Processing system, processing method, and program

Abstract

To provide a processing system, a processing method, and a program capable of performing presentation for suppressing variation in a blood-sugar level.SOLUTION: A processing system 100 includes: a meal data acquisition section 101 for acquiring meal data regarding a meal that a user takes; an exercise data acquisition section 102 for acquiring exercise data regarding a user's exercise; a prediction section 103 for generating prediction data obtained by predicting a variation in a user's blood-sugar level from meal data and exercise data; and a presentation section 105 for presenting meal time on the basis of prediction data.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a processing system, a processing method, and a program.

Background Art

[0002] Patent Document 1 discloses an apparatus that receives an input of an event (medical actions such as meals and medications) given to a subject (patient) and predicts a blood glucose level. When the input event affects the blood glucose level, this apparatus outputs, as an alert, a message prompting a change in the menu or amount of a meal or candidates for alternative menus. has an impact on

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above apparatus, since the blood glucose level is predicted from the patient's meals and medical actions (medications), it is difficult to predict accurately. Since only the amount and menu of meals are proposed, meals cannot be taken at appropriate times. Therefore, there is a risk that fluctuations in blood glucose levels will increase.

[0005] The present disclosure has been made to solve such problems, and provides a processing system, a processing method, and a program that can present suppression of fluctuations in blood glucose levels.

Means for Solving the Problems

[0006] The processing system in this embodiment includes a dietary data acquisition unit that acquires dietary data regarding the meals consumed by the user, a motion data acquisition unit that acquires motion data regarding the user's exercise, a prediction unit that generates prediction data predicting fluctuations in the user's blood glucose level from the dietary data and the motion data, and a presentation unit that presents meal times based on the prediction data.

[0007] In the above processing system, the presentation unit may present a meal menu based on the prediction data.

[0008] In the above processing system, the presentation unit may present exercise time and exercise content based on the prediction data.

[0009] The above processing system may further include a schedule information acquisition unit that acquires schedule information indicating the user's meal schedule, acquire future dietary data based on the schedule information, and predict the blood glucose level based on the future dietary data.

[0010] In the above processing system, schedule information indicating the user's schedule may be acquired, and an additional plan to be added to the free time in the schedule information may be presented based on the prediction data.

[0011] In the above processing system, schedule information indicating the user's schedule may be acquired, and the schedule may be adjusted based on the prediction data. In the above processing system, the user information of the user may be acquired, and the blood glucose level may be predicted using a prediction model personalized according to the user information.

[0012] The processing method in this embodiment uses at least one processor to obtain dietary data regarding the meals consumed by the user, obtain exercise data regarding the user's exercise, generate prediction data for predicting fluctuations in the user's blood glucose level from the dietary data and the exercise data, and present a meal time based on the prediction data.

[0013] In the above processing method, a meal menu may be presented based on the prediction data.

[0014] In the above processing method, an exercise time and exercise content may be presented based on the prediction data.

[0015] In the above processing method, schedule information indicating the user's meal schedule may be obtained, future dietary data may be obtained based on the schedule information, and the blood glucose level may be predicted based on the future dietary data.

[0016] In the above processing method, schedule information indicating the user's schedule may be obtained, and an additional plan to be added to the free time in the schedule information may be presented based on the prediction data.

[0017] In the above processing method, schedule information indicating the user's schedule may be obtained, and the schedule may be adjusted based on the prediction data.

[0018] In the above processing method, the user's user information may be obtained, and the blood glucose level may be predicted using a personalized prediction model according to the user information.

[0019] The program in this embodiment causes a computer to execute steps of acquiring meal data regarding meals consumed by a user, acquiring exercise data regarding the user's exercise, generating prediction data predicting fluctuations in the user's blood glucose level from the meal data and the exercise data, and presenting a meal time based on the prediction data.

Advantages of the Invention

[0020] According to the present disclosure, it is possible to provide a processing system, a processing method, and a program that can perform a presentation for suppressing fluctuations in blood glucose level.

