Prediction system, prediction program, and prediction method

Abstract

An object of the present invention is to provide a novel technique capable of predicting an activity amount in consideration of various physical activities in a day.SOLUTION: In order to solve the above problem, the present invention provides a prediction system for predicting an activity amount for one day, the prediction system including a step count management unit and an activity amount prediction unit, wherein the step count management unit acquires a step count of a user, and the activity amount prediction unit calculates a predicted activity amount for one day based on the step count and a prediction means.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] The Ministry of Health, Labor and Welfare recommends physical activity of 3 METs or more, 23 METs hours per week (= METs × exercise time (h)) to maintain health. An example of a technology for calculating such activity amount is proposed in, for example, Patent Document 1.

[0003] Patent Document 1 discloses a method of counting the number of steps taken by a user within a predetermined unit time, calculating an average stride length within the unit time using the counted number of steps, calculating the user's walking speed using the average stride length and number of steps, and calculating the user's exercise intensity within the unit time from the calculated walking speed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2008-81553 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the invention described in Patent Document 1 could only calculate the amount of activity based on the number of steps taken by a user in a unit time, and could not predict the amount of activity based on various physical activities in a day. In contrast, the present invention has discovered a prediction method that can predict the amount of activity taking into account various physical activities in a day.

[0006] In view of the above circumstances, an object of the present invention is to provide a novel technique that can predict the amount of activity taking into account various physical activities in one day. [Means for solving the problem]

[0007] In order to solve the above problem, the present invention provides a prediction system for predicting an amount of activity taking into account various physical activities in a day, the prediction system including a step count management unit and an activity amount prediction unit, the step count management unit acquiring the number of steps of a user, and the activity amount prediction unit calculating a predicted activity amount for the day based on the number of steps and a prediction means.

[0008] With this configuration, the amount of activity per day can be predicted using only the number of steps.

[0009] In a preferred embodiment of the present invention, the prediction means is a prediction function having a step count variable and an age variable, and the weight of the age variable is a negative number.

[0010] In a preferred embodiment of the present invention, the prediction function is a function in which the absolute value of the weight of the age variable is greater than the absolute value of the weight of the step count variable.

[0011] In a preferred embodiment of the present invention, the prediction function is a function in which the age variable has a weight of -10^(-1) to -10^(-2), and the step count variable has a weight of 10^(-4) to 10^(-3).

[0012] With this configuration, the amount of activity can be predicted using age in addition to the number of steps, thereby enabling the amount of activity to be calculated with higher accuracy.

[0013] In a preferred embodiment of the present invention, the prediction function has two to three constants.

[0014] With this configuration, it is possible to calculate an appropriate amount of activity.

[0015] In a preferred embodiment of the present invention, the prediction system further includes a prediction means creation unit, which creates the prediction function using a plurality of data including the number of steps, the product of activity intensity and activity time, and age.

[0016] With this configuration, it is possible to create a prediction function in which the number of steps and age are used as explanatory variables and the amount of activity is used as the objective function.

[0017] In a preferred embodiment of the present invention, the prediction means creating section creates the prediction function using the data in which the activity intensity is equal to or greater than a predetermined level.

[0018] With this configuration, a prediction function is created using only data that is more important as activity content, which reduces noise and allows for the creation of a more accurate prediction function.

[0019] In a preferred embodiment of the present invention, the prediction system further includes a step count prediction unit, which calculates the remaining number of steps required for the day based on the user's step count history, target activity amount, and the prediction function.

[0020] In a preferred embodiment of the present invention, the prediction system further includes a display processing unit that displays the remaining number of steps required for one day when the predicted activity amount has not reached a predetermined threshold.

[0021] By configuring in this way, the remaining activities required to achieve the target amount of activity become clear, and the user's motivation to continue the activity can be increased.

[0022] In a preferred embodiment of the present invention, the prediction system further includes a suggestion unit, and stores in a database a correspondence table in which activity intensity and activity content correspond to each other. The suggestion unit identifies the activity content and activity time as the exercise content that the user should perform based on the target activity amount, the predicted activity amount, and the correspondence table.

[0023] By configuring the system in this way, the remaining activities required to achieve the goal become clearer, and the user's motivation to continue the activities can be further increased.

[0024] In a preferred embodiment of the present invention, the prediction system further includes a display processing unit, wherein the step count management unit registers the step count history and time periods for a day, and the display processing unit performs display processing to prompt the user to input individual activity history information if there is a time period for which the step count history is not registered.

