Methods for providing customized health care services

Abstract

A method for providing a user-customized health management service according to one embodiment may include the steps of normalizing data entered by a user and collected data; calculating the user's health status as a numerical indicator by applying weights based on the normalized data; calculating the difference between the user's current state and target state based on the calculated indicator and setting an execution goal based on the difference; and providing a customized health management solution based on the user's health data in conjunction with the execution goal.

Description

Technology Field

[0001] The following examples relate to a method for providing user-customized health care services. Background Technology

[0002] In modern society, various digital solutions can be utilized for health management. Users can record and manage their health data through wearable devices, mobile applications, or online platforms, and some systems can analyze this data to provide personalized health management information.

[0003] Such health management systems can quantitatively evaluate a user's health status and provide personalized exercise and diet plans. Furthermore, some systems can apply artificial intelligence (AI) and data analysis technologies to generate predictive models based on a user's past health records. Through these systems, users can receive personalized health management solutions and be assisted in setting and achieving health goals.

[0004] However, existing health management systems may have limitations in that they fail to adequately reflect users' data characteristics and feasibility. For example, many general health management systems simply set static goals based on user input data, making it difficult to dynamically adjust based on changes in lifestyle patterns or goal achievement. Furthermore, because they fail to sufficiently reflect users' individual health status and environmental factors, there is a possibility that they may present goals that are difficult to apply in practice.

[0005] Furthermore, some systems may utilize limited data in the process of evaluating a user's health status and may not be able to effectively compensate for missing values. While health data can be collected from various sources, there is a possibility that data reliability may be compromised during the process of normalizing, integrating, and analyzing this data.

[0006] Accordingly, to provide more accurate and personalized health management solutions, technology capable of more precisely analyzing user health data, dynamically setting highly actionable goals, and continuously adjusting customized solutions may be required.

[0007] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure. means of solving the problem

[0008] A method for providing a user-customized health management service according to one embodiment may include: a step of normalizing data entered by a user and collected data; a step of calculating the user's health status as a numerical indicator by applying weights based on the normalized data; a step of calculating the difference between the user's current state and target state based on the calculated indicator and setting an execution goal based on the difference; and a step of providing a customized health management solution based on the user's health data in conjunction with the execution goal.

[0009] The step of normalizing the above data may include a step of standardizing the data entered by the user and the collected data so that comparison between different data types is possible.

[0010] The normalization step may include: a step of calculating weights suitable for replacing missing values ​​by analyzing the variability and correlation of the data entered by the user and the collected data when missing values ​​exist in the data entered by the user and the collected data; and a step of predicting and replacing missing values ​​in the user's past data and data of a similar user group based on the calculated weights.

[0011] The normalization step described above may include a step of dynamically replacing missing values ​​through pattern learning considering multiple variables using a machine learning model when missing values ​​exist in the data entered by the user and the collected data.

[0012] The step of calculating the above-mentioned numerical indicator may include: a step of dynamically calculating the relative importance of the individual elements by analyzing the correlation between the variability of the individual elements constituting the above-mentioned normalized data and the user's past health status; and a step of calculating the health status as a numerical indicator by reflecting the relative importance as the weight.

[0013] The step of setting the execution goal may include: analyzing execution patterns from the user's past execution records to calculate the user's execution probability as a probability value; and setting the execution goal through a multi-variable optimization model using the calculated execution probability, the user's current health status, and available resources as input variables.

[0014] The step of setting the execution goal may further include: a step of evaluating whether the user has achieved the goal at predetermined time intervals; a step of analyzing the goal achievement rate and the difficulty of achieving the goal based on the evaluation results; and a step of adjusting the execution goal or changing the execution strategy associated with the goal based on the analysis results.

[0015] The step of providing the customized health management solution may further include: applying a collaborative filtering algorithm to cluster other user groups having a health status similar to that of the user; analyzing behavioral data of user groups similar to the user based on the clustering results to generate the customized health management solution; and adjusting the priority of the customized health management solution according to the user's preference and feasibility score.

[0016] The step of providing the customized health management solution may further include: a step of evaluating the effectiveness of the customized health management solution based on the comparison results by comparing the effect of the customized health management solution linked to the execution goal with the user's behavioral data; and a step of modifying some elements of the customized health management solution or automatically generating a new alternative solution based on the evaluated effectiveness.

[0017] The step of providing the customized health management solution may further include: displaying the execution goal, the change history of the customized health management solution, and the user's progress in achieving the goal on a visual dashboard; providing the goal achievement rate, changes in health status, and the results of the effectiveness analysis of the customized health management solution in graph and chart format on the dashboard; and configuring the visual information differently according to the user's level of understanding.

[0018] An electronic device according to one embodiment includes at least one processor comprising a processing circuitry; and a memory for storing instructions. When the instructions are executed individually or collectively by the at least one processor, the electronic device may be configured to: normalize data input by a user and collected data; calculate the user's health status as a numerical indicator by applying weights based on the normalized data; calculate the difference between the user's current state and target state based on the calculated indicator; set an execution goal based on the difference; and provide a customized health management solution based on the user's health data in conjunction with the execution goal.

[0019] A method for providing a user-customized health management service according to one embodiment may include the steps of: storing data entered by a user and collected data in the memory of a terminal and normalizing the data; generating a numerical indicator representing the user's health status by applying weights based on the normalized data; calculating the difference between the user's current state and target state based on the calculated indicator and setting an execution goal based on the difference; providing a customized health management solution based on the user's health data in conjunction with the execution goal; and outputting the customized health management solution through a user interface. Brief explanation of the drawing

[0020] FIG. 1 is a diagram illustrating an overview of a system for a user-customized health management service according to one embodiment. FIG. 2 is a flowchart illustrating a method for providing a user-customized health management service according to one embodiment. FIG. 3 is a diagram illustrating a customer health loop of a user-customized health care service according to one embodiment. FIG. 4 is a diagram illustrating the process of evaluating a user's health status and calculating a Health Score according to one embodiment. FIG. 5 is a diagram illustrating a method for determining dietary habit typification according to one embodiment. FIG. 6 is a diagram illustrating the operation of a comment generation LLM (large-scale language model) according to one embodiment. FIG. 7 is a diagram illustrating the execution process of a user-customized health management service according to one embodiment. FIG. 8 is a diagram illustrating the process of generating answers using LLM in a user-customized health management system according to one embodiment. FIG. 9 is a drawing illustrating a user interface for data collection and goal setting in a health management service application according to one embodiment. FIG. 10 is a diagram illustrating an interface for querying a user's status in a health management service application according to one embodiment. FIG. 11a is a diagram illustrating an interface that provides AI-based coaching and personalized recommendations in a health management service application according to one embodiment, and FIG. 11b is a diagram illustrating an interface that monitors a user's health management challenge and provides feedback. FIG. 12 is a diagram illustrating an interface for providing a health score in a health management service application according to one embodiment. FIGS. 13a and 13b are drawings illustrating an interface that provides detailed analysis information by indicator of a health score in a health management service application according to one embodiment. FIG. 14 is a diagram illustrating a screen providing a dietary habit type interface in a health management service application according to one embodiment. FIG. 15 is a diagram illustrating an interface that provides information on dietary habits different from those of a user in a health management service application according to one embodiment. FIG. 16 is a diagram illustrating an interface that provides a healthy concierge function in a health management service application according to one embodiment. FIG. 17 is a diagram illustrating an interface that provides AI coaching through a healthy concierge in a health management service application according to one embodiment. FIG. 18 is a diagram illustrating an interface that provides AI coaching through a healthy concierge in a health management service application according to one embodiment. FIG. 19 is a diagram illustrating an interface for recommending a user's diet in a health management service application according to one embodiment. FIG. 20 is a diagram illustrating an interface that provides AI-customized recommendations in a health management service application according to one embodiment. FIG. 21 is a diagram illustrating an interface that provides AI-customized recommendations in a health management service application according to one embodiment. FIG. 22 is an example diagram of the hardware configuration of a system for a user-customized health care service according to one embodiment. Specific details for implementing the invention

[0021] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, actual implementations are not limited to the specific embodiments disclosed, and the scope of this specification includes modifications, equivalents, or substitutions included in the technical concept described by the embodiments.

[0022] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0023] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between.

[0024] The singular expression includes the plural expression unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to specify the existence of the described features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0025] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0026] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are given the same reference numeral regardless of the drawing number, and redundant descriptions thereof will be omitted.

[0027] FIG. 1 is a diagram illustrating an overview of a system for a user-customized health management service according to one embodiment.

[0028] Referring to FIG. 1, a system (100) for a user-customized health management service according to one embodiment may include a terminal (110), a server (120), and a network (130). Specific hardware configurations of the server (120) and the terminal (110) will be described in detail below.

[0029] A server (120) according to one embodiment may include a server that provides a user-customized health management service (instant messaging service) through a network (130). The user-customized health management service may include a service that analyzes the user's health data through a network (130), such as a wireless internet or wireless communication network, sets personalized action goals, provides customized health management solutions based thereon, and dynamically adjusts action goals and solutions by reflecting the user's real-time behavior data, as well as related services.

