Running analysis system and running analysis method

Abstract

A running analysis system and a running analysis method that realize easy running analysis based on information related to running are provided. In the running analysis system, an information acquisition section acquires position information and motion information of a user who runs as a runner, which are measured by a prescribed measurement device for each passing point in running. A measurement value acquisition section acquires measurement values of a plurality of motion analysis indexes that indicate a running motion state of the user for each measurement interval of a prescribed unit, based on the position information and the motion information that continue in time series. A classification processing section classifies the measurement values for each kind of the motion analysis indexes by a prescribed classification method for distinguishing the measurement values of the plurality of measurement intervals in characteristics. A form determination section determines an output form of the classified measurement values based on comparison with a prescribed comparison object. An output section outputs at least information related to the classified measurement values based on the determined output form.

Description

Technical Field

[0001] This invention relates to a running analysis system. More particularly, it relates to a system and method for analyzing running results. Background Technology

[0002] In recent years, the number of runners has increased due to rising health awareness. Especially in recent years, the widespread availability of smartphones and watches with built-in GPS modules has made it easy for anyone to record their running activities (hereinafter referred to as a "running log"). The effective use of such running logs motivates people to continue running and make it a habit, thus driving the popularity of running.

[0003] As the running population increases, the number of participants in marathons and the number of races also increase. Runners can review their running results after the race by recording running logs. As a technology for displaying running data, running data display methods or sports support devices are known (for example, see Patent Document 1 and Patent Document 2).

[0004] [Existing Technical Documents]

[0005] [Patent Literature]

[0006] [Patent Document 1] Japanese Patent No. 7031234

[0007] [Patent Document 2] Japanese Patent No. 5984002 Summary of the Invention

[0008] [The problem the invention aims to solve]

[0009] However, even with existing technology, and despite obtaining various information related to running volume or running posture, such as running time or distance during a race, identifying which information to focus on in order to improve one's performance may not be easy. Therefore, for users who cannot fully utilize all available information, it is difficult to establish the motivation to review race results based on that information.

[0010] The present invention was made in view of this situation, and its object is to provide a technique for facilitating running analysis based on running-related information.

[0011] [Technical means to solve the problem]

[0012] To address the aforementioned problem, a running analysis system according to one embodiment of the present invention includes: an information acquisition unit that acquires the runner's position information and motion information measured by a predetermined measuring device for each point passed during running; a measurement value acquisition unit that, based on the position information and motion information continuously over a time series, acquires measurement values ​​of multiple motion analysis indicators representing the user's running motion state for each measurement interval of a predetermined unit; a classification processing unit that classifies each type of motion analysis indicator using a predetermined classification method for distinguishing the measurement values ​​of multiple measurement intervals by characteristics; a morphology determination unit that determines the output morphology of the classified measurement values ​​based on a comparison with a predetermined comparison object; and an output unit that can output at least information related to the classified measurement values ​​based on the determined output morphology.

[0013] Another embodiment of the present invention is a running analysis method. The method includes the following steps: acquiring the runner's position and motion information measured by a prescribed measuring device at each point of travel during running; acquiring measured values ​​of multiple motion analysis indicators representing the user's running motion state for each measurement interval within a prescribed unit, based on the continuous position and motion information over a time series; classifying each type of motion analysis indicator according to a prescribed classification method for distinguishing the measured values ​​of multiple measurement intervals by characteristics; determining the output format of the classified measured values ​​based on comparison with a prescribed comparison object; and outputting at least information related to the classified measured values ​​based on the determined output format.

[0014] [The effects of the invention]

[0015] This invention provides a technique for facilitating running analysis based on running-related information. Attached Figure Description

[0016] Figure 1 This is a diagram showing the structure of the running analysis system.

[0017] Figure 2 This is a functional block diagram representing the various structures of the running analysis system.

[0018] Figure 3 This is a flowchart illustrating the processing steps in the running analysis system.

[0019] Figure 4 This is a diagram illustrating an example of classifying index measurements using the first classification method.

[0020] Figure 5 (a) to Figure 5 (c) is a diagram showing the preparatory processing when classifying index measurements using the second classification method.

[0021] Figure 6 (a) and Figure 6 (b) is a graph showing the process of classifying the measured values ​​of the index using the second classification method.

[0022] Figure 7 It is a horizontal bar chart that represents the proportion of each action analysis indicator in the classification.

[0023] Figure 8 This means that according to another benchmark, in Figure 7 The horizontal bar chart is a graph that evaluates the state of the indicators measured by segmenting them.

[0024] Figure 9 (a) and Figure 9 (b) is a diagram showing an example of limiting the output object to the measured values ​​of the indicators detected as values ​​of interest and displaying them.

[0025] Figure 10 This is a graph representing an example of an action analysis index that shows the longest interval of a range that tends to persist as a significant difference.

[0026] Figure 11 This is an example of a screen displaying the results of a match.

[0027] Figure 12 This is an example of a screen displaying competition evaluations.

[0028] Figure 13 This is an example of a screen displaying detailed explanations related to the evaluation points.

[0029] [Explanation of Symbols]

[0030] 10: Users

[0031] 20: Measuring device

[0032] 30: Information Acquisition Department

[0033] 40: Measurement Acquisition Department

[0034] 50: Information Terminal

[0035] 60: Running Analysis Server

[0036] 70: Information Acquisition Department

[0037] 80: Measurement Acquisition Department

[0038] 85: Sorting and Processing Department

[0039] 90: Morphological Determining Department

[0040] 99: Output Department

[0041] 100: Running Analysis System Detailed Implementation

[0042] Hereinafter, the present invention will be described with reference to the accompanying drawings according to suitable embodiments. In the embodiments and modifications, the same or equivalent constituent elements are labeled with the same symbols, and repeated descriptions are appropriately omitted.

