Information processing system, information processing program, and information processing method

Abstract

[Problem] To enable health management by considering individual differences. [Solution] An information processing system according to the present invention is provided with: a measurement value storage unit that stores a measurement value linked to an implementation target of a user; an intake storage unit for storing the intake of the plurality of nutrients taken by the user; an analysis unit that analyzes the relationship between the nutrient intake amount and the measured value, and specifies an improvement factor that is a nutrient contributing to improvement of the measured value and a modification factor that is a nutrient contributing to deterioration of the measured value; a recipe storage unit that stores information on the content of nutrients contained in the specified recipe; and a recipe suggestion unit that corrects the recipe by increasing the content of the improvement factor and / or reducing the content of the modification factor, and suggests the corrected recipe.

Description

[Technical field]

[0001] The present invention relates to an information processing system, an information processing program and an information processing method. [Background Technology]

[0002] Advice has been proposed to improve dietary lifestyle habits. For example, Patent Document 1 discloses a system that analyzes dietary information or vital sign data to provide advice. [Prior art literature] [Patent Document]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2004-302498 [Summary of the invention] [Problems to be solved by the invention]

[0004] However, in the system described in Patent Document 1, it is necessary to prepare suggestions in advance as a database, and therefore it is difficult to take individual differences into consideration.

[0005] The present invention has been made in view of such a background, and an object of the present invention is to provide a technology capable of managing health in consideration of individual differences. [Solutions to solve the problem]

[0006] The main invention of the present invention for solving the above-mentioned problems comprises: a measurement value storage unit, which stores the measurement values ​​linked to the user's achievement goals; an intake amount storage unit, which stores the intake amounts of multiple nutrients ingested by the user; an analysis unit, which analyzes the relationship between the intake amounts of the nutrients and the measurement values, and specifies the nutrients that contribute to the improvement of the measurement values, namely the improvement factors, and the nutrients that contribute to the deterioration of the measurement values, namely the deterioration factors; a recipe storage unit, which stores information on the content of the nutrients contained in the specified recipes; and a recipe suggestion unit, which corrects the recipe by increasing the content of the improvement factor and reducing the content of the deterioration factor, and suggests the corrected recipe.

[0007] In addition, the problems disclosed in the present application and their solutions will become more apparent through the column of embodiments of the invention and the accompanying drawings. [Effects of the Invention]

[0008] According to the present invention, health can be managed by taking individual differences into consideration. [Simple diagram description]

[0009] Figure 1 It is a diagram showing an overall configuration example of the information processing system according to the first embodiment. Figure 2 It is a diagram showing a hardware configuration example of the server device 1 according to the first embodiment. Figure 3 It is a diagram showing a functional configuration example of the server device 1 according to the first embodiment. Figure 4 This is a diagram showing a structural example of information stored in the recipe storage unit 135 of the first embodiment. Figure 5 It is a diagram showing a configuration example of information stored in the food information storage unit 136 according to the first embodiment. Figure 6 It is a diagram showing an example of the analysis result of the analysis unit 115 according to the first embodiment. Figure 7 It is a diagram showing an example of a formula of a prediction model generated by the analysis unit 115 of the first embodiment. Figure 8 It is a diagram showing an example of processing of the server device 1 according to the first embodiment. Fig. 9 This is a diagram showing a test schedule (conditional investigation test) to be implemented in 2020 according to the first embodiment. Fig.10 This is a diagram showing a test schedule (condition investigation test) to be performed in 2021 according to the first embodiment. Fig.11 It is a diagram showing the characteristics of the subjects in the first embodiment. Fig.12 This is a diagram showing the test schedule (clinical trials) to be implemented in 2020 according to the first embodiment. Fig.13 This is a diagram showing the test schedule (clinical trial) to be implemented in 2021 according to the first embodiment. Fig.14 It is a graph comparing the amount of energy and nutrients consumed by the subjects through the test foods during the intervention period. Fig.15 It is a graph comparing the amount of energy and nutrients consumed by the subjects through the test foods during the intervention period. Fig.16 It is a graph comparing the amount of energy and nutrients consumed by the subjects through the test foods during the intervention period. Fig.17 It is a graph comparing the amount of energy and nutrients consumed by the subjects through the test foods during the intervention period. Fig.18 It is a graph comparing the amount of energy and nutrients consumed by the subjects through the test foods during the intervention period. Fig.19 It is a graph comparing the amount of energy and nutrients consumed by the subjects through the test foods during the intervention period. Fig. 20 This graph compares the mean values ​​of the weight upon waking up during the observation period and the intervention period. Fig.21 This graph compares the mean values ​​of the weight upon waking up during the observation period and the intervention period. Fig. 22 This graph compares the mean values ​​of the weight upon waking up during the observation period and the intervention period. Fig.23 This is a graph showing body fat percentage, skeletal muscle percentage, and basal metabolic rate measured using a weight and body composition scale. Fig.24 This is a graph showing body fat percentage, skeletal muscle percentage, and basal metabolic rate measured using a weight and body composition scale. Fig.25 This is a diagram showing the results of measuring the amount of exercise (number of steps) measured using an activity meter. Fig.26 This is a diagram showing the results of measuring the amount of exercise (number of steps) measured using an activity meter. Fig. 27 It is a graph showing the degree of intervention of weight-related factors on the test subjects. Fig.28 It is a graph showing the degree of intervention of weight-related factors on the test subjects. Fig.29 It is a graph showing the degree of intervention of weight-related factors on the test subjects. Fig.30 It is a graph showing the degree of intervention of weight-related factors on the test subjects. Fig.31 It is a graph showing the degree of intervention of weight-related factors on the test subjects. Fig.32 It is a graph showing the degree of intervention of weight-related factors on the test subjects. Fig.33 It is a graph showing the transition of blood sugar level. Fig.34 It is a graph showing the transition of the total cholesterol level. Fig.35 It is a graph showing the transition of the HDL cholesterol level. Fig.36 It is a graph showing the transition of the LDL cholesterol level. Fig.37 This is a graph showing the results of multiple regression analysis of body weight upon waking up and nutrient intake on the day before the measurement of body weight upon waking up. Fig.38 This is a graph comparing energy intake during the observation period and the intervention period. Fig.39 This is a graph comparing the intake during the observation period and the intervention period. Fig.40 This is a graph comparing the intake during the observation period and the intervention period. Fig.41 This is a graph comparing the intake during the observation period and the intervention period. Fig.42 This is a graph comparing the intake during the observation period and the intervention period. Fig.43 This is a graph comparing the intake during the observation period and the intervention period. Fig.44 This is a graph comparing the intake during the observation period and the intervention period. Fig.45 This is a graph showing the results of comparing the measured values ​​during the observation period and the intervention period with respect to the body weight upon waking up. Fig.46 This is a graph showing the results of comparing the measured values ​​during the observation period and the intervention period with respect to the body weight upon waking up. Fig.47 This is a graph showing the results of comparing the measured values ​​during the observation period and the intervention period with respect to the body weight upon waking up. Fig.48 This is a graph showing the results of comparing the measured values ​​during the observation period and the intervention period with respect to the body weight upon waking up. Fig.49 This is a graph showing the results of comparing the measured values ​​during the observation period and the intervention period with respect to the body weight upon waking up. Fig.50 This is a graph showing the results of comparing the measured values ​​during the observation period and the intervention period with respect to the body weight upon waking up. Fig.51 It is a diagram showing body composition. Fig.52 It is a diagram showing body composition. Fig.53 It is a diagram showing body composition. Fig.54 It is a diagram showing body composition. Fig.55 It is a diagram showing body composition. Fig.56 It is a diagram showing body composition. Fig.57 It is a graph showing the degree of intervention of the participating factors. Fig.58 It is a graph showing the degree of intervention of the participating factors. Fig.59 It is a graph showing the degree of intervention of the participating factors. Fig.60 It is a graph showing the degree of intervention of the participating factors. Fig.61 It is a graph showing the amount of cholesterol in the blood. Fig.62 This is a diagram showing a test schedule to be implemented in 2020 according to the second embodiment. Fig.63 It is a graph showing the results of multiple regression analysis. Fig.64 It is a diagram showing the conditions in each analysis. Fig.65 is a diagram showing an example of a personalized optimal diet. Fig.66 It is a graph showing the degree of intervention of memory-related factors on the test subjects. Fig.67 It is a graph showing the degree of intervention of memory-related factors on the test subjects. Fig.68 It is a graph showing the degree of intervention of memory-related factors on the test subjects. Fig.69 It is a graph showing the degree of intervention of memory-related factors on the test subjects. Fig.70 It is a graph showing the degree of intervention of memory-related factors on the test subjects. Fig.71 It is a graph showing the degree of intervention of memory-related factors on the test subjects. Fig.72 It is a graph showing the degree of intervention of memory-related factors on the test subjects. Fig.73 This is a graph comparing the intake during the observation period and the intervention period. Fig.74 This is a graph comparing the intake during the observation period and the intervention period. Fig.75 This is a graph comparing the intake during the observation period and the intervention period. Fig.76 This is a graph comparing the intake during the observation period and the intervention period. Fig.77 This is a graph comparing the intake during the observation period and the intervention period. Fig.78 This is a graph comparing the intake during the observation period and the intervention period. Fig.79 This is a graph comparing the intake during the observation period and the intervention period. Fig.80 This is a graph showing the transition of memory test scores. Fig.81 This is a graph comparing the mean values ​​of memory test scores during the observation period and the intervention period. Fig.82 This is a graph comparing the mean values ​​of memory test scores during the observation period and the intervention period. Fig.83It is a graph showing the results of multiple regression analysis. Fig.84 It is a graph showing the degree of intervention of memory-related factors on the test subjects. Fig.85 This is a graph comparing the intake during the observation period and the intervention period. Fig.86 This is a graph showing the transition of memory test scores. Fig.87 This is a graph comparing the mean values ​​of memory test scores during the observation period and the intervention period. Fig.88 It is a graph comparing the distribution of memory test scores during the observation period and the intervention period. Fig.89 It is a diagram showing a test schedule for implementation of the third embodiment. Fig.90 It is a graph showing the results of multiple regression analysis. Fig.91 is a diagram showing an example of a personalized optimal diet. Fig.92 It is a graph showing the degree of intervention of endurance participation factors on the test subjects. Fig.93 It is a graph showing the degree of intervention of endurance participation factors on the test subjects. Fig.94 It is a graph showing the degree of intervention of endurance participation factors on the test subjects. Fig.95 It is a graph showing the degree of intervention of endurance participation factors on the test subjects. Fig.96 This is a graph comparing the intake during the observation period and the intervention period. Fig.97 This is a graph comparing the intake during the observation period and the intervention period. Fig.98 This is a graph comparing the intake during the observation period and the intervention period. Fig.99 This is a graph comparing the intake during the observation period and the intervention period. Fig.100 This is a graph showing changes in heart rate during resting state. Fig.101 This is a graph comparing the average resting heart rate during the observation period and the intervention period. Fig.102 This is a graph comparing blood oxygen saturation at the end of 45 minutes of jogging during the observation period and the intervention period. Fig.103 This is a graph comparing the average blood oxygen saturation values ​​at the end of 45 minutes of jogging during the observation period and the intervention period. Fig.104It is a graph showing the number of shuttle runs during the observation period and the intervention period. Fig.105 This is a graph comparing the average values ​​of the number of 20 m shuttle runs during the observation period and the intervention period. Fig.106 This is a graph showing changes in the resting heart rate during the post-observation period. Fig.107 It is a diagram showing a functional configuration example of a server device 1 according to the second embodiment. Fig.108 It is a diagram showing a structural example of user information. [Implementation Method]

[0010] The contents of the embodiment of the present invention are listed and described. The health management system according to the embodiment of the present invention has the following structure.

[0011] [Project 1] An information processing system, characterized by comprising: a measurement value storage unit that stores measurement values ​​linked to a user's achievement goal; an intake amount storage unit for storing intake amounts of a plurality of nutrients ingested by the user; an analyzing unit that analyzes the relationship between the intake of the nutrient and the measured value, and identifies the nutrient that contributes to the improvement of the measured value, i.e., an improvement factor, and the nutrient that contributes to the deterioration of the measured value, i.e., a deterioration factor; a recipe storage unit for storing information on the content of the nutrients included in the specified recipe; and A recipe suggestion unit amends the recipe by at least one of increasing the content of the improvement factor and decreasing the content of the deterioration factor, and suggests the amended recipe. [Project 2] The information processing system according to item 1, further comprising: A food information storage unit, which stores the content of the nutrient for each food; The recipe storage unit stores the ingredients included in the recipe, The recipe suggestion unit performs at least one of the following steps, namely, Selecting a second ingredient from the ingredient information storage unit that contains more of the nutrient as the improvement factor than at least one of the first ingredients included in the recipe, and modifying the recipe by replacing the first ingredient with the selected second ingredient; Selecting a third ingredient from the ingredient information storage unit that contains less of the nutrient serving as the malignant factor than the first ingredient, and changing the first ingredient to the selected third ingredient, thereby correcting the recipe; Selecting a fourth ingredient from the ingredient information storage unit that contains more of the nutrient as the improvement factor than the first ingredient and less of the nutrient as the deterioration factor than the first ingredient, and changing the first ingredient to the selected fourth ingredient, thereby correcting the recipe; Selecting the fifth ingredient containing the nutrient as the improvement factor from the ingredient information storage unit, and adding the selected fifth ingredient to correct the recipe; and Selecting the sixth ingredient containing the nutrient serving as the malignant factor from the ingredient information storage unit, deleting the selected sixth ingredient, and thereby correcting the recipe; and suggest a revised version of said recipe. [Item 3] The information processing system according to item 1 or 2, characterized in that The analyzing unit calculates the degree of improvement that contributes to the improvement with respect to the improvement factor, and calculates the degree of deterioration that contributes to the deterioration with respect to the deterioration factor, Regarding the recipe suggestion section, The first value is calculated by subtracting a value obtained by multiplying the degree of improvement of the improvement factor included in the recipe by the content from a value obtained by multiplying the degree of deterioration of the improvement factor included in the recipe by the content. A second value is obtained by multiplying the degree of improvement of the improvement factor included in the revised recipe by the content from a value obtained by multiplying the degree of improvement of the improvement factor included in the revised recipe by the content, and the recipe is corrected in such a way that the second value is greater than the first value. [Item 4] The information processing system according to item 1 or 2, characterized in that The analyzing unit calculates the degree of improvement that contributes to the improvement with respect to the improvement factor, and calculates the degree of deterioration that contributes to the deterioration with respect to the deterioration factor, Regarding the recipe suggestion section, a first improvement value is calculated by subtracting a value obtained by multiplying the intake amount of the improvement factor stored in the intake amount storage unit by the improvement degree from a value obtained by multiplying the intake amount of the improvement factor stored in the intake amount storage unit by the improvement degree, A second improvement value is obtained by multiplying the degree of improvement of the improvement factor included in the revised recipe by the content from a value obtained by multiplying the degree of improvement of the improvement factor included in the revised recipe by the content, and the recipe is corrected in such a way that the second improvement value is greater than the first improvement value. [Item 5] The information processing system according to any one of items 1 to 4, characterized by comprising: an action amount storage unit that stores the action amount of the action performed by the user; and a target value input unit for receiving an input of a target value of the measured value; The analyzing unit creates a prediction model for analyzing the relationship between the content of the nutrient and the amount of activity and the measured value, The recipe suggestion unit determines the amount of action based on a difference between a predicted value obtained by applying the content of the nutrient included in the corrected recipe to the prediction model and the target value, and suggests the determined amount of action together with the recipe. [Item 6] The information processing system according to any one of items 1 to 5, characterized in that The analyzing unit periodically performs analysis to identify the improvement factor and the deterioration factor, and the recipe suggesting unit suggests the corrected recipe. [Item 7] An information processing system, characterized by comprising: a measurement value storage unit for storing a measurement value of the first user linked to an achievement goal of the first user; an intake amount storage unit for storing intake amounts of a plurality of nutrients ingested by the first user; an analyzing unit that analyzes the relationship between the intake of the nutrient and the measured value for the first user, and identifies the nutrient that contributes to improvement of the measured value, i.e., an improvement factor, and the nutrient that contributes to deterioration of the measured value, i.e., a deterioration factor; A recipe storage unit storing information on the content of the nutrients contained in the specified recipe; a similar user identifying unit that identifies the first user, ie, a similar user, with attributes similar to those of the second user; and A recipe suggestion unit amends the recipe by at least either increasing the content of the improvement factor specified for the similar user or decreasing the content of the deterioration factor specified for the similar user, and suggests the amended recipe to the second user. [Item 8] An information processing system, characterized by comprising: a measurement value storage unit for storing a measurement value of the first user linked to an achievement goal of the first user; an intake amount storage unit for storing intake amounts of a plurality of nutrients ingested by the first user; A recipe storage unit storing information on the content of the nutrients contained in the specified recipe; a similar user identifying unit that identifies the first user, ie, a similar user, with attributes similar to those of the second user; and an analyzing unit, which reads the measured value and the intake amount corresponding to the similar user from the measured value storage unit and the intake amount storage unit, analyzes the relationship between the intake amount of the nutrient and the measured value, and identifies the nutrient that contributes to the improvement of the measured value, i.e., the improvement factor, and the nutrient that contributes to the deterioration of the measured value, i.e., the deterioration factor; and A recipe suggestion unit is configured to correct the recipe by at least one of increasing the content of the improvement factor and reducing the content of the deterioration factor, and to suggest the corrected recipe to the second user. [Item 9] An information processing method, characterized in that a computer is caused to execute the following steps: Storing measurements linked to the user's achievement goals; storing intake amounts of multiple nutrients ingested by the user; Analyzing the relationship between the intake of the nutrient and the measured value, identifying the nutrient that contributes to the improvement of the measured value, i.e., the improvement factor, and the nutrient that contributes to the deterioration of the measured value, i.e., the deterioration factor; storing information on the content of the nutrients contained in the specified recipe; and The recipe is corrected by at least one of increasing the content of the improvement factor and reducing the content of the deterioration factor, and the corrected recipe is suggested. [Item 10] A program, characterized in that it is used to make a computer execute the following steps: Storing measurements linked to the user's achievement goals; storing intake amounts of multiple nutrients ingested by the user; Analyzing the relationship between the intake of the nutrient and the measured value, identifying the nutrient that contributes to the improvement of the measured value, i.e., the improvement factor, and the nutrient that contributes to the deterioration of the measured value, i.e., the deterioration factor; storing information on the content of the nutrients contained in the specified recipe; and The recipe is corrected by at least one of increasing the content of the improvement factor and reducing the content of the deterioration factor, and the corrected recipe is suggested.

