Program, method, and system

Abstract

To enable a user to have more time of exercise maintained at a certain intensity more easily.SOLUTION: The present invention includes: a persistence-condition acquisition process (S11 to S13) for obtaining a second persistence condition for a subject to continue exercise at a predetermined intensity by inputting attribute information of the subject into a prediction model; a calculation process (S16) for calculating an exercise index indicating the intensity of the exercise while the subject is continuing the exercise; a determination process (S18) for determining whether the calculated exercise index satisfies the second persistence condition; and a determination-result output process (S19, S23) for outputting a determination result.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a program, a method, and a system. [Background technology]

[0002] There are known techniques for increasing motivation to exercise. For example, Patent Document 1 describes a technique for awarding points to a user when an activity factor corresponding to the user's activity exceeds a threshold value by multiplying the activity factor by the duration of the user's activity. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2015-511133 Summary of the Invention [Problem to be solved by the invention]

[0004] It is known that increasing the time spent exercising at a certain intensity (for example, moderate to vigorous physical activity (MVPA)) can have health benefits. However, how to exercise to maintain a certain intensity can vary depending on individual attributes.

[0005] In this regard, the technology described in Patent Document 1 requires that the activity factor exceed a threshold value, so depending on the user, points may be awarded even for exercise that does not meet a certain intensity, or the intensity of the exercise for which points are awarded may be too high.

[0006] One aspect of the present application aims to provide a technology that makes it easier for users to increase the amount of time they spend exercising at a constant intensity. [Effects of the Invention]

[0007] According to one aspect of the present invention, it is easier for a user to increase the amount of time they spend exercising at a constant intensity. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram showing the configuration of a system according to a first embodiment. [Figure 2] 1 is a flowchart showing the flow of a method according to the first embodiment. [Figure 3] FIG. 2 is a diagram showing an example of a start screen according to the first embodiment. [Figure 4] FIG. 10 is a diagram showing an example of a progress screen according to the first embodiment. [Figure 5] FIG. 10 is a diagram showing an example of an end screen when the challenge according to the first embodiment is successful. [Figure 6] FIG. 10 is a diagram showing an example of an end screen when the challenge according to the first embodiment is unsuccessful. DETAILED DESCRIPTION OF THE INVENTION

[0009] [Embodiment 1] An embodiment of the present invention will be described in detail below with reference to the drawings. FIG. 1 is a block diagram showing the configuration of a system 1 according to the first embodiment of the present invention. As shown in FIG. 1, the system 1 includes a user terminal 10 and a server 20. The user terminal 10 and the server 20 are communicatively connected via a network NW. The network NW may include, for example, a wired or wireless LAN (Local Area Network), a WAN (Wide Area Network), etc., but is not limited to this. Furthermore, while FIG. 1 shows one user terminal 10 and one server 20, the number of each device included in the system 1 is not limited to one.

[0010] (Server 20 configuration) The server 20 is a computer configured to be able to communicate with the user terminal 10. For example, the computer includes a processor and a memory. The server 20 includes a control unit 210, a storage unit 220, and a communication unit 230. The control unit 210 controls each unit of the server 20 in an integrated manner. For example, the control unit 210 is realized by the processor executing a server program. The server program constitutes part of a specific example of a program described in the claims. The storage unit 220 stores various data referenced by the control unit 210. For example, the storage unit 220 is constituted by a memory. The communication unit 230 communicates with other devices via a network NW. For example, the communication unit 230 is constituted by a communication interface.

[0011] The control unit 210 includes a sustained condition providing unit 211. The sustained condition providing unit 211 provides the user terminal 10 with a second sustained condition according to information about the subject who uses the user terminal 10. The information about the subject includes at least attribute information about the subject. The information about the subject may also include the subject's level. The information about the subject may also include information such as the amount of exercise the subject desires to do (walking distance, number of steps, etc.).

[0012] (Prediction model) The storage unit 220 stores a server program and a prediction model. The server program, when executed by the processor, causes the computer to function as the control unit 210. The prediction model is trained by machine learning using training data in which a person's attribute information is used as example data and a first continuation condition for the person to continue exercising at a predetermined intensity is used as correct answer data. Examples of the attribute information include, but are not limited to, age, gender, height, weight, and combinations of some or all of these. For example, one piece of training data may be generated based on a person's attribute information and the measurement results by measuring the person's physical activity level during exercise.

[0013] A training dataset consisting of multiple training data is used for machine learning of the predictive model. The training dataset preferably includes multiple training data for each classification of attribute information. The classification of attribute information refers to the classification of values ​​that the attribute information can take. For example, when height is applied as attribute information, examples of classifications include: less than 150 cm (centimeters), 150 to 160 cm, and 160 cm or more. When a combination of height and gender is applied as attribute information, examples of classifications include: women under 150 cm, men under 160 cm, women 150 cm or more, and men 160 cm or more. The predictive model after machine learning using the training dataset is configured to output a second continuation condition according to the attribute information of the subject when the subject's attribute information is input. The second continuation condition is an appropriate condition for the subject to maintain exercise at a predetermined intensity.