[0043] Figure 1 This describes the structure of the running analysis system 100. The running analysis system 100 includes a watch-type device 12 worn by a user 10 during a running activity, a waist-worn device 14, an information terminal device 16, and a running analysis server 60. The watch-type device 12, waist-worn device 14, and information terminal device 16 are collectively referred to as measuring devices 20. The watch-type device 12 is a sports watch or smartwatch capable of measuring location information or motion information. The waist-worn device 14 is a motion sensor worn near the user 10's waist that can measure location information or motion information. The information terminal device 16 is a portable information terminal such as a smartphone that can measure location information or motion information while held in the user 10's pocket or similar container. The user 10 wears one or more measuring devices 20 and performs running during a competition or similar activity to obtain location information or motion information. When multiple measuring devices 20 are worn on the body, the devices used can be distinguished based on information obtained by using the watch-type device 12 to obtain position information and the waist-wearing device 14 to obtain motion information.

[0044] Furthermore, the measuring device 20 is not limited to devices such as the watch-type device 12, the waist-worn device 14, or the information terminal-type device 16; it can also be a device worn on or inside the runner's shoes. Alternatively, it can be a belt-type device that wraps around the runner's chest, wrists, waist, or arms to acquire positional or motion information. Moreover, various wearable devices such as smart glasses are considered as the measuring device 20. Additionally, cameras can be placed near each point along the running route to photograph the runner, and image recognition can be used to acquire skeletal information such as joint positions, or motion information such as cadence or stride length calculated from this information. Alternatively, instead of placing cameras near each point, a drone can be used to photograph the runner.

[0045] User 10 runs while wearing at least one or all of the following: a watch-type device 12, a waist-worn device 14, and an information terminal device 16, which serve as the measuring device 20. The measuring device 20 synchronizes information with the running analysis server 60 via communication. The watch-type device 12 and the waist-worn device 14 in the measuring device 20 have short-range wireless communication components. Therefore, they do not communicate directly with the running analysis server 60, but instead synchronize information with the information terminal device 16 (which also functions as "information terminal 50" as described in detail later). The information terminal 50 then synchronizes information with the running analysis server 60. Thus, the watch-type device 12 and the waist-worn device 14 send information to the running analysis server 60 through synchronization with the information terminal 50, which presupposes the user holding the information terminal 50. However, it is not necessary to wear the information terminal 50 during the running process; synchronization with the information terminal 50 is sufficient after the exercise has commenced. As a variation, the waist-worn wearable device 14 may also be in the following form: temporarily synchronizing information with the watch-type device 12 via near-field wireless communication, and the watch-type device 12 then synchronizing information with the information terminal device 16 (information terminal 50) via near-field wireless communication.

[0046] User 10 primarily wears the measuring device 20 during running races such as marathons. However, it is not limited to measurements during races; measurements can also be taken during long-distance training runs simulating races, or even shorter runs. User 10 begins measurement and running log recording by operating buttons on the measuring device 20 at the start of the run. During the running exercise, the measuring device 20 uses a timer to measure the elapsed time from the start of recording as the running time, and records location information for each date and time at specified time intervals. The measuring device 20 uses built-in motion sensors to measure motion information such as cadence (steps per unit time), pelvic rotation / translation, or impact value. The measuring device 20 uses a built-in optical heart rate monitor to measure the user 10's heart rate.

[0047] After the running and running log recording are completed, the measuring device 20 sends running time or location information, motion information, heart rate, and other information as running log data to the running analysis server 60. In addition, the measuring device 20 can also calculate running time or running distance, running speed, cadence, stride length, and other information based on time or location information, and include this calculated information in the running log data and send it to the running analysis server 60.

[0048] The running analysis server 60 is a server computer connected to the Internet and that sends and receives data with multiple user 10 information terminals 50. The running analysis server 60 acquires running record data received from the information terminals 50, including time information, location information, motion information, heart rate, and user identification or attribute information, and accumulates these along with various measured or evaluated values ​​of running analysis indicators calculated based on this information. Upon request from the information terminals 50, the running analysis server 60 sends the accumulated running log data or measured and evaluated values ​​back to the information terminals 50.

[0049] Figure 2 This is a functional block diagram representing the various structures of the running analysis system 100. In this embodiment, the running analysis system 100 includes a measuring device 20, an information terminal 50, and a running analysis server 60. However, the running analysis system 100 can be implemented using various hardware or software structures. For example, the running analysis system 100 may include only the information terminal 50, or a combination of the information terminal 50 and the measuring device 20, or a combination of the information terminal 50 and the running analysis server 60. Alternatively, it may include a combination of the information terminal 50, the measuring device 20, and the running analysis server 60, or a combination of the measuring device 20 and the running analysis server 60, or only the running analysis server 60.

[0050] For example, assuming the use of various general-purpose devices as measuring devices 20 to detect running status and record it as a running log, the running analysis system 100 can be a combination of the information terminal 50 and the running analysis server 60, or it can be a single device containing all the software structures included in the information terminal 50 and the running analysis server 60 shown in this figure. Therefore, regardless of its hardware structure, the running analysis system 100 only needs to include at least the software structures of the information terminal 50 and the running analysis server 60 shown in this figure.

[0051] exist Figure 2In this paper, functional blocks that are implemented through the cooperation of various hardware and software structures are depicted for the measuring device 20, the information terminal 50, and the running analysis server 60. Therefore, those skilled in the art will understand that these functional blocks can be implemented in various forms, either solely through hardware, solely through software, or through a combination thereof. The measuring device 20 includes, for example, a combination of hardware such as a microprocessor, a display device, a memory, a communication module, a positioning module, a motion sensor, and an optical heart rate monitor. The information terminal 50 includes, for example, a combination of hardware such as a microprocessor, a touchscreen, a memory, a communication module, a positioning module, and a motion sensor. The running analysis server 60 includes, for example, a combination of hardware such as a microprocessor, a memory, a display, and a communication module. The functions of the measuring device 20, the information terminal 50, and the running analysis server 60 will be described below.