Brief Description of the Drawings

[0021]

Figure 1

Figure 2

Figure 3

Figure 4

Modes for Carrying Out the Invention

[0022] Hereinafter, the present invention will be described through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. Also, not all of the configurations described in the embodiments are necessarily essential as means for solving the problems.

[0023] A processing system according to this embodiment and its processing method will be described with reference to the drawings. FIG. 1 is a block diagram showing the configuration of a processing system 100. The processing system 100 includes a meal data acquisition unit 101, an exercise data acquisition unit 102, a prediction unit 103, and a presentation unit 105. Further, the processing system 100 may include a user data acquisition unit 111 and a schedule information acquisition unit 112.

[0024] The processing system 100 can be implemented by one or or a plurality of computers or the like. The processing system 100 is typically an information processing device such as a personal computer or a smartphone. Specifically, the processing system 100 includes a memory for storing programs and the like, and a processor for executing programs. The processing system 100 may have a plurality of processors for performing distributed processing. For example, a server device and a user terminal connected by a network may cooperate to perform processing.

[0025] The meal data acquisition unit 101 acquires meal data regarding the meals consumed by the user. The meal data acquisition unit 101 records the meal data in a memory or the like. The meal data is data indicating a meal menu and meal time. The meal data acquisition unit 101 acquires data regarding nutrients, ingredients, foodstuffs, etc. from the meal menu consumed by the user. The meal data preferably includes the amount of sugar. The meal data includes data not limited to breakfast, lunch, and dinner, but also includes data such as snacks and midnight snacks.

[0026] For example, the meal data may include data indicating the foodstuffs of the meal and their amounts. Alternatively, the meal data may include information such as calories, sugar, salt, lipids, vitamins, carbohydrates, etc. The meal data acquisition unit 101 acquires data on the intake amounts of each nutrient. Further, the meal data includes data on the meal time when the user had a meal. The meal data acquisition unit 101 stores the time-series meal data in the database 106. The meal data is is data in which each nutrient, meal menu, etc. are associated with the meal time.

[0027] The meal data can be acquired from image data obtained by imaging the user's meal. The meal data acquisition unit 101 may acquire the meal data using a sensor for detecting the meal data. The meal data acquisition unit 101 acquires the meal data from the detection result of the sensor. Alternatively, the user or the like inputs the meal menu consumed at, the meal data acquisition unit 101 may acquire meal data.

[0028] The exercise data acquisition unit 102 acquires exercise data related to the user's exercise. The exercise data is data indicating the exercise menu and exercise time that the user has performed. For example, exercises include walking, jogging, cycling, pedaling exercise on a rowing machine, etc. is mentioned . The exercise data may include data such as heart rate and exercise amount. The exercise data includes data indicating exercise time such as exercise start time and exercise end time.

[0029] By inputting the exercise performed by the user, the exercise data acquisition unit 102 may acquire exercise data. Alternatively, using a wearable device such as a smartwatch, the exercise data acquisition unit 102 may detect the exercise. Alternatively, using a camera to detect the user's exercise is fine That is, the exercise data acquisition unit 102 may use a sensor for detecting exercise. The exercise data acquisition unit 102 obtains data from the detection result of the sensor. exercise The exercise data acquisition unit 102 records time-series exercise data in a database 106 or the like. The exercise data is data in which the exercise amount, exercise menu, etc. are associated with the exercise time.

[0030] The prediction unit 103 predicts the fluctuation of the user's blood glucose level based on the exercise data and meal data, and generates prediction data. The prediction unit 103 predicts the fluctuation of the user's blood glucose level. For example, when the user ingests food, the blood glucose level increases. Also, after a meal, as time passes, the blood glucose level gradually decreases. Furthermore, when the user exercises, the increase in blood glucose level is suppressed or the decrease in blood glucose level is promoted. The prediction unit 103 may use a machine learning model for predicting the fluctuation of blood glucose level. That is, the prediction unit 103 can use a machine learning model that takes meal data and exercise data as input data. When new meal data and exercise data are input, the prediction unit 103 generates prediction data indicating the future fluctuation of blood glucose level.

