Information processing device, control method for information processing device, and information processing system

Abstract

The present invention provides an information processing device or the like for accurately predicting the exercise ability of a user by a simpler method without requiring the trouble of measuring an AT value at a specialized facility. The information processing device includes: a first storage unit for storing a correspondence relationship between travel time and running ability according to travel distance; a second storage unit for storing running lap times for each of a plurality of running activities performed by a prediction target user; a running ability calculation unit for calculating a plurality of running abilities according to a predetermined travel distance for each running activity on the basis of the lap times and the correspondence relationship; a determination unit for determining a representative value of the running ability for each running activity on the basis of the plurality of running abilities; a generation unit for generating a regression model that uses the representative value as an objective variable and uses travel distance in the running activity when the representative value is determined as an explanatory variable; and a prediction unit for predicting, on the basis of the regression model, the running ability when the prediction target user travels a predetermined distance.

Description

Information processing device, control method for information processing device, and information processing system

[0001] The present invention relates to an information processing device, a control method for an information processing device, and an information processing system.

[0002] Conventionally, the AT value (Anaerobic Threshold) is an index considered when creating a training menu for a running user. The AT value refers to the exercise load at which aerobic exercise switches to anaerobic exercise as the intensity of the exercise increases. Knowing an individual's AT value makes it possible to predict race records and set a running pace according to the purpose of the training menu. For example, Patent Document 1 discloses a method for calculating a user's exercise pulse rate based on a pulse wave signal and a body movement signal measured while the user is performing a predetermined exercise, and determining the degree to which the predetermined exercise contributes to the user's physical fitness based on the exercise pulse rate and lactate level information including the anaerobic threshold (AT value), which represents the relationship between the user's pulse rate and blood lactate level obtained in advance.

[0003] Japanese Patent Application Laid-Open No. 2016-195661

[0004] The AT value is estimated based on the relationship between the user's running speed and blood lactate concentration, VO2max (maximum oxygen uptake), race records under maximum effort, or the relationship between heart rate and running speed, etc. Here, values ​​such as blood lactate concentration and VO2max must be measured at a specialized facility, and measurement accuracy decreases if measurements are not performed under maximum effort.

[0005] Therefore, there has been a demand for a simpler method to accurately predict a user's athletic ability without the need for the time and effort of measuring AT values ​​and the like at specialized facilities.

[0006] An information processing device according to one aspect of the present invention includes a first memory unit that stores the correspondence between running time according to running distance and running ability, a second memory unit that stores the lap time for each running activity performed by the user to be predicted, a running ability calculation unit that calculates multiple running abilities according to a predetermined running distance for each running activity based on the lap time and the correspondence, a determination unit that determines a representative value of the running ability for each running activity based on the multiple running abilities, a generation unit that generates a regression model in which the representative value is the dependent variable and the running distance in the running activity when the representative value is determined is the explanatory variable, and a prediction unit that predicts the running ability of the user to be predicted when running a predetermined distance based on the regression model.

[0007] A control method for an information processing device according to one aspect of the present invention includes the steps of: storing in a first memory unit a correspondence between running time according to running distance and running ability; storing in a second memory unit the lap times for each running activity for multiple running activities performed by the user to be predicted; calculating multiple running abilities corresponding to predetermined running distances for each running activity based on the lap times and the correspondences; determining a representative value of running ability for each running activity based on the multiple running abilities; generating a regression model in which the representative value is the dependent variable and the running distance in the running activity when the representative value is determined is the explanatory variable; and predicting the running ability of the user to be predicted when running a predetermined distance based on the regression model.

[0008] According to one aspect of the present invention, an information processing system including an information processing device and a terminal of a user to be predicted comprises: a first memory unit in which the information processing device stores a correspondence between running time according to running distance and running ability; a second memory unit in which the lap times for each running activity acquired from the terminal of the user to be predicted for multiple running activities performed by the user to be predicted; a running ability calculation unit that calculates multiple running abilities corresponding to predetermined running distances for each running activity based on the lap times and the correspondence; a determination unit that determines a representative value of the running ability for each running activity based on the multiple running abilities; a generation unit that generates a regression model in which the representative value is used as the dependent variable and the running distance in the running activity when the representative value is determined is used as the explanatory variable; and a prediction unit that predicts the running ability of the user to be predicted when the user runs a predetermined distance based on the regression model.

[0009] According to one aspect of the present invention, it is possible to provide an information processing device, etc. that accurately predicts a user's athletic ability using a simpler method, without the need for the hassle of measuring AT values, etc. at a specialized facility.