[0030] The server (120) may be linked with an application (hereinafter referred to as "app") or a web related to a user-customized health management service executed on a terminal (110) for a user interface (UI), function, operation, or service. Hereinafter, the app related to a user-customized health management service or the web related to a user-customized health management service may be referred to as a health management platform.

[0031] The terminal (110) may refer to any electronic device capable of installing and running an app or running the web, such as a computer, portable computer, wireless phone, mobile phone, smartphone, PDA (Personal Digital Assistants), web tablet, or wearable device. At this time, the terminal (110) may receive services and / or content through the app or the web. For example, the terminal (110) may perform overall service operations, such as configuring a service screen, inputting data, transmitting and receiving data, and storing data, under the control of the app or the web. For example, the terminal (110) may process a user interface or user interaction through a processor, and may output or transmit the processing results through the output device of the terminal (110).

[0032] The terminal (110) can run a health management platform provided by the server (120). The user can run the health management platform on the terminal (110) to use the user-customized health management service provided by the server (120). The user can create a user account by subscribing to the user-customized health management service through the health management platform. The user can use the user-customized health management service through the terminal (110) of the account subscribed to the user-customized health management service. The terminal (110) of the account subscribed to the user-customized health management service may refer to a terminal logged in with the account subscribed to the user-customized health management service.

[0033] According to one embodiment, a health management interface may be provided to a terminal (110) through an app for a user-customized health management service. The health management interface is an interface for inputting and viewing a user's health data, setting execution goals, and receiving a customized health management solution. For example, it may include an interface for inputting and modifying health information, an interface for visually displaying the current health status and goal achievement status, an interface for checking and applying recommended health management solutions, and an interface for dynamically adjusting execution goals based on user feedback.

[0034] FIG. 2 is a flowchart illustrating a method for providing a user-customized health management service according to one embodiment. The description with reference to FIG. 1 can be substantially applied to FIG. 2.

[0035] For convenience of explanation, steps (210 to 240) are described as being performed using the server (120) illustrated in FIG. 1. However, these steps (210 to 220) may be used through any other suitable electronic device and within any suitable system.

[0036] Furthermore, the operations of FIG. 2 may be performed in the illustrated order and manner, but the order of some operations may be changed or some operations may be omitted without departing from the spirit and scope of the illustrated embodiment. Multiple operations illustrated in FIG. 2 may be performed in parallel or simultaneously.

[0037] In step (210), a server (120) according to one embodiment can normalize user input data and collected data. User input data may be health-related information provided directly by the user, and may include, for example, weight, diet information, exercise records, sleep time, etc. Collected data may include data collected through external integration and data collected internally.

[0038] Data collected through external linkage may be information provided by wearable devices, smartphone applications, health databases of medical institutions, etc., and may include, for example, step count, heart rate, blood pressure, blood sugar levels, etc.

[0039] Internally collected data may include data that is automatically recorded through the system without direct user input. For example, when dining at a company cafeteria, the meal information can be automatically stored in the internal system through employee ID tagging. Additionally, if a user subscribes to a corporate health management service, biometric information such as step count, heart rate, and sleep patterns can be automatically recorded through wearable devices or mobile applications provided by the service.

[0040] The server (120) can convert this data into a standardized format and normalize it so that consistent analysis is possible. The data normalization process may include processing such as correcting different unit systems, handling missing values, and removing noise.

[0041] A normalization operation according to one embodiment may include a process of standardizing user-inputted data and collected data to enable analysis and comparison. User-inputted data may include health-related information such as weight, diet information, exercise records, and sleep duration, and collected data may include data such as heart rate, step count, blood pressure, and blood sugar levels provided by wearable devices, smartphone applications, and health databases of medical institutions. However, these data may have different formats and units, and the timing and frequency of data collection may also vary. Therefore, a normalization process may be necessary to increase data reliability and facilitate analysis.

[0042] The normalization operation can first perform unit conversion. If the weight entered by the user is stored in kg units, while the wearable device provides it in lb units, the weight data can be converted to the same unit. For example, data in pounds can be converted to kg units through the operation lbs / 2.20462. Similarly, if blood glucose data is a mix of mg / dL and mmol / L units, it can be converted to a single unit system by applying mg / dL = mmol / L × 18.

[0043] Next, time alignment and interpolation can be performed. While a user's exercise records may be recorded on a daily basis, step count data from a wearable device may be provided in minute units. Therefore, the two data can be converted to allow comparison by adjusting the time interval. Additionally, if weight data is not recorded on some dates, linear interpolation can be applied to predict and compensate for missing values.

[0044] During the data format integration process, data can be converted into a consistent format. If blood pressure data is provided in a string format such as "120 / 80", it can be converted into individual values ​​such as "systolic blood pressure: 120, diastolic blood pressure: 80". Additionally, if some temperature data is stored as integers and some is provided with up to two decimal places, consistency in analysis can be ensured by aligning all data to two decimal places.

[0045] The normalization process may also include the handling of missing values. If blood pressure or heart rate values ​​are not recorded on a specific date in a user's health data, these can be supplemented. Methods for supplementing missing values ​​may include utilizing the user's historical data, replacing missing values ​​based on data from similar user groups, or predicting missing values ​​using machine learning algorithms. When using machine learning models such as Random Forest or K-Nearest Neighbors (KNN) algorithms, missing values ​​can be replaced more precisely by learning the correlations between multiple variables.

[0046] Data normalization can be performed as the final step of the normalization process. This is a process designed to improve analysis accuracy by converting health data into a specific range. For example, Min-Max Normalization can be applied to convert data values ​​into a range between 0 and 1. When normalizing heart rate data (minimum 50, maximum 180) into values ​​between 0 and 1, a transformation as shown in Equation 1 below can be applied.

[0047]

[0048] In addition, Z-score normalization using the mean and standard deviation can be applied. When converting blood pressure data with a mean of 100 and a standard deviation of 15 into a standard normal distribution, a normalization method such as Equation 2 below can be used.

[0049]

[0050] Through this normalization process, differences in data can be corrected, and the reliability of health status assessments can be enhanced. For example, if weight data entered by a user via an app is mixed with weight data provided by a smart scale, the following transformations can be performed during the normalization process. First, data in lbs units can be converted to kg units, and then linear interpolation can be used to supplement values ​​for dates when weight was not recorded. Subsequently, all weight data can be converted to two decimal places, and a normalization process using the mean and standard deviation can be applied to transform the data so that it can be utilized by machine learning models.

[0051] A normalization operation according to one embodiment may include data unit conversion, time alignment, data format integration, missing value compensation, and normalization processing. Through such a normalization process, more accurate health status analysis may be possible in a user-customized health management service, and the reliability of setting execution goals and providing customized solutions may be enhanced.

[0052] In step (220), a server (120) according to one embodiment may calculate a user's health status as a quantified indicator by applying weights based on normalized data. Below, the quantified indicator may be referred to as a health score. In the process of quantifying the health status, a method of applying differential weights to specific elements in the user's health data according to their importance may be used. For example, for a user with a chronic disease, the weights for blood pressure and blood sugar data may be set high, and for a user for whom physical activity is important, the weights for step count and exercise records may be increased. The quantified indicator can help objectively evaluate the user's health status and can be used as basic data for setting specific health goals.

[0053] The process of calculating specific health indicators may include a step of applying a weighting factor that reflects the importance of the data. When evaluating a user's health status, it may not be desirable for all data to have equal weight. For example, for a user with a chronic disease, blood pressure and blood sugar data may be more important factors, and different weights may be applied compared to users managing their general health status. Therefore, in one embodiment, weights may be applied differently depending on the user's health status, age, gender, lifestyle habits, etc.

[0054] The method of quantifying health status by applying weights to each data element can be defined as shown in Equation 3 below.

[0055]

[0056] Here, H is the finally calculated health status indicator, X1, X2, ..., Xn are normalized health data, and w1, w2, ..., wn are weights applied to each data element. For example, when evaluating the health status of a specific user, weight, heart rate, blood pressure, number of steps, and sleep time may be considered, and weights may be set for each data element. For example, if the weight for weight (kg) is 0.2, the weight for heart rate (bpm) is 0.3, the weight for blood pressure (mmHg) is 0.4, and the weight for number of steps (steps) is 0.1, and the user's normalized weight value is 0.7, heart rate value is 0.6, blood pressure value is 0.8, and number of steps value is 0.4, then the health status indicator can be calculated as shown in Equation 4 below.

[0057]

[0058] The health status indicators calculated in this way can numerically represent the user's current health status and can be used to evaluate the user's health status by comparing it with certain standards.

[0059] In addition, in one embodiment, health status indicators can be corrected by utilizing a user's past health data and data from a similar user group. For example, if a specific user's health status indicator shows a rapid change in the short term, outliers can be filtered by calculating a moving average of the past 7 days. It may also be possible to adjust weights based on data from a similar user group. For example, if there is a tendency for blood pressure to be high on average among a user group with the same age group and lifestyle habits, a more realistic health status indicator can be calculated by adjusting the weights of a specific user's blood pressure data.