[0031] The prompting unit 105 prompts the user of the meal time based on the prediction data. That is, the prompting unit 105 calculates and recommends an appropriate meal time based on the prediction data. Therefore, it is possible to perform a prompt for suppressing fluctuations in blood glucose level. Since the user can know the appropriate timing to take a meal, the user is can live in a healthier way.

[0032] For example, a recommended range of blood glucose level (hereinafter referred to as the recommended blood glucose level range) is set in advance in the prompting unit 105. The prompting unit 105 prompts the recommended meal time so that the blood glucose level falls within the recommended blood glucose level range based on the prediction result. The prompting unit 105 recommends the meal time so that the user takes a meal at a timing approaching the lower limit value of the recommended blood glucose level range. is blood When the blood glucose level drops to an appropriate level, it becomes possible for the user to take a meal. That is, the user can prevent taking a meal before the blood glucose level drops significantly. Alternatively, the user can prevent taking a meal when the blood glucose level is high. Since meals can be taken at appropriate intervals from the previous meal time, rapid fluctuations in blood glucose level can be suppressed. For example, fluctuations in blood glucose level can be suppressed within a preset limit range.

[0033]

[0034] 。 The prompting unit 105 may prompt a meal menu. For example, the prompting unit 105 may prompt a meal menu that the user should take based on the calories and nutrients to be ingested in a day. That is, the prompting unit 105 compares the nutrients included in the meal menu already ingested with the nutrients to be ingested, and prompts a meal menu including the lacking nutrients. 。 By doing so, it is possible to ingest necessary nutrients and manage the blood glucose level more appropriately. The user can live in a healthier way. The prompting unit 105 may prompt a meal menu together with the meal time.

[0035] The user data acquisition unit 111 acquires data related to the user. For example, the user data acquisition unit 111 acquires data related to the user's height, weight, age, gender, etc. Further, the user data may include data related to the user's body fat percentage, body fat mass, and muscle mass. Additionally, the user data may include data related to the user's occupation and medical history. The user data acquisition unit 111 records the user data in the database 106 or the memory.

[0036] The prediction unit 103 can make predictions based on the user data. That is, based on the user data, a prediction model can be realized that adjusts the ease of decrease and increase of blood glucose levels. The prediction unit 103 can predict the user's blood glucose level using a personalized prediction model according to the user information. Thereby, the prediction unit 103 can make more accurate predictions. Further, based on the user data, the recommended values and ranges of calories and nutrients that the user should intake per day may be determined.

[0037] The schedule information acquisition unit 112 acquires the user's schedule information. The schedule information is information indicating the user's schedule such as work, tasks, desk work, meetings, commuting, moving, meals, dinners, snacks, exercise, kindergarten drop-off and pick-up, receiving deliveries, etc. For each scheduled item, a start time and an end time are set in the schedule information. The schedule information acquisition unit 112 records the schedule information in the database 106 or the memory, etc. The schedule information acquisition unit 112 can identify the user's free time based on the schedule information.

[0038] The presentation unit 105 may present meal times based on the schedule information. For example, the presentation unit 105 sets meal times during the user's free time. Specifically, the presentation unit 105 presents meal times excluding during meetings or moving, etc. That is, if there is a time period when meals cannot be taken, the presentation unit 105 presents taking meals before or after that time period.

[0039] In this way, the schedule information acquisition unit 112 can identify the user's free time based on the schedule information. The presentation unit 105 presents a meal time for the user to have a meal during the free time based on the prediction data. The presentation unit 105 presents to the user the meal schedule as an additional schedule to add the meal plan to the free time. Therefore, more appropriate presentation can be performed, and the user's health condition can be further improved.

[0040] Furthermore, when there is a meal schedule indicating a meal plan in the user's schedule information, the prediction unit 103 may generate prediction data based on the meal schedule. The meal schedule may include information indicating the meal time, meal location, meal menu, etc. that the user has planned. The meal scheduled time may be set by the user, for example, or may be set from the reservation time of a restaurant, etc. When the user uses an in-company cafeteria, etc., the available time thereof may be set as the meal scheduled time. For example, as the meal location, an in-company cafeteria, an eating-out place (restaurant), home, etc. may be registered in the schedule.