[0012] The preferred embodiments of the present disclosure will be described in detail with reference to the following drawings. In addition, in the present specification and drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and repeated description is omitted.

[0013] <First Embodiment> Figure 1 is a diagram showing the overall structure of the health support system. Figure 1 As shown, the health support system includes a server device 1, a user terminal 3, a vital sign sensor 4, and an activity sensor 5. The server device 1 is connected to the user terminal 3, the vital sign sensor 4, and the activity sensor 5 via a network 2. Only one server device 1, user terminal 3, vital sign sensor 4, and activity sensor 5 are shown, but of course there may be more. The network 3 is, for example, the Internet, which is constructed by Ethernet (registered trademark) or a public telephone line network, a dedicated telephone line network, a mobile phone line network, a wireless communication channel, etc.

[0014] ==Server Device 1== The server device 1 is a computer that provides information on elements necessary to achieve a goal to a user in consideration of individual differences. The server device 1 is, for example, a personal computer or a workstation. The server device 1 can also be configured as a virtual computer based on cloud computing.

[0015] Figure 2 1 is a diagram showing an example of the hardware structure of the server device 1 of the present embodiment. The server device 1 includes a processor 101, a memory 102, a storage device 103, a communication interface 104, an input device 105, and an output device 106. The storage device 103 stores various data or programs, such as a hard disk drive, a solid state drive, a flash memory, etc. The communication interface 104 is an interface for connecting to the network 2, such as an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone line network, a wireless communication device for wireless communication, a USB (Universal Serial Bus) connector for serial communication, an RS232C connector, etc. The input device 105 is a device for receiving input of data through, for example, a keyboard or mouse, a touch screen, a key, a microphone, etc. The output device 106 includes, for example, a display or printer, a speaker, etc. for outputting data.

[0016] ==User Terminal 3== The user terminal 3 is a computer operated by a user who is a health support target. The user terminal 3 is, for example, a smartphone, a tablet computer, a personal computer, etc., but is not limited to these. The user can access the server device 1, for example, through an application or a web browser executed in the user terminal 3. The user terminal 3 is communicatively connected to the vital sign sensor 4 and the activity sensor 5. The user terminal 3 communicates with the vital sign sensor 4 and the activity sensor 5, for example, through Bluetooth (registered trademark) Low Energy (BLE, low-power Bluetooth) or serial communication.

[0017] ==Vital Signs Sensor 4== The vital sign sensor 4 is a device for acquiring the vital sign information of the user, and includes, for example, a sphygmomanometer, a pulse oximeter, and the like.

[0018] ==Activity Sensor 5== The activity sensor 5 is a device for acquiring activity information related to the user's activity. The activity sensor 4 includes, for example, a pedometer, an activity meter, and the like.

[0019] In addition, the vital sign sensor 4 and the activity sensor 5 may be the same device, and a part or the whole of the vital sign sensor 4 and the activity sensor 5 may also be installed as a part of the user terminal 3 .

[0020] Figure 3 is a block diagram showing the functional structure of the server device 1. Figure 3 As shown, the server device 1 is composed of various processing units including a measurement value acquisition unit 111, an intake amount acquisition unit 112, an action amount acquisition unit 113, a life stage information acquisition unit 114, an analysis unit 115, an evaluation unit 116, a recipe suggestion unit 117 and an action suggestion unit 118, and various storage units including a measurement value storage unit 131, an intake amount storage unit 132, an action amount storage unit 133, a life stage information storage unit 134, a recipe storage unit 135 and an ingredient information storage unit 136.

[0021] In addition, the above-mentioned processing units are implemented by the processor 101 of the server device 1 reading the program stored in the storage device 103 into the memory 102 for execution, and the above-mentioned storage units are implemented as part of the storage area provided by the memory 102 and the storage device 103 of the server device 1.

[0022] Here, in this embodiment, the data structure of the measurement value storage unit 131, the intake amount storage unit 132, the activity amount storage unit 133, the life stage information storage unit 134, the recipe storage unit 135 and the food information storage unit 136 is shown.

[0023] The measurement value storage unit 131 stores measurement values ​​linked to the user's achievement goals. The achievement goals include the acquisition, maintenance, and improvement of health, aesthetics, body shape, motor function, brain function, skills, endurance, etc., but are not limited to these. The measurement value can be any value that is linked to the action result and can be measured. For example, as the measurement value of endurance, the heart rate at rest can be used, the average heart rate during 30 minutes of running can be used, or the time of 1500m can be used. As long as these measurement values ​​are improved (in the case where the larger the value, the greater the degree of improvement, it can be expressed by the size of the value, in the case of wanting to approach a specified value, it can be expressed by the degree of deviation from the target value, and in the case where the smaller the value, the greater the degree of improvement, it can be expressed by the small value), it can be expressed that the result of the action has improved. The measurement value of the achievement goal can be associated with the measured time, and historical data can be stored. In addition, the measurement value storage unit 131 can also store the standard value of the measurement value of each user (hereinafter referred to as the measurement standard value). The measurement standard value can be set as the latest measurement value of the user, or as a statistical value (average value or median value, etc.) for a specified period in the past. The measurement value storage unit 131 can store a plurality of measurement values. For example, when the measurement value linked to the user's achievement goal is weight, blood pressure or heart rate, 1500m time, etc. can be recorded. Thus, when the user changes to another achievement goal, if the linked measurement value is logged in, the recipe can be evaluated using the data logged in in the past.

[0024] The intake storage unit 132 stores the intake of nutrients ingested by the user. The nutrients include nutritional component representation items based on food representation (calories, proteins, lipids, carbohydrates, sodium, saturated fatty acids, n-3 fatty acids, n-6 fatty acids, cholesterol, sugars, sugars (monosaccharides or disaccharides, not sugar alcohols), dietary fiber, zinc, potassium, calcium, chromium, selenium, iron, copper, magnesium, manganese, molybdenum, iodine, phosphorus, niacin, pantothenic acid, biotin, vitamins A, B1, B2, B6, B12, C, D, E, K, folic acid), and may include amino acids, components other than nutrients such as polyphenols or GABA, which are non-nutritional components, and a group of components consisting of multiple components determined from the nutrients (for example, cyclodextrin of dietary fiber), etc. The intake storage unit 132 can store the intake of nutrients ingested by the user, the date and time or time period of intake, and the intake of nutrients obtained at breakfast, lunch, dinner, snacks, etc.

[0025] The action amount storage unit 133 stores the user's action amount. The action amount is the amount of the user's action, including, for example, the type and amount (number of times, duration) of the exercise performed by the user, and the type and amount (number of times, duration) of the test (such as memory test, etc.) performed by the user, but is not limited to these. The action amount storage unit 133 can store the action amount for each unit period (for example, it can be set to one day, or it can be set to after breakfast, after lunch, after dinner, etc. according to the number of meals). In addition, the action amount storage unit 133 can also store the standard value of each user's action amount (hereinafter referred to as the action standard value). The action standard value can be set to the user's latest action amount, or it can be set to a statistical value (average value or median value, etc.) for a specified period in the past.

[0026] The life stage information storage unit 134 stores information related to the user's life stage. The life stage includes the user's age, or the stages classified by age such as childhood, youth, middle age, and old age, and may include status related to affiliation or employment such as student, social person, working, unemployed, and retired, and further information on lifestyles such as single, married, pregnant, maternity leave, paternity leave, and childcare (infants, toddlers, children, elementary and middle school students, and college students), but is not limited to these.

[0027] The recipe storage unit 135 stores recipes. A recipe is information including the types and contents of nutrients to be taken as food. Figure 4 As shown in one example, it may include the name, the types and amounts of the ingredients and seasonings contained, and further the types and amounts of nutrients contained in each ingredient and seasoning. Figure 4 In the recipe, the example of a so-called one-dish (tofu miso soup) is shown, but it can also be a set meal containing multiple dishes (for example, a combination of rice, tofu miso soup, ginger-roasted pork, spinach salad and yogurt). In addition, uncooked ingredients (such as oranges or almonds) or pre-cooked ingredients (such as beef leg) can also be included in the "recipe". Furthermore, the so-called nutrients include nutritional component representation items based on food representation (calories, proteins, lipids, carbohydrates, sodium, saturated fatty acids, n-3 fatty acids, n-6 fatty acids, cholesterol, sugars, carbohydrates (monosaccharides or disaccharides, not sugar alcohols), dietary fiber, zinc, potassium, calcium, chromium, selenium, iron, copper, magnesium, manganese, molybdenum, iodine, phosphorus, niacin, pantothenic acid, biotin, vitamins A, B1, B2, B6, B12, C, D, E, K, folic acid), and, although non-nutritional components, for example, components other than nutrients such as polyphenols or GABA and a group of components consisting of multiple components determined from nutrients (for example, cyclodextrin of dietary fiber), etc. In addition, information including recipes of recipes and cooking processes that may affect ingredients and nutrients (including heating, cooling, boiling, washing, etc., but not limited to these) can be stored together.

[0028] The food information storage unit 136 stores information about food. Figure 5 As shown in an example, the food information stores the types and amounts of nutrients contained in the food. In addition, the food information may also store information on seasonings, and also stores, for each food, the effects on nutrients caused by cooking (decomposition due to heating, etc.) or the effects on nutrients caused by the relationship with other food cooked at the same time.

[0029] Here, in this embodiment, the functions of the processing units of the measurement value acquisition unit 111, the intake amount acquisition unit 112, the activity amount acquisition unit 113, the life stage information acquisition unit 114, the analysis unit 115, the evaluation unit 116 and the recipe suggestion unit 117 are shown.

[0030] The measured value acquisition unit 111 acquires measured values ​​linked to the user's achievement goal and stores them in the measured value storage unit 131. The measured value acquisition unit 111 presents an input form to the user terminal 3, and can receive input such as a value or a selection of an option from the user to acquire the measured value. In addition, the measured value acquisition unit 111 can acquire the measured values ​​acquired from the vital sign sensor 4 or the activity sensor 5 through the user terminal 3, or directly acquire the measured values ​​from the vital sign sensor 4 or the activity sensor 5 through the network 2. In addition, the measured value acquisition unit 111 can receive input of the measured value from the user. The measured value acquisition unit 111 can access a computer (e.g., a database server) that manages the measured values ​​to acquire the measured values. The measured value acquisition unit 111 can acquire, for example, a measured value of time measured by a stopwatch, or a measured value such as a score of a test.

[0031] The intake amount acquisition unit 112 acquires information on the intake amount of nutrients ingested by the user. The intake amount acquisition unit 112 presents an input form to the user terminal 3, receives input of a consumed recipe or selection of a recipe option, and acquires information related to the consumed amount. The intake amount acquisition unit 112 can acquire information on an image (which may include animation) of consumed food from the user terminal 3, infer the recipe contained in the image by analyzing the image, present the inferred recipe to the user terminal 3 in a correctable manner, and acquire the consumed amount at the same time. The intake amount acquisition unit 112 acquires information on nutrients contained in the recipe consumed by the user obtained from the user terminal 3 from the recipe storage unit 135, associates the date and time of consumption, or the category of food such as breakfast, lunch, dinner, snacks, etc. with the recipe, and stores it in the intake amount storage unit.

[0032] The action amount acquisition unit 113 acquires information about the amount of action performed by the user. The action amount acquisition unit 113 presents an input form to the user terminal 3, receives input such as a value or a selection of an option from the user, and acquires the action amount. Furthermore, the action amount acquisition unit 113 may acquire the measured value acquired from the vital sign sensor 4 or the activity sensor 5 through the user terminal 3, or may directly acquire the measured value from the vital sign sensor 4 or the activity sensor 5 through the network 2. In addition, the action amount acquisition unit 113 may also acquire information about the action amount through an information terminal used by a supporter of the user (for example, including but not limited to a nursing staff, a medical staff, a trainer, etc.).

[0033] The life stage information acquisition unit 114 acquires information related to the life stage of the user. The life stage information acquisition unit 114 presents an input form to the user terminal 3, receives input such as a value or a selection of an option from the user, and acquires the life stage information.

[0034] The analysis unit 115 analyzes the relationship between the intake of nutrients and the measured value for achieving the target, and specifies the improvement factor that helps to improve the measured value and the deterioration factor that helps to worsen the measured value. The improvement factor and the deterioration factor include nutrients. Moreover, the improvement factor and / or the deterioration factor may include the amount of action of the user's action. In this embodiment, the analysis unit 115 analyzes the measured value of the second day after the user takes the nutrients and the relationship with the intake amount. The time point as the prediction object is not limited to the second day, and can also be set to a day after any period such as 1 week, 2 weeks, or 1 month. In the following description, the data collection period for analysis is referred to as the "observation period", and the period of the diet in which the intake measured value is close to the target value is referred to as the "intervention period". In addition, not only the data within the observation period can be used as the analysis object, but also the data within the intervention period can be used as the analysis object. The observation period and the intervention period can be set to any period. The intervention period can be set to a different length from the period for achieving the goal (hereinafter referred to as the trial period). For example, the intervention period can also be set to 1 week, and the trial period can be set to three months or one year. The analysis unit 115 can use the measured value at the end of the intervention period or after the end for analysis. The analyzing unit 115 may update the statistical model (prediction model) by performing analysis only before the start of the intervention period or periodically.

[0035] The analyzing unit 115 can obtain a prediction model (hereinafter referred to as a nutrition model) by multivariate analysis using the intake of nutrients as explanatory variables and the measured values ​​as target variables.

[0036] Furthermore, the analysis unit 115 can analyze the relationship between the nutrient intake and the action amount and the measured value, and identify the nutrients and / or actions that contribute to the improvement of the measured value, i.e., the improvement factor, and the nutrients and / or actions that contribute to the deterioration of the measured value, i.e., the amelioration factor. There can be multiple actions for the action amount. For example, the analysis unit 115 can obtain a prediction model (hereinafter referred to as a nutrition action model) by performing a multivariate analysis using the respective intake amounts of various nutrients such as energy, protein, lipid, carbohydrate, vitamin A, and the number of steps, exercise duration, and the number of times a memory test is taken as explanatory variables, and the measured value (weight, cardiopulmonary function, memory test results, etc.) as the target variable.

[0037] The analysis unit 115 can analyze the relationship between the nutrient intake and the life stage and the measured value, and identify the nutrients and / or life stage that contribute to the improvement of the measured value, i.e., the improvement factor, and the nutrients and / or life stage that contribute to the deterioration of the measured value, i.e., the deterioration factor. For example, the analysis unit 115 can obtain a prediction model (hereinafter referred to as a nutritional life stage model) by multivariate analysis using the intake of various nutrients such as energy, protein, lipid, carbohydrate, vitamin A, and dummy variables representing life stages such as middle-aged, college students, and pregnant women as explanatory variables and the measured value (weight, cardiopulmonary function, memory test results, etc.) as the target variable.

[0038] The analysis unit 115 can analyze the relationship between the nutrient intake and the date and time (which can be converted into a time period or season derived from the date and time) at which the measured value is measured, and the measured value, and identify the nutrients and / or date and time that contribute to the improvement of the measured value, i.e., the improvement factor, and the nutrients and / or date and time that contribute to the deterioration of the measured value, i.e., the deterioration factor. For example, the analysis unit 115 can obtain a prediction model (hereinafter referred to as a nutrient date and time model) by multivariate analysis using the respective intake amounts of various nutrients such as energy, protein, lipid, carbohydrate, vitamin A, and the date and time, time period, and season such as 9 a.m., 5 p.m., morning, daytime, night, spring, summer, autumn, and winter as explanatory variables and the measured value (weight, cardiopulmonary function, memory test results, etc.) as the target variable.

[0039] As described above, the analysis unit 115 can perform multivariate analysis by using the measured value as the target variable and at least one of the nutrient intake, the amount of activity, the life stage, and the date and time as the explanatory variable. The analysis unit 115 can obtain a prediction model (hereinafter referred to as a nutritional composite model) that combines multiple of the amount of activity, the life stage, and the date and time into the explanatory variable combined with the nutrient intake. The analysis unit 115 can also output the coefficients of each element used for the explanatory variable. Figure 6is a diagram showing an example of a multivariate analysis result performed by the analysis unit 115. Figure 6 As shown, regression coefficients (partial regression coefficients) can be output for nutrients, activity level, life stage, date and time.

[0040] In addition, the multivariate analysis of this embodiment includes univariate regression analysis, multivariate regression analysis, principal component analysis, independent component analysis, factor analysis, discriminant analysis, canonical discriminant analysis, quantification theory (type I, type II, type III, type IV), multi-group quantification type II, cluster analysis, joint analysis, logistic regression, multidimensional scaling (MDS), extended quantification type I, extended quantification type II, correspondence analysis, and covariance structure analysis.