[0014] (Example 1 of a sustained condition: number of steps and walking distance within a time limit) For example, if the exercise index is an index that increases as the exercise time increases, the first duration condition may include the exercise index exceeding a first reference value within a first time limit, and the second duration condition may include the exercise index exceeding a second reference value within a second time limit.

[0015] As an example, if the exercise performed by the subject is walking, the number of steps is an example of an exercise index that increases as the exercise time increases. In this case, a specific example of the first continuation condition is walking 1,500 steps (an example of a first reference value) or more within 15 minutes (an example of a first time limit). When the subject's attribute information is input, a prediction model trained using such a training dataset outputs a set of a second time limit and a second reference value for the number of steps. The set of the second time limit and the second reference value indicates a second continuation condition according to the subject's attribute information, in which the number of steps exceeds the second reference value within the second time limit.

[0016] The prediction model may be configured to fix the first time limit and the second time limit to the same value and output only the second reference value for the number of steps. The prediction model may also be configured to fix the first reference value and the second reference value to the same value and output only the second time limit. The prediction model may also be configured to receive the first time limit or the second time limit as input in addition to the attribute information and output the first reference value or the second reference value. The prediction model may also be configured to receive the first reference value or the second reference value as input in addition to the attribute information and output the first time limit or the second time limit.

[0017] Another example of an exercise index that increases as the exercise duration increases is walking distance. In this case, a specific example of the first continuation condition is walking at least 1 km (kilometer) within 15 minutes (an example of a first reference value). A prediction model trained using such a training dataset can be similarly described by replacing the number of steps with walking distance in the above description of applying the number of steps as an exercise index. For example, when the subject's attribute information and walking distance are input to the prediction model, the prediction model may be configured to output a corresponding second determination period. In this case, for example, the prediction model may output a second determination period appropriate for the subject's attribute information according to the distance of a walking course created by the subject using the map function of the user terminal 10.

[0018] (Example 2 of the sustained condition: Average value of the exercise index during the evaluation period) Also, for example, if the exercise index is an index indicating the amount of exercise per unit time, the first duration condition may include the average value of the exercise index in a first judgment period exceeding a first reference value, and the second duration condition may include the average value of the exercise index in a second judgment period exceeding a second reference value.

[0019] For example, if the exercise performed by the subject is walking, walking speed is an example of an exercise index that indicates the amount of exercise per unit time. In this case, a specific example of the first continuation condition is that the average walking speed over a 10-minute period (an example of a first judgment period) is equal to or greater than 5 kilometers per hour (an example of a first reference value). When attribute information of the subject is input, a prediction model trained using such a training dataset outputs a pair of a second judgment period and a second reference value. The pair of the second judgment period and the second reference value indicates a second continuation condition according to the subject's attribute information, in which the average walking speed over the second judgment period exceeds the second reference value.

[0020] The prediction model may be configured to fix the first judgment period and the second judgment period to the same value and output a second reference value of the walking speed according to the attribute information. The prediction model may be configured to fix the first reference value and the second reference value to the same value and output a second time limit according to the attribute information. The prediction model may be configured to receive the first judgment period or the second judgment period as input in addition to the attribute information and output the first reference value or the second reference value. The prediction model may be configured to receive the first reference value or the second reference value as input in addition to the attribute information and output the first judgment period or the second judgment period.

[0021] Another example of an exercise index indicating the amount of exercise per unit time is the "number of steps per minute." In this case, a specific example of the first continuation condition is that the average number of steps per minute over a 10-minute period (an example of a first determination period) is equal to or greater than 100 steps (an example of a first reference value). A prediction model trained using such a training dataset can be similarly explained by replacing walking speed with "number of steps per minute" in the above explanation in which walking speed is used as an exercise index.

[0022] (Example 3 of the continuation condition: Total points added under the partial continuation condition) Also, for example, the first duration condition may include the sum of points added when the motion index satisfies the first partial duration condition during a first addition period exceeding a first threshold, and the second duration condition may include the sum of points added when the motion index satisfies the second partial duration condition during a second addition period exceeding a second threshold.

[0023] As an example of the first partial duration condition, the above-mentioned condition "the exercise index is an index that increases as the exercise time becomes longer, and the exercise index exceeds the first reference value within the first time limit" may be applied. Also, as another example of the first partial duration condition, the above-mentioned condition "the exercise index is an index that indicates the amount of exercise per unit time, and the average value of the exercise index in the first determination period exceeds the first reference value" may be applied.

[0024] For example, if the exercise is walking, a specific example of the first continuation condition may be that the score, in which one point is added when walking 100 steps or more in one minute, is 30 points or more (an example of a first threshold) in one day (an example of a first addition period). In this example, another exercise index may be used instead of the number of steps. For example, it may be "one point is added when walking 80 meters or more in one minute," or "one point is added when the heart rate is 100 or more in one minute." A prediction model trained using such a training dataset outputs a set of a second addition period, a second partial continuation condition, and a second threshold when attribute information of a subject is input. The set of the second addition period, the second partial continuation condition, and the second threshold indicates a second continuation condition according to the subject's attribute information, in which the total of points added when the exercise index satisfies the second partial continuation condition in the second addition period exceeds the second threshold.