[0025] This configuration can prevent omission of input of the user's activity amount, thereby enabling more accurate prediction of the activity amount. [Effects of the Invention]

[0026] The present invention can provide a novel technique that can predict the amount of activity taking into account various physical activities in a day. [Brief explanation of the drawings]

[0027] [Figure 1] 1 is a block diagram showing a configuration of a system according to the present invention; [Figure 2] FIG. 1 is a hardware configuration diagram of a system according to the present invention. [Figure 3] FIG. 1 is a functional block diagram according to an embodiment of the present invention. [Figure 4] 1 is an example of a processing flowchart according to an embodiment of the present invention. [Figure 5] 10 is an example of a screen displayed on a user terminal device according to an embodiment of the present invention. [Figure 6] 1 is an example of a data set used to create a function of the present invention. [Figure 7] 1 is an example of a data set used to create a function of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0028] The present invention will be described in more detail below with reference to the accompanying drawings, in which preferred embodiments are shown, but which may be embodied in many different forms and are not limited to the embodiments set forth herein.

[0029] For example, although the configuration, operation, etc. of the prediction system are described in this embodiment, similar effects can be achieved by the executed method, device, computer program, etc. Furthermore, the program may be stored on a recording medium. By using this recording medium, the program can be installed on, for example, a computer, thereby configuring a prediction device or a prediction system. Here, the recording medium storing the program may be a non-transitory recording medium such as a CD-ROM.

[0030] <1. Overview of the present invention> The present invention relates to a system for predicting a user's daily activity amount using a user's step count and a prediction means. The present invention predicts a user's daily activity amount by using the step count to calculate an activity amount (hereinafter referred to as a predicted activity amount) that is close to the actual activity amount, taking into account various physical activities in a day. Here, the activity amount in this invention is the activity intensity (METs) multiplied by the actual working time (hours) of the activity.

[0031] In this embodiment, the amount of activity of a user in a day is more accurately predicted by using the amount of activity based on the number of steps taken by a user carrying a user terminal device on which the app of the present invention is installed, and the amount of activity based on strenuous exercise performed when the user is not carrying the user terminal device.

[0032] Furthermore, in this embodiment, exercise content for achieving the target activity amount is suggested to the user based on the most recent predicted activity amount for the day and the target activity amount for the day.

[0033] <1.1. System configuration of the present invention> Fig. 1 is a block diagram showing the configuration of a system of the present invention. As shown in Fig. 1, a prediction system 0 includes a prediction device 1 and a user terminal device 3, and is configured to be able to communicate via a communication network NW. The communication network NW in the present invention is an IP (Internet Protocol) network, but there is no limitation on the type of communication protocol, and there is also no limitation on the type or scale of the network.

[0034] A general-purpose server computer, a personal computer, or the like can be used as the prediction device 1. A smartphone, a tablet terminal, a personal computer, a wearable device, or the like can be used as the user terminal device 3. The prediction device 1 may also be configured with multiple computers that are capable of sending and receiving information via a communication network NW or another network.

[0035] <1.2. Hardware Configuration> 2 is a hardware configuration diagram of the prediction system 0. As shown in FIG. 2(a), the server 10 (prediction device 1) includes a processing unit 101, a storage unit 102, and a communication unit 103.

[0036] The processing unit 101 has one or more processors such as a CPU capable of executing an instruction set, and controls the overall operation and processing of the prediction device 1 by executing the prediction program according to the present invention, an OS, and other applications. The storage unit 102 has a volatile memory such as a RAM capable of storing an instruction set, and a non-volatile recording medium such as an HDD or SSD capable of recording an OS and a generation program according to the present invention. The communication unit 103 has a communication interface device with the communication network NW, and controls communication with the communication network NW to input and output information.

[0037] As shown in FIG. 2(b), the terminal device 9 (user terminal device 3) includes a processing unit 91, a storage unit 92, a communication unit 93, an input unit 94, and an output unit 95.

[0038] The processing unit 91 has one or more processors, such as a CPU, that can execute an instruction set, and controls the overall operation and processing of the terminal device 9 by executing a prediction device utilization program, an OS, and other applications for using the prediction device 1. The storage unit 92 has a volatile memory such as a RAM capable of storing an instruction set, and a non-volatile recording medium such as an HDD or SSD capable of recording an OS, a prediction device utilization program, and the like. The communication unit 93 has a communication interface device for connecting to a network, and controls communication with the communication network NW to input and output information. The input unit 94 has an input device capable of input processing, such as a keyboard or a touch panel. The output unit 95 has a display device capable of display processing, such as a display.

[0039] <1.3. System Functional Configuration> Fig. 3 is a functional block diagram of the prediction device 1 in embodiment 1. As shown in Fig. 3, the prediction device 1 includes a registration unit 11, a step count management unit 12, an activity amount prediction unit 13, a prediction means creation unit 14, a step count prediction unit 15, a distance prediction unit 16, a proposal unit 17, an update unit 18, a display processing unit 19, and a database 2. This is a specific implementation of information processing by software (stored in a storage unit 102) by hardware (a processing unit 101).