[0041] Meal data corresponding to the meal content to be consumed according to the meal location is acquired. For each meal location, average values or representative values of nutrients to be consumed in advance may be set as meal schedule information. Alternatively, when a meal menu is reserved for a dinner party, etc., corresponding meal schedule information is acquired. In this way, the meal data acquisition unit 101 acquires future meal data (meal schedule information) based on the schedule information. Then, the prediction unit 103 may perform a prediction based on the future meal data. For example, when a meal scheduled time is set in the schedule information, the presentation unit 105 presents the time more than a certain time before the meal scheduled time as the meal time. Thereby, it is possible to prevent the user from having a snack immediately before the meal scheduled time. That is, the user can keep a gap between meal times.

[0042] According to the scheduled items of the schedule, the prediction unit 103 may predict the fluctuation of blood glucose level. For example, for each scheduled item, the rate of decrease of blood glucose level or the amount of exercise may be set. For example, during meetings or desk work, the rate of decrease of blood glucose level and the amount of exercise are low, while during exercise, walking, or cycling, the rate of decrease of blood glucose level and the amount of exercise are high. When the user's schedule involves physical labor, cycling, or walking, the processing system 100 can also handle these scheduled items as exercise. That is, when there are scheduled items in the user's schedule that are handled as exercise, the exercise data acquisition unit 102 acquires these scheduled items as future exercise data. The prediction unit 103 can predict the fluctuation of blood glucose level based on this scheduled item.

[0043] In addition, the presentation unit 105 may present a meal menu based on the prediction data. The presentation unit 105 presents a meal menu such that the blood glucose level does not become too high. Here, the meal menu may include information regarding the amount of food to be consumed. By doing so, it is possible to keep the blood glucose level within the recommended blood glucose level range. Therefore, the fluctuation range of the blood glucose level can be suppressed, and the user can live healthily.

[0044] The presentation unit 105 may present the exercise time and exercise content based on the prediction data. For example, in the prediction data, when the blood glucose level exceeds the upper limit value of the recommended blood glucose level range, the presentation unit 105 recommends that the user exercise. Thereby, an increase in blood glucose level can be prevented. For example, the presentation unit 105 presents the content of exercise (exercise menu) and the period of exercise.

[0045] In addition, when presenting exercise, the presentation unit 105 may refer to the schedule information. The exercise is presented during the time period when the user can exercise. In other words, during a time period when exercise is not possible, such as during a meeting, the presentation unit 105 does not present exercise.

[0046] The schedule information acquisition unit 112 refers to the schedule information to identify free time (gaps). A time period with no scheduled event in the schedule is considered free time. The presentation unit 105 presents, based on the prediction data, to perform exercise during free time. That is, the presentation unit 105 presents to the user an additional schedule of adding an exercise schedule during free time. The processing system 100 can make a more appropriate presentation and can suppress an increase in blood glucose level. The health condition of the user can be further improved.

[0047] In this way, the prediction unit 103 predicts the fluctuation of blood glucose level. Therefore, it is possible to estimate a time period or time not suitable for meals. In other words, the presentation unit 105 presents the meal time so that the blood glucose level falls within the recommended blood glucose range. An alert may be notified for snacks at a timing not suitable for meals to restrict snacks. Thereby, it is possible to prevent the blood glucose level from exceeding the upper limit value of the recommended blood glucose range. Also, the presentation unit 105 can refer to the schedule information to estimate a time period or time suitable for meals. Therefore, the user can live healthier.

[0048] Furthermore, when a time suitable for meals is estimated, the presentation unit 105 may recommend a schedule change to the user according to that time. For example, the presentation unit 105 may present a rescheduling or cancellation of a meeting time. Also, when a time for exercise is estimated, a schedule change may be presented to enable exercise. The presentation unit 105 may present a schedule change so that the user can exercise and work at an appropriate time. For example, the presentation unit 105 may adjust the delivery receipt time, meeting time, kindergarten pick-up and drop-off time, etc.