[0010] FIG. 1 is a schematic diagram showing the configuration of a practice support system according to one embodiment of the present invention. FIG. 2 is an example functional block diagram of a server (information processing device) and a user terminal (communication terminal) according to one embodiment of the present invention. FIG. 3 is an example lap time table according to one embodiment of the present invention. FIGS. 4(a) to 4(c) are schematic diagrams illustrating the process of determining a representative value of running ability according to one embodiment of the present invention. FIG. 5 is an example plot graph of a data set according to one embodiment of the present invention. FIG. 6 is a flowchart showing an example operation of a server according to one embodiment of the present invention. FIGS. 7(a) and 7(b) are diagrams showing examples of display screens of a user terminal according to one embodiment of the present invention.

[0011] Hereinafter, one embodiment of the invention according to the present disclosure (also referred to as the present invention) will be described using the drawings. Note that the drawings are merely examples, and the present invention is not limited to those shown in the drawings. For example, the number of servers (information processing devices), user terminals (communication devices), database servers, and sensor devices, their size ratios, data sets (tables), display screens, and flowcharts shown in the drawings are merely examples, and the present invention is not limited thereto.

[0012] <System Configuration> FIG. 1 is a diagram illustrating an example configuration of a practice support system according to one embodiment of the present invention. The practice support system 600 may be an information processing system that supports a user (runner) in their practice. According to one embodiment of the present invention, a user's running ability when running a predetermined distance is predicted based on data (information) obtained from the user's daily practice. Note that "running ability" is an index related to the user's performance and records when running. For example, running ability can be expressed as VDOT (pseudo-VO2max), race completion time, AT pace (running pace at an exercise load near the AT value), etc., which correspond to each other. For example, VDOT can be converted into race completion time or AT pace.

[0013] In this specification, "practice" includes "training," "exercise," "training," etc., and may include things that an individual does independently or things that are done under the guidance of an expert or trainer.

[0014] The practice support system 600 may include a server 100, a database server 101, user communication terminals (user terminals) 200 (200A, 200B), and sensor devices 301 (301B) and 302 (302B). In FIG. 1 , two users, A and B, are shown, and the reference numerals for the user terminals and sensor devices are denoted by the letters "A" and "B." However, the number of users may be greater or less than this, and the number of user terminals and sensor devices may correspond to the number of users. Hereinafter, unless otherwise specified, the user terminal and sensor devices will be simply referred to as the user terminal 200 and the sensor devices 301 and 302, respectively. As will be described in detail later, the user terminal 200 and the sensor devices 301 and 302 may be communication devices with a location information acquisition function such as a Global Positioning System (GPS).

[0015] The server 100 can execute various processes related to the practice support service realized by the practice support system 600. The server 100 is also connected to the user terminal 200 via a network 500. The network 500 may include a wireless network or a wired network, such as a wireless LAN (WLAN), a wide area network (WAN), integrated service digital networks (ISDNs), wireless LANs, code division multiple access (CDMA), long term evolution (LTE), LTE-Advanced, fourth generation communication (4G), fifth generation communication (5G), sixth generation communication (6G) or later mobile communication systems, or a combination thereof.

[0016] The server 100 also transmits and receives various data to and from the database server 101. The database server 101 stores various data necessary to implement the functions of the practice assistance system 600. While FIG. 1 illustrates the server 100 and the database server 101 connected via a network 500, the server 100 and the database server 101 may be connected via a dedicated internal network. Although FIG. 1 illustrates the server 100 and the database server 101 separately, the database server 101 may function as a storage unit (first storage unit, second storage unit) of the server 100, which will be described later. While FIG. 1 illustrates one server 100 and one database server 101, this is not a limitation. That is, each function described as being provided by the server 100 may be implemented by multiple servers, or there may be multiple database servers 101. The server 100 may be, for example, a distributed server system that cooperates by communicating via a network, or a so-called cloud server. That is, the server 100 is not limited to a physical server, but may also include a virtual server implemented by software.

[0017] The user terminal 200 is a communication terminal used by a user, and has installed thereon an application for using the practice support service (hereinafter also referred to as a "practice support app"). As will be described in detail later, the user terminal 200 may be able to transmit information acquired by the user terminal 200 itself or the sensor devices 301 and 302 to the server 100 via the practice support app.

[0018] 1 shows a smartphone as the user terminal 200, the user terminal 200 may be any terminal capable of implementing the functions described in the following embodiments. For example, the user terminal 200 may be a computer (e.g., a tablet, desktop PC, or laptop), a handheld computing device (including, but not limited to, a wearable device (glasses-type device (smart glasses), watch-type device (smart watch)), a smart speaker, etc.). The sensor device 302 may also have various functions of the user terminal 200 described below and function as the user terminal 200.