[0040] Note that some or all of the functional components (units) of the prediction device 1 may be provided in the user terminal device 3, which is a client. For example, the user terminal device 3 may include a registration unit 11, a step count management unit 12, an activity amount prediction unit 13, a prediction means creation unit 14, a step count prediction unit 15, a distance prediction unit 16, a suggestion unit 17, an update unit 18, and a display processing unit 19, and the prediction device 1 may be a cloud storage that records and manages various data such as the daily activity history information described below. In this embodiment, the prediction system 0 is used via the user terminal device 3 that executes a prediction device utilization program, but the prediction device 1 may also be configured by installing the prediction program of the present invention in the user terminal device 3.

[0041] <1.4.Database 2> The database 2 includes a user-related information database 21 and a function creation database 22. The user-related information database 21 stores user information and daily activity history information. The function creation database 22 stores average activity history information as information used to create the prediction means. Note that the user-related information database 21 may also store average activity history information.

[0042] <1.4.1. User Information> The registration unit 11 registers user information, which is information about a user who uses the application of the present invention. The user information includes a user ID that uniquely identifies the user, a user name, sex, age, height, and weight.

[0043] <1.4.2. Daily activity history information> The daily activity history information is information indicating the daily activity history of each user. The daily activity history information includes a daily activity history ID that uniquely identifies the daily activity history information, a user ID, walking history information, movement history information, individual activity history information, device wearing time, and date.

[0044] <1.4.2.1. Walking history information> The walking history information is information about the user's walking history, and includes the number of steps for each time period and the total walking time. The time period can be set to any time period, for example, three-hour intervals.

[0045] <1.4.2.2. Movement History Information> The registration unit 11 registers movement history information, which is information indicating the amount of movement of the user. The movement history information includes the movement distance and the number of floors moved. In this embodiment, a calculation unit (not shown) calculates and registers the movement distance using the total number of steps based on the number of steps for each time period in the walking history information and the stride length based on the height of the user information. Note that an average stride length may be used as the stride length.

[0046] Furthermore, in this embodiment, the calculation unit calculates the travel distance using the stride length and the total number of steps, but the calculation unit may also obtain a history of the route traveled by the user and calculate the travel distance based on the route history.

[0047] <1.4.2.3. Individual Activity History Information> The registration unit 11 registers individual activity history information, which is information about individual activities performed when the user is not carrying the user terminal device 3. As the individual activity history information, the activity time (minutes) for each activity item and the activity intensity of the individual activity are registered. Here, the activity items are set as a major item, physical activity, and sub-items, daily activities and exercise. Furthermore, the activity intensity is set to one to eight levels, but the number of levels is not limited to this.

[0048] <1.4.3. Average Activity History Information> The average activity history information is information registered in advance to create the prediction means, and is information about the average of the user's activity history. The average activity history information includes an average activity history ID that uniquely identifies the average activity history information, a user ID, an average total number of steps based on walking history information, and an average activity time (minutes) for each activity intensity based on individual activity history information. In this embodiment, a 7-day average is used as the average total number of steps and exercise time, but there is no limitation on how the average is calculated, and a 5-day average, for example, may be used.

[0049] In this embodiment, the registration unit 11 may sequentially register the average activity history information. Specifically, each time an experiment is conducted to measure the amount of activity and walking, the registration unit 11 receives experimental data including the number of steps and the activity time for each activity intensity, and registers the average activity history information based on the average value of these data. In this embodiment, the registration unit 11 registers the average activity history information based on experimental data in which the terminal wearing time is equal to or longer than a predetermined time. Here, the predetermined time is set to a time (e.g., 400 minutes) that is sufficient to ensure that the user has worn the terminal device in order to measure the user's number of steps.

[0050] In a preferred embodiment of the present invention, the registration unit 11 registers average activity history information based on the predicted activity amount predicted by the activity amount prediction unit 13 and the individual activity history information. Specifically, the registration unit 11 acquires data including the number of steps and the activity time for each activity intensity based on the activity time for each activity intensity received from the user as the individual activity history information and the activity time obtained by dividing the predicted activity amount predicted by the activity amount prediction unit 13 by the activity intensity "3," assuming that the activity intensity is "3." Then, the registration unit 11 registers average activity history information based on the average value of these data.

[0051] <1.5. Step count management unit 12> The step count management unit 12 manages the number of steps of the user. The step count management unit 12 acquires the number of steps of the user. Furthermore, the step count management unit 12 registers walking history information based on the acquired number of steps.

[0052] <1.6. Activity amount prediction unit 13> The activity amount prediction unit 13 calculates a predicted activity amount using a prediction means, and predicts a predicted daily activity amount. The activity amount prediction unit 13 calculates the predicted activity amount based on the acquired number of steps and the prediction means. The activity amount prediction unit 13 also calculates the predicted daily activity amount based on the user's age. The activity amount prediction unit 13 also calculates the predicted activity amount based on individual activity history information.

[0053] <1.7. Prediction Means Creation Unit 14> The prediction means creation unit 14 creates a prediction means. In this embodiment, the prediction means creation unit 14 creates a prediction function as the prediction means. Details will be described later.

