Method for providing a custominzed healthy diet based on continuous glucose monitoring data and apparatus thereof

Abstract

The present invention relates to a method for providing a user-customized health diet based on continuous glucose information, comprising: a data management module that collects user data and reference data related to an individual's blood glucose; a data analysis module that analyzes the user data to extract user-specific characteristic information and food list information, analyzes the reference data to extract anonymous patient-specific characteristic information and food list information, and generates a postprandial blood glucose model based on the anonymous patient-specific characteristic information and food list information; and a health diet provision module that generates user-customized health diet information based on the user-specific food list information and the food list information of the postprandial blood glucose model.

Description

Technology Field

[0001] The present invention relates to a method and apparatus for providing a user-customized health diet, and more specifically, to a method and apparatus capable of providing user-customized health diet information based on continuous glucose information. Background Technology

[0002] Continuous Glucose Monitoring (CGM) is a device that provides real-time information on an individual's blood glucose levels and trends, and is classified into personal CGM and professional CGM. CGM technology is highly beneficial not only for diabetic patients requiring timely insulin delivery but also for individuals who wish to manage their blood glucose levels on a daily basis. With the continuous increase in the number of diabetic patients worldwide, there has long been a demand for the development of technologies to replace traditional blood sampling methods; currently, it is possible to continuously measure blood glucose fluctuations for over 24 hours using non-invasive, minimally invasive methods. Along with this, various technological development efforts are underway for innovative diabetes management through non-invasive intermittent or continuous blood glucose monitoring.

[0003] Blood sugar refers to the concentration of glucose contained in the blood, and humans must continuously maintain blood sugar levels within a certain range to maintain homeostasis. Blood sugar is maintained through the antagonistic action of various hormones; however, if abnormalities in these hormone secretions cause blood sugar levels to become unstable, diseases such as diabetes can occur. Therefore, properly managing blood sugar levels to prevent them from becoming too high or too low is crucial for disease prevention.

[0004] While various factors influence blood sugar levels, dietary factors play a significant role in blood sugar fluctuations, excluding functional disorders caused by genetic factors or congenital abnormalities. It is generally known that foods with a high glycemic index (GI) cause rapid spikes in blood sugar while those with a low GI cause a gradual increase; however, research has revealed that blood sugar changes vary from person to person even when consuming the same food. In other words, since even low-GI foods can cause a rapid spike in certain individuals, selecting and consuming foods that do not trigger such spikes can help prevent numerous diseases that may arise from frequent blood sugar spikes. Therefore, it is necessary to provide personalized healthy diets that consider individual characteristics.

[0005] (Patent Document 1) KR 10-1807853 B

[0006] (Patent Document 2) KR 10-2297323 B The problem to be solved

[0007] The present invention aims to solve the aforementioned problems and other problems. Another objective is to provide a method and apparatus capable of providing a user-customized healthy diet based on the user's continuous glucose information and dietary information.

[0008] Another objective is to provide a method and apparatus capable of generating a postprandial blood glucose model based on reference data similar to user data, and providing a user-customized healthy diet using the generated postprandial blood glucose model. means of solving the problem

[0009] According to one aspect of the present invention to achieve the above or other purposes, a user-customized health diet providing device is provided, comprising: a data management module for collecting user data and reference data related to an individual's blood glucose; a data analysis module for analyzing the user data to extract user-specific characteristic information and food list information, analyzing the reference data to extract anonymous patient-specific characteristic information and food list information, and generating a postprandial blood glucose model based on the anonymous patient-specific characteristic information and food list information; and a health diet providing module for generating user-customized health diet information based on the user-specific food list information and the food list information of the postprandial blood glucose model.

[0010] According to another aspect of the present invention, a method for providing a user-customized health diet, performed by a processor in a device, comprises the steps of: collecting user data and reference data related to an individual's blood glucose; analyzing the user data to extract user-specific characteristic information and food list information; analyzing the reference data to extract anonymous patient-specific characteristic information and food list information; generating a post-meal blood glucose model based on the anonymous patient-specific characteristic information and food list information; and generating user-customized health diet information based on the user-specific food list information and the food list information of the post-meal blood glucose model.

[0011] According to another aspect of the present invention, a computer program stored on a computer-readable recording medium is provided to enable the following processes to be executed on a computer: a process of collecting user data and reference data related to an individual's blood sugar; a process of analyzing the user data to extract user-specific characteristic information and food list information; a process of analyzing the reference data to extract anonymous patient-specific characteristic information and food list information; a process of generating a postprandial blood sugar model based on the anonymous patient-specific characteristic information and food list information; and a process of generating user-specific customized health diet information based on the user-specific food list information and the food list information of the postprandial blood sugar model. Effects of the invention

[0012] The effects of the method and apparatus for providing a user-customized healthy diet according to embodiments of the present invention are described as follows.