[0052] The measuring device 20 is, for example, a waist-worn wearable device 14. The measuring device 20 includes a communication unit 21, a time measuring unit 22, a position measuring unit 24, and a motion detection unit 26. The time measuring unit 22 measures the running time from the start of the run, i.e., the start time of the measurement, by counting with a timer. The position measuring unit 24 measures the current position based on location information received from a satellite positioning system using a GPS module. The motion detection unit 26 detects the user 10's stride frequency, pelvic rotation / translation movements, or impact values ​​using motion sensors.

[0053] As the measuring device 20, a watch-type device 12 or an information terminal-type device 16 can also be used. When using the watch-type device 12 as the measuring device 20, the motion detection unit 26 of the watch-type device 12 detects the user 10's step frequency, etc., using a motion sensor, and detects the heart rate, etc., using an optical heart rate monitor. When using the information terminal-type device 16 as the measuring device 20, the motion detection unit 26 of the information terminal-type device 16 detects the user 10's step frequency, etc., using a motion sensor. Furthermore, the information terminal 50 can also serve as the information terminal-type device 16 serving as the measuring device 20. In this case, for example, a portable terminal such as a smartphone can have all the functions of both the measuring device 20 and the information terminal 50. When the information terminal 50 is not used as the measuring device 20, the information terminal 50 is not limited to a smartphone, and can also be a tablet terminal or personal computer owned by the user 10.

[0054] The information terminal 50 includes an information acquisition unit 30, a measurement value acquisition unit 40, an input / output unit 51, and a communication unit 52. The information acquisition unit 30 receives, via the communication unit 52, the location and motion information of the user 10, measured by a measuring device 20 worn by the user 10 during a race, for each point passed during the run. Here, "points passed" refers to locations passed in time or distance during a race or similar activity. For each time or distance passed, the location and motion information are recorded in the measuring device 20. The location information includes the measured date and time, location coordinates, elevation, etc. The motion information includes information indicating stride frequency, pelvic rotation / translation, or impact value, etc. The information acquisition unit 30 can synchronize information with the measuring device 20 during the run and acquire the location and motion information from the measuring device 20 as information about the running status during the run, or it can acquire the entire location and motion information from the measuring device 20 after the run ends.

[0055] The measurement value acquisition unit 40 acquires measurement values ​​of various motion analysis indicators representing the running motion state of the user in each measurement interval of a specified unit, based on the information acquired by the information acquisition unit 30 and based on the location information and motion information continuously in chronological order. (Hereinafter, the measurement values ​​of the motion analysis indicators representing the running motion state are referred to as "indicator measurement values"). "Measurement interval of a specified unit" refers to a measurement interval in units of a specified elapsed time such as one second or one minute, or a measurement interval in units of a specified elapsed distance such as 100m or 1km.

[0056] The measurement acquisition unit 40 calculates the values ​​of various motion analysis indicators, such as single-lap pace, single-lap time, running time, running speed, cadence, stride length, stride-to-height ratio, trunk lean, vertical movement, vertical movement-to-height ratio, waist sinking, lateral pelvic tilt, pelvic lift, pelvic rotation, pelvic rotation timing, lateral impact, kicking time, landing time, landing time rate, landing impact, kicking acceleration, deceleration, stiffness, and stiffness-to-weight ratio. The measurement acquisition unit 40 records these continuous time-series measurement values ​​as time-series data throughout the entire running process, from start to finish.

[0057] The input / output unit 51 sends the location and motion information acquired by the measuring device 20, the index measurement values ​​acquired by the measurement value acquisition unit 40, and the attribute information of the user 10 (as a running log) to the running analysis server 60 via the communication unit 52. The input / output unit 51 displays the location and motion information acquired by the measuring device 20, the index measurement values ​​acquired by the measurement value acquisition unit 40, and the information received from the running analysis server 60 on the screen. The input / output unit 51 is subject to operation input from the user 10. The input / output unit 51 includes a touchscreen in hardware.

[0058] Furthermore, in this embodiment, an example of the measurement value acquisition unit 40 acquiring multiple indicator measurement values ​​will be described. However, by enabling the running analysis server 60 to have the function of the measurement value acquisition unit 40, the indicator measurement values ​​may not need to be calculated in the information terminal 50. In the following description of the running analysis server 60, an example of the running analysis server 60 having a measurement value acquisition unit 80 with the function equivalent to the measurement value acquisition unit 40 will be described.

[0059] The running analysis server 60 includes a communication unit 62, a log acquisition unit 64, an information acquisition unit 70, a measurement value acquisition unit 80, a classification processing unit 85, a morphology determination unit 90, a data storage unit 66, and an output unit 99.

[0060] The log acquisition unit 64 acquires running logs via the communication unit 62 and stores them in the data storage unit 66. The information acquisition unit 70 functions similarly to the information acquisition unit 30 of the measuring device 20. That is, the information acquisition unit 70 acquires the location and movement information of the user 10, measured by the measuring device 20 worn by the user 10 as a runner in the race, for each point passed during the run, from the running logs stored in the data storage unit 66.

[0061] The measurement value acquisition unit 80 functions similarly to the measurement value acquisition unit 40 of the information terminal 50. Specifically, based on the information acquired by the information acquisition unit 70, and based on continuous time-series location and motion information, the measurement value acquisition unit 80 acquires measurement values ​​of various motion analysis indicators representing the user's running motion state for each measurement interval within a specified unit. The measurement value acquisition unit 80 stores the continuous time-series measurement values ​​of these indicators throughout the entire running process, from start to finish, as time-series data in the data storage unit 66.

