Health management system and health management method

Abstract

To provide a health management system capable of predicting information for a user to improve health-related test values.SOLUTION: A health management system 100 includes: an acquisition part 24 that acquires a piece of first information either one of a target value regarding exercise intensity when a user rides an electrically assisted bicycle 10 and the amount of improvement in health-related test values; a prediction unit 28 that predicts a piece of second information representing the target value related to the exercise intensity, and the amount of improvement in test values related to health based on the acquired first information and a predetermined predictive model using the first information; and an output unit 27 that outputs the predicted second information.SELECTED DRAWING: Figure 1

Description

[[Technical Field]]

[0001] The present invention relates to a health management system using an electrically power-assisted bicycle. [[Background Art]]

[0002] In recent years, interest in health has been increasing. Patent Document 1 discloses a health management system that supports securing a necessary amount of exercise in daily activities. [[Prior Art Documents]] [[Patent Documents]]

[0003] [[Patent Document 1]] Japanese Unexamined Patent Application Publication No. 2018-45393 [[Summary of the Invention]] [[Problem to be Solved by the Invention]]

[0004] The present invention provides a health management system and the like that can predict information for a user to improve health-related test values (such as blood glucose level). [[Means for Solving the Problem]]

[0005] A health management system according to one aspect of the present invention comprises: an acquisition unit that acquires first information indicating one of a target value related to exercise intensity when a user rides and travels on an electrically power-assisted bicycle, and an improvement amount of a test value related to the health of the user; a prediction unit that predicts second information indicating the other of the target value related to exercise intensity and the improvement amount of the health-related test value based on the acquired first information and a predetermined prediction model using the first information; and an output unit that outputs the predicted second information.

[0006] A health management method according to one aspect of the present invention is a health management method performed by a computer, comprising: an acquisition step of acquiring first information indicating either a target value for exercise intensity when a user rides an electric assist bicycle or an amount of improvement in the user's health-related test values; a prediction step of predicting second information indicating the other of the target value for exercise intensity and an amount of improvement in the health-related test values ​​based on the acquired first information and a predetermined prediction model using the first information; and an output step of outputting the predicted second information.

[0007] A program according to one aspect of the present invention is a program for causing a computer to execute the health management method described above. [Effects of the Invention]

[0008] A health management system, etc., according to one aspect of the present invention, can predict information that will help the user improve their health-related test results. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is a block diagram showing the functional configuration of a health management system according to an embodiment. [Figure 2] Figure 2 is an external view of the electric assist bicycle and display device included in the health management system according to the embodiment. [Figure 3] Figure 3 is a flowchart showing the calculation process for %VO2max. [Figure 4] Figure 4 shows an example of displaying the %VO2max calculation results (Example 1). [Figure 5] Figure 5 shows an example of displaying the %VO2max calculation results (Example 2). [Figure 6] Figure 6 shows an example of displaying the %VO2max calculation results (Example 3). [Figure 7] Figure 7 is a flowchart of Example 1 of the VO2max estimation process. [Figure 8] Figure 8 shows an example of table information. [Figure 9] FIG. 9 is a flowchart of Example 2 of the VO2max estimation operation. [Figure 10] FIG. 10 is a flowchart of Example 3 of the VO2max estimation operation. [Figure 11] FIG. 11 is a diagram for explaining an estimation method for a period during which an electrically power assisted bicycle is traveling on an uphill slope. [Figure 12] FIG. 12 is a diagram showing the correlation between estimated maximum power values and actually measured VO2max values. [Figure 13] FIG. 13 is a flowchart of the VO2max update operation. [Figure 14] FIG. 14 is a diagram showing an example of display of exercise intensity information for a plurality of users. [Figure 15] FIG. 15 is a diagram showing a modified example of the calculation method for exercise time. [Figure 16] FIG. 16 is a flowchart of the operation for predicting an improvement amount of blood glucose level. [Figure 17] FIG. 17 is a diagram showing an example of a display screen used for predicting an improvement amount of blood glucose level. [Figure 18] FIG. 18 is a diagram showing an example of a first prediction formula showing the relationship between a target value related to exercise intensity and an improvement amount of blood glucose level. [Figure 19] FIG. 19 is a flowchart of the operation for predicting a target value related to exercise intensity. [Figure 20] FIG. 20 is a diagram showing an example of a display screen used for predicting a target value related to exercise intensity. [Figure 21] FIG. 21 is a diagram showing an example of a display screen used for predicting a target value related to exercise intensity. [Figure 22] FIG. 22 is a diagram showing an example of a second prediction formula showing the relationship between a target value related to exercise intensity and an improvement amount of blood glucose level. [Figure 23] FIG. 23 is a diagram showing an example of a display screen showing an expected improvement of blood glucose level. [Figure 24] FIG. 24 is a flowchart of the operation for predicting expected improvement of blood glucose level. [Figure 25]FIG. 25 is a diagram showing first modification 1 of the functional configuration of the health management system according to the embodiment. [Figure 26] FIG. 26 is a diagram showing second modification 2 of the functional configuration of the health management system according to the embodiment. [Figure 27] FIG. 27 is a diagram showing third modification 3 of the functional configuration of the health management system according to the embodiment. DESCRIPTION OF THE EMBODIMENTS

[0010] Hereinafter, embodiments will be described with reference to the drawings. All of the embodiments described below are illustrative or specific examples. Numerical values, shapes, materials, constituent elements, arrangement positions and connection forms of constituent elements, steps, order of steps, and the like shown in the following embodiments are examples, and are not intended to limit the present invention. Among constituent elements in the following embodiments, constituent elements not recited in the independent claims are described as optional constituent elements.

[0011] Each drawing is a schematic diagram and is not necessarily strictly illustrated. In addition, in each drawing, substantially identical configurations are denoted by the same reference numerals, and overlapping descriptions may be omitted or simplified.

[0012] (Embodiment) [Configuration] First, the configuration of the health management system according to the embodiment will be described. FIG. 1 is a block diagram showing the functional configuration of the health management system according to the embodiment. FIG. 2 is an external view of an electrically assisted bicycle and a display device included in the health management system according to the embodiment.

[0013] As shown in Figures 1 and 2, the health management system 100 is a system that calculates the exercise intensity of a user pedaling the electric assist bicycle 10 (a user riding the electric assist bicycle 10) and displays the calculated exercise intensity on the display unit 32 of the display device 30 and the display unit 42 of the administrator terminal 40. According to the health management system 100, users and their administrators can check their own exercise intensity. Specifically, the health management system 100 comprises an electric assist bicycle 10, a server device 20, a display device 30, and an administrator terminal 40.

[0014] First, let me describe the electric assist bicycle 10. The electric assist bicycle 10 is a bicycle that can be ridden on public roads. The electric assist bicycle 10 comprises a frame 11, a front wheel 12f, a rear wheel 12r, pedals 13, an electric motor 14 attached to the frame 11, a battery 15, a control unit 16, a pedaling force sensor 17a, a rotation speed sensor 17b, a memory unit 18, and a communication unit 19.

[0015] The electric assist bicycle 10 assists the forward movement of the vehicle body 11 by driving an electric motor 14 based on the user's pedaling force 13. The electric motor 14 is driven using power supplied from a battery 15. The battery 15 is a secondary battery, such as a lithium-ion battery, and also functions as a power source for the control unit 16, etc.

[0016] The control unit 16 is a control device that drives the electric motor 14. The control unit 16, for example, This is implemented by a microcomputer, but may also be implemented by a processor. The functions of the control unit 16 are realized by the execution of a computer program (software) stored in the storage unit 18 by the hardware, such as a processor or microcomputer, that constitutes the control unit 16.

[0017] Specifically, the control unit 16 determines the magnitude of the assist force (in other words, the auxiliary driving force) generated by the electric motor 14 based on the user's pedaling force 13 and the speed of the electric assist bicycle 10. The pedaling force 13 is obtained from the pedaling force sensor 17a.

[0018] The pedal force sensor 17a is, for example, a magnetostrictive torque sensor. The speed of the electric assist bicycle 10 is calculated based on the number of rotations per unit time of the rear wheel 12r (or front wheel 12f) and the size of the rear wheel 12r (or front wheel 12f). The speed of the electric assist bicycle 10 may also be measured by a sensor such as a Hall IC attached to the rear wheel 12r (or front wheel 12f). The method for detecting the speed of the electric assist bicycle 10 is not particularly limited.

[0019] The rotation speed sensor 17b measures the rotation speed of the crank. In other words, the rotation speed sensor 17b measures the rotation angle of the crank. The rotation speed sensor 17b is, for example, an optical sensor having a light emitting part and a light receiving part, and measures the rotation speed of the crank based on the number of times the path of light from the light emitting part to the light receiving part is blocked by a light shield located between the light emitting part and the light receiving part, which rotates in conjunction with the crank. The rotation speed sensor 17b is not limited to the optical configuration described above, as long as it can measure the rotation speed of the crank.

[0020] The memory unit 18 is a storage device that stores computer programs and the like executed by the control unit 16. The memory unit 18 is implemented, for example, by semiconductor memory.

[0021] The communication unit 19 is a communication circuit that enables the electric assist bicycle 10 to communicate with the server device 20 via a wide-area communication network. The wide-area communication network includes mobile communication networks and the internet. The communication performed by the communication unit 19 is, for example, wireless communication.

[0022] Specifically, the communication unit 19 transmits the measured value of the user's pedaling force (torque) applied to the pedal 13, obtained from the pedaling force sensor 17a, to the server device 20. The communication unit 19 also transmits the measured value of the crank rotation speed obtained from the rotation speed sensor 17b to the server device 20, or transmits the crank rotation speed per unit time, calculated by the control unit 16 based on the measured value of the rotation speed sensor 17b, to the server device 20. The crank rotation speed per unit time can be calculated, for example, by converting the difference between the most recent measured value of the crank rotation speed and the previous measured value of the crank rotation speed into the crank rotation speed per unit time. When the measured value of the rotation speed sensor 17b is transmitted to the server device 20, the crank rotation speed per unit time is calculated by the server device 20 (information processing unit 22). The unit time is, for example, one minute.

[0023] In the following embodiments, the measured pedaling force is referred to as the torque value, and the number of crank rotations per unit time is referred to as the cadence value.

[0024] Next, the configuration of the server device 20 will be described. The server device 20 calculates the exercise intensity of the user riding the electric assist bicycle 10 (the user pedaling the pedals 13). Specifically, the server device 20 comprises a communication unit 21, an information processing unit 22, and a storage unit 23.

