Information processing system

Abstract

To enable a user to grasp which of a dietary habit improvement and an increase in momentum is effective for weight losses.SOLUTION: In an information processing system, a control unit inputs, as an explanatory variable, at least one of body measurement information, biological sample information, and answer information of a discretionary user to a first trained model having been trained using, as an objective variable, at least one of body measurement information, biological sample information, life habits, health condition, and answer information to a questionnaire concerning personality of subjects for whom a dietary effect due to a dietary habit improvement is observed, and using, as an object variable, a first predictive value indicating a level of dietary effects, so as to acquire a first predictive value outputted from the first trained model. The control unit further acquires a second predictive value outputted from a second trained model having been trained using, as an explanatory variable, at least one of the body measurement information, the biological sample information, and the answer information of subjects for whom a dietary effect due to an increase in momentum is observed. Then, the control unit generates proposal information for proposing a dieting method to the user on the basis of a result from comparison of the predictive values.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program that can provide information on the diet effects of improving a user's eating habits or increasing the amount of exercise. [Background technology]

[0002] Conventionally, there have been systems for supporting users in improving their health. For example, Patent Document 1 listed below discloses a health support information providing method that acquires health support information (information on diet, information on exercise, and information on nutritional supplements) in association with a combination of genetic polymorphism information on a plurality of obesity genes, acquires two or more pieces of genetic polymorphism information related to the health of a user, identifies health support information from the acquired health support information that corresponds to the combination of two or more pieces of genetic polymorphism information of the user, and allows the user to confirm this health support information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-034845 Summary of the Invention [Problem to be solved by the invention]

[0004] Incidentally, some users find that improving their dietary habits is more effective than increasing their physical activity, while others find that increasing their physical activity is more effective than improving their physical activity. However, the technology in Patent Document 1 cannot provide information on which of information about food and information about exercise is more effective for the user's diet.

[0005] An object of the present invention is to provide an information processing system, an information processing method, and a program that enable a user to understand which of improving eating habits or increasing exercise is more effective for the user's diet. [Means for solving the problem]

[0006] An information processing system according to one aspect of the present invention includes a control unit. The control unit inputs at least one of a user's body measurement information, the biological sample information, and the answer information into a first trained model trained with at least one of the subject's body measurement information, biological sample information collected from the subject, and the subject's answer information to a questionnaire regarding lifestyle, health, or personality as explanatory variables, and a first predicted value indicating the extent of a diet effect resulting from the subject's dietary improvement as a dependent variable, and acquires the first predicted value output from the first trained model. The control unit also inputs at least one of the user's body measurement information, the biological sample information, and the answer information into a second trained model trained with at least one of the subject's body measurement information, the biological sample information collected from the subject, and the subject's answer information to the questionnaire as explanatory variables, and a second predicted value indicating the extent of a diet effect resulting from the subject's increased exercise volume as a dependent variable, and acquires the second predicted value output from the second trained model. The control unit then generates proposal information that proposes a diet method to the user based on the result of comparing the first predicted value with the second predicted value.

[0007] An information processing method according to another aspect of the present invention includes: inputting at least one of the body measurement information of an arbitrary user, the biological sample information, and the answer information to a questionnaire regarding the subject's lifestyle, health condition, or personality into a first trained model that has been trained using as an explanatory variable at least one of the body measurement information of the subject, the biological sample information collected from the subject, and the answer information to a questionnaire regarding the subject's lifestyle, health condition, or personality, and using as an objective variable a first predicted value that indicates the degree of a diet effect resulting from improving the subject's eating habits; Obtain the first predicted value output from the first trained model; inputting at least one of the body measurement information, the biological sample information, and the answer information of the user into a second trained model that has been trained using at least one of the body measurement information of the subject, the biological sample information collected from the subject, and the answer information of the subject to the questionnaire as an explanatory variable, and a second predicted value that indicates the degree of a diet effect due to an increase in the amount of exercise of the subject as a target variable; Obtain the second predicted value output from the second trained model; generating proposal information that proposes a diet method to the user based on a result of comparing the first predicted value with the second predicted value; This includes:

[0008] According to yet another aspect of the present invention, there is provided a program for executing the program on an information processing device, inputting at least one of the user's body measurement information, the biological sample information, and the answer information to a questionnaire regarding the subject's lifestyle, health condition, or personality into a first trained model, the first trained model being trained using at least one of the subject's body measurement information, the biological sample information collected from the subject, and the answer information to a questionnaire regarding the subject's lifestyle, health condition, or personality as an explanatory variable, and a first predicted value indicating the degree of diet effect due to the subject's eating habits improvement as a dependent variable; obtaining the first predicted value output from the first trained model; inputting at least one of the body measurement information, the biological sample information, and the answer information of the user into a second trained model trained using at least one of the body measurement information of the subject, the biological sample information collected from the subject, and the answer information of the subject to the questionnaire as an explanatory variable, and a second predicted value indicating the degree of the diet effect due to an increase in the subject's amount of exercise as a dependent variable; Obtaining the second predicted value output from the second trained model; generating proposal information that proposes a diet method to the user based on a result of comparing the first predicted value and the second predicted value; Execute the following. [Effects of the Invention]

[0009] According to an information processing system of an embodiment of the present invention, it is possible to allow a user to understand which of improving their diet habits or increasing their exercise amount is more effective for the user's diet. However, this effect does not limit the present invention. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram showing the configuration of a diet effect prediction model generation system according to one embodiment of the present invention. [Figure 2] 1 is a diagram showing a hardware configuration of a diet information providing server according to an embodiment of the present invention. [Figure 3] 2 is a diagram showing the configuration of a database included in a diet information providing server according to one embodiment of the present invention. FIG. [Figure 4] 10 is a flowchart showing the flow of a process for generating a diet effect prediction model by a diet information providing server according to one embodiment of the present invention. [Figure 5] 10 is a diagram illustrating the prediction accuracy of a diet effect prediction model by a diet information providing server according to one embodiment of the present invention. FIG. [Figure 6] 10 is a flowchart showing the flow of a diet suggestion information providing process using the diet effect prediction model by a diet information providing server according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0012] [System Configuration] As shown in FIG. 1, this system includes a diet information providing server 100 on the Internet 50 and a plurality of user terminals 200.

[0013] The diet information providing server 100 provides a service of suggesting diet methods to users of user terminals 200. Specifically, the diet information providing server 100 is connected to a plurality of user terminals 200 via the Internet 50, and predicts the diet effect when the user improves their eating habits and the diet effect when the user increases their exercise amount based on the user's body measurement information, biological sample information (e.g., blood test information), and answer information to a questionnaire, and transmits diet suggestion information to the user terminal 200 based on the predicted information. The diet effect is, for example, the weight loss rate or the amount of visceral fat loss, but is not limited to these.

[0014] The user terminals 200 (200A, 200B, 200C...) are terminals used by users, such as smartphones, mobile phones, tablet PCs (Personal Computers), notebook PCs, and desktop PCs. The user terminals 200 transmit the user's physical measurement information, blood test information, and questionnaire response information to the diet information providing server 100, and receive and display the diet suggestion information on a screen using a browser or the like. An application (hereinafter also referred to as a diet app) corresponding to a diet suggestion information providing service may also be installed in the user terminals 200, and the user terminals 200 may access the diet information providing server 100 using the diet app to display the diet suggestion information.

[0015] Here, "improving eating habits" means, for example, performing at least one of the following, and the diet information providing server 100 can set a definition of improving eating habits by appropriately combining the following. Eat less (set a daily calorie intake) Reduce snacking or eat healthier snacks Reduce the amount of carbohydrates (staple foods) you consume Reduce fat intake Reduce sugar in drinks Increase your intake of fruits and vegetables Eat meals at regular times Don't eat late at night (e.g. after 8pm) Limit the time during the day when you can eat (for example, 10 hours) Stop eating when you are 80% full Replace at least one meal a day with a menu designed specifically for dieting (for example, a menu that reduces fat and increases protein, replaces fat with omega-3, and includes carbohydrates with dietary fiber).

[0016] Furthermore, "increasing the amount of exercise" refers to, for example, performing at least one of the following, and the diet information providing server 100 can set the definition of increasing the amount of exercise by appropriately combining the following. Engage in a set number of minutes (e.g., at least 150-300 minutes) of moderate-intensity (3.0-6.0 METs) physical activity per week (e.g., brisk walking, dancing, mowing the lawn). Engage in vigorous-intensity (6.0 METs or greater) physical activity (e.g., running, swimming, stair climbing) for a set period of time (e.g., at least 75-150 minutes) per week. · Perform prescribed strength training (e.g., 15 minutes of multiple strength training such as squats) a prescribed number of times per week (e.g., 3 times)

[0017] In addition to the above, "increasing the amount of exercise" also includes increasing the intensity and / or duration of daily physical activity or exercise.

