JP7760945B2 - Information processing method, information processing device, program, and information processing system - Google Patents

Description

The present invention relates to an information processing method, an information processing device, a program, and an information processing system.

As a conventional method for assessing a user's diabetes-related emergency condition, for example, Patent Document 1 describes technology that determines a glycemic urgency index based on data such as the user's glucose concentration, deviation from a normal glucose pattern, and weight, and displays the determined glycemic urgency index on a mobile device.

Japanese Patent Application Laid-Open No. 2020-78648

However, the method disclosed in Patent Document 1 only presents the subject's glycemic urgency index and does not reveal the subject's diet-related obesity risk.

The present invention was made in consideration of these problems, and aims to reveal the obesity risk caused by a subject's diet.

In order to solve the above problems, an information processing method according to the present invention includes:
A processing unit of the information processing device
an obesity index representing the obesity level of the target user is estimated by inputting estimation information including information about an increase in blood glucose level caused by a meal into an obesity index estimation model machine-learned based on learning information including information about an increase in blood glucose level caused by a meal;
predicting the target user's risk of obesity based on the estimated obesity index;
It is characterized by:

In order to solve the above problem, the information processing device according to the present invention comprises:
an obesity index representing the obesity level of the target user is estimated by inputting estimation information including information about an increase in blood glucose level caused by a meal into an obesity index estimation model machine-learned based on learning information including information about an increase in blood glucose level caused by a meal;
predicting the target user's risk of obesity based on the estimated obesity index;
It is characterized by having a processing unit.

In order to solve the above problem, the program according to the present invention comprises:
The computer of the information processing device
a process of estimating an obesity index representing the obesity level of the target user by inputting estimation information including information about an increase in blood glucose level caused by the target user's diet into an obesity index estimation model machine-learned based on learning information including information about an increase in blood glucose level caused by the diet;
predicting the target user's risk of obesity based on the estimated obesity index;
The present invention is characterized in that the following is executed.

In order to solve the above problem, the information processing system according to the present invention comprises:
An information processing system in which an information processing device and a terminal device are communicatively connected to each other,
The information processing device includes:
an obesity index representing the obesity level of the target user is estimated by inputting, via the terminal device, estimation information including information about an increase in blood glucose level caused by the target user's diet into an obesity index estimation model that has been machine-learned based on learning information including information about an increase in blood glucose level caused by diet;
predicting the target user's risk of obesity based on the estimated obesity index;
a processing unit;
The terminal device
obtaining a result of the prediction of the target user's obesity risk;
Displaying the result on a display unit.
It is characterized by having a processing unit.

The present invention makes it possible to reveal the risk of obesity caused by a subject's diet.

FIG. 1 illustrates an obesity risk assessment system. FIG. 2 is a block diagram showing the functional configuration of a server. FIG. 2 is a block diagram showing the functional configuration of the terminal device. FIG. 2 is a block diagram showing the functional configuration of the wearable device. 10 is a flowchart showing a control procedure for a learning process. 1 is a graph plotting blood glucose level data over time. 10 is a flowchart showing a control procedure for obesity risk prediction processing.

The following describes an embodiment of the present invention with reference to the drawings.

<Configuration of obesity risk assessment system>
FIG. 1 is a diagram showing an obesity risk assessment system 1 of this embodiment.
As shown in FIG. 1 , the obesity risk assessment system (information processing system) 1 includes a server (information processing device) 10, a terminal device 20, and a wearable device 30. The obesity risk assessment system 1 predicts a user's diet-related obesity risk based on personal data of the user (target user) who uses the terminal device 20 and the wearable device 30, and presents the results to the user. The obesity risk assessment system 1 includes multiple terminal devices 20 and multiple wearable devices 30 used by multiple users, respectively, and can acquire personal data of these multiple users, predict each user's diet-related obesity risk based on the personal data, and present each result to each user. In FIG. 1 , the terminal device 20 and wearable device 30 used by a single user are depicted as representative examples.

FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG.
2, the server 10 includes a CPU (Central Processing Unit) 11, a RAM (Random Access Memory) 12, a storage unit 13, a communication unit 14, and a bus 15. The components of the server 10 are connected to each other via the bus 15. The server 10 may further include an operation unit, a display unit, and the like that are used by an administrator of the server 10.

The CPU 11 is a processor that controls the operation of each unit of the server 10 by reading and executing the program 131 stored in the storage unit 13 and performing various arithmetic processing. In this embodiment, the CPU 11 corresponds to the "processing unit." Note that the processing unit may have multiple processors (e.g., multiple CPUs), and the multiple processes performed by the CPU 11 in this embodiment may be executed by these multiple processors. In this case, the multiple processors correspond to the "processing unit." In this case, the multiple processors may be involved in a common process, or the multiple processors may independently execute different processes in parallel.