[0013] According to at least one of the embodiments of the present invention, there is an advantage in that user-specific customized health diet information can be generated and provided based on user data and reference data.

[0014] In addition, according to at least one embodiment of the present invention, there is an advantage in that a list of foods that cause a rapid increase in a user's blood sugar and a list of foods that do not cause a rapid increase can be extracted, and user-customized health diet information that takes into account the user's characteristics can be generated and provided based on the extracted food list.

[0015] In addition, according to at least one of the embodiments of the present invention, there is an advantage in that user-customized health diet information, which is expected not to cause a rapid increase in the user's blood sugar, can be generated and provided by utilizing a large amount of reference data even if only a portion of the user data is collected.

[0016] However, the effects that can be achieved by the method and apparatus for providing a user-customized healthy diet according to the embodiments of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present invention belongs from the description below. Brief explanation of the drawing

[0017] FIG. 1 is a block diagram of a user-customized healthy diet providing device according to one embodiment of the present invention; FIG. 2 is a diagram showing the configuration of the data management module of FIG. 1; FIG. 3 is a diagram showing the configuration of the data analysis module of FIG. 1; FIG. 4 is a diagram showing the configuration of the healthy diet provision module of FIG. 1; FIG. 5 is a diagram showing the configuration of the database of FIG. 1; FIG. 6 is a diagram illustrating time-series data among user data; FIG. 7 is a diagram illustrating non-time series data among user data; FIG. 8 is a diagram illustrating characteristic information extracted by a characteristic analysis unit; FIG. 9 is a drawing illustrating a list of postprandial blood glucose levels extracted by a postprandial blood glucose analysis unit; FIG. 10 is a diagram illustrating a list of foods that cause a rapid increase in blood sugar / a slow increase in blood sugar extracted by a post-meal blood sugar analysis unit; FIG. 11 is a diagram illustrating a postprandial blood glucose model extracted by a postprandial blood glucose model generation unit; FIG. 12 is a diagram illustrating a food list by user / postprandial blood glucose model; Fig. 13 is a drawing illustrating a list of modified foods per user. FIG. 14 is a drawing illustrating a list of customized healthy diets for each user; FIG. 15 is a flowchart illustrating a method for providing a user-customized healthy diet according to an embodiment of the present invention; FIG. 16 is a block diagram of a computing device according to one embodiment of the present invention. Specific details for implementing the invention

[0018] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components regardless of drawing symbols will be assigned the same reference number, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" for components used in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not inherently possess distinct meanings or roles. That is, the term "part" used in this invention refers to a hardware component such as software, FPGA, or ASIC, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or may be configured to run one or more processors. Accordingly, as an example, a 'part' includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or further separated into additional components and 'parts'.

[0019] In addition, when describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art may obscure the essence of the embodiments disclosed in this specification, such detailed description is omitted. Furthermore, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings; it should be understood that they include all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the present invention.

[0020] The present invention proposes a method and apparatus capable of providing a user-customized healthy diet based on the user's continuous glucose information and dietary information. In addition, the present invention proposes a method and apparatus capable of generating a postprandial blood glucose model based on reference data similar to user data and using the generated postprandial blood glucose model to provide a user-customized healthy diet.

[0021] Hereinafter, various embodiments of the present invention will be described in detail with reference to the drawings.

[0022] FIG. 1 is a block diagram of a user-customized healthy diet providing device according to an embodiment of the present invention, FIG. 2 is a diagram showing the configuration of a data management module of FIG. 1, FIG. 3 is a diagram showing the configuration of a data analysis module of FIG. 1, FIG. 4 is a diagram showing the configuration of a healthy diet providing module of FIG. 1, and FIG. 5 is a diagram showing the configuration of a database of FIG. 1.

[0023] Referring to FIGS. 1 through 5, a user-customized healthy diet providing device (100) according to one embodiment of the present invention may include a data management module (110), a data analysis module (120), a healthy diet providing module (130), and a database (140). Since the components illustrated in FIG. 1 are not essential for implementing the user-customized healthy diet providing device, the user-customized healthy diet providing device described herein may have more or fewer components than those listed above.

[0024] The data management module (110) can collect user data and reference data and store the collected user and reference data in a database (140). The data management module (110) can update or manage the user and reference data stored in the database (140).

[0025] The data management module (110) may include a user data management unit (111) for managing user data and a reference data management unit (112) for managing reference data.

