Information processing device, method for operating information processing device, and information processing program

Abstract

Provided is an information processing device or the like capable of classifying running practices performed by a trainee into practice menus classified in detail.　An information processing device or the like according to the present disclosure is characterized by comprising: an acquisition unit that acquires position information including time information received by a wearable terminal carried by a user who performs running training; a calculation unit that calculates pace information relating to a pace of the running training and running distance information relating to a running distance of the running training on the basis of the position information; a determination unit that determines a type of the running training on the basis of the graph shape of a speed-versus-distance graph based on running data configured as a pair of the pace information and the running distance information; and an output unit that outputs the type of the running training.

Description

Information processing device, method of operating the information processing device, and information processing program

[0001] This disclosure relates to an information processing device, a method for operating an information processing device, and an information processing program.

[0002] Running is a fundamental training method for all sports, and therefore, it is a training method that many athletes engage in. There are various types of running training menus. For example, running training menus include interval training, build-up runs, and even-pace runs. Athletes consider and select their running training menu based on their training goals and their physical condition on any given day.

[0003] Recording the daily training menu is important because it allows one to concretely understand their growth and progress, and helps maintain motivation. However, only a limited number of trainees actually record their daily training. Therefore, a device has been proposed that can automatically record the daily training menu (see, for example, Patent Document 1).

[0004] Patent Document 1 discloses a method for calculating pace and energy consumption that can accurately evaluate a user's energy consumption, such as calorie consumption, during physical activity. However, the technology disclosed in Patent Document 1 classifies the user's movements as running or walking, but the granularity of the running training menu is too coarse and not practical for trainees.

[0005] Japanese Patent Publication No. 2019-653

[0006] Therefore, the purpose of this disclosure is to provide an information processing device, a method for operating the information processing device, and an information processing program that can classify the running practice performed by a trainee into detailed training menus.

[0007] In other words, an information processing device according to one aspect of the present disclosure is characterized by comprising: an acquisition unit that acquires location information including time information received by a wearable terminal carried by a user performing running training; a calculation unit that calculates pace information relating to the pace of running training and distance information relating to the distance traveled during running training based on the location information; a determination unit that determines the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with a pair of pace information and distance information; and an output unit that outputs the type of running training.

[0008] A method for operating an information processing device according to another aspect of the present disclosure is characterized in that the processor of the information processing device performs the following steps: an acquisition step of acquiring location information including time information received by a wearable terminal carried by a user performing running training; a calculation step of calculating pace information relating to the pace of running training and distance information relating to the distance traveled during running training based on the location information; a determination step of determining the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with a pair of pace information and distance information; and an output step of outputting the type of running training.

[0009] Furthermore, an information processing program according to another aspect of the present disclosure is characterized in that the processor of the information processing device implements an acquisition function that acquires location information including time information received by a wearable terminal carried by a user performing running training; a calculation function that calculates pace information related to the pace of running training and distance information related to the distance covered during running training based on the location information; a determination function that determines the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with pace information and distance information as a pair; and an output function that outputs the type of running training.

[0010] An information processing device according to one aspect of this disclosure is characterized by comprising: an acquisition unit that acquires location information including time information received by a wearable terminal carried by a user performing running training; a calculation unit that calculates pace information and distance information based on the location information; a determination unit that determines the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with a pair of pace information and distance information; and an output unit that outputs the type of running training. Thus, the running training performed by the trainee can be classified into detailed training menus.

[0011] The method of operating an information processing device and the information processing program according to another aspect of the present disclosure can classify the running practice performed by a trainee into a detailed training menu, similar to the information processing device according to another aspect of the present disclosure.

[0012] Figure 1 is a diagram illustrating an example of the hardware configuration of the information processing device according to this embodiment. Figure 2 is a diagram illustrating an example of the functional configuration of the information processing device according to this embodiment. Figure 3 is a diagram illustrating an overview of the processing content of the processing unit of the information processing device according to this embodiment. Figure 4 is a diagram illustrating an overview of the processing content of the processing unit of the information processing device according to this embodiment. Figure 5 is a diagram illustrating the overall processing content of the determination unit of the information processing device according to this embodiment. Figure 6 is a diagram illustrating speed correction due to slope gradient according to this embodiment. Figure 7 is a diagram illustrating relative information and non-relative information according to this embodiment. Figure 8 shows the types of running force intensity according to this embodiment. Figure 9 is a diagram illustrating the processing content of the processing unit of the information processing device according to this embodiment in determining interval running. Figure 10 is a diagram illustrating the determination of interval running by the information processing device according to this embodiment. Figure 11 is a diagram illustrating the determination of interval running by the information processing device according to this embodiment. Figure 12 is a diagram illustrating the determination of interval running by the information processing device according to this embodiment. Figure 13 is a diagram illustrating the determination of interval running by the information processing device according to this embodiment. Figure 14 is a diagram illustrating the determination of interval running by the information processing device according to this embodiment. Figure 15 is a diagram illustrating the determination of interval running by the information processing device according to this embodiment. Figure 16 is a diagram illustrating the processing content of the determination unit of the information processing device according to this embodiment for determining build-up running. Figure 17 is a diagram illustrating the graph shape of build-up running according to this embodiment. Figure 18 is a diagram illustrating the graph shape of build-up running according to this embodiment. Figure 19 is a diagram illustrating the running data of build-up running according to this embodiment. Figure 20 is a diagram illustrating the running data of build-up running according to this embodiment. Figure 21 is a diagram illustrating the running data of build-up running according to this embodiment. Figure 22 is a diagram illustrating the determination of even-pace running by the determination unit of the information processing device according to this embodiment. Figure 23 is a diagram illustrating the graph shape of even-pace running according to this embodiment.Figure 24 is a diagram illustrating an example of the display screen of a user terminal according to this embodiment. Figure 25 is a diagram illustrating an example of the display screen of a user terminal according to this embodiment. Figure 26 is an example of a flowchart of an information processing program according to this embodiment. Figure 27 is a diagram illustrating an overview of the processing of an information processing device according to the second embodiment. Figure 28 is a graph visualizing the practice load, practice fatigue level, and performance score of the information processing device according to the second embodiment, where (a) is a graph of practice load and practice fatigue level, and (b) is a graph visualizing the performance score. Figure 29 is a diagram illustrating an example of the functional configuration of an information processing device according to the second embodiment. Figure 30 is an example of a flowchart of an information processing program according to the second embodiment.

[0013] An information processing device 100 according to one embodiment of the present disclosure will be described with reference to Figures 1 to 25. (Hardware configuration of the information processing device 100) First, the hardware configuration of the information processing device 100 according to this embodiment will be described with reference to Figure 1. Figure 1 is a diagram illustrating an example of the hardware configuration of the information processing device 100 according to this embodiment. The information processing device 100 includes a communication unit 100a, a ROM 100b, a RAM 100c, a storage unit 100d, a processing unit 100e, and an input / output interface 100f, etc. Furthermore, the information processing device 100 includes an input device 100g and an output device 100h as external devices that perform data input and output via the input / output interface 100f.

[0014] The communication unit 100a has a function for performing bidirectional communication with other information processing devices. When the communication unit 100a performs bidirectional communication with other information processing devices, it may do so via the information communication network 150, or it may connect directly to the other information processing device and perform bidirectional communication. The communication unit 100a may use wired communication or wireless communication for communication with other information processing devices.

[0015] ROM 100b can be used as a recording device and stores the BIOS (Basic Input Output System), which is necessary for controlling the operation of each functional unit of the information processing device 100, as well as various data used by the BIOS. The BIOS is a program that manages the basic input and output functions of the information processing device 100. It is the first program to run when the information processing device 100 is powered on, and it controls hardware such as the communication unit 100a, ROM 100b, RAM 100c, storage unit 100d, processing unit 100e, and input / output interface 100f, and prepares for the startup of the OS (Operating System).

[0016] RAM 100c is used in the configuration of the main memory accessed by the processing unit 100e, and is also used to temporarily store various data acquired or generated by the information processing device 100 before storing them in the storage unit 100d.

[0017] The storage unit 100d is implemented using an HDD (Hard Disk Drive), SSD (Solid State Drive), online storage, etc., and stores the OS, the information processing programs described later, other application software, and various data used by these programs. The storage unit 100d also stores various data acquired or generated by the information processing device 100.

[0018] The processing unit 100e includes a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), etc., and is realized by logic circuits or dedicated circuits formed by integrated circuits (IC (Integrated circuit) chips, LSI (Large-Scale Integration)), etc. The processing unit 100e functions as the processor of the information processing device 100. The input / output interface 100f is an interface for sending and receiving data to and from external devices such as the input device 100g and the output device 100h. The input device 100g includes a wearable terminal 101 (described later), a keyboard, a mouse, etc., and accepts user input for operation of the information processing device 100. The output device 100h includes a monitor, a printer, etc., and displays data generated by the information processing device 100 to the user.

[0019] (Functional Configuration of Information Processing Device 100) Next, an example of the functional configuration of the information processing device 100 will be described with reference to Figures 2 to 5. Figure 2 is a diagram illustrating the functional configuration of the information processing device 100 according to this embodiment, Figures 3 and 4 are diagrams illustrating an overview of the processing content of the processing unit 100e of the information processing device 100 according to this embodiment, and Figure 5 is a diagram illustrating the overall processing content of the determination unit 30 of the information processing device 100 according to this embodiment. The information processing device 100 takes the information processing program, which will be described later, stored in the storage unit 100d into the main memory configured with RAM 100c or the like. The processing unit 100e accesses the main memory into which the information processing program has been taken and executes the information processing program. By executing the information processing program, the information processing device 100 provides the processing unit 100e with functional units such as an acquisition unit 10, a calculation unit 20, a determination unit 30, and an output unit 40. As shown in Figures 3, 4, and 5, processing is executed in the order of the acquisition unit 10, the calculation unit 20, the determination unit 30, and the output unit 40.

[0020] Referring to Figures 3, 4, and 5, the overall processing content of the processing unit 100e of the information processing device 100 will be explained. After the processing of the acquisition unit 10, the processing unit 100e performs the processing of the calculation unit 20, which will be described later (step S60). Next, the processing unit 100e determines whether it is an interval run 57 (steps S61 to S63). Specifically, the processing unit 100e uses the determination unit 30 to determine whether the running data, which is composed of a pair of pace information and running distance information calculated by the calculation unit 20, corresponds to an interval run 57. If it is determined that it corresponds to an interval run 57 (step S62: YES), the processing of the processing unit 100e ends after it is determined that the running training that forms the basis of the running data is an interval run 57 (step S63). An interval run 57 is a type of running training that alternates between a fast-speed dash (sprint 55) and a rest run (jog 51) such as a slow jog.

[0021] If the running data is not determined to be an interval run 57 (step S62: No), the processing unit 100e uses the determination unit 30 to determine whether the running data is a build-up run 56 (steps S64 to S66). A build-up run 56 is a training method in which the runner starts at a comfortable pace and gradually increases the pace while running a certain distance or time, and is a type of running training in which the pace (speed) is increased in a step-like manner. Specifically, the processing unit 100e uses the determination unit 30 to determine whether the running data, which is composed of a pair of pace information and running distance information calculated by the calculation unit 20, is a build-up run 56. If it is determined to be a build-up run 56 (step S65: YES), the processing of the processing unit 100e ends after it is determined that the running training that forms the basis of the running data is a build-up run 56 (step S66).

[0022] If the running data is not determined to be a build-up run 56 (step S65: No), the processing unit 100e uses the determination unit 30 to determine which of the even-pace runs it is: JOG (51: running training at a relatively slow pace), comfortable run 52, pace run 53, fast pace run 54, and sprint 55 (steps S67 to S72), and then the processing unit 100e terminates processing. An even-pace run is a type of running training where you run at a constant pace. Therefore, the processing unit 100e determines which of the even-pace runs it is: JOG 51, comfortable run 52, pace run 53, fast pace run 54, and sprint 55, for the running data that is determined not to be an interval run 57 or a build-up run 56 (steps S67 to S72). A comfortable run 52 is running training where you run comfortably without worrying about pace (speed). Pace run 53 refers to running training where you consciously maintain a pace (speed). Fast pace run 54 refers to running training where you consciously maintain a faster pace (speed). Sprint 55 refers to running training at a very fast pace (speed).

[0023] The acquisition unit 10 acquires location information, including time information, received by a wearable terminal 101 carried by a user performing running training (see Figures 3 and 4). The wearable terminal 101 refers to devices such as mobile phones, smartphones, smartwatches, portable motion sensors, and tablet personal computers (hereinafter referred to as PCs), and is equipped with a positioning function that determines the position of the device in real time. A portable motion sensor is, for example, a wearable terminal 101 that incorporates a GPS (Global Positioning System) signal receiver and a 9-axis sensor, and can record the position and posture of the person carrying it. The location information, including time information, represents the real-time position of the wearable terminal 101, and the acquisition unit 10 acquires the location information, including time information, by receiving signals from the Global Navigation Satellite System (GNSS). Furthermore, location information including time information may be acquired not only by receiving signals from GNSS, but also by receiving Bluetooth®, Wi-Fi, or UWB (Ultra-Wideband) signals. Alternatively, location information including time information may be acquired by using a combination of signals from GNSS and signals from Wi-Fi, etc. In this case, signals from Wi-Fi, etc., can be used to supplement signals when reception from GNSS is insufficient. The acquisition unit 10 can acquire the user's location in real time by having the user, who is a trainee in driving practice, carry the wearable terminal 101.

[0024] The calculation unit 20 calculates pace information related to the pace of the running training and distance information related to the distance covered during the running training, based on the location information. Specifically, the calculation unit 20 calculates pace information related to the pace of the running training and distance information related to the distance covered during the running training, based on the location information including time information acquired by the acquisition unit 10. Pace refers to the average speed over a predetermined distance or time, while speed refers to the instantaneous speed at a given point in time; however, in this embodiment, pace may be used interchangeably with speed. Pace information refers to the specific value of the running training pace and is represented in a data format that the information processing device 100 can process. Distance covered refers to the distance traveled during the running training, and distance information refers to the specific value of the distance covered and is represented in a data format that the information processing device 100 can process.