[0018] The inventors tested the diet effects of a certain number of subjects by separately improving their dietary habits (hereinafter also referred to as "dietary intervention") and increasing their physical activity (hereinafter also referred to as "exercise intervention"). They found that a certain percentage of subjects saw a diet effect in both dietary and exercise interventions, and that those who benefited from dietary and exercise interventions had different characteristics (at least one of anthropometric information, biological sample information collected from the subject, and information on responses to questionnaires regarding the subject's lifestyle, health status, or personality). Therefore, the inventors decided to separately predict the diet effects of dietary intervention and exercise intervention for the target user, and by comparing the two predicted values, provide the user with suggested information on a more effective diet method.

[0019] To provide the suggested information, the diet information providing server 100 uses a first trained model 10 and a second trained model 20. The first trained model 10 is a trained model that uses at least one of the subject's physical measurement information, blood test information, and answer information to a questionnaire about lifestyle habits, health status, or personality as explanatory variables, and a first predicted value indicating the degree of diet effect due to the subject's eating habits improvement as a dependent variable. The second trained model 20 is a trained model that uses at least one of the above physical measurement information, the above blood test information, and the above answer information as explanatory variables, and a second predicted value indicating the degree of diet effect due to the subject's increased exercise volume as a dependent variable.

[0020] [Hardware configuration of diet information server] FIG. 2 is a diagram showing the hardware configuration of the diet information providing server 100. As shown in FIG.

[0021] As shown in the figure, the diet information providing server 100 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, an input / output interface 15, and a bus 14 connecting these together.

[0022] The CPU 11 accesses the RAM 13 etc. as needed, and performs various arithmetic processing while controlling all blocks of the diet information providing server 100. Multiple CPUs 11 may be provided depending on the processing. The ROM 12 is a non-volatile memory in which firmware such as the OS, programs, and various parameters to be executed by the CPU 11 are permanently stored. The RAM 13 is used as a working area for the CPU 11, and temporarily stores the OS, various applications currently being executed, and various data currently being processed.

[0023] The input / output interface 15 is connected to a display unit 16, an operation reception unit 17, a storage unit 18, a communication unit 19, and the like.

[0024] The display unit 16 is a display device that uses, for example, an LCD (Liquid Crystal Display), an OLED (Organic ElectroLuminescence Display), a CRT (Cathode Ray Tube), or the like.

[0025] The operation reception unit 17 is, for example, a pointing device such as a mouse, a keyboard, a touch panel, or other input device. When the operation reception unit 17 is a touch panel, the touch panel can be integrated with the display unit 16.

[0026] The storage unit 18 is a non-volatile memory such as a hard disk drive (HDD), a flash memory (solid state drive (SSD)), or other solid-state memory. The storage unit 18 stores the OS, various applications, and various data.

[0027] As will be described later, particularly in this embodiment, the memory unit 18 has programs such as applications necessary for the process of generating a diet effect prediction model described later and the process of providing diet suggestion information using the prediction model, as well as a physical measurement information database, a blood test information database, a questionnaire information database, and an effect prediction information database.

[0028] The communication unit 19 is, for example, a NIC (Network Interface Card) for Ethernet or various modules for wireless communication such as wireless LAN, and is responsible for communication processing with the user terminal 200.

[0029] Although not shown, the basic hardware configuration of the user terminal 200 is also substantially the same as the hardware configuration of the diet information providing server 100 described above.

[0030] [Database configuration of diet information server]

[0031] 3, the diet information providing server 100 has, in the memory unit 18, a body measurement information database 31, a blood test information database 32, a questionnaire information database 33, and an effect prediction information database 34. Note that each of these databases may be stored in a storage device or server externally connected to the diet information providing server 100, rather than in the memory unit 18.

[0032] The physical measurement information database 31 stores the physical measurement information received from the user terminal 200, such as the user's age, sex, height, weight, body composition, visceral fat area, waist size, blood pressure, heart rate, and body temperature, in association with general information such as the user's name, a user ID for identifying the user, occupation, address, and email address.