[0026] The user data management unit (111) can collect user data related to the user's blood sugar. At this time, the user data management unit (111) can receive user data directly from the user or collect it through a device attached to the user's body. In addition, the user data management unit (111) can collect user data from external institutions, such as hospitals and the National Health Insurance Service, after obtaining the user's consent or approval.

[0027] The user data management unit (111) can store collected user data in a database (140) for each user and manage the user data stored in the database (140).

[0028] User data can be collected automatically in real-time, and data at a specific point in time can be collected based on user requests, etc. Additionally, user data can be collected through a process of updating previously collected data with new data when the information in the data changes.

[0029] User data may include time-series data recorded sequentially over a specific time or period of time, and non-time-series data recorded regardless of a specific time.

[0030] For example, as illustrated in FIG. 6, time series data (600) may include continuous glucose information in which a user's blood glucose is periodically measured and recorded through a continuous glucose monitoring (CGM), medication information in which medication or drug administration information is recorded at a specific point in time, dietary information such as the type of food, amount consumed, calories, and nutritional components at the time of meal, and activity information such as the type of activity, number of steps, and calories burned at the time of activity.

[0031] For example, as illustrated in FIG. 7, non-time series data (700) may include demographic information such as the user's gender and year of birth, physical health information such as blood pressure, body mass index (BMI), and blood test results, medical information such as disease history and prescription history, genetic information obtainable through genetic testing, and microbiome information obtainable through microbiome testing.

[0032] Not all information included in user data is necessarily required, and a user-customized healthy diet according to the present invention can be provided even with only some collectible information. In particular, the present invention can provide a user-customized healthy diet, rather than a general diet recommendation, by utilizing reference data to extract a post-meal blood glucose model even if only a portion of user data is provided. However, since accuracy increases as the diversity or quantity of user data becomes sufficient, a user-customized healthy diet can be provided more accurately with more user data. In particular, the more continuous glucose information and dietary information are collected from the user data, the more accurately a healthy diet that does not cause a rapid spike in the user's blood glucose can be provided. It is best for continuous glucose information to be measured and recorded at regular intervals to identify the user's daily blood glucose changes; however, even if not for the entire day, to verify post-meal blood glucose changes which are highly relevant to diet creation, the user's fasting blood glucose, pre-meal blood glucose, and continuous blood glucose levels from the start of the meal for at least two hours must be recorded.

[0033] The reference data management unit (112) can generate or collect reference data similar to user data. Here, the reference data refers to various data related to an individual's blood sugar, which is anonymized or pseudonymized data.

[0034] The reference data management unit (112) can generate reference data by processing user data into anonymized or pseudonymized form, and can store the generated reference data in the database (140) for each anonymous user (or each anonymous patient). Additionally, the reference data management unit (112) can collect reference data from external institutions such as hospitals and the National Health Insurance Service, and store the collected reference data in the database (140) for each anonymous user.

[0035] The reference data management unit (112) can update or manage reference data stored in the database (140). Reference data stored in the database (140) can be updated whenever user data is added or changed, or data from an external organization is added or changed.

[0036] Similar to user data, reference data may include time-series data recorded sequentially over a specific time or period of time, and non-time-series data recorded regardless of a specific time. The time-series data may include continuous glucose information, medication information, dietary information, activity information, etc., and the non-time-series data may include demographic information, physical health information, medical information, genetic information, microbiome information, etc.

[0037] The data analysis module (120) can analyze user data stored in the database (140) to extract user-specific characteristic information and user-specific food list information. Here, the user-specific food list information may include food list information that causes a rapid increase in blood sugar for each user (hereinafter referred to as 'blood sugar rapid increase food list information') and food list information that does not cause a rapid increase in blood sugar (hereinafter referred to as 'blood sugar slow increase food list information').

[0038] The data analysis module (120) can generate a post-meal blood glucose model by analyzing reference data stored in the database (140). At this time, the data analysis module (120) can generate the post-meal blood glucose model using a machine learning algorithm.

[0039] The data analysis module (120) may include a characteristic analysis unit (121), a post-meal blood glucose analysis unit (122), and a post-meal blood glucose model generation unit (123).

[0040] The characteristic analysis unit (121) can extract characteristic information for each user by analyzing the characteristics of user data stored in the database (140). That is, the characteristic analysis unit (121) can extract characteristic information for each user by analyzing the characteristics of demographic information, physical health information, medical information, genetic information, microbiome information, continuous glucose information, dietary information, and activity information included in the user data.

