Motion analysis device, motion analysis method, and computer-readable storage medium

Abstract

The present invention provides a motion analysis device, a motion analysis method, and a computer-readable storage medium, which can appropriately analyze motion based on the overall tendency of motion. The motion analysis device (100) includes: a group classification unit (120) that classifies activity data, which records measurement data related to motion and predetermined baseline data that changes during motion, into multiple groups based on the baseline data; a representative data generation unit (130) that generates representative data of the activity data in each group; and a tendency analysis unit (140) that analyzes the tendency of the representative data in the multiple groups relative to the baseline data. With this motion analysis device (100), it is possible to appropriately analyze motion based on the overall tendency of motion.

Description

Technical Field

[0001] The present invention relates to a technology for analyzing motion movements, and in particular to a motion analysis device, a motion analysis method, and a computer-readable storage medium. Background Art

[0002] In recent years, portable communication devices such as smartphones have become increasingly lightweight, and the development of so-called wearable devices, typified by smartwatches, has also become increasingly popular. These devices can be worn during activities such as running and measure athletic performance using built-in accelerometers. Services and applications exist that provide guidance for improving athletic performance based on these measurement results.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 2015-154988 Summary of the Invention

[0006] Problems to be solved by the invention

[0007] Patent Document 1 discloses a technology that reduces the amount of data transmitted and speeds up motion analysis processing by setting selection conditions when transmitting data measured by various devices during activities such as running or walking to a server for motion analysis. Examples of selection conditions include conditions based on distances such as "every 1 km," time periods such as "every 5 minutes," and pace changes such as "when leaving the set pace range." As described above, the goal is to perform efficient motion analysis by setting selection conditions that are expected to affect the user's movements.

[0008] In the technology disclosed in Patent Document 1, only measurement data that meets the selection criteria is transmitted to the motion analysis server, thereby enabling appropriate motion analysis to be performed within the scope of the selected measurement data. However, there is no guarantee that the results of the motion analysis performed within this limited scope will also be reasonable for the overall motion, including the majority of the unselected measurement data. In particular, there is the possibility that the selected measurement data may, for some reason, become abnormal data that is contrary to the overall motion trend. In such cases, the motion analysis results may even worsen the user's motion movements.

[0009] The present invention has been made in view of the above situation, and an object of the present invention is to provide a motion analysis device capable of appropriately analyzing exercise motion based on the overall tendency of exercise.

[0010] Technical means to solve the problem

[0011] In order to solve the above-mentioned problem, a motion analysis device of a certain embodiment of the present invention includes: a group classification unit, which classifies activity data that records measurement data related to motion movements and specified baseline data that changes during motion into multiple groups based on the baseline data; a representative data generation unit, which generates representative data of the activity data in each group; and a tendency analysis unit, which analyzes the tendency of the representative data in multiple groups relative to the baseline data.

[0012] According to the embodiment, by classifying a series of activity data recorded during exercise into a plurality of groups and analyzing the trends between the groups of the representative data, it is possible to appropriately analyze exercise motion based on the overall trend of the exercise.

[0013] Another embodiment of the present invention is a motion analysis method. The method includes: a group classification step of classifying activity data, which records measurement data related to exercise movements and predetermined baseline data that changes during exercise, into multiple groups based on the baseline data; a representative data generation step of generating representative data of the activity data in each group; and a trend analysis step of analyzing the trends of the representative data in the multiple groups relative to the baseline data.

[0014] Furthermore, optional combinations of the above-described constituent elements and expressions of the present invention in the form of methods, apparatuses, systems, recording media, computer programs, and the like may also be practiced as additional aspects of the present invention.

[0015] Effects of the Invention

[0016] According to the present invention, it is possible to appropriately analyze exercise motion based on the overall tendency of exercise. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 FIG. 1 is an overall configuration diagram of a system including a motion analysis device according to an embodiment.

[0018] Figure 2 This is a diagram showing an example of how the motion analysis device processes activity data.

[0019] Figure 3 This is a diagram showing an example of display of trend analysis results and guidance information.

[0020] Figure 4 This is a diagram showing an example of display of trend analysis results and guidance information.

[0021] Figure 5 This is a diagram showing an example of display of trend analysis results and guidance information.