[0033] The blood test information database 32 stores the user's blood test information received from the user terminal 200. The blood test information includes, for example, values ​​measured in a general blood test such as white blood cell count, red blood cell count, hemoglobin level, hematocrit value, platelet count, mean corpuscular volume, mean corpuscular hemoglobin level, and mean corpuscular hemoglobin concentration, and values ​​measured in a blood biochemistry test such as creatinine, uric acid, urea nitrogen, aspartate aminotransferase, alanine aminotransferase, γ-glutamyltranspeptidase, alkaline phosphatase, lactate dehydrogenase, creatine kinase, total cholesterol, HDL cholesterol, non-HDL cholesterol, LDL-cholesterol, triglycerides, total bilirubin, total bile acid, sodium, potassium, chloramphenicol, thiamin monophosphate ... These include, but are not limited to, values ​​such as cholesterol, calcium, magnesium, inorganic phosphorus, iron, total protein, albumin, albumin / globulin ratio, free fatty acids, blood glucose, HbA1c, insulin, NEFA, total ketone bodies, acetoacetate, 3-hydroxybutyrate, high-sensitivity CRP (hsCRP), leptin, growth hormone, cortisol, dehydroepiandrosterone (DHEA), testosterone, androgens, TNF-α, IGF-1, T3 / T4 / TSH / free T3 / free T4, ammonia, amino acid fractions, fatty acid composition, glyceride composition, polyphenol composition, vitamin composition, FGF21, BDNF, TARC, and metabolomic analysis.

[0034] The diet information providing server 100 may receive the physical measurement information and blood test information not from the user terminal 200 but from a terminal (institutional terminal) of another organization, such as a health checkup institution, a sports gym, or a clinical trial institution.

[0035] The questionnaire information database 33 stores questionnaire information for users and information on responses to the questionnaire information received from the user terminal 200. Specifically, the questionnaires are related to the user's lifestyle, health status, or personality. Questionnaires related to lifestyle include the BDHQ (Brief Self-Administered Diet History Questionnaire), the International Standardized Physical Activity Questionnaire, and the Eating Behavior Questionnaire. Questionnaires related to health status include the 35-item Diet Questionnaire, the WHO-5 Mental Health Questionnaire, the Occupational Stress Brief Questionnaire, the Chalder Fatigue Scale, and the Athens Insomnia Scale. Questionnaires related to personality include, for example, the Big-five questionnaire.

[0036] The effect prediction information database 34 stores the diet effect prediction information (weight loss rate information) due to dietary intervention and the diet effect prediction information (weight loss rate information) due to exercise intervention, which are obtained by inputting the physical measurement information, blood test information, and response information received from the user terminal 200 into the first trained model 10 and the second trained model 20, respectively, in association with the user ID.

[0037] These databases are used by mutual reference as needed in the diet suggestion information providing process by the diet information providing server 100, which will be described later.

[0038] [Operation of diet information server] Next, the operation of the diet information providing server 100 configured as above will be described. The operation is performed by the cooperation of hardware such as the CPU 11 and communication unit 19 of the diet information providing server 100 and software stored in the storage unit 18. For convenience, in the following description, the CPU 11 is the subject of the operation.

[0039] (Diet effect prediction model generation process) First, the process of generating the diet effect prediction models (the first trained model 10 and the second trained model 20) by the diet information providing server 100 will be described.

[0040] Fig. 4 is a flowchart showing the details of the process for generating the diet effect prediction model. As a premise of this process, it is assumed that a clinical trial of a predetermined dietary improvement (e.g., daily calorie intake restriction) is conducted on a plurality of subject users for, for example, several weeks, and subject users who have observed a diet effect (weight loss) as a result are identified.

[0041] As shown in the figure, first, CPU 11 receives body measurement information, blood test information, and answer information to a questionnaire from user terminal 200 of a subject user who has been observed to have achieved a diet effect through improving their eating habits (step 41). The body measurement information and answer information to the questionnaire are received, for example, via a body information input screen having input fields and a questionnaire (questionnaire) screen having answer fields, both of which are displayed on user terminal 200. In addition, blood test information may be received in advance by user terminal 200 from a testing institution and stored in the diet app, and the test result data may be transmitted to diet information providing server 100 via the diet app.

[0042] Next, the CPU 11 performs pre-processing on each piece of received information, i.e., normalization processing by setting the minimum value to 0 and the maximum value to 1 (step 42). These pieces of information are received and normalized as data of, for example, about 2000 types of feature amounts in total.

[0043] Next, the CPU 11 divides the normalized data into training (teacher) data and verification data (step 43).

[0044] Next, the CPU 11 selects feature quantities (parameters) to be used for prediction from the large number of feature quantities of the training data (for example, selects 20 from the 2000 types) (step 44). For this selection, for example, Lasso regression can be used. Lasso regression is a regression model in which an L1 regularization term is added to the objective function. By adding the regularization term, the values ​​of some regression coefficients become 0, allowing for automatic feature selection.

[0045] Then, the CPU 11 performs multiple regression analysis using the selected feature data as training data to construct a prediction model of the diet effect (weight loss rate or visceral fat area reduction amount) resulting from dietary improvement (dietary intervention) (step 45).