[0049] Next, the generation and use of a prediction model for predicting the fluctuation of blood glucose level will be described. Fig. 2 is a schematic diagram showing the generation flow and use flow of the prediction model. Figs. 3 and 4 are graphs showing a prediction model for predicting the fluctuation of blood glucose level.

[0050] First, the generation of the prediction model will be described. Here, the learning unit 201 performs machine learning to obtain the prediction model. First, the learning unit 201 acquires training data for generating the prediction model (S101). The training data is data such as the sugar intake of the user, the blood glucose level of the user, and the amount of exercise. The training data includes measurement data of the blood glucose level.

[0051] The measurement data of the blood glucose level is acquired, for example, as time-series data. The user wears a sensor for monitoring the blood glucose level. Thereby, time-series data of the blood glucose level can be obtained. That is, by the user wearing a blood glucose monitor, the actual measured values of the blood glucose level during meals and exercise can be obtained. Note that the time-series data of the sugar content and the amount of exercise may be input by the user or detected by a sensor.

[0052] Next, a prediction model is generated by machine learning using the blood glucose level, sugar content, and amount of exercise as training data (S102). Here, a prediction model is generated by supervised learning with the measurement data of the blood glucose level as the correct label (also referred to as the teacher signal). The prediction model is a machine learning model generated by supervised learning. The machine learning model takes the sugar content and the amount of exercise as input data and outputs the blood glucose level.

[0053] The learning unit 201 identifies parameters for predicting the blood glucose level. The learning unit 201 may construct a learning model by deep learning. The learning unit 201 may construct a learning model by a CNN (Convolutional Neural Network) that performs a convolutional operation. In this case, the prediction model may have a convolutional layer, a pooling layer, etc. The learning unit 201 may construct a learning model by an RNN (Recurrent Neural Network) that handles time-series data. For example, the learning unit 201 performs machine learning using time-series data such as the blood glucose level, the amount of exercise, and the sugar content as training data.

[0054] The learning unit 201 updates parameters such as the weights of the neural network based on the correct labels. That is, the learning unit 201 calculates parameters that minimize the error function with respect to the correct labels. The measured blood glucose data serves as the correct label. When a multi-dimensional vector including exercise data and meal data is input to the prediction model, the blood glucose level is output. Furthermore, by sequentially inputting time-series data, the prediction model can predict fluctuations in the blood glucose level.

[0055] Here, the type and algorithm of the prediction model to be learned by the learning unit 201 are not limited, but as the algorithm, a neural network can be used. In particular, it is preferable to use a deep neural network (DNN) with multiple hidden layers. As the DNN, for example, a feed-forward (forward propagation type) neural network such as a multi-layer perceptron (MLP) that employs the error backpropagation method can be used.

[0056] Furthermore, the learning unit 201 may perform machine learning using user data. For example, the user data is data indicating the user's weight, height, gender, and age. The learning unit 201 can construct a prediction model that takes the user data as input. By doing so, a more accurate prediction model can be generated. For example, based on user data such as the user's weight, height, and gender, the learning unit 201 can perform machine learning. Also, it becomes possible to generate a prediction model without measuring the blood glucose level of an actual user. of Measurement

[0057] In addition, the training data can use measurement data of actual users for predicting blood glucose levels. Alternatively, the training data may include measurement data of multiple users. By using measurement data of multiple users, a large number of training data can be prepared. The learning unit 201 can personalize the prediction model by performing machine learning using user data. In this case, the learning unit 201 can perform machine learning with the user data as input data. Therefore, the input data of the prediction model becomes a multi-dimensional vector including meal data, exercise data, and user data. A prediction model for predicting blood glucose levels according to the user can be generated. The learning unit 201 can generate a personalized prediction model. Thereby, a prediction model with high prediction accuracy can be realized.