[0060] Based on health status indicators, the user's target state and current state can be compared to set action goals, which can then be utilized to provide customized health management solutions. Through this, the present invention enables more precise analysis of individual users' health status and the provision of more effective health management services.

[0061] In step (230), a server (120) according to one embodiment may calculate the difference between the user's current state and the target state based on the calculated indicators, and set an execution goal based on the difference. The execution goal may include specific criteria that can be set to promote the user's health, for example, target weight, target blood pressure, target number of steps, target calorie intake, target sleep time, etc. These execution goals may be used as indicators to improve the user's health status and may be set dynamically by reflecting the user's individual situation and feasibility, rather than being simple standard values.

[0062] Various factors can be considered in the process of analyzing the difference between a user's current state and their target state. For example, if a user's health indicators show a consistent pattern, past data can be analyzed to gradually adjust the goal. If a user's weight has decreased by an average of 1 kg per month over the past six months, an action goal can be set to maintain the same rate of decrease; conversely, if weight changes are inconsistent, the rate of weight loss can be adjusted, or the goal can be modified to a realistic range.

[0063] In addition, the user's lifestyle habits and environmental factors may be reflected in the process of setting execution goals. If a user's job involves primarily sedentary work, setting a goal of walking 10,000 steps a day may not be realistic. In this case, the target number of steps can be adjusted to 7,000, or instead, periodic stretching and simple exercises can be set as goals. On the other hand, for users who are frequently outdoors, a high exercise volume goal can be set, and additional physical activity may be recommended as needed.

[0064] When setting execution goals, the server (120) may also consider the user's past goal achievement history. If the user has consistently achieved previously set goals, the difficulty of the goal may be gradually increased. For example, if the user has achieved the goal of walking 5,000 steps every day for 4 consecutive weeks, the goal may be adjusted to 7,000 steps in the next month. Conversely, if the goal achievement rate is low or the user is unable to repeatedly perform the set goals, the difficulty of the goal may be lowered or the goal setting method may be changed.

[0065] Action goals can be provided not only based on numerical criteria but also in an optimized manner that considers the user's health condition. For example, if a user has high blood pressure, instead of simply setting a target blood pressure value, specific action goals to lower blood pressure can be established. By adding goals such as walking for more than 30 minutes a day, limiting salt intake to 5g or less per day, and restricting caffeine intake, a specific action plan to achieve the target blood pressure can be established.

[0066] Furthermore, execution goals can be set based not only on the user's current status but also on available resources. For example, if a user is unable to access a gym, they can set exercise goals that can be performed indoors, or set strength training as an alternative goal instead of aerobic exercise. Considering the user's dietary habits, if they do not consume specific foods, a diet plan containing substitute nutrients can be set as a goal.

[0067] In one embodiment, changes in the user's continuous health status may be reflected during the process of setting execution goals, and goals may be dynamically adjusted as needed. For example, if a user fails to perform a specific exercise goal, the goal may be partially modified or an alternative goal with a high probability of success may be suggested. If the user's goal achievement rate is consistently low, the goal itself may be adjusted to a realistic range, while conversely, if the goal achievement rate is high, a challenging goal may be presented.

[0068] In this way, in one embodiment, the difference between the user's current state and the target state can be analyzed to set customized execution goals that consider feasibility and sustainability. Through this, the user can perform health management based on realistically achievable goals and receive support to continuously monitor and adjust the process of achieving the goals.

[0069] In step (240), a server (120) according to one embodiment may provide a customized health management solution based on the user's health data in conjunction with an execution goal. The customized health management solution may be provided in an optimized form for each individual, taking into account the user's health status, the likelihood of achieving the goal, past behavioral patterns, etc., and may support the user in efficiently achieving the execution goal.

[0070] Health management solutions can include various elements centered around the user's health goals. For example, if the user's goal is weight loss, the solution may be provided in the form of personalized exercise plans, dietary recommendations, methods for improving lifestyle habits, and health monitoring. If the user's goal is blood pressure management, it may include customized guidelines such as a low-sodium diet, recommendations for aerobic exercise, and improvements to sleep patterns.

[0071] The server (120) can continuously monitor the user's real-time behavior data to evaluate the effectiveness of the health management solution and, as needed, adjust the execution goal or create a new alternative solution. For example, if a user has set a specific exercise goal (e.g., walking for 30 minutes a day) but fails to consistently achieve the goal as a result of real-time data analysis, the server can provide an alternative solution by adjusting the difficulty of the goal. By analyzing the user's exercise pattern, the server can also suggest aerobic exercises that can be performed indoors (e.g., cycling, climbing stairs) instead of walking.

[0072] The customized health management solution can be optimized by taking into account the user's behavioral patterns and environmental constraints. For example, if the user is in an environment where outdoor exercise is difficult, the server (120) can suggest an exercise program that can be performed at home. If the user does not prefer a specific diet or cannot consume certain ingredients due to reasons such as allergies, a diet containing alternative nutrients may be recommended.

[0073] When providing customized health management solutions, the server (120) can utilize collaborative filtering or content-based recommendation algorithms to analyze data from user groups with similar health conditions and derive effective health management plans. For example, if a user prefers a specific type of diet (e.g., Mediterranean diet), the server can recommend a diet plan that has been proven effective in a user group that prefers the same diet.

[0074] The health management solution can be continuously adjusted by reflecting user feedback. For example, if a user feels discomfort after performing a specific exercise program, the exercise intensity can be adjusted or alternative exercises can be suggested by reflecting that feedback. The server (120) can optimize the health management solution through interaction with the user and support the user in achieving their goals.

[0075] As such, in one embodiment, a customized health management solution is provided based on the user's health data, and the solution can be continuously adjusted by reflecting real-time behavioral data and feedback. Through this, the user can achieve health goals in a more efficient manner and receive optimal health management services tailored to individual characteristics.

[0076] FIG. 3 is a diagram illustrating a customer health loop of a user-customized health management service according to one embodiment. The description with reference to FIG. 1 and FIG. 2 can be substantially applied to FIG. 3.

[0077] The cycle process of a user-customized health care service according to one embodiment may consist of a series of steps including recognizing the user's health condition (310), analyzing the cause of the health condition (320), setting an action goal (340), and providing a customized health care solution (330).

[0078] As illustrated in FIG. 3, in the health awareness stage (310), a health score (310) may be calculated to evaluate the user's health status. The health score (310) may be generated by applying weights based on the user's health data and may be used as an indicator to quantitatively express the health status. The score may be calculated based on data such as the user's physical condition, exercise habits, eating habits, and sleep patterns, and the higher the value of the health score (310), the better the health status may be judged. For example, the health score (310) may be quantified as a value between 0 and 100 by combining the user's step count, heart rate, blood pressure, and diet data, and if this value is below a certain standard, it may be judged that health improvement is needed.

[0079] After the health score (310) is calculated, factors related to the user's health status can be analyzed in the cause understanding step (320). By performing dietary habit typification (320), the user's eating patterns can be analyzed and the impact on the health status can be evaluated. Dietary habit typification (320) may be a process of analyzing the user's eating patterns and evaluating the impact on the health status. The user's dietary data may be collected in various ways and may include dietary records entered directly by the user, collected nutritional data, food order records, and intake data through smart wearable devices. By analyzing this data, the user's dietary habits can be classified into specific types, and a customized guide for health improvement can be provided.

[0080] Dietary habit classification (320) may be a process of deriving specific patterns, and the user's eating patterns may be evaluated from various angles using machine learning models or statistical analysis. If the user has an excessive intake or deficiency of specific nutrients, dietary habit classification (320) may recognize this and suggest ways to improve the eating habits. For example, if carbohydrate intake is excessive, dietary habit classification (320) may determine that the user belongs to the "high-carbohydrate dietary habit type," and accordingly, a guide may be provided to supplement a diet containing protein and fiber.

[0081] After the user's health status and its causes are analyzed, a customized health management solution can be generated in the solution provision stage (340). AI coaching (340) can set action goals based on the user's health status and analyzed cause data, and provide guidance for health improvement. AI coaching (340) can evaluate the user's likelihood of achieving goals and generate an action plan to reduce the gap between the user's current state and the target state. For example, if the user's health status is analyzed to have deteriorated due to unbalanced nutrition, AI coaching (340) can set specific diet improvement goals and provide a customized nutrition management plan linked to the food ingredients preferred by the user.

[0082] After the solution provided to the user is executed, the effectiveness of the solution is analyzed in the improvement verification step (330), and if necessary, customized feedback may be provided. The customized recommendation (330) may provide additional improvement measures by analyzing whether the user has achieved their execution goals and changes in their behavior. For example, if the user has not consistently achieved their set exercise goals, the customized recommendation (330) may be provided by adjusting the exercise intensity or recommending alternative exercises.

[0083] Personalized recommendations (330) and AI coaching (340) can interact with the user through personalized comments based on a Large Language Model (LM). The LLM-based personalized comments can operate by analyzing the user's behavioral data and providing feedback linked to health goals. For example, if the user achieves a set diet goal for a certain period, the LLM-based personalized comments can provide feedback such as, "Great progress. Try adding a new diet while maintaining your goal." Conversely, if the goal achievement rate is low, it can provide a message such as, "Your current goal might be too difficult. How about adjusting your goal or starting with a smaller goal?"