[0025] The communication unit 21 is a communication circuit for the server device 20 to communicate with the electric assist bicycle 10, the display device 30, and the administrator terminal 40, etc. The communication performed by the communication unit 21 is, for example, wired communication, but it may also be wireless communication.

[0026] The information processing unit 22 performs information processing to calculate the user's exercise intensity. The information processing unit 22 is implemented by, for example, a microcomputer, but may also be implemented by a processor. The information processing unit 22 includes, as functional components, an acquisition unit 24, an estimation unit 25, a calculation unit 26, an output unit 27, and a prediction unit 28. The functions of the acquisition unit 24, estimation unit 25, calculation unit 26, output unit 27, and prediction unit 28 are realized by the execution of a computer program (software) stored in the storage unit 23 by the hardware, such as a microcomputer or processor, that constitutes the information processing unit 22.

[0027] The memory unit 23 is a storage device that stores information necessary for calculating exercise intensity. This information includes computer programs executed by the information processing unit 22. The memory unit 23 is implemented, for example, by a semiconductor memory.

[0028] Next, the display device 30 will be described. The display device 30 receives exercise intensity information, which indicates the exercise intensity calculated by the server device 20, from the server device 20 and displays (visualizes) the received information. The display device 30 displays the information to the user. The display device 30 is a general-purpose portable terminal such as a smartphone or tablet, but it may also be a dedicated terminal for the electric assist bicycle 10, such as a cycle computer. If the display device 30 is a dedicated terminal for the electric assist bicycle 10, the display device 30 can be considered as part of the electric assist bicycle 10. As shown in Figure 1, the display device 30 is attached to the handlebars of the electric assist bicycle 10, for example, but if the display device 30 is a general-purpose portable terminal, it does not need to be attached to the handlebars.

[0029] The display device 30 specifically comprises an input receiving unit 31, a display unit 32, a communication unit 33, an information processing unit 34, and a storage unit 35.

[0030] The input receiving unit 31 receives user input. Specifically, the input receiving unit 31 is implemented by a touch panel or hardware keys (buttons), etc.

[0031] The display unit 32 displays an image (also referred to as the input screen) that the user views in order to input the perceived load. The display unit 32 displays, for example, an image showing the calculated exercise intensity, and other similar information.

[0032] The communication unit 33 is a communication circuit that enables the display device 30 to communicate with the server device 20 via a wide-area communication network. The communication performed by the communication unit 33 is, for example, wireless communication.

[0033] The information processing unit 34 performs information processing to display information related to the user's exercise intensity. The information processing unit 34 is implemented by, for example, a microcomputer, but may also be implemented by a processor. The information processing unit 34 includes a display processing unit 36 ​​as a functional component. The function of the display processing unit 36 ​​is realized by the execution of a computer program (software) stored in the storage unit 35 by the hardware, such as a microcomputer or processor, that constitutes the information processing unit 34.

[0034] The memory unit 35 is a storage device that stores the information necessary for the above-mentioned information processing. This information includes computer programs executed by the information processing unit 34. The memory unit 35 is implemented, for example, by a semiconductor memory.

[0035] Next, the administrator terminal 40 will be described. The administrator terminal 40 receives exercise intensity information, which indicates the exercise intensity calculated by the server device 20, from the server device 20 and displays (visualizes) the received information. While the display device 30 described above displays information to the user, the administrator terminal 40 displays information to the administrator who manages the user's exercise status. The server device 20 can calculate the exercise intensity of multiple users, and the administrator terminal 40 displays information related to the exercise intensity of multiple users.

[0036] The administrator terminal 40 is, for example, a stationary information terminal such as a personal computer, but it may also be a portable information terminal such as a smartphone or tablet. Specifically, the administrator terminal 40 comprises an input receiving unit 41, a display unit 42, a communication unit 43, an information processing unit 44, and a storage unit 45.

[0037] The input receiving unit 41 receives user input. Specifically, the input receiving unit 41 is implemented by a mouse, keyboard, or touch panel, etc.

[0038] The display unit 42 displays an image (also referred to as the input screen) that the user views in order to input the perceived load. The display unit 42 displays, for example, an image showing the calculated exercise intensity, and other similar information.

[0039] The communication unit 43 is a communication circuit that allows the administrator terminal 40 to communicate with the server device 20 via a wide-area communication network. The communication performed by the communication unit 43 may be, for example, wired communication, but it may also be wireless communication.

[0040] The information processing unit 44 performs information processing to display information related to the user's exercise intensity. The information processing unit 44 is implemented by, for example, a microcomputer, but may also be implemented by a processor. The information processing unit 44 includes a display processing unit 46 and a notification unit 47 as functional components. The functions of the display processing unit 46 and the notification unit 47 are realized by the execution of a computer program (software) stored in the storage unit 45 by the hardware, such as a microcomputer or processor, that constitutes the information processing unit 44.

[0041] The memory unit 45 is a storage device that stores the information necessary for the above-mentioned information processing. This information includes computer programs executed by the information processing unit 44. The memory unit 45 is implemented, for example, by a semiconductor memory.

[0042] [Calculation process for %VO2max (exercise intensity)] The oxygen uptake level (%VO2max) is a well-known indicator of a person's exercise intensity. The oxygen uptake level (%VO2max) is expressed by the following equation 1.

[0043] Oxygen consumption level (%VO2max) = Oxygen consumption (VO2) ÷ Maximum oxygen consumption (VO2max) ··Equation 1

[0044] In some guidelines for improving symptoms such as hypertension, hyperglycemia, and hyperlipidemia, exercise duration is specified based on %VO2max. However, measuring oxygen consumption requires a large-scale exhaled gas analyzer.

[0045] In contrast, the health management system 100 calculates the user's %VO2max using a method different from directly measuring oxygen intake using an exhaled gas analyzer, etc., and displays the calculated %VO2max. The %VO2max calculation operation of the health management system 100 is described below. Figure 3 is a flowchart of the %VO2max calculation operation.

[0046] When a user pedals the electric assist bicycle 10, the pedaling force sensor 17a measures the torque value, the rotation speed sensor 17b measures the cadence value, and the control unit 16 stores the riding data, which is time-series data of the torque value and cadence value pair, in the storage unit 18. The communication unit 19 transmits the time-series data stored in the storage unit 18 to the server device 20 at a predetermined timing. For example, the electric assist bicycle 10 transmits the riding data accumulated from when the power is turned on until it is turned off as one riding data set to the server device 20 when the user instructs it to turn off the power. The electric assist bicycle 10 may also transmit the most recent riding data set to the server device 20 when the user instructs it to turn on the power. In other words, the electric assist bicycle 10 transmits riding data periodically, for example, when the power is turned off or on.

[0047] The communication unit 21 of the server device 20 receives driving data, and the acquisition unit 24 acquires the received driving data (S11). In step S11, noise reduction (invalidation of irregular values) is performed on the acquired driving data as necessary.

[0048] The calculation unit 26 calculates the power value applied by the user to the pedal 13 based on the torque value and cadence value included in the acquired riding data (S12). More specifically in step S12, time-series data of the power value is calculated based on the time-series data of the torque value and cadence value pair. For example, if the time-series data of the torque value and cadence value pair is time-series data measured at predetermined time intervals such as 1 second, the time-series data of the power value calculated in step S12 will also be time-series data at predetermined time intervals. The power value [W] can be calculated based on the formula: 2π × crank length [m] × torque value [N·m] × cadence value [rpm] / 60.

[0049] Alternatively, the power value may be calculated by the control unit 16, and time-series data of the power value may be stored in the storage unit 18. In this case, the acquisition unit 24 acquires the time-series data of the power value as driving data in step S11, and the power value calculation process is omitted. Thus, in step S11, the acquisition unit 24 only needs to acquire driving data related to the power value (time-series data of a set of torque value and cadence value, or time-series data of the power value).

[0050] Next, the calculation unit 26 calculates the user's VO2 (oxygen consumption) based on the power value calculated in step S12 (S13). More specifically, in step S13, time-series data of VO2 is calculated based on time-series data of the power value. It is known that there is a proportional relationship between the power value and VO2, and the storage unit 23 has a conversion formula (linear function) for calculating VO2 from the power value stored in advance. The calculation unit 26 can calculate VO2 by substituting the power value into this conversion formula.

[0051] The conversion formula can be generated by a gradual increase in load test on a bicycle ergometer. Specifically, the conversion formula can be obtained by measuring VO2 using an exhaled gas analyzer while changing the load (actual power value) applied to the pedals of a bicycle ergometer in multiple subjects.

[0052] The calculation unit 26 may also calculate VO2 by substituting the moving average of the power values ​​for the most recent predetermined period into the above conversion formula. According to the inventors' knowledge, the predetermined period for calculating the moving average is preferably about 3 minutes (for example, a period of 2 minutes 30 seconds or more and 3 minutes 30 seconds or less). It is known that the power value (input) applied by the user to the pedal 13 and VO2 (output) form a first-order lag system, and the process of converting the moving average of the power values ​​to VO2 is considered appropriate.

[0053] Next, the calculation unit 26 calculates %VO2max (exercise intensity) by dividing the VO2 calculated in step S13 by VO2max (maximum oxygen uptake) based on the above formula 1 (S14). In step S14, more specifically, time-series data of %VO2max is calculated. VO2max is estimated by the estimation unit 25 before the processing in step S14 is performed and is stored in the storage unit 23 in advance. Details of the VO2max estimation method (estimation operation) will be described later.

[0054] Next, the output unit 27 outputs exercise intensity information showing the calculated %VO2max (S15). The exercise intensity information output by the output unit 27 is transmitted to the display device 30 by the communication unit 21, and the communication unit 33 of the display device 30 receives the exercise intensity information. The exercise intensity information is stored in the storage unit 23 along with the user's ID.

[0055] Next, the display processing unit 36 ​​displays an image on the display unit 32 showing the calculation result of %VO2max based on the received exercise intensity information (S16). In other words, the display unit 32 displays an image showing the calculation result in response to a command from the display processing unit 36. The display unit 32 displays %VO2max as a number, for example, but may also display the calculation result of %VO2max as a graph, as shown below.

[0056] As shown in Figure 4, the display processing unit 36 ​​displays, for example, the change in the calculated %VO2max over time in a graph. Figure 4 shows an example 1 of the display of the %VO2max calculation results. In the graph in Figure 4, the horizontal axis represents time, and the vertical axis represents the instantaneous value of %VO2max.