[0062] Furthermore, running routes, such as those used in races, can vary greatly in elevation and can be significantly affected by external environmental factors such as season, weather, temperature, humidity, time of day, and number of participants. Therefore, the measurement acquisition unit 80 can acquire information related to route or environmental conditions and standardize it to data unaffected by these conditions. In this case, by similarly standardizing the data used for comparison (described later), comparisons under equal conditions can be achieved, thereby improving analytical accuracy.

[0063] The classification processing unit 85 classifies motion analysis indicators according to each category using a prescribed classification method that distinguishes indicator measurement values ​​across multiple measurement intervals based on their characteristics. There are two classification methods. The first method classifies the indicator measurement values ​​according to each category based on a range calculated from the average and standard deviation of the indicator measurement values. The second method classifies the indicator measurement values ​​according to each category using cluster analysis. Through these classification methods, the indicator measurement values ​​can be distinguished based on their similarity to each other within each category of motion analysis indicators.

[0064] In the first classification method, the classification processing unit 85 classifies the indicator measurement values ​​using the mean and standard deviation. The classification processing unit 85 classifies the time series data of the indicator measurement values ​​based on whether they fall within the range of the mean ± standard deviation. Thus, the indicator measurement values ​​can be distinguished by normal values ​​and outliers, or by indicator measurement values ​​representing stable running postures and indicator measurement values ​​representing unstable running postures.

[0065] In the second classification method, the classification processing unit 85 classifies the index measurements using cluster analysis. As a preparatory process for cluster analysis, the classification processing unit 85 calculates the average and standard deviation of the data at predetermined intervals from the starting point to the ending point in the time series data of the index measurements. That is, after setting a window of a predetermined length from the starting point in the time series data of the index measurements, window processing is performed, which slides the window across the entire range to the ending point while sequentially calculating the average and standard deviation of the index measurements within the window. The calculated average and standard deviation values ​​are then clustered into a predetermined number of groups through cluster analysis, thereby classifying the index measurements into multiple groups and labeling the groups. Details regarding cluster analysis will be described later.

[0066] Depending on the measured index value, the choice between the first and second classification methods can vary, and the specific classification method can be preset based on the measured index value. Alternatively, the classification processing unit 85 can perform classification processing using both the first and second classification methods for each measured index value, and determine which method to use based on the execution result. For example, if the result of using one classification method fails to classify the index into an appropriate number, the other classification method can be used.

[0067] The format determination unit 90 determines the output format of the classified index measurement value based on a comparison with a specified comparison object. Here, "output format" refers to the format of the information output to the information terminal 50, including the type or content of information displayed on the screen of the information terminal 50, the display format, and the data content sent to the information terminal 50. The format determination unit 90 determines the type of information to be output, the comparison object of the information, and the output format of the information based on instructions from the user 10 input to the input / output unit 51 of the measuring device 20. The format determination unit 90 includes an instruction acquisition unit 91, an output object determination unit 92, a comparison object setting unit 93, a comparison processing unit 94, a change condition setting unit 95, and a change detection unit 96.

[0068] The instruction acquisition unit 91 acquires instructions from the user 10 via the input / output unit 51 of the measuring device 20. The instruction acquisition unit 91 can set the measured value of the index corresponding to the selected analysis viewpoint as an output object or comparison object by allowing the user 10 to select an analysis viewpoint of interest. For example, as various analysis viewpoints selected by the user 10, seven analysis viewpoints are prepared: "Low-burden landing," "Stable posture," "Full-body coordination around the pelvis," "Smooth center of gravity shift," "Activity intensity," "Left-right symmetry," and "Speed ​​of the race." These are analysis viewpoints that individually affect one or more index measured values.

[0069] The output object determination unit 92 sets the indicator measurement values ​​corresponding to the analysis viewpoint selected by the user 10 as the output object. For example, the indicator measurement values ​​corresponding to the analysis viewpoint of "low-burden landing" are the vertical height ratio, landing impact, and kicking acceleration. The indicator measurement values ​​corresponding to the analysis viewpoint of "stable posture" are the lateral tilt of the pelvis and the amount of trunk posterior tilt. The indicator measurement values ​​corresponding to the analysis viewpoint of "full-body linkage around the pelvis" are kicking time, pelvic rotation timing, and waist sinking. The indicator measurement values ​​corresponding to the analysis viewpoint of "smooth center of gravity shift" are deceleration and lateral impact. The indicator measurement values ​​corresponding to the analysis viewpoint of "activity intensity" are stride-to-height ratio, pelvic rotation, and pelvic lift. All indicator measurement values ​​correspond to the analysis viewpoint of "left-right symmetry". The indicator measurement value corresponding to the analysis viewpoint of "race speed" is running speed.

[0070] Furthermore, the output target determination unit 92 can, particularly in the absence of instructions from user 10, use all measured index values ​​as output targets. Alternatively, the output target determination unit 92 can use all measurement intervals within a single measured index value as output targets, or, if the instruction acquisition unit 91 receives a selection instruction from user 10 regarding a measurement interval of interest, it can limit the output targets to a specific measurement interval based on user 10's instruction. The output target determination unit 92 can also limit the output targets to measurement intervals where particularly noticeable anomalies are detected by the change detection unit 96 (described later) or measurement intervals indicating particularly excellent results.

[0071] The output data generation unit 98 generates output data in a manner that includes the measured values ​​of the indexes set as output objects by the output object determination unit 92. The output data at least includes the content displayed on the screen by the input / output unit 51 of the measuring device 20.