[0025] The calculation unit 20 may use the speed calculated from the distance traveled per unit time based on position information including time information as pace information related to the pace of the running training. Furthermore, the calculation unit 20 may use the distance traveled between any two points in time during the running training, obtained based on position information including time information, as distance information related to the distance traveled during the running training. Pace information is information that shows the fluctuation of the user's speed during the running training, and may be relative information consisting of relative values ​​with the starting pace set to 1 (see Figures 3 and 4). In addition, pace information may be relative information consisting of relative values ​​with the average pace of the running training set to 1, or further, relative information consisting of relative values ​​with the median pace of the running training set to 1. Note that pace information may be non-relative information that has not been relativized, rather than the relative information described above. However, since non-relative information is relatively susceptible to outliers and its value fluctuates, it is preferable to relativize it. Note that when pace information is used as non-relative information, the pace information may be used after speed correction to correct for the effects of speed changes caused by slopes and low-pass filtering to remove high-frequency signals caused by noise.

[0026] The speed correction performed by the calculation unit 20 to compensate for the effects of speed changes caused by slopes will be explained with reference to Figures 4 and 6. When the pace increases or decreases due to a slope, it is unclear whether the user intentionally accelerated or decelerated. Therefore, the calculation unit 20 performs speed (pace) correction using its own correction formula. That is, it corrects the speed (pace) at gradient g using the energy cost of driving at gradient g and the energy cost of driving at zero gradient, and calculates the corrected speed (pace) at gradient g. Note that the unit of gradient g is expressed in %.

[0027] Refer to Figure 7 to compare relative and non-relative information. Figure 7 is a diagram for comparing relative and non-relative information according to this embodiment. Graph (a) in Figure 7 shows relative information, where running data consisting of pace information and running distance information as a pair is relative, and graph (b) in Figure 7 shows non-relative information, where the running data has not been relativeized. Note that the non-relative information has already undergone speed correction to compensate for the effects of speed changes due to slopes, and low-pass filtering to remove high-frequency signals due to noise. As shown in Figure 7, there is no significant difference between the graph shapes of relative information and non-relative information, so the judgment described below is performed similarly for both relative and non-relative information. Note that non-relative information is relatively susceptible to outliers and its values ​​fluctuate, so it is fundamental to relativeize it. The running data shown in Figure 7 is judged to be a comfortable run 52. Running distance information for running training may also be relative information consisting of relative distance, where 100% represents the distance from start (0%) to finish (Goal: 100%) (see Figures 3 and 4).

[0028] Incidentally, the calculation unit 20 may calculate the running power of the user based on the running data (see FIGS. 4 and 9). That is, the running power may be calculated based on the running data configured by taking the pace information and the running distance information acquired by the acquisition unit 10 as a pair. Alternatively, the calculation unit 20 may be calculated based on the user's personal best time at an arbitrary distance by self-reporting, based on %HRmax or %Vo2max described later, or may be calculated based on the Daniels theory of Jack Daniels described later. Further, the calculation unit 20 may delete unnecessary data (see FIG. 4). Specifically, the calculation unit 20 may delete the running data immediately after the start and immediately after the end of the activity, the running data during the walking time, and the running data during the time of stopping due to traffic signals or the like as unnecessary data.

[0029] The determination unit 30 determines the type of running training based on the graph shape of the speed-distance graph based on the running data configured by taking the pace information and the running distance information as a pair. Note that the type of running training may be used in the same sense as the training menu. The type of running training will be described with reference to FIG. 8. FIG. 8 shows the types of running power intensities according to the present embodiment and also shows the reference pace for each running power intensity. The types of running training include jogging (JOG) 51, comfortable running 52, pace running 53, buildup running 56, faster pace running 54, and interval running 57.

[0030] The types of running intensity are, as shown in FIG. 8, Easy, Moderate, Active, Hard, and Interval (1 km), etc. The reference pace for each type of running intensity is set according to the characteristics of the subject such as endurance. The example shown in FIG. 8 is the running intensity of a person who finishes a full marathon with a personal best time of 4:00:00 (4 hours). The running intensity shown in FIG. 8 may be set based on %HRmax or %Vo2max, etc. %HRmax refers to the ratio of the heart rate during exercise to the maximum heart rate (HRmax). The maximum heart rate (HRmax) refers to the maximum number of heartbeats per minute during exercise. %Vo2max refers to the ratio of the oxygen uptake during exercise to the maximum oxygen uptake (Vo2max). The maximum oxygen uptake (Vo2max) refers to the amount of oxygen taken in per unit time (usually 1 minute) when the cardiopulmonary function and the oxygen utilization ability of the muscles reach their limits during exercise. Also, the running intensity shown in FIG. 8 may be calculated using Jack Daniels' Daniels theory based on the subject's own record.

[0031] The speed - distance graph is a graph that takes pace information related to the pace of running training on the vertical axis and running - distance information related to the running distance of running training on the horizontal axis, and visualizes the running data composed of a pair of pace information and running - distance information in a graph shape.

[0032] (Regarding the determination unit 30) The determination unit 30 may determine that the type of running training is running training that alternately and periodically performs anaerobic exercise with an increased running speed and aerobic exercise with a decreased running speed when the extreme value of the amplitude spectrum obtained by extracting and acquiring the frequency components included in the running data exceeds a threshold at a frequency where the extreme value of the amplitude spectrum corresponding to the amplitude at the obtained frequency is not less than a predetermined value. That is, the determination unit 30 determines that the running data has periodicity at the frequency showing the amplitude spectrum when the extreme value of the amplitude spectrum exceeds the threshold. Note that the extreme value may include both the maximum value and the minimum value.

[0033] An amplitude spectrum, which associates frequency with amplitude, is obtained by decomposing running data, which is composed of pace information and running distance information as a pair, into frequency components and showing the amplitude (intensity) of each frequency component. In this embodiment, it is displayed by a graph with frequency on the horizontal axis and amplitude on the vertical axis. Running training that alternates periodically between anaerobic exercise at a high running speed and aerobic exercise at a low running speed may be called interval running 57. A local maximum is the point in the vicinity of a given point on the graph of a function that takes the largest value. A local minimum is the point in the vicinity of a given point on the graph of a function that takes the smallest value. Frequencies above a predetermined value are set in order to exclude frequencies below the predetermined value from the judgment target of the judgment unit 30 as noise. The predetermined value is set appropriately depending on the magnitude of the noise.

[0034] The determination unit 30 may determine that the type of running training is running training in which anaerobic exercise at a faster running speed and aerobic exercise at a slower running speed are performed alternately and periodically, if there are two or more peak values ​​(extreme values) in the speed-to-distance graph, and none of the extreme values ​​of the amplitude spectrum obtained by extracting frequency components contained in the running data representing the speed-to-distance graph and corresponding the amplitude to the frequency do not exceed the threshold at frequencies above a predetermined value, and furthermore, if at least one of the extreme values ​​of the amplitude spectrum obtained by extracting frequency components contained in the running data for the section where the length of the absolute time calculated for each interval between the peak values ​​(extreme values) of two adjacent speed-to-distance graphs remains below the threshold exceeds the threshold, then the determination unit 30 may determine that the type of running training is running training in which anaerobic exercise at a faster running speed and aerobic exercise at a slower running speed are performed alternately and periodically.

[0035] Furthermore, the determination unit 30 determines that the type of running training is running training in which anaerobic exercise at a faster running speed and aerobic exercise at a slower running speed are performed alternately and periodically, if there are two or more peak values ​​(extreme values) in the speed-to-distance graph, and none of the extreme values ​​of the amplitude spectrum obtained by extracting frequency components contained in the running data representing this speed-to-distance graph and associating amplitude with frequency do not exceed the threshold at frequencies above a predetermined value, and furthermore, if the length of the interval between the peak values ​​(extreme values) of two adjacent speed-to-distance graphs for which the absolute time calculated remains below the threshold is the same, and therefore it is not possible to select the maximum of 1 intervals, then at least one of the extreme values ​​of the amplitude spectrum obtained by extracting frequency components contained in the running data for the interval in which the value of pace variance for each of these intervals of the same length is maximum exceeds the threshold.

[0036] The determination of interval running 57 by the determination unit 30 will be explained with reference to Figures 9 to 15. Figure 9 is a diagram illustrating the processing content in the determination of interval running 57 by the processing unit 100e of the information processing device 100 according to this embodiment, and Figures 10 to 15 are diagrams illustrating the determination of interval running 57 by the information processing device 100. First, with reference to Figure 9, the processing flow of the determination of interval running 57 by the determination unit 30 will be explained.

[0037] Step S61a: The running data calculation unit 20, which has been processed by the calculation unit 20, calculates running training pace information and running distance information, which are running data, based on the location information including time information acquired by the acquisition unit 10.

[0038] Step S61b: The determination unit 30 detects the peak value (extreme value) of the speed-distance graph for the driving data. Specifically, the determination unit 30 detects the peak value (extreme value) of the pace in the driving data, which is composed of a pair of pace information and driving distance information. The peak value (extreme value) of the pace in the driving data appears as a shape that is convex in the positive direction of the vertical axis representing the pace, or convex in the negative direction of the vertical axis representing the pace, in the graph shape of the speed-distance graph based on the driving data.

[0039] Step S61c: Are there two or more peak values ​​in the speed-distance graph? The determination unit 30 determines whether there are two or more peak values ​​(extreme values) in the speed-distance graph. If there are not two or more peak values ​​(extreme values) in the speed-distance graph (S61c: No), it determines that the running data is not from interval running 57. If there are two or more peak values ​​(extreme values) in the speed-distance graph (S61c: Yes), it proceeds to step S61d.

[0040] Step S61d: Determine the top 10% pace between peak values. If there are multiple intervals between peak values ​​and multiple top 10% paces between these intervals, the average is taken. Note that it is not limited to the top 10%, but may be between 10% and 30%. The determination unit 30 determines the top 10% pace among the paces between the peak values ​​(extreme values) of the speed-distance graph. If there are three or more peak values ​​(extreme values) excluding the start and finish points of the speed-distance graph, there will be two or more intervals between peak values ​​(extreme values) of the speed-distance graph. Therefore, the determination unit 30 determines the top 10% pace for each of the multiple intervals between peak values ​​(extreme values) of the speed-distance graph and takes their average.

[0041] Graph (a) in Figure 10 is a diagram illustrating the speed-to-distance graph of interval running 57, graph (b) in Figure 10 is a diagram illustrating the graph shape of the speed-to-distance graph determined to be interval running 57, and graph (c) in Figure 10 is a graph showing the amplitude spectrum obtained by Fourier transforming the speed-to-distance graph, with the amplitude corresponding to the frequency. As shown in graph (a) in Figure 10, the speed-to-distance graph of interval running 57 has pace (speed) on the vertical axis and distance on the horizontal axis, with the pace (speed) decreasing as you go higher on the vertical axis. As shown in graph (a) in Figure 10, the speed-to-distance graph of interval running 57 has many fluctuations due to changes in pace in one activity (i.e., one running training session) because it repeats sprinting 55 and jogging 51. In other words, the speed-to-distance graph of interval running 57 has a waveform shape because it has many fluctuations due to changes in pace. Therefore, in order to confirm the presence or absence of periodicity and the magnitude of that periodicity in the running data, which is composed of pace information and running distance information as a pair, a Fourier transform is performed to extract the periodic component. Graph (b) in Figure 10 shows an example of a speed-to-distance graph that is determined to be an interval run 57. Running training that consists of two or fewer sprints 55, or where the jog 51 connecting the sprints 55 is walked or stopped, is not determined to be an interval run 57, but is determined to be a jog 51 or a sprint 55. As shown in the upper graph of graph (c) in Figure 10, when the speed-to-distance graph of an interval run 57 is Fourier transformed, a maximum value of 60 is prominently displayed in the graph showing the amplitude spectrum, where the amplitude corresponds to the frequency. This is because the speed (pace)-to-distance graph in the upper part of graph (c) in Figure 10 is for an interval run, and the waveform shape is due to the many fluctuations caused by changes in pace. On the other hand, as shown in the lower graph of graph (c) in Figure 10, when the speed-to-distance graph of the pace run 53 is Fourier transformed, no significant maximum value 60 appears in the amplitude spectrum graph, which corresponds to frequency and amplitude. This is because the speed (pace)-to-distance graph in the lower graph (c) in Figure 10 is for a pace run, and there are hardly any fluctuations due to changes in pace.

[0042] Graph (a) in Figure 11 is a speed-to-distance graph of the interval run 57, and graph (b) in Figure 11 is a graph showing the amplitude spectrum obtained by Fourier transforming the speed-to-distance graph and associating the amplitude with the frequency. As shown in graph (a) in Figure 11, in the interval run section 73, the user alternates between sprinting 55 and jogging 51. As shown in graph (b) in Figure 11, in the graph showing the amplitude spectrum, the multiple maximum values ​​74 do not reach the area 77 defined by a predetermined frequency 75 and threshold 76. In such cases, the determination unit 30 executes the processing from step S61i (see Figure 9) onward to determine whether or not there is periodicity in the running data, which is composed of pace information and running distance information as a pair. If at least one maximum value 74 is within the area 77 (step S61h: Yes), the running training from which the running data was acquired is determined to be an interval run 57.

[0043] Step S61e: Is the above speed above the threshold? That is, it is determined whether the above is faster than the running intensity Hard. Above refers to the pace in the top 10% of the peak values ​​of the running data. The threshold refers to the lower limit of the guideline pace (min / km) for running intensity Hard. That is, in the example shown in Figure 8, the threshold is 4:39 (min / km). This threshold is not limited to this and can be changed as appropriate. The determination unit 30 determines whether the pace in the top 10% of the peak values ​​(extreme values) of the speed vs. distance graph is faster than the threshold. If the determination unit 30 determines that the above is faster than the threshold, it proceeds to step S61f, and if it determines that the above is not faster than the threshold, it determines that the running data is not from an interval run. Steps S61b to S61e determine whether the pace of the section of the running data that is considered to be a sprint section is faster than the threshold. If the pace in a section considered to be a sprint section is determined not to be faster than a threshold, then it is determined that there is no sprint section in the running data. If you try to run at the same speed even if there is a hill during running training, that pace will be corrected. In particular, if there is a steep downhill slope, the pace in that section will be evaluated as slower, and there is a concern that this will cause the graph shape of the speed-to-distance graph based on the running data to take on a waveform shape similar to that of interval running. For this reason, in determining whether interval running 57 occurred in the determination unit 30, it first determines whether the pace in the section considered to be a sprint section in the running data is faster than a threshold (steps S61b to S61e), and then determines whether or not sprinting occurred in the section of the running data.