[0041] The analysis unit 115 may store the above-mentioned prediction models (including nutrition model, nutrition action model, nutrition life stage model, nutrition date and time model, nutrition complex model) in the server device 1. Moreover, in this case, the server device 1 also stores parameters such as regression coefficients or constants applied to the prediction model.

[0042] The analysis unit 115 performs, for example, a multiple regression analysis to obtain a prediction model, and can estimate a regression coefficient and a constant for at least one of the nutrients, the amount of action, the life stage, and the date and time used as explanatory variables. The analysis unit 115 stores the estimated regression coefficient and constant in the server device 1. For the prediction model to which the estimated regression coefficient and constant are applied, by applying at least one of the nutrients, the amount of action, the life stage, and the date and time, when the user takes a diet containing such nutrients and performs the action of the amount of action, it is possible to estimate the measured value of the user when the user is in the life stage or when the measured value is measured on the date and time. In addition, the absolute value of the regression coefficient indicates the degree of improvement or deterioration of the measured value.

[0043] In addition, when the target value of the measured value that the user achieves the goal is greater than the current measured value, the explanatory variable that is a positive or 0 regression coefficient can be set as an improvement factor to improve the measured value, and the explanatory variable that is a negative regression coefficient can be set as a deterioration factor to worsen the measured value. When the target value of the measured value that the user achieves the goal is less than the current measured value, the factor that is a negative or 0 regression coefficient can be set as an improvement factor, and the factor that is a positive regression coefficient can be set as a deterioration factor.

[0044] The evaluation unit 116 can evaluate the recipe based on the content of the nutrient as the improvement factor and the content of the nutrient as the deterioration factor. Regarding the evaluation unit 116, for example, if the number of improvement factors contained in the recipe is greater, the evaluation of the recipe is higher, and if the number of deterioration factors contained in the recipe is greater, the evaluation of the recipe is lower. The evaluation unit 116 can, for example, evaluate the recipe based on the weighted average of the nutrient content of the improvement factor and the coefficient of the deterioration factor (for example, when the improvement factor and the deterioration factor have opposite signs, it can be calculated in the form of Σ(content of improvement factor×coefficient of improvement factor)+Σ(content of deterioration factor×coefficient of deterioration factor); when the coefficient represents the "degree" of improvement or deterioration such as the absolute value of the regression coefficient of multivariate regression, it can be calculated in the form of Σ(content of improvement factor×coefficient of improvement factor)-Σ(content of deterioration factor×coefficient of deterioration factor)).

[0045] The evaluation unit 116 may also evaluate the recipe based on the prediction model generated by the analysis unit 115. For example, the evaluation unit 116 may receive an input of a target value corresponding to the measured value of the target variable of the prediction model from the user terminal 3, and estimate the intake of the nutrient (hereinafter referred to as the predicted intake) whose predicted value inferred by the prediction model becomes the target value. The evaluation unit 116 may highly evaluate recipes with nutrient amounts close to the predicted intake amount, and less highly evaluate recipes with nutrient amounts that deviate from the predicted intake amount. The evaluation unit 116 may assign an evaluation value to each recipe for each prediction model. The evaluation value may quantify the degree of deviation from the estimated predicted intake amount, but is not limited to this.

[0046] The evaluation unit 116 may evaluate the combination of recipes based on the prediction model. The evaluation unit 116 may highly evaluate the combination of recipes in which the total nutrient amount of the nutrients contained in the plurality of recipes is close to the predicted intake amount, and may lowly evaluate the combination of recipes in which the total nutrient amount of the nutrients contained in the plurality of recipes is deviated from the predicted intake amount. The evaluation unit 116 may assign an evaluation value to each combination of recipes for each prediction model.

[0047] In addition, the evaluation unit 116 may evaluate the amount of activity, life stage, date and time, amount of activity, and diet based on the prediction model generated by the analysis unit 115. The evaluation method may be performed according to the above-mentioned diet evaluation method.

[0048] The target value input unit 119 receives input of a target value that is a measured value for achieving a user's goal, such as a target weight value, a target sprint time value, a target test score value, etc.

[0049] The recipe suggestion unit 117 can select recipes to be recommended to the user based on the evaluation values ​​of the recipes, and present them on the user terminal 3. For example, the recipe suggestion unit 117 can calculate the evaluation values ​​of each recipe stored in the recipe storage unit 135 in the evaluation unit 116, select a prescribed number (which can be one, ten, or any other number) of one recipe or a combination of multiple recipes in order of the evaluation values ​​from high to low, and present the selected recipes or combinations of recipes on the user terminal 3. In addition, the recipe suggestion unit 117 can pre-set restriction conditions when combining multiple recipes. For example, the restriction conditions can include a limit on the number of recipes included in a combination, an upper limit on the total amount of ingredients included in a recipe, an upper limit on the intake of one or more nutrients in one meal, etc.

[0050] Furthermore, the recipe suggestion unit 117 can select and present a recipe that can achieve the target value received by the target value input unit 119. The recipe suggestion unit 117 can provide the content of nutrients contained in the recipe to the prediction model obtained by analyzing the nutrients and the measured values ​​by the analysis unit 115 to estimate the predicted value of the measured value, determine whether the predicted value achieves the target (when the measured value is as large as possible, the predicted value is above the target value, when the measured value is as small as possible, the predicted value is below the target value, and when it is preferably close to a specific value, the difference between the predicted value and the target value is less than a specified threshold), and select a recipe that achieves the target. In addition, in the case of a prediction model other than a nutritional model, at least one of the user's life stage (which can be pre-set or received as input), the current date and time or the date and time scheduled to take the recipe during the intervention period, and the standard scheduled action amount (which can be pre-set or received as input) can be provided to estimate the change in the measured value.

[0051] Moreover, the recipe suggestion unit 117 can suggest adjusting (changing, adding, deleting) nutrients for a given recipe to improve the measured value. The intervention degree (adjustment degree) of the recipe suggestion unit 117 by nutrient adjusts the nutrients in such a way that the improvement degree of the improvement factor exceeds the improvement degree of the deterioration factor. The so-called intervention degree (adjustment degree) refers to the degree of increase when comparing the improvement degree of the improvement factor and the deterioration factor included in the diet before adjustment by the recipe suggestion unit 117 (i.e., the diet previously adopted by the user) with the improvement degree of the improvement factor and the deterioration factor included in the diet after the nutrient content recommended by the recipe suggestion unit 117 is adjusted.

[0052] For example, suppose that the target value is higher than the current value of the measured value (i.e., if the regression coefficient is positive, it becomes an improvement factor, and if the regression coefficient is negative, it becomes a deterioration factor). Here, the regression coefficient × content of the improvement factor included in the recipe before adjustment is 5, and the regression coefficient × content of the deterioration factor included in the recipe before adjustment is -3. Furthermore, if the regression coefficient × content of the improvement factor included in the adjusted recipe using the recipe suggestion unit 117 is 8, and the regression coefficient × content of the deterioration factor included in the adjusted recipe is -1, then regarding the adjustment degree (intervention degree) of the nutrient, the total adjustment amount of the coefficient × content of the improvement factor (i.e., 8-5=3) and the total adjustment amount of the coefficient × content of the deterioration factor (i.e., (-1)-(-3)=2), that is, "5", becomes the intervention degree (adjustment degree). The recipe suggestion unit 117 adjusts the nutrients in a manner such that the intervention degree (adjustment degree) is positive, and expects the measured value to increase.

[0053] In addition, when the target value of the measured value is lower than the current value, if the regression coefficient is negative, it becomes an improvement factor, and if the regression coefficient is positive, it becomes a deterioration factor. By adjusting the nutrients in such a way that the total change of the regression coefficient × content before and after adjustment (intervention degree, adjustment degree) is negative, the measured value is expected to decrease (improve).

[0054] Moreover, when the recipe suggestion unit 117 uses the degree of improvement and the degree of deterioration (the absolute value of the regression coefficient), if the value obtained by subtracting the degree of deterioration × the content of the improvement factor contained in the adjusted recipe (adjusted improvement value) is greater than the value obtained by subtracting the degree of deterioration × the content of the improvement factor contained in the recipe before adjustment (improvement value before adjustment), that is, the intervention degree (adjustment degree) is positive, then the expected measured value is improved (increased or decreased).

[0055] The recipe suggestion unit 117 may adjust the nutrients so that the degree of intervention (adjustment degree) leads to improvement (when using a regression coefficient, it is positive when the measured value is increased and negative when the measured value is decreased).

[0056] In this way, by adding the improvement factor and the deterioration factor respectively, the total intervention degree (adjustment degree) can be obtained as an indicator of the overall impact brought about by the adjustment of the improvement factor and the deterioration factor during the intervention period. The total intervention degree (adjustment degree) is always the improvement factor > deterioration factor. The total intervention degree (adjustment degree) becomes the improvement factor > deterioration factor in the three modes of (1) the improvement factor is positive and the deterioration factor is positive, (2) the improvement factor is positive and the deterioration factor is negative, and (3) the improvement factor is negative and the deterioration factor is negative. If this total intervention degree (adjustment degree) mode can be achieved, then regardless of whether it is the improvement factor or the deterioration factor, individual nutrients (including the amount of action) can be adjusted freely.

[0057] Furthermore, the recipe suggestion unit 117 can suggest, for a given recipe, to adjust the measured value to a target value by changing or adding ingredients (including seasonings). In this embodiment, the recipe provided to the recipe suggestion unit 117 is a recipe for each meal of multiple meals (preferably all meals) taken during the intervention period.

[0058] In addition, a recipe for one meal or a recipe for three meals a day may be provided to the recipe suggestion unit 117. In this case, the intervention period may be set to one time or one day for analysis.

[0059] The recipe suggestion unit 117 may change, add, and / or delete the ingredients included in the recipe (or the recipes included in the recipe set) in such a way that the improvement degree × content of the improvement factor exceeds the deterioration degree × content of the deterioration factor, and the excess is as large as possible. Moreover, the recipe suggestion unit 117 may change, add, and / or delete the ingredients included in the recipe (or the recipes included in the recipe set) in such a way that the above-mentioned total intervention degree (adjustment degree) becomes the improvement factor (adjustment value of improvement degree × content) > the deterioration factor (adjustment value of deterioration degree × content).

[0060] For example, the recipe suggestion unit 117 can select ingredient B that contains more nutrients that serve as improvement factors than ingredient A from the ingredient information storage unit 136 for one or more ingredients A included in a given recipe, change ingredient A to the selected ingredient B, and present it on the user terminal 3.

[0061] The recipe suggestion unit 117 provides the content of nutrients contained in the selected recipe to the nutrition model to estimate the change in the measured value, and adds the estimated change to the measured standard value stored in the measured value storage unit 131 to calculate a first predicted value of the measured value. When the predicted value does not reach the target, with respect to one or more ingredients B, ingredient A can be changed to ingredient B and a second predicted value of the measured value can be calculated in the same manner as above, and the second predicted value is tested to see whether it reaches the target, and ingredient B that reaches the target is selected.

[0062] When there is no ingredient B that achieves the target, the recipe suggestion unit 117 may select the ingredient B with the smallest difference between the target value and the predicted value. In this case, the recipe suggestion unit 117 may output the second predicted value as the achievable measured value.

[0063] The recipe suggestion unit 117 may select an ingredient D containing less nutrients serving as a deteriorating factor than ingredient C from the ingredient information storage unit 136 for ingredient C included in a given recipe, change ingredient C to the selected ingredient D, and present it to the user terminal 3 .

[0064] Moreover, the recipe suggestion unit 117 may suggest deleting ingredients containing a nutrient that serves as a modifier in an amount exceeding a prescribed amount, ingredients or recipes containing a nutrient that serves as a modifier in an amount exceeding a prescribed amount, ingredients or recipes in which the amount of a nutrient that serves as a modifier is greater than the amount of a nutrient that serves as an improvement factor, and ingredients or recipes in which the sum of the absolute values ​​of the regression coefficients of the modifier factors is greater than the sum of the absolute values ​​of the regression coefficients of the improvement factors.

[0065] The recipe suggestion unit 117 may select ingredients containing nutrients serving as improvement factors from the ingredient information storage unit 136 , add the ingredients to the recipe, and present the ingredients to the user terminal 3 .

[0066] The recipe suggestion unit 117 may select a recipe using the degree of improvement or deterioration, i.e., the absolute value of the regression coefficient calculated by the analysis unit 115 (referred to as the improvement coefficient for the improvement factor and the deterioration coefficient for the deterioration factor). The recipe suggestion unit 117 calculates a first value by multiplying the content of the improvement factor included in the recipe by the improvement coefficient of the improvement factor (hereinafter referred to as the improvement value) and subtracting the value obtained by multiplying the content of the deterioration factor included in the recipe by the deterioration coefficient of the deterioration factor (hereinafter referred to as the deterioration value). For a changed recipe in which at least one ingredient F included in the recipe is changed to ingredient G, the ingredient G may be selected in such a manner that a second value obtained by subtracting the deterioration value of the changed recipe from the improvement value of the changed recipe is greater than the first value, and the ingredient F is changed to the selected ingredient G, and the recipe is presented to the user terminal 3.

[0067] The recipe suggestion unit 117 calculates a first value obtained by subtracting the improvement value of the recipe from the deterioration value of the recipe. Regarding the recipe after the additional ingredient H is added to the recipe, the ingredient H can be selected in such a way that a second value obtained by subtracting the improvement value from the deterioration value is greater than the first value, and the selected ingredient H is added to the recipe and presented on the user terminal 3.

[0068] In addition, the analysis unit 115 periodically performs analysis to identify improvement factors and deterioration factors, and the evaluation unit 116 can evaluate the recipe along with the analysis of the analysis unit 115. For example, multiple analyses and suggestions can be performed during the intervention period. In this case, the recipe suggestion unit 117 does not change the ingredients (nutrients) and activity amount of the past recipes, but adjusts the future recipes (and activity amount).

[0069] The action suggestion unit 118 may prompt the user terminal 3 with an action amount for achieving the goal.

[0070] For example, when the target value cannot be achieved only by the recipe suggested by the recipe suggestion unit 117, the action suggestion unit 118 can make action suggestions. The action suggestion unit 118 can calculate the action amount estimated to achieve the target value with respect to the action amount of the suggested action. For example, according to the recipe suggested by the recipe suggestion unit 117 based on the nutrition model (with the ingredients changed, added or deleted), the first predicted value of the measured value achieved when the action amount is 0 can be calculated (which can be calculated by providing the content of the nutrients contained in the recipe to the nutrition model), and when the first predicted value does not reach the target value, it can be suggested to adjust the action standard value. In this case, the analysis unit 115 pre-estimates the nutrition action model, and the recipe suggestion unit 117 provides the action standard value and the content of the nutrients to the nutrition action model to calculate the first predicted value, and can suggest changing, adding, and / or deleting the recipe of the ingredients in a way that the first predicted value is closest to the target value. In addition, the action suggestion unit 118 can adjust the action amount according to the improvement coefficient or deterioration coefficient of the action. The action suggestion unit 118 can adjust the action amount by changing the action amount in such a way that the second predicted value calculated by providing the action amount and the content of nutrients included in the recipe suggested by the recipe suggestion unit 117 to the nutrition-action model reaches the target value.

[0071] Furthermore, when the predicted value estimated by the nutrition action model does not reach the target value, the action suggestion unit 118 can calculate the increase in the amount of action corresponding to the shortfall by, for example, dividing the shortfall by the improvement coefficient, and calculate the amount of action by adding the calculated amount to the action standard value, and send the calculated amount of action and a message suggesting to take action to the user terminal 3. Conversely, when the action is a deterioration factor, the action suggestion unit 118 can calculate the decrease in the amount of action corresponding to the shortfall by dividing the shortfall by the deterioration coefficient (making the action standard value the maximum value), and send the calculated decrease and a message suggesting not to take action to the user terminal 3.

[0072] The action suggestion unit 118 may also use the regression coefficient (improvement coefficient or deterioration coefficient) of the action amount in the nutritional action model calculated by the analysis unit 115 to suggest the action amount for improving the measured value. The action suggestion unit 118, for example, calculates the value obtained by multiplying the action amount analyzed by the analysis unit 115 by the regression coefficient (hereinafter referred to as the action amount value). When the action amount is an improvement factor, the larger the action amount value, the more it is related to the improvement of the measured value. When the action amount is a deterioration factor, the smaller the action amount value, the more it is related to the improvement of the measured value. When the action amount is an improvement factor, the action suggestion unit 118 estimates the action amount recommended for the user's age group or gender, or the action amount that is the average of the user's past actions multiplied by a specified value without being excessive, and may present these action amounts on the user terminal 3. Moreover, when the action amount is a correction factor, the action recommendation unit 118 can recommend an action amount of 0 in a manner that minimizes the action amount value. However, for actions that will cause health or life problems if the action amount is 0 (such as walking, but not limited to these), the minimum action amount recommended for the user's age group or gender, or the average of the user's past action amounts multiplied by a specified value that is not too small can be estimated, and these action amounts can be presented on the user terminal 3.

[0073] Furthermore, the recipe suggestion unit 117 may make suggestions on recipes and actions after adjusting the nutrients (ingredients) of a given recipe and adjusting the amount of action.