[0057] As mentioned above, guidelines for improving symptoms such as hypertension, hyperglycemia, and hyperlipidemia sometimes recommend exercise that raises %VO2max above the standard value (e.g., 40%). Therefore, in the example in Figure 4, the standard value is shown in the graph, and the period during which %VO2max is above the standard value is shown on the time axis.

[0058] Such graphs allow users to easily understand the changes in %VO2max over time and the periods during which %VO2max was above the baseline value.

[0059] Furthermore, the above guidelines may recommend performing exercise that results in a %VO2max of 150 minutes or more per week for a certain period of time (for example, 150 minutes). Therefore, the display processing unit 36 ​​may display the cumulative value of the time during which the calculated %VO2max is 150 minutes or more (hereinafter also referred to as exercise time). The display processing unit 36 ​​may, for example, display the cumulative value as a number, but may also display the change in the cumulative value over time as a graph, as shown in Figure 5. Figure 5 is a diagram showing an example 2 of the display of the %VO2max calculation results. In the graph in Figure 5, the horizontal axis represents time, and the vertical axis represents the cumulative value of the time during which %VO2max is 150 minutes or more (cumulative time). The cumulative time here is the cumulative time per predetermined period, such as 1 week, 1.5 months (6 weeks), or 3 months (12 weeks), and the time axis can be switched by the user.

[0060] Furthermore, in the example in Figure 5, the aforementioned fixed time period and the baseline pace are illustrated with dashed lines. The graph in Figure 5 can also be described as a graph in which the value increases only during the period when %VO2max is above the baseline value.

[0061] According to graphs like this, users can easily understand how far they are getting from the amount of time they should be spending exercising to achieve a %VO2max above a certain threshold.

[0062] Furthermore, as shown in Figure 6, the display processing unit 36 ​​may display the cumulative value of the time (the time the user achieved that exercise intensity) for each calculated magnitude of %VO2max. In other words, the display processing unit 36 ​​may display a histogram of %VO2max in units of time. Figure 6 is a diagram showing example 3 of the display of the %VO2max calculation results. In the graph in Figure 6, the horizontal axis shows the magnitude of %VO2max, and the vertical axis shows the cumulative value over time. The cumulative value is the cumulative value per predetermined period, such as 1 day, 1 week, 1.5 months (6 weeks), or 3 months (12 weeks).

[0063] Such graphs allow users to easily understand the histogram of %VO2max over time.

[0064] The health management system 100 may simultaneously display two or more of the display screens shown in Figures 4-6, or it may selectively display the display screens shown in Figures 4-6 according to user input, etc. Furthermore, the health management system 100 may be implemented as a system capable of displaying only a portion of the display screens shown in Figures 4-6.

[0065] As explained above, the health management system 100 can calculate %VO2max based on the torque value and cadence value included in the data acquired from the electric assist bicycle 10, and display information related to the calculated %VO2max on the display unit 32. %VO2max is an example of an index indicating exercise intensity.

[0066] Such a health management system 100 can help determine the user's %VO2max while riding an electric assist bicycle 10.

[0067] Furthermore, as shown in the display example in Figure 5, when the displayed exercise time is such that %VO2max is equal to or greater than the reference value, the display processing unit 36 ​​needs to calculate the exercise time based on the exercise intensity information. Here, the calculation of the exercise time may be performed by the server device 20, and the server device 20 may provide exercise time information indicating the exercise time to the display device 30.

[0068] In this case, the calculation unit 26 calculates the time during which the %VO2max calculated in step S14 is equal to or greater than the reference value as the exercise time, and the output unit 27 outputs exercise time information indicating the calculated exercise time. The exercise time information output by the output unit 27 is transmitted to the display device 30 by the communication unit 21, and the communication unit 33 of the display device 30 receives the exercise time information.

[0069] [Example 1 of VO2max estimation behavior] As shown in Equation 1 above, the value of VO2max is necessary to calculate %VO2max. Since there are individual differences in the value of VO2max, there is room for consideration as to how to estimate the value of VO2max. Below, we will explain Example 1 of the user's VO2max estimation process. Figure 7 is a flowchart of Example 1 of the VO2max estimation process.

[0070] First, the acquisition unit 24 acquires the user's attribute information (S21). This attribute information is input to the input receiving unit 31 of the display device 30, for example, during the initial setup when a user starts using the health management system 100. The attribute information input to the input receiving unit 31 is transmitted from the communication unit 33 of the display device 30 to the communication unit 21 of the server device 20, and then acquired by the acquisition unit 24. Specifically, the attribute information includes the user's gender, age, weight, and whether or not they have an exercise habit.

[0071] Next, the acquisition unit 24 acquires table information from the storage unit 23 for converting attribute information into VO2max (S22). Figure 8 shows an example of table information. As shown in Figure 8, the table information specifies the value of VO2max per unit body weight (unit: ml / kg / min) according to the user's gender, age, and whether or not they have an exercise habit. Such table information is statistically generated, for example, based on the measured VO2max values ​​of a large number of subjects with various attributes. Note that the table information may also take into account the user's height.

[0072] Next, the estimation unit 25 estimates the user's VO2max based on the attribute information obtained in step S21 and the table information obtained in step S22 (S23). The estimation unit 25 identifies the value of VO2max per unit body weight by comparing the user's gender, age, and whether or not they have exercise habits, which are included in the attribute information, with the table information, and estimates the user's VO2max by multiplying the identified value by the user's weight, which is included in the attribute information.

[0073] [Example 2 of VO2max estimation behavior] The estimation unit 25 may estimate the user's VO2max using a machine learning model. The machine learning model is constructed, for example, using the measured VO2max values ​​of a large number of subjects with various attributes used to create the table information in Figure 8 as training data, and outputs the user's VO2max when the user's attribute information is input.

[0074] Furthermore, the machine learning model may be constructed using time-series data (torque and cadence values) of electric assist bicycles 10 from a large number of subjects whose VO2max is known as training data. Below, we will describe Example 2 of the VO2max estimation process using such a machine learning model. Figure 9 is a flowchart of Example 2 of the VO2max estimation process.

[0075] First, the acquisition unit 24 acquires driving data (S31). This process is the same as step S11 in Figure 3.

[0076] Next, the estimation unit 25 estimates the user's VO2max based on the acquired driving data and the machine learning model (S32).

[0077] The machine learning model here is, for example, a trained model that can take one or more features calculated from the user's driving data as input and output the user's VO2max. The machine learning model is constructed using features calculated from the driving data of a large number of subjects whose VO2max is known as training data. In step S32, the estimation unit 25 can estimate VO2max by calculating features from the driving data acquired in step S31 and inputting the calculated features into the machine learning model. In addition to driving data, the training data may also include information indicating the condition of the road surface during driving (such as the slope of the road surface).

[0078] Furthermore, the machine learning model may be a model to which deep learning is applied, and which can estimate VO2max using the driving data itself as input. In this case, the calculation of features by the estimation unit 25 is omitted.

[0079] Thus, a machine learning model for estimating maximum oxygen uptake from riding data is generated by acquiring riding data for multiple users, which consists of torque and cadence values ​​measured by the electric assist bicycle 10 when a subject (user) with a known VO2max is riding the electric assist bicycle 10, and then training the model with the acquired riding data from multiple users. The generation of such a machine learning model may be performed by the server device 20 or by another computer not shown in the figure. Training the model with riding data here includes both training the model with features obtained from the riding data and training the model with the riding data itself.

[0080] [Example 3 of VO2max estimation behavior] By the way, as explained in step S13 of Figure 3, VO2 and power value are proportional, so VO2max can be considered to be the maximum power that the user can exert. In the operation of the electric assist bicycle 10, the user's maximum power is exerted when the electric assist bicycle 10 is traveling uphill (traveling in the direction of going uphill).

[0081] Below, we will describe Example 3 of the VO2max estimation process based on running data while running uphill. Figure 10 is a flowchart of Example 3 of the VO2max estimation process.

[0082] First, the acquisition unit 24 acquires driving data (S41). This process is the same as step S11 in Figure 3. As mentioned above, the driving data is time-series data of torque values ​​and cadence values. Noise reduction (invalidation of irregular values) is performed on the driving data acquired in step S41 as needed.

[0083] Next, the estimation unit 25 calculates the power value applied by the user to the pedal 13 based on the torque value and cadence value included in the acquired driving data (S42). This process is similar to step S12 in Figure 3, and more specifically, time-series data of the power value is calculated based on the time-series data of the torque value and cadence value pair.

[0084] Next, the estimation unit 25 estimates the period during which the electric assist bicycle 10 is traveling uphill based on the time-series data of power values ​​(S43). Figure 11 is a diagram illustrating the method for estimating the period during which the electric assist bicycle 10 is traveling uphill, and Figure 11 shows the time-series data of power values ​​and the time-series data of cadence values. Figure 11(b) is an enlarged view of the area enclosed by the dashed frame in Figure 11(a).

[0085] After diligent research, the inventors discovered that when the electric assist bicycle 10 is traveling uphill, the power output is higher than when it is traveling on a flat road, and that both the power output and cadence decrease over time (monotonically). The decrease in power output and cadence over time is thought to be due to the user gradually becoming fatigued.

[0086] Therefore, in step S43, the estimation unit 25 identifies a period in which the power value is greater than a predetermined value, and in which the power value and the cadence value corresponding to that power value decrease. In Figure 11, the area enclosed by the solid line frame in Figure 11(b) corresponds to such a period.

[0087] In the example shown in Figure 11, the predetermined value is, for example, the average value of the power values ​​over the entire period of the time-series data of power values ​​calculated in step S42 (80 [W]). The predetermined value is the average value of all power values ​​calculated so far and may be updated each time driving data is acquired. Alternatively, the predetermined value may be a fixed value such as 100 [W]. If the predetermined value is a fixed value, it is determined empirically or experimentally as appropriate by the designer of the health management system 100.

[0088] In addition, in step S43, a requirement may be added that the duration of the specified period must be greater than or equal to a predetermined length, in addition to the two requirements mentioned above. The predetermined length is, for example, about 5 to 10 seconds. This excludes periods in which the power value and cadence value decrease in the short term, that is, periods in which it is estimated that the electric assist bicycle 10 is not traveling uphill.

[0089] Next, the estimation unit 25 estimates the user's VO2max based on the maximum power value during the estimated period (S44). In the example in Figure 11, the maximum power value during the specified period is 175 [W]. The estimation unit 25 can estimate VO2max by substituting the maximum power value into the conversion formula used in step S13 of Figure 3. The estimated VO2max is stored in the storage unit 23.