[0044] Step S61f: Fourier transform, detection of peak value of the above data. The determination unit 30 performs a Fourier transform on the running data, which is composed of pace information and running distance information as a pair, extracts frequency components, and detects the peak value (extreme value) of the amplitude spectrum, which corresponds the amplitude to the acquired frequency.

[0045] Step S61g: Is there a peak value in the amplitude spectrum? The determination unit 30 determines whether or not there is a peak value (extreme value) in the amplitude spectrum. If there is no peak value (extreme value) in the amplitude spectrum (S61g: No), it determines that the running data is not from interval running 57. If there is a peak value (extreme value) in the amplitude spectrum (S61g: Yes), it proceeds to step S61h.

[0046] Step S61h: Is at least one of the peak values ​​of the amplitude spectrum greater than the threshold? The threshold is an amplitude spectrum of 0.085 at a frequency of 0.01 (Hz). This threshold is not limited to this and can be changed as appropriate. The determination unit 30 determines that the running data is from an interval run 57 if at least one of the peak values ​​(extreme values) of the amplitude spectrum is greater than the threshold (S61h: Yes), and proceeds to step S61i if all of the peak values ​​(extreme values) of the amplitude spectrum are less than the threshold (S61h: No).

[0047] Step S61i: The determination unit 30, which determines the absolute time interval between peak values ​​of running data, which is composed of pace information and running distance information as a pair, determines the absolute time interval between the peak value (extreme value) of an adjacent speed-to-distance graph and the peak value (extreme value) of the speed-to-distance graph. Absolute time refers to time that flows uniformly regardless of the circumstances or observer, and progresses at a constant speed without being affected by external factors.

[0048] Step S61j: The threshold for determining the length over which the absolute time of the interval remains below the threshold is 600 seconds. This threshold is not limited to this and can be changed as appropriate. The determination unit 30 determines the length over which the absolute time of the interval between peak values ​​(extreme values) of the velocity-distance graph (the interval between adjacent peak values ​​(extreme values) of the velocity-distance graph and the peak value (extreme value) of the velocity-distance graph remains below the threshold (e.g., 600 s). The length over which the absolute time of the interval remains below the threshold is the length (expressed as the number of intervals) until the interval to which 0 is assigned is reached, when the absolute time of the interval between extrema is longer than the threshold. An interval is the range between two adjacent extrema. For intervals where the absolute time of the interval between extrema is shorter than the threshold, a predetermined number is assigned according to the distance (expressed as the number of intervals) to the interval to which 0 is assigned. For example, an interval to which 0 is assigned is zero (i.e., an adjacent interval) is assigned 1. A section that is one section away from a section assigned a value of 0 will be assigned a value of 2. A section that is two sections away from a section assigned a value of 0 will be assigned a value of 3.

[0049] Referring to graph (a) and table (b) in Figure 12, we will specifically explain the length over which the absolute time of an interval remains below the threshold. Graph (a) in Figure 12 is a speed-distance graph with relative distance (%) on the horizontal axis and relative pace on the vertical axis. The absolute time of the interval from maximum 1 to maximum 2 is 258.3 seconds, as shown in table (b) in Figure 12, which is below the threshold (600 seconds). The absolute time of the interval from maximum 2 to maximum 3 is 735.2 seconds, as shown in table (b) in Figure 12, which is above the threshold (600 seconds). The absolute time of the interval from maximum 3 to maximum 4 is 397.4 seconds, as shown in table (b) in Figure 12, which is below the threshold (600 seconds). The absolute time of the interval from maximum 4 to goal is not a number, and as shown in table (b) in Figure 12, it is forcibly set above the threshold (600 seconds). In other words, the interval from the local maximum to goal is necessarily assumed to exceed the threshold (600 seconds). As shown in Table (b) in Figure 12, intervals where the absolute time is below the threshold are assigned a value of 1, and intervals where the absolute time is above the threshold are assigned a value of 0. In the example shown in Table (b) in Figure 12, the length of time for which the absolute time of an interval remains below the threshold is "1" for the interval from local maximum 1 to local maximum 2, and also "1" for the interval from local maximum 3 to local maximum 4. In this case, the length of time for which the absolute time of an interval remains below the threshold is the same for the interval from local maximum 1 to local maximum 2 and the interval from local maximum 3 to 4, and therefore it is impossible to determine in step S61l described later (S61l; Yes).

[0050] Next, referring to graph (c) and table (d) in Figure 12, we will explain a case that differs from the example shown in graph (a) and table (b) in Figure 12. Figure 12(c) is a speed-to-distance graph with relative distance (%) on the horizontal axis and relative pace on the vertical axis. The example shown in Figure 12(c) has six local maximums. The absolute time in the interval from local maximum 1 to local maximum 2 is 258.3 seconds, as shown in graph (c) in Figure 12, which is below the threshold (600 seconds). The absolute time in the interval from local maximum 2 to local maximum 3 is 397.4 seconds, as shown in graph (c) in Figure 12, which is below the threshold (600 seconds). The absolute time in the interval from local maximum 3 to local maximum 4 is 497.3 seconds, as shown in graph (c) in Figure 12, which is below the threshold (600 seconds). The absolute time in the interval from local maximum 4 to local maximum 5 is 735.2 seconds, as shown in graph (c) in Figure 12, which exceeds the threshold (600 seconds). The absolute time in the interval from local maximum 5 to local maximum 6 is 337.4 seconds, as shown in graph (c) in Figure 12, which falls below the threshold (600 seconds). The absolute time in the interval from local maximum 6 to goal is not a number, and as shown in graph (c) in Figure 12, it is forcibly set to exceed the threshold (600 seconds). In the example shown in table (d) in Figure 12, there are two lengths in which the absolute time of the interval remains below the threshold. One of these lengths is the interval from local maximum 1 to local maximum 4 (expressed by the number of intervals), which is the interval to which 0 is assigned (local maximum 4 to local maximum 5), and its length is expressed as "3, 2, 1". That is, the interval between local maximum 1 and local maximum 2 is "3", the interval between local maximum 2 and local maximum 3 is "2", and the interval between local maximum 3 and local maximum 4 is "1". The other length is the interval to which 0 is assigned (local maximum 6 to goal) (expressed by the number of intervals), which is the interval between local maximum 5 and local maximum 6, and its length is expressed as "1". In this case, the length for which the absolute time of an interval remains below the threshold is the length of the interval between local maximum 1 and local maximum 4, which is "3, 2, 1", and the length of the interval between local maximum 5 and local maximum 6, which is "1". Between the interval from local maximum 1 to local maximum 4 and the interval from local maximum 5 to local maximum 6, the interval from local maximum 1 to local maximum 4 is the longest, which can be determined in step S61l described later (S61l; No), and in step S61n described later, a Fourier transform is performed on the driving data for the portion of the interval from local maximum 1 to local maximum 4 to calculate the peak value.

[0051] Step S61k: The determination unit 30, which extracts the longest portion from the driving data, extracts the driving data for the portion (section) where the absolute time between peak values ​​(extreme values) of the speed vs. distance graph remains below a threshold.

[0052] Step S61l: Is it impossible to determine because the lengths are the same? The determination unit 30 determines whether there are multiple lengths for which the absolute time between the peak values ​​(extreme values) of the speed-distance graph remains below a threshold, and whether these lengths are the same, making it impossible to identify the longest portion. If the lengths are the same and a determination cannot be made (S61l: Yes), the determination unit 30 proceeds to step S61m. If the lengths are not the same and the longest portion can be determined (S61l: No), the determination unit 30 proceeds to step S61n.

[0053] Step S61m: The variance of the running speed in the range from the start point to the end point that includes each of the above lengths is taken, and the length with the maximum is adopted. The start point is, for example, the coordinate value of X at the first point of the section minus 5% of the section. The end point is, for example, the coordinate value of X at the last point of the section plus 5% of the section. The determination unit 30 calculates, for example, the relative running speed variance from the start point to the end point that includes the maximum values ​​1 to 2 shown in Figure 12, and the relative running speed variance from the start point to the end point that includes the maximum values ​​3 to 4, and adopts the length with the maximum variance. Furthermore, the section from the starting point to the ending point that includes local maximums 1 and 2 refers to interval A shown in graph (b) of Figure 13, and is defined as the coordinate value obtained by subtracting 5% of the interval from the starting point (the X coordinate value at the first point (local maximum 1) in the interval from local maximum 1 to local maximum 2) to the ending point (the coordinate value obtained by adding 5% of the interval to the X coordinate value at the last point (local maximum 2) in the interval from local maximum 1 to local maximum 2). Also, the section from the starting point to the ending point that includes local maximums 3 and 4 refers to interval B shown in graph (b) of Figure 13, and is defined as the coordinate value obtained by subtracting 5% of the interval from the starting point (the X coordinate value at the first point (local maximum 3) in the interval from local maximum 3 to local maximum 4) to the ending point (the coordinate value obtained by adding 5% of the interval to the X coordinate value at the last point (local maximum 4) in the interval from local maximum 3 to local maximum 4). In the example shown in Figure 12, the variance of the running speed from the start point to the end point (section A) including the maximum values ​​1 and 2 is 0.097, and the variance of the running speed from the start point to the end point (section B) including the maximum values ​​3 and 4 is 0.283 (see graph (b) in Figure 13). The determination unit 30 adopts the section from the start point to the end point (section B) including the maximum values ​​3 and 4, where the variance of the running speed is 0.283, as the section with the longest length.

[0054] Step S61n: The determination unit 30 performs a Fourier transform on the driving data of the selected length portion and detects the peak value of the amplitude spectrum. The determination unit 30 detects the peak value (maximum value) 91 of the amplitude spectrum obtained by performing a Fourier transform on the driving data of the longest portion (S61k), or the portion (S61m) of the length portion in which the variance of the driving speed in the range from the start point to the end point including the length is maximum (see graph (b) in Figure 14).

[0055] Step S61o: Fourier transform the running data for the selected length and check if at least one of the peak values ​​of the amplitude spectrum is greater than the threshold. The threshold is 0.085 for an amplitude spectrum at a frequency of 0.01 (Hz). This threshold is not limited to this and can be changed as appropriate. The determination unit 30 determines that the running data is from an interval run if at least one of the peak values ​​(maximum values) 91 of the amplitude spectrum obtained by Fourier transforming the running data for the longest length (S61k) or the length (S61m) in which the variance of the running speed in the range from the start point to the end point including the length is maximum is greater than the threshold 76 (S61o: Yes) (see Figure 14). The determination unit 30 determines that the running data is not from an interval run if all of the peak values ​​(maximum values) 91 of the amplitude spectrum are less than the threshold 76 (S61o) (see Figure 14).

[0056] Referring to Figures 12 to 14, the determination of the interval run 57 by the determination unit 30 will be explained when the extreme values ​​of the amplitude spectrum, obtained by extracting frequency components from the running data and associating the amplitude with the frequency, do not exceed a threshold at frequencies above a predetermined value. Graph (a) in Figure 12 is a speed-distance graph of the interval run 57, and table (b) in Figure 12 shows the absolute time interval (s) between each of the maximum values ​​and whether or not the absolute time remains below the threshold. The running data shown in graph (a) in Figure 12 has maximum values ​​1, 2, 3, and 4. As shown in table (b) in Figure 12, the absolute time interval between maximum value 1 and maximum value 2 is 258.3 (s), the absolute time interval between maximum value 2 and maximum value 3 is 735.2 (s), and the absolute time interval between maximum value 3 and maximum value 4 is 397.4 (s). The interval between maximum value 4 and Goal is not a number (NaN). When the absolute time threshold is set to 600 (s), the intervals that are less than or equal to this threshold are the interval between maximum 1 and maximum 2, and the interval between maximum 3 and maximum 4. Of these, the interval that continues to be the longest while remaining below the threshold is subjected to another Fourier transform using the following two points as the start and end points. The following two points are as follows: ・Start point: [X coordinate value at the first point of that interval] - 5% ・End point: [X coordinate value at the last point of that interval] + 5% In this embodiment, the absolute time of the interval between maximum 1 and maximum 2 is less than the threshold, the absolute time of the interval between maximum 2 and maximum 3 is greater than the threshold, the absolute time of the interval between maximum 3 and maximum 4 is less than the threshold, and the absolute time of the interval between maximum 4 and Goal is not a number, so it is forcibly set to be greater than the threshold.

[0057] Table (a) in Figure 13, similar to Table (b) in Figure 12, shows the absolute time interval (s) for each interval between maxima and whether or not the absolute time remains below the threshold. Figure 13(b) shows the variance of the relative pace between intervals A and B in a speed-to-distance graph. Comparing the absolute time interval between maxima 1 and maxima 2 with the absolute time interval between maxima 3 and maxima 4, the length for which the absolute time interval remains below the threshold is "1" for both, making it impossible to select the longest length. In this case, we calculate the variance of the relative pace for each of intervals A and B from the start point to the end point corresponding to the interval between maxima 1 and maxima 2. As shown in Figure 13(b), the variance of the relative pace for interval A is 0.097, and the variance of the relative pace for interval B is 0.283. Since the variance for interval B is larger, we assume this interval is an "interval running interval" and perform the Fourier transform again on this interval only.

[0058] Graph (a) in Figure 14 is a velocity-distance graph for interval B, which includes the maximum values ​​3 and 4, and graph (b) in Figure 14 is a graph of the amplitude spectrum obtained by performing a Fourier transform on interval B. As shown in graph (b) in Figure 14, the maximum value 91 of the amplitude spectrum obtained by performing a Fourier transform on interval B is within area 77, so it is determined that interval B is an interval running interval and the analysis is terminated.

[0059] Referring to Figure 15, examples of running data that the determination unit 30 determines to be interval running 57 and running data that it does not determine to be interval running 57 are shown. Graph (a) in Figure 15 illustrates the graph of the amplitude spectrum corresponding to the amplitude of the running data that the determination unit 30 determines to be interval running 57 and its frequency. Graph (b) in Figure 15 illustrates the graph of the amplitude spectrum corresponding to the amplitude of the running data that the determination unit 30 does not determine to be interval running 57 and its frequency. Graph (b) in Figure 15 illustrates the cases where there are two or fewer sprints 55 and where the connecting jog 51 is "walking" or "stopping". A connecting jog refers to a jog 51 that connects two sprints 55.