[0084] The cyclic process of a user-customized health management service according to one embodiment can be configured so that the process of evaluating a user's health status and providing a customized health management solution based on the analyzed results can be carried out cyclically. Feedback may be provided repeatedly until the user's health status improves, and health goals may be continuously adjusted. Through this, the user can perform personalized health management and receive continuous AI-based health management support.

[0085] FIG. 4 is a diagram illustrating the process of evaluating a user's health status and calculating a Health Score according to one embodiment. The description with reference to FIG. 1 to 3 can be substantially applied to FIG. 4.

[0086] Referring to FIG. 4, the configuration illustrated in FIG. 4 can be divided into a data and model processing step and a health score calculation step, each of which may be a process of analyzing and evaluating the user's health data to ultimately predict a score and provide coaching for health improvement.

[0087] In the data and model processing stage, various data may be utilized to evaluate the user's health status. As illustrated in FIG. 4, meal data, exercise data, and medical examination data may be input. Meal data may include information such as the nutritional components of the food consumed by the user, intake patterns, and types of dietary habits, while exercise data may include data such as the user's physical activity level, exercise intensity, frequency, and duration. Medical examination data may include health information provided by medical institutions, such as blood pressure, blood sugar, and body composition analysis results.

[0088] The server (120) can analyze input data and process it in a judgment classification model (e.g., XGBoost & FTTransformer) and a score prediction model (e.g., XGBoost). The judgment classification model can evaluate the user's health status according to specific criteria, for example, a specific user's eating pattern can be classified into types such as "high-carbohydrate diet," "balanced diet," and "low-protein diet." Exercise data can also be classified into categories such as "high-intensity exercise," "low-intensity aerobic exercise," and "lack of exercise" according to the user's activity level.

[0089] The score prediction model (XGBoost) can calculate a user's health score based on the output of the judgment classification model. Using a machine learning-based model, it can learn the relationships between input data and predict scores by reflecting the user's specific health indicators (e.g., Body Mass Index, heart rate, blood pressure, etc.).

[0090] The server (120) can calculate the user's health score based on a judgment classification model and a score prediction model. As illustrated in FIG. 4, the health score can be calculated by combining the individual evaluation results of the nutrition score, exercise score, and health score.

[0091] A nutrition score according to one embodiment may be calculated in a rule-based manner. The balance of specific nutrients (e.g., carbohydrates, protein, fat, minerals, etc.) in a user's diet may be evaluated, and a score may be assigned in comparison to nutritional recommendations. For example, if a user's daily protein intake is 80% or more of the recommended intake, a bonus point may be awarded in the nutrition score. On the other hand, if a specific nutrient (e.g., sodium) exceeds the recommended amount, a penalty point may be applied.

[0092] An exercise score according to one embodiment can be calculated using a rule-based method. The score can be calculated by evaluating the user's exercise frequency, intensity, duration, etc. For example, a user who performs moderate-intensity exercise three or more times a week may receive a high score, while a user with insufficient exercise may receive a low score.

[0093] A health score according to one embodiment can be calculated using a machine learning-based predictive model (e.g., XGBoost). The health score can evaluate specific health risk factors by analyzing the user's medical examination data and quantify the user's health status. For example, a user with a body mass index (BMI) within the normal range and stable blood pressure may receive a high health score, but a user with high blood sugar levels may receive a low health score.

[0094] After individual nutrition scores, exercise scores, and health scores are calculated according to one embodiment, the server (120) can integrate them to calculate a comprehensive score (e.g., model prediction score). The comprehensive score may be a sum of the individual scores with weights applied, and specific weights may be applied differently depending on the user's health status and data characteristics. For example, in the case of a user with a chronic disease, the weight of the health score may be set relatively high.

[0095] After the health score is calculated, the server (120) can provide feedback for predicting changes in the user's health status and improving health. Predicting changes in the score may be a process of analyzing the user's health data patterns to predict future changes in the health score. For example, if the user's exercise score has continuously increased over the past three months, it may be predicted that the overall score is likely to improve in the future. On the other hand, if the recent eating habit score has decreased, it may be analyzed that the overall score is likely to decrease. Coaching and recommendations may be a process of providing customized feedback based on the user's health status. Based on the health score, the server (120) can identify areas that the user needs to improve and provide customized health management solutions. For example, if the user's nutrition score is low, a diet rich in protein and dietary fiber may be recommended, and if the exercise score is low, physical activities that can be easily performed in daily life (e.g., climbing stairs, walking, etc.) may be suggested.

[0096] The health score calculation process can be repeated periodically and reflect changes in the user's health status in real time. Based on the health score, users can continuously manage their health status and achieve their goals by applying customized health management solutions.

[0097] FIG. 5 is a diagram illustrating a method for determining dietary habit typification according to one embodiment. The description with reference to FIG. 1 to 4 can be substantially applied to FIG. 5.

[0098] The method illustrated in FIG. 5 may include a process of classifying types based on the user's meal data, exercise data, and medical examination data, and a process of determining the user's dietary habit type information (e.g., NBTI type) based thereon.

[0099] A server (120) according to one embodiment can collect a user's meal data, exercise data, and medical examination data to analyze the user's health status and lifestyle habits. Meal data may include the composition of nutrients consumed by the user, meal times, types of food, etc., and exercise data may include information such as exercise intensity, frequency, and duration. Medical examination data may include medical data such as blood pressure, blood sugar, body mass index (BMI), and cholesterol levels.

[0100] The server (120) can cluster the types of users' eating habits by applying a type classification model (e.g., K-means clustering model) based on the collected data. K-means clustering may be a method of grouping data that have similar patterns in multidimensional data. As illustrated in FIG. 5, the type classification model may form multiple (e.g., 8) clusters, and each cluster may represent a group of users with similar eating habits and health conditions.

[0101] For example, if a specific user exhibits a pattern of high carbohydrate intake, that user can be classified as the "high-carbohydrate diet group." Conversely, a user with high protein intake and low fat intake can be classified as the "high-protein, low-fat diet group." In this way, type classification models can analyze users' dietary patterns and form groups with similar health characteristics.

[0102] The server (120) can determine the user's NBTI type based on the output of the type classification model. Like MBTI, NBTI can be classified into a total of 16 types by utilizing four attribute groups, and each type can reflect the user's dietary tendencies and nutritional balance patterns. The user's data can be input into the type classification model after undergoing a normalization process, and the server (120) can analyze the user's characteristics and assign an appropriate type using the type classification model based on the collected data.

[0103] The NBTI classification method may include four attribute axes to reflect the user's dietary tendencies. The first attribute relates to the level of stimulation preferred by the user, which can be divided into cases where one prefers mild (Mild, M) foods and cases where one prefers spicy / salty (Spicy / Salty) foods. The second attribute relates to nutrient intake and can be classified into cases where one consumes a relatively nutrient-rich diet (Enough, E) and cases where one consumes a nutrient-deficient diet (Insufficient, I). The third attribute relates to the diversity of ingredients and can be divided into cases including a variety of ingredients (Diverse, D) and cases preferring only limited ingredients (Finicky, F). The fourth attribute represents the weight of ingredients and can be divided into cases where one prefers light cooking methods (Light, L) and cases where one prefers heavy cooking methods (Heavy, H). A total of 16 NBTI types can be generated through the combination of these attributes, and each type can be used to analyze the user's dietary habits and nutritional balance patterns.

[0104] The server (120) can quantitatively analyze the health characteristics of users using NBTI types and evaluate the association with health problems such as obesity, diabetes, blood pressure, and dyslipidemia. For example, a type that prefers spicy food (S), lacks nutrients (I), mainly consumes only specific ingredients (F), and eats meals prepared with heavy cooking methods (H) can be classified as a group with a high risk of obesity. On the other hand, a type that prefers bland food (M), consumes sufficient nutrients (E), includes various ingredients (D), and eats meals prepared with light cooking methods (L) can be analyzed as a group that is advantageous for maintaining health.

[0105] This type classification can be utilized to provide customized health management solutions based on users' health data. For example, specific health goals can be set based on a user's NBTI type, and action plans can be established to achieve those goals. Additionally, personalized health management strategies can be proposed by analyzing behavioral data from groups with similar types to the user. Results regarding the user's goal achievement rate, changes in health status, and the analysis of the effectiveness of customized health management solutions can also be presented as a visual dashboard, allowing users to intuitively monitor their health status.

[0106] FIG. 6 is a diagram illustrating the operation of a comment generation LLM (large-scale language model) according to one embodiment. The description with reference to FIG. 1 to 5 can be substantially applied to FIG. 6.

[0107] Referring to Fig. 6, dietary, exercise, and health checkup data can be utilized as input data, and the LLM can analyze this to generate health score reporting comments, comprehensive health score comments, and dietary habit type reporting comments. Through this, users will be able to understand their health status more intuitively and establish customized health management strategies.