[0025] The prediction model may be configured to fix some of the first and second summation periods, the first and second partial duration conditions, and the first and second thresholds, and output only some of the remaining values ​​that are not fixed. For example, the first and second summation periods, and the first and second duration conditions may be fixed to be the same. In this case, the prediction model is configured to output only the first threshold or the second threshold.

[0026] Furthermore, the prediction model may be configured to receive as input the first and second summation periods, the first and second partial duration conditions, and some of the first and second thresholds in addition to the attribute information, and output other parts. For example, the prediction model may be configured to receive as input the first or second summation period and the first or second duration condition in addition to the attribute information, and output the first or second threshold.

[0027] (Information input into the predictive model) In addition to attribute information, a level may be input to the prediction model. The level indicates one of multiple levels associated with the subject. The level is, for example, a value that can change depending on the determination result of whether the subject satisfies the second sustaining condition. In this case, the prediction model is trained by machine learning using training data in which a person's attribute information and level are used as example data and the first sustaining condition is used as correct answer data. The level used as example data may be a level that is tentatively assumed to be the level of the person. This allows the prediction model to output a second sustaining condition according to the level, even if the attribute information is the same. For example, the second sustaining conditions for multiple people who have the same attribute information but different levels may differ from one another. Furthermore, for example, when a person's level increases, the second sustaining condition may also change.

[0028] (Configuration of user terminal 10) The user terminal 10 is a computer configured to be portable by the subject who is exercising. For example, the computer includes a processor and a memory. Examples of the user terminal 10 include, but are not limited to, a smartphone, a tablet, a wearable device, etc. From the perspective of increasing the amount of time that more subjects exercise at a constant intensity, it is desirable that the user terminal 10 be at least a popular device (e.g., a smartphone) that can be carried by the subject. In other words, it is desirable that the terminal program according to this embodiment is at least a program that causes a popular portable device to function as the user terminal 10 according to this embodiment. However, the user terminal 10 is not limited to the above-mentioned examples.

[0029] The user terminal 10 includes a control unit 110, a storage unit 120, a communication unit 130, a display unit 140, an input unit 150, and a sensor 160. The control unit 110 controls each unit of the user terminal 10. For example, the control unit 110 is realized by a processor executing a terminal program. The terminal program constitutes an example of at least a part of the program described in the claims. The storage unit 120 stores various data referenced by the control unit 110. For example, the storage unit 120 is constituted by a memory. The communication unit 130 communicates with other devices via a network NW. For example, the communication unit 130 is constituted by a communication interface.

[0030] The display unit 140 displays information visually recognizable to the subject. The input unit 150 accepts operations by the subject. For example, the display unit 140 and the input unit 150 may be, but are not limited to, a touch panel formed integrally. For example, the display unit 140 may be configured with a display. Furthermore, for example, the input unit 150 may be configured with a keyboard, a touchpad, a mouse, or the like. The sensor 160 is, for example, a device that detects the amount of exercise performed by the subject. The sensor 160 is not limited to one type of sensor, but may include multiple types of sensors. For example, if the exercise is walking, the sensor 160 may include some or all of an acceleration sensor, a gyro sensor, a GPS (Global Positioning System) receiver, a biometric information measuring device, etc. The biometric information measuring device may be, for example, but is not limited to, a pulse wave sensor, etc. Note that the display unit 140, the input unit 150, and the sensor 160 are not necessarily built into the user terminal 10, but may be connected as peripheral devices.

[0031] The memory unit 120 stores information indicating a terminal program, attribute information, a second continuation condition, a judgment result history, points, and a level. The terminal program, when executed by the processor, causes the computer to function as the control unit 110. The attribute information is information indicating the attributes of the subject. The second continuation condition is a condition for continuing exercise at a predetermined intensity according to the attribute information of the subject using the user terminal 10. The judgment result history indicates the history of judgment results by the judgment unit 113. The reward is a value associated with the subject and is also referred to as "points," for example. The initial value of the reward may be zero or any value greater than zero. The level is a value associated with the subject and indicates one of multiple levels.

[0032] The control unit 110 includes a sustained condition acquisition unit 111, a calculation unit 112, a judgment unit 113, a judgment result output unit 114, a level update unit 115, a reward calculation unit 116, a start screen output unit 117, and a warning information output unit 118.

[0033] The duration condition acquisition unit 111 executes a duration condition acquisition process. The duration condition acquisition process is a process of acquiring a second duration condition for the subject to continue exercising at a predetermined intensity by inputting attribute information of the subject to a prediction model. As an example, the duration condition acquisition unit 111 transmits the attribute information of the subject to the server 20 that stores the prediction model, and thereby acquires, from the server 20, the second duration condition output from the prediction model.

[0034] The calculation unit 112 executes a calculation process. The calculation process is a process of calculating an exercise index that indicates the intensity of exercise when the subject is continuing the exercise. As an example, the calculation unit 112 calculates the exercise index using sensor information obtained from the sensor 160. For example, the calculation unit 112 can calculate the number of steps based on sensor information obtained from an acceleration sensor, a gyro sensor, etc. Furthermore, for example, the calculation unit 112 can calculate the walking distance, walking speed, etc. based on a time series of the current location obtained from a GPS receiver. Furthermore, for example, the calculation unit 112 can calculate the heart rate from a pulse wave obtained from a pulse wave sensor, which is an example of a biological information measuring device.