[0041] For example, as illustrated in Fig. 8, characteristic information of human statistical information includes gender and age, characteristic information of physical health information includes blood pressure index, obesity index, and blood sugar index, characteristic information of medical information includes past diseases and current diseases, characteristic information of genetic information includes blood sugar genetic factors and obesity genetic factors, and characteristic information of microbiome information includes beneficial bacteria, harmful bacteria, and obesity bacteria. Characteristic information of continuous glucose information includes average blood sugar, estimated glycated hemoglobin, time of exposure to hypoglycemia, time in normal blood sugar range, time of exposure to hyperglycemia, and blood sugar variability, characteristic information of dietary information includes the average number of meals per day, average daily calorie intake, and average daily carbohydrate intake, and characteristic information of activity information includes the average number of steps per day, average daily calories burned, and activity level.

[0042] The characteristic analysis unit (121) can store characteristic information regarding user data in the database (140). The characteristic information regarding user data can be used later to derive a user-customized healthy diet.

[0043] The characteristic analysis unit (121) can extract anonymous user-specific characteristic information by analyzing the characteristics of reference data stored in the database (140). That is, the characteristic analysis unit (121) can extract each characteristic information by analyzing the characteristics of demographic information, physical health information, medical information, genetic information, microbiome information, continuous glucose information, dietary information, and activity information included in the reference data.

[0044] The characteristic analysis unit (121) can store characteristic information regarding reference data in the database (140). The characteristic information regarding the reference data can be used later to generate a post-meal blood glucose model.

[0045] The post-meal blood glucose analysis unit (122) can extract information on changes in post-meal blood glucose according to the food consumed by each user by comparing and analyzing blood glucose before food intake (i.e., pre-meal blood glucose) and blood glucose after food intake (i.e., post-meal blood glucose) based on continuous blood glucose information and dietary information included in user data. For example, as shown in FIG. 9, the post-meal blood glucose analysis unit (122) can extract a post-meal blood glucose list (900) for each user by analyzing changes in post-meal blood glucose according to the food consumed by each user.

[0046] The post-meal blood sugar analysis unit (122) can extract a list of foods that cause a rapid increase in blood sugar (i.e., a list of foods that cause a rapid increase in blood sugar) and a list of foods that do not cause a rapid increase in blood sugar (i.e., a list of foods that cause a moderate increase in blood sugar) based on information on changes in blood sugar after eating according to the food consumed by each user. For example, as shown in FIG. 10, the post-meal blood sugar analysis unit (122) can extract a list of foods that cause a rapid increase in blood sugar (1010) and a list of foods that cause a moderate increase in blood sugar (1020) for each user.

[0047] The post-meal blood sugar analysis unit (122) can store information regarding the list of foods that cause a rapid increase in blood sugar / a slow increase in blood sugar for each user in the database (140). The information regarding the list of foods that cause a rapid increase in blood sugar / a slow increase in blood sugar for each user can be used later to derive a customized healthy diet for the user.

[0048] The post-meal blood glucose analysis unit (122) can compare and analyze pre-meal blood glucose and post-meal blood glucose based on continuous blood glucose information and dietary information included in the reference data to extract information on changes in post-meal blood glucose according to the food consumed by each anonymous user.

[0049] The post-meal blood sugar analysis unit (122) can extract a list of foods that cause a rapid increase in blood sugar and a list of foods that cause a moderate increase in blood sugar for each anonymous user based on information on changes in blood sugar after eating according to the foods consumed by each anonymous user.

[0050] The post-meal blood glucose analysis unit (122) can store information regarding a list of foods that cause a rapid increase in blood glucose or a slow increase in blood glucose for each anonymous user in the database (140). The information regarding the list of foods that cause a rapid increase in blood glucose or a slow increase in blood glucose for each anonymous user can be used later to create a post-meal blood glucose model.

[0051] The post-meal blood sugar model generation unit (123) can generate a post-meal blood sugar model based on anonymous user-specific characteristic information analyzed through the characteristic analysis unit (121) and anonymous user-specific food list information analyzed through the post-meal blood sugar analysis unit (122). That is, the post-meal blood sugar model generation unit (123) can generate a post-meal blood sugar model based on anonymous user-specific characteristic information extracted based on reference data and anonymous user-specific food list information. Here, the anonymous user-specific food list information may include anonymous user-specific food list information for rapid blood sugar increase and food list information for moderate blood sugar increase.

[0052] In the method for generating a post-meal blood glucose model in the post-meal blood glucose model generation unit (123), an artificial intelligence-based machine learning algorithm capable of performing classification or clustering by learning data can be used. As the machine learning algorithm, a supervised learning algorithm or an unsupervised learning algorithm can be used.

