prediction data based on the biological prognostic data and the physical movement data, and the prediction model is further trained on a plurality of biological prognostic data and a plurality of physical movement data. Claim 11 In claim 7, the method is configured such that if the diabetic patient prediction data is determined not to exceed the first threshold value, the diabetic patient is determined to be in a normal state; if the diabetic patient prediction data is determined to exceed the first threshold value but not to exceed a second threshold value set to be greater than the first threshold value, the diabetic patient is determined to require caution; and if the diabetic patient prediction data is determined to exceed both the first threshold value and the second threshold value, the diabetic patient is determined to require urgent action due to a high probability of deterioration. Claim 12 In claim 11, the method is configured to transmit, through the communication interface, the diabetic patient prediction data determined to have exceeded the first threshold value and the first guideline data stored in the memory based on the diabetic patient prediction data exceeding the first threshold value to an external electronic device of the diabetic patient, and through the communication interface, the diabetic patient prediction data determined to have exceeded the first threshold value and the second threshold value and the second guideline data stored in the memory based on the diabetic patient prediction data exceeding the second threshold value to an external electronic device of the diabetic patient and an external electronic device of the patient's specialist.

Images