[0074] use Figure 8 A representative processing flow of the server device 1 is described. The measurement value acquisition unit 111 acquires the measurement value from the user terminal 3 (1001). The intake amount acquisition unit 112 acquires the intake amount from the user terminal 4 (1002). The action amount acquisition unit 113 acquires the action amount from the user terminal 3 (1003). The life stage information acquisition unit 114 acquires the life stage information from the user terminal 3 (1004). The analysis unit 115 analyzes the relationship between the measurement value and other factors such as the intake amount, the action amount, and the life stage information (1005). The evaluation unit 116 evaluates the recipe based on the analysis result of the analysis unit 115 (1006). The recipe suggestion unit 117 presents the selected recipe to the user terminal 3 based on the evaluation result of the evaluation unit 116. (1007). The action suggestion unit 118 presents the selected action to the user terminal 3 based on the evaluation result of the evaluation unit 116. (1008).

[0075] The preferred embodiments of the present invention are described in detail with reference to the accompanying drawings, but the technical scope of the present invention is not limited to the relevant examples. It should be understood that it is obvious that the technicians of the present invention can think of various changes or modifications within the scope of the technical ideas recorded in the scope of the patent application, and these certainly also belong to the technical scope of the present invention.

[0076] For example, the recipe suggestion unit 117 may select a recipe by considering the information of the recipe or process of the recipe stored in the recipe storage unit 135, and the information of the influence on nutrients caused by cooking for each ingredient, or the influence on nutrients caused by the relationship with other ingredients cooked at the same time, stored in the ingredient information storage unit 136. In this case, when adding ingredients to a recipe, the recipe suggestion unit 117 evaluates the relationship between the process of the recipe and the added ingredients, and when the nutrients of the added ingredients or the ingredients originally included change, the changed nutrients are used as the amount of the above-mentioned improvement factor or the above-mentioned deterioration factor for estimation. Moreover, when adding ingredients to a recipe, the recipe suggestion unit 117 evaluates the relationship between the ingredients included in the recipe and the added ingredients, and when the nutrients of the added ingredients or the ingredients originally included change, the changed nutrients are used as the amount of the above-mentioned improvement factor or the above-mentioned deterioration factor for estimation.

[0077] Moreover, in the present embodiment, the regression coefficient is directly used as the improvement coefficient and the deterioration coefficient, but it is not limited to this. The intervention degree (adjustment degree) can be calculated by multiplying the difference from the standardized nutrient content by the standardized coefficient (the coefficient obtained by standardizing the coefficient of the explanatory variable in the multiple regression equation). In this case, the intervention degree (adjustment degree) when adjusting the nutrient content becomes the difference between the nutrient content contained in the recipe before the change and the nutrient content contained in the recipe after the change. In this case, the intervention degree (adjustment degree) can be calculated by multiplying the difference from the unstandardized nutrient content by the unstandardized coefficient (the coefficient of the explanatory variable itself in the multiple regression equation). And, if the total intervention degree (adjustment degree) becomes a pattern of improvement factor > deterioration factor, the recipe suggestion unit 117 can make nutrient adjustments to achieve the target value (close to the target value).

[0078] The devices described in this specification may be implemented as a single device, or may be implemented by multiple devices (such as cloud servers) partially or entirely connected via a network. For example, each functional unit and each storage unit of the server device 1 may be implemented by different servers connected to each other via a network.

[0079] The series of processes of the device described in this specification can be implemented using any of software, hardware, and a combination of software and hardware. A computer program for implementing the various functions of the server device 1 of this embodiment can be produced and installed on a personal computer (PC) or the like. In addition, a computer-readable recording medium storing such a computer program can also be provided. The recording medium is, for example, a magnetic disk, an optical disk, a magneto-optical disk, a flash memory, etc. In addition, the above-mentioned computer program can be transmitted, for example, via a network without using a recording medium.

[0080] Furthermore, the processes described in the flowcharts in this specification may not necessarily be performed in the order shown in the diagrams. Some process steps may also be performed in parallel. Furthermore, additional process steps may be used, or some process steps may be omitted.

[0081] Furthermore, the effects described in this specification are always illustrative or exemplary effects and are not limited thereto. That is, in addition to the above effects, the technology disclosed in this specification can also have other effects that are obvious to those skilled in the art based on the description of this specification to replace the above effects.

[0082] Hereinafter, an example of the health support system according to the present embodiment will be described.

[0083] <First Embodiment> In the first embodiment, body weight is selected as a health indicator achieved by optimizing the amount of nutrient intake. The relationship between body weight, nutrient intake, and exercise volume (number of steps) is clarified through analysis, and whether a personal optimal diet that optimizes the amount of nutrients can achieve a weight improvement effect is verified by conducting experiments on humans, and an analytical method for efficient nutrient optimization is studied.

[0084] Test methods Equipment and software used The measurement and recording equipment used and the software including the mobile application are shown below. In addition, when the equipment used in the conditional research test and the clinical trial is different, a mark is added to the item. (+) indicates that it is used only in the conditional research test, and (*) indicates that it is used only in the clinical trial.

[0085] Equipment and reagents used 1) Weight and body composition scale (HBF-255T, Omron Healthcare Co., Ltd., Kyoto) 2) Activity meter (*) (Fitbit Charge 3, Fitbit (Google), United States) 3) Smartphone (*) (iPhone (registered trademark) SE (2020), Apple, United States) 4) Blood test kit (+) (DEMECAL blood test kit [Metabolic syndrome & lifestyle disease self-test], Leisure Co., Ltd., Tokyo)

[0086] Using Software 1)OMRON connect(+) (OMRON Healthcare Co., Ltd., Kyoto) 2) ASKEN (+) (ASKEN INC., Tokyo) 3) Fitbit (+) (Fitbit (Google), United States) 4) Mr. Dateman Web (*) (Chi-technology Co., Ltd., Tokyo) 5) SPSS Statistics ver.25 (IBM, USA) 6) SPSS Statistics ver.28(+)(IBM, USA)

[0087] Personal optimization of nutrient intake

[0088] Derivation of the weight prediction model formula In the first embodiment, a "weight prediction model formula" is created to predict the weight of the subject based on factors such as nutrients. The weight prediction model formula predicts the weight of each subject when waking up every day based on the amount of nutrients (selected from 21 components of water, protein, lipid, sugar, total dietary fiber, carbohydrates, sodium, potassium, calcium, magnesium, iron, zinc, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B2, vitamin B6, vitamin C, salt equivalent, and saturated fatty acids) and the energy intake, exercise volume (number of steps) and other data. When deriving the model formula, multiple regression analysis is used, which is an analysis method that predicts a certain target variable (target variable) only from the relationship between the explanatory variable and multiple other variables (explanatory variables). The software for multiple regression analysis uses SPSS Statistics ver.25 and ver.28 (IBM, USA), and the target variable is set to the weight when waking up, and the explanatory variable is set to the amount of nutrients and exercise volume from the previous day to three days ago to perform a multiple regression analysis of the variable reduction method.

[0089] It is known that when there is a strong correlation between the selected explanatory variables, the model formula cannot be correctly calculated and the possibility of the prediction error becoming larger becomes higher. Generally, the number of data required in the multiple regression analysis is 10 to 15 times the number of explanatory variables, but when applied to the first embodiment, the required period exceeds one year, which is unrealistic and cannot adapt to seasonal changes or body growth. Therefore, the data collection period is based on one month, and the model formula (Formula 1) is adopted. The number of explanatory variables selected is less than seven, which is one-fourth of the period, and the variance expansion coefficient (VIF) of the explanatory variables is less than 10, which can exclude the possibility of multicollinearity, that is, the correlation coefficient is inappropriately higher than the true value due to the correlation between the variables. The intake nutrients (explanatory variables) selected here are variables selected to predict the weight when getting up, and are considered to be weight-related nutrients that affect weight. In the formula, nutrients with positive signs of the multiple regression coefficient become weight gain factors, which are considered to be positively correlated with weight, so weight gain occurs through intake. On the other hand, nutrients with negative signs of the multiple regression coefficient become weight loss factors, which are considered to be negatively correlated with weight, so weight loss occurs through intake.

[0090] (Formula 1) Weight prediction model formula Weight when getting up = nutrient 1 × coefficient 1 + nutrient 2 × coefficient 2 ... + constant term

[0091] Optimization of nutrient content When individually designing a test diet that is expected to improve the subject's weight, the amount of food containing nutrients that contribute to weight gain or weight loss is adjusted for the subject determined by the weight prediction model formula.

[0092] When the total value of nutrients contained in the subject's daily diet is substituted into the model formula, the amount of nutrients the subject consumes in a day is optimized by changing the ingredients used in the subject's diet menu or making adjustments centered on changing the amount of prepared food on the menu in such a way that the predicted weight is close to the target range of the body mass index (BMI, Body Mass Index), which is 21.5 to 24.9 kg / m2.

[0093] However, in order to avoid health problems caused by excess or deficiency of nutrients, the following conditions (1) to (4) are established, and (2) and (4) are followed in conditional research experiments, and all (1) to (4) are followed in clinical trials. In addition, the menu content of the subjects' diet is different for each meal and is not continuous to avoid psychological pressure on the subjects from continuing to eat the same menu.

[0094] "condition" (1) The three major nutrients (carbohydrates, The estimated average required amount and target amount of lipids and proteins are amounts that are greater than or equal to the minimum value and less than 130% of the maximum value for the age and gender of the test subjects. (2) For nutrients with a tolerable upper limit, do not exceed the upper limit. (3) The amount of the component contributing to body weight specified during the observation period is 70% or more of the estimated average required amount or standard amount in the dietary intake standards for Japanese people. (4) The energy intake for one week was the same as the subjects' daily diet.

[0095] Test foods and nutrient intake The test food uses commercially available ingredients and is cooked in the same way that ordinary people prepare their daily meals. In the conditional study, the subjects buy and cook the food specified in the menu sheet at the supermarket, etc., which optimizes the amount of nutrients and specifies the ingredients and the amount to be used.

[0096] In clinical trials, a basic menu is prepared under the supervision of a nutritionist and taking into account the balance of main dishes and side dishes. The amount of nutrients is optimized by adjusting or replacing the amount of ingredients, and the ingredients and usage are specified. The ingredients and usage are sent to the trial site in the form of an "ingredient list" and cooked according to it, and meals are prepared for the subjects. The diet is basically three meals a day in the morning, noon and evening, and snacks (10 o'clock, 15 o'clock, and midnight snacks) are added and taken according to previous eating habits. In addition, if the subject does not finish the specified amount of test food, the amount of leftover food is recorded, and the completion rate is calculated based on the prepared meal amount to calculate the intake amount.

[0097] Conditional research test Characteristics of test subjects The subject of the conditional research trial was a healthy adult male who was 25 years old in April 2021. The height was 172.1 cm, and this value was used when calculating BMI (kg / m2).

[0098] Test schedule The conditional research experiment was conducted twice, a total of 98 days from September 1, 2020 to December 7, 2020, and 63 days from October 26, 2021 to December 27, 2021.

[0099] Implementation of the test in 2020 According to the four-phase schedule ( Fig. 9 ) Experiment implementation: observation period (28 days), washout period (7 days × 2 times), intervention period (28 days × 2 times), follow-up period (14 days).

[0100] During the observation period, weight and body composition were measured and recorded when getting up and before going to bed, and the types and amounts of food used in the diet were recorded. During the washout period, considering that the data collection during the observation period may lead to changes in the subjects' lifestyle and other actions to improve their weight, no data measurement was performed and they returned to their normal life state, and a diet with optimized nutrients was prepared based on the analysis of the subject data and the analysis results. During the intervention period, as during the observation period, the subject's diet with nutrients adjusted for the subject was consumed with breakfast, lunch, and dinner as the basic structure, and weight and body composition were measured as during the observation period.

[0101] Implementation of the trial in 2021 Based on the schedule consisting of two periods, the observation period (35 days) and the intervention period (28 days) Fig.10 ) to conduct clinical trials. Compared with the trial conducted in 2020, the changes are: the washout period without data collection has been cancelled, and daily data measurement continues uninterruptedly; considering that the internal environment is constantly changing, nutrients that are factors involved in weight may also change, and the intervention period is divided into the first to fourth periods. Multiple regression analysis is performed once a week, and the weight prediction model formula for nutrient optimization is updated.

[0102] Weight and body composition data measurement When measuring weight, body composition (body fat percentage (%), skeletal muscle percentage (%), basal metabolic rate (kcal)) and other data, use a home weight and body composition scale to perform three measurements when getting up. When processing each data, calculate and use the average of the three measured values.

[0103] The amount of exercise (number of steps) was measured using a watch-type activity meter that was worn on the left wrist throughout the day, except when it was taken off to charge the main unit during a shower.

[0104] Estimation of dietary nutrient intake During the observation period, the diet was recorded at breakfast, lunch, and dinner using a smartphone app for diet management. The diet recording function of the app estimated the intake of 20 ingredients including protein, lipids, sugars, total dietary fiber, carbohydrates, sodium, potassium, calcium, magnesium, iron, zinc, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B2, vitamin B6, vitamin C, salt equivalent, and saturated fatty acids, as well as the energy intake from the diet, and the total amount per day was recorded to create a model formula for predicting body weight based on the daily nutrient amount. The energy intake was used to set a diet that optimized the nutrient amount so that the energy remained unchanged during the observation period.

[0105] In addition, in the tests conducted in 2020, data based on the Japanese Standard Food Composition Table (2015 edition, seventh revision) were used, and in the tests conducted in 2021, data based on the Japanese Standard Food Composition Table (2020 edition, eighth revision) revised in December 2020 were used.

[0106] Blood tests In the conditional research experiment implemented in 2021, in order to investigate the internal environment of diet and life during the observation period and the intervention period, blood tests were performed using blood test kits. The measurement points were set to be a total of two times after the end of the observation period and the end of the intervention period, and blood was collected after getting up and before breakfast. The blood samples obtained by blood collection were sent to the testing agency for testing. The blood collection volume was 0.065mL per time.

[0107] Clinical trials Subject characteristics The clinical trial was conducted in accordance with the "Ethical Review Methods for Life Science and Medical Research Involving Human Beings". After explaining the situation to the staff of the institution, the candidate subjects, and the agent of the candidate subjects of the dementia patient (the subject's parents, spouse, guardian or equivalent) and finally obtaining written consent, a total of 9 people became the subjects of the clinical trial. Fig.11 shown.

[0108] Test schedule In the clinical trial, BMI was calculated based on the weight and height obtained in advance, and after screening to select and group the subjects, the clinical trial was implemented based on a schedule consisting of four periods: observation period (28 days), washout period (14 days), intervention period (28 days), and follow-up period (14 days). Fig.12 ).

[0109] During the observation period, body weight and body composition were measured when getting up and before going to bed. In addition, the amount of prepared meals and the amount of leftover food were recorded on a pre-provided menu sheet to calculate the amount of food used and the subject's dietary intake rate.

[0110] During the washout period, considering that the data collection during the observation period may lead to changes in the subjects' lifestyle and other behavioral changes that may improve their weight, no data measurements are performed and the subjects return to their normal lifestyle. In addition, a diet for the subjects with optimized nutrients is prepared based on the subject data analysis and analysis results.

[0111] During the intervention period, as during the observation period, each subject consumed a diet with individual nutrient adjustments based on breakfast, lunch, dinner, and snacks (10 a.m., 3 p.m., and midnight snack). Body weight and body composition were measured as during the observation period, and the amount of food used, the amount of food prepared for the subjects, and the amount of leftover food were recorded.

[0112] During the follow-up period, body weight and body composition were measured when getting up and before going to bed, as in the observation period. In addition, the amount of food used, the amount of food prepared for the subjects, and the amount of leftover food were recorded.

[0113] This clinical trial was conducted with the approval of the Ethics Review Committee. In addition, an informed consent meeting was held for the subjects and their consent was obtained.

[0114] Subject screening Body weight and body composition scales and weight recording sheets were distributed, and weight was measured for three days (when getting up and before going to bed), and screening was performed based on the results. BMI was calculated based on the weight measurement results and height, and the subjects were divided into two groups: the experimental group and the control group based on the following selection criteria.

[0115] “Criteria for selecting the experimental group” (1) A person who has received the explanation in advance, understands its contents and agrees to its gist, and has given written consent by himself or his agent. (2) Those whose BMI value calculated based on the weight measured over three days is not within the target weight range shown below (3) Target weight (over 65 years old): BMI 21.5-24.9 kg / m 2 (4) People who are not picky eaters and who eat breakfast, lunch, and dinner on a daily basis and consume a normal diet consisting of staple food, main dishes, and side dishes (5) Those who can consume the test food prepared according to the prescribed menu and preparation instructions (6) Those who do not drink alcoholic beverages on a daily basis and can control their alcohol intake during the test period

[0116] “Criteria for selecting the control group” (1) Among the subjects who met (1), (2), (4) to (8) of the above “Criteria for Selection of Test Group”, those whose BMI values ​​calculated based on the weight measured on three days were within the target weight range shown below (target weight (over 65 years old): BMI 21.5 to 24.9 kg / m 2 )

[0117] “Exceptional Benchmarks” (1) People whose weight is significantly abnormal (2) Those who have undergone laparotomy within six months from the start of the trial (3) Women who have experienced significant changes in their physical condition before and after menopause (4) People who may have allergic symptoms to drugs or food (5) Women who are pregnant or may become pregnant, or women who are breastfeeding (6) Those who are currently participating in other clinical trials or have participated in other clinical trials within four weeks (7) People who donate blood or receive continuous treatment through intravenous, intramuscular, or subcutaneous injections (8) In addition, any person who is deemed unqualified by the research representative

[0118] Weight and body composition data measurement When measuring weight, body composition (body fat percentage (%), skeletal muscle percentage (%), basal metabolic rate (kcal)) and other data, use a weight and body composition scale to perform three measurements when waking up and before going to bed. When processing data, the average of the three measured values ​​is calculated and used.