[0090] Figure 12 shows the correlation between the maximum power values ​​calculated by the processing in steps S41 to S44 for five subjects and the measured VO2max values ​​of those five subjects. As shown in Figure 12, there is a strong correlation between the maximum power values ​​calculated by the processing in steps S41 to S44 and the measured VO2max values ​​of the five subjects, indicating that Example 3 of the VO2max estimation process is a highly valid estimation method.

[0091] Alternatively, another method for determining the duration during which the electric assist bicycle 10 is traveling uphill could be to use a GNSS (Global Navigation Satellite System) module, such as a GPS (Global Positioning System) module.

[0092] For example, the display device 30 attached to the electric assist bicycle 10, or the electric assist bicycle 10 itself, may be equipped with a GNSS module, and the riding data may include time-series data of the coordinates (latitude and longitude) of the electric assist bicycle 10's current position. In such a case, the estimation unit 25 can identify the period during which the electric assist bicycle 10 is riding uphill by querying another server device that manages map information (topographic information) for the slope of the road surface while the electric assist bicycle 10 is riding.

[0093] [VO2max update behavior] VO2max can be considered an indicator of a user's aerobic exercise capacity. If a user's aerobic exercise capacity improves, the VO2max value will increase, and if the user's aerobic exercise capacity decreases, the VO2max value will decrease. Therefore, a user's VO2max value may be updated. Figure 13 is a flowchart of the VO2max update process.

[0094] For example, the electric assist bicycle 10 collects riding data from the time it is turned on until it is turned off, and when the user instructs it to turn off the power, it sends this single riding data to the server device 20.

[0095] The communication unit 21 of the server device 20 receives one run data, and the acquisition unit 24 acquires the received run data (S51).

[0096] Next, the estimation unit 25 calculates the power value applied by the user to the pedal 13 based on the torque value and cadence value included in the acquired driving data (S52). This process is similar to step S12 in Figure 3, and more specifically, time-series data of the power value is calculated based on the time-series data of the torque value and cadence value pair.

[0097] Next, the estimation unit 25 determines whether the time-series data of the power value includes a period in which the electric assist bicycle 10 is traveling uphill (S53). Similar to the process in step S43, the estimation unit 25 determines whether there is a period in which the power value is greater than a predetermined value and in which the power value and the cadence value corresponding to that power value decrease. The estimation unit 25 may also determine whether there is a period in which the power value is greater than a predetermined value and in which the power value and the cadence value corresponding to that power value decrease, and in which the duration is greater than or equal to a predetermined length.

[0098] If the estimation unit 25 determines that the time-series data of the power value includes a period in which the electric assist bicycle 10 is traveling uphill (Yes in S53), it updates the VO2max (S54). Specifically, the estimation unit 25 replaces (overwrites) the VO2max stored in the memory unit 23 with the VO2max based on the maximum power value during that period.

[0099] On the other hand, if the estimation unit 25 determines that the time-series data of the power value does not include the period during which the electric assist bicycle 10 is traveling uphill (No in S53), it does not update the VO2max.

[0100] As explained above, when the estimation unit 25 calculates a new maximum power value, it updates the VO2max stored in the memory unit 23 with the newly calculated maximum power value. As a result, the calculation unit 26 can calculate the user's exercise intensity based on the latest VO2max stored in the memory unit 23.

[0101] As the initial value of VO2max (or maximum power value), the VO2max (or the corresponding maximum power value) is determined based on the user's attribute information and the table information (Figure 8) that converts the attribute information to maximum oxygen consumption, as explained in Example 1 of the VO2max estimation operation. The initial value refers to the value used when VO2max has never been estimated, such as immediately after the introduction of the health management system 100.

[0102] [Displaying information on the administrator terminal] As described above, the server device 20 can acquire riding data from multiple users from multiple electric assist bicycles 10, estimate the exercise intensity of multiple users, and store the exercise intensity information of multiple users in the storage unit 23. The exercise intensity information is distinguished by being stored in the storage unit 23 in association with the user's ID.

[0103] Here, the output unit 27 of the server device 20 may output exercise intensity information for multiple users. Once the outputted exercise intensity information for multiple users is transmitted from the server device 20 to the administrator terminal 40, the display processing unit 46 can display information related to the exercise intensity of multiple users on the display unit 42 based on the exercise intensity information of multiple users. Figure 14 shows an example of the display of exercise intensity information for multiple users.

[0104] In the example shown in Figure 14, the display unit 42 shows the exercise time, achievement rate, ranking, status, and estimated VO2max for five users.

[0105] Exercise time is the cumulative value of the time during which the %VO2max (calculated by the calculation unit 26) indicated by the exercise intensity information exceeds a certain threshold. If the exercise time is updated and displayed daily, administrators can monitor the exercise status of multiple users.

[0106] When the exercise time is displayed in this manner, the display processing unit 46 needs to calculate the exercise time based on the exercise intensity information. Here, the calculation of the exercise time may be performed by the server device 20 (calculation unit 26), and the server device 20 (output unit 27) may provide exercise time information indicating the exercise time to the administrator terminal 40. This eliminates the need for the display processing unit 46 to calculate the exercise time.

[0107] The achievement rate shows the percentage of exercise time achieved relative to the target value (target time). The ranking is the ranking of exercise time among multiple users (ranking based on exercise intensity), with the user with the longest exercise time ranking first. The status indicates the degree of achievement, and is displayed with symbols such as "○" for 100% or more, "△" for 50% or less but less than 100%, and "×" for less than 50%.

[0108] The VO2max estimate is the VO2max calculated (estimated) by the estimation unit 25. When the VO2max estimate is displayed in this way, the maximum oxygen consumption information indicating the VO2max calculated by the estimation unit 25 is provided from the server device 20 to the administrator terminal 40.

[0109] Specifically, the output unit 27 of the server device 20 outputs maximum oxygen consumption information, which represents the calculated VO2max (maximum oxygen consumption corresponding to the maximum power value). The maximum oxygen consumption information output by the output unit 27 is transmitted to the administrator terminal 40 by the communication unit 21, and the communication unit 43 of the administrator terminal 40 receives the maximum oxygen consumption information. As a result, the display processing unit 46 can display VO2max on the display unit based on the maximum oxygen consumption information output by the output unit 27.

[0110] The VO2max estimate displayed in Figure 14 is estimated based on Example 3 of the VO2max estimation process and is updated daily. In other words, the maximum oxygen consumption information is provided from the server device 20 to the administrator terminal 40 each time the VO2max estimated by the estimation unit 25 is updated.

[0111] The estimated VO2max can be considered an indicator of a user's aerobic exercise capacity, and if the estimated VO2max is updated and displayed daily, administrators can track the progress of fitness improvements for multiple users.

[0112] The display processing unit 46 may also display the fluctuations (changes over time) of the estimated VO2max value and the update frequency. As mentioned above, the estimated VO2max value is not updated unless the user rides the electric assist bicycle 10 uphill. If it is displayed that the estimated VO2max value remains at its initial value, or that the update frequency of the estimated VO2max value is low, the administrator can investigate the cause and take steps to improve it (or encourage the user to improve it).

[0113] Incidentally, the administrator terminal 40 manages the exercise time of multiple users and can notify users who are deemed to be not getting enough exercise. For example, the notification unit 47 notifies a user if it determines that the user is not getting enough exercise based on their exercise time. The notification unit 47 can determine, for example, that a user whose status is marked with an "X" is not getting enough exercise.

[0114] Notifications from the notification unit 47 are possible because the user's ID and the recipient (email address, etc.) are associated. The content of the notification may be an alert or it may be something like encouraging the user's exercise.

[0115] [Variations in the method for calculating exercise time] In the above embodiment, the calculation unit 26 calculates the time during which %VO2max is equal to or greater than a reference value as exercise time, and does not treat the time during which %VO2max is less than a reference value as exercise time. However, if the time during which %VO2max is less than a reference value continues for a predetermined period of time or less (i.e., %VO2max falls below a reference value in the short term), such time may be treated as exercise time. Figure 15 shows a modified example of this method for calculating exercise time.

[0116] As shown in Figure 15, the calculation unit 26 does not treat the time T1 during which the state in which %VO2max is below the reference value continues for a longer period than a predetermined time as exercise time. On the other hand, the calculation unit 26 treats the time T2 during which the state in which %VO2max is below the reference value continues for a longer period than a predetermined time as exercise time. The predetermined time is, for example, 3 minutes.

[0117] This calculation method allows you to obtain almost the same exercise time as when calculating %VO2max from instantaneous power values, compared to calculating %VO2max using a moving average of power values.

[0118] [Predictive behavior regarding the amount of improvement in health-related test values] The health management system 100 can predict the amount of improvement in health-related test values ​​based on target values ​​for exercise intensity when the user rides the electric assist bicycle 10, and display this on the display unit 32 of the display device 30.

[0119] Here, the target value for exercise intensity is defined, for example, by the cumulative value of the exercise time (the time during which the user's %VO2max is above a certain threshold while riding the electric assist bicycle 10).

[0120] Health-related test values ​​refer to biometric values ​​such as blood glucose levels, triglyceride levels, or BMI (Body Mass Index) that are included as test items when a user undergoes a health checkup. The most recent health-related test values ​​are entered. Below, an example of predicting the amount of improvement in blood glucose levels is explained. Figure 16 is a flowchart of the operation for predicting the amount of improvement in blood glucose levels. Note that the health management system 100 may also predict the amount of improvement in triglyceride levels or the amount of improvement in BMI, etc.

[0121] The input receiving unit 31 of the display device 30 receives input from the user regarding the user's target value for exercise intensity and the current blood glucose level (most recent test value) (S61). At this time, the display unit 32 of the display device 30 displays a display screen as shown in Figure 17. Figure 17 is a diagram showing an example of a display screen used to predict the amount of improvement in blood glucose levels.

[0122] The upper part of the display screen in Figure 17 shows information entered by the user, including blood glucose test results. In the example in Figure 17, not only blood glucose test results, but also user attribute information, triglyceride test results, BMI test results, and medical questionnaire data have been entered. The medical questionnaire data is equivalent to a medical questionnaire and specifically includes data indicating at least one of the following: whether or not the user has a drinking habit, the amount of alcohol consumed, whether or not they smoke, and the amount of smoking.