[0058] Next, the usage stage of the prediction model will be described. The user or the processing system 100 performs personal settings (S201). First, the parameters obtained in step S102 are set in the prediction model. The user or the processing system 100 sets a target blood glucose level. The target blood glucose level may be a recommended blood glucose range defined by an upper limit value and a lower limit value. Alternatively, only the upper limit value may be shown for the target blood glucose level. The processing system 100 may automatically set the target blood glucose level from user data such as height, age, weight, and gender.

[0059] Then, the meal data acquisition unit 101 acquires the user's meal data (S202). The exercise data acquisition unit 102 acquires exercise data (S203). The meal data and the exercise data may be data detected by a sensor or the like, or may be data input by the user operating a touch panel or the like. The meal data acquisition unit 101 and the exercise data acquisition unit 102 store the meal data and the exercise data in the database 106 as time series data (S204).

[0060] The processing system 100 inputs the meal data and exercise data stored in the database 106 into a prediction model to predict blood glucose levels (S205). The processing system 100 estimates the fluctuations in blood glucose levels by inputting the meal data and exercise data, which are time-series data, into the prediction model. The prediction model generates prediction data for blood glucose levels using the meal data and exercise data. The prediction data becomes time-series data indicating the fluctuations in blood glucose levels. Of course, the prediction model may be a machine learning model that uses user data as input data.

[0061] Based on the prediction data, the presentation unit 105 recommends meals or exercise (S206). For example, the presentation unit 105 recommends meal times that do not exceed the recommended blood glucose level range. Furthermore, the presentation unit 105 may present a meal menu, exercise time, exercise menu, etc. that do not exceed the recommended blood glucose level range. By doing so, it is possible to perform exercise and meals at the optimal time, so that blood glucose levels can be appropriately managed.

[0062] Also, the presentation unit 105 may refer to the schedule information and present meal times and the like. Since it is possible to present meals, exercise, etc. during the free time of the schedule, effective recommendations can be made. Also, the schedule information may include a meal schedule. That is, the schedule information acquisition unit 112 acquires schedule information indicating a meal schedule.

[0063] If there is a meal schedule in the schedule information indicating a future meal plan, the meal data acquisition unit 101 may acquire the future meal plan. In this case, the meal data including the future meal plan is sequentially input into the prediction model. The prediction unit 103 predicts the blood glucose level based on the future meal data. The presentation unit 105 presents meals and exercise using the future meal data.

[0064] In addition, when the meal time presented to the user overlaps with the scheduled time in the user's schedule, the presentation unit 105 may prompt the user to change the schedule. This enables the user to have meals and exercise at appropriate times. Therefore, since exercise and meals can be carried out at optimal times, blood glucose levels can be appropriately managed.

[0065] Figure 3 is a graph showing the results of predicting blood glucose levels using a prediction model. The horizontal axis represents time, and the vertical axis represents blood glucose levels [mg / dl]. Here, the fluctuations in blood glucose levels after the user had lunch from 12:00 to 12:15 are shown. Also shown are the prediction results A when at rest after lunch and the prediction results B when walking from 12:30 to 13:00. As the meal is digested, the blood glucose level rises. By exercising after a meal, the rise in blood glucose level can be suppressed.

[0066] Figure 4 is a graph showing the results of predicting blood glucose levels using another prediction model. The horizontal axis represents time, and the vertical axis represents blood glucose levels. Here, the fluctuations in blood glucose levels after the user had a meal are shown. Here, the meal consists of 100 g of white rice. Also shown are the prediction results C when no cycling exercise was done for 30 minutes after the meal and the prediction results D when cycling exercise was done. As the white rice is digested, the blood glucose level rises. By the user exercising after having a meal, the rise in blood glucose level can be suppressed. Furthermore, exercise promotes the decrease in blood glucose level.

[0067] Thus, in any case of Regardless of the prediction model, the fluctuations in blood glucose levels can be accurately predicted. The increase in blood glucose level due to meals and the suppression of the increase in blood glucose level due to exercise can be modeled.