RAM 12 provides working memory space for CPU 11 and stores temporary data.

The memory unit 13 is a non-transitory recording medium readable by the CPU 11 as a computer, and stores the program 131 and various data. The memory unit 13 includes a non-volatile memory such as a flash memory. The program 131 is stored in the memory unit 13 in the form of computer-readable program code. The memory unit 13 also stores an obesity index estimation model 132.

The obesity index estimation model 132 is a learning model (trained model) that has been machine-learned based on learning data (learning information) containing information about increases in blood glucose levels due to meals. By inputting personal data (estimation information) containing information about increases in blood glucose levels due to the user's meals into this obesity index estimation model 132, it is possible to estimate a body fat percentage (obesity index) that represents the user's obesity level. Here, the body fat percentage to be estimated refers to the body fat percentage (predicted body fat percentage) a predetermined time (e.g., 48 hours) has passed since the user finished their meal. The reason the body fat percentage to be estimated is the body fat percentage a predetermined time (e.g., 48 hours) has passed since the user finished their meal is because carbohydrates and lipids stored in the liver are accumulated as body fat a predetermined time (e.g., 48 hours) has passed since the user finished their meal.

The communication unit 14 performs communication operations in accordance with a predetermined communication standard. Through this communication operation, the communication unit 14 sends and receives information to and from the terminal device 20 via the network N. The network N is, for example, the Internet, but is not limited to this.

FIG. 3 is a block diagram showing the functional configuration of the terminal device 20. As shown in FIG.
3 , the terminal device 20 includes a CPU 21, a RAM 22, a storage unit 23, a display unit 24, an operation unit 25, a communication unit 26, a bus 27, etc. The components of the terminal device 20 are connected via the bus 27. The terminal device 20 is a device that is primarily carried and used by a user, such as a smartphone. Note that the terminal device 20 is not limited to a smartphone, and may be, for example, a tablet terminal or a notebook PC, or a stationary terminal such as a desktop PC.

The CPU 21 is a processor that controls the operation of each part of the terminal device 20 by reading and executing programs such as the obesity risk assessment app 231 stored in the memory unit 23 and performing various arithmetic processing. The terminal device 20 may have multiple processors (e.g., multiple CPUs), and the multiple processes performed by the CPU 21 of this embodiment may be executed by these multiple processors. In this case, the multiple processors may be involved in a common process, or the multiple processors may independently execute different processes in parallel.

RAM 22 provides working memory space for the CPU 21 and stores temporary data.

The memory unit 23 is a non-transitory recording medium readable by the CPU 21 as a computer, and stores various data and programs such as an obesity risk assessment app 231 for providing users with a service that assesses the obesity risk caused by the user's diet. The memory unit 23 includes non-volatile memory such as flash memory. The program is stored in the memory unit 23 in the form of computer-readable program code.

Under the control of the CPU 21, the display unit 24 displays the operation screen of the obesity risk assessment app 231 and information such as the predicted results of the user's obesity risk received from the server 10. The display unit 24 may be, for example, a liquid crystal display device that displays using a dot matrix method, but is not limited to this.

The operation unit 25 accepts input operations from the user and outputs an input signal corresponding to the input operation to the CPU 21. The operation unit 25 has a touch panel overlaid on the display screen of the display unit 24, and detects contact with the user's finger or the like as an input operation using this touch panel. The operation unit 25 may also have hardware buttons in addition to or instead of the touch panel, and may be able to accept input operations using these hardware buttons.

The communication unit 26 performs communication operations in accordance with a predetermined communication standard. Through this communication operation, the communication unit 26 sends and receives information to and from the server 10 via the network N. The communication unit 26 also sends and receives information to and from the wearable device 30 via wireless communication (in this embodiment, Bluetooth (registered trademark) as short-range wireless communication).

FIG. 4 is a block diagram showing the functional configuration of the wearable device 30.
4, the wearable device 30 includes a CPU 31, a RAM 32, a storage unit 33, a blood glucose sensor 34, a motion sensor 35, a communication unit 36, and a bus 37. The components of the wearable device 30 are connected to each other via the bus 37. The wearable device 30 is a wrist terminal (wearable terminal) that is worn on the user's body (for example, on the wrist), and is, for example, a smart watch.

The CPU 31 is a processor that controls the operation of each part of the wearable device 30 by reading and executing the program 331 stored in the memory unit 33 and performing various arithmetic processing. The wearable device 30 may have multiple processors (e.g., multiple CPUs), and the multiple processes performed by the CPU 31 of this embodiment may be executed by these multiple processors. In this case, the multiple processors may be involved in a common process, or the multiple processors may independently execute different processes in parallel.

RAM 32 provides working memory space for CPU 31 and stores temporary data.