[0108] More specifically, the server (120) may collect the user's health-related data and provide it as input to a comment-generating LLM (e.g., Llama3). The input data may include the user's meal data, exercise data, and health checkup data for the past week. The meal data may include the type of food consumed by the user, nutrient composition, time of consumption, diet pattern, etc., and the exercise data may include information such as exercise intensity, frequency, and duration. The health checkup data may include data such as blood pressure, blood sugar, body mass index (BMI), and cholesterol levels.

[0109] The server (120) can structure input data and provide it to the LLM, and based on this, evaluate the user's health status and generate customized comments. For example, if the user's diet consumed over the past week has a high carbohydrate ratio and insufficient protein intake, the LLM can generate feedback such as, "The carbohydrate ratio in your recent diet was found to be high. Increase your protein intake and recommend a balanced diet containing various nutrients." If the user has barely performed any exercise over the past week, it can provide comments such as, "It was analyzed that your exercise volume has decreased. It may be helpful to start with light aerobic exercise and gradually increase your activity level."

[0110] The server (120) can classify the comments generated by the LLM and output them as health score reporting comments, health score comprehensive comments, and dietary habit type reporting comments. Health score reporting comments can evaluate the health status based on the user's health score and provide feedback on the current status, and can be provided in a form such as, "The current health score is 72 points, which is 5 points lower than last week. The decrease in exercise volume and changes in diet are analyzed as the main causes." Health score comprehensive comments can comprehensively analyze the user's health data and suggest directions for improvement, and comments such as, "Nutrient intake has been maintained in balance over the past week, but sodium intake tends to be somewhat high. It is advisable to consider a low-salt diet." Dietary habit type reporting comments can classify the user's dietary habits into a specific type and suggest improvements, and feedback such as, "The recent dietary habit type is classified as a 'high-carbohydrate diet.' Increasing protein and fiber intake can help with health management."

[0111] The server (120) can periodically generate new comments based on changes in the user's health status and can customize the comment content as needed. Additionally, if the user provides feedback on the provided comments, the server (120) can update the training data of the LLM to reflect this. For example, if the user evaluates that the provided comments differ from the actual health status, the server (120) can adjust the comment generation algorithm based on this or generate more precise feedback by reflecting additional user data.

[0112] FIG. 7 is a diagram illustrating the execution process of a user-customized health management service according to one embodiment. The description with reference to FIG. 1 to 6 can be substantially applied to FIG. 7.

[0113] The process illustrated in Fig. 7 may consist of a series of steps that analyze the user's health data, provide customized coaching, and link with health management solutions.

[0114] Referring to FIG. 7, a server (120) according to one embodiment can calculate a health score by collecting a user's meal data, exercise data, and health checkup data for the past week. The health score can be used as an indicator to quantitatively evaluate the user's health status and can be provided in the form of a specific score. For example, a score between 0 and 100 can be calculated based on the user's nutritional balance, physical activity level, and health metrics, and in FIG. 7, the score can be displayed as "82 points (Good)". In addition, the server (120) can analyze the health score by detailed indicators to evaluate the user's health status more specifically.

[0115] After the health score is calculated, a dietary habit typification process can be performed to analyze the user's eating patterns and evaluate their relationship with their health status. As illustrated in Fig. 7, dietary habit typification can classify the user's dietary habits into specific types by utilizing an NBTI-based health statistical analysis index. If the user overconsumes or is deficient in specific nutrients, such information can be presented visually, and based on this, customized health improvement measures can be suggested.

[0116] The server (120) can perform AI coaching and personalized recommendations based on analyzed data. AI coaching can analyze the user's health data to provide personalized diet, exercise, and lifestyle improvement methods. Users can view their individual exercise data on the "My Exercise Coach" screen and receive specific coaching based on data such as the average number of steps taken over the past week. For example, if the user's exercise volume has decreased recently, AI coaching can recommend light aerobic exercise and may also recommend adding specific strength training exercises.

[0117] The server (120) can provide health-related product recommendation and purchase linkage functions in conjunction with AI coaching. Users can check health management products linked to AI coaching through the "Health Recommendation Shop" screen and, if necessary, purchase the recommended products directly. For example, if it is analyzed that the user has insufficient protein intake, the AI ​​coaching can recommend a protein supplement, and the product can be linked so that it can be purchased directly from the Health Recommendation Shop.

[0118] Users can check their health scores, analyze their dietary habits, and receive personalized health management methods through AI coaching. Additionally, the system may include features that allow users to receive recommendations for health management products in conjunction with AI coaching and purchase products when necessary. The server (120) can continuously analyze the user's health data to provide optimal health management solutions in real time, and users will be able to perform more effective health management based on this.

[0119] FIG. 8 is a diagram illustrating the process of generating answers using LLM in a user-customized health management system according to one embodiment. The content described with reference to FIG. 1 to 7 can be substantially applied to FIG. 8.

[0120] Referring to Fig. 8, the user can input questions related to meals, exercise, and health checkups through a conversation manager (user interface). For example, if the user inputs a question such as "Recommend a lunch menu suitable for a man in his 60s," the system can convert the question into a form that the LLM can process and pass it to a retrieval manager so that relevant information can be searched.

[0121] A search manager according to one embodiment can search for relevant documents based on user questions. In this process, documents stored in a vector store may be utilized, and document search may be performed using vector data generated during the process of building a vector database. The vector store may include various documents related to health management, such as nutrition guides, exercise guides, and health checkup guides, and these documents may be stored in a vectorized form.

[0122] Once the search is complete, the search manager can provide the retrieved documents to the LLM fine-tuning model. Based on the retrieved documents, the LLM fine-tuning model can generate answers to user questions; it can not only provide simple information but also generate customized responses based on the chatbot's interaction characteristics (sentiment logic, pattern-based conversation). For example, if the user's question is "What kind of exercise helps with blood pressure management?", the LLM can extract exercise information related to blood pressure management from the retrieved documents and generate an answer in the form of, "Aerobic exercise can be helpful for blood pressure management. For example, exercises such as brisk walking, swimming, and cycling may be recommended."

[0123] Answers generated by the LLM can be provided to the user through a conversation manager (user interface) and may also function in a way that prompts additional questions to continue interaction with the user. For example, if the user enters a follow-up question such as "Then, how many minutes should I exercise a day?" based on the provided answer, the search manager performs an additional search, and the LLM can generate a new answer.

[0124] The system illustrated in Fig. 8 may include a data preprocessing process. A data preprocessing unit collects documents such as nutrition guides, exercise guides, and medical examination guides, and refines them into a form that can be processed by an LLM. The refined documents can be stored in a vector store through the construction of a vector DB, and a search manager can search for and utilize the documents when needed.

[0125] FIG. 9 is a drawing illustrating a user interface for data collection and goal setting in a health management service application according to one embodiment. The description with reference to FIG. 1 through 8 can be substantially applied to FIG. 9.

[0126] Referring to FIG. 9, the user can input their health-related data through the screen (910). The screen (910) may provide a summary of the user's health status, for example, the user's current health score (e.g., 82 points) may be displayed in the "My Health Status" section. Additionally, the user's dietary type (e.g., NBTI-based dietary type) may be provided, allowing the user to check their current health status more intuitively. The user can set personalized health goals by selecting the "Set Goal (911)" button.

[0127] When the user selects the goal setting function, a health questionnaire screen (920) may be provided. The health questionnaire may include questions to evaluate the user's health status and lifestyle habits, and may include questions regarding specific dietary habit elements (e.g., obesity, fat intake) as illustrated in FIG. 9. The user may select a response to each question, and the selected response may be stored in the system and utilized for health status analysis and personalized coaching. The health questionnaire may be used as a process to collect additional data to analyze the user's health status more precisely.

[0128] When the health questionnaire input is completed, the health questionnaire results (930) may be provided to the user. The health questionnaire results may be a summary of the results analyzed based on the user's health data and survey responses, and may provide guidance on health management points that the user should currently pay attention to. For example, a comment such as "Based on the analysis of 000's health data and survey results, managing high blood pressure may be important" may be provided.

[0129] When a user sets a goal based on a health questionnaire, the system can generate a customized guide for improving the user's health and subsequently evaluate whether the user has achieved the goal through continuous health monitoring.

[0130] FIG. 10 is a diagram illustrating an interface for querying a user's status in a health management service application according to one embodiment. The contents described with reference to FIG. 1 to 9 can be applied in the same way to FIG. 10.

[0131] The user can check their health status through the screen (1010), and the user's health score (1011) may be displayed on the screen. The health score is a value that quantitatively evaluates the user's health status and may also visualize changes over a specific period as a graph. For example, the user's health score may be displayed as "82 points," and weekly or monthly trends may be checked through the graph. Additionally, the user can add or modify health goals by selecting the "Set Goal" button.

[0132] To check the progress of health goals (1012), the user can view data recorded during a specific period. For example, if the "Check May Record Achievement Status" button is selected, the user's health goal achievement rate may be displayed. Whether the goal has been achieved can be automatically evaluated by comparing it with health data entered by the user (e.g., amount of exercise, meal records, weight changes, etc.), and items that have been achieved and items that have not been achieved can be displayed separately.