[0072] The form determination unit 90 can output the index measurement value in different output forms depending on which value is used as the comparison object. The comparison object setting unit 93 sets certain benchmark values ​​as comparison objects. For example, the comparison object setting unit 93 can be set to compare the average values ​​of each group label after classification by the classification processing unit 85 with each other. For example, the comparison object setting unit 93 can use the average value in the time series data of the index measurement value, or the average value within a specified measurement interval as the comparison object, or it can use the same index measurement value in other measurement intervals as the comparison object. The comparison object setting unit 93 can also use the index measurement value of the other foot as the comparison object when the index measurement value is for one of the left or right feet. The comparison object setting unit 93 can also use the same index measurement value from other dates and times or other users as the comparison object.

[0073] The comparison processing unit 94 compares the measured value of the output object with the comparison object set by the comparison object setting unit 93. For example, when the average value of each group label after classification by the classification processing unit 85 is used as the comparison object, the comparison processing unit 94 compares the average values ​​of each group label with each other. The evaluation decision unit 97 evaluates each group of the measured values ​​of the index after classification by the classification processing unit 85 based on the comparison results obtained by the comparison processing unit 94. Regarding the measured value of the index set as the output object by the output object determination unit 92, the evaluation decision unit 97 determines the evaluation of the measured value based not only on the comparison results obtained by the comparison processing unit 94, but also on the detection results obtained by the change detection unit 96.

[0074] The change detection unit 96 detects changes that meet predetermined change conditions in the time series data of the index measurement values ​​that are the output objects. The change condition setting unit 95 sets the change conditions that are the objects of detection by the change detection unit 96. The change condition setting unit 95 can set specific change conditions as standard detection conditions, or it can set conditions specified by the user 10 as change conditions. For example, a change condition can be a condition determined by detecting the index measurement value as a value of interest when the difference between a predetermined benchmark value and the index measurement value exceeds a predetermined range. For example, it can also be detected when the index measurement value is significantly better than or significantly worse than the benchmark value. The benchmark value that is the object of comparison can be a comparison object set by the comparison object setting unit 93.

[0075] Regarding the index measurement value set as the output object by the output object determination unit 92, the evaluation determination unit 97 determines the evaluation of the index measurement value based on the comparison result obtained by the comparison processing unit 94 or the detection result obtained by the change detection unit 96.

[0076] The output data generation unit 98 generates output data in a manner that distinguishes the measurement intervals of index measurements where changes were detected by the change detection unit 96 from other index measurements, i.e., the measurement intervals where no changes were detected. Furthermore, the output data generation unit 98 generates output data in a manner that distinguishes the motion analysis indexes whose changes were detected by the change detection unit 96 from other motion analysis indexes, i.e., the index measurements of motion analysis indexes where the same changes were not detected. When the evaluation is determined by the evaluation decision unit 97, the output data generation unit 98 generates output data in a manner that includes the evaluation result.

[0077] Figure 3This is a flowchart illustrating the processing steps in the running analysis system. The information acquisition unit 70 acquires position or motion information measured by the measuring device 20 during running, such as in a race, by the user 10 (S10). The measurement value acquisition unit 80 acquires measurement values ​​of various motion analysis indicators based on the acquired position or motion information (S12). The classification processing unit 85 classifies the indicator measurement values ​​corresponding to various motion analysis indicators according to a prescribed classification method (S14). The instruction acquisition unit 91 acquires information about the analysis viewpoint when the user 10 inputs the analysis viewpoint (S16). The output object determination unit 92 determines the output object of the indicator measurement values ​​based on the analysis viewpoint (S18). The change detection unit 96 detects motion analysis indicators or their indicator measurement values ​​that meet the prescribed change conditions (S22). The evaluation determination unit 97 determines the evaluation of the indicator measurement values ​​(S24). The output data generation unit 98 generates output data by combining the indicator measurement values ​​(which are the output objects) with comparison results or detection results and evaluations. The output unit 99 outputs the indicator measurement values ​​based on the output data generated by the output data generation unit 98 (S26). Furthermore, considering the various orders in which S12 to S26 are executed, the order of S12 to S26 in the flowchart of this figure is only a convenient one.

[0078] Figure 4 This illustrates an example of classifying indicator measurements using a first classification method. In this first classification method, the classification processing unit 85 classifies the indicator measurements using the mean and standard deviation. Figure 4 In the chart, the measured values ​​of the index, which are set as the classification objects, are plotted in a way that corresponds to the running distance and location, representing the time series data of the measured values ​​of the index, which represents the amount of pelvic rotation. The vertical axis represents the amount of pelvic rotation [deg], and the horizontal axis represents the distance and location [km]. The solid line 110 represents the average value of the time series data of the amount of pelvic rotation, and the dashed line 112 represents the range of the average value ± standard deviation of the time series data of the number of pelvic rotations. The measured values ​​within the range of the two dashed lines 112 are plotted as circles, and the measured values ​​outside the range of the dashed lines 112 are plotted as diamonds. In the example of this chart, the diamond plots of plot groups 114a to 114k are the measured values ​​of the index outside the range of the dashed lines 112, and are classified in a way that distinguishes them from the measured values ​​of the measured values ​​of the circle plots within the range of the dashed lines 112. The measured values ​​represented by the circle plots are classified as measured values ​​representing stable running posture within the standard deviation, and the measured values ​​represented by the diamond plots are classified as measured values ​​representing unstable or disordered running posture outside the standard deviation.

[0079] Thus, by classifying the time series data of index measurements according to whether they are within the range of mean ± standard deviation, it is possible to distinguish between index measurements representing stable running posture and those representing unstable running posture.