[0119] The weight and body composition data were recorded on a recording sheet by the person assisting the subject in the measurement. If the measured value had an error of more than 0.15 kg, a fourth measurement was performed, and the average of the three closest values ​​was calculated and used during data processing.

[0120] Estimation of dietary nutrient intake Nutrition management software was used to estimate the nutrient intake of the subjects.

[0121] By the supply nutrition scale output by the nutrition management software, energy, water, protein, lipid, sugar, total dietary fiber, carbohydrate, sodium, potassium, calcium, magnesium, iron, zinc, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B2, vitamin B6, vitamin C, salt equivalent, saturated fatty acid, a total of 21 kinds of ingredients are calculated according to the diet taken in one day. Here, the supply nutrition scale is a table that lists the daily intake of nutrients for a subject. In addition, the nutrition management software uses data based on the Japanese Food Standard Composition Table (2020 edition, eighth revision).

[0122] Statistical processing Evaluation of the intervention degree of nutrients involved in body weight In order to evaluate the degree of participation of weight-related factors during the intervention period in the weight improvement effect, a new indicator called intervention degree was set up. The intervention degree is the value of each weight-related nutrient, which is obtained by subtracting the average value of the standardized weight-related factors during the observation period from the average value of the standardized weight-related factors during the intervention period, multiplied by the absolute value of the standardized coefficient derived from the multiple regression analysis (Formula 2).

[0123] (Formula 2) Intervention degree calculation formula Intervention degree = [standardized mean value of weight participation factor (intervention period) - standardized mean value of weight participation factor (observation period)] × |standardization coefficient|

[0124] Here, standardization is a statistical method that corrects the value by making the mean value of the data 0 and the variance 1, and can compare factors such as weight-related factors with different units of nutrients. In addition, the standardized coefficient is a value used when comparing the multiple regression coefficients derived from multiple regression analysis with different explanatory variables, and these two values ​​are used to calculate the degree of intervention.

[0125] When the intervention level calculated for a single subject using Formula 2 (1) becomes a negative value and the weight improvement factor becomes a positive value, or (2) the intervention level of the weight improvement factor exceeds the intervention level of the weight improvement factor, it is evaluated that nutrient adjustments can be made to expect weight improvement compared to the observation period.

[0126] Inspection methods The measurement results calculated the mean value and standard error for each observation period and intervention period. Since the body weight measurement value on the first day of the intervention was the result of not taking the test food, the data on the first day of the intervention period were excluded from the test and statistical processing was performed. Regarding the individual body weight measurement values ​​of the subjects, in order to compare the mean values ​​during the observation period and the intervention period, a non-corresponding t-test was selected for statistical processing. The significance level in the test was set to 5% or less in a two-sided test, and the p value was indicated by "*" when it was less than 0.05, "**" when it was less than 0.01, and "***" when it was less than 0.001.

[0127] Experimental Results Conditional Study Test Results

[0128] Weight prediction model formula The weight at the time of waking obtained during the observation period was used as the target variable, and the amount of nutrients consumed and the amount of exercise (number of steps) were used as explanatory variables. Multiple regression analysis was performed using SPSS Statistics ver. 25 and 28 ( Fig.13 ). The model formula for predicting body weight when waking up was constructed by using the obtained multiple regression coefficients, and the weight-involved factors were identified based on the coefficient signs. The average value of the multiple correlation coefficients of the six model formulas used in the two-condition study was 0.80, and a high correlation was observed between nutrient intake and body weight. This suggests that body weight when waking up can be predicted based on nutrient intake and exercise volume (number of steps).

[0129] 2020, first period of intervention (Formula 3) Weight when getting up = -0.018×protein+0.0079×lipid-0.054×dietary fiber-0.16×iron+0.43×vitamin B6+0.014×vitamin C-0.00017×exercise (number of steps)+71.13

[0130] 2020, second period of intervention (Formula 4) Weight when getting up = 0.042 × lipids - 0.0054 × carbohydrates + 0.00059 × potassium + 0.0015 × calcium - 0.24 × vitamin E - 0.81 × vitamin B6 - 0.079 × saturated fatty acids + 71.87

[0131] 2021, first period of intervention (Formula 5) Weight when getting up = 0.0065 × carbohydrate + 0.0014 × potassium - 0.011 × magnesium + 0.034 × vitamin D - 2.01 × vitamin B6 + 0.0070 × vitamin C - 0.032 × saturated fatty acids + 71.84

[0132] 2021, second period of intervention (Formula 6) Weight when getting up = 0.019 × protein - 0.0024 × sugar + 0.0054 × carbohydrate + 0.0014 × calcium - 0.14 × iron - 0.068 × zinc - 0.24 × vitamin B1 + 70.76

[0133] 2021, third period of intervention (Formula 7) Weight when getting up = -0.000022 × sodium + 0.0011 × potassium - 0.0052 × zinc + 0.00076 × vitamin A - 1.01 × vitamin B6 + 71.19

[0134] 2021, intervention period 4 (Formula 8) Weight when getting up = 0.00036 × sodium + 0.00092 × potassium - 0.00093 × calcium + 0.028 × vitamin D - 0.72 × vitamin B6 + 0.14 × salt equivalent + 70.88

[0135] Weight-related nutrients in the test food The following Figures 14 to 19 The graph shows a comparison of the energy and nutrient amounts ingested by the subjects through the test food during the intervention period, with the intake during the observation period set as 100%. In the two bar graphs with the same label, the left side shows the intake during the observation period, and the right side shows the intake during the intervention period. The ○ mark indicates the weight improvement factor, and the × mark indicates the weight improvement factor. In addition, when designing the test food menu, conditions were set to keep the energy constant, so it was compared in the same way as the nutrients. The energy during the intervention period was adjusted within the range of 95% to 106% compared to the observation period. In addition, except for individual cases, the adjustment of the nutrient amount achieved an increase in the weight improvement factor and a decrease in the weight improvement factor. In addition, in the conditional research experiment implemented in 2020, the quality of sugar was also adjusted to remain consistent with the observation period.

[0136] Weight measurement results Regarding your morning weight as measured by a weight and body composition scale, Figures 20-22 A graph comparing the mean values ​​during the observation period and the intervention period is shown in the figure. In the comparison of the measurement periods of the conditional study trial conducted in 2020 and the conditional study trial conducted in 2021, a significant (p<0.001) weight loss (improvement in weight) was confirmed compared to the average weight of the subjects before the intake of the diet and during the observation period.

[0137] Body composition test results In the following Fig.23 , 24 The figure shows the body fat percentage, skeletal muscle percentage, and basal metabolic rate measured by weight and body composition scales. In the measurement of body composition, in the conditional research test implemented in 2020 and the conditional research test implemented in 2021, it was confirmed that the body fat percentage and basal metabolic rate showed a monotonically decreasing trend ( Fig.23 (a) Fig.24 (a)). Regarding skeletal muscle rate, no trend was observed throughout the trial period, so it was judged that the improvement in body weight (weight loss) in the conditional study trial depended on the reduction in body fat.

[0138] Activity measurement results The results of the activity meter measuring the amount of exercise (number of steps) are shown below. Figures 25-26 middle.

[0139] In the conditional research trial conducted in 2020, since the amount of exercise (number of steps) was included in the model formula as a weight improvement factor during the intervention period (first phase), the target number of steps increased from the observation period was set within a reasonable range (approximately 200% of the observation period), and walking was consciously performed so that the total number of steps per day reached that value. However, during the other periods, the amount of exercise (number of steps) was not included in the model formula as a weight participation factor, so walking was not performed consciously and life was maintained as usual. In the conditional research trial conducted in 2021, the amount of exercise (number of steps) was not included in the model formula as a weight participation factor, so walking was not performed consciously and life was maintained as usual.

[0140] Evaluation of the degree of nutrient intervention The following shows the degree of intervention of weight-related factors on the subjects ( Figures 27 to 32). In each figure, the ○ mark indicates the intervention degree of the weight-improving factor or the nutrient as its structural factor, and the × mark indicates the intervention degree of the weight-improving factor or the nutrient as its structural factor. When the intervention degree indicates a positive value, it means that the intake of the nutrient during the intervention period is increased compared with the observation period, and when it indicates a negative value, it means that the intake during the observation period is reduced. When the intervention degree of the weight-improving factor is a positive value, and the intervention degree of the weight-improving factor is a negative value, it means that an ideal intervention is performed to expect the subject's weight to be improved.

[0141] In the conditional research trial conducted in 2020, when focusing on various weight-related factors, there are nutrients that cannot be ideally intervened, such as vitamin B6 in the first phase of intervention. Even though it is a factor for improvement, the intervention level is positive ( Fig. 27 a), or if vitamin B6 is used in the second phase of intervention, even if it becomes an improvement factor, the degree of intervention is negative ( Fig.28 a) etc. However, when looking at the participating factors as a whole, the intervention degree of the improvement factor is positive, and the intervention degree of the deterioration factor is negative (the intervention degree of the improvement factor>0, the intervention degree of the deterioration factor<0). Moreover, in the conditional research trial implemented in 2021, among the overall weight participating factors, the intervention degree of the deterioration factor was positive in any period from the first to the fourth intervention period, but it was solved by further increasing the intervention degree of the improvement factor (the intervention degree of the improvement factor>the intervention degree of the deterioration factor>0).

[0142] Thus, even when the intervention levels of the individual weight-related factors are opposite to the ideal, from the perspective of the overall participating factors, by making the intervention level of the weight-improving factor a positive value and the intervention level of the weight-improving factor a negative value, a diet that is expected to improve the weight of the subject can be designed. Furthermore, even when the intervention level of the weight-improving factor is a positive value, by increasing the intervention level of the weight-improving factor to a value above the positive value, a weight-improving effect can also be expected.

[0143] Blood test results The results of blood tests conducted in the conditional research trial to be carried out in 2021 are shown below. The results confirmed that blood sugar levels and total cholesterol levels decreased ( Figures 33-36 ).

[0144] Clinical trial results Analyzing the subjects Although the amount of food consumed by the subjects during the intervention period was adjusted to keep it consistent with the energy intake during the observation period, it was confirmed that some of the nine subjects who completed the clinical trial had leftovers during the intervention period. When leftovers occur, the nutrient composition no longer conforms to the nutrient optimization design, and it is difficult to verify the effect under the expected conditions. Therefore, during the 28-day intervention period, three subjects who had leftovers for more than eight days (30%) at any of breakfast, lunch, and dinner were excluded from the effectiveness analysis.

[0145] As a result, there were four subjects (E-02, E-08, E-09, N-02) and two controls (E-04, N-06). In addition, the details of the subjects were that three subjects received intervention aimed at weight gain, and one subject received intervention aimed at weight loss.

[0146] Weight prediction model formula The body weight at the time of waking obtained during the observation period was used as the target variable, and the nutrient intake on the day before the body weight at the time of waking was used as the explanatory variable. Multiple regression analysis was performed using SPSS Statistics ver.25. The results are shown below ( Fig.37 ).

[0147] The model formula for predicting the weight at waking up was constructed by using the obtained multiple regression coefficients, and the weight factor was specified for each subject according to the sign of the coefficient. The average value of the multiple correlation coefficients of the seven model formulas was 0.64, and a correlation was found between the nutrient intake and the weight measurement value, which suggests that the weight at waking up can be predicted based on the nutrient intake. The following is an example.

[0148] E-02 (Formula 9) Weight when getting up = 0.00013 × sodium - 0.0051 × magnesium + 0.10 × iron + 0.0072 × vitamin D - 0.32 × vitamin B2 + 0.021 × saturated fatty acids + 44.58 E-08 (Formula 10) Weight when getting up = 0.014 × lipids + 0.0060 × carbohydrates - 0.0025 × calcium + 0.0091 × magnesium - 0.16 × vitamin E + 0.0038 × vitamin C + 42.86 E-09 (Formula 11) Weight when getting up = -0.018×protein+0.00025×sodium-0.16×iron-0.00084×vitamin A-0.066×vitamin E+0.0027×vitamin C+50.95 N-02 (Formula 12) Weight when getting up = -0.032×protein+0.00047×sodium+0.029×iron+0.0017×vitamin A-0.059×saturated fatty acids+62.24

[0149] Weight-related nutrients in the test food For the seven subjects assigned to the experimental group, the percentages were used to show the extent to which the energy and nutrients in the subjects' diet during the intervention period were adjusted compared to those during the observation period ( Fig.38 ). The energy intake of the subjects was 96.7% higher than that during the observation period. Even without changing the energy intake, the weight factor could be adjusted. In addition, for the two subjects assigned to the control group, only the energy intake was compared during the observation period and the intervention period. Figures 39 to 43 ). Dietary nutrient optimization was not performed, but energy intake did not change compared with the observation period. In addition, the left side of the bar graph indicates the intake during the observation period, and the right side indicates the intake during the intervention period. In each series, a circle mark indicates a weight improvement factor, and an × mark indicates a weight deterioration factor.

[0150] Weight measurement results The weight of each subject when getting up, measured by a body weight and body composition scale, was compared between the observation period and the intervention period. The results are shown below. Figures 45-50 .

[0151] Body composition test results The body fat percentage, skeletal muscle percentage, and basal metabolic rate measured by weight and body composition scale are shown below. Figures 51-56 . The analysis results of different nutrients involved in weight can be obtained for each subject. Since individual nutrient optimization is performed, it can be confirmed that even if people make the same adjustments for weight gain, each subject will show different behaviors, such as an increase in body fat percentage or an increase in skeletal muscle percentage, or no change in both.

[0152] Evaluation of the degree of nutrient intervention The intervention levels of the weight-related factors of the four subjects during the intervention period are shown in Figures 57-60 As shown in Section 6 of Chapter 3, if it is a single weight factor, we can observe that although it is an improvement factor, the intervention degree of the weight factor is negative, and although it is a deterioration factor, the intervention degree of the weight factor is positive ( Fig.57 a~ Fig.60 a). On the other hand, from the perspective of the overall participation factor, regarding subject number E-02, it indicates that the intervention level of the improvement factor > the intervention level of the weight improvement factor > 0 is implemented in the same manner as the conditional research trial implemented in 2021 ( Fig.57b) Regarding the subject numbers E-08, E-09, and N-02, the intervention level of the improvement factor>0 and the intervention level of the deterioration factor<0 were implemented, indicating that both interventions are expected to improve the weight of the subjects.

[0153] Summarize In the first embodiment, a conditional research experiment of an optimization method of nutrients for effective weight improvement and a clinical trial of confirming the weight improvement effect using personal optimization of nutrients were conducted.

[0154] The relationship between an individual's weight and the amount of nutrients they take in was analyzed, and the results showed that the nutrients included in the weight prediction model formula vary from person to person, and the weight participating factors of each person are different. In the intervention conditional research trial of nutrient-optimized diet, which was implemented three times for a total of 28 days, intentional weight improvement was confirmed in any intervention (-2.67kg, -1.85kg, -3.01kg compared to before the intervention, all p<0.001). In the continuous analysis of each week, a different model formula can be obtained each time the analysis is performed. Magnesium, which is specifically a weight improvement factor, is excluded from the participating factors in the next analysis, and carbohydrates, which are weight improvement factors, are specifically used as weight improvement factors in the next analysis. Therefore, even for the same person, due to changes in the internal or external environment, the nutrients that are weight participating factors will change. In the intervention using this continuous analysis, -3.01kg (4.2% weight loss) compared to before the intervention, the largest weight improvement effect in the conditional research trial conducted so far can be obtained. Therefore, it is believed that continuous analysis helps to continuously obtain weight improvement effects.

[0155] In the results of the clinical trial, among the seven subjects assigned to the experimental group, three subjects who had leftovers in eight or more of the twenty-eight intervention meals (30%) were excluded from the analysis because they did not meet the standard nutrient intake. Among the four subjects who became the subjects of the effectiveness analysis, four (100%) were observed to have a significant weight improvement in the comparison before and after the intervention (p<0.01). Since no significant weight change was found in the control group, it is presumed that the weight change obtained through this trial was due to the optimization of nutrients.

[0156] These results indicate that body weight can be predicted by the amount of nutrients consumed, and that body weight can be brought toward a healthy level by adjusting the amount of nutrients identified as improvement and deterioration factors using multiple regression analysis that derives the relationship between body weight and nutrients, that is, by continuously consuming a diet that optimizes nutrients for an individual. In this study, which aims to improve body weight, it was stipulated that the condition for optimizing nutrients was that energy intake should not be changed. The results of this experiment confirmed the effect of improving body weight without changing energy, that is, without relying on calorie control, which can be said to have overturned the previous conclusions about weight loss.

[0157] In the analysis of the weight participation factors that affect personal weight, the analysis method used in this embodiment is characterized in that anything that can be quantified can be included, not limited to the amount of nutrients. In fact, in the conditional research test, the amount of exercise is included in the analysis as a factor other than nutrients in the form of steps, and the result is that it is specified as a weight improvement factor in the first phase of the intervention of the conditional research test implemented in 2020. In the first phase of the intervention, in addition to taking a diet that optimizes nutrients, the test subjects are allowed to increase walking within a reasonable range. The expected value of the amount of weight improvement expected by walking refers to the energy consumption during walking proposed by the American Sports Medicine Association, and it is believed that the result calculated based on the energy (kcal) required to burn 1kg of fat and the energy (kcal) consumed by walking is 0.4kg. This is equivalent to about 15% of the actual observed weight improvement of 2.7kg. Therefore, it is speculated that increasing the amount of exercise has the effect of assisting the weight improvement effect of nutrient optimization, but it is speculated that its effect is less than the amount of nutrients. In addition, the amount of exercise (number of steps) is specified as a weight participation factor only for this time, and it is not specified as a weight participation factor in the second phase of the intervention or the trial implemented in 2021.