The memory unit 33 is a non-transitory recording medium readable by the CPU 31 as a computer, and stores the program 331 and various data (for example, a personal DB (database) 332). The memory unit 33 includes a non-volatile memory such as a flash memory. The program 331 is stored in the memory unit 33 in the form of computer-readable program code. The personal DB 332 records basic personal data of the user, such as age, gender, height, weight, and body fat percentage, as well as blood glucose level data and exercise amount data of the user.

The blood glucose sensor 34 is a non-invasive sensor that measures blood glucose levels using, for example, a high-intensity mid-infrared laser. The blood glucose sensor 34 measures blood glucose levels at a predetermined sampling frequency via the wrist of a user wearing the wearable device 30, and outputs blood glucose level data as the measurement result to the CPU 31. The blood glucose level data output to the CPU 31 is associated with the measurement time and recorded in the personal DB 332 of the memory unit 33 under the control of the CPU 31.

The motion sensor 35 includes, for example, a triaxial acceleration sensor, a triaxial gyro sensor, and a triaxial geomagnetic sensor as sensors for detecting the motion state of the wearable device 30. The triaxial acceleration sensor detects acceleration in each axial direction applied to the wearable device 30 in response to the user's motion at a predetermined sampling frequency and outputs acceleration data as the detection result to the CPU 31. The triaxial gyro sensor detects angular velocities around each axis applied to the wearable device 30 in response to the user's motion at a predetermined sampling frequency and outputs angular velocity data as the detection result to the CPU 31. The triaxial geomagnetic sensor detects the direction of the geomagnetism passing through the wearable device 30 at a predetermined sampling frequency and outputs geomagnetic data as the detection result to the CPU 31. The data output from the triaxial acceleration sensor, the triaxial gyro sensor, and the triaxial geomagnetic sensor include signal components for three mutually orthogonal axes. The motion sensor 35 includes an amplifier (not shown) that amplifies analog signals output from the three-axis acceleration sensor, the three-axis gyro sensor, and the three-axis geomagnetic sensor, and an AD converter (not shown) that converts the amplified analog signals into digital data and outputs the digital data to the CPU 31. The CPU 31 calculates the amount of exercise performed by the user based on the acceleration data, angular velocity data, and geomagnetic data input from the motion sensor 35, as well as basic vital information of the user recorded in the vital DB 332, and records the calculated exercise amount data in the personal DB 332 of the storage unit 33 in association with time. Here, the amount of exercise refers to the total calories burned (kcal) that is the sum of the user's basal metabolic rate and the calories burned through the user's exercise.
The motion sensor 35 may be any sensor capable of detecting the motion state of the wearable device 30, and is not limited to a configuration including a three-axis acceleration sensor, a three-axis gyro sensor, and a three-axis geomagnetic sensor.

The communication unit 36 performs communication operations in accordance with a predetermined communication standard. Through this communication operation, the communication unit 36 transmits and receives data (e.g., blood glucose level data and exercise amount data) to and from the terminal device 20 via wireless communication (in this embodiment, Bluetooth as short-range wireless communication).

<Operation of the Obesity Risk Assessment System>
Next, the operation of the obesity risk assessment system 1 will be described.

(Learning process)
As an operation of the obesity risk assessment system 1, first, a control procedure of a learning process for machine learning the obesity index estimation model 132 will be described with reference to the flowchart of FIG.
FIG. 5 is a flowchart showing the control procedure for the learning process. The learning process is executed by the CPU 11 of the server 10. However, this is not limited to this, and the learning process may also be executed by an information processing device external to the server 10. To execute this learning process, personal data acquired from each of a large number of users is prepared in advance and stored in the storage unit 13 as data for machine learning. This personal data includes basic personal data for each user, such as age, gender, height, weight, and body fat percentage, as well as blood glucose level data and postprandial activity data for the user. Furthermore, the personal data is acquired from the wearable device 30 worn by each of the large number of users, similar to the users who are the prediction targets for the obesity risk prediction process described below. The basic personal data, such as age, gender, height, weight, and body fat percentage, are assumed to be data registered by the user immediately before the meal for which blood glucose level data is to be sampled. The blood glucose level data is assumed to be blood glucose level data sampled at least from immediately before the meal until a predetermined time (e.g., two hours) has elapsed since the end of the meal. For example, a user may wear the wearable device 30 immediately before a meal and continue to wear the wearable device 30 for a predetermined time (e.g., 48 hours) after finishing the meal, thereby acquiring blood glucose level data and postprandial activity data. The timing immediately before a meal is determined by the CPU 31 based on the user's input operation on the wearable device 30. However, the CPU 31 may also determine the timing immediately before the meal based on, for example, the timing of a rise in blood glucose level due to a meal. The postprandial activity data is exercise amount data indicating the amount of exercise related to the period from the end of the meal for which blood glucose level data is to be sampled until the predetermined time (e.g., 48 hours) has elapsed. Furthermore, this personal data is accompanied by training data, such as the subject's body fat percentage (obesity index) measured a predetermined time (e.g., 48 hours) after finishing the meal. Here, the time when the subject has finished eating is determined by the CPU 31 based on the subject's input operation on the wearable device 30. However, for example, based on the blood glucose level data, the CPU 31 may determine that the subject has finished eating two hours before the blood glucose level, which has risen due to eating, drops back to a fasting value (e.g., 70 to 110 mg/dL). Note that in the learning process of this embodiment, personal data is acquired from each of a large number of users as data for machine learning, but the large number of users does not include users who are the targets of prediction in the obesity risk prediction process described below.