[0035] The determination unit 113 executes a determination process. The determination process is a process for determining whether or not the exercise index calculated by the calculation process satisfies a second continuation condition. The determination result output unit 114 executes a determination result output process. The determination result output process is a process for outputting the determination result by the determination process. The determination result may be output to the display unit 140, a printer, a speaker (neither of which are shown), or the like.

[0036] The level update unit 115 executes a level update process. The level update process is a process for changing the level associated with the subject depending on the determination result of the determination process. The level may be increased depending on the determination result. For example, the level update unit 115 may increase the level if the success rate at which the exercise index successfully satisfies the second continuation condition is equal to or greater than a third threshold. The level may not be decreased regardless of the determination result, or may be decreased depending on the determination result. In a mode in which the level may be decreased, the level update unit 115 may decrease the level if the success rate is equal to or less than a fourth threshold. In this case, the level is maintained if the success rate is greater than the fourth threshold and less than the third threshold. The success rate can be calculated as the number of times the second continuation condition is satisfied relative to the number of times the subject attempts to satisfy the second continuation condition.

[0037] The reward calculation unit 116 executes a reward calculation process. The reward calculation process is a process of adding or subtracting a reward associated with the subject depending on the determination result of the determination process. The reward may be added depending on the determination result. For example, the reward calculation unit 116 may add a reward when the exercise index satisfies a second sustained condition. Furthermore, the reward may not be subtracted regardless of the determination result, or may be subtracted depending on the determination result. Furthermore, in a mode where the reward may be subtracted, the reward may be deposited (i.e., a reward equal to or greater than zero is previously associated with the subject). For example, the reward calculation unit 116 may subtract the reward when the exercise index does not satisfy the second sustained condition even once within a predetermined period (e.g., one day, one week, etc.).

[0038] The start screen output unit 117 executes a start screen output process. The start screen output process is a process for displaying a start screen including the second duration condition acquired by the duration condition acquisition process and an operation object that accepts an operation to start an exercise for which an exercise index is to be calculated, on the display unit 140. The calculation process, determination process, and determination result output process described above are executed in response to the subject's operation on the operation object.

[0039] The warning information output unit 118 executes a warning information output process. The warning information output process is a process for outputting warning information regarding the fact that the exercise index does not satisfy the second duration condition. For example, the content of the warning information may be, but is not limited to, a warning about an increased health risk. The output destination of the warning information may be, but is not limited to, the display unit 140, a printer, a speaker, or a combination thereof. The condition for the warning may be that the exercise index is determined not to satisfy the second duration condition. In other words, in this case, the warning information is output each time a challenge fails. The condition for the warning may be that the exercise index does not satisfy the second duration condition even once for a predetermined period. The condition for the warning may be that the terminal program is not started even once for a predetermined period.

[0040] (The flow of how System 1 executes S1) The system 1 configured as above executes the method S1 according to this embodiment. Fig. 2 is a flow diagram illustrating the flow of the method S1. The method S1 includes steps S11 to S25.

[0041] In step S11, the control unit 110 of the user terminal 10 acquires the attribute information and level of the subject. The control unit 110 also transmits the acquired attribute information and level to the server 20. For example, the control unit 110 may acquire one or both of the attribute information and the level from the storage unit 120. Note that, for example, when the terminal program is executed for the first time, the attribute information or the level may not be stored in the storage unit 120. In this case, the control unit 110 may acquire the attribute information based on an input operation by the subject and store the acquired attribute information in the storage unit 120. The control unit 110 may also acquire the lowest level and store it in the storage unit 120.

[0042] In step S12, the sustained condition providing unit 211 of the server 20 inputs the received attribute information and level into the prediction model. In addition, the sustained condition providing unit 211 transmits the second sustained condition output from the prediction model to the user terminal 10. In step S13, the sustained condition acquiring unit 111 stores the received second sustained condition in the storage unit 120. Steps S11 to S13 are an example of a sustained condition acquiring process. Note that if the attribute information and level information in the storage unit 120 have not changed since the previous execution of method S1, the second sustained condition may be acquired from the storage unit 120 instead of executing steps S11 to S13.

[0043] In step S14, the start screen output unit 117 of the user terminal 10 displays the start screen on the display unit 140. FIG. 3 is a diagram showing an example of the start screen. As shown in FIG. 3, a screen example G1, which is an example of the start screen, is displayed based on, for example, an operation by the subject to select a challenge function. The challenge function is a function that challenges the subject to exercise so that the exercise index satisfies the second continuation condition.

[0044] The example screen G1 includes areas G11 and G12 and operation objects G13 to G17. The area G11 displays a challenge condition of "achieve 1500 steps in 15 minutes" (hereinafter also referred to as challenge condition G11). The challenge condition G11 is an example of a second duration condition according to the attribute information of the subject. Furthermore, "15 minutes" and "1500 steps" in the challenge condition G11 are examples of a second time limit and a second reference value.