[0060] The determination unit 30 may extract frequency components contained in the running data, which is composed of pace information and running distance information as a pair, by Fourier transform. The determination unit 30 may also determine whether or not periodicity is contained in the running data using autocorrelation, supervised learning, unsupervised learning, peak value, zero crossing, and spectral analysis.

[0061] In the method using autocorrelation, the driving data to be judged may be shifted in the x-axis direction for a certain period of time as shown in the graph above, and the correlation (autocorrelation) between the driving data before the shift and the driving data after the shift may be taken to determine whether or not it has periodicity. If the autocorrelation result shows that it has periodicity, the driving data to be judged is determined to have periodicity.

[0062] In the supervised learning method, the periodic driving data is prepared in advance as ground truth data, and the similarity (e.g., correlation coefficient or cosine similarity) between the driving data to be judged and the ground truth data is calculated. If the similarity exceeds a threshold, the driving data to be judged is determined to be periodic. Alternatively, in the supervised learning method, a machine learning model may be prepared using a large number of driving data that include both periodic and non-periodic driving data, with the periodic driving data annotated as the ground truth, to determine whether or not the driving data to be judged is periodic.

[0063] In methods using unsupervised learning, clustering may be performed on a large number of the driving data, and the driving data classified into clusters (groups) that exhibit periodicity may be determined to be periodic.

[0064] In the method using local maximums, the local maximum of the driving data subject to evaluation is obtained, and if multiple local maximums exist at regular time intervals, the driving data subject to evaluation may be determined to have periodicity. Alternatively, in the method using local minimums, the local minimum of the driving data subject to evaluation is obtained, and if multiple local minimums exist at regular time intervals, the driving data subject to evaluation may be determined to have periodicity.

[0065] In the zero-crossing method, the driving data subject to evaluation may be determined to have periodicity if the number of times it crosses the average value (or x-axis) of the driving data is greater than or equal to a threshold. Alternatively, in the zero-crossing method, the driving data subject to evaluation may be determined to have periodicity if the intersection points between the driving data subject to evaluation and the average value (or x-axis) exist at regular time intervals.

[0066] In a method using spectral analysis, the power spectrum of the frequency components included in the driving data subject to determination is obtained, and if the power spectrum in the target frequency band is above a threshold, it may be determined that the driving data has periodicity in the frequency that shows that power spectrum.

[0067] (Regarding the determination of the build-up run 56 by the determination unit 30) The determination unit 30 determines that the type of running training is running training in which the running speed is increased in stages if the graph shape of the speed versus distance graph is stepwise, and the median value of the pace corresponding to each step that makes up the stepwise shape gets progressively faster as the running distance increases. Running training in which the running speed is increased in stages may be defined as a build-up run 56.

[0068] The determination of the build-up run 56 by the determination unit 30 will be explained with reference to Figures 16 to 21. Figure 16 is a diagram illustrating the processing content of the determination of the build-up run 56 by the determination unit 30 of the information processing device 100 according to this embodiment, Figures 17 and 18 are diagrams illustrating the graph shape of the build-up run 56 according to this embodiment, and Figures 19 to 21 are diagrams illustrating the running data of the build-up run 56 according to this embodiment.

[0069] First, referring to Figure 16, the processing details of the determination unit 30's determination of the build-up run 56 will be explained. Step S64a: The running data calculation unit 20, processed by the calculation unit 20, calculates the pace information and running distance information of the running training, which are running data, based on the location information including time information acquired by the acquisition unit 10.

[0070] Step S64b: Calculate the moving median (noise reduction). The determination unit 30 calculates the moving median based on the driving data. The moving median is a method used in time series data to smooth out changes and provide an overview of the data. It is an indicator used to understand the trend of time series data, and the number that falls in the middle when the data is arranged in order is used as the median. The median has the characteristic of being less affected by outliers.

[0071] Step S64c: The difference is taken at the above-mentioned midpoint of movement and the acceleration is calculated. The determination unit 30 extracts the difference acceleration of the above-mentioned midpoint of movement and detects the pace change as a peak value. Graph (a) in Figure 16 is a step-shaped velocity-distance graph, and graph (b) in Figure 16 is an acceleration-distance graph with the difference acceleration of the midpoint of movement extracted.

[0072] Step S64d: Smoothing is performed to detect the peak value (extreme value). In graph (b) in Figure 16, graph line 82 is the graph line before smoothing, graph line 83 is the graph line after smoothing, and point 84 is the peak value (extreme value). Depending on how the y-axis of the graph in graph (b) in Figure 16 is defined, the extreme value can be either a local maximum or a local minimum.

[0073] Step S64e: Has a peak value been detected? If the determination unit 30 detects a peak value (extreme value) (Step S64e: Yes), the process proceeds to step S64f. If the determination unit 30 does not detect a peak value (extreme value) (Step S64e: No), it is determined that the running training related to the running data is not a build-up run 56.

[0074] Step S64f: The speed from point n where the peak value was detected to the next point n+1 is defined as speed n+1, and the median speed is calculated. The determination unit 30 defines the speed from point n where the peak value (extreme value) was detected to the next point n+1, and calculates the median speed in that section. For example, the first point from the start is speed 1, the point from the first to the second point is speed 2, ..., and the point from the nth point to the end is speed n+1.

[0075] Step S64g: Are both of the following conditions met? Condition 1: Speed ​​k is slower than speed k+1. Condition 2: Speed ​​n+1 (finish) is faster than speed 1 by a threshold. Speed ​​k is defined as the distance from point k-1 where the peak value (extreme value) was detected to the next point k. If condition 1 is met, then at any point k, speed k is slower than speed k+1. The determination unit 30 determines that if both conditions are met (Step S64g: Yes), the running training related to the running data is a build-up run 56, and if either of the two conditions is not met (Step S64g: No), the running training related to the running data is not determined to be a build-up run 56.

[0076] Referring to Figures 17 to 21, the graph shape and running data of the build-up run 56 will be explained. The characteristic of the build-up run 56 is that after running at a constant pace, the pace quickens in a short time, and then the pace returns to a constant pace, and this cycle is repeated. Because the pace quickens in a short time, the graph shape of the build-up run 56 is stepped. For this reason, the step-like shape is made easier to show by finding the median of movement. The difference is taken at the median of movement, and the acceleration is calculated to detect the pace change using the peak value (extreme value) 84. A build-up run 56 is defined as one that satisfies both of the following two conditions A and B. A: The median of each speed gradually increases. B: The final speed is faster than the initial speed by a threshold or more. Graph (a) in Figure 17 is a diagram to explain the characteristics of the graph shape of the build-up run 56. As shown in graph (a) in Figure 17, the speed increases in a stepped manner from the start: speed 1 < speed 2 < speed 3 < speed 4. Graph (b) in Figure 17 illustrates a graph shape that the determination unit 30 determines to be a build-up run 56, while graph (c) in Figure 17 illustrates a graph shape that the determination unit 30 does not determine to be a build-up run. The graph shape illustrated in graph (c) in Figure 17 is determined to be either a jog 51 or a sprint 55.

[0077] Graph (a) in Figure 18 shows the running data for the build-up run 56, and graph (b) in Figure 18 shows the graph shape of the acceleration-to-distance graph. Graph (c) in Figure 18 shows an example where the distance from the point n where the peak value was detected to the next point n+1 is defined as speed n+1, and graph (d) in Figure 18 shows the interrelationship of the relative pace averages of speed 1, speed 2, speed 3, and speed 4. Note that n is an integer greater than or equal to 0 (zero), and n=0 indicates that the distance run in the speed-to-distance graph is 0 (=start). As shown in graph (b) in Figure 18, a peak value (extreme value) is detected in the acceleration-to-distance graph, and the distance from the point n where the peak value (extreme value) was detected to the next point n+1 is defined as speed n+1. As shown in graph (d) in Figure 18, the running data in graph (c) in Figure 18 satisfies the two conditions A and B above, so the running data in graph (c) in Figure 18 is determined to be the build-up run 56.

[0078] Referring to graph (a) in Figure 19, the noise reduction associated with the calculation of the moving median performed in step S64b will be explained, and referring to graph (b) in Figure 19, the implementation of the low-pass filter performed in step S64c will be explained below. As shown in graph (a) in Figure 19, comparing graph 85 before taking the moving median with graph 86 after taking the moving median, the step shape of graph 86 after taking the moving median is clearly visible, indicating the effect of noise reduction. As shown in graph (b) in Figure 19, comparing graph 87 before implementing the low-pass filter with graph 88 after implementing the low-pass filter, it can be seen that a removed maximum value 90 exists. The removed maximum value 90 is thought to be due to noise, and two peak values ​​(maxima) 89 that were not removed were obtained.

[0079] Referring to Figure 20, the procedure by which the judgment unit 30 makes a judgment on the build-up run 56 will be explained. In Figure 20, the upper graph of graph (a) is a speed-to-distance graph, the lower graph is an acceleration-to-distance graph, and graph (b) in Figure 20 is a table for confirming the above-mentioned conditions A and B. First, as shown in graph (a) in Figure 20, the median of movement is calculated for graph 85 before taking the median of movement of the speed-to-distance graph of the running data, and graph 86 after taking the median of movement is obtained. The difference is taken at the median of movement for graph 86, the acceleration is calculated, and graph 88 (graph before low-pass filtering is performed) is obtained. Then, low-pass filtering is performed on graph 87 to obtain graph 88 (graph after low-pass filtering is performed). The peak value (maximum value) of graph 88 is detected, and speed 1, speed 2, and speed 3 are set based on the distance traveled at the detected peak value (maximum value). For each of the set speeds 1, speed 2, and speed 3, the median of the relative speed (median of movement) is calculated, and the magnitudes of speeds 1, speed 2, and speed 3 are compared with each other. As shown in graph (b) in Figure 20, speed 2 is faster than speed 1, and speed 3 is faster than speed 2, so condition A is satisfied. Speed ​​3 is 5% (threshold) or more faster than speed 1, so condition B is satisfied. Therefore, since conditions A and B are satisfied as described above, it can be determined that the running training related to the running data shown in graph (a) in Figure 20 is a build-up run 56.

[0080] Referring to Figure 21, we will describe the running data that is determined to be a build-up run 56 and the running data that is not determined to be a build-up run 56. Graph (a) in Figure 21 illustrates running data that is determined to be a build-up run 56, and graph (b) in Figure 21 illustrates running data that is not determined to be a build-up run 56. As shown in graph (b) in Figure 21, it can be seen that there are no peak values ​​(extreme values) in the acceleration-to-distance graph.

[0081] (Determination of even-pace running by the determination unit 30) The determination of even-pace running by the determination unit 30 will be explained with reference to Figures 22 and 23. Figure 22 is a diagram for explaining the determination of even-pace running by the determination unit 30 of the information processing device 100 according to this embodiment, and Figure 23 is a diagram for explaining the graph shape of even-pace running according to this embodiment.

[0082] The determination unit 30 may determine that the type of running training is running training where the running speed is kept constant, if the graph shape of the speed-distance graph is not waveform or step-like. The calculation unit 20 calculates the user's running ability based on the running data, and the determination unit 30 may determine further subdivided types of running training based on the running ability for running training determined to be running training where the running speed is kept constant. Running training where the running speed is kept constant may be defined as even-pace running. Further subdivided types may be classified based on the pace during running. Further subdivided types may be, for example, jog 51, comfortable run 52, pace run 53, fast pace run 54, and sprint 55.

[0083] First, referring to Figure 22, the processing details of the determination unit 30's determination of even-pace running will be explained. Step S67a: The running data calculation unit 20 processed by the calculation unit 20 calculates the pace information and running distance information of the running training, which are running data, based on the location information including time information acquired by the acquisition unit 10.

[0084] Step S67b: Is the median speed of the running data processed by the calculation unit 20 slower than (Moderate + easy) / 2? The determination unit 30 determines whether the median speed of the running data is slower than (Moderate + easy) / 2. If it is slower (Step S67b: Yes), the running data is determined to be a jog 51. If it is not slower (Step S67b: No), the process proceeds to step S67c. Note that in the processing of step S67b, "(Moderate + easy) / 2" is the threshold value of the median speed of the running data used by the determination unit 30. However, this threshold is not limited to "(Moderate + easy) / 2". It may be a threshold value expressed based on the intensity of other running abilities, a threshold value expressed using an index different from the intensity of running abilities, or a threshold value expressed using a specific numerical value. This threshold can be changed as appropriate.

[0085] Furthermore, although the median speed of the driving data is used in the processing of the determination unit 30, it is not limited to this, and the average value of the driving data, or the top predetermined percentage of the driving data, may also be used.

[0086] Step S67c: Is the median speed of the running data processed by the calculation unit 20 slower than Moderate? The determination unit 30 determines whether the median speed of the running data is slower than Moderate. If it is slower (Step S67c: Yes), the running data is determined to be a comfortable run 52. If it is not slower (Step S67c: No), the process proceeds to step S67d. Note that in the processing of step S67c, "Moderate" is the threshold value of the median speed of the running data used by the determination unit 30. However, this threshold is not limited to "Moderate". It may be a threshold expressed based on the intensity of other running abilities, a threshold expressed using an index different from the intensity of running abilities, or a threshold expressed using a specific numerical value. This threshold can be changed as appropriate.

[0087] Step S67d: Is the median speed of the running data processed by the calculation unit 20 slower than Active? The determination unit 30 determines whether the median speed of the running data is slower than Active. If it is slower (Step S67d: Yes), the running data is determined to be a pace run 53. If it is not slower (Step S67d: No), the process proceeds to step S67e. In the processing of step S67d, "Active" is the threshold value of the median speed of the running data used by the determination unit 30. However, this threshold is not limited to "Active". It may be a threshold value expressed based on the intensity of other running abilities, a threshold value expressed using an index different from the intensity of running abilities, or a threshold value expressed using a specific numerical value. This threshold can be changed as appropriate.