[0068] Note that the processing system 100 and the learning unit 201 are not necessarily physically single devices. For example, the prediction model generated by the learning unit 201 through machine learning may be stored in a server different from the user terminal. For example, the user terminal transmits meal data and exercise data it has acquired to the server. The server storing the prediction model generates prediction data and transmits it to the user terminal. Then, the user terminal presents meals and exercises.

[0069] Some or all of the above processes may be executed by a computer program. That is, by the control computer constituting the processing system 100 executing the program, the control of the above processing system 100 is executed. The above-described program, when loaded into a computer, includes a group of instructions (or software code) for causing the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD), or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disc, or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0070] As described above, the invention made by the present inventor has been specifically described based on the embodiments. However, it goes without saying that the present invention is not limited to the above embodiments and can be variously modified without departing from the gist thereof.

Explanation of Reference Numerals

[0071] 100 Processing System 101 Diet Data Acquisition Unit 102 Exercise Data Acquisition Unit 103 Prediction Unit 105 Presentation Unit 106 Database 111 User Data Acquisition Unit 112 Schedule Information Acquisition Unit

Claims

1. A dietary data acquisition unit that acquires dietary data regarding the meals consumed by the user, A motion data acquisition unit that acquires motion data regarding the user's exercise, A prediction unit that generates prediction data predicting fluctuations in the user's blood glucose level from the dietary data and the motion data, A schedule information acquisition unit that acquires schedule information indicating the user's schedule including work, meetings, or movement, A presentation unit that presents meal times based on the prediction data, comprising: Based on the schedule information, identify free time before or after the time period of the movement or meeting, Present a meal time so as to have a meal during the free time, A processing system that adjusts the schedule so as to reset the meeting time or cancel the meeting based on the prediction data.

2. The processing system according to claim 1, wherein the presentation unit presents a meal menu based on the prediction data.

3. The processing system according to claim 1 or 2, wherein the presentation unit presents exercise time and exercise content based on the prediction data.

4. The schedule information acquisition unit acquires schedule information indicating the user's meal schedule, Based on the schedule information, acquire the future dietary data, The processing system according to claim 1 or 2, wherein the prediction unit predicts the blood glucose level based on the future dietary data.

5. The processing system according to claim 4, wherein a time more than a certain time before the meal scheduled time indicated by the meal schedule is presented as the meal time.

6. Acquire the user information of the user, The processing system according to claim 1 or 2, wherein the blood glucose level is predicted using a prediction model personalized according to the user information.

7. At least one processor Acquires dietary data regarding the meals consumed by the user, Acquires schedule information indicating the user's schedule including work, meetings, or movement, Acquires motion data regarding the user's exercise, Based on the schedule information, identify free time before or after the time period of the movement or meeting, Generates prediction data predicting fluctuations in the user's blood glucose level from the dietary data and the motion data, Based on the prediction data, presents a meal time so as to have a meal during the free time, A processing method for adjusting the schedule so as to reschedule the meeting time or cancel the meeting based on the prediction data.

8. The processing method according to claim 7, presenting a meal menu based on the prediction data.

9. The processing method according to claim 7 or 8, presenting exercise time and exercise content based on the prediction data.

10. Obtain schedule information indicating the user's meal schedule, Based on the schedule information, obtain the future meal data, The processing method according to claim 7 or 8, predicting the blood glucose level based on the future meal data.

11. The processing method according to claim 10, presenting a meal time as a time more than a certain time before the meal scheduled time indicated by the meal schedule.

12. Obtain the user information of the user, The processing method according to claim 7 or 8, predicting the blood glucose level using a prediction model personalized according to the user information.

13. For a computer, Obtaining meal data regarding the meal consumed by the user; Obtaining exercise data regarding the exercise of the user; Generating prediction data predicting the fluctuation of the user's blood glucose level from the meal data and the exercise data; Obtaining schedule information indicating a schedule including the user's work, meeting, or movement; Identifying free time before or after the time period of the movement or meeting based on the schedule information; Presenting a meal time so as to have a meal during the free time based on the prediction data; A program for causing the computer to execute steps of adjusting the schedule so as to reschedule the meeting time or cancel the meeting based on the prediction data.

Images