[0045] Additionally, an operation object G13 (also referred to as a start button G13) accepts an operation to start an exercise to satisfy the challenge condition G11. Additionally, the area G12 displays the progress status of the challenge function (hereinafter also referred to as progress status G12). In the example screen G1, the start button G13 has not yet been operated, so the 15 minutes and 1500 steps indicated by the challenge condition G11 are displayed as the progress status G12.

[0046] Furthermore, the operation object G14 (also written as the step count button G14) accepts an operation to display the total number of steps taken over a predetermined period (for example, one day). The operation object G15 (also written as the challenge button G15) accepts an operation to display the start screen. However, the challenge button G15 is displayed in a manner that makes operation invalid on the example screen G1, which is the start screen itself. The operation object G16 (also written as the balance button G16) accepts an operation to display the reward balance. The operation object G17 (also written as the record button G17) accepts an operation to display the judgment result history.

[0047] The example screen G1 allows the subject to operate the start button G13 after visually confirming the challenge condition G11, which increases the subject's motivation to exercise intentionally to satisfy the challenge condition G11. As a result, the subject is more likely to succeed in the challenge, and the subject is able to exercise for a longer period of time while maintaining a certain intensity.

[0048] In step S15, the control unit 110 accepts an operation by the subject to start exercising. For example, in the example screen G11, an operation on the start button G13 is accepted. As a result, the subject starts exercising (for example, walking).

[0049] In step S16, the calculation unit 112 calculates an exercise index when the subject continues exercising. The calculated exercise index is an exercise index targeted in the second continuation condition. For example, as in screen example G1, when a second continuation condition based on the number of steps is acquired, the calculation unit 112 calculates the number of steps as the exercise index. Furthermore, when the second continuation condition includes a second partial continuation condition, the calculation unit 112 executes a process of adding points when the exercise index satisfies the second partial continuation condition. Note that the points are stored in the storage unit 120, although not shown in the figure. Furthermore, the initial value of the points is zero.

[0050] In step S17, the determination unit 113 determines whether a predetermined period has elapsed. The predetermined period may be the second time limit, the second determination period, or the second addition period included in the second duration condition. If the determination in step S17 is No, the process from step S16 is repeated. In this case, the challenge is in progress. FIG. 4 is a diagram showing an example of a progress screen displayed on the display unit 140 while the challenge is in progress. As shown in FIG. 4, the example screen G2, which is an example of the progress screen, includes a challenge condition G11, a progress status G12, and operation objects G13 to G17, similar to the example screen G1. The progress status G12 has changed from the example screen G11. The progress status G12 in the example screen G12 indicates that there are "36 seconds" remaining until the second time limit of 15 minutes. Furthermore, the progress status G12 indicates that there are "-46 steps" remaining compared to the second reference value of 1500 steps. This indicates that the subject has already walked more than the second reference value (1546 steps in this example) within the second time limit. The operation objects G13 to G17 are displayed in a manner that makes operations invalid because a challenge is in progress.

[0051] Screen example G2 allows the subject to continue exercising while checking the progress of challenge condition G11. As a result, the subject is more likely to succeed in the challenge and can increase the duration of exercise at a certain intensity for the subject.

[0052] If the determination in step S17 is Yes, the next step S18 is executed. That is, the challenge is ended. In step S18, the determination unit 113 determines whether the exercise index satisfies the second continuation condition. If the determination in step S18 is No, step S23, which will be described later, is executed. If the determination in step S18 is Yes, the next step S19 is executed. That is, the challenge is successful.

[0053] In step S19, the determination result output unit 114 outputs a determination result indicating that the challenge was successful. The determination result output unit 114 also adds the determination result to the determination result history in the storage unit 120 in association with the date and time.

[0054] In step S20, the reward calculation unit 116 adds the reward. Specifically, the reward calculation unit 116 performs a process of adding an increment to the reward stored in the storage unit 120. For example, a fixed value may be applied as the increment. Alternatively, a larger value may be applied as the increment as the success rate or number of successes increases. Alternatively, a candidate value selected by lottery from multiple candidate values ​​may be applied as the increment.

[0055] In step S21, the level update unit 115 determines whether the condition for raising the level is met. Specific examples of the condition are as described above. For this determination process, for example, the determination result history in the storage unit 120 is referenced. If the determination in step S21 is No, the next step S22 is not executed, and the method S1 ends. If the determination in step S21 is Yes, the next step S22 is executed.

[0056] In step S22, the level update unit 115 raises the level. Specifically, the level update unit 115 performs processing to raise the level stored in the storage unit 120 by one level. However, the number of levels to be raised is not limited to one. Then, the method S1 ends. Note that the processing of steps S19 to S22 does not have to be performed in this order, and they may be performed in a different order or in parallel.

[0057] FIG. 5 is a diagram showing an example of an end screen displayed on the display unit 140 in steps S19 to S22 when the challenge is successful. As shown in FIG. 5, screen example G3, which is an example of the end screen, includes a challenge condition G11 and operation objects G14 to G17, similar to screen examples G1 and G2. Also, unlike screen examples G1 and G2, screen example G3 includes an area G31 instead of the progress status G12. The area G31 includes a challenge result G32, a determination result G33, a reward calculation result G34, and a level-up result G35. The challenge result G32 indicates the result of the challenge, and in this case indicates that "1,611 steps were walked in 15 minutes." The determination result G33 indicates that the challenge of challenge condition G11 was successful. The reward calculation result G34 indicates that 10 points have been added to the reward. The level-up result G35 indicates that the level has been increased to 3.