When the learning process begins, the CPU 11 acquires personal data for a target from the memory unit 13 (step S1).

Next, the CPU 11 extracts information about the rise in blood glucose level due to meals as feature quantities based on the blood glucose level data included in the personal data acquired in step S1 (step S2). Specifically, as shown in FIG. 6, a graph plotting blood glucose level data over time (a graph showing blood glucose level changes over 10 hours before and after a single meal) captures an ascending curve where the blood glucose level exceeds a predetermined threshold (e.g., 140 mg/dL). The CPU 11 then extracts the following features: the date and time (DateTime) when the ascending curve begins (i.e., when sugar enters the bloodstream through a meal), the maximum slope (Slope) of the ascending curve, the peak value (Peak) of the ascending curve, and the time (Period) from when the blood glucose level exceeds the threshold to when it falls below the threshold. Specifically, the point in time when the blood glucose level increases by more than a predetermined value relative to a certain reference value (e.g., 100 mg/dL (normal fasting blood glucose level)) is extracted as the date and time when the ascending curve begins. The slope of the tangent to the ascending curve at the point where the slope (rate of change) of the tangent is maximum is extracted as the maximum slope of the ascending curve. The blood glucose level at the point where the blood glucose level reaches its maximum on the ascending curve is extracted as the peak value of the ascending curve. This information is extracted as features because, although it takes approximately two hours for blood glucose levels to converge after a meal, the maximum slope of the ascending curve, the peak value of the ascending curve, and the time it takes for the blood glucose level to exceed a specified value and fall below it all vary significantly depending on the amount and quality of the meal. According to the general mechanism of obesity, the above features (Slope, Peak, Period) tend to accumulate more fat as their values increase, making them key features that increase the risk of obesity.

Next, the CPU 11 acquires learning data including the feature values extracted in step S2 (step S3). Specifically, the CPU 11 acquires, as learning data, information about the rise in blood glucose levels due to meals, which is the feature value, i.e., the date and time (DateTime) when the blood glucose level rise curve began, the maximum slope (Slope) of the rise curve, the peak value (Peak) of the rise curve, and the time (Period) from when the blood glucose level exceeded a specified value until it fell below the specified value, as well as basic personal data (age, sex, height, weight, and body fat percentage) from the personal data acquired in step S1, post-meal exercise data, and training data.

Next, the CPU 11 performs machine learning on the obesity index estimation model 132 using the training data acquired in step S3 (step S4). Specifically, the CPU 11 updates the weighting coefficients and bias values of the obesity index estimation model 132 using the backpropagation method so that the value (body fat percentage) output from the obesity index estimation model 132 when the acquired training data is input to the obesity index estimation model 132 approaches the value of the training data included in the training data.

Next, the CPU 11 determines whether the series of processes from step S1 to step S4 has been repeated a predetermined number of times (step S5). The predetermined number of times is the number of times equal to the number of pieces of personal data, which is data for machine learning, that are pre-stored in the memory unit 13.

If it is determined in step S5 that the series of processes from step S1 to step S4 have not been repeated the predetermined number of times (step S5; NO), the CPU 11 returns the process to step S1 and repeats the subsequent processes. Note that when returning the process to step S and acquiring personal data for a single target, personal data for a target different from the target related to the personal data acquired up to that point is acquired, i.e., personal data is acquired so as not to overlap with the target.

Furthermore, in step S5, if it is determined that the series of processes from step S1 to step S4 has been repeated a predetermined number of times (step S5; YES), the CPU 11 ends the learning process. Through the above learning process, an obesity index estimation model 132 (trained model) is generated.