[0133] When a user checks the health board screen (1030), health data for that date can be provided in detail. For example, when viewing health data for May 19, 2024, information such as health scores, meal records, and exercise records for that date can be provided. The user can check calorie information for breakfast, lunch, and dinner, and can also view detailed nutritional information for specific meals. For example, it can be confirmed that "1,504 kcal" was consumed for breakfast and that "egg and dried pollack soup and 4 other types" were included as main foods.

[0134] FIG. 11a is a diagram illustrating an interface that provides AI-based coaching and personalized recommendations in a health management service application according to one embodiment, and FIG. 11b is a diagram illustrating an interface that monitors a user's health management challenge and provides feedback. The description with reference to FIG. 1 to 10 can be applied equally to FIG. 11a and FIG. 11b.

[0135] Referring to Fig. 11a, the user can receive AI coaching through the healthy concierge service screens (1110, 1120, 1130). The AI ​​coaching can provide personalized feedback and recommendations by analyzing the user's health data. For example, after analyzing the meal data recorded by the user, feedback such as "Looking at yesterday's meal record, you consumed an average of 1600 kcal and ate spicy food" may be provided. Along with this, alternative food options that the user can choose from may also be recommended.

[0136] When a user requests exercise-related coaching, the AI ​​coaching can suggest appropriate exercise methods by taking into account the user's schedule and exercise habits. For example, if the user inputs "I don't have enough time to exercise," the AI ​​coaching can recommend "ways to burn calories by utilizing walking time during daily activities" and can also guide the user toward actionable goals such as "walking 10 minutes more during the commute."

[0137] The health management solution may also include a personalized product recommendation feature. For example, the recommendation product interface (1130) may recommend health supplements or related products that the user may need based on health data analyzed by AI. The user can view the recommended products and purchase them as needed, and the AI ​​may also provide the reason for the product recommendation.

[0138] Referring to FIG. 11b, the user can have their current health management compliance evaluated through the record rating screen (1140) and check feedback provided by the AI. For example, the results of checking the user's challenge progress may be provided along with a notification that "feedback arrived on May 19."

[0139] Users can check their health management habits through AI coaching on the healthy concierge service screen (1150) and receive personalized feedback. The AI ​​can analyze the user's activity data and suggest actionable goals, for example, by providing an analysis result such as "You walked 2,600 steps out of a goal of walking 5,000 steps a day" and providing feedback such as "It would be good to aim for 3,000 steps tomorrow."

[0140] FIG. 12 is a diagram illustrating an interface for providing a health score in a health management service application according to one embodiment. The description with reference to FIG. 1 to FIG. 11b can be substantially applied to FIG. 12.

[0141] Referring to Fig. 12, the user can view their health score in a numerical form through the interface and visually understand the trend of score fluctuations.

[0142] On the health score screen (1210), a health score that quantitatively evaluates the user's health status may be provided. The user can check the health score for a specific week (e.g., week 24.05.2, 82 points) and can also check the trend of change based on past data in a graph. For example, the user can compare the health status over the past few weeks and determine whether the health status has improved or worsened in a specific week.

[0143] In the analysis result screen (1220) by indicator, individual health indicators constituting the health score may be provided in detail. For example, a health indicator reflecting the user's eating habits, such as "nutrition score (91 points)," may be displayed, and an analysis result for it may be provided. Additionally, if a specific health indicator is low, a customized guide to improve that area may be provided.

[0144] In the weekly health score comparison screen (1230, 1240), whether the user's health score exceeds a certain standard can be visually displayed. For example, in the example illustrated in FIG. 12, "exercise score 82 points" and "health score 75 points" are displayed respectively, and a notice may be provided indicating that the user should pay attention if a specific indicator is low. In this way, the user can comprehensively check their health status and determine whether improvement is needed for a specific indicator.

[0145] FIGS. 13a and 13b illustrate an interface that provides detailed analysis information by indicator of a health score in a health management service application according to one embodiment. The description with reference to FIGS. 1 to 12 can be applied substantially identically to FIGS. 13a and 13b.

[0146] Referring to Fig. 13a, the user can analyze their health condition more precisely through the interface and check the evaluation results and improvement plans for individual indicators.

[0147] In the indicator analysis result screen (1310), results evaluating the user's health status by detailed indicator may be provided. For example, the user's nutrition score may be evaluated as "91 points", and the analysis results for this may be provided. Based on the indicator, the user can determine their nutritional status and take measures for health management. The user may select the detailed analysis area (1311) to check additional details regarding a specific health indicator. When the user selects the detailed analysis area (1311), detailed analysis result screens by indicator (1320, 1330) may be provided.

[0148] In the detailed analysis results screen by indicator (1320, 1330), multiple detailed indicators can be comprehensively analyzed to evaluate the user's health status from various angles. For example, the user's health status may consist of six major indicators (e.g., nutrition, exercise, sleep, stress, weight management, blood pressure management), and the user can visually check the balance between each indicator through a radar chart. If the score of a specific indicator is relatively low, the user can consider measures to improve that indicator.

[0149] Referring to FIG. 13b, the user can select a change analysis result area (1312) to check the analysis results by indicator for a specific health indicator. When the user selects the change analysis result area (1312), a change analysis result screen by indicator (1340) may be provided.

[0150] In the indicator change analysis result screen (1340), results evaluating the user's health change status by detailed indicator may be provided. For example, comments such as "healthy meal score is 91 points, which is in the top 5% level, average calories per meal is 983 kcal, which is within the appropriate range, galbitang is the highest at 1,240 kcal, and chwinamul mushroom rice and smoked duck oat salad influenced the increase in score" may be provided.

[0151] FIG. 14 is a diagram illustrating a screen providing a dietary habit type interface in a health management service application according to one embodiment. The description with reference to FIG. 1 to FIG. 13b can be applied in the same way to FIG. 14.

[0152] Referring to Fig. 14, the user can analyze their eating habits through the interface, check trends in eating habits and detailed dietary patterns, and perform health management based on this.

[0153] In the dietary type analysis screen (1410), the user's dietary type can be classified based on NBTI. For example, the user's dietary type can be classified as "S, I, F, H," which indicates that the user prefers stimulating foods (Salty), consumes a diet lacking in nutrition (Insufficient), tends to prefer or avoid certain ingredients (Finicky), and frequently consumes foods prepared using heavy cooking methods (Heavy). The user can check their dietary type and compare it with other types.

[0154] In the detailed dietary habit analysis screen (1420), the user's dietary characteristics can be analyzed in more detail. For example, if the user's dietary habits include a preference for spicy or salty flavors at 70% or more, a diet lacking nutritional balance at 45% or more, a preference for specific ingredients at 35% or more, and a frequency of consuming heavy-cooked food at 32% or more, this information can be visually provided. In addition, regarding the type of dietary habits, a customized health guide such as "If there is a high preference for spicy flavors, salt intake needs to be controlled" may also be provided.

[0155] The eating habit type change screen (1430) can visually display the user's recent eating habit change trends. For example, if the user's eating habit change over the past six months has shifted from the "MEDL" type to the "SIFH" type, this can be provided in a graph or timeline format. Additionally, changes in eating habits for each period can be compared, and if a specific pattern appears repeatedly, it can be highlighted. For example, if the nutritional deficiency indicator continues to rise during a specific period, a warning message regarding this may be displayed.

[0156] In the eating habits check screen (1440), the average calorie intake and major dietary patterns may be provided based on the user's recent meal records. For example, if the user has recorded 5 meals during the past week and consumed an average of 1034 kcal, that information may be provided in the interface. Additionally, individual meal details recorded by the user (e.g., May 8th lunch: beef jjamppong, May 9th breakfast: budaejjigae, etc.) may be displayed, and if there is a need to improve the user's eating habits, feedback such as "Be careful!" or "Praise!" may be provided.

[0157] FIG. 15 is a diagram illustrating an interface that provides information on dietary habits different from those of a user in a health management service application according to one embodiment. The description with reference to FIG. 1 to FIG. 14 can be substantially applied to FIG. 15.

[0158] Referring to Fig. 15, the user can identify their eating habits type through this interface, compare it with other types, and receive recommendations for types that are good to eat with.

[0159] On the dietary habit type verification screen (1510), the user can select the other type viewing area (1511). If the user selects the other type viewing area (1511), the other type comparison screen (1520) may be provided.

[0160] In the comparison screen (1520) for other types, dietary habits different from the user's may be displayed. For example, various dietary types such as "MEFH", "MEFL", "MEDH", and "MEDL" may exist over the past six months, and types similar to or significantly different from the user may be provided together. The user can explore various types based on their own type, compare them with their own patterns, and set a direction for dietary changes.

[0161] Additionally, a feature recommending suitable dining partners may be provided. For example, if a user's type is "SIFH," the "SIDH" type may be recommended as a good dining partner. This feature is designed to help foster more balanced eating habits by matching users with individuals whose dietary patterns complement their own. For instance, if the "SIDH" type is classified as a "Relaxed Gourmet," users of this type may enjoy meals relatively slowly and prefer a variety of foods; this can serve to complement the user's hurried and stimulating eating habits.

[0162] FIG. 16 is a diagram illustrating an interface providing a healthy concierge function in a health management service application according to one embodiment. The description with reference to FIG. 1 through 15 can be substantially applied to FIG. 16.