[0058] Screen example G3 allows the subject to recognize that by succeeding in the challenge, a reward has been added and the subject's level has increased. As a result, the subject's motivation to exercise again next time in order to meet challenge condition G11 is increased.

[0059] On the other hand, if the determination in step S18 is No, step S23 is executed. That is, the challenge is unsuccessful. In step S23, the determination result output unit 114 outputs a determination result indicating that the challenge is unsuccessful. In addition, the determination result output unit 114 adds the determination result to the determination result history in the storage unit 120 in association with the date and time.

[0060] In step S24, the warning information output unit 118 determines whether the warning conditions are met. Specific examples of the warning conditions are as described above. For this determination process, for example, the determination result history in the storage unit 120 is referenced. If the determination in step S24 is No, the next step S25 is not executed, and the method S1 ends. If the determination in step S24 is Yes, the next step S25 is executed.

[0061] In step S25, the warning information output unit 118 outputs warning information regarding the unsuccessful challenge. Then, the method S1 ends. Note that the processing of steps S23 to S25 does not have to be performed in this order, and they may be performed in a different order or in parallel.

[0062] FIG. 6 is a diagram showing an example of an end screen displayed on the display unit 140 in steps S23 to S25 when the challenge is unsuccessful. As shown in FIG. 6, screen example G4, which is an example of the end screen, includes a challenge condition G11 and operation objects G14 to G17, similar to screen examples G1 and G2. Also, unlike screen examples G1 and G2, screen example G4 includes an area G41 instead of the progress status G12. Area G41 includes a challenge result G42, a determination result G43, and warning information G44. The challenge result G42 indicates the challenge result that 1,236 steps were walked in 15 minutes. The determination result G43 indicates that the challenge was unsuccessful. The warning information G44 warns of a "possibility of increased health risks" because the warning condition "not succeeding in the challenge within one week" has been met.

[0063] Screen example G4 allows the subject to recognize that failing the challenge of challenge condition G11 will increase the risk to their health. As a result, the subject's motivation to exercise next time will increase so that they will meet challenge condition G11.

[0064] (Variation 1) In the above-described method S1, a mode in which reward deduction and level downgrade are not performed has been described, but this is not limiting. For example, if step S18 is determined to be No, in addition to steps S23 to S25, a process of deducting reward may be performed. Also, if step S18 is determined to be No, in addition to steps S23 to S25, a process of downgrading the level if a level downgrade condition is met may be performed. In this case, information indicating the reward deduction result and level downgrade result may be included in screen example G4, which is an example of an ending screen when the challenge fails.

[0065] (Variation 2) In the present embodiment, the example in which the exercise performed by the subject is walking has been described. However, the exercise is not limited to this, and may be squats, radio calisthenics, cycling, swimming, badminton, jogging, mountain climbing, etc.

[0066] (Variation 3) In this embodiment, multiple types of second duration conditions may be obtained according to the attribute information of the subject. For example, a second duration condition based on a time limit and a second duration condition based on an added point may be obtained according to the attribute information of the subject. Furthermore, multiple second duration conditions with different levels of difficulty may be obtained according to the attribute information of the subject. Furthermore, multiple second duration conditions with different types of exercise may be obtained according to the attribute information of the subject. Furthermore, the subject may be able to select one of the multiple types of second duration conditions to challenge, or may be able to challenge them in parallel, or may be able to challenge them sequentially.

[0067] (Variation 4) In the present embodiment, the second sustaining condition acquired by the user terminal 10 is mainly described as being acquired from a prediction model generated by machine learning, but this is not limiting. For example, the second sustaining condition may be common regardless of the subject. Also, for example, the second sustaining condition may be predetermined according to attribute information of the subject. Also, for example, the second sustaining condition may be acquired from a prediction model constructed as a rule-based model. Also, for example, the second sustaining condition may be set by the user.

[0068] (Variation 5) The functional blocks and information included in the user terminal 10 and the server 20 are not limited to the examples described above, and may be located in either the user terminal 10 or the server 20. For example, the system 1 may be configured such that all functional blocks and information are located in the user terminal 10, making the server 20 unnecessary. Furthermore, for example, the system 1 may be configured such that information such as the reward and level of each subject is stored in the server 20. Furthermore, for example, the system 1 may be configured such that functional blocks and information other than the calculation unit 112 that calculates the exercise index are located in the server 20 and provided as a web application.

[0069] [Software implementation example] The functions of the user terminal 10 and the server 20 (hereinafter referred to as "devices") can be realized by a program that causes a computer to function as the device, and a program that causes a computer to function as each control block of the device (particularly each part included in the control units 110, 210).

[0070] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program, thereby realizing the functions described in each of the above embodiments.

[0071] The program may be non-transitory and may be recorded on one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0072] Furthermore, some or all of the functions of the control blocks can be realized by logic circuits. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of the control blocks can also be realized by, for example, a quantum computer.

[0073] Furthermore, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI ​​may run on the control device or on another device (for example, an edge computer or a cloud server).