(Obesity risk prediction processing)
Next, the control procedure of the obesity risk prediction process will be described with reference to the flowchart of FIG.
FIG. 7 is a flowchart showing the control procedure for the obesity risk prediction process. The obesity risk prediction process is executed by the CPU 11 of the server 10. The obesity risk prediction process is initiated when a user inputs an instruction to display the predicted results of diet-related obesity risk on the obesity risk assessment app 231 of the terminal device 20. The instruction to display the predicted results of diet-related obesity risk is assumed to be issued at a predetermined time each day (e.g., 6:00 AM). The user whose obesity risk is predicted is assumed to be not included in the large number of users who provided personal data in the learning process described above. It is assumed that, when the obesity risk prediction process is executed, the user's personal data has been transferred from the wearable device 30 to the terminal device 20 in advance. When the above instruction is input, the personal data is transmitted from the terminal device 20 to the server 10. The personal data includes basic personal data of the user, such as age, gender, height, weight, and body fat percentage, as well as blood glucose level data and postprandial activity data of the user. The basic personal data, age and gender, are data registered immediately before the meal for which the user's blood glucose level data is to be sampled. The height, weight, and body fat percentage are composed of data measured immediately before the meal for which the user's blood glucose level data is sampled and data measured a predetermined time (e.g., 48 hours) after the end of the meal. The blood glucose level data is blood glucose level data sampled at least from immediately before the meal until a predetermined time (e.g., 2 hours) has elapsed since the end of the meal. Here, the timing immediately before the meal is determined by the CPU 31 based on the user's input operation on the wearable device 30. However, the CPU 31 may also determine the timing immediately before the meal based on, for example, the timing of the rise in blood glucose level due to the meal. The postprandial activity amount data is exercise amount data indicating the amount of exercise related to the period from the end of the meal for which the blood glucose level data is sampled until a predetermined time (e.g., 48 hours) has elapsed. In other words, the personal data is data acquired (generated) each time the user eats (a meal for which blood glucose level data is sampled), and the estimation information acquired in step S13 (described later) is also information acquired each time the user eats.

When the obesity risk prediction process begins, the CPU 11 acquires (receives) the user's personal data transmitted from the terminal device 20 (step S11).

Next, the CPU 11 extracts, as feature quantities, information related to the rise in blood glucose level caused by the user's meals, based on the blood glucose level data included in the personal data acquired in step S11 (step S12). Specifically, similar to step S2 of the learning process described above, the CPU 11 extracts, as feature quantities, the date and time (DateTime) when the rise in the user's blood glucose level curve began, the maximum slope (Slope) of the rise curve, the peak value (Peak) of the rise curve, and the time (Period) from when the blood glucose level exceeded a specified value until it fell below the specified value.

Next, the CPU 11 acquires estimation information including the feature values extracted in step S12 (step S13). Specifically, the CPU 11 acquires information related to the rise in blood glucose levels due to the meal, which is the feature value, i.e., the date and time (DateTime) when the blood glucose level rise curve began, the maximum slope (Slope) of the rise curve, the peak value (Peak) of the rise curve, and the time (Period) from when the blood glucose level exceeded a specified value until it fell below the specified value. In addition, the CPU 11 acquires, as estimation information, basic personal data (age, gender, height, weight, and body fat percentage) from the user's personal data acquired in step S11 and postprandial exercise amount data. Here, the postprandial exercise amount data is exercise amount data indicating the amount of exercise during a predetermined period (e.g., 48 hours) from the time the meal ended.

Next, the CPU 11 inputs the estimation information acquired in step S13 into the obesity index estimation model 132, and causes the obesity index estimation model 132 to estimate and acquire the body fat percentage (predicted body fat percentage), which is an obesity index (step S14).

Next, CPU 11 predicts the user's diet-related obesity risk based on the body fat percentage (predicted body fat percentage), which is the obesity index estimated by obesity index estimation model 132 in step S14 (step S15). Specifically, CPU 11 derives the user's diet-related obesity risk (= predicted body fat percentage / current body fat percentage) by dividing the body fat percentage estimated in step S14 (predicted body fat percentage) by the body fat percentage (current body fat percentage) measured before the target meal) acquired as estimation information in step S13. Then, CPU 11 predicts that the body fat percentage is on an increasing trend if the derived obesity risk value exceeds a second predetermined value (e.g., 1.05). Furthermore, CPU 11 predicts that the body fat percentage is on a maintaining trend if the derived obesity risk value is within a predetermined range defined by a first predetermined value (e.g., 0.95) and a second predetermined value (e.g., 1.05). Furthermore, for example, if the derived obesity risk value is below a first predetermined value, the CPU 11 predicts that the body fat percentage is on a decreasing trend.

Next, the CPU 11 transmits information about the predicted results of the obesity risk due to the user's diet to the terminal device 20, and causes the terminal device 20 to present the predicted results of the obesity risk to the user on the display unit 24 (step S16), and ends the obesity risk prediction process.