[0123] In the middle section of the display screen in Figure 17, the target value for exercise intensity entered by the user is shown. The target value for exercise intensity is entered in two parts, for example, the length of exercise time per week [unit: minutes] and the duration of that exercise time [unit: n weeks, where n is a natural number]. In other words, the target value for exercise intensity is determined by the exercise time. For the sake of simplicity in this explanation, the duration (how long the exercise time will be continued) is fixed at 12 weeks, and the user enters the length of exercise time per week.

[0124] The information entered in step S61 is displayed on the display unit 32 of the display device 30, as shown in Figure 17. The first piece of information entered is transmitted to the server device 20 by the communication unit 33 and received by the communication unit 21. The first piece of information indicates the target value for the user's exercise intensity. In addition to the first piece of information, a third piece of information (described later) may also be transmitted, which may include at least one of the entered information, such as the current blood glucose level, health test results other than blood glucose levels, attribute information, and medical interview data.

[0125] The acquisition unit 24 acquires the first information received by the communication unit 21 (S62). The prediction unit 28 predicts the amount of improvement in blood glucose levels based on the acquired first information and a predetermined prediction model (S63). Here, the predetermined prediction model is, for example, a calculation formula (hereinafter also referred to as the first prediction formula) that shows the relationship between the target value related to exercise intensity (exercise time) and the amount of improvement in blood glucose levels. Figure 18 is a diagram showing an example of such a first prediction formula.

[0126] In Figure 18, the six points correspond to six subjects, and the vertical axis shows how much the subjects' blood glucose levels changed (improved) as a result of exercising by riding an electric-assist bicycle 10 over 12 weeks. The amount of change in blood glucose levels [unit: mg / dl] is based on actual measurements.

[0127] The horizontal axis shows the average weekly exercise time [in minutes] over a 12-week period. As mentioned above, exercise time is the time during which the subject's %VO2max is above the baseline value (40% in Figure 18) while riding the electric assist bicycle 10. The %VO2max (exercise intensity used to generate the first prediction formula) of the six subjects is calculated, for example, based on the %VO2max calculation process described above. In other words, in data collection for generating the first prediction formula (a predetermined prediction model), the %VO2max (exercise intensity) of multiple subjects (other users) is calculated based on the %VO2max calculation process described above. The same applies when the subject's maximum power value is required to generate the first prediction formula.

[0128] As shown in Figure 18, there is a strong correlation between the amount of exercise time per week and the amount of improvement in blood glucose levels. Therefore, the equation obtained by linearly approximating the six points shown in Figure 18 is used as the first prediction equation (a predetermined prediction model). The prediction unit 28 can predict the amount of improvement in blood glucose levels (y in the first prediction equation) by substituting the target value (length of exercise time per week) indicated by the acquired first information into x in the first prediction equation shown in Figure 18. Note that in the range of x values ​​where the amount of improvement in blood glucose levels is positive in the first prediction equation, processing such as treating y as 0 may be performed.

[0129] If the user can change the duration from 12 weeks on the display screen in Figure 17, the amount of improvement will be appropriately adjusted according to the entered duration. One possible method of adjustment is to proportionally distribute the amount of improvement in blood glucose levels for each weekly exercise time × duration (i.e., cumulative exercise time) entered by the user, assuming that the first prediction formula represents the amount of improvement in blood glucose levels for each weekly exercise time × duration. Specifically, if the amount of improvement for 120 minutes of exercise per week × 12 weeks (=1440) is -20, then the amount of improvement for 120 minutes of exercise per week × 6 weeks (=720) will be -20 × (720 / 1440) = -10.

[0130] Next, the output unit 27 outputs second information indicating the predicted improvement in blood glucose levels (S64). The second information output by the output unit 27 is transmitted to the display device 30 by the communication unit 21, and the communication unit 33 of the display device 30 receives the second information.

[0131] Next, the display processing unit 36 ​​displays the amount of improvement in blood glucose level (information related to the second information) on the display unit 32 based on the received second information (S65). In other words, the display unit 32 displays an image showing the amount of improvement in blood glucose level in response to a command from the display processing unit 36. For example, as shown in the lower part of Figure 17, the display processing unit 36 ​​displays the value 116 obtained by adding the improvement amount (-20) to the blood glucose test value (136) entered in step S61 on the display unit 32, but it may also display the improvement amount itself. In other words, the manner in which the amount of improvement in blood glucose level is displayed is not particularly limited.

[0132] In this way, the health management system 100 can predict the amount of improvement in health-related test values ​​from the target value of exercise intensity when the user rides the electric assist bicycle 10, and present (display) the predicted amount of improvement to the user.

[0133] [Predictive behavior regarding target values ​​for exercise intensity] The health management system 100 can predict a target value for exercise intensity necessary to achieve the desired improvement in health-related test values ​​by riding (exercising) the electric assist bicycle 10, and display it on the display unit 32 of the display device 30. Below, an example is described in which the target value for exercise intensity necessary to achieve the desired improvement is predicted based on the improvement in blood glucose levels. Figure 19 is a flowchart of the operation for predicting the target value for exercise intensity. The health management system 100 may also predict the target value for exercise intensity necessary to achieve the desired improvement based on the improvement in triglyceride levels or the improvement in BMI, etc.

[0134] The input receiving unit 31 of the display device 30 receives input from the user regarding the amount of improvement in blood glucose levels that the user wants to achieve, and the current blood glucose level (most recent test value) (S71). At this time, the display unit 32 of the display device 30 displays a display screen as shown in Figure 20. Figure 20 is a diagram showing an example of a display screen used to predict target values ​​related to exercise intensity.

[0135] The upper section of the display screen in Figure 20 shows information entered by the user, including blood glucose test results. This is the same as the display screen in Figure 17.

[0136] In the middle section of the display screen in Figure 20, the amount of blood glucose improvement that the user wants to achieve (corresponding to the improvement target in Figure 20) is displayed, as entered by the user.

[0137] The information entered in step S71 is displayed on the display unit 32 of the display device 30, as shown in Figure 20. The first piece of information entered is transmitted to the server device 20 by the communication unit 33 and received by the communication unit 21. The first piece of information indicates the amount of improvement in blood glucose level that the user wants to achieve. In addition to the first piece of information, a third piece of information (described later) is also transmitted, which may include at least one of the health-related test values ​​other than blood glucose level, attribute information, and medical questionnaire data, as well as information indicating the current blood glucose level. The information indicating the current blood glucose level may also be included in the third piece of information.

[0138] The acquisition unit 24 acquires the first information received by the communication unit 21 (S72). The prediction unit 28 predicts a target value for exercise intensity based on the acquired first information and a predetermined prediction model (S73). Here, the predetermined prediction model is, for example, a calculation formula that shows the relationship between the target value for exercise intensity (exercise time) and the amount of improvement in blood glucose levels, and is the first prediction formula shown in Figure 18 above.

[0139] The prediction unit 28 can predict the target value for exercise intensity (x in the first prediction formula) by substituting the amount of improvement in blood glucose level indicated by the acquired first information into y in the first prediction formula shown in Figure 18. The target value for exercise intensity is defined, for example, by the amount of exercise time per week that should be continued for 12 weeks.

[0140] Next, the output unit 27 outputs second information indicating a target value for the predicted exercise intensity (S74). The second information output by the output unit 27 is transmitted to the display device 30 by the communication unit 21, and the communication unit 33 of the display device 30 receives the second information.

[0141] Next, the display processing unit 36 ​​displays a target value for exercise intensity (information related to the second information) on the display unit 32 based on the received second information (S75). In other words, the display unit 32 displays an image showing the target value for exercise intensity in response to a command from the display processing unit 36. The display processing unit 36 ​​displays, for example, the exercise time and how many weeks that exercise time should be continued (duration), as shown in the lower part of Figure 20.

[0142] Furthermore, by making a predetermined input to the input reception unit 31, the user can change the display of either the exercise time or the duration on the display screen in Figure 20. In this case, the display processing unit 36 ​​changes the values ​​of the exercise time and duration, for example, assuming that the first prediction formula shows the amount of improvement in blood glucose levels for the exercise time per week × duration (i.e., the cumulative value of exercise time). Specifically, if the cumulative value of exercise time required to achieve an improvement of -20 is 120 minutes of exercise × 12 weeks = 1440, and the user changes the exercise time per week to 60 minutes, the duration will be changed to 24 weeks (= 1440 / 60).

[0143] In step S71, instead of manually entering the amount of blood glucose improvement, the user can enter the blood glucose test value and then select the "Within Reference Range" button in Figure 20 to automatically input the amount of blood glucose improvement needed to bring the blood glucose level within the normal range. Note that "within the normal range" here corresponds to the reference range described later. Figure 21 shows another example of the display screen used to predict target values ​​related to exercise intensity.

[0144] The upper limit of the normal range for blood glucose levels is 109. As shown in Figure 21, when the blood glucose test value entered in step S71 is entered and the "Within Reference Range" button in Figure 21 is selected, the improvement amount (-27), which is the upper limit of blood glucose levels (109) minus the test value (136), is automatically entered, and the target value for exercise intensity to achieve this improvement amount is displayed.

[0145] In this way, the health management system 100 can predict a target value for exercise intensity based on the amount of improvement in health-related test values ​​that the user wants to achieve by riding the electric assist bicycle 10, and can present (display) the predicted target value for exercise intensity to the user.

[0146] [Variations of the calculation formula used for predictive actions] In the two predicted actions described above, the target value for exercise intensity was defined by the exercise time. However, the target value for exercise intensity may also be defined by the total energy (power value [W] × time [s]) when the user is riding the electric assist bicycle 10. In other words, in the description of the two predicted actions described above, the exercise time [minutes / week] may be replaced with the total energy [J / week].

[0147] In this case, the formula for predicting the amount of improvement in blood glucose levels and the target values ​​for exercise intensity (hereinafter also referred to as the second prediction formula) is shown in Figure 22. Figure 22 is a diagram showing an example of such a second prediction formula.

[0148] In Figure 22, the seven points correspond to seven subjects. The vertical axis shows how much each subject's blood glucose level changed (improved) as a result of exercising by riding an electric-assist bicycle 10 over 12 weeks. The changes in blood glucose levels were measured. The horizontal axis shows the total energy intake [unit: J] over 12 weeks.

[0149] As shown in Figure 22, there is a strong correlation between the total energy intake over 12 weeks and the improvement in blood glucose levels. Therefore, the equation obtained by linearly approximating the seven points shown in Figure 22 is used as the second prediction equation (a predetermined prediction model). The prediction unit 28 can predict the improvement in blood glucose levels and target values ​​for exercise intensity using the second prediction equation shown in Figure 22. In addition, in the range of x values ​​where the improvement in blood glucose levels is positive in the second prediction equation, processing such as treating y as 0 may be performed.