[0088] Step S67e: Is the median speed of the running data processed by the calculation unit 20 slower than (Hard + Internal) / 2? The determination unit 30 determines whether the median speed of the running data is slower than (Hard + Internal) / 2. If it is slower (Step S67e: Yes), the running data is determined to be a fast-paced run 54. If it is not slower (Step S67e: No), the running data is determined to be a sprint 55. In the processing of step S67e, "Hard + Internal" is the threshold value of the median speed of the running data used by the determination unit 30. However, this threshold is not limited to "Hard + Internal". It may be a threshold value expressed based on the intensity of other running abilities, a threshold value expressed using an index different from the intensity of running abilities, or a threshold value expressed using a specific numerical value. This threshold can be changed as appropriate.

[0089] Referring to Figure 23, the graph shape and running data of an even-pace run will be explained. An even-pace run is characterized by running at a generally constant pace, although small pace changes are observed but no regularity is found. The running data is basically flat, but if the pace trend is irregular, the judgment unit 30 obtains the median pace for running data that is not judged as interval running 57 or build-up running 56 and makes a judgment. Graphs (a) and (b) in Figure 23 illustrate speed-distance graphs that are judged as even-pace runs.

[0090] (Regarding the output unit 40) The output unit 40 outputs the type of driving training. That is, the output unit 40 outputs the type of driving training determined by the determination unit 30 to the user terminal 160 or the like, informing the user of the determination result.

[0091] Referring to Figures 24 and 25, an example of the display screen of the user terminal 160 will be described. Figures 24 and 25 are diagrams illustrating an example of the display screen of the user terminal 160 according to this embodiment. The example of the user terminal 160 display shown in Figure 24(a) displays the training menu for each day. That is, the display screen of the user terminal 160 displays the date and time, distance traveled, average pace, and the type of training determined to be running training. Note that the display screen of the user terminal 160 shown in Figure 24(a) is merely an example, and the display content of the user terminal 160 display screen can be changed as appropriate, and may also be changed by the user.

[0092] The example display of the user terminal 160 shown in Figure 24(b) shows the practice status performed during the practice period set by the user, with the area of ​​each sector changing for each type of practice, in a pie chart. The area of ​​each sector is set according to the amount of practice performed during the practice period. The information processing device 100 may also display the types and amounts of practice recommended to the user based on the practice status, and may further add advice to the user. These recommended practices, amounts of practice, and advice may be generated automatically using AI or other means, or they may be provided by a staff member.

[0093] Referring to Figure 25(a), the case of presenting recommended ratios to the user terminal 160 will be explained. Recommended ratios refer to the amount of training for each type of running training expressed as a ratio. Displaying the user's current training volume ratios for each type of training alongside the recommended ratios can make it easier for the user to recognize what needs improvement. Also, since the optimal training menu differs depending on the training period, presenting recommended ratios allows users to understand what they are lacking by comparing themselves to the recommended ratios.

[0094] Referring to Figure 25(b), an example of displaying training content modification suggestions on the user terminal 160 will be explained. In the training content modification suggestions, the user's motivation to train may be improved by specifically indicating the types of training that are lacking. For example, it may be suggested to modify it to "interval running 1km x 3". An algorithm for training content modification suggestions may be constructed to automatically indicate the missing parts, and if it is not achieved, it may be programmed to make appropriate modifications and propose an adaptive training menu.

[0095] (Regarding the operation method of the information processing device and the information processing program) Next, with reference to Figure 26, the information processing program according to this embodiment of the information processing device 100 will be described together with the operation method of the information processing device 100. Figure 26 is an example of a flowchart of the information processing program according to this embodiment. The operation method of the information processing device 100 is executed by the processing unit 100e of the information processing device 100 based on the information processing program. The information processing program includes an acquisition step S10, a calculation step S20, a determination step S30, and an output step S40, etc. The information processing program enables the processing unit 100e of the information processing device 100 to perform acquisition, calculation, determination, and output functions, etc. These functions are executed in the order shown in the flowchart of Figure 26, but the order can be changed as appropriate. Note that each function overlaps with the description of the various functional units of the information processing device 100 described above, so a detailed explanation will be omitted.

[0096] The acquisition function acquires location information, including time information, received by a wearable device carried by a user performing running training (S10: acquisition step).

[0097] The calculation function calculates pace information related to the running training pace and distance information related to the running training distance based on location information (S20: calculation step).

[0098] The determination function determines the type of running training based on the graph shape of a speed-to-distance graph, which is composed of running data consisting of pace information and running distance information as a pair (S30: determination step).

[0099] The output function outputs the type of running training (S40: output step).

[0100] According to the embodiment described above, the type of running training can be determined based on the graph shape of the speed-to-distance graph based on running data, so that the running training performed by the trainee can be classified into detailed training menus. Detailed training menus include, for example, jogging 51, comfortable running 52, pace running 53, fast pace running 54, sprinting 55, build-up running 56, interval running 57, and even-pace running.

[0101] Furthermore, according to the above-described embodiment, the determination result of determining the type of driving training can be presented to the user terminal 160, which can contribute to maintaining and improving the user's motivation and enthusiasm for driving training.

[0102] Furthermore, according to the above-described embodiment, the type of running training can be determined to be interval training based on the amplitude spectrum obtained by extracting frequency components contained in the running data and associating the amplitude with the frequency. The extraction of frequency components contained in the running data can be done relatively easily using the Fourier transform.

[0103] Furthermore, according to the above-described embodiment, even if there are no peak values ​​(extreme values) exceeding a threshold in the amplitude spectrum graph obtained by extracting frequency components contained in the running data, if there are two or more peak values ​​(extreme values) in the speed-distance graph, and at least one of the extreme values ​​of the amplitude spectrum obtained by extracting frequency components contained in the running data for the section where the length of the absolute time calculated for each interval between two adjacent peak values ​​(extreme values) remains below the threshold exceeds the threshold, then the type of running training can be determined to be interval training.

[0104] Furthermore, according to the embodiment described above, even if there are no peak values ​​(extreme values) exceeding a threshold in the amplitude spectrum graph obtained by extracting frequency components contained in the running data, and there are other sections with the same "length of remaining below the threshold," making it impossible to select the running data for the section with the maximum value, it is possible to assume that the section with the maximum value of pace variance for each section is the "interval running section," and to determine whether or not it is an interval run based only on this section.

[0105] Furthermore, according to the above-described embodiment, if the graph shape of the speed-distance graph is step-like, and the median pace value corresponding to each step of the step-like graph progressively increases with increasing distance, the type of running training can be determined to be a build-up run.

[0106] Furthermore, according to the above-described embodiment, if the shape of the speed-to-distance graph is not waveform or step-like, the type of running training can be determined to be an even-pace run.

[0107] Furthermore, according to the above-described embodiment, the type of running training determined to be an even-pace run can be further subdivided based on the pace during the run.

[0108] Furthermore, according to the above-described embodiment, the type of running training determined to be an even-paced run can be further subdivided based on the user's running ability.

[0109] Furthermore, according to the above-described embodiment, by acquiring location information including time information obtained by receiving GNSS signals, the type of driving training can be determined without using other data.

[0110] Furthermore, according to the above-described embodiment, the judgment result of the information processing device 100 can be displayed on the user terminal 160, so the user can easily find out the judgment result of their driving training.

[0111] This disclosure is not limited to the information processing apparatus 100, the method of operating the information processing apparatus 100, and the information processing program according to the above-described embodiment. It can be implemented in various other modifications or applications without departing from the gist of this disclosure as described in the claims. Furthermore, although the term "data" is used in the above-described embodiment, the term "data" can be replaced with "information," and the term "information" can be replaced with "data."

[0112] (Regarding the second embodiment) Next, an information processing device 110 according to the second embodiment of this disclosure will be described with reference to Figures 27 to 30. Figure 27 is a diagram for illustrating the overview of the processing of the information processing device 110 according to the second embodiment, Figure 28 is a graph visualizing the training load (TRIMP), training fatigue (Fatigue Score), and performance score (Performance Score) of the information processing device 110 according to the second embodiment, where (a) is a graph of training load (TRIMP) and training fatigue (Fatigue Score), and (b) is a graph visualizing the performance score (Performance Score), Figure 29 is a diagram for illustrating an example of the functional configuration of the information processing device 110 according to the second embodiment, and Figure 30 is an example of a flowchart of the information processing program according to the second embodiment.

[0113] In describing the information processing device 110, the operation method of the information processing device 110, and the information processing program according to the second embodiment, the descriptions in the description of the information processing device 100, the operation method of the information processing device 100, and the information processing program according to the above-described embodiment will be incorporated into the description of the information processing device 110, the operation method of the information processing device 110, and the information processing program according to the second embodiment. Accordingly, in the drawings according to the second embodiment, the same reference numerals as those used in the information processing device 100, the operation method of the information processing device 100, and the information processing program according to the above-described embodiment will be used for parts that are identical to those used in the information processing device 100, the operation method of the information processing device 100, and the information processing program according to the above-described embodiment, and their description will be omitted.

[0114] The information processing device 110 according to the second embodiment is a so-called computer, and may be, for example, a workstation, server, personal computer (hereinafter referred to as PC), notebook PC, tablet PC, or smartphone. The hardware configuration of the information processing device 110 is the same as the hardware of the information processing device 100 shown in Figure 1, and includes a communication unit 100a, ROM 100b, RAM 100c, storage unit 100d, processing unit 100e, and input / output interface 100f. Furthermore, the information processing device 110 includes an input device 100g and an output device 100h as external devices that perform data input and output via the input / output interface 100f.

[0115] (Outline of the processing content of the information processing device 110 according to the second embodiment) An outline of the processing content of the information processing device 110 according to the second embodiment will be described with reference to Figures 27 and 28. The outline of the processing content of the information processing device 110 according to the second embodiment is shown in steps 1 (111) to 4 (114) as shown in Figure 27.

[0116] Step 1 (111) The acquisition unit 10 acquires location information including time information received by the wearable terminal 101, and the calculation unit 20 calculates pace information related to the pace of the running training and distance information related to the distance run during the running training based on this location information (see Figure 29). The information processing device 110 acquires time information, location information, pace information, and distance run information for each running training session performed by the user wearing the wearable terminal 101 through the wearable terminal 101. The information processing device 110 may further record the user's personal best using this information. Step 1 (111) is the same as the acquisition unit 10 and calculation unit 20 of the information processing device 100 according to the above embodiment, the acquisition step S10 and calculation step S20 of the operation method of the information processing device 100, and the processing content performed by the acquisition function and calculation function of the information processing program.

[0117] Step 2 (112) The determination unit 30 determines the type of driving training (see Figure 29). The information processing device 110 determines the type of driving training based on the information acquired in Step 1 (111). Step 2 (112) is the same as the processing content performed by the determination unit 30 of the information processing device 100 according to the above embodiment, the determination step S30 of the operation method of the information processing device 100, and the determination function of the information processing program.

[0118] Step 3 (113) The training load calculation unit 123 calculates the training load (TRIMP) based on the information obtained in Step 1 (111) and the type of running training determined in Step 2 (112). Furthermore, the training fatigue calculation unit 125 calculates the training fatigue score based on the training load (TRIMP), and the performance score calculation unit 126 calculates the performance score based on the training load (TRIMP) (see Figure 29). In Step 3 (113), the training effectiveness value calculation unit 124 further calculates the training effectiveness value (Fitness Score) (see Figure 29).

[0119] Step 4 (114) The output unit 40 visualizes the training load (TRIMP), training fatigue score, and performance score (see Figure 29). The information processing device 110 displays the total daily training load (TRIMP) 115 as a bar graph, as shown in graph (a) in Figure 28, and the daily training fatigue score (Fatigue Score) as a curve graph. Furthermore, the information processing device 110 displays the daily performance score 117 as a curve graph, as shown in graph (b) in Figure 28. In this embodiment, the training load (TRIMP), training fatigue score (Fatigue Score), training effectiveness score (Fitness Score), and performance score (Performance Score) are graphed using daily values ​​with a daily unit of time. However, the unit of time is not limited to daily, and may be, for example, every two days, every week, every month, every year, or every half-day divided into morning and afternoon. The user can adjust the timing of rest and the intensity of training in preparation for the actual competition by viewing the trends of the training load (TRIMP), training fatigue score (Fatigue Score), and performance score (Performance Score) visualized as graphs by the information processing device 110.

[0120] As described above, the processing content of the information processing device 110 according to the second embodiment differs from the processing content of the information processing device 100 according to the above embodiment in that steps 3 (113) and 4 (114) are added. In the following description of the information processing device 110 according to the second embodiment, the differences from the information processing device 100 according to the above embodiment will be explained, and for the same points, the reference numerals used in the description of the information processing device 100 according to the above embodiment will be used, and the description of the information processing device 100 according to the above embodiment will be referenced.

[0121] (About Training Load (TRIMP)) Training load (TRIMP) is an abbreviation for Training Impulse, and it is an index that quantifies the load of running training by combining the duration of running training (described below) and the load intensity coefficient (Intensity) (described below), and measures the load of running training as a whole. TRIMP, proposed by Eric Banister, is expressed by the following formula (1) and is described by a function that includes the rate of increase in heart rate (ΔHR rate). Banister's TRIMP = D × ΔHR rate × Y1 ... Formula (1) where, D: Duration of running training. ΔHR rate: Rate of increase in heart rate, expressed as (exercise heart rate - resting heart rate) / (maximum heart rate - resting heart rate). Y1: Intensity weighting coefficient, expressed as exp(b × ΔHR rate). Where, for men: b = 1.92, for women: b = 1.67. exp is a mathematical symbol and represents the exponential function. The information processing device 110 according to the second embodiment eliminates the need to measure the user's heart rate by using the load intensity coefficient (described later), which is set for each type of running training, instead of the heart rate increase rate, making it easier for the user to use.

[0122] The training load (TRIMP) used by the information processing device 110 according to the second embodiment is expressed by the following formula (2), using the load intensity coefficient (Intensity) instead of the heart rate increase rate (ΔHR rate). TRIMP = D × Intensity × Y ... Formula (2) where, D: Duration of running training. Intensity: Load intensity coefficient, a coefficient that indicates the intensity (difficulty) set in advance for each type of running training. Note that the load intensity coefficient may be used after correction as described below. Y: Intensity weighting coefficient, expressed as exp(b × Intensity), which refers to the gender coefficient described below. However, male: b = 1.92, female: b = 1.67.