[0080] Figure 5 (a) to Figure 5 (c) represents the preparatory processing when classifying the indicator measurements using the second classification method. In the second classification method, the classification processing unit 85 classifies the indicator measurements through cluster analysis. Figure 5 (a) to Figure 5 In the graph (c), the measured values ​​of the index, which are set as the category objects, are plotted as time series data representing the measured values ​​of running pace in a way that corresponds to the running distance and location. The vertical axis represents running pace [min / km], and the horizontal axis represents distance and location [km]. Figure 5 (a) Directly plot the measured index values. Here, as a preparatory process, a window W of a specified length interval is set as shown in the figure, and window processing is performed to calculate the average and standard deviation of the measured index values ​​contained in window W while sliding window W from the starting point to the ending point. Window W covers an interval that may contain multiple, for example, five, measured index values ​​consecutively in a time series. If the measured index values ​​are measured at intervals of 100m, a window with an interval of 500m is set. Alternatively, if the measured index values ​​are measured at intervals of 10 seconds, for example, a time window with an interval of 60 seconds is set.

[0081] The first window W1 covers the first to fifth indicator measurements, and the second window W2 covers the second to sixth indicator measurements. The windows are set up by sliding one indicator measurement at a time. When sliding towards the endpoint, the window starts from the (n-1)th window W... n-1 Reaching the final nth window W n At that time, window processing ends. Figure 5 In (b), time series data of the average values ​​of the index measurements in each window, calculated through window processing, are plotted in a manner corresponding to the running distance locations of each window. Figure 5 In (c), the time series data of the standard deviation of the index measurements in each window, calculated through window processing, are plotted in a way that corresponds to the running distance location of each window.

[0082] Figure 6 (a) and Figure 6 (b) indicates the process of classifying the measured values ​​of the index using the second classification method. Figure 6 The chart in (a) is based on Figure 5 (a) to Figure 5 (c) is calculated for each window Figure 5 The average of (b) is the horizontal axis, with Figure 5 The standard deviation of (c) is used as the vertical axis to plot the scatter plot. For example, all plots are clustered using the K-means method. For the number of clusters K, an estimated value based on the pipe bending method can be set, or a fixed value such as "4" can be set if it is desired to divide all plots into four stages regardless of the type of running evaluation value. As shown in the figure, all plots are clustered according to their distance from K centroids and classified into the first group 120 with centroid 121 as the core, the second group 122 with centroid 123 as the core, the third group 124 with centroid 125 as the core, and the fourth group 126 with centroid 127 as the core. Each plot is labeled with the group label after classification. Figure 6 The chart in (b) represents Figure 5 The average of (b). Each plot is categorized into... Figure 6 The labeled groups in (a) are Group 120, Group 222, Group 324, and Group 426. The number of clusters can vary depending on the metric measurement value, and can also vary depending on the deviation of the metric measurement value for each user or each run.

[0083] Thus, by using cluster analysis to classify the time series data of indicator measurements, we can distinguish them according to the similarity of their characteristics, and objectively capture and detect deviations in the indicator measurements.

[0084] Figure 7 This is a horizontal bar chart representing the proportion of each motion analysis indicator's category. For each motion analysis indicator, its measured values ​​are classified using either the first or second classification method, and the time series data is segmented at the points of change in the categories. The measured values ​​of each indicator are arranged on the vertical axis, and the running distance [km] is taken as the horizontal axis. In the case of a marathon, the total distance is set to 42km, and the horizontal bar chart of the measured values ​​of each motion analysis indicator is segmented according to the proportion of each category. For example, in the motion analysis indicator "stiffness," it is segmented into two categories with the boundary around 34.5km. In the motion analysis indicator "pelvic rotation timing," it is segmented into three categories with the boundaries around 4km and 14.5km. For example, in the case of motion analysis indicators classified using the first classification method, the time series data of the indicator measured values ​​is segmented based on whether the boundary is within or outside the standard deviation. In the case of motion analysis indicators classified using the second classification method, the time series data of the indicator measured values ​​is segmented based on the points of change in the group labels.

[0085] Figure 8 This indicates that, according to another benchmark, in Figure 7The evaluation process involves segmenting the measured values ​​of the indicators from a horizontal bar chart. The comparison processing unit 94 uses the comparison objects set by the comparison object setting unit 93 as benchmark values ​​to evaluate the classification of each motion analysis indicator. For example, when using the average value of each group label after classification by the classification processing unit 85 as the comparison object, the comparison processing unit 94 compares the average values ​​of each group label with each other. Based on the comparison results obtained by the comparison processing unit 94, the evaluation decision unit 97 evaluates each group of indicator measured values ​​after classification by the classification processing unit 85, and proceeds according to the order of the average values ​​of each group, such as... Figure 8 The values ​​are distinguished and displayed using colors to differentiate them from other indicator measurement values. The first color 130 represents the best value category (e.g., blue). The second color 131 represents the slightly better value category (e.g., green). The third color 132 represents the slightly worse value category (e.g., yellow). The fourth color represents the worst value category (e.g., red). As a variation, the comparison processing unit 94 can also calculate the average value of the overall indicator measurement values ​​of the competition, compare it with the overall average value of the competition according to the group label, and distinguish and display it using colors according to the comparison results.

[0086] Figure 9 (a) and Figure 9 (b) represents an example of limiting the output object to the measured values ​​of the indicators detected as the focus and displaying them. Figure 9 of (a), Figure 9 In (b), as a comparison result obtained by the comparison processing unit 94, the classifications that are significantly better than the specified benchmark value that is the object of comparison and the classifications that are significantly worse than the specified benchmark value that is the object of comparison are defined and displayed. The classification of significantly better is represented by the fourth color 134 (e.g., red), and the classification of significantly worse is represented by the fifth color 135 (e.g., blue). Figure 9 The comparison object in (a) can be, for example, user 10's own data or data from other runners. The comparison object can be set from the metric measurements of the same runner in the same race, from the metric measurements of the same runner in past races, or from the metric measurements of other runners. When using the metric measurements of other runners as the comparison object, the metric measurements of other runners within the same measurement interval can also be used. Regarding... Figure 9 The comparison objects in (b) can be, for example, the comparison objects in (b). Figure 5 The value of the previous window in each window of (a) can be used as the comparison object, or the value of the previous circle in each circle can be used as the comparison object.