[0150] Incidentally, the first prediction formula shown in Figure 18 is a calculation formula that shows the relationship between exercise time and the amount of improvement in blood glucose levels. However, it may also be a calculation formula that shows the relationship between exercise time, other features other than exercise time, and the amount of improvement in blood glucose levels. For example, it is conceivable to identify features that contribute highly to the amount of improvement in blood glucose levels from among the features included in health-related test values ​​other than blood glucose levels (such as triglyceride levels), user attribute information, and medical questionnaire data, using regression analysis or similar methods, and then use a calculation formula that includes these identified features as variables in addition to exercise time.

[0151] Thus, the first prediction formula (a predetermined prediction model) can be any formula (model) that shows the relationship between one or more features, including exercise time, and the amount of improvement in blood glucose levels. Similarly, the second prediction formula (a predetermined prediction model) shown in Figure 22 can be any formula (model) that shows the relationship between one or more features, including total energy intake, and the amount of improvement in blood glucose levels.

[0152] Incidentally, the subjects whose data was collected to determine the first and second prediction formulas had blood glucose levels between 109 and 160. Applying the first and second prediction formulas to users with higher blood glucose levels may reduce prediction accuracy.

[0153] Therefore, multiple first prediction formulas are prepared for each blood glucose level range, and in steps S61 and S71, the first prediction formula suitable for the user may be selectively used from among the multiple first prediction formulas according to the user's current blood glucose level input. In other words, the prediction unit 28 may predict the second information based on the acquired first information and the first prediction formula (a predetermined prediction model) determined by the acquired current blood glucose level (health-related test value). The same applies to the second prediction formula.

[0154] Furthermore, multiple first prediction formulas may be prepared by considering not only blood glucose levels, but also other health-related test values, user attribute information, and at least one of the user's medical questionnaire data. For example, the prediction unit 28 selects a first prediction formula suitable for the user from among the multiple first prediction formulas, in accordance with the user's current blood glucose level, other health-related test values, user attribute information, and user's medical questionnaire data entered in steps S61 and S71, and performs a prediction using the selected first prediction formula. The same applies to the second prediction formula.

[0155] The above describes variations of the calculation formulas used in the two prediction operations. When the prediction uses at least one of the following: the current blood glucose level, health test results other than blood glucose levels, user attribute information, and user medical interview data, in step S62 (or step S72), the acquisition unit 24 acquires third information in addition to the first information, which represents at least one of the current blood glucose level, health test results other than blood glucose levels, user attribute information, and user medical interview data. In step S63 (or step S73), the prediction unit 28 predicts the second information based on the first and third information acquired by the acquisition unit 24. As described above, when the third information is used in the prediction, the prediction formula may include cases where the third information is included as a feature, or cases where the prediction formula is selected using the third information.

[0156] [Variations of the predictive model] In the two prediction operations described above, a prediction formula (calculation formula, calculation algorithm) was used as the prediction model, but a machine learning model may also be used as the prediction model.

[0157] For example, the first machine learning model used to predict the amount of improvement in blood glucose levels is a trained model that can take multiple features, including target values ​​related to exercise intensity, as input and output the amount of improvement in blood glucose levels. The first machine learning model is constructed using features such as the cumulative amount of exercise time (or total energy amount) required to improve blood glucose levels, current blood glucose levels, health test results other than blood glucose levels, attribute information, and medical interview data from a large number of subjects whose blood glucose improvement is known.

[0158] In step S62, the acquisition unit 24 acquires, in addition to the first information, a third piece of information indicating at least one of the following: the current blood glucose level, health-related test results other than blood glucose levels, attribute information, and medical interview data. As a result, in step S63, the prediction unit 28 can predict the amount of improvement in blood glucose levels (second information) by inputting the first information and the third information into the first machine learning model.

[0159] Furthermore, the second machine learning model used to predict target values ​​for exercise intensity is a pre-trained model that can output target values ​​for exercise intensity (cumulative exercise time or total energy) by taking multiple features, including the amount of improvement in blood glucose levels, as input. The second machine learning model is constructed using features such as the amount of improvement in blood glucose levels, attribute information, and medical interview data from a large number of subjects whose cumulative exercise time (or total energy) required to improve blood glucose levels is known as training data.

[0160] In step S72, the acquisition unit 24 acquires, in addition to the first information, a third piece of information indicating at least one of the following: the current blood glucose level, health-related test results other than blood glucose levels, attribute information, and medical interview data. As a result, in step S73, the prediction unit 28 inputs the first information and the third information into the first machine learning model to predict the target value (second information) related to exercise intensity.

[0161] Furthermore, if the subject's %VO2max is required to generate training data, this %VO2max is calculated, for example, based on the %VO2max calculation operation described above. In other words, in data collection for generating the first or second machine learning model (a predetermined predictive model), the %VO2max (exercise intensity) of multiple subjects (other users) is calculated based on the %VO2max calculation operation described above. The same applies if the subject's maximum power value is required to generate training data.

[0162] [Predictive behavior indicating potential improvement in blood glucose levels] Incidentally, among the six subjects corresponding to the six points shown in Figure 18, the top two subjects with the longest exercise time reached (improved) the normal blood glucose level after 12 weeks, while of the next two subjects with the longest exercise time, only one of them reached (improved) the normal blood glucose level after 12 weeks. Furthermore, the remaining two subjects with the shortest exercise time did not reach the normal blood glucose level after 12 weeks. Based on this data, the length of exercise time (horizontal axis in Figure 18) can be divided into zones corresponding to the probability of blood glucose levels reaching the normal range. Therefore, the health management system 100 may present (display) to the user the probability that blood glucose levels will reach the normal range after a predetermined period (hereinafter also referred to as the expected improvement in blood glucose levels). Figure 23 shows an example of a display screen for the expected improvement in blood glucose levels.

[0163] The following describes the process of predicting the expected improvement in blood glucose levels, which is necessary to display a screen like the one shown in Figure 23. Figure 24 is a flowchart of the process for predicting the expected improvement in blood glucose levels.

[0164] First, the calculation unit 26 calculates the user's exercise time (S81). Specifically, the calculation unit 26 calculates the cumulative value of exercise time over a recent period (for example, one week). The method for calculating exercise time is as described above.

[0165] Next, the prediction unit 28 predicts the probability (hereinafter also referred to as the probability of reaching the target range) that the user's blood glucose level will reach the target range after a predetermined period (for example, 12 weeks) based on the exercise time calculated in step S81. Reaching the target range means, for example, that the blood glucose level goes from exceeding the upper limit of the target range (10⁹ in the case of blood glucose) to falling below the upper limit.

[0166] For example, probability information, in which the probability of reaching a certain zone is predetermined for each zone of exercise time, is stored in the storage unit 23 beforehand. The prediction unit 28 can then refer to this probability information to predict the probability of reaching a certain zone, depending on which zone the calculated exercise time belongs to.

[0167] The probability of achieving the target is defined for each zone of exercise duration. For example, if the exercise duration is 110 minutes / week or more, the probability of achieving the target is 100%; if the exercise duration is between 75 minutes / week and 110 minutes / week, the probability of achieving the target is 50%; and if the exercise duration is less than 75 minutes / week, the probability of achieving the target is 0%. This probability of achieving the target can be generated, for example, based on the data of the six subjects shown in Figure 18. If data from a larger number of subjects than those in Figure 18 is available, it is possible to generate more detailed probability of achieving the target. In other words, the zones can be further subdivided, and the accuracy of the probabilities can be improved.

[0168] Next, the output unit 27 outputs fourth information indicating the predicted probability of arrival (S83). The fourth information output by the output unit 27 is transmitted to the display device 30 by the communication unit 21, and the communication unit 33 of the display device 30 receives the fourth information.

[0169] Next, the display processing unit 36 ​​displays the arrival probability (information related to the fourth information) on the display unit 32 based on the received third information (S84). In other words, the display unit 32 displays the arrival probability in response to a command from the display processing unit 36. The display processing unit 36 ​​displays the predicted arrival probability by displaying the calculated user's exercise time on a chart showing the categories of exercise time lengths indicated by the arrival probability information, for example, as shown in Figure 23.

[0170] In step S82, the prediction unit 28 can also predict how the probability of reaching the goal will change if the user's exercise time changes. Specifically, based on the probability of reaching the goal information, it can predict how much the probability of reaching the goal will increase if the exercise time is extended. In this case, in step S84, the display processing unit 36 ​​can display on the display unit 32 how much the probability of reaching the goal will increase if the exercise time is extended. In the example in Figure 23, it is shown that increasing the exercise time by +60 [minutes / week] increases the probability of reaching the goal to 50%, and increasing the exercise time by +90 [minutes / week] increases the probability of reaching the goal to 100%.

[0171] In step S82, the prediction unit 28 can also predict how much the probability of reaching the destination will decrease if the exercise time is shortened. In this case, in step S84, the display processing unit 36 ​​can display on the display unit 32 how much the probability of reaching the destination will decrease if the exercise time is shortened.

[0172] [Example 1 of the functional configuration of a health management system] In the above embodiment, the calculation of %VO2max, the estimation of VO2max, and the prediction of VO2max were mainly performed by the server device 20. In other words, the health management system 100 was mainly realized by the server device 20, which included an acquisition unit 24, an estimation unit 25, a calculation unit 26, an output unit 27, and a prediction unit 28. However, in the health management system 100, the calculation of %VO2max, the estimation of VO2max, and the prediction of VO2max may also be performed by the electric assist bicycle 10. Figure 25 shows a modified example 1 of the functional configuration of the health management system 100.

[0173] As shown in Figure 25, the health management system 100a comprises an electric assist bicycle 10a and a display device 30a. The main difference between the electric assist bicycle 10a and the electric assist bicycle 10 is the configuration of the control unit 16a.

[0174] The control unit 16a is a control device implemented by a microcomputer or processor. The control unit 16a comprises, as functional components, an acquisition unit 16b, an estimation unit 16c, a calculation unit 16d, an output unit 16e, and a prediction unit 16f. The functions of the acquisition unit 16b, estimation unit 16c, calculation unit 16d, output unit 16e, and prediction unit 16f are realized by the execution of a computer program (software) stored in the storage unit 18 by the hardware, such as a processor or microcomputer, that constitutes the control unit 16a.