[0053] For example, when using a supervised learning algorithm, user-specific characteristic information and food information are set as independent variables (i.e., the problem), and whether the food included in that information causes a rapid increase in blood sugar is set as the dependent variable (i.e., the correct answer). Based on the training data consisting of the aforementioned independent and dependent variables, an optimal classification model, namely a post-meal blood sugar model, can be generated. Upon completion of supervised learning, if the characteristic information of the user for whom a healthy diet is to be derived and the food information for which blood sugar spikes are to be determined are input into the classification model, the model can classify whether the food causes a rapid increase or a moderate increase in blood sugar for the user. In other words, a list of foods that cause a rapid increase or a moderate increase in blood sugar for each user can be inferred using a single post-meal blood sugar model.

[0054] Meanwhile, as another example, when using an unsupervised learning algorithm, user-specific characteristic information and user-specific food list information for rapid blood sugar spikes / slow blood sugar spikes can be set as training data without separating the problem and the answer, and a clustering model can be generated that forms optimal clusters of similar items by exploring the characteristics among the training data. In this case, each clustering model can be viewed as an individual post-meal blood sugar model. For instance, as illustrated in Figure 11, various post-meal blood sugar models can be generated by extracting representative characteristic elements and food lists for rapid blood sugar spikes / slow blood sugar spikes for each clustering model.

[0055] Hereinafter, in this embodiment, for convenience of explanation, the generation of multiple post-meal blood glucose models using an unsupervised learning algorithm in the post-meal blood glucose model generation unit (123) will be described as an example.

[0056] The health diet provision module (130) can provide customized health diet information for each user to help maintain each user's blood sugar within a normal range by using the food list information for each user and the food list information of the post-meal blood sugar model for each user.

[0057] The healthy diet provision module (130) may include a healthy diet generation unit (131) and a healthy diet management unit (132).

[0058] The health diet generation unit (131) can obtain user-specific characteristic information from the database (140). Here, the user-specific characteristic information is characteristic information analyzed through the characteristic analysis unit (121).

[0059] The healthy diet generation unit (131) can obtain user-specific food list information for rapid blood sugar spikes / slow blood sugar spikes from the database (140). Here, the user-specific food list information for rapid blood sugar spikes / slow blood sugar spikes is food list information analyzed through the post-meal blood sugar analysis unit (122).

[0060] The health diet generation unit (131) can select a post-meal blood sugar model that has characteristics most similar to each user's characteristics based on user characteristic information, and detect a list of foods that cause a rapid increase in blood sugar / a slow increase in blood sugar of the selected post-meal blood sugar model for each user.

[0061] For example, as illustrated in FIG. 12, the health diet generation unit (131) can detect a list of foods that cause a rapid increase in blood sugar / a slow increase in blood sugar per user, and a list of foods that cause a rapid increase in blood sugar / a slow increase in blood sugar per post-meal blood sugar model corresponding to each user.

[0062] The health diet generation unit (131) can generate user-customized health diet information based on user-specific blood sugar spike / slow blood sugar spike food list information, user-specific post-meal blood sugar model blood sugar spike / slow blood sugar spike food list information, daily recommended nutrient intake information according to user characteristics, and nutrient information for each food. The user-customized health diet information can be provided in various forms depending on the diet generation request period, such as one meal, one day (breakfast, lunch, dinner, snack), or one week.

[0063] When the list of foods that cause a rapid increase in blood sugar / slow increase in blood sugar per user conflicts with the list of foods that cause a rapid increase in blood sugar / slow increase in blood sugar per user's post-meal blood sugar model, the healthy diet generation unit (131) can generate user-customized healthy diet information by giving higher priority to the list of foods that cause a rapid increase in blood sugar / slow increase in blood sugar per user's post-meal blood sugar model than to the list of foods that cause a rapid increase in blood sugar / slow increase in blood sugar per user's post-meal blood sugar model.

[0064] For example, as illustrated in FIG. 13, the health diet generation unit (131) can generate a user-specific modified food list (1320, 1330) by assigning a negative (-) weight to foods that cause a rapid increase in blood sugar and a positive (+) weight to foods that cause a moderate increase in blood sugar among the basic food list (1310) stored in the food nutrition DB. At this time, if the user's data and the data of the post-meal blood sugar model match each other regarding foods that cause a rapid increase in blood sugar or foods that cause a moderate increase in blood sugar, the same weight can be assigned twice as much, and if they conflict, the data of the post-meal blood sugar model can be ignored and weight can be assigned only to the user's data.

[0065] The healthy meal plan generation unit (131) can generate a customized healthy meal plan list for each user based on the user-specific modified food list. For example, as illustrated in FIG. 14, the healthy meal plan generation unit (131) can generate a healthy meal plan list (1400) for breakfast / lunch / dinner / snack for each user.

[0066] The health diet generation unit (131) can store user-specific customized health diet information in the database (140).