[0163] Referring to FIG. 16, the user can check their record grade through the health board (1610) and receive a customized dietary management service using the healthy concierge (1611) function.

[0164] On the health board (1610), a record grade reflecting the user's health data may be displayed. For example, the user's record grade may be displayed as "Intern Grade," which may vary depending on the user's level of health data input and management. The user may select a healthy concierge (1611) to receive coaching for improving their health and eating habits.

[0165] Personalized health management coaching may be provided on the healthy concierge service screen (1620). For example, if the user's dietary type is analyzed as "SEDH," a recommendation comment may be displayed suggesting that it is advisable to reduce stimulating foods based on the food data consumed last week. Additionally, recommendations and feedback on specific meal menus may be provided, and the user may receive specific guidance to improve their dietary habits.

[0166] Users can review recommended meal patterns and set up a meal plan for the new week. For example, if a user consumed a large amount of spicy food and meat last week, the Healthy Concierge might provide feedback such as, "It is advisable to reduce the intake of spicy foods this week and develop a habit of leaving some broth and noodles behind." Such comments can help users continuously improve their eating habits and maintain healthy patterns. The user interface can be designed to allow users to easily view their health records, check coaching feedback, and improve their eating habits.

[0167] FIG. 17 is a diagram illustrating an interface for providing AI coaching through a healthy concierge in a health management service application according to one embodiment. The description with reference to FIG. 1 through 16 can be substantially applied to FIG. 17.

[0168] Referring to FIG. 17, the user's health score may be displayed on the initial screen (1710) of the healthy concierge page. For example, if the health score is analyzed as "62 points," the user can see that the score has decreased by -4 points compared to the previous week. If the user selects the "button to check ways to improve this week's health score (1711)" on this screen, an AI coaching screen (1720) may be provided.

[0169] In the AI ​​coaching screen (1720), methods to improve health scores may be provided. For example, "methods to reduce liquid fructose" and "methods to consume foods high in dietary fiber" may be recommended. The user can select methods to improve eating habits, and if the user selects the "button to receive recommendations for foods high in dietary fiber (1712)," the user can move to a screen (1730) containing a list of recommended products.

[0170] On the product recommendation screen (1730, 1740), products high in dietary fiber can be recommended based on the user's health data analyzed by AI. For example, "BBB products" may be recommended, and the user can check the reason for the recommendation or add the products to the shopping cart. If the user wants to receive more recommendations, they can select the additional product recommendation button, and additional products such as "CCC products" may be displayed.

[0171] FIG. 18 is a diagram illustrating an interface for providing AI coaching through a healthy concierge in a health management service application according to one embodiment. The description with reference to FIG. 1 to FIG. 17 can be substantially applied to FIG. 18.

[0172] Referring to FIG. 18, in a health management service application, a healthy concierge can provide customized health management coaching by analyzing the user's recent health data. On the chronic disease information screen (1810), comprehensive management plans can be provided based on the user's health data. For example, if an analysis of the user's eating habits reveals a deficiency in the intake of specific nutrients, coaching regarding this can be provided. After checking the coaching suggested by the AI, the user can select "methods to adjust carbohydrate intake ratios" and move to the in-house meal recommendation screen (1820).

[0173] On the company meal recommendation screen (1820), users can view personalized diet management guides provided by AI. For example, "how to reduce the intake of stimulating foods and maintain a balanced diet" may be provided. If the user wishes to receive more specific coaching, they can select "how to drink enough water" to move to the health knowledge content screen (1830).

[0174] On the health information content screen (1830), the appropriate daily water intake can be guided by taking into account the user's physical activity level and lifestyle habits. Based on AI coaching, the user can adjust their activity level or improve their water intake habits. In addition, continuous health management is possible through personalized coaching provided by the AI.

[0175] FIG. 19 is a diagram illustrating an interface for recommending a user's diet in a health management service application according to one embodiment. The description with reference to FIG. 1 to FIG. 18 can be substantially applied to FIG. 19.

[0176] Referring to Fig. 19, interconnected information can be provided depending on the user's selection.

[0177] Today's Menu screen (1910) is a screen that displays today's menu, and the user can select a specific date to check the menu for that date. A customized menu recommended by AI can be provided by taking into account the user's nutritional intake patterns and health data. The user can select a health-recommended menu in area (1911) or a taste-recommended menu in area (1912).

[0178] When the user selects the area (1911), they can move to the health recommendation menu screen (1920). The health recommendation menu screen (1920) is a screen that displays health recommendation menus, and AI can recommend a diet that takes health into account. For example, a salad that takes into account the balance of carbohydrates, protein, and fat can be provided as a health recommendation menu. This screen can provide information on the nutritional information, calories, and main ingredients of the menu, and the user can select a healthy diet by referring to this information.

[0179] When a user selects an area (1912), they can move to a taste recommendation menu screen (1930). The taste recommendation menu screen (1930) is a screen that displays taste recommendation menus and can recommend customized meals that reflect the user's preferences. For example, spicy pork neck and potato stew can be recommended for a user who prefers spicy food. The taste recommendation menu screen (1930) can also provide nutritional information and meal information for the menu so that the user can refer to them when selecting a meal.

[0180] FIG. 20 is a diagram illustrating an interface for providing AI-customized recommendations in a health management service application according to one embodiment. The description with reference to FIG. 1 to FIG. 19 can be substantially applied to FIG. 20.

[0181] Referring to FIG. 20, the health recommendation shop screen (2010) is a screen that displays a health recommendation shop interface, where AI recommendation (AI recommendation system) can suggest health products tailored to the user. For example, specific exercise aid products may be recommended based on the user's exercise volume and health data. The products are displayed along with their prices, and the user can select a recommended item to view detailed information. When the user selects an area (2011), they can move to a screen (2020).

[0182] Screen (2020) can display an AI coaching-based recommendation screen provided by the Health Recommendation Shop. The AI ​​can suggest appropriate products based on the user's health goals and interests. For example, if the user sets a goal of dieting or increasing muscle strength, health supplements suitable for this can be recommended. When the user selects area (2021), they can move to screen (2030).

[0183] The screen (2030) is a screen that displays a list of recommended products based on AI coaching, and several health products may be provided in a list format. After checking the price and basic information for each product, the user can select an individual product to view detailed information. Recommended products may be automatically recommended based on the user's health data, dietary habits, activity records, etc., and may be filtered according to specific criteria (e.g., price, rating, health goals).

[0184] The screen (2040) is a screen that provides detailed information about a specific product selected by the user, and may include images of the product, nutritional information, reasons for recommendation, etc. For example, if the user selects a specific protein supplement, the ingredients, calorie information, and method of consumption of the product may be displayed together. In addition, the AI ​​may provide text explaining why the product meets the user's health goals.

[0185] FIG. 21 is a diagram illustrating an interface for providing AI-customized recommendations in a health management service application according to one embodiment. The description with reference to FIG. 1 to 20 can be substantially applied to FIG. 21.

[0186] Referring to FIG. 21, the in-house meal recommendation screen (2110) can recommend specific menus based on the user's recent meal history and preferences. For example, if the user consumed spicy food the previous day, the AI ​​can recommend shrimp fried rice containing fresh vegetables and protein, considering the replenishment of energy and balanced nutrition. Along with a description of the recommended meal, the nutritional benefits of the food (e.g., low fat, high protein) can be provided. The user can select the recommended menu and purchase it for 12,000 won, and the menu can be added to the order list via the "Add" button.

[0187] On the health-related product recommendation screen (2120), appropriate products can be suggested by considering the user's health goals (e.g., blood sugar control). If the user wants to maintain healthy blood sugar levels every morning, the AI ​​can recommend the "ABC Blood Sugar Care" product. This product can contribute to maintaining overall health as well as blood sugar control, and a detailed description of this can be provided. The user can select the product and purchase it for 24,000 won, or press the "Add to Cart" button to add it to the cart.

[0188] FIG. 22 is an example diagram of the hardware configuration of a system for a user-customized health management service according to one embodiment. The description with reference to FIG. 1 to FIG. 21 can be substantially applied to FIG. 22.

[0189] The interfaces illustrated in FIGS. 5 to 21 are merely examples of one implementation method of a health management service application and are not limited thereto. The drawings represent some of the various methods of collecting and analyzing user health data to provide customized health management solutions, and the configuration of the interface may be changed according to the actual service environment or technical requirements.

[0190] For example, in addition to providing health scores and dietary habits types on separate screens, they may also be provided integrally on a single screen. Furthermore, the classification method or alphabetical display method of NBTI types shown in FIG. 5 may be changed according to customer preferences or service operation strategies, and other visual representations or category structures may be applied as needed. As such, the interface configurations of FIG. 5 to FIG. 21 are for convenience of explanation and may be subject to various modifications and changes.

[0191] Referring to FIG. 22, a system according to one embodiment (e.g., the system (100) of FIG. 1) may include a terminal (110) and a server (120) connected via a network (130).

[0192] A terminal (110) according to one embodiment may be a mobile terminal implemented as a computer device. For example, the terminal (110) may communicate with a server (120) and / or other electronic devices through a network (130) using a wireless or wired communication method.