[0158] In the experiment conducted in the first embodiment, "the amount of various nutrients contained in the diet" is an important value required on the basis of specifying the nutrients involved in body weight. When estimating this value, the smartphone application "ASKEN" is used in the conditional research experiment, and the WEB software "Mr. DATEMAN web" is used in the clinical trial. Both are systems that answer the amount of nutrients by entering the recipe name or ingredient name and referring to the Japanese Food Standard Composition Table. In addition to the ingredient table, "ASKEN" also includes commercially available foods, and the prediction accuracy is also reported in the literature. The Japanese Food Standard Composition Table is represented by the three major nutrients, and is analyzed using an analytical method that specifies the amount of various minerals and vitamins, and the estimated values ​​are calculated and included, but these data are not absolute values. This is because there are many differences in food ingredients in terms of season, origin, variety, etc., so the amount of nutrients is not uniquely determined. However, in this study, the participating factors can be judged based on the estimated value of the amount of nutrients contained in the food.

[0159] Regarding the conditional research experiment implemented in 2021, after the intervention period began, each time the model formula was updated by re-analysis, a linear approximation was derived with y as body weight (kg) and x as the number of days (days) after the model formula was used, relative to the weight change in one week, and its slope was calculated. The slopes of the four periods were -0.27, -0.15, -0.03, and -0.20, respectively, confirming continuous improvement in weight. According to the slope, a 1kg weight improvement can be foreseen in about one week. In the experiment conducted in this study, the analysis was performed once a week, but if the time spent on optimizing the nutrients of the diet based on the weight prediction model formula updated by the analysis can be shortened, theoretically the analysis can be performed once a day and the model formula can be updated. It is believed that this continuous analysis can quickly reflect the physical condition of the subject that changes constantly due to external factors such as the environment in which he is located, and can be a useful method for more accurately identifying nutrients that affect personal health indicators. In the continuous analysis, the same nutrients are not necessarily selected in the model formula, so it is believed that the update of the model formula is expected to make the changes in the diet pattern more diverse and ensure the quality of life (QOL). It is speculated that the model formula is updated by continuous analysis to correspond to the changes in body composition over time, and it is also useful from the perspective of ensuring the QOL (quality of life) of the subject. According to the above results, the experiment implemented in the first embodiment shows that, after blood pressure, body weight can also be predicted and controlled by nutrients ingested through diet.

[0160] Regarding the degree of adjustment of nutrients as factors involved in weight, an index, namely the degree of intervention, is newly defined, calculated and evaluated in the first embodiment. The ideal adjustment is to increase the nutrients as factors for improving weight and reduce the nutrients as factors for improving weight, but it is conceivable that there will be cases where the above ideal adjustment cannot be made due to the strong desire of the subject or in order to ensure QOL. Specifically, for subjects who want to "increase protein" while protein is a factor for improving weight, it is necessary to make adjustments so that other factors for improving weight can be reduced by increasing the amount of protein, thereby achieving the goal by reducing the sum of the intervention degrees of the factors for improving weight. In this case, although "protein as an individual factor for improving weight increases", "the sum of the intervention degrees of the factors for improving weight decreases". Sometimes there is also the opposite situation, that is, although "individual factors for improving weight decrease", "the sum of the intervention degrees of the factors for improving weight increases". Moreover, even if individual factors for improving weight decrease and "the sum of the intervention degrees of the factors for improving weight decreases", and individual factors for improving weight increase, if the adjustment is made so that "the reduction in the sum of the factors for improving weight exceeds the effect of the reduction in the sum of the factors for improving weight", the goal can be achieved. On the contrary, even if the individual ameliorative factors increase and the "sum of intervention levels of ameliorative factors increases" and the individual improving factors decrease, if the "sum of intervention levels of improving factors exceeds the sum of intervention levels of ameliorative factors (intervention levels of improving factors > intervention levels of improving factors > 0)", the goal can be expected to be achieved. Therefore, it is estimated that there is a high degree of freedom in optimizing nutrients to achieve personal goals.

[0161] As shown above, in the first embodiment, the improvement effect of personal optimization of nutrient intake on body weight was confirmed through clinical trials with humans as subjects. In addition to body weight, in addition to physical data such as skeletal muscle rate or brain function, numerical data such as sports competition time are also used as improvement indicators to optimize nutrient intake. Experiments to measure the effect are in progress, and each has achieved certain results. These results show that as long as it is related to biological indicators and can be quantified, improvement effects can be obtained through personal optimization of nutrients, and the health desired by individuals can be obtained, and self-realization can be achieved.

[0162] <Second Embodiment> In the second embodiment, brain function (memory) is taken as the improvement target. By analyzing the correlation between the daily nutrient intake and the memory test, a personalized optimal diet with optimized nutrient intake is designed and taken to verify the memory improvement effect.

[0163] Experimental Materials and Methods Experimental Materials Subjects A healthy adult male During the test period, you will have three meals a day, and you are prohibited from taking health foods or supplements, alcohol, and meals other than the three meals (snacks or snacks). Drinks are limited to water. In addition, you should avoid irregular lifestyles and maintain a certain exercise habit.

[0164] Statistical software, applications IBM SPSS Statistics ver.25 (IBM, the United States of America) APPRON (Health and Nutrition Support Center, Osaka) ※Based on the Japanese Food Composition Table 2020 Edition (8th revision)

[0165] Experimental methods Test schedule ( Fig.62 ) The test period was divided into two periods, namely the observation period (28 days) and the verification period (28 days). During the observation period, the memory test scores and the number of memory tests were recorded, and the nutrient intake was recorded using nutrient quantity calculation software. During the verification period, multiple regression analysis was performed on the data obtained during the observation period, and a personalized optimal diet with nutrient adjustment based on the analysis results was taken for three meals (morning, noon, and dinner). The memory test scores, number of times, and nutrient intake were recorded in the same way as during the observation period.

[0166] Memory test In the second embodiment, as an indicator of memory, a test using digital measurement of short-term memory is used. The memory test is performed 6 to 10 times a day, and the number of tests is randomly assigned. Six of them are performed at specified times (twice each at 10 o'clock, 13 o'clock, and 22 o'clock), and the remaining 0 to 4 times are performed at any time. In order to make a before-and-after comparison under the condition that there is no difference in the test time or the number of tests, the average score of the six tests performed at the specified time is taken as the score of the day. In order to exclude the increase in scores due to habit, the same memory test is performed every day before the start of this test, and the test is started only after confirming that the score is no longer rising.

[0167] Memory test sequence 1. Remember the numbers displayed in random order in a 5×7 grid. After 2.3 seconds, the numbers are no longer displayed. 3. Select from 1 to repeat the displayed number. 4. The number displayed increases every time you answer correctly, so the maximum number displayed until you answer incorrectly is your score.

[0168] Derivation of model formula When designing a memory-improving diet, it is necessary to analyze the relationship between memory and nutrients, and identify the nutrients that serve as improvement factors and deterioration factors in memory. In order to clarify the specific nutrients involved in memory and the influence of nutrients on the formula, multiple regression analysis was performed using SPSS to derive the model formula. The target variable was set as the memory test score, and the explanatory variables were set as the number of memory tests and the total intake of 20 nutrients the day before (protein, lipid, total dietary fiber, carbohydrates, sodium, potassium, calcium, magnesium, iron, zinc, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B2, vitamin B6, vitamin C, salt equivalent, saturated fatty acids, sugars) and energy. The analysis method used the variable reduction method. In order to reflect the latest data in the model formula, the data of the 24 days closest to the analysis time point was used, and a total of seven analyses were performed every four days. Moreover, when there is a high correlation between the explanatory variables, the reliability of the regression formula decreases, and the prediction error may become larger. Therefore, the model formula using the variance expansion factor (VIF) with explanatory variables of less than 10 is adopted. In the case where the VIF is above 10, measures are taken such as staggering the data to be analyzed by one day, increasing the number of data, etc. In the model formula, the selected nutrients are variables selected through multiple regression analysis to predict memory, and nutrients with positive multiple regression coefficients are considered to be memory improvement factors, while negative nutrients are considered to be memory deterioration factors, etc.

[0169] Design of a personalized optimal diet The target prediction point of the memory test is set, and the memory improvement factor and memory deterioration factor determined in the derived model formula are adjusted to design a personalized optimal diet that can achieve the prediction point. The total amount of nutrients consumed in a day is substituted into the model formula, and the calculated prediction point is used as the set target point. The diet is designed and optimized by changing the ingredients to be used, adjusting the amount of ingredients used, etc. In order to maintain QOL, three meals a day (breakfast, lunch, and dinner) are set, and the average energy intake during the observation period is designed to be within ±200kcal (±11.6%) to avoid large deviations from the diet consumed during the observation period.

[0170] Evaluation of nutrient adjustment The intake of nutrients is standardized, and the degree of adjustment of each nutrient is calculated and evaluated. Standardization scales the mean value of the data to 0 and the variance to 1. By performing standardization, nutrients with different units can be compared. The mean value and standard deviation of the nutrient data used in the analysis are used for standardization. The value obtained by subtracting the standardized nutrient amount during the observation period from the mean value of the standardized nutrient amount during the verification period is multiplied by the absolute value of the standardized coefficient derived from the multiple regression analysis, and the resulting value is used as the adjustment degree. The adjustment degree is calculated based on the overall adjustment degree of memory participation factors and the individual adjustment degree of memory participation factors. When the value of the adjustment degree is positive, more adjustment is made than during the observation period, and when it is negative, less adjustment is made than during the observation period.

[0171] Significant difference test The mean and standard deviation of the memory test results were calculated for each observation period and verification period. Since the results corresponding to a certain improved diet were the results of the second day, the memory test data of the first day of the verification period were excluded. The comparison of memory test results during the observation period and the intervention period was statistically processed using an uncorrelated t-test. The significance level in the test was set to 5% or less in a two-sided test (*p<0.05, **p<0.01, ***p<0.001).

[0172] Experimental Results Specific factors involved in memory The data of the amount of nutrients consumed the previous day and the number of memory tests the previous day obtained during the observation period were used as explanatory variables, and the memory test scores were used as target variables for multiple regression analysis. The model formula for predicting the memory test scores based on the obtained multiple regression coefficients was derived, and the improvement factors and deterioration factors were identified based on the signs of the coefficients ( Fig.63 ). The average correlation coefficient of the seven analyses was 0.776, showing a high correlation. Moreover, the results showed that the types of improvement factors and deterioration factors in each analysis were different. The conditions of each analysis are shown in Fig.64 .

[0173] Memory test score prediction model formula Analysis No.1 Correlation coefficient: 0.864 Memory test score = 0.0667 [number of tests 次 ]+0.00049[Potassium mg ]+0.195[Iron mg ]-0.0289[Vitamin D μg ]-0.773[Vitamin B2 mg ]-0.678[Vitamin B6 mg ]-0.119[Salt equivalent g ]+9.381

[0174] Analysis No.2 Correlation coefficient: 0.890 Memory test score = 0.00207 [lipid g ]+0.00069[Potassium mg ]+0.241[Iron mg ]-0.173[Zinc mg ]-0.0301[Vitamin D μg ]-0.554[Vitamin B6 mg ]-0.141[Salt equivalent g ]+9.731

[0175] Analysis No.3 Correlation coefficient: 0.897 Memory test score = 0.00627 [lipid g ]+0.0120[Mg mg ]+0.101[Iron mg ]+0.000087[Vitamin A μg ]-1.0247[Vitamin B2 mg ]-0.880[Vitamin B6 mg ]-0.176[Salt equivalent g ]+9.480

[0176] Analysis No.4 Correlation coefficient: 0.740 Memory test score = 0.00707 [lipid g ]+0.0232[Total dietary fiber g ]-0.000331[Sodium mg ]-0.00508[Mg mg ]+0.680[Iron mg ]-0.361[Vitamin B2 mg ]-0.00310[Sugar g ]+9.506

[0177] Analysis No.5 Correlation coefficient: 0.627 Memory test score = 0.0831 [number of tests 次 ]-0.00821[Protein g ]+0.0368[Iron mg ]+0.0407[Zinc mg ]+0.0347[Vitamin E mg ]-0.200[Vitamin B2 mg ]-0.0809[Salt equivalent g ]+8.982

[0178] Analysis No.6 Correlation coefficient: 0.728 Memory test score = 0.0944 [number of tests 次 ]-0.00498[Mg mg ]+0.0571[Iron mg ]+0.0822[Zinc mg ]+0.0526[Vitamin E mg ]-0.408[Vitamin B2 mg ]-0.0923[Salt equivalent g ]+9.006

[0179] Analysis No.7 Correlation coefficient: 0.683 Memory test score = 0.0239 [lipid g ]+0.000877[Calcium mg ]-0.00237[Mg mg ]+0.0133[Iron mg ]-0.0206[Vitamin D μg ]-0.527[Vitamin B1 mg ]-0.0481[Saturated fatty acids g ]+9.049

[0180] Design of a personalized optimal diet The target prediction point is set based on the memory test score during the observation period, and a personalized optimal diet (three meals a day) is designed to achieve the target prediction point. The prediction point is set to 10.3 points, and the menu is created by adjusting the ingredients. The menu example is shown in Fig.65 .

[0181] Nutrient adjustment The overall adjustment degree and individual adjustment degree of the memory improvement factor and memory deterioration factor identified in each analysis are shown below: Figures 66-72 ). The adjustment degrees of the improvement factors are all positive values, but the adjustment degrees of the deterioration factors are not the same. They are positive values ​​in analysis No. 1, 3, 6, and 7, and negative values ​​in analysis No. 2, 4, and 5. As a nutrient adjustment, it is ideal to increase each improvement factor and decrease each deterioration factor, but in order to maintain QOL, ideal adjustment is sometimes not possible. For example, if you do not want to reduce or want to increase the intake of protein as a deterioration factor, you need to make adjustments such as reducing other deterioration factors and increasing improvement factors. Moreover, even if individual improvement factors are reduced, adjustments can be made by increasing other improvement factors and reducing deterioration factors. In this way, by making adjustments such as "the effect of the sum of improvement factors exceeds the effect of the sum of deterioration factors", a personalized optimal diet that achieves the target value can be designed.

[0182] Changes in nutrient intake In order to compare the nutrient intake during the observation period and the verification period, a graph is shown for comparison, with the intake during the observation period set as 100% ( Figures 73-79 ). In the two bar graphs with the same label, the left side indicates the observation period, and the right side indicates the verification period. The ○ mark indicates the memory improvement factor, and the × mark indicates the memory deterioration factor. Regarding energy, a design roughly equal to the average energy intake during the observation period is used as a condition. The energy during the verification period is 104-109%, and the design within the condition can be achieved. The number of memory tests is adjusted to increase when it is an improvement factor, otherwise it is adjusted to be roughly equal to the average number of times during the observation period.

[0183] Results of the memory test The changes in the scores of the memory test during the observation period and the verification period are shown ( Fig.80 ). During the observation period, no increase in memory test scores was confirmed, but during the verification period, an upward trend in scores was confirmed. The average score during the observation period was 8.80 points, and the average score during the verification period was 9.31 points. The average score increased significantly (p<0.001) ( Fig.81 ). In addition, the score distribution of each period was compared. During the observation period and the confirmation period, the score of 7 points was 12 times (7.1%) and 0 times (0%), the score of 8 points was 41 times (24.4%) and 31 times (18.5%), the score of 9 points was 86 times (51.2%) and 72 times (42.9%), the score of 10 points was 27 times (16.1%) and 48 times (28.6%), the score of 11 points was 2 times (1.2%) and 16 times (9.5%), the score of 12 points was 0 times (0%) and 1 time (0.6%), and the confirmation test score was improved ( Fig.82 ).

[0184] Summarize In the second embodiment, by analyzing the data of daily nutrient intake, memory test scores, and memory test frequency of a healthy adult male, factors that improve memory and factors that worsen memory are identified, and memory improvement is tested by designing and consuming a diet that adjusts these factors.

[0185] In a second embodiment, a model formula for predicting memory test scores based on the amount of nutrients ingested and the number of memory tests is derived by performing multiple regression analysis on the vital signs data during the test. The analysis was performed seven times in total, and the average multiple correlation coefficient of the model formula was 0.776±0.100. A high correlation can also be seen in each analysis, so it is suggested that the memory test score can be predicted by the model formula. Moreover, for each analysis, the types of memory improvement factors and improvement factors contained in the model formula and the degree of influence of each nutrient on the target variable are different, and for some nutrients, the sign of the coefficient is reversed. The data used is different in each analysis, and the latest data at each analysis point is used. Therefore, it is inferred that the physical state at the time of analysis is reflected, and it is believed that a diet with high accuracy based on the updated data can be designed.

[0186] The nutrients included in each model formula are different, but there are nutrients with high frequency of use, and it is believed that these have a greater impact. It is known that iron, which is an improvement factor, has the ability to transport oxygen, which is vital to brain function, but the absorption rate is low, about 15%. It is believed that increasing the intake as an improvement factor is shown to compensate for this low absorption rate. Lipids, which are also improvement factors, are important nutrients that make up 60% of the brain. The main energy source of the brain is glucose, but when glucose is insufficient, the liver produces ketone bodies from lipids and constantly adjusts so that energy is not short. Moreover, this is a component of cells and participates in information transmission. It is believed that this function participates in brain function. The salt equivalent as an improvement factor represents the amount of sodium. Sodium moves inside and outside the cell through active transport, forming a concentration gradient. Various substances such as sugars or amino acids are transported depending on this concentration gradient. Active transport of sodium is also involved in maintaining the ion environment inside the cell, and this function may also participate in brain function. Among the nutrients included in the model formula, nutrients that reversed between improvement and deterioration during the test period were also found. These are minerals, which are important nutrients involved in various metabolisms of the human body. In existing studies on personalized optimal diets, minerals or vitamins are mostly shown as participating factors, which may be closely related to physical activity functions, and because the required amount often changes depending on the physical condition, it is believed that there may be improvements or reversals of improvement.