[0067] The health diet management department (132) can manage or update customized health diet information for each user. The health diet management department (132) can update customized health diet information for each user as user data and reference data are added to the database (140).

[0068] The health diet management unit (132) receives a health diet list configured by the user, rather than a health diet list extracted from the health diet generation unit (131), and informs whether it contains foods that cause a rapid increase in blood sugar, and can provide a list of alternative foods that do not cause a rapid increase in blood sugar while containing calories and nutrients similar to the foods that cause a rapid increase in blood sugar.

[0069] The database (140) may include a user data DB (141), a reference data DB (142), a post-meal blood sugar model DB (143), and a food nutrition DB (144). Meanwhile, although not shown in the drawing, the database (140) may further include a healthy diet DB.

[0070] The user data DB (141) can store collected user data, user-specific characteristic information analyzed based on the user data, and user-specific food list information.

[0071] The reference data DB (142) can store collected reference data, anonymous user-specific characteristic information analyzed based on the reference data, and anonymous user-specific food list information.

[0072] The post-meal blood glucose model DB (143) can store post-meal blood glucose models generated through the post-meal blood glucose model generation unit (123).

[0073] The food nutrition DB (144) can store information on nutrients for each food and information on daily recommended nutritional intake guidelines.

[0074] The health diet DB can store user-specific customized health diet information generated through the health diet generation unit (131).

[0075] As described above, a user-customized health diet providing device according to one embodiment of the present invention can generate and provide user-customized health diet information based on user data and reference data. In addition, the user-customized health diet providing device can extract a list of foods that cause a rapid increase in the user's blood sugar and a list of foods that do not cause a rapid increase, and generate and provide user-customized health diet information that takes into account the user's characteristics based on the extracted food lists. Furthermore, even if only a portion of the user data is collected, the user-customized health diet providing device can generate and provide user-customized health diet information that is expected not to cause a rapid increase in the user's blood sugar by utilizing a large amount of reference data.

[0077] FIG. 15 is a flowchart illustrating a method for providing a user-customized healthy diet according to an embodiment of the present invention. The method according to the present embodiment can be performed by a user-customized healthy diet providing device (100).

[0078] Referring to FIG. 15, a user-customized health diet providing device (100) according to one embodiment of the present invention may collect user data related to the user's blood sugar and store the collected user data in a database (140) (S1510). Here, the user data may be classified into time-series data and non-time-series data. The time-series data may include continuous glucose information, medication information, dietary information, activity information, etc., and the non-time-series data may include demographic information, physical health information, medical information, genetic information, microbiome information, etc.

[0079] A user-customized health diet providing device (100) can collect reference data similar to user data and store the collected reference data in a database (140) (S1520). Here, the reference data refers to various data related to an individual's blood sugar, which is anonymized or pseudonymized data. The reference data can be classified into time-series data and non-time-series data. The time-series data may include continuous glucose information, medication information, dietary information, activity information, etc., and the non-time-series data may include demographic information, physical health information, medical information, genetic information, microbiome information, etc.

[0080] The user-customized healthy diet providing device (100) can analyze the characteristics of user data stored in the database (140) for each user to extract user-specific characteristic information and store the extracted user-specific characteristic information in the database (140) (S1530). Additionally, the user-customized healthy diet providing device (100) can analyze the characteristics of reference data stored in the database (140) for each anonymous user to extract anonymous user-specific characteristic information and store the extracted anonymous user-specific characteristic information in the database (140).

[0081] A user-customized healthy diet providing device (100) can extract information on changes in blood sugar levels after meals based on food consumed by each user, based on continuous blood sugar information and dietary information included in user data, and can extract food list information for each user, namely food list information for a rapid increase in blood sugar and food list information for a moderate increase in blood sugar, based on the extracted information on changes in blood sugar after meals (S1540). The user-customized healthy diet providing device (100) can store the food list information for each user in a database (140).

[0082] A user-customized healthy diet providing device (100) can extract information on changes in blood sugar levels after meals based on food consumed by an anonymous user, based on continuous blood sugar information and dietary information included in reference data, and can extract food list information for an anonymous user, namely, food list information for a rapid increase in blood sugar and food list information for a moderate increase in blood sugar, based on the extracted information on changes in blood sugar after meals (S1540). The user-customized healthy diet providing device (100) can store the food list information for an anonymous user in a database (140).

[0083] The user-customized healthy diet provider (100) can generate a post-meal blood glucose model based on anonymous user-specific characteristic information extracted based on reference data and anonymous user-specific food list information (S1550). At this time, the user-customized healthy diet provider (100) can generate a post-meal blood glucose model using a machine learning algorithm.