[0046] Then, the CPU 11 predicts the weight loss rate by inputting the verification data into the constructed prediction model (step 46) and verifies the prediction accuracy (step 47). The CPU 11 repeatedly executes the above process by changing the training data and verification data among the data of multiple subjects until a predetermined or higher prediction accuracy is achieved, and constructs a final prediction model for predicting the diet effect of any user as a result of improving the user's eating habits.

[0047] The CPU 11 also constructs a prediction model of the diet effect (weight loss rate or visceral fat area reduction amount) due to an increase in the amount of exercise (exercise intervention) by performing the same processing as in steps 41 to 47. In this case, a clinical trial of a predetermined increase in the amount of exercise is performed on a plurality of subject users, for example, for several weeks, and subject users who have been observed to lose weight as a result are identified, and body measurement information, blood test information, and questionnaire response information are received from the user terminal 200 of the subject user who has been observed to have a diet effect due to the increase in the amount of exercise.

[0048] The explanatory variables (physical measurement information, blood test information, and questionnaire response information) used to construct the prediction model of the diet effect due to the above-mentioned dietary improvement and the explanatory variables used to construct the prediction model of the diet effect due to increased exercise volume may be received from the same subject user or from different subject users.

[0049] FIG. 6 is a diagram illustrating the prediction accuracy of the diet effect prediction model.

[0050] Figure 1A shows the accuracy of a model predicting weight loss following dietary intervention, using explanatory variables such as physiologic measurements (visceral fat area, weight, body fat percentage, waist size, hip size, blood pressure, heart rate, and body temperature); blood test data (blood metabolome, leptin, tumor necrosis factor-α (TNF-α), blood glucose, and insulin); and questionnaire responses to a 35-question diet questionnaire, physical activity questionnaire, WHO-5 mental health status questionnaire, and BDHQ (short self-administered diet history questionnaire). Figure 1B shows the accuracy of a model predicting weight loss following exercise intervention, using the above information as explanatory variables. Figure 1C shows the accuracy of a model predicting visceral fat area reduction following dietary intervention, using the above information as explanatory variables. Figure 1D shows the accuracy of a model predicting visceral fat area reduction following exercise intervention, using the above information as explanatory variables. The target user in this example is a person with a BMI of 23 kg / m 2 The above men were included in the dietary intervention group (20 men) and the exercise intervention group (36 men).

[0051] The 35-question dietary questionnaire involves responding to questions such as those about appetite, health consciousness, meal times, dietary restrictions, exercise, etc. on a five-point scale: "does not apply," "does not really apply," "cannot say either way," "somewhat applies," or "applies." Even if I'm not hungry, I can't help but eat something that smells delicious. I feel guilty about eating too much so I eat less. Eat a late-night snack after dinner I try to avoid animal fats and eat vegetable fats and fish fats instead. -Doesn't exercise much

[0052] The WHO-5 Mental Health Questionnaire asks participants to answer the following five items (1) to (5) on a five-point scale, asking how often they have experienced each of the following in the past two weeks: "Never (0 points)," "Very rarely (1 point)," "Less than half the time (2 points)," "More than half the time (3 points)," "Almost always (4 points)," and "Always (5 points)." (1) I was in a cheerful and happy mood. (2) I felt calm and relaxed. (3) I was motivated and active. (4) I had a good night's rest and woke up feeling refreshed. (5) There were many interesting things in my daily life.

[0053] The prediction accuracy (correlation coefficient r between true value and predicted value) of each of the above prediction models was 0.89 for Spearman and 0.92 for Pearson in the example of Figure (A), 0.82 for Spearman and 0.83 for Pearson in the example of Figure (B), 0.84 for Spearman and 0.79 for Pearson in the example of Figure (C), and 0.80 for Spearman and 0.78 for Pearson in the example of Figure (D).

[0054] In this way, both prediction models were able to achieve high prediction accuracy when dietary and exercise interventions were performed as interventions, and when predicting weight loss rate and visceral fat area reduction as diet effects.

[0055] (Diet effect prediction information provision process) Next, a description will be given of a process for providing diet suggestion information to the user terminal 200 using the diet effect prediction model constructed above. Fig. 6 is a flowchart showing the flow of the process for providing diet suggestion information.

[0056] As shown in the figure, first, the CPU 11 determines whether or not a diet suggestion request has been received from the user terminal 200 (step 61). The diet suggestion request includes the above-mentioned body measurement information, blood test information, and answer information to the questionnaire.