[0054] <1.8. Step Count Prediction Unit 15> The step count prediction unit 15 calculates the remaining number of steps required for one day. The step count prediction unit 15 calculates the remaining number of steps required for one day based on the target activity amount and the prediction means. In this embodiment, a daily target activity amount and a weekly target activity amount are set as the target activity amount, and a physical activity target activity amount and an exercise target activity amount are set as target activity amounts corresponding to the activity items, but some or all of the daily target activity amount, weekly target activity amount, physical activity target activity amount, and exercise target activity amount may also be set.

[0055] <1.9. Distance Prediction Unit 16> The distance prediction unit 16 calculates the remaining travel distance required for one day. The distance prediction unit 16 calculates the remaining travel distance required for one day based on the user's stride length and the remaining number of steps required for one day calculated by the step number prediction unit.

[0056] <1.10. Proposal section 17> The suggestion unit 17 specifies the exercise content to be suggested to the user. The suggestion unit 17 specifies the exercise content to be performed by the user based on the target activity amount and the predicted activity amount. In this embodiment, the suggestion unit 17 calculates the remaining activity amount required for one day based on the target activity amount and the predicted activity amount. Then, the suggestion unit 17 specifies the activity time and activity content corresponding to the activity amount as the exercise content to be performed by the user.

[0057] <1.11. Update part 18> The update unit 18 updates the parameters of the prediction means. The update unit 18 updates the parameters of the prediction means based on the average activity history information. Details will be described later.

[0058] <1.12. Display Processing Unit 19> The display processing unit 19 performs display processing of various screens and causes the display processing results to be displayed on the user terminal device 3. Specific screens will be described later.

[0059] <2. Prediction Function of the Present Invention> The process of creating and updating the prediction function of the present invention will be described in detail below. Figures 6 and 7 are diagrams showing an example of a data set used to create the prediction function of the present invention.

[0060] FIG. 6 is a diagram in which the seven-day average total number of steps of a user is plotted on the horizontal axis and activity time on the vertical axis for each activity intensity of physical activity (daily activities and exercise). FIG. 6 suggests that there is a positive correlation between the number of steps and activity amount. FIG. 7 is a diagram in which the age of a user is plotted on the horizontal axis and activity time on the vertical axis for each activity intensity of physical activity. FIG. 7 suggests that there is a negative correlation between age and activity amount. In this embodiment, a prediction function is created based on these data.

[0061] <2.1. Creating a prediction function> The prediction means creation unit 14 creates a prediction function. In this embodiment, the prediction means creation unit 14 creates the prediction function using a plurality of data including the number of steps, the product of activity intensity and activity time, and age. Specifically, the prediction means creation unit 14 creates the prediction function using a plurality of data including the number of steps, the product of activity intensity and activity time in a major activity item (physical activity), i.e., daily activities and exercise, and age.

[0062] More specifically, the prediction means creation unit 14 acquires the average total number of steps, the average activity time for each activity intensity equal to or greater than a predetermined activity intensity, and the age based on the user ID from multiple pieces of average activity history information.The prediction means creation unit 14 then performs multiple regression analysis based on the average total number of steps, the sum of the products of the activity intensities and the average activity time for each activity intensity, and the age, to create a prediction function having the activity amount as the objective variable and the number of steps and age as explanatory variables.Here, the predetermined activity intensity is set to, for example, activity intensity "3."

[0063] More specifically, in the prediction function, the weight of the age variable is a negative number. Even more specifically, in the prediction function, the absolute value of the weight of the age variable is greater than the absolute value of the weight of the step count variable. Even more specifically, in the prediction function, the age variable has a weight of -10^(-1) to -10^(-2), and the step count variable has a weight of 10^(-4) to 10^(-3). Even more specifically, the prediction function has a constant in the range of 2 to 3. Even more specifically, the prediction function is activity amount (at MEts) = 2.2595 + (0.0006 x step count) + (-0.021 x age). The coefficient of determination of this prediction function is 0.7, making it a highly accurate function.

[0064] In a preferred embodiment of the present invention, the prediction means creation unit 14 may create a prediction function for each predetermined age. Specifically, the prediction means creation unit 14 acquires the average value of the average total number of steps, the average value of the activity time for each activity intensity equal to or greater than a predetermined activity intensity, and the age from a plurality of pieces of average activity history information for which the age based on the user ID is the predetermined age. The prediction means creation unit 14 then performs multiple regression analysis based on the average total number of steps, the sum of the products of the activity intensities and the average activity time for each activity intensity, and the age, to create a prediction function for each predetermined age. Here, the predetermined age may be set to an age range such as the 60s, or a specific age such as 60 years old. This allows a prediction function to be used for each age group, and the predicted activity amount can be calculated with higher accuracy.