[0084] The user-customized health diet providing device (100) can select a post-meal blood glucose model corresponding to each user based on the user's characteristic information (S1560). At this time, the user-customized health diet providing device (100) can select a post-meal blood glucose model having characteristics most similar to each user's characteristics based on the user's characteristic information.

[0085] The user-customized healthy diet providing device (100) can generate user-customized healthy diet information using user-specific food list information and user-specific post-meal blood sugar model food list information (S1570).

[0086] When the food list information for each user and the food list information of the post-meal blood sugar model for each user conflict with each other, the user-customized healthy diet providing device (100) can generate user-customized healthy diet information by giving higher priority to the food list information for each user than to the food list information of the post-meal blood sugar model.

[0087] As described above, a method for providing a user-customized healthy diet according to one embodiment of the present invention can generate and provide user-customized healthy diet information based on user data and reference data. The method for providing a user-customized healthy diet can extract a list of foods that cause a rapid increase in the user's blood sugar and a list of foods that do not cause a rapid increase, and can generate and provide user-customized healthy diet information that takes into account the user's characteristics based on the extracted food lists. Furthermore, even if only a portion of the user data is collected, the method for providing a user-customized healthy diet can generate and provide user-customized healthy diet information that is expected not to cause a rapid increase in the user's blood sugar by utilizing a large amount of reference data.

[0089] FIG. 16 is a block diagram of a computing device according to one embodiment of the present invention.

[0090] Referring to FIG. 16, a computing device (1600) according to one embodiment of the present invention includes at least one processor (1610), a computer-readable storage medium (1620), and a communication bus (1630). The computing device (1600) may be one or more components included in the user-customized healthy diet providing device (100) described above or in the elements constituting the user-customized healthy diet providing device (100).

[0091] The processor (1610) may enable the computing device (1600) to operate according to the exemplary embodiment described above. For example, the processor (1610) may execute one or more programs (1625) stored in a computer-readable storage medium (1620). The one or more programs may include one or more computer-executable instructions, and the computer-executable instructions may be configured to enable the computing device (1600) to perform operations according to the exemplary embodiment when executed by the processor (1610).

[0092] A computer-readable storage medium (1620) is configured to store computer-executable instructions or program code, program data and / or other suitable forms of information. A program (1625) stored in the computer-readable storage medium (1620) includes a set of instructions executable by a processor (1610). In one embodiment, the computer-readable storage medium (1620) may be memory (volatile memory such as random access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, other forms of storage media that are accessed by a computing device (1600) and capable of storing desired information, or a suitable combination thereof.

[0093] The communication bus (1630) interconnects various other components of the computing device (1600), including the processor (1610) and the computer-readable storage medium (1620).

[0094] The computing device (1600) may also include one or more input / output interfaces (1640) and one or more network communication interfaces (1660) that provide interfaces for one or more input / output devices (1650). The input / output interfaces (1640) and network communication interfaces (1660) are connected to a communication bus (1630).

[0095] An input / output device (1650) may be connected to other components of a computing device (1600) through an input / output interface (1640). An exemplary input / output device (1650) may include input devices such as a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or touchscreen), a voice or sound input device, various types of sensor devices and / or imaging devices, and / or output devices such as a display device, a printer, a speaker and / or a network card. An exemplary input / output device (1650) may be included inside the computing device (1600) as a component constituting the computing device (1600), or it may be connected to the computing device (1600) as a separate device distinct from the computing device (1600).

[0096] The present invention described above can be implemented as computer-readable code on a medium on which a program is recorded. The computer-readable medium may be one that continuously stores a program executable by a computer, or temporarily stores it for execution or download. Furthermore, the medium may be various recording or storage means in the form of a single or multiple hardware components, and is not limited to a medium directly connected to a computer system but may also exist distributed over a network. Examples of media may 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 media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software. Accordingly, the above detailed description should not be interpreted restrictively in all respects and should be considered exemplary. The scope of the present invention shall be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the present invention are included within the scope of the present invention. Explanation of the symbols

[0097] 100: User-customized healthy meal plan provider 110: Data management module 111: User Data Management Department 112: Reference Data Management Department 120: Data Analysis Module 121: Feature Analysis Unit 122: Postprandial Blood Glucose Analysis Unit 123: Postprandial Blood Glucose Model Generation Unit 130: Healthy Meal Plan Provision Module 131: Healthy Meal Plan Generation Unit 132: Healthy Diet Management Department 140: Database 141: User Data DB 142: Reference Data DB 143: Postprandial Blood Glucose Model DB 144: Food and Nutrition DB