[0175] The acquisition unit 16b, estimation unit 16c, calculation unit 16d, output unit 16e, and prediction unit 16f can perform the same processing as the acquisition unit 24, estimation unit 25, calculation unit 26, output unit 27, and prediction unit 28. In the above embodiment, the acquisition unit 24, estimation unit 25, calculation unit 26, output unit 27, and prediction unit 28 may be replaced with the acquisition unit 16b, estimation unit 16c, calculation unit 16d, output unit 16e, and prediction unit 16f.

[0176] Another difference between the electric assist bicycle 10a and the electric assist bicycle 10 is that the communication unit 19a communicates with the communication unit 33a of the display device 30a, and exercise intensity information, exercise time information, and maximum oxygen consumption information are provided from the electric assist bicycle 10a to the display device 30a. The communication unit 19a is a communication circuit that performs short-range wireless communication with the communication unit 33a according to a communication standard such as BLE (Bluetooth® Low Energy) or Wi-Fi®. If the display device 30a is a cycle computer provided by the electric assist bicycle 10a, the communication unit 19a may be a communication circuit that performs wired communication with the communication unit 33a.

[0177] Thus, the health management system 100a may be implemented by an electric assist bicycle 10a including an acquisition unit 16b, an estimation unit 16c, a calculation unit 16d, an output unit 16e, and a prediction unit 16f. In the case where the display device 30a in the health management system 100a is a cycle computer provided by the electric assist bicycle 10a, the health management system 100a can be said to be implemented by an electric assist bicycle 10a including an acquisition unit 16b, an estimation unit 16c, a calculation unit 16d, an output unit 16e, a prediction unit 16f, and a display processing unit 36.

[0178] [Variation 2 of the functional configuration of the health management system] Furthermore, in the health management system 100, the calculation of %VO2max, the estimation of VO2max, and the prediction may be performed by the display device 30. Figure 26 shows a modified example 2 of the functional configuration of the health management system 100.

[0179] As shown in Figure 26, the health management system 100b comprises an electric assist bicycle 10b and a display device 30b. The main difference between the display device 30b and the display device 30 lies in the configuration of the information processing unit 34b.

[0180] The information processing unit 34b performs information processing for displaying information related to the user's exercise intensity, as well as calculating %VO2max and estimating VO2max. The information processing unit 34b is implemented by, for example, a microcomputer, but may also be implemented by a processor. The information processing unit 34b comprises, as functional components, an acquisition unit 34c, an estimation unit 34d, a calculation unit 34e, an output unit 34f, a prediction unit 34g, and a display processing unit 36. The functions of the acquisition unit 34c, estimation unit 34d, calculation unit 34e, output unit 34f, prediction unit 34g, and display processing unit 36 ​​are realized by the execution of a computer program (software) stored in the storage unit 35 by hardware such as a microcomputer or processor that constitutes the information processing unit 34b.

[0181] The acquisition unit 34c, estimation unit 34d, calculation unit 34e, output unit 34f, and prediction unit 34g can perform the same processing as the acquisition unit 24, estimation unit 25, calculation unit 26, output unit 27, and prediction unit 28. In the above embodiment, the acquisition unit 24, estimation unit 25, calculation unit 26, output unit 27, and prediction unit 28 may be replaced with the acquisition unit 34c, estimation unit 34d, calculation unit 34e, output unit 34f, and prediction unit 34g.

[0182] Another difference between the display device 30b and the display device 30 is that the communication unit 33b communicates with the communication unit 19b of the electric assist bicycle 10b, and torque values, cadence values, etc., are provided from the electric assist bicycle 10b to the display device 30b. The communication unit 33b is a communication circuit that performs short-range wireless communication with the communication unit 19b according to a communication standard such as BLE or Wi-Fi (registered trademark). If the display device 30b is a cycle computer provided by the electric assist bicycle 10, the communication unit 33b may be a communication circuit that performs wired communication with the communication unit 19b.

[0183] Thus, the health management system 100b may be implemented by a display device 30b (a portable terminal or cycle computer) that includes an acquisition unit 34c, an estimation unit 34d, a calculation unit 34e, an output unit 34f, and a prediction unit 34g.

[0184] [Variation 3 of the functional configuration of the health management system] In the health management system 100, the electric assist bicycle 10 and the display device 30 do not have a communication unit that connects to a wide-area communication network, and it is conceivable that a mobile terminal may be used as a relay for communication between the electric assist bicycle 10 and the display device 30 and the server device 20. Figure 27 shows a modified example 3 of the functional configuration of the health management system 100.

[0185] As shown in Figure 27, the health management system 100c comprises an electric assist bicycle 10c, a server device 20, a display device 30c, an administrator terminal 40, and a mobile terminal 50.

[0186] Since the only difference between the electric assist bicycle 10c and the electric assist bicycle 10c is the communication unit 19c, the diagrams of components other than the communication unit 19c are omitted. The communication unit 19c is a communication circuit that performs short-range wireless communication with the first communication unit 51 of the mobile terminal 50, for example, according to a communication standard such as BLE or Wi-Fi (registered trademark).

[0187] Since the display device 30c differs from the display device 30 only in its communication unit 33c, the other components are not shown in the diagram. The communication unit 33c is a communication circuit that performs short-range wireless communication with the first communication unit 51 of the mobile terminal 50, for example, according to a communication standard such as BLE or Wi-Fi (registered trademark).

[0188] The mobile terminal 50 is a general-purpose mobile terminal such as a smartphone or tablet. The mobile terminal 50 includes a first communication unit 51 and a second communication unit 52.

[0189] The first communication unit 51 is a communication circuit that performs short-range wireless communication with the communication unit 19c of the electric assist bicycle 10c and the communication unit 33c of the display device 30c.

[0190] The second communication unit 52 is a communication circuit that communicates with the communication unit 21 of the server device 20 via a wide-area communication network. The wide-area communication network here includes mobile communication networks and the internet.

[0191] Such a health management system 100c can perform the same operations as the health management system 100.

[0192] [Effects, etc.] The following describes examples of inventions that can be obtained from the disclosures in this specification, and explains the effects and other benefits that can be obtained from these examples.

[0193] Invention 1 is a health management system 100 comprising: an acquisition unit 24 that acquires first information indicating either a target value for exercise intensity when a user rides an electric assist bicycle 10 or the amount of improvement in the user's health-related test values; a prediction unit 28 that predicts second information indicating the other of the target value for exercise intensity and the amount of improvement in health-related test values ​​based on the acquired first information and a predetermined prediction model using the first information; and an output unit 27 that outputs the predicted second information.

[0194] Such a health management system 100 can predict information that will help users improve their health-related test results.

[0195] Invention 2 is a health management system 100 of Invention 1, wherein the acquisition unit 24 further acquires third information indicating at least one of health-related test values, other health-related test values ​​of the user, user attribute information, and user medical interview data, and the prediction unit 28 predicts second information based on the acquired first and third information and a predetermined prediction model using the first and third information.

[0196] Such a health management system 100 can predict information that will help the user improve their health test results, using at least one of the user's other health test results, user attribute information, and user medical questionnaire data.

[0197] Invention 3 is a health management system 100 of Invention 1 or 2, further comprising a display processing unit 36 ​​that displays information related to the second information on a display unit 32 based on the output second information.

[0198] Such a health management system 100 can display information that helps users improve their health-related test results.

[0199] Invention 4 is a health management system 100 that is one of Inventions 1 to 3, wherein the first information indicates a target value related to exercise intensity, and the second information indicates the amount of improvement in health-related test values.

[0200] Such a health management system 100 can predict the amount of improvement in health-related test values ​​when target values ​​for exercise intensity are achieved.

[0201] Invention 5 is a health management system 100 that is one of Inventions 1 to 3, wherein the first information indicates the amount of improvement in health-related test values, and the second information indicates a target value related to exercise intensity.

[0202] Such a health management system 100 can predict target values ​​for exercise intensity that need to be achieved in order to realize improvements in health-related test results.

[0203] Invention 6 is a health management system 100 according to any of Inventions 1 to 5, wherein the target value for exercise intensity is defined by the exercise time, which is the time during which the exercise intensity is equal to or greater than a standard value while the user is riding an electric assist bicycle 10.

[0204] Such a health management system 100 can predict the amount of improvement in test results from exercise time, or predict the amount of exercise time required to achieve the desired improvement in test results.

[0205] Invention 7 is a health management system 100 of Invention 6, wherein the predetermined prediction model is a model that shows the relationship between one or more features, including exercise time, and the amount of improvement in health-related test values. Such a prediction model is a first prediction formula, a first machine learning model, or a second machine learning model, etc.

[0206] Such a health management system 100 can use a predetermined predictive model regarding exercise time to predict information that will help users improve their health-related test results.

[0207] Invention 8 is a health management system 100 according to any of Inventions 1 to 5, in which the target value for exercise intensity is determined by the total amount of energy the user expends while riding the electric assist bicycle 10.

[0208] Such a health management system 100 can predict the amount of improvement in test results from the total energy intake, or predict the total amount of energy required to achieve the improvement in test results.

[0209] Invention 9 is a health management system 100 of Invention 8, wherein the predetermined predictive model is a model that shows the relationship between one or more features, including total energy amount, and the amount of improvement in health-related test values. Such a predictive model is a second predictive formula, a first machine learning model, or a second machine learning model, etc.

[0210] Such a health management system 100 can use a predetermined predictive model regarding total energy intake to predict information that will help the user improve their health test results.

[0211] Invention 10 is a health management system 100 of any of Inventions 1 to 9, wherein the acquisition unit 24 further acquires the current values ​​of the user's health-related test results, and the prediction unit 28 predicts second information based on the acquired first information and a predetermined prediction model determined by the acquired current values ​​of the health-related test results.

[0212] Such a health management system 100 can take into account the user's current health test results and predict information that will help the user improve their health test results.

[0213] Invention 11 further comprises an estimation unit 25 and a calculation unit 26, and in data collection for generating a predetermined predictive model, the exercise intensity of multiple other users is calculated, and in calculating the exercise intensity of other users, an acquisition unit 24 acquires data related to the power values ​​applied to the pedals by other users riding the electric assist bicycle 10, an estimation unit 25 estimates the period during which the electric assist bicycle 10 is traveling uphill based on the acquired data and calculates the maximum power value during the estimated period, and a calculation unit 26 calculates the user's exercise intensity based on the calculated maximum power value, which is a health management system 100 of Inventions 1 to 10.

[0214] Such a health management system 100 can use an electric assist bicycle 10 to collect data for generating a predetermined predictive model.