[0065] In a preferred embodiment of the present invention, the prediction means creation unit 14 may create a prediction function for each sub-item of an activity item. Specifically, the prediction means creation unit 14 acquires, for each activity item (daily activities and exercise) from the average activity history information, the average value of the average total number of steps, the average activity intensity and the average activity time for each activity intensity, and age. The prediction means creation unit 14 then performs multiple regression analysis based on the average total number of steps, the sum of the products of the average activity intensity and the average activity time for each activity intensity, and the age, to create a prediction function associated with each sub-item of the activity item. This allows the predicted activity amount for each activity item to be calculated based on the number of steps, making it easier to compare the predicted activity amount with the daily target activity amount and the weekly target activity amount.

[0066] In this embodiment, a multiple regression model is used as the prediction function, but the model is not limited to this and any known regression model can be used as appropriate. In this embodiment, a prediction function is created as a prediction means, but a machine learning model that is trained in advance by inputting the number of steps and age may also be used, or a correspondence table in which the number of steps and age correspond to the amount of activity.

[0067] <2.2. Updating the prediction function> The process of updating the prediction function created by the above process of the prediction means creating unit 14 will be described below.

[0068] The update unit 18 updates the parameters of the prediction function based on the average activity history information. In this embodiment, the update unit 18 updates the parameters of the prediction means at a predetermined timing. Specifically, the update unit 18 updates the weights of one or more variables of the prediction function based on the plurality of average activity history information at the predetermined timing, i.e., when a predetermined number of average activity history information has been registered. Here, the predetermined number is set to an amount that can sufficiently ensure the accuracy of the prediction function to be created. Specifically, 100 is set. Preferably, 100 to 1000 is set.

[0069] In a preferred embodiment of the present invention, the update unit 18 updates the parameters to make the prediction function more suitable for the individual. Specifically, the update unit 18 extracts daily activity history information for each user, calculates a weight for the prediction function based on the total number of steps, the total amount of activity, and the user's age in the daily activity history information, and registers the weight in association with the user.

[0070] <3. Processing flowchart of prediction method> A prediction method using the prediction system 0 of the present invention will be described with reference to Fig. 6. Fig. 6 is a processing flowchart showing the process in which the prediction system 0 calculates a predicted activity amount by substituting the number of steps acquired from a user terminal device 3 on which the app of the present invention is installed into a prediction function, and causes the user terminal device 3 to display a screen based on the predicted activity amount.

[0071] <3.1. Acquisition of user information> First, in step S1 (hereinafter, "step SX" will be abbreviated as "SX"), the registration unit 11 accepts and registers user information from the user terminal device 3. In this embodiment, the registration unit 11 accepts input of user name, sex, age, height, and weight from a user who has installed the app of the present invention, and registers the information in the database 2 as user information.

[0072] <3.2. Acquiring step count> In S2, the step count management unit 12 registers the number of steps of the user. In this embodiment, the step count management unit 12 acquires the number of steps measured using a well-known step counting technology provided in the app of the present invention. Then, the step count management unit 12 tallies the acquired number of steps for each predetermined time interval (time period), and registers the walking history information in the database 2, in which the tallied number of steps and the time period are associated with each other.

[0073] The step count management unit 12 may acquire the number of steps measured by an external step counting technology installed in the user terminal device 3.

[0074] <3.3. Registering individual activity history information> In S3, the registration unit 11 receives and registers individual activity history information as information regarding strenuous activities performed by the user when the user was not carrying the user terminal device 3. In this embodiment, the registration unit 11 receives and registers input of activity duration (minutes) for each activity intensity as individual activity history information from the user terminal device 3. Specifically, in this embodiment, the display processing unit 19 performs display processing on activity examples corresponding to the activity intensity, and displays them on the user terminal device 3 alongside the activity intensity.

[0075] In a preferred embodiment of the present invention, the registration unit 11 receives and registers the activity time (minutes) for each activity intensity for each activity item (daily activities and exercise). Note that the activity time for each activity intensity input as individual activity history information may be in hours.

[0076] <3.4. Calculation of predicted activity> In S4, the activity amount prediction unit 13 calculates the predicted activity amount using the prediction function created by the prediction means creation unit 14. In this embodiment, the activity amount prediction unit 13 calculates the predicted activity amount based on the number of steps acquired by the step count management unit 12, the age registered in S1, and the individual activity history information input in S3.

[0077] Specifically, the activity amount prediction unit 13 calculates a predicted activity amount by substituting the number of steps into a prediction function at a predetermined timing. The activity amount prediction unit 13 calculates a predicted activity amount up to the most recent time by substituting the total number of steps counted up to the most recent time in a day into the prediction function at the time interval at which the number of steps is counted by the step count management unit 12, which is the predetermined timing.

[0078] Furthermore, the activity amount prediction unit 13 may calculate the predicted activity amount for one day by substituting the total number of steps counted in one day into a prediction function at midnight, which is the predetermined timing.

[0079] In addition, the activity amount prediction unit 13 may calculate the predicted activity amount up to the time the app is launched by substituting the total number of steps tallied up to the time the app is launched in one day into a prediction function at the predetermined timing when the app of the present invention is launched.