As described above, in the information processing method according to this embodiment, the CPU 11 of the server 10 inputs estimation information (personal data) including information regarding an increase in blood glucose level due to a meal of the user (target user) into the obesity index estimation model 132 that has been machine-learned based on learning data (learning information) including information regarding an increase in blood glucose level due to a meal (step S13 in FIG. 7), thereby estimating an obesity index (body fat percentage) representing the obesity level of the user (step S14 in FIG. 7), and predicting the user's risk of obesity based on the estimated obesity index (step S15 in FIG. 7).
Therefore, the information processing method according to this embodiment can reveal the risk of obesity caused by the user's diet, which can encourage the user to understand and reflect on their diet, and ultimately enable dietary control that suits the user's characteristics.

Furthermore, the obesity index estimation model 132 is machine-trained using as training data the body fat percentage (obesity index) measured a predetermined time after a subject finishes eating. This allows the learning accuracy of the obesity index estimation model 132 to be improved by using as a training model the body fat percentage measured a predetermined time after a subject finishes eating, i.e., at the time when carbohydrates and lipids stored in the liver are accumulated as body fat. As a result, the obesity index estimation model 132 can more accurately estimate the user's body fat percentage (predicted body fat percentage).

In addition, information regarding increases in blood glucose levels due to meals is information obtained from blood glucose level data. This makes it possible to machine-learn the obesity index estimation model 132 using this highly reliable information. As a result, the obesity index estimation model 132 can more accurately estimate the user's body fat percentage (predicted body fat percentage).

In addition, since the estimation information is information obtained each time the user eats, the user's body fat percentage (predicted body fat percentage) can be estimated each time the user eats.

In addition, the information regarding the rise in blood glucose levels due to meals includes the maximum slope of the blood glucose level rise curve, the peak value of the rise curve, and the time it takes for the blood glucose level to fall below a specified value after exceeding it. Therefore, the obesity index estimation model 132 can be machine-learned using the above information, which is closely related to the accumulation of body fat due to excessive insulin secretion. As a result, the obesity index estimation model 132 can more accurately estimate the user's body fat percentage (predicted body fat percentage).

The learning data also includes postprandial exercise data, which indicates the amount of exercise of the subject for which information regarding a rise in blood glucose level due to a meal is measured, and indicates the amount of exercise during a predetermined period from the time the subject finishes the meal, and the estimation information includes the user's postprandial exercise data. This makes it possible to estimate the user's body fat percentage (predicted body fat percentage) by taking into account the user's amount of exercise during the period during which exercise can prevent the carbohydrates and lipids stored in the liver from converting to fat. As a result, the obesity index estimation model 132 can more accurately estimate the user's body fat percentage (predicted body fat percentage).

In addition, the information processing method according to this embodiment predicts the obesity risk of a user based on a parameter representing the ratio (relationship) between the body fat percentage (predicted body fat percentage) estimated based on the estimation information and the body fat percentage measured before the user's target meal, which is included in the estimation information.
Therefore, according to the information processing method of this embodiment, the user's predicted body fat percentage is compared with the body fat percentage measured before the target meal to predict the user's risk of obesity, thereby enabling the obesity risk to be predicted accurately.

Although the present invention has been specifically described above based on the embodiments, the present invention is not limited to the above embodiments and can be modified within the scope of the invention.
For example, in the above embodiment, the obesity risk is predicted based on a single meal of the user, but the obesity risk may also be predicted based on all meals taken over any period, such as daily or weekly.

Furthermore, in the above embodiment, information regarding a rise in blood glucose level due to a meal is extracted from blood glucose level data, but this information may also be extracted from biometric data (e.g., bioimpedance) that is correlated with blood glucose level data.

In the above embodiment, the user's risk of obesity is predicted based on a parameter representing the ratio between the body fat percentage (predicted body fat percentage) estimated based on the estimation information and the body fat percentage measured before the user's target meal, which is included in the estimation information. However, the user's risk of obesity may also be predicted based on a parameter representing the difference between the body fat percentage (predicted body fat percentage) estimated based on the estimation information and the body fat percentage measured before the user's target meal, which is included in the estimation information. Specifically, the user's risk of obesity due to the meal (= predicted body fat percentage - current body fat percentage) is derived by subtracting the body fat percentage measured before the target meal (current body fat percentage) from the predicted body fat percentage. For example, if the derived obesity risk value exceeds a second predetermined value (e.g., 0.05), the body fat percentage is predicted to be increasing. Furthermore, if the derived obesity risk value is within the range of a first predetermined value (e.g., -0.05) to a second predetermined value (e.g., +0.05), the body fat percentage is predicted to be maintaining its original value. Furthermore, for example, if the derived obesity risk value is below a first predetermined value, it is predicted that the body fat percentage is on a decreasing trend.

In addition, in the above embodiment, body fat percentage is used as an obesity index representing the user's obesity level, but for example, BMI (Body Mass Index) may also be used. In such cases, the personal data includes BMI instead of body fat percentage.