[0187] Sometimes the model formula includes the number of memory tests (analysis No. 1, No. 5, No. 6), which can adjust not only the amount of nutrients but also the number of memory tests. Therefore, it is believed that the influence of non-nutritional factors can also be considered and combined with nutrient adjustment to design an optimized menu.

[0188] In order to show the degree of adjustment of the nutrient amount and the number of trials of the personalized optimal diet designed each time for analysis, the nutrient adjustment degree is calculated and compared. In the second embodiment, the memory improvement factor is adjusted to increase in all nutrients compared to the observation period, similarly to the existing research. The improvement factor is basically adjusted to decrease, but some nutrients are also adjusted to increase or remain roughly unchanged. It is believed that by adjusting "the effect of the sum of the improvement factors exceeds the effect of the sum of the improvement factors", a personalized optimal diet can be designed, and personal lifestyle or dietary preferences can be taken into consideration.

[0189] In the second embodiment, amino acids were analyzed as nutrients other than the 20 nutrients. As a result, amino acids had a high correlation with each other, and thus the VIF was 10 or more, which greatly reduced the reliability of the model formula, so they were excluded from the variables. However, if there is no problem with the amino acids included in the model formula, nutrients can be adjusted by using supplements, etc., and an appropriate personalized optimal diet can be designed.

[0190] A preliminary test was conducted to conduct the conditional study of the second embodiment. In the preliminary test, nutrients were analyzed for intake, nutrients that serve as factors for memory improvement and deterioration were adjusted, and a personalized optimal diet was designed and ingested. In the preliminary test, a post-observation period in which the personalized optimal diet was not ingested was set after the confirmation period, and the memory test results are shown in the "Supplement Data Preliminary Test Results". Compared to the observation period in which no upward trend in the memory test score was observed, an upward trend in the score was observed during the confirmation period, and the average score increased intentionally (p<0.001). However, no upward trend in the score was observed during the post-observation period, and no intentional increase in the average score was confirmed compared to the confirmation period ( Figure 83 to Figure 88 ). Therefore, it is believed that the increase in scores confirmed during the validation period was caused by nutrient adjustment and not the placebo effect.

[0191] The analysis method used in the second embodiment is not limited to nutrients. As long as it can be quantified, it can be included in the model formula. Therefore, it can also promote the improvement effect from the perspective of other than nutrients, and can be applied to the improvement of various health indicators. Moreover, since it is analyzed based on personal data, it is different from the previous guidance for the general public and can provide personalized guidance to maintain the individual's physique or QOL. Therefore, this personalized optimal diet may become a new type of personalized medical care.

[0192] <Third Embodiment> In the third embodiment, the cardiopulmonary function improvement effect of optimizing the amount of nutrient intake is verified with the goal of improving personal endurance. The index of cardiopulmonary function uses the heart rate at rest. The heart rate at rest changes due to diet therapy or exercise habits, and endurance is improved by reducing the heart rate at rest. In addition, in order to improve the improvement effect, the introduction of exercise volume as a factor other than the amount of nutrient intake is also studied.

[0193] Test materials and methods Test materials Subjects 1) A healthy adult male During the trial period, the diet is limited to three meals a day. It is forbidden to take health foods or supplements, alcohol, and food other than three meals (snacks or snacks). Drinks are limited to water. In addition, avoid irregular lifestyles and do not engage in intense exercise other than designated exercise.

[0194] 2. Experimental Equipment 1) Weight and body composition scale (HBF-255T, Omron Healthcare Co., Ltd., Kyoto) 2) Wearable devices (Fitbit Charge 3, Fitbit (Google), USA) 3) Smartphone (iPhone(registered trademark) XR, Apple, USA) 4) Pulse oximeter (Yuyue Pulse Oximeter YX301, Glox Co., Ltd., Tokyo) 5) New physical fitness test 20m round trip running sound source (Ministry of Education, Culture, Sports, Science and Technology)

[0195] 3. Software and Applications 1)OMRON connect (OMRON Healthcare Co., Ltd., Kyoto) 2) ASKEN (ASKEN INC., Tokyo) 3) Fitbit (Fitbit (Google), California, USA) 4)SPSS Statistics ver.25 (IBM, New York, USA)

[0196] Test methods Test schedule The trial period is divided into two periods, based on the observation period (28 days), the confirmation period (28 days) and the schedule ( Fig.89) is implemented. The verification period is divided into the first to fourth periods, and a multiple regression analysis is performed once a week to create a resting heart rate prediction model formula. During the observation period, the amount of nutrients consumed and the amount of exercise for three meals a day (described on the next page) are recorded as data for analysis. During the verification period, a multiple regression analysis is performed on the data obtained during the observation period, and the nutrients and exercise amount are adjusted based on the analysis results. The three meals (morning, noon, and dinner) are taken with a personalized optimal diet, and exercise is performed and recorded. In addition, a 20m round-trip run is performed every seven days to evaluate endurance, and a before-and-after comparison is made during the observation period and the verification period to confirm the endurance improvement of each analysis.

[0197] Measurement method of each data Resting heart rate When measuring the resting heart rate as the target variable, the measurement is performed using a wearable device.

[0198] Nutrient intake During the observation period, a smartphone application for diet management was used to take photos of the three meals a day to estimate and record nutrients. The recording object was set according to the diet consumed, including protein, lipids, sugars, total dietary fiber, carbohydrates, sodium, potassium, calcium, magnesium, iron, zinc, vitamin A, vitamin D, vitamin E, vitamin B1, vitamin B2, vitamin B6, vitamin C, salt equivalent, saturated fatty acids, a total of 20 nutrients intake and energy intake, and the total amount per day was recorded. A model formula for predicting the heart rate at rest is created based on the daily nutrient amount. In addition, the Japanese Food Standard Composition Table (2020 Edition, Eighth Revision) revised in December 2020 is used.

[0199] Amount of exercise In this experiment, in addition to the amount of nutrients consumed, the change in the amount of exercise was used as an explanatory variable, and the time of aerobic exercise (jogging) that affects the heart rate at rest was used as the amount of exercise. During the observation period, the time was randomly selected from 0 minutes, 15 minutes, 30 minutes, and 45 minutes, and it was performed once a day at a fixed speed of 12 km / h (0 minutes: 7 times, 15 minutes: 6 times, 30 minutes: 7 times, 45 minutes: 8 times). In addition, in order to eliminate the reduction in the heart rate at rest caused by the influence of jogging, jogging was performed in the same way as during the observation period from one month before the start of this experiment.

[0200] Derivation of model formula SPSS Statistics ver.25 (IBM, New York, USA) was used to perform multiple regression analysis when deriving the model formula for designing the optimal personalized diet. The target variable was set as the daily resting heart rate, and the explanatory variables were set as the amount of exercise and the amount of nutrients consumed the previous day. The analysis method of variable reduction was used. Based on the analysis results, a model formula for predicting the resting heart rate based on seven factors was constructed. Nutrients with positive coefficients were set as resting heart rate reduction factors (improvement factors), and negative nutrients were set as resting heart rate increase factors (deterioration factors).

[0201] Design of a personalized optimal diet The target prediction point of the heart rate at rest is set, and the improvement factor specified in the derived model formula is increased, and the deterioration factor is reduced to make adjustments, and a personalized optimal diet that can achieve the prediction point is designed for three meals a day. In order to maintain the QOL of the implementer, the balance of main dishes, side dishes, etc. is considered in the same way as the diet consumed during the observation period, and a personalized optimal diet is prepared. In addition, when jogging time is an improvement factor, 45 minutes of jogging is performed except on the days of round-trip running. When it is not adopted by the model formula, jogging is performed at a random time as in the observation period.

[0202] Endurance Assessment Items 20m shuttle run (New physical fitness test of the Ministry of Education, Culture, Sports, Science and Technology) At the education site, 20m shuttle runs were performed as a method of measuring endurance to evaluate endurance. In order to reduce the impact of the 20m shuttle runs on endurance improvement, the runs were performed every seven days, and four measurements were taken during the observation period and the verification period. In addition, in order to exclude the factor of technical improvement due to repetition, the tests were conducted one month before the test, and the records were observed to have not improved.

[0203] Blood oxygen saturation The blood oxygen saturation was measured at the end of the daily jogging. The blood oxygen saturation is a value that measures the binding ratio of hemoglobin and oxygen contained in red blood cells flowing in the blood (arterial blood) supplied from the heart to the whole body through the skin (transcutaneous), and is also used to evaluate cardiopulmonary function. Therefore, the improvement of endurance was confirmed by comparing before and after the observation period and the verification period.

[0204] Statistical processing Significant difference test The mean and standard deviation of the measurement results were calculated for each observation period and verification period. Since the physical changes corresponding to the improvement of diet were reflected on the second day, the test data of the first day of the verification period were excluded. When comparing the observation period and the verification period, the statistical processing was performed using the non-corresponding t-test. The significance level in the test was set to 5% or less in the two-sided test (*p<0.05, **p<0.01, ***p<0.001).

[0205] Evaluation of nutrient adjustment The intake of nutrients is standardized, and the degree of adjustment of each nutrient is calculated and evaluated. Standardization scales the mean value of the data to 0 and the variance to 1. By performing standardization, nutrients with different units can be compared. The mean value and standard deviation of the nutrient data used in the analysis are used for standardization. The value obtained by subtracting the standardized nutrient amount during the observation period from the mean value of the standardized nutrient amount during the verification period is multiplied by the absolute value of the standardized coefficient derived from the multivariate regression analysis, and the resulting value is used as the adjustment degree. The adjustment degree is calculated based on the individual adjustment degree of the factors participating in the resting heart rate. When the value of the adjustment degree is positive, it is adjusted more than during the observation period, and when it is negative, it is adjusted less than during the observation period.

[0206] Test results Specific factors involved in cardiopulmonary function The resting heart rate obtained during the observation period was used as the target variable, and the amount of nutrients consumed and the amount of exercise (jogging time) were used as explanatory variables. SPSS Statistics ver.25 was used to perform a multiple regression analysis. The model formula for predicting the resting heart rate was constructed based on the obtained multiple regression coefficients, and the resting heart rate participation factors ( Fig.90 ). The average value of the multiple correlation coefficient of the four analyses was 0.835, and a high correlation was observed between nutrient intake and resting heart rate measurements, suggesting that resting heart rate can be predicted based on nutrient intake and exercise volume (jogging time).

[0207] Analysis 1 Analysis data: 2021.10.05~2021.10.29 (25 days) R=0.86 Resting heart rate (bpm) = -0.033 [jogging time minutes] -0.042 [protein g] + 0.043 [lipid g] -0.01 [sugar g] + 0.255 [zinc mg] -0.001 [vitamin A μg] + 1.23 [vitamin B6 mg]

[0208] Analysis 2 Analysis data: 2021.10.12~2021.11.05 (25 days) R=0.84 Resting heart rate (bpm) = -0.024 [jogging time minutes] -0.01 [magnesium mg] + 0.213 [iron mg] + 0.842 [vitamin B2 mg] -0.526 [vitamin B6 mg] + 0.023 [dietary fiber g] -0.000259 [sodium mg]

[0209] Analysis 3 Analysis data: 2021.10.19~2021.11.12 (25 days) R=0.83 Resting heart rate (bpm) = -0.005 [Mg mg] -0.236 [Zinc mg] + 0.117 [Vitamin E mg] + 0.255 [Vitamin B1 mg] + 2.31 [Vitamin B2 mg] -0.005 [Vitamin C mg] + 0.057 [Total dietary fiber g]

[0210] Analysis 4 Analysis data: 2021.10.26~2021.11.19 (25 days) R=0.81 Resting heart rate (bpm) = -0.022 [lipid g] -0.001 [potassium mg] + 0.001 [calcium mg] -0.262 [zinc mg] + 1.30 [vitamin B2 mg] + 0.087 [total dietary fiber g] + 0.067 [saturated fatty acid g]

[0211] Design of a personalized optimal diet The target prediction value is set based on the resting heart rate during the observation period, and the optimal personal diet (three meals a day) that can achieve the target prediction value is designed. The predicted resting heart rate is set to 50 (bpm), and the menu is created by adjusting the ingredients. An example of the optimal personalized diet is an example of analysis 2, shown in ( Fig.91 ). In addition, the jogging time was specified as an improvement factor in Analysis 1 and Analysis 2, so it was adjusted from an average of 23.6 minutes during the observation period to an average of 30.0 minutes during the verification period (0 minutes: 6 times, 15 minutes: 4 times, 30 minutes: 2 times, 45 minutes: 16 times).

[0212] Nutrient adjustment The overall adjustment and individual adjustment of the improvement factors and amelioration factors ingested during the verification period are shown below (Figs. 92 to 95). The overall adjustment of the improvement factors is all positive, but the overall adjustment of the amelioration factors is negative in Analysis 1 and Analysis 4, and positive in Analysis 2 and Analysis 3. In the design of the personalized optimal diet, it is ideal to make adjustments to make the improvement factors positive and the amelioration factors negative, so the results are as in Analysis 1 and Analysis 4. However, it is important to reflect dietary preferences to maintain personal QOL, and not to significantly change the usual diet, and sometimes not to reduce the ingredients containing amelioration factors. In this case, adjustments are made to increase or change the ingredients containing more improvement factors, and the design is performed so that the target value can be achieved. In addition, there are ingredients that contain more amelioration factors but have a greater total of improvement factors. In this experiment, brown rice is equivalent to this ingredient, and brown rice is used in Analysis 2 and Analysis 3, so the amelioration factor becomes a positive value.

[0213] Resting heart rate and nutrients The following Figures 96 to 99 The figure shows a comparison of the energy and nutrient intake of the subjects through the test food during the verification period, with the intake during the observation period set as 100%. In the two bar graphs with the same label, the left side represents the intake during the observation period, and the right side represents the intake during the verification period. ○ represents the improvement factor of the heart rate at rest, and × represents the deterioration factor of the heart rate at rest. The energy changes within ±10% compared with the average value during the observation period. In analysis 3, the result is that the jogging time during the verification period is 28% less than the jogging time during the observation period. As described in the next item, the heart rate at rest also decreased during the period of analysis 3, so it is suggested that the influence of the nutrient amount is greater.

[0214] Changes in heart rate at rest The changes of the resting heart rate during the observation period and the verification period are shown ( Fig.100 ). In addition, the average value during the observation period and the average value during the verification period are shown ( Fig.101 ). Compared with the mean value of 54.4±0.97 (bpm) during the observation period, it was significantly lower (p<0.001) during the confirmation period, which was 51.6±1.84 (bpm).

[0215] Results of motor function tests The ratio of blood oxygen saturation at the end of jogging for 45 minutes is shown ( Fig.102 Compared with the average value of 93.6±0.48% during the observation period, the average value during the confirmation period increased significantly (p<0.001) to 95.1±0.66% ( Fig.103 ). In addition, the results of the 20m round trip run are shown ( Fig.104 ). It increased from 75 times during the observation period to 95 times during the verification period. In addition, the results of the 20m shuttle run were 77.3 times on average during the observation period and 91.0 times on average during the verification period, which showed a significant increase (p<0.001) ( Fig.105 ).

[0216] Summarize In the third embodiment, the cardiopulmonary function improving effect of optimizing the amount of nutrient intake was examined with the goal of improving endurance.

[0217] The results of this experiment suggest that it is possible to reduce resting heart rate by optimizing the amount of nutrients and exercise for an individual, and that resting heart rate can be predicted. As for the results of the endurance evaluation items, the results of blood oxygen saturation at the end of 20m round-trip running and jogging also increased significantly (p<0.001). Therefore, it is suggested that endurance can be estimated from an individual's resting heart rate.

[0218] Furthermore, by incorporating the amount of exercise into the analysis, it is possible to design a diet that matches the amount of exercise that is appropriate for one’s life. Furthermore, it was shown that any quantifiable indicator such as the amount of exercise can be included in the analysis, so it is possible to consider the influence of external factors such as stress and sleep that could not be considered in this experiment.

[0219] In this experiment, in order to cope with the changes in the internal environment every day, a continuous analysis method of performing analysis once a week was adopted. In each analysis result, the factors of the model formula are all different, and it is speculated that the physical state at the time of analysis is reflected, and it is believed that a diet with high accuracy based on the updated data can be designed. In addition, the jogging time, which is closely related to the heart rate at rest, is not reflected in the model formula in Analysis 3 and Analysis 4. This means that the influence of jogging time is lower than the seven selected nutrients, suggesting that the influence of nutrient adjustment is greater than the increase in exercise volume according to the individual's physical condition. Moreover, in this experiment, the factor with the highest improvement is magnesium. It shows that the higher the serum magnesium value, the more the risk of cardiovascular disease is reduced, and the more magnesium intake from the diet (up to about 250 mg a day), the more the risk of ischemic heart disease caused by reduced myocardial blood supply is reduced. Therefore, it is believed that in this experiment, magnesium may also be involved in the strengthening of cardiopulmonary function. Moreover, minerals have a high frequency of becoming a factor of improvement. Minerals are very likely to be involved in physical activity functions, and the required amount often changes depending on the state or purpose of the body. Therefore, in this experiment, it is believed that the required amount of the subject's heart rate at rest may be exceeded.