[0080] Then, the activity amount prediction unit 13 calculates the predicted activity amount as the sum of the predicted activity amount calculated based on the number of steps and the activity amount based on the product of the activity intensity and activity time of the individual activity history information.

[0081] In this embodiment, the predicted activity amount is calculated as the sum of the predicted activity amount calculated based on the number of steps and the activity amount based on the product of the activity intensity and activity time in the individual activity history information. On the other hand, the activity amount prediction unit 13 may calculate the predicted activity amount for each activity item. Specifically, the activity amount prediction unit 13 calculates the predicted activity amount calculated based on the number of steps as the predicted activity amount for the activity item "daily activity." Furthermore, the activity amount prediction unit 13 calculates the activity amount based on the product of the activity intensity and activity time in the individual activity history information as the predicted activity amount for the activity item "exercise."

[0082] Additionally, the activity amount prediction unit 13 may calculate the predicted activity amount for each activity item using a prediction function created for each activity item. Specifically, the activity amount prediction unit 13 calculates the predicted activity amount calculated using the prediction function associated with daily activities as the predicted activity amount for the activity item "daily activities." Furthermore, the activity amount prediction unit 13 calculates the predicted activity amount for the activity item "exercise" as the sum of the predicted activity amount calculated using the prediction function associated with exercise and the activity amount based on the product of the activity intensity and activity time in the individual activity history information.

[0083] <3.5. Prediction of remaining steps and remaining distance> In S5, if the predicted activity amount calculated in S4 exceeds the target activity amount (YES in S5), the process proceeds to S10. On the other hand, if the predicted activity amount calculated in S4 does not exceed the target activity amount (NO in S5), the process proceeds to S6.

[0084] In this embodiment, the target activity amount is set to a predetermined value (e.g., 3.3 METs) for the predicted activity amount calculated in S4, but is not limited to this. For example, the target activity amount may be set only for the predicted activity amount obtained by substituting the number of steps and age into a prediction function.

[0085] In a preferred embodiment of the present invention, the target activity amount may be set based on the age input in S1. Specifically, if the user is under 65 years old, the target activity amount is set to "a total of 3.3 METs per day of physical activity (daily activities and exercise) with an activity intensity of 3 METs or more." On the other hand, if the user is 65 years old or older, the target activity amount is set to "a total of 2.1 METs per day of physical activity with an activity intensity of 3 METs or more."

[0086] In a preferred embodiment, a target activity amount may be set for each activity category based on the user's age. Specifically, if the user is under 65 years old, the target activity amount is set as follows: "a total of 3.3 METs per day for physical activities (daily activities and exercise) with an intensity of 3 METs or more" and "a total of 4 METs per week for exercise with an intensity of 3 METs or more." On the other hand, if the user is 65 years old or older, the target activity amount is set as follows: "a total of 2.1 METs per day for physical activities (daily activities and exercise) with an intensity of 3 METs or more" and "multi-component exercise, such as aerobic exercise, strength training, balance exercise, and flexibility exercise, for 3 days or more per week."

[0087] In a preferred embodiment, the daily and weekly target activity amounts may be set based on the user's age. Specifically, if the user is under 65 years old, the daily target activity amount is set to "a total of 3.3 METs for physical activity with an activity intensity of 3 METs or more," and the weekly target activity amount is set to "a total of 4 METs for exercise with an activity intensity of 3 METs or more." On the other hand, if the user is 65 years old or older, the daily target activity amount is set to "a total of 2.1 METs for physical activity (daily activities and exercise)."

[0088] If the user is under 65 years old, the daily target activity amount may be set to "0.6 METs in total activity amount for exercise with an activity intensity of 3 METs or more" instead of the weekly target activity amount.

[0089] In S6, the step count prediction unit 15 calculates the remaining number of steps required for one day. In this embodiment, the step count prediction unit 15 calculates the number of steps obtained by subtracting the predicted activity amount calculated in S4 from the target activity amount and substituting the result into a prediction function, as the remaining number of steps required for one day.

[0090] Note that the step count prediction unit 15 may calculate the remaining number of steps for one day using the walking history information, the target activity amount, and the prediction function. Specifically, the target number of steps required for one day may be calculated by substituting the target activity amount into the prediction function, and the remaining number of steps required for one day may be calculated by subtracting the total number of steps for each time period in the walking history information from the target number of steps required for one day.

[0091] In S7, the distance prediction unit 16 calculates the remaining distance to travel in one day. In this embodiment, the distance prediction unit 16 calculates the remaining distance to travel in one day based on the stride length based on the height of the user information and the remaining number of steps to be taken in one day calculated by the step number prediction unit 15. Here, the stride length based on the height may be, for example, height x 0.45.

[0092] The distance prediction unit 16 calculates the user's stride length based on the user's walking history information and movement history information, and calculates the remaining movement distance required for one day based on the stride length and the remaining number of steps required for one day. In this case, the user's stride length is calculated using the movement distance calculated from the user's route history as the movement history information.