[0019] The users may include a target user whose running ability when running a predetermined distance is predicted, and a reference user who has running data from when they have previously run the predetermined distance. Here, the predetermined distance may be any distance the user wishes to complete, such as a full marathon (42.195 km) or a half marathon (21.0975 km). In one aspect of the present invention, the running data of the reference user is used to correct the prediction results of the target user, thereby improving prediction accuracy. When there is no need to distinguish between the target user and the reference user, the term "user" is used.

[0020] A user may run while wearing at least one of the user terminal 200 and the sensor devices 301 and 302, each of which has a position information acquisition function. The sensor device 301 may be a motion sensor, a wearable device with a communication function, capable of acquiring information about the user's running form and distance traveled and transmitting the acquired information to the user terminal 200. The sensor device 302 may also include a vital sensor capable of detecting biometric information such as the user's body temperature, blood pressure, heart rate, and number of breaths per unit time in addition to measuring the distance traveled. However, in one aspect of the present invention, it is sufficient to acquire information about the user's running time and distance traveled, and acquiring information about the running form and biometric information is not required. In other words, according to one aspect of the present invention, data acquired by running while holding the user terminal 200 is sufficient, and wearing a motion sensor or a vital sensor is not required.

[0021] Next, the hardware configuration and functional configuration of the server 100 and the user terminal 200 will be described with reference to FIG.

[0022] <User Terminal> (1) Hardware Configuration of User Terminal The user terminal 200 includes a control unit 210 , a communication unit 220 , a display unit 230 , an input / output unit 240 , and a storage unit 270 .

[0023] The control unit 210 is typically a processor, and is realized by a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), etc. The control unit 210 reads out a program stored in the storage unit 270 and executes the code or instructions included in the program, thereby performing the functions and methods described in each embodiment.

[0024] The control unit 210 controls the communication unit 220, the display unit 230, and the input / output unit 240. Specifically, the control unit 210 controls communication between the user terminal 200, the server 100, and the sensor devices 301 and 302 via the communication unit 220, and transmits and receives various data therebetween. For example, the control unit 210 may acquire data on the user's running, such as a running distance or a running time, measured by the sensor devices 301 and 302. The control unit 210 also controls the display of data on the display unit 230. For example, the control unit 210 may cause the display unit 230 to display, for example, the user's predicted running ability when running a predetermined distance. Furthermore, the control unit 210 controls the transmission of various information to external devices via the input / output unit 240. For example, the control unit 210 may transmit various information to each functional unit in response to a user's input operation received via an input device, or transmit information from each functional unit to an output device (not shown), such as a touch panel, monitor, or speaker.

[0025] The storage unit 270 stores various programs and data required for the operation of the user terminal 200. For example, the storage unit 270 may store the program for the practice assistance app described above. The storage unit 270 may include, for example, a flash memory or the like, and may also include memory (such as a RAM (Random Access Memory) or a ROM (Read Only Memory)) that provides a working area for the control unit 210. The storage unit 270 may also temporarily store lap times, which will be described later.

[0026] The communication unit 220 is implemented as hardware such as a network adapter, communication software, or a combination of these, and transmits and receives various data to and from the server 100 and the sensor devices 301 and 302 via the network 500 in accordance with a predetermined protocol.

[0027] The display unit 230 is a monitor that displays data in accordance with the display data written in the frame buffer, and may be, for example, a touch panel, a touch display, or the like.

[0028] The input / output unit 240 includes an input device for inputting various operations to the user terminal 200, and an output device for outputting processing results processed by the user terminal 200. The input device may include, for example, a touch panel, a touch display, a camera, and a microphone, and the output device may include, for example, a display, a touch panel, a speaker, etc.

[0029] (2) Functional Configuration of User Terminal The user terminal 200 includes a location information acquisition unit 211 and a conversion unit 212 as functions realized by the control unit 210. The location information acquisition unit 211 acquires location information related to the current location of the user terminal 200. For example, the location information acquisition unit 211 uses a global positioning system (GPS) to acquire information on the latitude and longitude of the user terminal 200 as location information on the current location of the user terminal 200. Note that the location information acquisition unit 211 may acquire location information using any method, and may acquire location information using, for example, a wireless LAN, an indoor messaging system (IMES), a radio frequency identifier (RFID), Bluetooth low energy (BLE) (registered trademark), geomagnetism, or the like.

[0030] The conversion unit 212 converts the user's movement amount per unit time acquired by the position information acquisition unit 211 into a lap time for each predetermined section. The predetermined section may be, for example, 1000 m, but is not limited to this. Note that if the user runs while wearing the sensor devices 301 and 302 and the sensor devices 301 and 302 have a function for converting the amount into a lap time, the sensor devices 301 and 302 may convert the amount into a lap time. Alternatively, the server 100, which will be described later, may convert the amount into a lap time.