[0087] The change detection unit 96 pairs of motion analysis indicators with the longest interval of the interval that is considered to be significantly better and has a sustained tendency (in Figure 9In example (a), it is "lateral tilt of the pelvis"; or the action analysis index with the longest interval of the tendency to persist as a significant difference (in Figure 9 In example (a), the "deceleration" is detected.

[0088] The variation detection unit 96 can also detect combinations of motion analysis indicators where any one of multiple motion analysis indicators has a sustained range of significantly good tendencies, or combinations of motion analysis indicators where any one of multiple motion analysis indicators has a sustained range of significantly poor tendencies. For example, the variation detection unit 96 might detect a combination of landing impact / kickout acceleration (low-burden landing) and lateral impact (smooth weight transfer) as a combination of motion analysis indicators that has a sustained range of significantly good tendencies in the final stage of the race. In this case, the evaluation decision unit 97 can decide on a recommendation to run with efficient power utilization as the evaluation result. Alternatively, it can detect a combination of pelvic rotation (force of movement) and kickout time (full-body coordination around the pelvis) as a combination of motion analysis indicators that has a sustained range of significantly poor tendencies in the final stage of the race. In this case, the evaluation decision unit 97 can decide on a recommendation to reduce kickout activity and use the pelvis to extend the leg forward while running as the evaluation result.

[0089] Figure 10 This is an example of a motion analysis index representing the longest interval with a tendency to persist as a significant difference. In this figure, the pelvic rotation is graphically represented by the longest interval with a tendency to persist as a significant difference in the final stage of the race. Time series data representing the pelvic rotation are plotted as index measurements, corresponding to running distance and location. The vertical axis represents the pelvic rotation [deg], and the horizontal axis represents the distance [km]. Specifically, the user 10's pelvic rotation showed a significant tendency to persist as a significant difference in interval 139 during the final stage of the race, and this was detected as a significant change by the change detection unit 96. While the user 10 often perceives such significant changes during the race, they sometimes cannot fully recognize at which stage the change begins, even as a warning sign. Through this embodiment, significant changes in objective data and the timing of the change's onset can be detected as warning signs, providing useful data for improving the user 10's performance.

[0090] Figure 11This is an example of a screen displaying race results. When user 10 instructs to display a summary of the race results, a race summary screen 140 generated by the morphology determination unit 90 is displayed. In the race summary screen 140, in addition to displaying information indicating running status such as running distance, running time, average pace, average stride length, and average cadence, a radar chart is also displayed showing scores based on various motion analysis indicators as running posture scores. Additionally, route information based on running location information is displayed. The bottom bar displays evaluation content including suggestions for user 10.

[0091] Figure 12 This is an example of a screen displaying race evaluation. When user 10 instructs that a race evaluation be displayed, a race review screen 142 generated by the morphology determination unit 90 is displayed. In the race review screen 142, the first column 143 displays evaluations related to running pace. The second column 144 displays a graph showing the progress of running pace. The third column 145 displays evaluations of pace divided into the start, middle, and end stages of the race, as well as evaluations related to posture.

[0092] The fourth column 146 displays evaluations based on significant changes detected by the change detection unit 96, or evaluations related to motion analysis indicators corresponding to the viewpoint selected by the user 10. The fourth column 146 displays multiple evaluation points determined by the evaluation decision unit 97, and switches to a screen like the one shown below that displays detailed explanations or charts related to each evaluation point, according to the user 10's instructions.

[0093] Figure 13 This is an example of a screen displaying detailed explanations related to the evaluation points. When user 10 instructs that detailed explanations related to the evaluation points be displayed, a point explanation screen 150 generated by the morphology determination unit 90 is displayed. In the point explanation screen 150, explanations of the motion analysis indicators themselves, explanations of changes when significant changes are detected, and explanations of comparison results with specified comparison objects are displayed in text and charts.

[0094] The present invention has been described above according to embodiments. These embodiments are examples, and those skilled in the art will understand that various modifications may be possible in the combination of their constituent elements or processing procedures, and such modifications are also within the scope of the present invention. Furthermore, if the embodiments are summarized, the following configuration is obtained.

[0095] [Form 1]

[0096] A running analysis system, comprising:

[0097] The information acquisition department acquires the user's location and movement information as a runner, measured by a prescribed measuring device at each point the runner passes through during the run.

[0098] The measurement acquisition unit acquires measurement values ​​of various motion analysis indicators representing the running motion state of the user in each measurement interval of a specified unit, based on the location information and motion information that are continuously updated over a time series.

[0099] The classification processing unit classifies each type of the motion analysis index using a prescribed classification method that distinguishes the measured values ​​of multiple measurement intervals by characteristics.

[0100] The morphology determination unit determines the output morphology of the classified measurement values ​​based on a comparison with a specified comparison object; and

[0101] The output unit is capable of outputting at least information related to the classified measurement value based on the determined output format.

[0102] [Form 2]

[0103] According to the running analysis system of form 1, the classification processing unit classifies the measured values ​​according to each category of the motion analysis index by a prescribed classification method that distinguishes the measured values ​​from each other based on their similarity.

[0104] [Form 3]

[0105] According to the running analysis system described in form 1 or 2, the classification processing unit classifies the measured values ​​according to each category of the motion analysis index, based on the range calculated from the average value and standard deviation of the measured values.