[0123] (Regarding the Load Intensity Coefficient) The Load Intensity Coefficient is a coefficient that represents the intensity (difficulty) predetermined for each type of running training. It is set for each type of running training determined by the judgment unit 30 described above, and is a coefficient that is uniquely identified when the type of running training is identified.

[0124] The load intensity coefficient is fine-tuned (corrected) from a preset value, taking into account the pace and distance of the running training. Even for the same type of running training, the pace and distance vary each time, so the relative intensity will differ slightly. The load intensity coefficient is corrected by considering the pace factor, which is the factor of the running training, and the distance factor, which is the factor of the running training. The distance factor is determined based on the following formula (3), using distance criteria (Table 1 below) set according to the user's running ability. Note that SUB indicates the attribute (category) of the runner's running ability; for example, SUB4 indicates a runner who has the ability to complete a full marathon in under 4 hours.

[0125]

[0126] Distance factor = 1 + (distance factor a - distance factor b) × 0.015 ... (3) However, 0.015 is a hyperparameter and is a value that is manually adjusted according to each user's running ability. Therefore, 0.015 is an example value and is a value that can be changed. Distance factor a: Actual running distance Distance factor b: Distance standard derived from Table 1 For example, if a male runner with SUB4 runs a comfortable distance of 5 km in 30 minutes (i.e., a pace of 6 minutes per km), distance factor a will be 5 and distance factor b will be b ３２ Therefore, the distance factor is expressed by the following equation (4): Distance factor = 1 + (5 - b ３２ ) × 0.015 ... (4)

[0127] Next, pace factors are determined based on the following formula (5), using a basic pace (Table 2 below) for each type of running training. Table 2 is provided for each attribute of running ability, and Table 2 below shows the basic pace for someone with a full marathon time of approximately 4:00:00 (4 hours).

[0128]

[0129] Pace factor = pace b / pace a ... (5) where, pace a: actual average running pace [sec / km] pace b: basic pace derived from Table 2 [sec / km] For example, if a male runner with a SUB4 bike runs a comfortable distance of 5km in 30 minutes (i.e., a pace of 6 minutes per km), pace a will be 6:00 and pace b will be 5:38. Therefore, the pace factor will be 0.939 according to the following formula (6). Pace factor = 5:38 / 6:00 = 338 / 360 ≈ 0.939 ... (6)

[0130] The load intensity coefficient (Intensity) is corrected using the distance factor, which is the result of calculation in equation (4), and the pace factor (0.939), which is the result of calculation in equation (6). The corrected load intensity coefficient (Intensity) is calculated by the following equation (7). Corrected load intensity coefficient (Intensity) = Load intensity coefficient b × Distance factor × Pace factor ... (7) However, Load intensity coefficient b: This is the load intensity coefficient (Intensity) before correction, and as mentioned above, it is a coefficient that represents the intensity (difficulty) that is set in advance for each type of running training. For example, the load intensity coefficient b for a comfortable run is 0.75. For example, if a male runner with SUB4 performs a comfortable run of 5 km in 30 minutes (i.e., at a pace of 6 minutes per km), the corrected load intensity coefficient (Intensity) will be 0.652 according to the following equation (8). Corrected load intensity coefficient = 0.75 × 0.985 × 0.939 ≈ 0.652 ... (8) Note that 0.985 is the value of b in the above equation (4). ３２ This is the value obtained by substituting 6 into the formula. ３２ This indicates the standard distance for a comfortable run for a runner with running ability SUB4 (see Table 1), and in this embodiment, it is assumed to be 6.

[0131] If the calculation result of equation (8) (0.652) is lower than the load intensity coefficient b of jogging, which is one level lower in intensity than a comfortable run (in this embodiment, it is assumed to be pre-set to 0.70), then the load intensity coefficient b of the running training one level lower in intensity is used as the corrected load intensity coefficient (Intensity). Therefore, the corrected load intensity coefficient (Intensity) becomes 0.70.

[0132] (Gender Coefficient) The gender coefficient is a coefficient determined based on the user's gender and load intensity coefficient, and corresponds to the intensity weighting coefficient (Y) in equation (2), and is expressed by the following equation (9): Y = exp(b × Intensity) ... (9) where exp: exponential function Male: b = 1.92, Female: b = 1.67 Intensity: corrected load intensity coefficient

[0133] (Fitness Score) The fitness score is a value that indicates the effect of training that a user gains each time they do running training. Each time a running training session is performed, one training load (TRIMP) is accumulated in the user as potential ability, and this value gradually decreases as time passes without running training. The fitness score g(t) is expressed by the following formula (10). exp is a mathematical symbol and represents an exponential function. The fitness score g(t) shows the fitness score obtained from one day of training performed on the current training day, and g(t-1) shows the fitness score obtained from one day of training performed on the previous training day.

[0134]

[0135] However, t: day g(t): training effectiveness value of running training at the end of the current training day g(t-1): training effectiveness value of running training at the end of the previous training day interval: number of days from the previous training day to the current training day τ １ : This is the decay time constant related to the practice effect value, indicating the number of days it takes for the practice effect value to return to approximately 37% of the original value. exp(-interval / τ) １): This corresponds to the gradually decreasing effect value described below. TRIMP: This indicates the total training load of the running training performed on one day of this training. The initial value of the training effect value may be set to zero, or it may be set based on the user's running ability at the start of the running training. For example, the initial value of the training effect value may be set to 1000 if the user is SUB3, 800 if the user is SUB3.5, 600 if the user is SUB4, and 400 in all other cases. The correspondence between the user's running ability and the initial value of the training effect value can be statistically derived from the relationship between the initial data at the start of the running training and the results of the actual race.

[0136] (Training Fatigue Score) The training fatigue score is the fatigue a user experiences each time they perform a running training session. Each time a running training session is performed, one training load (TRIMP) is accumulated as fatigue in the user, and this value gradually decreases as time passes without running training. The training fatigue score h(t) is expressed by the following formula (11). exp is a mathematical symbol representing the exponential function. The training fatigue score h(t) indicates the training fatigue incurred from one day of training performed on the current training day, and h(t-1) indicates the training fatigue incurred from one day of training performed on the previous training day.

[0137]

[0138] However, t: day, h(t): fatigue level of running training at the end of the current training day, h(t-1): fatigue level of running training at the end of the previous training day, interval: number of days from the previous training day to the current training day. τ ２ : This is the decay time constant related to training fatigue, representing the number of days it takes for training fatigue to return to approximately 37% of its original level. exp(-interval / τ) ２): It corresponds to the gradually decreasing fatigue level described later. TRIMP: It represents the total value of the training load of the running training conducted on one day of the current training day. Note that the initial value of the training fatigue level may be estimated from the running distance immediately before the start of the running training. For example, the initial value of the training fatigue level for a user who runs 50 km per week may be 200, and the initial value of the training fatigue level for a user who runs 25 km per week may be 100, etc. Furthermore, an initial value of the training fatigue level may be corrected by conducting a questionnaire that asks about the user's subjective feelings.

[0139] (Performance Score) The Performance Score refers to the potential performance ability that can be expected from the user's condition (state) at that time. That is, the Performance Score includes both the maximum ability that can be demonstrated in the actual race at that time and the maximum ability that can be demonstrated in daily running training, and is an index that indicates the overall performance that can be expected from the user's condition (state) regardless of the situation in which the user is placed. The Performance Score P(t) is expressed by the following formula (12). P(t) = k １ ·g(t) - k ２ ·h(t) ··· (12) However, P(t): The Performance Score for the current training day. k １ , k ２ : Hyperparameter. g(t): The training effect value obtained by the training conducted on one day of the current training day. h(t): The training fatigue level suffered by the training conducted on one day of the current training day. The Performance Score is calculated using two independent elements: the training effect value (g(t)) and the training fatigue level (h(t)). The Performance Score increases in proportion to the training effect value accumulated each time of practice, but decreases in proportion to the training fatigue level accumulated each time of practice. Therefore, the Performance Score is determined by subtracting the negative element of the accumulated training fatigue level from the accumulated training effect value.

[0140] (τ １ 、τ ２ 、k １ 、k２ (Method of adjustment) τ １ , τ ２ , k １ , k ２ It is adjusted to suit each user's running ability. １ , τ ２ , k １ , k ２ The adjustment method may involve selecting the value that best matches the user's perception from among several values ​​selected based on past experience or achievements, or it may involve determining the optimal value using a machine learning model. The method of determining the optimal value using a machine learning model may include, for example, good research or Bayesian optimization. Good research refers to τ １ , τ ２ , k １ , k ２ This method involves comprehensively searching for candidates and selecting the value that yields the best result. Bayesian optimization is a technique that quickly arrives at the optimal solution by repeatedly trying predictions and uncertainties, and it can reduce the computational load compared to good research.

[0141] (Functional Configuration of Information Processing Device 110 According to the Second Embodiment) An example of the functional configuration of the information processing device 110 will be described with reference to Figure 29. The information processing device 110 takes in the information processing program according to the second embodiment, which will be described later, stored in the storage unit 100d, into the main memory which is configured as RAM 100c or the like. The processing unit 100e accesses the main memory into which the information processing program according to the second embodiment has been taken in and executes the information processing program. By executing the information processing program according to the second embodiment, the information processing device 110 provides the processing unit 100e with functional units such as an acquisition unit 10, a calculation unit 20, a determination unit 30, a duration timing unit 120, a load intensity coefficient acquisition unit 121, a gender coefficient calculation unit 122, a training load calculation unit 123, a training effect value calculation unit 124, a training fatigue level calculation unit 125, a performance score calculation unit 126, and an output unit 40.

[0142] The information processing device 110 according to the second embodiment further includes: a duration timing unit 120 that measures the duration of running training based on location information; a load intensity coefficient acquisition unit 121 that acquires a load intensity coefficient (Intensity) that is set in advance according to the load intensity for each type of running training; and a training load calculation unit 123 that calculates a training load (TRIMP) indicating the load imposed on the user for each running training based on the duration and the load intensity coefficient (Intensity).

[0143] The information processing device 110 according to the second embodiment further includes a training effectiveness value calculation unit 124 that calculates the training effectiveness value (Fitness Score) of running training at the end of the current training day, based on a gradually decreasing effect value that takes into account the decay of the training effectiveness value (Fitness Score) at the end of the previous training day of running training, which is affected by the number of days elapsed from the previous training day to the current training day, and the total value of the training load (TRIMP) of the running training performed on the current training day.

[0144] The information processing device 110 according to the second embodiment further includes a training fatigue calculation unit 125 that calculates the training fatigue score for running training at the end of the current training day, based on the training fatigue score that indicates the degree of fatigue of running training, taking into account the decay of the training fatigue score at the end of the previous training day of running training, which is affected by the number of days elapsed from the previous training day to the current training day, and the sum of the training load (TRIMP) of the running training performed on the current training day.

[0145] The information processing device 110 according to the second embodiment further includes a performance score calculation unit 126 that calculates a performance score indicating the ability that the user can demonstrate, based on a fitness score indicating the training effect of running training and a fatigue score indicating the level of fatigue from running training.

[0146] The information processing device 110 according to the second embodiment further includes a gender coefficient calculation unit 122 that calculates a gender coefficient based on the user's gender and load intensity coefficient, and a training load calculation unit 123 that calculates the training load (TRIMP) for each running training based on the duration, load intensity coefficient (Intensity), and gender coefficient.

[0147] (Duration timing unit 120) The duration timing unit 120 measures the duration of the running training based on location information. The duration timing unit 120 measures the duration of the running training based on time information included in the location information received by the wearable terminal 101 carried by the user performing the running training.

[0148] (Load Intensity Coefficient Acquisition Unit 121) The Load Intensity Coefficient Acquisition Unit 121 acquires a load intensity coefficient (Intensity) that is set in advance according to the load intensity for each type of running training. The Load Intensity Coefficient Acquisition Unit 121 may also accept input of the load intensity coefficient from the user. The Load Intensity Coefficient Acquisition Unit 121 may acquire the load intensity coefficient for each type of running training in a table. The Load Intensity Coefficient Acquisition Unit 121 may correct the load intensity coefficient as described above, taking into account the pace and distance of the running training, and may also correct the load intensity coefficient based on the pace information and distance information calculated by the calculation unit 20.

[0149] (Gender Coefficient Calculation Unit 122) The gender coefficient calculation unit 122 calculates a gender coefficient based on the user's gender and load intensity coefficient. The gender coefficient calculation unit 122 calculates a gender coefficient using the above formula (9) based on the user's gender and the load intensity coefficient which is uniquely identified by the type of running training determined by the determination unit 30.

[0150] (Training load calculation unit 123) The training load calculation unit 123 calculates the training load (TRIMP) that indicates the load on the user for each running training session, based on the duration and load intensity coefficient. The training load calculation unit 123 calculates the training load that indicates the load on the user for each running training session, based on the duration of the running training session measured by the duration timing unit 120 and the load intensity coefficient (Intensity) obtained by the load intensity coefficient acquisition unit 121. The training load calculation unit 123 may also calculate the training load that indicates the load on the user for each running training session by multiplying the duration and load intensity coefficient and obtaining the resulting product.

[0151] The training load calculation unit 123 may also calculate the training load for each running training session based on the duration, load intensity coefficient, and gender coefficient. The training load calculation unit 123 may also calculate the training load for each running training session based on the duration of the running training session measured by the duration timing unit 120, the load intensity coefficient (Intensity) obtained by the load intensity coefficient acquisition unit 121, and the gender coefficient determined by the gender coefficient calculation unit 122. The training load calculation unit 123 may also calculate the training load for each running training session as the product obtained by multiplying the duration, load intensity coefficient, and gender coefficient. The training load calculation unit 123 may also calculate the training load for each running training session using the above formula (2).

[0152] (Training Effect Value Calculation Unit 124) The training effect value calculation unit 124 calculates the training effect value of running training at the end of the current training day based on the training effect value indicating the training effect of running training, which takes into account the decay of the training effect value at the end of the previous training day of running training, which is affected by the number of days elapsed from the previous training day to the current training day, and the total training load of the running training performed on the current training day. The training effect value calculation unit 124 may also calculate the training effect value (g(t)) of running training at the end of the current training day using the above formula (10). That is, the training effect value calculation unit 124 calculates the training effect value indicating the training effect of running training, which takes into account the decay of the training effect value (g(t-1)) at the end of the previous training day of running training, which is affected by the number of days elapsed from the previous training day to the current training day (exp(-interval / τ)). １ Based on the total training load (TRIMP) of the running training performed on this training day, the training effect value (g(t)) of the running training at the end of this training day is calculated.