In addition, in the above embodiment, information regarding the rise in blood glucose levels due to the meal is extracted from blood glucose level data measured when the user actually eats, and the body fat percentage (predicted body fat percentage) is estimated based on estimation information including this information to predict the risk of obesity. However, for example, blood glucose level data for each meal menu when that meal is eaten may be linked and prepared, and when the user selects a desired meal menu, information regarding the rise in blood glucose levels due to eating that meal menu may be extracted from the blood glucose level data corresponding to that meal menu, and the body fat percentage (predicted body fat percentage) may be estimated based on estimation information including this information to predict the risk of obesity. This allows the user to select a meal menu while taking the risk of obesity into consideration.

In addition, in the above embodiment, the obesity risk prediction results are presented to the user via the terminal device 20. However, for example, the obesity risk prediction results and associated information may be compiled for a certain period of time, such as one day, one week, or one month, and the information may be presented in a bird's-eye view by graphing, illustrating, or arranging in a matrix. This makes it possible to discover patterns by time, day of the week, month, etc., and supports dietary improvements from a long-term perspective.

Furthermore, in the above embodiment, the processing (e.g., obesity risk prediction processing) performed by the server 10 as an information processing device may be executed by the terminal device 20. In this case, the terminal device 20 corresponds to the information processing device, and the CPU 21 of the terminal device 20 corresponds to the processing unit.
Furthermore, in the above embodiment, the processing (e.g., obesity risk prediction processing) performed by the server 10 as an information processing device may be executed by the wearable device 30. In this case, the wearable device 30 corresponds to the information processing device, and the CPU 31 of the wearable device 30 corresponds to the processing unit.

The terminal device 20 and the wearable device 30 may also be integrated. For example, if the wearable device 30 is capable of performing the functions performed by the terminal device 20 in the above embodiment, the terminal device 20 may be omitted.

Furthermore, the obesity index estimation model 132 stored in the memory unit 13 may be stored in an external storage device provided outside the server 10. In this case, the CPU 11 simply acquires the output of the obesity index estimation model 132 from the external storage device.

In addition, while the above-described embodiment discloses an example in which storage units 13, 23, and 33 are used as computer-readable media for the program of the present invention, this is not a limitation. Other computer-readable media may include information recording media such as HDDs, SSDs, flash memory, and CD-ROMs. Furthermore, carrier waves may also be used as a medium for providing program data of the present invention via a communication line.

Although the embodiments of the present invention have been described, the scope of the present invention is not limited to the above-described embodiments, but includes the scope of the invention described in the claims and its equivalents.
The inventions described in the claims originally attached to this application are as follows. The claim numbers described in the appendix are the same as those of the claims originally attached to this application.
[Note]
<Claim 1>
A processing unit of the information processing device
an obesity index representing the obesity level of the target user is estimated by inputting estimation information including information about an increase in blood glucose level caused by a meal into an obesity index estimation model that has been machine-learned based on learning information including information about an increase in blood glucose level caused by a meal;
predicting the target user's risk of obesity based on the estimated obesity index;
1. An information processing method comprising:
<Claim 2>
The obesity index estimation model is machine-learned using as training data an obesity index actually measured when a predetermined time has elapsed since a certain subject finished eating.
2. The information processing method according to claim 1,
<Claim 3>
The information regarding the increase in blood glucose level due to the meal is information obtained from blood glucose level data or biological data correlated with the blood glucose level data.
3. The information processing method according to claim 1 or 2.
<Claim 4>
The estimation information is information acquired each time the target user eats a meal.
4. The information processing method according to claim 1, wherein:
<Claim 5>
The information regarding the rise in blood glucose level due to the meal includes information regarding the maximum slope indicating the gradient of the tangent line at the point where the gradient of the tangent line of the blood glucose level rise curve is maximum, the peak value of the rise curve, and the time from when the blood glucose level exceeds a specified value until when the blood glucose level falls below the specified value.
5. The information processing method according to claim 1, wherein the first and second information processing units are connected to each other.
<Claim 6>
the learning information includes exercise amount data indicating an exercise amount of the subject for whom information regarding the increase in blood glucose level due to the meal is measured, the exercise amount being related to a period from the time the subject finished the meal until a predetermined time has elapsed;
The estimation information includes the activity amount data of the target user.
6. The information processing method according to claim 1, wherein:
<Claim 7>
the information for estimation includes the target user's current obesity index,
predicting an obesity risk of the target user based on a parameter representing a relationship between the obesity index estimated based on the information for estimation and the current obesity index of the target user included in the information for estimation;
7. The information processing method according to claim 1, wherein:
<Claim 8>
The obesity index is body fat percentage or BMI (Body Mass Index),
8. The information processing method according to claim 1, wherein:
<Claim 9>
an obesity index representing the obesity level of the target user is estimated by inputting estimation information including information about an increase in blood glucose level caused by a meal into an obesity index estimation model that has been machine-learned based on learning information including information about an increase in blood glucose level caused by a meal;
predicting the target user's risk of obesity based on the estimated obesity index;
An information processing device comprising a processing unit.
<Claim 10>
The computer of the information processing device
A process of estimating an obesity index representing the obesity level of a target user by inputting estimation information including information about an increase in blood glucose level caused by a meal of the target user into an obesity index estimation model machine-learned based on learning information including information about an increase in blood glucose level caused by a meal;
predicting the target user's risk of obesity based on the estimated obesity index;
A program characterized by executing the following.
<Claim 11>
An information processing system in which an information processing device and a terminal device are communicatively connected to each other,
The information processing device includes:
an obesity index representing the obesity level of the target user is estimated by inputting, via the terminal device, estimation information including information about an increase in blood glucose level caused by the target user's diet into an obesity index estimation model that has been machine-learned based on learning information including information about an increase in blood glucose level caused by diet;
predicting the target user's risk of obesity based on the estimated obesity index;
a processing unit;
The terminal device
obtaining a result of the prediction of the target user's obesity risk;
Displaying the result on a display unit.
An information processing system comprising a processing unit.