[0031] <Server> (1) Hardware Configuration of Server The server 100 includes a control unit 110 , a communication unit 120 , a display unit 130 , and a storage unit 170 .

[0032] The storage unit 170 is typically realized by various recording media such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory, and has the function of storing various programs and data required for the operation of the server 100. The storage unit 170 also includes memory (RAM, ROM, etc.) that provides a working area for the control unit 110.

[0033] The control unit 110 is typically a processor, and is realized by a central processing unit (CPU), an MPU, a GPU, etc. The control unit 110 may execute the functions and methods described in each embodiment by reading a program stored in the storage unit 170 and executing code or instructions included in the program.

[0034] The communication unit 120 is implemented as hardware such as a network adapter, communication software, or a combination of these. The communication unit 120 may transmit and receive various data to and from the user terminal 200 via the network 500 using any communication protocol.

[0035] (2) Functional Configuration of Server The server 100 includes, as functions realized by the control unit 110, an acquisition unit 111, a calculation unit 112, a determination unit 113, a generation unit 114, a prediction unit 115, a correction unit 116, and an output unit 117. Note that in FIG. 2 , functional units that are not essential for the embodiments described hereinafter may be omitted. Furthermore, the functions or processes of each functional unit may be realized by machine learning or AI to the extent feasible.

[0036] The acquisition unit 111 acquires from the database server 101 the lap times for each of the multiple running activities performed by the user to be predicted. FIG. 3 shows an example of lap times stored in the database server 101. In FIG. 3, a lap time table TB10A shows the lap times of the user to be predicted (user A), and tables TB10B and TB10C show the lap times of the reference users (user B and user C). Hereinafter, unless there is a need to distinguish between them, these lap time tables will be simply referred to as TB10. The lap time table TB10 may record the lap times measured for each running activity in an identifier (activity ID (IDentifier)) that identifies the running activity. In the example of the lap time table TB10, user A performed a running activity of "7001 m" on "2023 / 5 / 1," and the lap times for every 1000 m are recorded. Furthermore, user A performed a running activity of "4001 m" on "2023 / 5 / 4," and lap times for every 1000 m were recorded. These data may be calculated based on data measured by the user terminal 200 or the sensor devices 301 and 302.

[0037] The calculation unit 112 calculates multiple running abilities corresponding to predetermined running distances for each running activity based on the lap time and the correspondence between running time corresponding to the running distance and running ability. That is, the calculation unit 112 functions as a running ability calculation unit. Here, the "correspondence between running time corresponding to the running distance and running ability" may be, for example, a data set similar to a calculation table based on VDOT proposed by Jack Daniels (hereinafter also referred to as "Daniels' data set"). VDOT is a pseudo-VO2max (maximum oxygen uptake) and is an index that indicates the user's current running ability level.

[0038] FIG. 4B shows an example of a data set showing the correspondence between running time and running ability according to running distance. Table TB20 shows that, theoretically, if a running ability (VDOT) is "30," a person can complete 1500 m in "8 minutes 30 seconds" and a full marathon (42.195 km) in "4 hours 49 minutes 17 seconds." Furthermore, if a running ability is "32," a person can complete 3000 m in "16 minutes 59 seconds" and a full marathon in "4 hours 34 minutes 59 seconds." In one embodiment of the present invention, VDOT is calculated as running ability and converted into AT pace and completion time. The values ​​enclosed by dashed lines in Table TB20 will be described later.

[0039] Continuing with FIG. 4 , the processing of the calculation unit 112 will be described. Table TB10A′ in FIG. 4( a) is a data set of lap times for a single running activity identified by the activity ID “act_01” in the lap time table TB10A of the user (user A) to be predicted shown in FIG. 3 . Based on the data in table TB10A′, the calculation unit 112 calculates the fastest pace for each of predetermined running distances of 1500 m, 3000 m, and 5000 m. Here, 1500 m, 3000 m, and 5000 m are running distances that correspond to running ability in the Daniels data set described above. Note that in the example of table TB10A′, the total running distance was 7001 m, so the fastest pace up to 5000 m was calculated. However, if the total running distance is 10 km or more, the fastest pace for 10 km may be calculated.