[0153] (Training fatigue calculation unit 125) The training fatigue calculation unit 125 calculates the training fatigue level of running training at the end of the current training day based on the training fatigue level indicating the fatigue level of running training, which takes into account the decay of the training fatigue level at the end of the previous training day of running training, which is determined by the number of days elapsed from the previous training day to the current training day, and the total value of the training load of running training performed on the current training day. The training fatigue calculation unit 125 may also calculate the training fatigue level (h(t)) of running training at the end of the current training day using the above formula (11). That is, the training fatigue calculation unit 125 calculates the training fatigue level indicating the fatigue level of running training, which takes into account the decay of the training fatigue level (h(t-1)) at the end of the previous training day of running training, which is determined by the number of days elapsed from the previous training day to the current training day (exp(-interval / τ) ２ Based on the total training load (TRIMP) of the running training performed on this training day, the training fatigue level (h(t)) of the running training at the end of this training day is calculated.

[0154] (Performance Score Calculation Unit 126) The performance score calculation unit 126 calculates a performance score that indicates the ability the user can demonstrate based on the training effect value that indicates the training effect of the running training and the training fatigue level that indicates the fatigue level of the running training. The performance score calculation unit 126 calculates a performance score that indicates the ability the user can demonstrate based on the training effect value calculated by the training effect value calculation unit 124 and the training fatigue level calculated by the training fatigue level calculation unit 125. The performance score calculation unit 126 may also calculate a performance score that indicates the ability the user can demonstrate using the above formula (12). That is, the performance score calculation unit 126 takes the training effect value (g(t)) of the running training on the current training day and the first hyperparameter (k １ From the first product obtained by multiplying by ), the training fatigue level (h(t)) of the running training on this practice day is multiplied by the second hyperparameter (k ２ The second product obtained by multiplying by ) is subtracted to calculate the performance score (P(t)) for this practice day.

[0155] (Regarding the output unit 40) The output unit 40 outputs and presents to the user the values ​​of the training load calculated by the training load calculation unit 123, the training effect value calculated by the training effect value calculation unit 124, the training fatigue level calculated by the training fatigue level calculation unit 125, and the performance score calculated by the performance score calculation unit 126. The output unit 40 may output to a monitor, printer, etc. connected as an output device 100h, or it may output to a user terminal 160, or it may output to another information processing device (not shown) connected to the information communication network 150. The output unit 40 may output the training load calculated by the training load calculation unit 123, the training effect value calculated by the training effect value calculation unit 124, the training fatigue level calculated by the training fatigue level calculation unit 125, and the performance score calculated by the performance score calculation unit 126 as a graph with the respective values ​​set on the vertical axis and time on the horizontal axis. The unit of the vertical axis may be the unit of each value, and the unit of the horizontal axis may be days. Furthermore, the type of graph is not particularly limited and may include bar graphs, line graphs, curve graphs, etc. The output unit 40 may output the graphed training load, training effectiveness value, training fatigue level, and performance score to the user terminal 160. The user terminal 160 displays the acquired training load, training effectiveness value, training fatigue level, and performance score graphs on its monitor, and the user can view these graphs displayed on the monitor of the user terminal 160.

[0156] The output unit 40 outputs a bar graph, as shown in graph (a) in Figure 28, which represents the total daily training load 115 calculated by the training load calculation unit 123 for each running training session, with the height of the bars set for each day.

[0157] Furthermore, the output unit 40 outputs a curve graph (not shown) with the training effect value (g(t)) of the running training at the end of the training day, calculated by the training effect value calculation unit 124, as the vertical axis and time as the horizontal axis.

[0158] Furthermore, the output unit 40 outputs a curve graph with the training fatigue level 116 calculated by the training fatigue level calculation unit 125 at the end of the training day as the vertical axis, and time as the horizontal axis, as shown in graph (a) in Figure 28.

[0159] Furthermore, the output unit 40 outputs a curve graph with the performance score 117, which represents the ability that the user can demonstrate and is calculated by the performance score calculation unit 126, on the vertical axis and time on the horizontal axis, as shown in graph (b) in Figure 28.

[0160] Furthermore, the output unit 40 may also display a bar graph representing the total daily training load of 115 using bars set for each day, and a curve graph with the training effect value (g(t)) on the vertical axis and time on the horizontal axis, superimposed as a single graph (not shown).

[0161] Furthermore, the output unit 40 may also display a bar graph that shows the total daily training load 115 using bars set for each day, and a curve graph with training fatigue level 116 on the vertical axis and time on the horizontal axis, superimposed to form a single graph (see graph (a) in Figure 28).

[0162] Furthermore, the output unit 40 may also display a bar graph representing the total daily training load 115 using bars set for each day, a curve graph with training effectiveness value (g(t)) on the vertical axis and time on the horizontal axis, and a curve graph with training fatigue level 116 on the vertical axis and time on the horizontal axis, superimposed as a single graph (not shown).

[0163] Furthermore, the output unit 40 may also display a bar graph representing the total daily training load 115 using bars set for each day, a curve graph with training effectiveness value (g(t)) on the vertical axis and time on the horizontal axis, a curve graph with training fatigue level 116 on the vertical axis and time on the horizontal axis, and a curve graph with performance score 117, which indicates the ability the user can demonstrate, on the vertical axis and time on the horizontal axis, superimposed as a single graph (not shown).

[0164] (Regarding the operation method of the information processing device 110 and the information processing program according to the second embodiment) Next, with reference to Figure 30, the information processing program according to the second embodiment of this disclosure will be described together with the operation method of the information processing device 110. Figure 30 is an example of a flowchart of the information processing program according to the second embodiment. The operation method of the information processing device 110 is executed by the processing unit 100e of the information processing device 110 based on the information processing program.

[0165] The information processing program according to the second embodiment shown in Figure 30 is another embodiment of the information processing program shown in Figure 26, and differs from the information processing program shown in Figure 26 in that it includes the addition of a duration timing step S120, a load intensity coefficient acquisition step S121, a gender coefficient calculation step S122, a training load calculation step S123, a training effect value calculation step S124, a training fatigue level calculation step S125, and a performance score calculation step S126.

[0166] The information processing program according to the second embodiment includes an acquisition step S10, a calculation step S20, a determination step S30, a duration timing step S120, a load intensity coefficient acquisition step S121, a gender coefficient calculation step S122, a training load calculation step S123, a training effectiveness value calculation step S124, a training fatigue level calculation step S125, a performance score calculation step S126, and an output step S40. The information processing program according to the second embodiment enables the processing unit 100e of the information processing device 110 to perform acquisition, calculation, determination, duration timing, load intensity coefficient acquisition, gender coefficient calculation, training load calculation, training effectiveness value calculation, training fatigue level calculation, performance score calculation, and output functions. These functions are executed in the order shown in the flowchart of Figure 30, but the order can be changed as appropriate. Note that each function overlaps with the description of the operation method of the information processing device 100 and the information processing program related to Figure 26 above, so the overlapping explanations are omitted. Furthermore, since each function overlaps with the descriptions of the various functional units of the information processing device 100 and the information processing device 110 mentioned above, detailed explanations will be omitted.

[0167] The duration timing function measures the duration of the running training based on location information (S120: duration timing step).

[0168] The load intensity coefficient acquisition function acquires a load intensity coefficient that is set in advance according to the load intensity for each type of running training (S121: Load Intensity Coefficient Acquisition Step).

[0169] The gender coefficient calculation function calculates a gender coefficient based on the user's gender and load intensity coefficient (S122: Gender coefficient calculation step).

[0170] The training load calculation function calculates the training load, which indicates the load on the user for each running training session, based on the duration and load intensity coefficient (S123: Training Load Calculation Step).

[0171] The training effectiveness value calculation function calculates the training effectiveness value for running training at the end of the current training day, based on the training effectiveness value that indicates the training effectiveness of running training, taking into account the decay effect value that takes into account the number of days elapsed from the previous training day to the current training day as a factor, and the total training load of the running training performed on the current training day (S124: Training Effectiveness Value Calculation Step).

[0172] The training fatigue calculation function calculates the training fatigue level for running training at the end of the current training day, based on the training fatigue level, which indicates the level of fatigue from running training, and the decreasing fatigue level, which takes into account the number of days elapsed from the previous training day to the current training day, and the total training load of the running training performed on the current training day (S125: Training fatigue calculation step).

[0173] The performance score calculation function calculates a performance score that indicates the user's potential ability based on the training effect value, which indicates the training effect of the running training, and the training fatigue level, which indicates the level of fatigue from the running training (S126: Performance score calculation step).

[0174] (Effects of the Information Processing Device 110 according to the Second Embodiment) According to the Information Processing Device 110 according to the Second Embodiment described above, the training load (TRIMP), training effectiveness value (Fitness Score), training fatigue level (Fatigue Score), and performance score (Performance Score) of the user's running training can be calculated based on information acquired through the wearable terminal 101 worn by the user, without using the user's heart rate data during running training. Therefore, the user does not have to feel the hassle of acquiring heart rate data.

[0175] Furthermore, according to the information processing device 110 of the second embodiment described above, when a user performs running training, they can obtain the training load (TRIMP), training effectiveness value (Fitness Score), training fatigue level (Fatigue Score), and performance score (Performance Score) of the running training by wearing the wearable terminal 101.

[0176] Furthermore, according to the information processing device 110 of the second embodiment described above, the information processing device 110 can output a graph in which the acquired running training values ​​(TRIMP), training effectiveness value (Fitness Score), training fatigue level (Fatigue Score), and performance score (Performance Score) are set on the vertical axis and time (days) is set on the horizontal axis. As a result, users can visually grasp the changes in these values, and furthermore, users can grasp the correlation between the changes in these values, and can predict the cause of any sudden changes in the trends of the training effectiveness value, training fatigue level, and performance score (for example, insufficient or excessive training load). Furthermore, according to the information processing device 110 of the second embodiment described above, the information processing device 110 can output the trends of the acquired running training values, training effectiveness value, training fatigue level, and performance score as graphs. Therefore, the user can predict the effective upper and lower limits of the daily training load for each runner and create a training plan, taking into account the correlation between the training load and the training effectiveness value, the correlation between the training load and training fatigue level, and the correlation between the training load and the performance score. In addition, the user can predict the effective upper and lower limits of the daily training load for each type of running training and create a training plan.

[0177] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can make adjustments for the actual race while looking at the progress of the performance score displayed in a graph.

[0178] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can aggregate the training load, training effectiveness value, training fatigue level, and performance score for each training day, and furthermore, based on the results of these aggregations, can create a training plan while predicting the training effectiveness value, training fatigue level, and performance score.

[0179] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can aggregate training load, training effectiveness value, training fatigue level, and performance score for each type of running training.

[0180] Furthermore, according to the information processing device 110 of the second embodiment described above, it is possible to aggregate training load, training effectiveness value, training fatigue level, and performance score for predetermined periods such as daily, weekly, monthly, or yearly.

[0181] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can calculate training load, training effectiveness value, training fatigue level, and performance score for each runner, and then aggregate and analyze this information for each runner.

[0182] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can classify the types of running training in detail (with high resolution), and calculate the training load, training effectiveness value, training fatigue level, and performance score for each classification, making it possible to create a training plan that matches the attributes of the runner, such as their running ability.

[0183] Furthermore, according to the information processing device 110 of the second embodiment described above, by using a gender coefficient, it is possible to calculate a training load, training effect value, training fatigue level, and performance score that take gender into consideration.

[0184] Furthermore, according to the information processing device 110 of the second embodiment described above, the load intensity coefficient can be corrected by taking into account the distance and pace of running training, so that a more accurate training load, training effect value, training fatigue level, and performance score can be calculated.

[0185] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can identify the type of running training that efficiently contributes to improving each runner's performance score by observing the trend of the performance score, and can create a training plan that incorporates the type of running training best suited to each runner.

[0186] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can identify types of running training that are not suitable for improving each runner's performance score by looking at the trend of the performance score, and can create a training plan by eliminating types of running training that are not suitable for each runner.

[0187] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can create a training plan so that the peak of the performance score coincides with the day of the actual race by observing the trend of the performance score.

[0188] Furthermore, according to the information processing device 110 of the second embodiment described above, the user can create a training plan that takes into account the runner's fatigue level by observing the changes in the training fatigue level.

[0189] Furthermore, this disclosure is not limited to the information processing devices 100 and 110, the operating methods of the information processing devices 100 and 110, and the information processing programs according to the embodiments described above. Various other modifications or applications are possible without departing from the gist of this disclosure as described in the claims. Also, although the word "data" is used in the embodiments described above, the word "data" can be replaced with "information," and the word "information" can be replaced with "data." Also, although the word "driving training" is used in the embodiments described above, the word "driving training" can be replaced with "practice," and the word "practice" can be replaced with "driving training."

[0190] Furthermore, the above-described functional units of the information processing devices 100 and 110 are merely examples of functional units of the information processing devices 100 and 110, and do not limit the functions that the information processing devices 100 and 110 may have. For example, the information processing devices 100 and 110 do not need to have all of the above-described functional units, and may have only some of them. Also, the information processing devices 100 and 110 may have other functions other than those described above. In addition, as described above, the above-described functional units of the information processing devices 100 and 110 have been described as being implemented by software. However, at least one or more of the above-described functional units may be implemented by hardware.

[0191] Furthermore, any of the above-mentioned functional units may be implemented by dividing one functional unit into multiple functional units. Alternatively, any two or more of the above-mentioned functional units may be combined into a single functional unit. Also, the above description represents the functions of the information processing devices 100 and 110 in terms of functional blocks, and does not indicate, for example, that each functional unit is composed of a separate program file or the like.

[0192] Furthermore, the information processing devices 100 and 110 may be devices implemented in a single enclosure, or they may be systems implemented from multiple devices connected via a network or the like. For example, some or all of the functions of the information processing devices 100 and 110 may be implemented by virtual devices such as cloud services provided by a cloud computing system. In other words, the information processing devices 100 and 110 may implement at least one of the above-mentioned functional units in other devices. Also, the information processing devices 100 and 110 may be general-purpose computers such as desktop PCs, or they may be dedicated devices with limited functions.