[0057] The body measurement information and answer information to the questionnaire are received, for example, via a body measurement information input screen having input fields and a questionnaire (questionnaire) screen having answer fields, which are displayed on user terminal 200. As for blood test information, test results may be received in advance by user terminal 200 from a testing institution and stored in the diet app, and the test result data may be transmitted to diet information providing server 100 by the diet app. Similarly, as for body measurement information, body measurement results may be received by user terminal 200 from a health checkup institution or the like, stored in the diet app, and transmitted to diet information providing server 100. The received information is stored in body measurement information database 31, blood test information database 32, and questionnaire information database 33, respectively.

[0058] If it is determined that the proposal request has been received (Yes in step 61), the CPU 11 inputs the physical measurement information, blood test information, and questionnaire response information included in the proposal request into the first trained model 10 (step 62).

[0059] Next, the CPU 11 acquires a first predicted value of the diet effect (weight reduction rate or visceral fat area reduction amount) due to the dietary intervention from the first trained model 10 (step 63). The first predicted value is stored in the predicted effect information database 34.

[0060] Next, the CPU 11 inputs the received and stored physical measurement information, blood test information, and questionnaire response information into the second trained model 20 (step 64).

[0061] Next, the CPU 11 obtains a second predicted value of the diet effect (weight reduction rate or visceral fat area reduction amount) due to the exercise intervention from the second trained model 20 (step 65). The second predicted value is also stored in the predicted effect information database 34.

[0062] Next, the CPU 11 compares the first predicted value with the second predicted value (step 66).

[0063] Then, the CPU 11 generates diet suggestion information based on the higher value from the comparison result, and transmits it to the user terminal 200 (step 67).

[0064] If the above comparison shows that the first predicted value is higher, the CPU 11 may display a message on the diet app as the above suggested information, such as, "For you, dietary restrictions are more effective than exercise for dieting. If you continue dietary restrictions correctly for xx days, you can expect to lose xx% of your weight. As for dietary restrictions, it is recommended that you limit your daily calorie intake to xx kilocalories."

[0065] Furthermore, if the second predicted value is higher in the above comparison, the CPU 11 may display a message on the diet app such as, "Exercise is more effective for you to lose weight than restricting your food intake. If you continue to exercise correctly for x number of days, you can expect to lose x number of pounds. As for exercise, it is recommended that you focus on aerobic exercise such as jogging or swimming, and consume more than x number of calories per day."

[0066] Also, in the above flowchart, instead of receiving a diet suggestion request from the user terminal 200 and sending diet suggestion information to the user terminal 200, the diet information providing server 100 may receive a diet suggestion request for the user on behalf of the user from a terminal of another organization such as the health checkup institution, sports gym, or clinical trial institution, and send diet suggestion information to the terminal of the other organization on behalf of the user.

[0067] As described above, according to this embodiment, the diet information providing server 100 can allow the user to understand which of improving their dieting habits or increasing their exercise volume is more effective for their diet by comparing the first predicted value of the first trained model 10, which predicts the diet effect of dietary intervention using the user's physical measurement information, blood test information, and questionnaire response information as explanatory variables, with the second predicted value of the second trained model 20, which predicts the diet effect of exercise intervention using the above information as explanatory variables.

[0068] [Variations] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and it goes without saying that various modifications can be made within the scope of the gist of the present invention.

[0069] In the above embodiment, the diet information providing server 100 uses all of the body measurement information, blood test information, and questionnaire response information as explanatory variables to build the diet effect prediction model for each of the diet intervention and exercise intervention. However, the diet information providing server 100 may use any two or one of the body measurement information, blood test information, and questionnaire response information as explanatory variables to build each diet effect prediction model.

[0070] In the above-described embodiment, the diet information providing server 100 compares the first predicted value with the second predicted value and generates the suggested information based on the higher value. Alternatively, the diet information providing server 100 may compare the first predicted value with the second predicted value and generate the diet suggested information based on the ratio between the two. For example, the diet information providing server 100 may send to the user terminal 200 as suggested information a message such as, "For you, dietary restrictions and exercise are effective in a ratio of 7:3. It would be a good idea to restrict your diet for xx days and exercise on at least xx days of that time."

[0071] In the above-described embodiment, the first trained model 10 and the second trained model 20 predicted the weight loss rate as the diet effect, but they may be trained to predict the weight loss amount (kg) instead of the weight loss rate. Similarly, the first trained model 10 and the second trained model 20 may be trained to predict the visceral fat area reduction rate instead of the visceral fat area reduction amount.