[0040] Here, the fastest paces for running 1500m, 3000m, and 5000m were "8 minutes 29 seconds," "17 minutes 9 seconds," and "30 minutes 77 seconds," respectively, as shown in table TB11 in FIG. 4(c). The calculation unit 112 compares the fastest pace with Daniels' dataset and determines the running ability for the user A when running that distance as the running ability for that distance. In the example of FIGS. 4(a) and 4(b), the running ability "30," which stores the pace "8 minutes 30 seconds" closest to the fastest pace for running 1500m, "8 minutes 29 seconds," may be calculated as user A's running ability for running 1500m. Similarly, the running abilities shown in table TB11 in FIG. 4(c) are calculated for 3000m and 5000m.

[0041] The determination unit 113 determines a representative value of running ability for each running activity based on the multiple running abilities. For example, the determination unit 113 may determine the maximum value of the multiple running abilities calculated by the calculation unit 112 as the representative value. In the example of table TB11 in FIG. 4( c), the representative value of running ability for the running activity identified by the activity ID "act_01" is "32." The database server 101 associates and stores the running distance and running ability for the running activity when the representative value is determined. In the example of FIG. 4, the representative value of running ability for the running activity identified by the activity ID "act_01," "32," and the total running distance of "7001 m," may be associated and stored as table TB12. The calculation unit 112 and the determination unit 113 perform the above-described processing for each running activity identified by the activity ID, and therefore, a data set consisting of the representative value of running ability and the total running distance is generated for each running activity.

[0042] The generation unit 114 generates a regression model using the representative value as the objective variable and the distance traveled during the running activity when the representative value was determined as the explanatory variable. This will be described with reference to FIG. 5. FIG. 5 is an example of a graph plotting data for each running activity collected from a single user, with the horizontal axis representing the distance traveled (total distance traveled) and the vertical axis representing the representative value of running ability. Based on these datasets, the generation unit 114 may generate a regression curve, indicated by the solid line in the figure, as a regression model using an existing statistical method such as the least squares method. For example, when the regression curve is expressed as y(x) = β1 logx + β2, the generation unit 114 calculates the coefficients β1 and β2. Note that the regression curve is not limited to this. A regularization term (penalty term) may be included to ensure robustness. Alternatively, the generation unit 114 may generate the regression model through machine learning using the dataset. Furthermore, multiple parameters, in addition to the distance traveled, may be used as explanatory variables.

[0043] The prediction unit 115 predicts the running ability of the user to be predicted when the user runs a predetermined distance, based on the regression model generated by the generation unit 114. For example, if the predetermined distance is a full marathon of 42.195 km, the prediction unit 115 may predict the running ability by substituting x = 42.195 into the generated regression curve y(x).

[0044] <Server Control Flowchart> The control method of the server 100 described above will be described using the flowchart of FIG. 6. First, a correspondence between running time and running ability corresponding to a running distance is stored in the first storage unit (step S11). The correspondence may be the Daniels dataset described above, as shown in table TB20 of FIG. 4(b). Furthermore, the second storage unit stores lap times for each running activity performed by the user to be predicted (step S12). The lap times stored in the second storage unit may be those stored in the lap time table TB10 described above in FIG. 3. The first storage unit and the second storage unit may be the database server 101. The acquisition unit 111 may acquire the data stored in the first storage unit and the second storage unit as needed and use them in the prediction process. The calculation unit 112 calculates multiple running abilities corresponding to predetermined running distances for each running activity based on the lap times and the correspondence (step S13). The determination unit 113 determines a representative value of running ability for each running activity based on the multiple running abilities (step S14). The generation unit 114 generates a regression model in which the representative value is the objective variable and the distance traveled in the running activity at the time the representative value was determined is the explanatory variable (step S15). The prediction unit 115 predicts the running ability of the user to be predicted when the user runs a predetermined distance based on the regression model (step S16).

[0045] As described above, according to one aspect of the present invention, running ability for running a predetermined distance is predicted using only lap times acquired during daily training by the user, without the need to measure biological information such as the user's VO2max. Furthermore, the lap times of the user to be predicted do not need to be data measured at maximum effort, and data on long-distance runs such as full marathons is not required. Therefore, running ability can be predicted more easily. Furthermore, predicting running ability allows for appropriate pacing during training and races, thereby improving training efficiency.

[0046] In the above description, the determination unit 113 determines the maximum value of the multiple running abilities calculated by the calculation unit 112 as the representative value. In this case, it is possible to predict a running ability close to the user's personal best. However, the representative value is not limited to the maximum value, and may be the median, average, minimum, mode, etc. When the median or mode is used as the representative value, if there is a bias in the distribution of user data in the graph 30, the prediction will be close to the actual measurement. Furthermore, when the minimum value is used as the representative value, the prediction may be lower than the actual measurement.