[0093] <3.6. Identifying the proposal content> In S8, the suggestion unit 17 identifies the exercise content to be suggested to the user. In this embodiment, a correspondence table in which activity amounts and activity contents are associated with each other is stored in the database 2, and the suggestion unit 17 calculates the remaining activity amount required for one day based on the target activity amount and the predicted activity amount. Then, based on the correspondence table, the suggestion unit 17 identifies the activity time and activity content corresponding to the calculated activity amount as the exercise content to be performed by the user.

[0094] In a preferred embodiment of the present invention, the database 2 stores a correspondence table in which activity intensity and activity content are associated with each activity item, and the suggestion unit 17 calculates the remaining activity amount required for each activity item based on the daily target activity amount, weekly target activity amount, physical activity target activity amount, and / or exercise target activity amount and the predicted activity amount, and may identify the exercise content that the user should perform.

[0095] Specifically, the suggestion unit 17, for example, compares the predicted activity amount calculated using the prediction function with the target physical activity amount to calculate the remaining activity amount required for one day for the activity item "physical activity." The suggestion unit 17 also compares the activity amount based on the individual activity history information input in S3 with the target exercise activity amount to calculate the remaining activity amount required for one day for the activity item "exercise." The suggestion unit 17 then compares the calculated remaining activity amounts required for one day with the correspondence table to identify the activity content and activity time to be suggested to the user for each activity item.

[0096] In a more preferred embodiment, the suggestion unit 17 may calculate the remaining amount of activity required per day for each activity item based on the age-based daily target activity amount, weekly target activity amount, physical activity target activity amount, and / or exercise target activity amount, and the predicted activity amount, and identify the exercise content that the user should perform.

[0097] In another preferred embodiment, the suggestion unit 17 may identify the content of exercise to be performed by the user for each activity item based on the predicted activity amount calculated using the prediction function created for each activity item. Specifically, the suggestion unit 17 compares the predicted activity amount calculated using the prediction function as the predicted activity amount for physical activity with the target physical activity amount to calculate the remaining activity amount required for one day for the activity item "physical activity." The suggestion unit 17 also compares the predicted activity amount calculated using the prediction function as the predicted activity amount for exercise with the target exercise activity amount to calculate the remaining activity amount required for one day for the activity item "exercise." Then, the suggestion unit 17 compares the calculated remaining activity amounts required for one day with the correspondence table to identify the activity content and activity time to be suggested to the user for each activity item.

[0098] Additionally, the suggestion unit 17 may compare the predicted activity amount calculated using a prediction function as the predicted activity amount for physical activity with the daily target activity amount to calculate the remaining activity amount required for one day for the activity item "physical activity." The suggestion unit 17 may also compare the predicted activity amount calculated using a prediction function as the predicted activity amount for exercise with the weekly target activity amount to calculate the remaining activity amount required for one day for the activity item "exercise."

[0099] <3.7. Display screen example> In S9, the display processing unit 19 displays the remaining number of steps required for the day and / or the distance calculated in S6 and S7, and the exercise content identified in S8, and displays them on the user terminal device 3. Fig. 7 shows an example of a screen displayed on the user terminal device 3, which displays the daily activity history information and the remaining number of steps required for the day.

[0100] In the illustrated example, the daily activity history information includes the total number of steps, distance traveled, and number of floors traveled that have been collected up to the most recent day, the predicted activity amount calculated in S4, the remaining number of steps required for the day, and content suggested to the user. Specifically, for daily activities among the activity items, "Brisk walking: about 10 minutes (1000 steps)" indicating the activity content, activity time, and the remaining number of steps required for the day, and for exercise among the activity items, "Strength training: about 5 minutes" indicating the activity content and activity time, is displayed.

[0101] In a preferred embodiment of the present invention, the display processing unit 19 displays the predicted activity amount according to the activity item. Specifically, when the activity item is daily activity, the display processing unit 19 updates and displays the predicted activity amount daily. On the other hand, when the activity item is exercise, the display processing unit 19 updates and displays the predicted activity amount weekly. This allows users to check their predicted activity volume on a weekly basis for less frequent exercise, and the screen can be updated at the user's pace.

[0102] In a preferred embodiment, the display processing unit 19 may change and display the target activity amount (daily target activity amount, weekly target activity amount, physical activity target activity amount, and exercise target activity amount) based on the age input by the user.

[0103] <3.8. Prompt for input of individual activity history information> If there is a missing step count for each time period in the walking history information in S10 (YES in S10), proceed to S11. On the other hand, if there is no missing step count for each time period in the walking history information in S10 (NO in S10), end the process.

[0104] In S11, the display processing unit 19 performs a display process to prompt the user to input individual activity history information. In this embodiment, when the display processing unit 19 identifies a time period in which the user's step count is not registered, the display processing unit 19 performs a display process to prompt the user to input individual activity history information, assuming that the user terminal device 3 was not carried during that time period, and causes the user terminal device 3 to display the message.