[0193] Those skilled in the art will understand that the embodiments described above are specific examples of the following embodiments. Those skilled in the art will understand that the components (functional parts, steps, functions, etc.) described in each of these embodiments can be combined with each other at will, as long as they do not conflict with other descriptions herein. In particular, each of the following embodiments may be adopted alone or in combination with the configurations of one or more other embodiments, and relationships in which multiple embodiments are combined with multiple other embodiments (corresponding to so-called multiple dependencies and multi-multi-dependencies) are also permitted. This paragraph describes the relationships between embodiments and does not limit the permissible scope of dependency forms of claims in each country, and if it is contrary to the practice of each country's jurisdiction, it shall be reinterpreted as a dependency form within the permissible scope of each country's jurisdiction. Furthermore, the expressions for apparatus, method, and program can be reinterpreted as corresponding concepts. Of the following embodiments, combinations of configurations that are technically incompatible are excluded. [1] The information processing device of the present disclosure is characterized by comprising: an acquisition unit that acquires location information including time information received by a wearable terminal carried by a user performing running training; a calculation unit that calculates pace information relating to the pace of the running training and running distance information relating to the running distance of the running training based on the location information; a determination unit that determines the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with the pace information and the running distance information as a pair; and an output unit that outputs the type of running training. [2] In the information processing device of [1] above, the determination unit may determine that the type of running training is running training in which anaerobic exercise with increased running speed and aerobic exercise with reduced running speed are performed alternately and periodically when the extreme value of the amplitude spectrum, which corresponds to the amplitude of the frequency obtained by extracting frequency components contained in the running data, exceeds a threshold at a frequency of a predetermined value or higher.[3] In the information processing device described in [2] above, the determination unit may determine that the type of running training is running training in which anaerobic exercise with increased running speed and aerobic exercise with reduced running speed are performed alternately and periodically, provided that there are two or more extreme values ​​in the speed-to-distance graph, and that none of the extreme values ​​in the amplitude spectrum obtained by extracting frequency components contained in the running data representing the speed-to-distance graph and corresponding the amplitude to the frequency do not exceed a threshold at frequencies above a predetermined value, and furthermore, if at least one of the extreme values ​​in the amplitude spectrum obtained by extracting frequency components contained in the running data in the section where the length of the absolute time calculated for each interval between two adjacent extreme values ​​of the speed-to-distance graphs remains below a threshold is the maximum, then the determination unit determines that the type of running training is running training in which anaerobic exercise with increased running speed and aerobic exercise with reduced running speed are performed alternately and periodically. [4] In the information processing device described in any one of the above paragraphs [2] to [3], the determination unit may determine that the type of running training is running training in which anaerobic exercise at an increased running speed and aerobic exercise at a reduced running speed are performed alternately and periodically when there are two or more extreme values ​​in the speed-distance graph, and when none of the extreme values ​​in the amplitude spectrum obtained by extracting frequency components contained in the running data showing the speed-distance graph and corresponding the amplitude to the frequency have exceeded a predetermined value, and further, when the length in which the absolute time calculated for each interval between the extreme values ​​of the speed-distance graphs remains below a threshold is the same and therefore it is not possible to select the maximum of 1 interval, and at least one of the extreme values ​​in the amplitude spectrum obtained by extracting frequency components contained in the running data of the interval in which the value of the pace variance for each interval of the same length is the maximum has exceeded a threshold, the determination unit may determine that the type of running training is running training in which anaerobic exercise at an increased running speed and aerobic exercise at a reduced running speed are performed alternately and periodically. [5] In the information processing device described in any one of the above paragraphs [1] to [4], the determination unit may determine that the type of running training is running training in which the running speed is increased in stages, if the graph shape of the speed versus distance graph is stepped, and the median value of the pace corresponding to each step that constitutes the stepped shape increases sequentially as the running distance increases.[6] In the information processing device described in any one of the above items [1] to [5], the determination unit may determine that the type of running training is running training in which the running speed is kept constant, if the graph shape of the speed-distance graph is not waveform or step-like. [7] In the information processing device described in any one of the above items [1] to [6], the calculation unit may calculate the user's running ability based on the running data, and the determination unit may determine further subdivided types of the running training determined to be running training in which the running speed is kept constant, based on the running ability. [8] In the information processing device described in any one of the above items [2] to [7], the running training in which anaerobic exercise with increased running speed and aerobic exercise with reduced running speed are alternately and periodically performed may be interval training. [9] In the information processing device described in [5], the running training in which the running speed is increased in stages may be build-up training.

[10] In the information processing device described in [6] above, the running training in which the running speed is kept constant may be an even-pace run.

[11] In the information processing device described in [7] above, the further subdivided types may be classified based on the pace during running.

[12] In the information processing device described in any one of the above items [1] to

[11] , the device may further include: a duration timing unit that measures the duration of the running training based on the position information; a load intensity coefficient acquisition unit that acquires a load intensity coefficient that is set in advance according to the load intensity of each type of running training; and a training load calculation unit that calculates a training load indicating the load on the user for each running training based on the duration and the load intensity coefficient.

[13] The information processing device described in

[12] above may further include a practice effect value calculation unit that calculates the practice effect value of the running training at the end of the current practice day based on a gradually decreasing effect value that takes into account the decay of the practice effect value at the end of the previous practice day of the running training due to the number of days elapsed from the previous practice day to the current practice day, and the total value of the practice load of the running training performed on the current practice day.

[14] The information processing device described in

[12] or

[13] above may further include a practice fatigue calculation unit that calculates the practice fatigue level of the running training at the end of the current practice day based on a gradually decreasing fatigue level that takes into account the decay of the practice fatigue value at the end of the previous practice day of the running training due to the number of days elapsed from the previous practice day to the current practice day, and the total value of the practice load of the running training performed on the current practice day.

[15] The information processing device described in any one of the above paragraphs

[12] to

[14] may further include a performance score calculation unit that calculates a performance score indicating the ability that the user can demonstrate, based on a practice effect value indicating the practice effect of the running training and a practice fatigue level indicating the degree of fatigue of the running training.

[16] The information processing device described in any one of the above paragraphs

[12] to

[15] may further include a gender coefficient calculation unit that calculates a gender coefficient determined based on the gender of the user and the load intensity coefficient, and the practice load calculation unit may calculate the practice load for each running training based on the duration, the load intensity coefficient, and the gender coefficient.

[17] The method for operating the information processing device of the present disclosure is a method for operating the information processing device, characterized in that the processor of the information processing device performs an acquisition step of acquiring location information including time information received by a wearable terminal carried by a user performing running training; a calculation step of calculating pace information relating to the pace of the running training and distance information relating to the distance of the running training based on the location information; a determination step of determining the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with the pace information and the distance information as a pair; and an output step of outputting the type of running training.

[18] The information processing program of the present disclosure is characterized in that the processor of the information processing device implements an acquisition function of acquiring location information including time information received by a wearable terminal carried by a user performing running training; a calculation function of calculating pace information relating to the pace of the running training and distance information relating to the distance of the running training based on the location information; a determination function of determining the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with the pace information and the distance information as a pair; and an output function of outputting the type of running training.

[0194] Table 7 Table 8 Table 10 Acquisition Unit 20 Calculation Unit 30 Judgment Unit 40 Output Unit 51 jog 52 comfortable run 53 pace run 54 fast pace run 55 sprint 56 build-up run 57 interval run 59 maximum value 73 interval run execution section 74 maximum value 75 predetermined frequency 76 threshold 77 area 78 maximum value 79 maximum value 80 maximum value 81 maximum value 82 graph line before smoothing 83 graph line after smoothing 84 maximum value 85 graph before taking moving median 86 graph after taking moving median 87 graph before low-pass filter application 88 graph after low-pass filter application 89 maximum value 90 maximum value 91 maximum value 100 Information Processing Device 100a Communication unit 100b ROM (Read Only Memory) 100c RAM (Random Access Memory) 100d Storage unit 100e Processing unit 100f Input / Output interface 100g Input device 100h Output device 101 Wearable terminal 110 Information processing device (second embodiment) 111 Step 1 112 Step 2 113 Step 3 114 Step 4 115 Daily total value of training load (TRIMP) 116 Training fatigue level 117 Performance score 120 Duration timing unit 121 Load intensity coefficient acquisition unit 122 Gender coefficient calculation unit 123 Training load calculation unit 124 Training effect value calculation unit 125 Training fatigue level calculation unit 126 Performance score calculation unit 150 Information communication network 160 User terminal

Claims

1. An information processing device comprising: an acquisition unit that acquires location information including time information received by a wearable terminal carried by a user performing running training; a calculation unit that calculates pace information and distance information based on the location information; a determination unit that determines the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with the pace information and the distance information as a pair; and an output unit that outputs the type of running training.

2. The information processing apparatus according to claim 1, characterized in that the determination unit determines that the type of running training is running training in which anaerobic exercise at an increased running speed and aerobic exercise at a reduced running speed are performed alternately and periodically, when the extreme value of the amplitude spectrum obtained by extracting frequency components contained in the running data and corresponding the amplitude to the frequency exceeds a threshold value at a frequency of a predetermined value or higher.

3. The information processing apparatus according to claim 2, characterized in that the determination unit determines that the type of running training is running training in which anaerobic exercise with increased running speed and aerobic exercise with reduced running speed are performed alternately and periodically, when there are two or more extreme values ​​in the speed-to-distance graph, and none of the extreme values ​​in the amplitude spectrum obtained by extracting frequency components contained in the running data representing the speed-to-distance graph and corresponding the amplitude to the frequency do not exceed a threshold at frequencies above a predetermined value, and further, when at least one of the extreme values ​​in the amplitude spectrum obtained by extracting frequency components contained in the running data in the section where the length of the absolute time calculated for each interval between two adjacent extreme values ​​of the speed-to-distance graph that remains below a threshold is the maximum, the type of running training is running training in which anaerobic exercise with increased running speed and aerobic exercise with reduced running speed are performed alternately and periodically.

4. The information processing device according to claim 2, characterized in that the determination unit determines that the type of running training is running training in which anaerobic exercise with increased running speed and aerobic exercise with reduced running speed are performed alternately and periodically when there are two or more extreme values ​​in the speed-to-distance graph, and when none of the extreme values ​​in the amplitude spectrum obtained by extracting frequency components contained in the running data representing the speed-to-distance graph and corresponding the amplitude to the frequency have exceeded a predetermined value, and further, when the length for which the absolute time calculated for each interval between the extreme values ​​of the speed-to-distance graphs remains below the threshold is the same and therefore it is not possible to select the maximum of 1 intervals, and at least one of the extreme values ​​in the amplitude spectrum obtained by extracting frequency components contained in the running data of the interval in which the value of the pace variance for each interval of the same length is maximized exceeds the threshold, the type of running training is running training in which anaerobic exercise with increased running speed and aerobic exercise with reduced running speed are performed alternately and periodically.

5. The information processing device according to claim 1, characterized in that the determination unit determines that the type of running training is running training in which the running speed is increased in stages, when the graph shape of the speed versus distance graph is stepwise, and the median value of the pace corresponding to each step constituting the stepwise shape increases sequentially as the running distance increases.

6. The information processing device according to claim 1, characterized in that the determination unit determines that the type of running training is running training in which the running speed is kept constant, when the graph shape of the speed-distance graph is not waveform or step-like.

7. The information processing apparatus according to claim 6, wherein the calculation unit calculates the user's running ability based on the running data, and the determination unit determines, based on the running ability, further subdivided types of the running training that has been determined to be running training in which the running speed is kept constant.

8. The information processing device according to claim 2, characterized in that the running training, which involves alternately and periodically performing anaerobic exercise at an increased running speed and aerobic exercise at a reduced running speed, is interval running.

9. The information processing device according to claim 5, characterized in that the running training, which involves gradually increasing the running speed, is a build-up run.

10. The information processing device according to claim 6, characterized in that the running training, in which the running speed is maintained at a constant rate, is an even-paced run.

11. The information processing device according to claim 7, characterized in that the further subdivided types are classified based on the pace during driving.

12. The information processing device according to claim 1, further comprising: a duration timing unit that measures the duration of the running training based on the position information; a load intensity coefficient acquisition unit that acquires a load intensity coefficient that is set in advance according to the load intensity for each type of running training; and a training load calculation unit that calculates a training load indicating the load applied to the user for each running training based on the duration and the load intensity coefficient.

13. The information processing device according to claim 12, further comprising a training effect value calculation unit that calculates the training effect value of the running training at the end of the current practice day, based on a gradually decreasing effect value that takes into account the decay of the training effect value at the end of the previous practice day of the running training, which is determined by the number of days elapsed from the previous practice day to the current practice day, and the total value of the training load of the running training performed on the current practice day.

14. The information processing device according to claim 12, further comprising a training fatigue calculation unit that calculates the training fatigue level of the running training at the end of the current training day, based on the training fatigue level indicating the fatigue level of the running training, which takes into account the decay of the training fatigue level at the end of the previous training day of the running training, taking into account the number of days elapsed from the previous training day to the current training day, and the total value of the training load of the running training performed on the current training day.

15. The information processing apparatus according to claim 12, further comprising a performance score calculation unit that calculates a performance score indicating the ability that the user can demonstrate, based on a practice effect value indicating the practice effect of the running training and a practice fatigue level indicating the degree of fatigue of the running training.

16. The information processing device according to claim 12, further comprising a gender coefficient calculation unit that calculates a gender coefficient based on the user's gender and the load intensity coefficient, wherein the training load calculation unit calculates the training load for each running training based on the duration, the load intensity coefficient, and the gender coefficient.

17. A method for operating an information processing device, characterized in that the processor of the information processing device performs: an acquisition step of acquiring location information including time information received by a wearable terminal carried by a user performing running training; a calculation step of calculating pace information relating to the pace of the running training and running distance information relating to the running distance of the running training based on the location information; a determination step of determining the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with the pace information and the running distance information as a pair; and an output step of outputting the type of running training.

18. An information processing program characterized in that the processor of an information processing device implements: an acquisition function that acquires location information including time information received by a wearable terminal carried by a user performing running training; a calculation function that calculates pace information and distance information based on the location information that determine the type of running training; a determination function that determines the type of running training based on the graph shape of a speed-to-distance graph based on running data configured with the pace information and the distance information as a pair; and an output function that outputs the type of running training.

Images