[0193] A server (120) according to one embodiment may be implemented as a computer device or a plurality of computer devices that communicate with a terminal (110) and / or another server through a network (130) to provide commands, code, files, content, services, etc. The communication method is not limited and may include a communication method utilizing a communication network (e.g., mobile communication network, wired internet, wireless internet, broadcasting network) that the network (130) may include, and a short-range wireless communication method between devices. For example, the network (130) may include any one or more networks such as a PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet.

[0194] According to one embodiment, a server (120) may provide a file for installing an application to a terminal (110) connected via a network (130). In this case, the terminal (110) may install the application using the file provided by the server (120). Additionally, the terminal (110) may connect to the server (120) and receive services or content provided by the server (120) under the control of an operating system (OS) and at least one program (e.g., a browser or an installed application) included in the terminal (110). For example, if the terminal (110) transmits a service request message to the server (120) via the network (130) under the control of an application, the server (120) may transmit a code corresponding to the service request message to the terminal (110), and the terminal (110) may provide content to the user by configuring and displaying a screen according to the code under the control of the application.

[0195] According to one embodiment, the terminal (110) and the server (120) may include a memory (2211, 2221), a processor (2213, 2223), a communication module (2215, 2225), and an input / output interface (2217, 2227).

[0196] A processor (2213, 2223) according to one embodiment may perform at least one operation described above through FIGS. 1 to 21. For example, the processor (2213) may perform at least one operation performed in an instant messenger installed on the terminal (110) described above through FIGS. 1 to 21, and the processor (2223) may perform at least one operation regarding a user-customized health management service described above through FIGS. 1 to 21. For example, the processor (2223) may perform at least one of the following operations: normalizing data input by the user and collected data; calculating the user's health status as a numerical indicator by applying weights based on the normalized data; calculating the difference between the user's current state and the target state based on the calculated indicator and setting an execution goal based on the difference; and providing a customized health management solution based on the user's health data in conjunction with the execution goal. The processor (2213, 2223) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. The instruction may be provided to the processor (2213, 2223) by the memory (2211, 2221) or the communication module (2215, 2225).

[0197] The memory (2211, 2221) is a computer-readable recording medium and may be a volatile memory or a non-volatile memory. The memory (2211, 2221) according to one embodiment may store information for operating the application described above through FIGS. 1 to 21.

[0198] A memory (2211) according to one embodiment may include code for an application installed and run on a terminal (110) by files provided by a server (120) through a network (130).

[0199] A memory (2221) according to one embodiment can store a program in which operations for the user-customized health management service described above through FIGS. 1 to 21 are implemented.

[0200] A memory (2221) according to one embodiment may store commands, and when the commands are executed by a processor (2223), the server (120) may perform the steps of: storing user input data and collected data in the memory of the terminal and normalizing the data; generating a numerical indicator representing the user's health status by applying weights based on the normalized data; calculating the difference between the user's current state and target state based on the calculated indicator and setting an execution goal based on the difference; providing a customized health management solution based on the user's health data in conjunction with the execution goal; and outputting the customized health management solution through a user interface.

[0201] A communication module (2215, 2225) according to one embodiment may provide a function for a terminal (110) and a server (120) to communicate with each other through a network (130), and may provide a function for communicating with other electronic devices or other servers.

[0202] For example, a request generated by the processor (2213) of the terminal (110) according to program code regarding an application stored in a recording device such as memory (2211) can be transmitted to the server (120) through the network (130) under the control of the communication module (2215).

[0203] For example, control signals, commands, content, files, etc. provided under the control of the processor (2223) of the server (120) can be received by the terminal (110) through the communication module (2215) of the terminal (110) via the communication module (2225) and the network (130).

[0204] The input / output interface (2217, 2227) may be a means for interfacing with an input / output device (1219). For example, the input device may include a device such as a keyboard or a mouse, and the output device may include a device such as a display for displaying a communication session of an application. As another example, the input / output interface (2217) may be a means for interfacing with a device in which the functions for input and output are integrated into one, such as a touchscreen. As a more specific example, the processor (2213) of the terminal (110) may display a service screen or content configured using data provided by the server (120) in processing instructions of a computer program loaded in memory (2211) on the display through the input / output interface (2217). Input received from the user through the input / output device (1219) may be provided in a form that can be processed by the processor (2213) of the terminal (110) through the input / output interface (2217).

[0205] According to one embodiment, the terminal (110) and the server (120) may include other components not shown in FIG. 22. For example, the terminal (110) may be implemented to include at least some of the input / output devices (1219) described above, or may further include other components such as a transceiver, a Global Positioning System (GPS) module, a camera, various sensors, a database, etc.

[0206] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0207] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave in order to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on computer-readable recording media.

[0208] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination, and the program instructions recorded on the medium may be those specifically designed and configured for the embodiment or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0209] The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0210] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based thereon. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0211] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for providing a user-customized health management service comprising: a step of normalizing data entered by a user and collected data; a step of calculating the user's health status as a numerical indicator by applying weights based on the normalized data; a step of calculating the difference between the user's current state and target state based on the calculated indicator and setting an execution goal based on the difference; and a step of providing a customized health management solution based on the user's health data in conjunction with the execution goal. Claim 2 A method for providing a user-customized health management service, wherein the step of normalizing the data includes the step of standardizing the data entered by the user and the collected data so that comparison between different data types is possible. Claim 3 A method for providing a user-customized health management service according to claim 1, wherein the normalization step comprises: a step of calculating a weight suitable for replacing missing values ​​by analyzing the variability and correlation of the data entered by the user and the collected data when missing values ​​exist in the data entered by the user and the collected data; and a step of predicting and replacing missing values ​​in the user's past data and data of a similar user group based on the calculated weight. Claim 4 A method for providing a user-customized health management service, wherein, in claim 1, the normalization step includes a step of dynamically replacing missing values ​​through pattern learning considering multiple variables using a machine learning model when missing values ​​exist in the data entered by the user and the collected data. Claim 5 A method for providing a user-customized health management service, wherein the step of calculating the numerical indicator comprises: a step of dynamically calculating the relative importance of the individual elements by analyzing the correlation between the variability of the individual elements constituting the normalized data and the user's past health status; and a step of calculating the health status as a numerical indicator by reflecting the relative importance as a weight. Claim 6 A method for providing a user-customized health management service according to claim 1, wherein the step of setting the execution goal comprises: a step of analyzing execution patterns from the user’s past execution records to calculate the user’s execution probability value; and a step of setting the execution goal through a multi-variable optimization model using the calculated execution probability, the user’s current health status, and available resources as input variables. Claim 7 A method for providing a user-customized health management service according to claim 1, wherein the step of setting the execution goal further comprises: a step of evaluating whether the user has achieved the goal at predetermined time intervals; a step of analyzing the goal achievement rate and the difficulty of achieving the goal based on the evaluation results; and a step of adjusting the execution goal or changing the execution strategy associated with the goal based on the analysis results. Claim 8 A method for providing a user-customized health management service according to claim 1, wherein the step of providing the customized health management solution further comprises: a step of clustering other user groups having a state similar to the user's health state by applying a collaborative filtering algorithm; a step of generating the customized health management solution by analyzing behavioral data of user groups similar to the user based on the clustering results; and a step of adjusting the priority of the customized health management solution according to the user's preference and feasibility score. Claim 9 A method for providing a user-customized health care service according to claim 1, wherein the step of providing the customized health care solution further comprises: a step of evaluating the effectiveness of the customized health care solution based on the comparison result by comparing the effectiveness of the customized health care solution linked to the execution goal with the user's behavioral data; and a step of modifying some elements of the customized health care solution or automatically generating a new alternative solution based on the evaluated effectiveness. Claim 10 A method for providing a user-customized health care service according to claim 1, wherein the step of providing the customized health care solution further comprises: displaying the execution goal, the change history of the customized health care solution, and the progress of the user's goal achievement on a visual dashboard; providing the goal achievement rate, changes in health status, and the results of the effect analysis of the customized health care solution in graph and chart format on the dashboard; and configuring the visual information differently according to the user's level of understanding. Claim 11 A computer program stored on a computer-readable recording medium in combination with hardware to execute the method of any one of claims 1 to 10. Claim 12 An electronic device comprising: at least one processor including processing circuitry; and a memory for storing instructions, wherein when the instructions are executed individually or collectively by the at least one processor, the electronic device is configured to: normalize data input by a user and collected data; calculate a numerical indicator of the user's health status by applying weights based on the normalized data; calculate the difference between the user's current state and target state based on the calculated indicator; set an execution goal based on the difference; and provide a customized health management solution based on the user's health data in conjunction with the execution goal. Claim 13 A method for providing a user-customized health management service, comprising: storing data entered by a user and collected data in the memory of a terminal and normalizing the data; generating a numerical indicator representing the user's health status by applying weights based on the normalized data; calculating the difference between the user's current state and target state based on the calculated indicator and setting an execution goal based on the difference; providing a customized health management solution based on the user's health data in conjunction with the execution goal; and outputting the customized health management solution through a user interface.

Images