1 Obesity risk assessment system 10 Server (information processing device)
11 CPU (processing unit)
12 RAM
13 Storage unit 131 Program 132 Obesity index estimation model 14 Communication unit 15 Bus 20 Terminal device 21 CPU
22 RAM
23 Memory unit 231 Obesity risk assessment application 24 Display unit 25 Operation unit 26 Communication unit 27 Bus 30 Wearable device (wearable terminal)
31 CPU
32 RAM
33 Storage unit 331 Program 332 Vital DB
34 Blood glucose sensor 35 Motion sensor 36 Communication unit 37 Bus N Network

Claims (11)

A processing unit of the information processing device
an obesity index representing the obesity level of the target user is estimated by inputting estimation information including information about an increase in blood glucose level caused by a meal into an obesity index estimation model machine-learned based on learning information including information about an increase in blood glucose level caused by a meal;
predicting the target user's risk of obesity based on the estimated obesity index;
1. An information processing method comprising: The obesity index estimation model is machine-learned using as training data an obesity index actually measured when a predetermined time has elapsed since a certain subject finished eating.
2. The information processing method according to claim 1, The information regarding the increase in blood glucose level due to the meal is information obtained from blood glucose level data or biological data correlated with the blood glucose level data.
3. The information processing method according to claim 1 or 2. The estimation information is information acquired each time the target user eats a meal.
4. The information processing method according to claim 1, wherein: The information regarding the rise in blood glucose level due to the meal includes information regarding the maximum slope indicating the gradient of the tangent line at the point where the gradient of the tangent line of the blood glucose level rise curve is maximum, the peak value of the rise curve, and the time from when the blood glucose level exceeds a specified value until when the blood glucose level falls below the specified value.
5. The information processing method according to claim 1, wherein: the learning information includes exercise amount data indicating an exercise amount of the subject for whom information regarding the increase in blood glucose level due to the meal is measured, the exercise amount being related to a period from the time the subject finished the meal until a predetermined time has elapsed;
The estimation information includes the activity amount data of the target user.
6. The information processing method according to claim 1, wherein: the information for estimation includes the target user's current obesity index,
predicting an obesity risk of the target user based on a parameter representing a relationship between the obesity index estimated based on the information for estimation and the current obesity index of the target user included in the information for estimation;
7. The information processing method according to claim 1, wherein: The obesity index is body fat percentage or BMI (Body Mass Index),
8. The information processing method according to claim 1, wherein: an obesity index representing the obesity level of the target user is estimated by inputting estimation information including information about an increase in blood glucose level caused by a meal into an obesity index estimation model machine-learned based on learning information including information about an increase in blood glucose level caused by a meal;
predicting the target user's risk of obesity based on the estimated obesity index;
An information processing device comprising a processing unit. The computer of the information processing device
a process of estimating an obesity index representing the obesity level of the target user by inputting estimation information including information about an increase in blood glucose level caused by the target user's diet into an obesity index estimation model machine-learned based on learning information including information about an increase in blood glucose level caused by the diet;
predicting the target user's risk of obesity based on the estimated obesity index;
A program characterized by executing the following. An information processing system in which an information processing device and a terminal device are communicatively connected to each other,
The information processing device includes:
an obesity index representing the obesity level of the target user is estimated by inputting, via the terminal device, estimation information including information about an increase in blood glucose level caused by the target user's diet into an obesity index estimation model that has been machine-learned based on learning information including information about an increase in blood glucose level caused by diet;
predicting the target user's risk of obesity based on the estimated obesity index;
a processing unit;
The terminal device
obtaining a result of the prediction of the target user's obesity risk;
Displaying the result on a display unit.
An information processing system comprising a processing unit.