[0047] Furthermore, each time the user runs, the lap time for each run may be measured and updated (accumulated) in the lap time table TB10. Then, the newly accumulated lap times may be added to the prediction, thereby improving the prediction accuracy.

[0048] <Display of Prediction Results> The output unit 117 may display information regarding the time required to run a predetermined distance on the user terminal 200. That is, based on the prediction results for running the predetermined distance, the output unit 117 may display information regarding a training menu recommended for the user to complete the predetermined distance, as well as information regarding AT pace, VO2max, target time, predicted completion time, etc. on the user terminal 200. FIGS. 7( a) and 7(b) show examples of prediction result screens displayed on the user terminal 200. Note that the figures are merely examples, and the displayed format and wording are not limited thereto. Screen 10 in FIG. 7( a) shows the prediction results at the initial stage of training, with the training menu 11 displaying "10 km pace run at 5:30 / km." Furthermore, screen 10 displays information regarding the currently predicted running ability, such as a predicted time 12 required to complete a target race. Here, the predicted time 12 may indicate an error of plus or minus 20 minutes due to the low accuracy of the predictions at the initial stage of training when no running data has been accumulated. 7(b), the user has been training for six months and their running ability has improved, and the more strenuous "10km pace run at 4:30 / km" is displayed as the training menu 21. The predicted time 22 is also faster than the predicted time 12 at the beginning of training, and as the user's running data has been accumulated, the prediction accuracy has improved to an error of about plus or minus 10 minutes.

[0049] Thus, according to one aspect of the present invention, information regarding the training ability that the user is expected to acquire is provided to the user, which is expected to have the effect of maintaining the user's motivation.

[0050] <Correction Process> According to one aspect of the present invention, the prediction result of the user to be predicted may be corrected based on data obtained from multiple running activities performed by a reference user who has running data from when the user previously ran a predetermined distance. As shown in FIG. 3 , the database server 101 further stores lap times (lap time tables TB10B, TB10C) for each running activity performed by the reference user who has running data from when the user previously ran a predetermined distance. The calculation unit 112, the determination unit 113, the generation unit 114, and the prediction unit 115 predict the running ability of the reference user when the user runs a predetermined distance based on the lap times of the reference user's running, using the same processing as for the user to be predicted described above. The correction unit 116 corrects the prediction result of the running ability of the user to be predicted by the prediction unit 115 using the prediction result of the reference user's running ability and the reference user's actual running ability based on running data from when the reference user previously ran a predetermined distance.

[0051] Here, the actual running ability may be a running ability corresponding to the completion time of a reference user running a predetermined distance, with reference to the Daniels dataset described above. The correction unit 116 corrects the predicted result of the running ability of the user to be predicted using the difference (prediction error) between the predicted result of the reference user's running ability predicted by the prediction unit 115 and the actual running ability. At this time, a correction term that minimizes the sum of the prediction errors calculated for multiple reference users is calculated, and is applied to correct the predicted result of the user to be predicted.

[0052] Thus, according to one aspect of the present invention, data on a reference user who has actually run a predetermined distance and whose actual running ability is known is used to correct the prediction result for the user to be predicted, thereby improving the prediction accuracy even for users who have not actually run the predetermined distance.

[0053] While the present invention has been described based on the drawings and examples, it should be noted that those skilled in the art would readily be able to make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of the present invention. For example, the functions included in each means, step, etc. may be rearranged so as not to cause logical inconsistencies, and multiple means, steps, etc. may be combined or separated into one. Furthermore, the configurations described in the above embodiments may be appropriately combined. For example, each component described as being included in the server 100 may be realized in a distributed manner across multiple servers. Furthermore, processing described as a function of the server 100 may be performed by the user terminal 200 or the sensor devices 301 and 302. Conversely, processing described as being performed by the user terminal 200 may be performed by the server 100 or the sensor devices 301 and 302.

[0054] For example, the above description has been given of a case where running ability is predicted, but the object of prediction is not limited to this and may be, for example, a lap time, an AT value, a completion time for a full marathon, or the like.

[0055] Each functional unit of the server 100 or the information processing device 100 may be realized by a logic circuit (hardware) formed in an integrated circuit (IC (Integrated Circuit) chip, LSI (Large Scale Integration)), or a dedicated circuit, or may be realized by software using a CPU (Central Processing Unit). Furthermore, each functional unit may be realized by one or more integrated circuits, and the functions of multiple functional units may be realized by a single integrated circuit.

[0056] The program of each embodiment of the present disclosure may be provided in a state stored in a storage medium readable by an information processing device. The storage medium may store the program in a "non-transitory tangible medium." The program includes, for example, a software program and an information processing device program. When each functional unit of the information processing device 100 is realized by software, the information processing device 100 functions as an acquisition unit 111, a calculation unit 112, a determination unit 113, a generation unit 114, a prediction unit 115, a correction unit 116, and an output unit 117 by the processor executing the program loaded on the memory.