[0105] In a preferred embodiment of the present invention, when no individual activity history information has been input at the end of a day and there is a gap in the step count history, the display processing unit 19 displays a message prompting the user to input the individual activity history information. On the other hand, the display processing unit 19 may also display a message prompting the user to input the information when there is a gap in the past time period starting from the current time in a day.

[0106] <3.9. Updating predicted activity> In S12, the activity amount prediction unit 13 accepts input of individual activity history information and updates the predicted activity amount. In this embodiment, the activity amount prediction unit 13 accepts input of activity time for each activity intensity as individual activity history information from the user who confirmed the message in S11, and calculates a new predicted activity amount by adding together the activity amount based on the product of the activity intensity and the activity time and the predicted activity amount calculated in S4.

[0107] As described above, by executing the processes of S1 to S12, it is possible to calculate the predicted activity amount of the user, and ultimately to calculate the predicted activity amount for one day. Furthermore, by calculating the predicted activity amount by summing the predicted activity amount based on the number of steps and the activity amount based on the product of the individually input activity intensity and activity time, it is possible to predict the activity amount by comprehensively considering activities performed when the user terminal device 3 is not carried.

[0108] In this embodiment, the display process refers to a process in which the display processing unit 19 executes a process of generating information necessary for display, and transmits the generated information to the terminal device 9, thereby causing the terminal device 9 to display the generated information. On the other hand, in the case where the display processing unit 19 is provided in the terminal device 9 (in the case of a stand-alone type), the display process may be a process in which the display processing unit 19 executes a process of generating necessary information, and transmits the generated information to the output unit 95 of the terminal device 9, thereby causing the output unit 95 to display the generated information. [Explanation of symbols]

[0109] 0: Prediction system 1: Prediction device 2: Database 3: User terminal device 10: Server 101: Processing section 102: Storage section 103: Communications Department 9: Terminal device 91: Processing section 92: Storage section 93: Communications Department 94: Input section 95: Output section 11: Registration Department 12: Step count management section 13: Activity amount prediction section 14: Prediction method creation section 15: Step count prediction section 16: Distance prediction unit 17: Proposal Department 18: Update section 19: Display processing section 21: User-related information database 22: Database for creating functions NW: Communication network

Claims

1. A prediction system for predicting an amount of activity taking into account various physical activities in one day, the prediction system includes a step count management unit and an activity amount prediction unit; the step count management unit acquires the number of steps of the user; The activity amount prediction unit calculates a predicted daily activity amount based on the number of steps and a prediction means. Prediction system.

2. The prediction means is a prediction function, The prediction function has a step count variable and an age variable, The weight of the age variable is a negative number The prediction system of claim 1 .

3. The prediction function is a function in which the absolute value of the weight of the age variable is greater than the absolute value of the weight of the step count variable. The prediction system of claim 2 .

4. The prediction function is a function in which the age variable has a weight of -10^(-1) to -10^(-2) and the step count variable has a weight of 10^(-4) to 10^(-3). The prediction system of claim 2 .

5. The prediction function has a few constants The prediction system of claim 2 .

6. The prediction system further includes a prediction means creation unit, The prediction means creation unit creates the prediction function using a plurality of data including the number of steps, the product of activity intensity and activity time, and age. The prediction system of claim 2 .

7. The prediction means creation unit creates the prediction function using the data in which the activity intensity is equal to or greater than a predetermined level. The prediction system of claim 6 .

8. The prediction system further includes a step count prediction unit, The step count prediction unit calculates the remaining number of steps required for one day based on the user's step count history, the target activity amount, and the prediction function. The prediction system of claim 2 .

9. The prediction system further includes a display processing unit, If the predicted activity amount does not reach a predetermined threshold, the remaining number of steps required for the day is displayed. The prediction system of claim 8 .

10. The prediction system further includes a proposing unit, A correspondence table in which activity intensity and activity content are associated is stored in a database, The suggestion unit identifies an activity content and an activity time as an exercise content to be performed by the user based on the target activity amount, the predicted activity amount, and the correspondence table. The prediction system of claim 1 .

11. The prediction system further includes a display processing unit, The step count management unit registers a step count history and a time period for one day, The display processing unit performs a display process to prompt input of individual activity history information when there is a time period in which the step count history is not registered. The prediction system of claim 1 .

12. A prediction program for predicting an amount of activity taking into account various physical activities in one day, The computer functions as a step count management unit and an activity amount prediction unit, the step count management unit acquires the number of steps of the user; The activity amount prediction unit calculates the predicted daily activity amount based on the number of steps and a prediction means. Prediction program.

13. A prediction method for predicting an activity amount taking into account various physical activities in one day, A process in which the computer acquires the number of steps of the user; A process of calculating the predicted daily activity amount based on the number of steps and a prediction means; A forecasting method that performs.

Images