[0072] In the above-described embodiment, the diet information providing server 100 may charge a predetermined amount as a service fee (subscription fee) to the account (user ID) of the user terminal 200 as consideration for the service of providing the diet suggestion information to the user terminal 200. In this case, after transmitting the diet suggestion information to the user terminal 200, when the diet information providing server 100 receives information (such as the weight loss rate or the amount of visceral fat area reduction after dieting) from the user terminal 200 via the diet app (such as its weight / visceral fat recording function) indicating that the weight loss effect indicated by the suggestion information has been achieved, the server 100 may deduct a predetermined amount (a predetermined percentage of the amount) from the amount charged and notify the user terminal 200 of the result.

[0073] In the above-described embodiment, blood test information is used as an example of biological sample information. However, the biological sample information is not limited to blood test information and may be, for example, sebum test information, or test information on urine, sweat, saliva, phlegm, nasal discharge, exhaled breath, dental plaque, gingival crevicular fluid, skin, hair, skin flakes, tears, semen, feces, etc.

[0074] Such test information may include component information, information on the expression level of genes or their expression products, and more specifically, information on the expression level of mRNA, information on bacterial flora, and the like.

[0075] Furthermore, in the present invention, the term "gene" encompasses double-stranded DNA including human genomic DNA, single-stranded DNA (positive strand) including cDNA, single-stranded DNA (complementary strand) having a sequence complementary to the positive strand, and fragments thereof, and refers to DNA in which some biological information is contained in the sequence information of the bases that make up the DNA.

[0076] Furthermore, the "gene" in the present invention includes not only "genes" represented by a specific base sequence, but also their homologues (i.e., homologs or orthologs), variants such as genetic polymorphisms, and derivatives.

[0077] Here, the names of the genes disclosed in this specification are in accordance with the official symbols listed in NCBI ([www.ncbi.nlm.nih.gov / ]).

[0078] In the present invention, the term "expression product" of a gene encompasses both transcription products and translation products of the gene. A "transcription product" is RNA generated by transcription from a gene (DNA), and a "translation product" refers to a protein encoded by the gene that is translated and synthesized based on the RNA.

[0079] In the present invention, the expression level of a target gene or its expression product can be measured using RNA, DNA encoding the RNA, a protein encoded by the RNA, a molecule that interacts with the protein, a molecule that interacts with the RNA, or a molecule that interacts with the DNA, with RNA being preferred and mRNA being more preferred. Here, molecules that interact with RNA, DNA, or protein include DNA, RNA, proteins, polysaccharides, oligosaccharides, monosaccharides, lipids, fatty acids, and their phosphorylations, alkylations, and sugar adducts, as well as complexes of any of the above. Furthermore, the expression level comprehensively refers to the expression amount and activity of the gene or expression product.

[0080] In the present invention, in a preferred embodiment, skin surface lipids (SSL) are used as a biological sample. In this case, the expression level of mRNA contained in the skin surface lipids (SSL) is analyzed, specifically, the RNA is converted to cDNA by reverse transcription, and then the cDNA or its amplification product is measured.

[0081] RNA can be extracted from SSL using methods commonly used for extracting or purifying RNA from biological samples, such as the phenol / chloroform method, the AGPC (acid guanidinium thiocyanate-phenol-chloroform extraction) method, methods using columns such as TRIzol (registered trademark), RNeasy (registered trademark), or QIAzol (registered trademark), methods using special silica-coated magnetic particles, methods using Solid Phase Reversible Immobilization magnetic particles, and extraction using commercially available RNA extraction reagents such as ISOGEN.

[0082] In the above embodiment, only one diet information providing server 100 is shown, but the processes executed by the diet information providing server 100 may be distributed and executed by multiple servers. For example, the process of generating each diet effect prediction model shown in Fig. 4 and the process of providing diet suggestion information using the prediction model shown in Fig. 6 may be executed by separate servers.

[0083] Among the inventions described in the claims of this application, the invention described as an "information processing method" is one in which each step is automatically performed by at least one device such as a computer through software-based information processing, and is not performed by a human using a device such as a computer. In other words, the "information processing method" is an information processing method using computer software, and is not a method in which a human operates a computing tool called a computer. [Explanation of symbols]

[0084] 10…First trained model 20…Second trained model 11...CPU 18...Storage section 19…Communications Department 31...Body measurement information database 32...Blood test information database 33...Questionnaire information database 34...Effectiveness prediction information database 100...Restaurant information server 200...User terminal