[0106] [Form 4]

[0107] According to any one of the forms 1 to 3, in the running analysis system, the classification processing unit classifies the measured values ​​by cluster analysis according to each category of the motion analysis index.

[0108] [Form 5]

[0109] According to any one of the forms 1 to 4, the form determination unit determines the output form by distinguishing the measured value obtained by detecting changes that meet the prescribed change conditions from other measured values.

[0110] [Form 6]

[0111] According to any one of the forms 1 to 5 of the running analysis system, the form determination unit determines the output form by distinguishing the motion analysis index obtained by detecting changes that meet the prescribed change conditions from other motion analysis indices.

[0112] [Form 7]

[0113] According to any one of the forms 1 to 6, the form determination unit determines the output form by distinguishing the measured value obtained from detecting changes that meet the change conditions specified by the user from other measured values.

[0114] [Form 8]

[0115] According to any one of the forms 1 to 7, the form determination unit determines the output form by distinguishing the measured value obtained by detecting changes that meet the prescribed change conditions in the motion analysis indicators specified by the user from other measured values.

[0116] [Form 9]

[0117] According to any one of the forms 1 to 8, the form determination unit determines the output form in a manner that distinguishes the measured value obtained by detecting changes that meet the prescribed change conditions in the measurement interval specified by the user from other measured values.

[0118] [Form 10]

[0119] According to any one of the morphologies 1 to 9, in the running analysis system, the morphology determination unit determines the output morphology of the classified measurement value based on a comparison with a comparison object specified by the user.

[0120] [Form 11]

[0121] A running analysis method includes the following process:

[0122] Acquire the location and motion information of the user as a runner, measured by a specified measuring device at each point passed during the run;

[0123] Based on the location information and the action information continuously over time, the measured values ​​of various action analysis indicators representing the running action state of the user in each measurement interval of a specified unit are obtained.

[0124] According to each category of the motion analysis index, it is classified by a prescribed classification method for distinguishing the measured values ​​of multiple measurement intervals by characteristics;

[0125] The output format of the classified measurement values ​​is determined based on comparison with specified comparison objects; and

[0126] Based on the determined output format, at least information related to the classified measurement values ​​will be output.

Claims

1. A running analysis system, characterized in that, include: The information acquisition department acquires the user's location and movement information as a runner, measured by a prescribed measuring device at each point the runner passes through during the run. The measurement acquisition unit acquires measurement values ​​of various motion analysis indicators representing the running motion state of the user in each measurement interval of a specified unit, based on the location information and motion information that are continuously updated over a time series. The classification processing unit classifies each type of the motion analysis index using a prescribed classification method that distinguishes the measured values ​​of multiple measurement intervals by characteristics. The morphology determination unit determines the output morphology of the classified measurement values ​​based on comparison with specified comparison objects; as well as The output unit is capable of outputting at least information related to the classified measurement values ​​based on the determined output format. The morphology determination unit determines the output morphology by distinguishing the measured value obtained from detecting changes that meet the prescribed change conditions from other measured values, and detects the timing of the change as a precursor for the combination of motion analysis indicators in which each of the motion analysis indicators has the longest interval of the interval in which the tendency to be significantly better or significantly worse persists.

2. The running analysis system according to claim 1, characterized in that, The classification processing unit classifies the measured values ​​according to each category of the motion analysis index using a prescribed classification method that distinguishes the measured values ​​from each other based on their similarity.

3. The running analysis system according to claim 2, characterized in that, The classification processing unit classifies the measured values ​​according to each category of the motion analysis index, based on the range calculated from the average value and standard deviation of the measured values.

4. The running analysis system according to claim 2, characterized in that, The classification processing unit classifies the measured values ​​according to each category of the action analysis index through cluster analysis.

5. The running analysis system according to any one of claims 1 to 4, characterized in that, The morphology determination unit determines the output morphology by distinguishing motion analysis indicators obtained from detecting changes that meet the prescribed change conditions from other motion analysis indicators.

6. The running analysis system according to any one of claims 1 to 4, characterized in that, The morphology determination unit determines the output morphology by distinguishing the measured values ​​obtained from detecting changes that meet the user-specified change conditions from other measured values.

7. The running analysis system according to any one of claims 1 to 4, characterized in that, The form determination unit determines the output form by distinguishing the measured value obtained from detecting changes that meet the specified change conditions in the motion analysis indicators specified by the user from other measured values.

8. The running analysis system according to any one of claims 1 to 4, characterized in that, The morphology determination unit determines the output morphology by distinguishing the measured value obtained from detecting changes that meet the specified change conditions within the measurement interval specified by the user from other measured values.

9. The running analysis system according to any one of claims 1 to 4, characterized in that, The morphology determination unit determines the output morphology of the classified measurement value based on a comparison with a comparison object specified by the user.

10. A running analysis method, characterized in that, The process includes the following: Acquire the location and motion information of the user as a runner, measured by a specified measuring device at each point passed during the run; Based on the location information and the action information continuously over time, the measured values ​​of various action analysis indicators representing the running action state of the user in each measurement interval of a specified unit are obtained. According to each category of the motion analysis index, it is classified by a prescribed classification method for distinguishing the measured values ​​of multiple measurement intervals by characteristics; The output form of the classified measurement value is determined based on the comparison with the specified comparison object, and the output form is determined in a way that distinguishes the measurement value obtained by detecting changes that meet the specified change conditions from other measurement values. The combination of the motion analysis indicators, in which each of the motion analysis indicators has the longest interval of the interval that is a significantly better or significantly worse tendency, is detected and the timing of the start of the change is detected as a precursor. as well as Based on the determined output format, at least information related to the classified measurement values ​​will be output.

Images