[0074] 〔summary〕 A program according to a first aspect is a program executed by one or more processors. The program causes the one or more processors to execute the following: a continuation condition acquisition process for acquiring a second continuation condition for the subject to maintain exercise at a predetermined intensity by inputting the subject's attribute information into a prediction model trained by machine learning using teacher data in which the person's attribute information is used as example data and a first continuation condition for the subject to maintain exercise at a predetermined intensity is used as correct answer data; a calculation process for calculating an exercise index indicating the intensity of the exercise when the subject is maintaining the exercise; a determination process for determining whether the exercise index calculated by the calculation process satisfies the second continuation condition; and a determination result output process for outputting the determination result by the determination process. With the above configuration, the second continuation condition is expected to be a condition suitable for the subject to maintain exercise at a predetermined intensity. The subject is more motivated to exercise to satisfy the second continuation condition, which allows the subject to increase the amount of time they spend exercising at a constant intensity.

[0075] A program according to aspect 2 is the same as that of aspect 1, wherein the exercise index is an index that increases as the exercise time increases, the first continuation condition includes the exercise index exceeding a first reference value within a first time limit, and the second continuation condition includes the exercise index exceeding a second reference value within a second time limit. With the above configuration, the second time limit is expected to be a length appropriate for the subject to continue walking at that intensity. Furthermore, the second reference value is expected to be a value appropriate for the subject to maintain a predetermined intensity during walking sustained within the second time limit. The subject is more motivated to walk so that the exercise index exceeds the second reference value within the second time limit, thereby enabling the subject to increase the amount of time for which a certain intensity is maintained during exercise.

[0076] A program according to a third aspect of the present invention is the program of the first aspect, wherein the exercise index is an index indicating the amount of exercise per unit time, the first continuation condition includes an average value of the exercise index in a first determination period exceeding a first reference value, and the second continuation condition includes an average value of the exercise index in a second determination period exceeding a second reference value. With the above configuration, the second reference value is expected to be a value suitable for the subject's walking in a unit time (e.g., one minute) to reach a predetermined intensity. Furthermore, the second determination period (e.g., 10 minutes) is expected to be a length suitable for the subject to maintain walking at that intensity. The subject is more motivated to maintain walking at a predetermined intensity for the second determination period so that the average value of the exercise index per unit time exceeds the second reference value, and the subject can increase the amount of time he or she exercises at a constant intensity.

[0077] Aspect 4 is a program according to aspect 1, wherein the first continuation condition includes a sum of points added when the exercise index satisfies a first partial continuation condition during a first addition period exceeding a first threshold, and the second continuation condition includes a sum of points added when the exercise index satisfies a second partial continuation condition during a second addition period exceeding a second threshold. This configuration increases the subject's motivation to intermittently perform exercise during the second addition period in which the exercise index exceeds a second reference value so that the sum of points awarded to the subject exceeds the second threshold. As a result, the subject can increase the amount of time spent exercising at a constant intensity.

[0078] A program according to aspect 5 is any one of aspects 1 to 4, wherein the subject is associated with one of a plurality of levels, the level is input to the prediction model in addition to attribute information, and the one or more processors are further caused to execute a level update process for changing the level associated with the subject in accordance with the determination result of the determination process. With the above configuration, the second duration condition acquired next time can be updated in accordance with the determination result of whether the subject was able to perform exercise whose exercise index satisfies the second duration condition. For example, if the previous determination result was good, the level can be increased, and a second duration condition for sustaining higher intensity exercise can be acquired. Furthermore, for example, if the determination result was not good, the level can be decreased, and a second duration condition for sustaining lower intensity exercise can be acquired. As a result, the subject is more motivated to exercise to satisfy the second duration condition that best suits them, thereby increasing the amount of time the subject spends exercising at a constant intensity.

[0079] The program according to aspect 6, in any one of aspects 1 to 5, further causes the one or more processors to execute a reward calculation process that adds or subtracts a reward associated with the subject depending on the determination result of the determination process. With the above configuration, the subject is more motivated to exercise so that the exercise index satisfies the second continuation condition in order to obtain a reward or to avoid a reduction in the reward, and therefore the subject can increase the amount of time he or she exercises at a constant intensity.

[0080] The program according to aspect 7, in any one of aspects 1 to 6, further causes the one or more processors to execute a warning information output process that outputs warning information regarding the motion index not satisfying the second continuation condition. With the above configuration, the subject who views the warning information is more motivated to satisfy the second continuation condition.

[0081] The program according to aspect 8, in any one of aspects 1 to 7, further causes the one or more processors to execute a start screen output process of displaying on a display device a start screen including the second duration condition acquired by the duration condition acquisition process and an operation object that accepts an operation to start an exercise for which the exercise index is to be calculated, and causes the one or more processors to execute the calculation process, the determination process, and the determination result output process in response to an operation by the subject on the operation object. With the above configuration, the subject can visually recognize the second duration condition suitable for the subject and consciously start an exercise whose exercise index satisfies the second duration condition, thereby making it possible to increase the duration of exercise suitable for the subject to maintain a predetermined intensity.