Claims

1. At least one of the body measurement information of a subject in which a diet effect due to dietary improvement has been observed, the biological sample information collected from the subject, and the answer information to a questionnaire regarding the subject's lifestyle, health condition, or personality is used as an explanatory variable, and at least one of the body measurement information, the biological sample information, and the answer information of an arbitrary user is input into a first trained model that has been trained using a first predicted value that indicates the degree of the diet effect due to the dietary improvement of the subject as a target variable; Obtain the first predicted value output from the first trained model; At least one of the body measurement information of the subject in whom a diet effect due to an increase in the amount of exercise has been observed, the biological sample information collected from the subject, and the answer information of the subject to the questionnaire is used as an explanatory variable, and a second predicted value indicating the degree of the diet effect due to an increase in the amount of exercise of the subject is used as a target variable. At least one of the body measurement information, the biological sample information, and the answer information of the subject is input to a second trained model. Obtain the second predicted value output from the second trained model; generating proposal information that proposes a diet method to the user based on a result of comparing the first predicted value with the second predicted value; Control unit An information processing system comprising:

2. The control unit receives proposal request information including at least one of the user's physical measurement information, the biological sample information, and the response information from the user terminal of the user or the institution terminal of the institution that performed the user's physical measurement or biological sample test, and transmits the generated proposal information to the user terminal or the institution terminal. The information processing system according to claim 1 .

3. The control unit compares the first predicted value and the second predicted value and generates the proposal information based on the higher value. The information processing system according to claim 1 .

4. The control unit compares the first predicted value with the second predicted value and generates the proposal information based on a ratio between the first predicted value and the second predicted value. The information processing system according to claim 1 .

5. The diet effect is a weight loss effect, The control unit receiving information indicating the weight of the user as part of the proposal request information from the user terminal or the institution terminal; As the suggestion information, information indicating how much the user's weight will be reduced in a predetermined period of time by improving the eating habits or increasing the amount of exercise is generated. The information processing system according to claim 2 .

6. The diet effect is a visceral fat area reduction effect, The control unit receiving information indicating the weight of the user as part of the proposal request information from the user terminal or the institution terminal; As the suggestion information, information indicating how much the visceral fat area of ​​the user will be reduced in a predetermined period of time by the improvement of the dietary habits or the increase in the amount of exercise is generated. The information processing system according to claim 2 .

7. The control unit When generating the proposed information, a predetermined first amount is charged to an account corresponding to the user; When receiving information from the user terminal indicating that the reduction effect indicated by the proposal information has been achieved, a predetermined second amount is subtracted from the first amount.

7. The information processing system according to claim 5 or 6.

8. The biological sample information is blood test information. The information processing system according to claim 1 .

9. The biological sample information is sebum test information. The information processing system according to claim 1 .

10. At least one of the body measurement information of a subject in which a diet effect due to dietary improvement has been observed, the biological sample information collected from the subject, and the answer information to a questionnaire regarding the subject's lifestyle, health condition, or personality is used as an explanatory variable, and at least one of the body measurement information, the biological sample information, and the answer information of an arbitrary user is input into a first trained model that has been trained using a first predicted value that indicates the degree of the diet effect due to the dietary improvement of the subject as a target variable; Obtain the first predicted value output from the first trained model; At least one of the body measurement information of the subject in whom a diet effect due to an increase in the amount of exercise has been observed, the biological sample information collected from the subject, and the answer information of the subject to the questionnaire is used as an explanatory variable, and a second predicted value indicating the degree of the diet effect due to an increase in the amount of exercise of the subject is used as a target variable. At least one of the body measurement information, the biological sample information, and the answer information of the subject is input to a second trained model. Obtain the second predicted value output from the second trained model; generating proposal information that proposes a diet method to the user based on a result of comparing the first predicted value with the second predicted value; An information processing method executed by an information processing device.

11. In the information processing device, a step of inputting at least one of the body measurement information of a subject in which a diet effect due to dietary improvement has been observed, the biological sample information collected from the subject, and the answer information to a questionnaire regarding the subject's lifestyle, health condition, or personality as explanatory variables, and inputting at least one of the body measurement information, the biological sample information, and the answer information of an arbitrary user into a first trained model trained using a first predicted value indicating the degree of the diet effect due to the subject's dietary improvement as a dependent variable; Obtaining the first predicted value output from the first trained model; a step of inputting at least one of the body measurement information of the subject in whom a diet effect due to an increase in the amount of exercise has been observed, the biological sample information collected from the subject, and the answer information of the subject to the questionnaire as an explanatory variable, and inputting at least one of the body measurement information, the biological sample information, and the answer information of the subject to the questionnaire as an objective variable into a second trained model trained with a second predicted value indicating the degree of the diet effect due to an increase in the amount of exercise of the subject; Obtaining the second predicted value output from the second trained model; generating proposal information that proposes a diet method to the user based on a result of comparing the first predicted value and the second predicted value; A program that executes the following.

Images