[0057] The storage medium may, where appropriate, comprise one or more semiconductor-based or other integrated circuits (ICs) (e.g., field programmable gate arrays (FPGAs), application specific ICs (ASICs), etc.), hard disk drives (HDDs), hybrid hard drives (HHDs), optical disks, optical disk drives (ODDs), magneto-optical disks, magneto-optical drives, floppy diskettes, floppy disk drives (FDDs), magnetic tapes, solid state drives (SSDs), RAM drives, secure digital cards or drives, any other suitable storage media, or any suitable combination of two or more of these. The storage medium may, where appropriate, be volatile, non-volatile, or a combination of volatile and non-volatile.

[0058] Furthermore, the program of the present disclosure may be provided to the information processing device 100 via any transmission medium (such as a communication network or broadcast waves) capable of transmitting the program.

[0059] Furthermore, each embodiment of the present disclosure may be realized in the form of a data signal embedded in a carrier wave, in which the program is embodied by electronic transmission. Note that the program of the present disclosure may be implemented using, for example, a scripting language such as JavaScript (registered trademark) or Python, or the C language, Go language, Swift, Koltin, Java (registered trademark), or the like.

[0060] It will be understood by those skilled in the art that the above-described embodiments are specific examples of the following aspects: [1] An information processing device according to the present disclosure includes a first storage unit that stores a correspondence relationship between running time corresponding to a running distance and running ability, a second storage unit that stores lap times for each of a plurality of running activities performed by a user to be predicted, a running ability calculation unit that calculates a plurality of running abilities corresponding to predetermined running distances for each of the running activities based on the lap times and the correspondence relationship, a determination unit that determines a representative value of running ability for each of the running activities based on the plurality of running abilities, a generation unit that generates a regression model in which the representative value is used as a response variable and the running distance in the running activity at the time the representative value is determined is used as an explanatory variable, and a prediction unit that predicts the running ability of the user to be predicted when the user runs a predetermined distance based on the regression model. [2] In the information processing device of [1] above, the second storage unit may further store lap times for each running activity for multiple running activities performed by a reference user who has running data from when the reference user previously ran the predetermined distance, the running ability calculation unit may calculate multiple running abilities corresponding to predetermined running distances for each running activity of the reference user based on the lap times of the reference user and the correspondence, the determination unit may determine a representative value of the running ability for each running activity of the reference user based on the multiple running abilities of the reference user, the generation unit may generate a regression model in which the representative value of the reference user is used as a dependent variable and a running distance in the running activity at the time the representative value was determined is used as an explanatory variable, the prediction unit may predict the running ability of the reference user when running the predetermined distance based on the regression model of the reference user, and the information processing device may further include a correction unit that corrects the prediction result of the running ability of the user to be predicted by the prediction unit using the prediction result of the running ability of the reference user and the reference user's actual running ability based on running data from when the reference user previously ran the predetermined distance. [3] In the information processing device described in [1] above, the determination unit may determine the maximum value of the plurality of running abilities calculated by the running ability calculation unit as the representative value.[4] In the information processing device described in [1] above, the determination unit may determine a median value of the plurality of running abilities calculated by the running ability calculation unit as the representative value. [5] In the information processing device described in [1] above, the determination unit may determine an average value of the plurality of running abilities calculated by the running ability calculation unit as the representative value. [6] The information processing device described in [1] above may further include an output unit that displays, on a terminal, information regarding a time required to run the predetermined distance, which is converted from the running ability of the user to be predicted corrected by the correction unit. [7] The control method of the present disclosure includes the steps of: storing in a first memory unit a correspondence relationship between running time according to running distance and running ability; storing in a second memory unit lap times for each of multiple running activities performed by the user to be predicted; calculating multiple running abilities according to predetermined running distances for each of the running activities based on the lap times and the correspondence relationship; determining a representative value of running ability for each of the running activities based on the multiple running abilities; generating a regression model in which the representative value is used as a dependent variable and the running distance in the running activity when the representative value is determined is used as an explanatory variable; and predicting the running ability of the user to be predicted when running a predetermined distance based on the regression model.[8] In an information processing system including an information processing device of the present disclosure and a terminal of a user to be predicted, the information processing device includes: a first memory unit that stores a correspondence between running time according to running distance and running ability; a second memory unit that stores lap times for each running activity acquired from the terminal of the user to be predicted for multiple running activities performed by the user to be predicted; a running ability calculation unit that calculates multiple running abilities according to predetermined running distances for each running activity based on the lap times and the correspondence; a determination unit that determines a representative value of running ability for each running activity based on the multiple running abilities; a generation unit that generates a regression model in which the representative value is used as a dependent variable and the running distance in the running activity when the representative value is determined is used as an explanatory variable; and a prediction unit that predicts the running ability of the user to be predicted when running a predetermined distance based on the regression model.