Claims

Claim 1 A user-customized healthy diet providing device comprising: a data management module that collects user data and reference data related to an individual's blood sugar; a data analysis module that analyzes the user data to extract user-specific characteristic information and food list information, analyzes the reference data to extract anonymous patient-specific characteristic information and food list information, and generates a plurality of postprandial blood sugar models based on the anonymous patient-specific characteristic information and food list information; and a healthy diet providing module that selects a postprandial blood sugar model corresponding to each user's characteristics based on the user-specific characteristic information from among the plurality of postprandial blood sugar models, and generates user-customized healthy diet information based on user-specific food list information inferred through the selected postprandial blood sugar model and user-specific food list information extracted through analysis of the user data. Claim 2 A user-customized health diet providing device according to claim 1, wherein the user data includes time-series data and non-time-series data, the time-series data includes at least one of continuous glucose information, medication information, dietary information, and activity information, and the non-time-series data includes at least one of demographic information, physical health information, medical information, genetic information, and microbiome information. Claim 3 A user-customized health diet providing device according to claim 1, wherein the reference data is data similar to the user data and is anonymized or pseudonymized. Claim 4 A user-customized health diet providing device according to claim 1, characterized in that the food list information includes food list information that causes a rapid increase in blood sugar and food list information that does not cause a rapid increase in blood sugar. Claim 5 A user-customized health diet providing device according to claim 1, wherein the data management module comprises a user data management unit for managing user data and a reference data management unit for managing reference data. Claim 6 A user-customized health diet providing device according to claim 1, wherein the data analysis module comprises: a characteristic analysis unit that analyzes the user data and reference data to extract the user-specific characteristic information and the anonymous patient-specific characteristic information; a post-meal blood glucose analysis unit that analyzes the user data and reference data to extract the user-specific food list information and the anonymous patient-specific food list information; and a post-meal blood glucose model generation unit that generates a plurality of post-meal blood glucose models based on the anonymous patient-specific characteristic information and food list information. Claim 7 A user-customized health diet providing device according to claim 6, wherein the post-meal blood glucose analysis unit analyzes continuous allocation information and dietary information included in the user data and reference data to extract food list information for each user and food list information for each anonymous patient. Claim 8 A user-customized health diet providing device according to claim 6, wherein the postprandial blood glucose model generating unit generates the plurality of postprandial blood glucose models based on learning data including the anonymous patient-specific characteristic information and food list information using a predetermined machine learning algorithm. Claim 9 A user-customized healthy diet providing device according to claim 1, wherein the healthy diet providing module comprises a healthy diet generating unit that generates user-customized healthy diet information and a healthy diet management unit that manages user-customized healthy diet information. Claim 10 In claim 9, the health diet generation unit is characterized by generating user-specific customized health diet information based on user-specific food list information, food list information of the selected post-meal blood glucose model, daily recommended nutrient intake information according to user characteristics, and nutrient information for each food. Claim 11 In claim 9, the user-customized health diet providing device is characterized in that the health diet management unit updates the user-customized health diet information as new user data and reference data are collected. Claim 12 A user-customized healthy diet providing device according to claim 1, further comprising a database storing the collected user data and reference data. Claim 13 A method for providing a user-customized healthy diet performed by a processor within a device, comprising: collecting user data and reference data related to an individual's blood sugar; analyzing the user data to extract user-specific characteristic information and food list information; analyzing the reference data to extract anonymous patient-specific characteristic information and food list information; generating a plurality of postprandial blood sugar models based on the anonymous patient-specific characteristic information and food list information; and selecting a postprandial blood sugar model that corresponds to the characteristics of each user based on the user-specific characteristic information, and generating user-customized healthy diet information based on user-specific food list information inferred through the selected postprandial blood sugar model and user-specific food list information extracted through analysis of the user data. Claim 14 A method for providing a user-customized health diet according to claim 13, wherein the user data includes time-series data and non-time-series data, the time-series data includes at least one of continuous glucose information, medication information, dietary information, and activity information, and the non-time-series data includes at least one of demographic information, physical health information, medical information, genetic information, and microbiome information. Claim 15 A method for providing a user-customized healthy diet according to claim 13, wherein the reference data is data similar to the user data and is anonymized or pseudonymized. Claim 16 A method for providing a user-customized healthy diet according to claim 13, wherein the food list information includes food list information that causes a rapid increase in blood sugar and food list information that does not cause a rapid increase in blood sugar. Claim 17 A computer program stored on a computer-readable recording medium so that a method according to any one of claims 13 to 16 can be performed on a computer. Claim 18 A user-customized health diet providing device according to claim 1, wherein the health diet providing module generates user-customized health diet information by assigning a higher priority to the user-customized food list information than to the food list information of the post-meal blood sugar model when the user-customized food list information and the food list information of the post-meal blood sugar model conflict with each other.

Images