[0215] Invention 12 further comprises a calculation unit 26 and a display processing unit 36, wherein the acquisition unit 24 acquires data related to the power values ​​applied to the pedals 13 by a user riding an electric assist bicycle 10, the calculation unit 26 calculates the user's exercise intensity based on the acquired data and calculates the time during which the calculated exercise intensity exceeds a standard value as the exercise time, the prediction unit 28 predicts the probability that the user's health-related test values ​​will reach a standard range after a predetermined period of time has elapsed based on the calculated exercise time, and the display processing unit 36 ​​displays the probability as fourth information on the display unit 32, making it a health management system 100 of any of Inventions 1 to 12.

[0216] Such a health management system 100 can predict the likelihood of improvement in health-related test results if the current exercise time is maintained. In other words, the health management system 100 can predict information that will help the user improve their health-related test results.

[0217] Invention 13 is a health management system 100 of Invention 12, wherein the prediction unit 28 further predicts how the probability will change when it is assumed that the user's exercise time has changed, and the display processing unit 36 ​​displays how the probability has changed on the display unit 32.

[0218] Such a health management system 100 can predict the potential improvement in health-related test results if current exercise time is changed. In other words, the health management system 100 can predict information that users can use to improve their health-related test results.

[0219] Invention 14 is a health management method performed by a computer such as a health management system 100. The health management method includes an acquisition step of acquiring first information indicating either a target value for exercise intensity when a user rides an electric assist bicycle 10, or the amount of improvement in the user's health-related test values; a prediction step of predicting second information indicating the other, a target value for exercise intensity, or the amount of improvement in health-related test values, based on the acquired first information and a predetermined prediction model using the first information; and an output step of outputting the predicted second information.

[0220] This type of health management method can predict information that will help users improve their health test results.

[0221] (Other embodiments) Although embodiments have been described above, the present invention is not limited to the embodiments described above.

[0222] For example, in the above embodiment, the health management system was implemented by multiple devices. In this case, the components of the health management system (especially the functional components) may be distributed among the multiple devices in any way.

[0223] Furthermore, the health management system may be implemented by a single device. For example, the health management system may be implemented as a single device corresponding to the electric assist bicycle, server device, or display device in the above embodiment.

[0224] Furthermore, in the above embodiment, the processing performed by a specific processing unit may be performed by another processing unit. Also, the order of multiple processing units may be changed, or multiple processing units may be executed in parallel.

[0225] Furthermore, in the above embodiment, each component may be realized by executing a software program suitable for each component. Each component may also be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.

[0226] Furthermore, each component may be implemented by hardware. For example, each component may be a circuit (or integrated circuit). These circuits may form a single circuit as a whole, or they may be separate circuits. Also, each of these circuits may be a general-purpose circuit or a dedicated circuit.

[0227] Furthermore, general or specific embodiments of the present invention may be implemented as a system, apparatus, method, integrated circuit, computer program, or recording medium such as a computer-readable CD-ROM. Alternatively, they may be implemented as any combination of a system, apparatus, method, integrated circuit, computer program, and recording medium.

[0228] For example, the present invention may be implemented as an electric assist bicycle, server device, display device, or administrator terminal according to the above embodiment. Furthermore, the present invention may be implemented as a health management method executed by a computer, such as a health management system, or as a program for causing a computer to execute such a health management method. The present invention may also be implemented as a computer-readable non-temporary recording medium on which such a program is stored.

[0229] Furthermore, the present invention may be implemented as a method for generating machine learning models to be executed by a computer, such as a health management system, or as a program for causing a computer to execute such a method for generating machine learning models. The present invention may also be implemented as a computer-readable non-temporary recording medium on which such a program is recorded.

[0230] Furthermore, the present invention also includes forms obtained by applying various modifications to each embodiment that a person skilled in the art could conceive, or forms realized by arbitrarily combining the components and functions of each embodiment without departing from the spirit of the present invention. [Explanation of Symbols]

[0231] 10, 10a, 10b, 10c Electric-assist bicycles 16b, 24, 34c acquisition part 16c, 25, 34d Estimation section 16d, 26, 34e calculation section 16e, 27, 34f output section 16f, 28, 34g prediction section 32, 42 display section 36, 46 Display Processing Unit 100, 100a, 100b, 100c Health Management System

Claims

1. An acquisition unit that acquires first information indicating a target value for exercise intensity when a user rides an electric assist bicycle, A prediction unit predicts second information indicating the amount of improvement in the user's health-related test values ​​based on the acquired first information and a predetermined prediction model using the first information. An output unit that outputs the predicted second information, Estimation unit, It includes a calculation unit, In the data collection for generating the predetermined predictive model, the exercise intensity of multiple other users is calculated. In calculating the exercise intensity of the other user, The acquisition unit acquires data related to the power values ​​applied to the pedals by the other user riding the electric assist bicycle. The estimation unit estimates the period during which the electric assist bicycle is traveling uphill based on the acquired data, and calculates the maximum power value during the estimated period. The calculation unit calculates the user's exercise intensity based on the calculated maximum power value. Health management system.

2. An acquisition unit that acquires first information indicating the amount of improvement in the user's health-related test values, A prediction unit predicts second information indicating a target value for exercise intensity when the user rides an electric assist bicycle, based on the acquired first information and a predetermined prediction model using the first information. An output unit that outputs the predicted second information, Estimation unit, It includes a calculation unit, In the data collection for generating the predetermined predictive model, the exercise intensity of multiple other users is calculated. In calculating the exercise intensity of the other user, The acquisition unit acquires data related to the power values ​​applied to the pedals by the other user riding the electric assist bicycle. The estimation unit estimates the period during which the electric assist bicycle is traveling uphill based on the acquired data, and calculates the maximum power value during the estimated period. The calculation unit calculates the user's exercise intensity based on the calculated maximum power value. Health management system.

3. An acquisition unit that acquires first information indicating a target value for exercise intensity when a user rides an electric assist bicycle, A prediction unit predicts second information indicating the amount of improvement in the user's health-related test values ​​based on the acquired first information and a predetermined prediction model using the first information. An output unit that outputs the predicted second information, Calculation unit, It includes a display processing unit, The acquisition unit acquires data related to the power values ​​applied to the pedals by the user riding the electric assist bicycle. The calculation unit calculates the user's exercise intensity based on the acquired data, and calculates the time during which the calculated exercise intensity is equal to or greater than a standard value as the exercise time. The prediction unit predicts, based on the calculated exercise time, the probability that the user's health-related test values ​​will reach a standard range after a predetermined period of time has elapsed. The display processing unit displays the probability as fourth information on the display unit. Health management system.

4. An acquisition unit that acquires first information indicating the amount of improvement in the user's health-related test values, A prediction unit predicts second information indicating a target value for exercise intensity when the user rides an electric assist bicycle, based on the acquired first information and a predetermined prediction model using the first information. An output unit that outputs the predicted second information, Calculation unit, It includes a display processing unit, The acquisition unit acquires data related to the power values ​​applied to the pedals by the user riding the electric assist bicycle. The calculation unit calculates the user's exercise intensity based on the acquired data, and calculates the time during which the calculated exercise intensity is equal to or greater than a standard value as the exercise time. The prediction unit predicts, based on the calculated exercise time, the probability that the user's health-related test values ​​will reach a standard range after a predetermined period of time has elapsed. The display processing unit displays the probability as fourth information on the display unit. Health management system.

5. The prediction unit further predicts how the probability will change when it is assumed that the user's exercise time has changed. The display processing unit displays on the display unit how the probability changes. The health management system according to claim 3 or 4.

6. A health management method performed by a computer, An acquisition step to obtain first information indicating a target value for exercise intensity when a user rides an electric assist bicycle, A prediction step in which a second piece of information indicating the amount of improvement in the user's health test values ​​is predicted based on the acquired first piece of information and a predetermined prediction model using the first piece of information, An output step that outputs the predicted second information, The data collection for generating the predetermined predictive model includes a calculation step of calculating the exercise intensity of multiple other users. In the calculation step described above, The system acquires data related to the power values ​​applied to the pedals by the other user riding the electric assist bicycle. Based on the acquired data, the period during which the electric assist bicycle is traveling uphill is estimated, and the maximum power value during the estimated period is calculated. Based on the calculated maximum power value, the user's exercise intensity is calculated. Health management method.

7. A health management method performed by a computer, An acquisition step to obtain first information showing the amount of improvement in the user's health-related test values, A prediction step in which, based on the acquired first information and a predetermined prediction model using the first information, a second information indicating a target value for exercise intensity when the user rides an electric assist bicycle is predicted, An output step that outputs the predicted second information, The data collection for generating the predetermined predictive model includes a calculation step of calculating the exercise intensity of multiple other users. In the calculation step described above, The system acquires data related to the power values ​​applied to the pedals by the other user riding the electric assist bicycle. Based on the acquired data, the period during which the electric assist bicycle is traveling uphill is estimated, and the maximum power value during the estimated period is calculated. Based on the calculated maximum power value, the user's exercise intensity is calculated. Health management method.

8. A health management method performed by a computer, An acquisition step to obtain first information indicating a target value for exercise intensity when a user rides an electric assist bicycle, A prediction step in which a second piece of information indicating the amount of improvement in the user's health test values ​​is predicted based on the acquired first piece of information and a predetermined prediction model using the first piece of information, An output step that outputs the predicted second information, The steps include obtaining data related to the power values ​​applied to the pedals by the user riding the electric assist bicycle, The steps include: calculating the user's exercise intensity based on the acquired data, and determining the exercise time as the time during which the calculated exercise intensity is equal to or greater than a standard value; A step of predicting the probability that the user's health test values ​​will reach a standard range after a predetermined period of time, based on the calculated exercise time; The step includes displaying the aforementioned probability as fourth information on the display unit. Health management method.

9. A health management method performed by a computer, An acquisition step to obtain first information showing the amount of improvement in the user's health-related test values, A prediction step in which, based on the acquired first information and a predetermined prediction model using the first information, a second information indicating a target value for exercise intensity when the user rides an electric assist bicycle is predicted, An output step that outputs the predicted second information, The steps include obtaining data related to the power values ​​applied to the pedals by the user riding the electric assist bicycle, The steps include: calculating the user's exercise intensity based on the acquired data, and determining the exercise time as the time during which the calculated exercise intensity is equal to or greater than a standard value; A step of predicting the probability that the user's health test values ​​will reach a standard range after a predetermined period of time, based on the calculated exercise time; The step includes displaying the aforementioned probability as fourth information on the display unit. Health management method.

10. A program for causing the computer to execute the health management method described in any one of claims 6 to 9.

Images