[0061] DESCRIPTION OF SYMBOLS 100 Server (information processing device) 110 Control unit 111 Acquisition unit 112 Calculation unit 113 Determination unit 114 Generation unit 115 Prediction unit 116 Correction unit 117 Output unit 120 Communication unit 130 Display unit 170 Storage unit 101 Database server 200 User terminal (communication terminal) 210 Control unit 211 Position information acquisition unit 212 Conversion unit 220 Communication unit 230 Display unit 240 Input / output unit 270 Storage unit 301 Sensor device 302 Sensor device 500 Network 600 Practice support system

Claims

1. A first storage unit that stores the correspondence relationship between the running time and the running ability according to the running distance; a second storage unit that stores the lap time of each running activity for a plurality of running activities performed by a user to be predicted; a running ability calculation unit that calculates a plurality of running abilities according to a predetermined running distance for each running activity based on the lap time and the correspondence relationship; a determination unit that determines a representative value of the running ability for each running activity based on the plurality of running abilities; a generation unit that generates a regression model with the representative value as the target variable and the running distance in the running activity when the representative value is determined as the explanatory variable; and a prediction unit that predicts the running ability when the user to be predicted runs a predetermined distance based on the regression model. An information processing apparatus comprising the above components.

2. The second storage unit further stores the lap time of each running activity for a plurality of running activities performed by a reference user having running data when the reference user has run the predetermined distance in the past. The running ability calculation unit calculates a plurality of running abilities according to a predetermined running distance for each running activity of the reference user based on the lap time of the reference user and the correspondence relationship. The determination unit determines a representative value of the running ability for each running activity of the reference user based on the plurality of running abilities of the reference user. The generation unit generates a regression model with the representative value of the reference user as the target variable and the running distance in the running activity when the representative value is determined as the explanatory variable. The prediction unit predicts the running ability when the reference user runs a predetermined distance based on the regression model of the reference user. The information processing apparatus according to claim 1, further comprising a correction unit that corrects the prediction result of the running ability of the user to be predicted by the prediction unit by using the prediction result of the running ability of the reference user and the actual running ability of the reference user based on the running data when the reference user has run the predetermined distance in the past.

3. The determination unit determines the maximum value among the plurality of running abilities calculated by the running ability calculation unit as the representative value. The information processing apparatus according to claim 1.

4. The information processing apparatus according to claim 1, wherein the determination unit determines the median of the plurality of running abilities calculated by the running ability calculation unit as the representative value.

5. The information processing apparatus according to claim 1, wherein the determination unit determines the average value of the plurality of running abilities calculated by the running ability calculation unit as the representative value.

6. The information processing apparatus according to claim 1, further comprising an output unit that causes a terminal to display information regarding the time required to travel the predetermined distance, which is converted from the running ability of the prediction target user corrected by the correction unit.

7. A control method for an information processing apparatus, the method including: storing, in a first storage unit, a correspondence relationship between a running time corresponding to a running distance and a running ability; storing, in a second storage unit, a lap time of running for each of a plurality of running activities performed by a prediction target user; calculating, based on the lap time and the correspondence relationship, a plurality of running abilities corresponding to a predetermined running distance for each of the running activities; determining, based on the plurality of running abilities, a representative value of the running ability for each of the running activities; generating a regression model having the representative value as an objective variable and the running distance in the running activity when the representative value is determined as an explanatory variable; and predicting, based on the regression model, the running ability when the prediction target user travels a predetermined distance.

8. An information processing system comprising an information processing device and a terminal of a user to be predicted, wherein the information processing device includes: a first storage unit that stores a correspondence relationship between a running time corresponding to a running distance and a running ability; a second storage unit that stores, for a plurality of running activities performed by the user to be predicted, a lap time of running for each running activity acquired from the terminal of the user to be predicted; a running ability calculation unit that calculates a plurality of running abilities corresponding to a predetermined running distance for each running activity based on the lap time and the correspondence relationship; a determination unit that determines a representative value of the running ability for each running activity based on the plurality of running abilities; a generation unit that generates a regression model having the representative value as an objective variable and the running distance in the running activity when the representative value is determined as an explanatory variable; and a prediction unit that predicts the running ability when the user to be predicted runs a predetermined distance based on the regression model.

Images