[0082] A method according to aspect 9 is a method executed by one or more processors, and includes: a continuation condition acquisition process in which the one or more processors input attribute information of a subject into a prediction model trained by machine learning using teacher data in which the person's attribute information is used as example data and a first continuation condition for the subject to maintain exercise at a predetermined intensity is used as ground truth data, thereby acquiring a second continuation condition for the subject to maintain exercise at a predetermined intensity; a calculation process in which the one or more processors calculates an exercise index indicating the intensity of the exercise when the subject is maintaining the exercise; a determination process in which the one or more processors determine whether the exercise index calculated by the calculation process satisfies the second continuation condition; and a determination result output process in which the one or more processors output a determination result of the determination process. The above configuration achieves the same effects as aspect 1.

[0083] A system according to aspect 10 includes a duration condition acquisition unit that acquires a second duration condition for the subject to maintain exercise at a predetermined intensity by inputting attribute information of the subject into a prediction model that is trained by machine learning using teacher data in which attribute information of the subject is used as example data and a first duration condition for the subject to maintain exercise at a predetermined intensity is used as correct answer data, a calculation unit that calculates an exercise index that indicates the intensity of the exercise when the subject is maintaining the exercise, a determination unit that determines whether the exercise index calculated by the calculation unit satisfies the second duration condition, and a determination result output unit that outputs the determination result by the determination unit. The above configuration achieves the same effects as aspect 1.

[0084] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0085] 1 System 10 User terminal 20 servers 110, 210 control unit 120, 220 storage section 130, 230 Communications Department 140 Display section 150 Input section 160 sensors 111 Persistence condition acquisition unit 112 Calculation Unit 113 Judgment section 114 Judgment result output unit 115 Level Update Section 116 Remuneration Calculation Department 117, 118 Start screen output section 117, 118 Warning information output section 211 Sustainability Conditions Provision Department

Claims

1. A program to be executed by one or more processors, the program comprising: a sustained condition acquisition process for acquiring a second sustained condition for the subject to sustain exercise at a predetermined intensity by inputting the subject's attribute information into a prediction model trained by machine learning using teacher data in which the subject's attribute information is used as example data and a first sustained condition for the subject to sustain exercise at a predetermined intensity is used as correct answer data; a calculation process for calculating an exercise index indicating the intensity of the exercise when the subject is continuing the exercise; a determination process for determining whether the motion index calculated by the calculation process satisfies the second continuation condition; a determination result output process for outputting a determination result obtained by the determination process; A program that executes the following.

2. The exercise index is an index that increases as the exercise time increases, the first sustained condition includes the motion index exceeding a first reference value within a first time limit; the second sustained condition includes the motion index exceeding a second reference value within a second time limit; The program according to claim 1.

3. the exercise index is an index indicating the amount of exercise per unit time, the first persistence condition includes an average value of the motion index in a first determination period exceeding a first reference value; the second persistence condition includes an average value of the motion index in a second determination period exceeding a second reference value; The program according to claim 1.

4. the first continuation condition includes a condition in which a total of points added when the movement index satisfies a first partial continuation condition in a first addition period exceeds a first threshold; The second continuation condition includes that a total of points added when the motion index satisfies a second partial continuation condition during a second addition period exceeds a second threshold. The program according to claim 1.

5. The subject is associated with one of a plurality of levels, The level is input to the prediction model in addition to the attribute information, further causing the one or more processors to execute a level update process for changing the stage of the level associated with the subject in accordance with a determination result of the determination process; The program according to claim 1.

6. further causing the one or more processors to execute a reward calculation process that adds or subtracts a reward associated with the subject depending on a determination result of the determination process; The program according to claim 1.

7. the one or more processors further executing a warning information output process for outputting warning information relating to the motion index not satisfying the second duration condition; The program according to claim 1.

8. the one or more processors further executing a start screen output process for displaying on a display device a start screen including the second duration condition acquired by the duration condition acquisition process and an operation object for accepting an operation to start an exercise for which the exercise index is to be calculated; executing the calculation process, the determination process, and the determination result output process in response to the subject's operation on the operation object; The program according to claim 1.

9. A method executed by one or more processors, comprising: a sustainment condition acquisition process in which the one or more processors input the attribute information of the subject into a prediction model trained by machine learning using teacher data in which the attribute information of the subject is used as example data and a first sustainment condition for the subject to sustain exercise at a predetermined intensity is used as correct answer data; and a calculation process in which the one or more processors calculate an exercise index that indicates the intensity of the exercise when the subject is continuing the exercise; a determination process in which the one or more processors determine whether the motion index calculated by the calculation process satisfies the second continuation condition; a determination result output process in which the one or more processors output a determination result from the determination process; A method comprising:

10. a duration condition acquisition unit that acquires a second duration condition for the subject to continue exercising at a predetermined intensity by inputting the subject's attribute information into a prediction model that is trained by machine learning using teacher data in which the subject's attribute information is used as example data and a first duration condition for the subject to continue exercising at a predetermined intensity is used as correct answer data; and a calculation unit that calculates an exercise index that indicates the intensity of the exercise when the subject is continuing the exercise; a determination unit that determines whether the motion index calculated by the calculation unit satisfies the second continuation condition; a determination result output unit that outputs a determination result by the determination unit; A system with.

Images