[0220] During the verification period, the amount of exercise increased compared to the observation period. Therefore, in order to consider the possibility that the decrease in heart rate (change in endurance) is the result of the increase in exercise, a post-observation period was set after the verification period. The same amount of exercise was set during the post-observation period as during the verification period, and no personalized optimal diet was taken. Results The average resting heart rate during the verification period and the post-observation period was compared, and no significant changes were found ( Fig.106 ), thus suggesting that the effect of personalized optimal diet was stronger during the validation period.

[0221] This experiment showed that cardiopulmonary function can be improved by individually optimizing diet and exercise. In this method, it is expected that all quantifiable indicators, not only cardiopulmonary function, can be predicted and improved, so it has the potential to become a new medical care technology that can improve various health indicators.

[0222] <Second Embodiment> In the first embodiment described above, a prediction model is created by analyzing the correlation between the measured values ​​linked to the achievement of the goal and the data acquired by the user himself (nutrient intake, actions, life stage, etc.), and improvement factors and / or deterioration factors are identified, but in the second embodiment, the user uses the data and / or analysis results of other users to identify the improvement factors and / or deterioration factors of the user.

[0223] Hereinafter, a method of suggesting a recipe to a user using nutrients acquired for other users and measured values ​​linked to achievement of a goal and / or nutrient models analyzed for other users will be described.

[0224] Fig.107 1 is a diagram showing an example of a functional structure of the server device 1 according to the second embodiment. As shown in the figure, in the second embodiment, the server device 1 further includes a user information storage unit 137 storing information related to a user (hereinafter referred to as user information), a prediction model storage unit 138, and a similar user identification unit 120.

[0225] The prediction model storage unit 138 stores the prediction models (nutrition model, nutrition action model, nutrition life stage model, nutrition date and time model, nutrition complex model) created by the analysis unit 115. The prediction model storage unit 138 stores information containing prediction models (hereinafter referred to as prediction model information). The prediction model information may include: information that establishes a correspondence with information of a specific user (such as a user ID) and represents the user's goal to be achieved (hereinafter referred to as target data. The target data can be, for example, text data such as "weight loss" and "lowering blood pressure"); information representing measured values ​​associated with the goal to be achieved (hereinafter referred to as measurement value specific information. For example, it can be set to text data or labeled values ​​such as "weight" and "blood pressure"); and prediction models (nutrition model, nutrition action model, nutrition life stage model, nutrition date and time model, nutrition complex model, etc.).

[0226] Fig.108 1 is a diagram showing an example of the structure of user information stored in the user information storage unit 137. The user information includes information that establishes a correspondence with the information of a specific user (user ID), and includes various attributes related to the user. Attributes may include, for example, age, gender, genetic genes, blood test results, urine test results, biological indicators (weight, body fat percentage, skeletal muscle percentage, BMI, blood pressure, etc.), lifestyle (diet, exercise, sleep time, drinking, smoking, etc.), place of residence, place of birth, race, occupation, etc. Regarding diet, it may include the results of user questionnaires such as food preferences (likes, dislikes), nutrient composition, and calorie intake (you can choose pre-prepared options or set them as freely described text data).

[0227] In the second embodiment, data and / or analysis results of other users (hereinafter referred to as similar users) with similar attributes to the user are used. The similar user identification unit 120 identifies similar users with attributes similar to the user. The similarity of user attributes can be obtained by a known method. For example, the similarity can be obtained by standardizing and summing the degree of consistency of numerical values ​​or texts.

[0228] There are four modes of using similar user data and / or analysis results. Mode 1: Use the resolution result of another similar user. Mode 2: Use the analysis result of analyzing the data of another similar user. Mode 3: Use the analysis results of analyzing the data of multiple other similar users. Mode 4: Use the analysis results of multiple other similar users. Each mode is described below.

[0229] <Mode 1: Use the analysis result of another similar user> In mode 1, the parsing result of a similar user is directly used for the user.

[0230] The similar user identification unit 120 can identify a user with the most similar attributes from other users who have the same achievement goal as the user as a similar user. The similar user identification unit 120 receives an input of an achievement goal from the user, retrieves prediction model information that is consistent with the received achievement goal (or similar to a predetermined degree or more) from the prediction model storage unit 138, obtains user information corresponding to the user ID included in the retrieved prediction model information from the user information storage unit 137, determines the attributes included in the obtained user information and the similarity with the attributes included in the user information corresponding to the user, and can identify the user information with the highest similarity (excluding itself).

[0231] The analyzing unit 115 obtains the prediction model (and the improvement factor and deterioration factor as explanatory variables of the prediction model) created for the similar user from the prediction model storage unit 138, and sets the prediction model and the improvement factor and deterioration factor as the prediction model of the user.

[0232] The evaluation unit 116 evaluates the recipes based on the improvement factors and deterioration factors of similar users, and the recipe suggestion unit 117 can select a recipe according to the evaluation value, or adjust nutrients to improve the measured value.

[0233] In addition, in the case where the measured value uses a dimensionless index represented by the ratio of multiple measured values, the coefficient can be corrected each time the prediction model of similar users is used. For example, when the measured value is BMI, BMI is calculated based on weight and height, and the difference in weight can be used for correction. For example, when the data of a similar user with BMI=26 and weight=60kg is adapted to a user with BMI=26 and weight=80kg, it can be corrected according to (80÷60)×coefficient. In this way, the evaluation unit 116 can evaluate the recipe by multiplying the ratio of the attributes of the similar user to the attributes of the user by a coefficient with respect to the attributes related to the measured value (other measured values).

[0234] <Mode 2: Using the analysis results of another user's data> In mode 2, the data obtained for a similar user is parsed.

[0235] The similar user identifying unit 120 may identify one user having the most similar attributes from among other users who have registered measurement values ​​associated with the achieved goals of the user in the measurement value storage unit 131 as a similar user.

[0236] The analysis unit 115 reads the measurement values ​​and nutrient intake corresponding to the identified similar users from the measurement value storage unit 131 and the intake amount storage unit 132, and creates a prediction model (nutritional model) by multivariate analysis using the nutrient intake as an explanatory variable and the measurement value as a target variable. It is possible to identify nutrients that contribute to the improvement of the measurement value, i.e., improvement factors, and nutrients that contribute to the deterioration of the measurement value, i.e., deterioration factors.

[0237] The evaluation unit 116 and the recipe suggestion unit 117 can suggest recipes to the user, similarly to the first embodiment.

[0238] <Common to Modes 1 and 2> In the case of modes 1 and 2, when a recipe is recommended using the data or analysis results of a similar user, if no improvement in the measurement results related to the achievement of the user's goal is found, another similar user may be selected.

[0239] For example, the similar user identification unit 120 identifies a first similar user, the evaluation unit 116 uses the data or analysis results of the first similar user to evaluate a recipe, and the recipe suggestion unit 117 recommends a recipe that is expected to improve the measurement result to the user based on the evaluation. After a predetermined period (e.g., one week or one month, etc.), the measurement value acquisition unit 111 obtains whether the measurement value related to the target, such as weight or blood pressure, has improved. The measurement value acquisition unit 111 may conduct a questionnaire survey on whether the measurement value has improved to the user instead of obtaining the measurement value. Here, in the case where the measurement value has not improved (e.g., when the measurement value has deteriorated, when the measurement value has not changed, when the improvement of the measurement value is lower than the predetermined value), the similar user identification unit 120 identifies a second similar user different from the first similar user in the same manner as the first similar user (selected based on the similarity of the attributes), uses the data or analysis results of the identified second similar user, the evaluation unit 116 evaluates the recipe, and the recipe suggestion unit 117 recommends a recipe that is expected to improve the measurement result to the user based on the evaluation. This process may be repeated until the user's measurement value is observed to improve.

[0240] <Mode 3: Using analysis results of data from multiple other users> In pattern 3, data on a plurality of similar users having attributes similar to that of the user are analyzed.

[0241] The similar user identifying unit 120 can identify users with similar attributes from other users who have registered measurement values ​​associated with the user's achieved goals in the measurement value storage unit 131 as multiple similar users (a specified number can be selected, or all or some of the users with a specified similarity or above can be selected randomly).

[0242] The analysis unit 115 reads all the measurement values ​​and nutrient intakes corresponding to the identified similar users from the measurement value storage unit 131 and the intake amount storage unit 132, and creates a prediction model (nutritional model) by multivariate analysis using the nutrient intake as an explanatory variable and the measurement value as a target variable. It can identify nutrients that contribute to the improvement of the measurement values, i.e., improvement factors, and nutrients that contribute to the deterioration of the measurement values, i.e., deterioration factors.

[0243] The evaluation unit 116 and the recipe suggestion unit 117 can suggest recipes to the user, similarly to the first embodiment.

[0244] <Mode 4: Using analysis results from multiple other users> In mode 4, the analysis results of multiple similar users are used to evaluate and recommend recipes.

[0245] First, the similar user identifying unit 120 may identify a plurality of users with similar attributes (a predetermined number, or all or some of the users with a predetermined similarity or above) from other users who have achieved the same goal as the user as similar users.

[0246] Next, the analysis unit 115 obtains a plurality of prediction models created for a plurality of similar users from the prediction model storage unit 138, and combines the obtained prediction models to create a prediction model (hereinafter referred to as a composite model). The analysis unit 115 may, for example, select explanatory variables common to a plurality of prediction models (for prediction models of a predetermined number or more), and use the selected explanatory variables as explanatory variables of the composite model. The analysis unit 115 may select the coefficient with the largest absolute value, or select the middle value of the coefficient, or calculate the average value of the coefficient, as the coefficient of the explanatory variable of the composite model. Furthermore, the analysis unit 115 may select the explanatory variable with the greatest influence, for example, by using principal component analysis.

[0247] The evaluation unit 116 and the recipe suggestion unit 117 may use the synthesis model created in the above manner as a prediction model to suggest recipes to the user in the same manner as in the first embodiment.

[0248] As described above, according to the health support system of the second embodiment, the user can easily achieve the goal without obtaining the nutrient intake or the measured values ​​linked to the achievement of the goal.

[0249] In addition, in the second embodiment, the nutrition model was described, but the same method can be used for the nutrition action model. [Explanation of symbols]

[0250] 1 Server device 2 Communication Network 3 User Terminal 4 Vital Signs Sensors 5 Activity Sensor 111 Measurement value acquisition unit 112 Intake quantity acquisition unit 113 Action Acquisition Department 114 Life stage information acquisition department 115 Analysis Department 116 Evaluation Department 117 Recipe Suggestion Department 118 Action Suggestion Department 131 Measurement value storage unit 132 Intake amount storage unit 133 Action Storage Unit 134 Life stage information storage unit 135 Recipe Storage 136 Food information storage unit.

Claims

1. An information processing system, characterized in that: have: a measurement value storage unit that stores measurement values ​​linked to a user's achievement goal; an intake amount storage unit for storing intake amounts of a plurality of nutrients ingested by the user; an analyzing unit that analyzes the relationship between the intake of the nutrient and the measured value, and identifies the nutrient that contributes to the improvement of the measured value, i.e., an improvement factor, and the nutrient that contributes to the deterioration of the measured value, i.e., a deterioration factor; a recipe storage unit for storing information on the content of the nutrients included in the specified recipe; and A recipe suggestion unit amends the recipe by at least one of increasing the content of the improvement factor and decreasing the content of the deterioration factor, and suggests the amended recipe.

2. The information processing system according to claim 1, characterized in that Also available: A food information storage unit, which stores the content of the nutrient for each food; The recipe storage unit stores the ingredients included in the recipe, The recipe suggestion unit performs at least one of the following steps, namely, Selecting a second ingredient from the ingredient information storage unit that contains more of the nutrient as the improvement factor than at least one of the first ingredients included in the recipe, and modifying the recipe by replacing the first ingredient with the selected second ingredient; Selecting a third ingredient from the ingredient information storage unit that contains less of the nutrient serving as the malignant factor than the first ingredient, and changing the first ingredient to the selected third ingredient, thereby correcting the recipe; Selecting a fourth ingredient from the ingredient information storage unit that contains more of the nutrient as the improvement factor than the first ingredient and less of the nutrient as the deterioration factor than the first ingredient, and changing the first ingredient to the selected fourth ingredient, thereby correcting the recipe; Selecting the fifth ingredient containing the nutrient as the improvement factor from the ingredient information storage unit, and adding the selected fifth ingredient to correct the recipe; as well as Selecting the sixth ingredient containing the nutrient serving as the malignant factor from the ingredient information storage unit, deleting the selected sixth ingredient, and thereby correcting the recipe; and suggest a revised version of said recipe.

3. The information processing system according to claim 1 or 2, characterized in that: The analyzing unit calculates the degree of improvement that contributes to the improvement with respect to the improvement factor, and calculates the degree of deterioration that contributes to the deterioration with respect to the deterioration factor, Regarding the recipe suggestion section, The first value is calculated by subtracting a value obtained by multiplying the degree of improvement of the improvement factor included in the recipe by the content from a value obtained by multiplying the degree of deterioration of the improvement factor included in the recipe by the content. A second value is obtained by multiplying the degree of improvement of the improvement factor included in the revised recipe by the content from a value obtained by multiplying the degree of improvement of the improvement factor included in the revised recipe by the content, and the recipe is corrected in such a way that the second value is greater than the first value.

4. The information processing system according to claim 1 or 2, characterized in that: The analyzing unit calculates the degree of improvement that contributes to the improvement with respect to the improvement factor, and calculates the degree of deterioration that contributes to the deterioration with respect to the deterioration factor, Regarding the recipe suggestion section, a first improvement value is calculated by subtracting a value obtained by multiplying the intake amount of the improvement factor stored in the intake amount storage unit by the improvement degree from a value obtained by multiplying the intake amount of the improvement factor stored in the intake amount storage unit by the improvement degree, A second improvement value is obtained by multiplying the degree of improvement of the improvement factor included in the revised recipe by the content from a value obtained by multiplying the degree of improvement of the improvement factor included in the revised recipe by the content, and the recipe is corrected in such a way that the second improvement value is greater than the first improvement value.

5. The information processing system according to any one of claims 1 to 4, characterized in that: have: an action amount storage unit that stores the action amount of the action performed by the user; and a target value input unit for receiving an input of a target value of the measured value; The analyzing unit creates a prediction model for analyzing the relationship between the content of the nutrient and the amount of activity and the measured value, The recipe suggestion unit determines the amount of action based on a difference between a predicted value obtained by applying the content of the nutrient included in the corrected recipe to the prediction model and the target value, and suggests the determined amount of action together with the recipe.

6. The information processing system according to any one of claims 1 to 5, characterized in that: The analyzing unit periodically performs analysis to identify the improvement factor and the deterioration factor, and the recipe suggesting unit suggests the corrected recipe.

7. An information processing system, characterized in that: have: a measurement value storage unit for storing a measurement value of the first user linked to an achievement goal of the first user; an intake amount storage unit for storing intake amounts of a plurality of nutrients ingested by the first user; an analyzing unit that analyzes the relationship between the intake of the nutrient and the measured value for the first user, and identifies the nutrient that contributes to improvement of the measured value, i.e., an improvement factor, and the nutrient that contributes to deterioration of the measured value, i.e., a deterioration factor; A recipe storage unit storing information on the content of the nutrients contained in the specified recipe; a similar user identifying unit, which identifies the first user having attributes similar to those of the second user, namely, a similar user; as well as A recipe suggestion unit amends the recipe by at least either increasing the content of the improvement factor specified for the similar user or decreasing the content of the deterioration factor specified for the similar user, and suggests the amended recipe to the second user.

8. An information processing system, characterized in that: have: a measurement value storage unit for storing a measurement value of the first user linked to an achievement goal of the first user; an intake amount storage unit for storing intake amounts of a plurality of nutrients ingested by the first user; A recipe storage unit storing information on the content of the nutrients contained in the specified recipe; a similar user identifying unit, which identifies the first user having attributes similar to those of the second user, namely, a similar user; as well as an analyzing unit that reads the measured value and the intake amount corresponding to the similar user from the measured value storage unit and the intake amount storage unit, analyzes the relationship between the intake amount of the nutrient and the measured value, and identifies the nutrient that contributes to the improvement of the measured value, i.e., the improvement factor, and the nutrient that contributes to the deterioration of the measured value, i.e., the deterioration factor; as well as A recipe suggestion unit is configured to correct the recipe by at least one of increasing the content of the improvement factor and reducing the content of the deterioration factor, and to suggest the corrected recipe to the second user.

9. An information processing method, characterized in that: Instruct the computer to perform the following steps: Storing measurements linked to the user's achievement goals; storing intake amounts of multiple nutrients ingested by the user; Analyzing the relationship between the intake of the nutrient and the measured value, identifying the nutrient that contributes to the improvement of the measured value, i.e., the improvement factor, and the nutrient that contributes to the deterioration of the measured value, i.e., the deterioration factor; Storing information on the content of the nutrients contained in a specific recipe; as well as The recipe is corrected by at least one of increasing the content of the improvement factor and reducing the content of the deterioration factor, and the corrected recipe is suggested.

10. A program product, characterized in that Used to make the computer perform the following steps: Storing measurements linked to the user's achievement goals; storing intake amounts of multiple nutrients ingested by the user; Analyzing the relationship between the intake of the nutrient and the measured value, identifying the nutrient that contributes to the improvement of the measured value, i.e., the improvement factor, and the nutrient that contributes to the deterioration of the measured value, i.e., the deterioration factor; Storing information on the content of the nutrients contained in a specific recipe; as well as The recipe is corrected by at least one of increasing the content of the improvement factor and reducing the content of the deterioration factor, and the corrected recipe is suggested.

Images