[0022] Figure 6 This is a diagram showing the flow of motion analysis processing performed by the motion analysis device.

[0023] Explanation of symbols

[0024] 100: Motion analysis device

[0025] 110: Activity data recording department

[0026] 120: Group Classification Department

[0027] 130: Representative data generation unit

[0028] 140: Trend Analysis Department

[0029] 150: Guidance Information Generation Department

[0030] 160: Display control unit

[0031] 20: Measuring equipment

[0032] 30: Display device DETAILED DESCRIPTION

[0033] In this embodiment, based on the data measured during the user's exercise, an analysis of the movement and guidance for improvement are performed. When analyzing the movement, the measured data are grouped based on benchmark data such as speed. For example, the data are classified into three groups: a group with a speed within the normal range, a group with a speed greater than the normal range, and a group with a speed less than the normal range. In this case, the amount of measured data for the group with a speed greater than or less than the normal range is reduced, but by performing an analysis using representative data of each group, the tendency of each group can be accurately grasped regardless of the amount of data included in each group.

[0034] Figure 1 This is a diagram illustrating the overall structure of a system including a motion analysis device 100 according to an embodiment. Motion analysis device 100 analyzes a user's athletic performance based on measurement data obtained by measurement device 20 during running. The analysis results are displayed on display device 30 used by the user, along with guidance for improving athletic performance.

[0035] The measuring device 20 is, for example, a wearable device such as a smartwatch or a smartphone that a user can wear while running, and measures the running motion using built-in sensors. However, in this embodiment, the measuring device 20 is not limited to these and can be any device as long as it has the function of measuring data during running and the minimum data transmission function for transmitting the measured data to the motion analysis device 100. For example, a camera (photographing device) that captures a user while running can also be used as the measuring device 20. In this case, the data captured by the camera is provided to the motion analysis device 100 as the measurement data.

[0036] As described above, since various devices can be used as the measurement device 20 , the motion analysis apparatus 100 can obtain various measurement data related to the user's running motion.

[0037] For example, when a wearable device or a smartphone is used as the measuring device 20 as described above, basic physical quantities related to the user's position or movement can be obtained as measurement data from the acceleration sensors, angular velocity sensors, position sensors (Global Positioning System (GPS) etc.), magnetic sensors etc. built into these devices. By appropriately combining and calculating these measurement data, not only basic information such as the position, speed, and acceleration of the user while running can be obtained, but also biomechanical data related to the details of the movement, such as the user's posture, the rotation angle of the waist or pelvis, the up and down movement of the body's center of gravity, the intensity or angle of the pedaling, the spacing, the stride, the contact time, the contact position or angle, the body's elastic modulus, and the impact of the landing, can be obtained. Furthermore, information related to the running route, such as the distance, height, and inclination, can be obtained.

[0038] Furthermore, if measurement device 20 includes sensors for measuring the external environment, such as ambient light sensors for measuring brightness, temperature sensors, and humidity sensors, motion analysis device 100 can also perform appropriate analysis based on the external environment during running. Furthermore, if measurement device 20 uses a wearable device that can measure biosignals such as heart rate, which has become increasingly popular in recent years, motion analysis device 100 can also perform appropriate analysis and provide improvement guidance based on the user's physical condition.

[0039] Furthermore, the measurement device 20 can also measure the user's surroundings while exercising, rather than requiring the user to wear it during exercise. The aforementioned camera recording is considered a typical example, but is not limited to this. For example, if a user runs indoors on a treadmill or other confined space, the measurement device 20, which is difficult to carry, can be used, dramatically increasing the types of measurement data that can be used.

[0040] Multiple measurement devices 20, as described above, can be used during a single exercise session. For example, a user can wear a wearable device as a first measurement device 20 for measurement, while simultaneously filming the user with a camera as a second measurement device 20. The motion analysis device 100 can analyze the user's exercise movements in various aspects based on measurement data from multiple measurement devices 20, generating guidance information for effective improvement.

[0041] The display device 30 is a device that displays the results of motion analysis generated by the motion analysis apparatus 100 based on the measurement data from the measurement device 20, as well as guidance information for improving exercise performance. For example, when a smartphone is used as the measurement device 20, it also functions as the display device 30 for displaying the analysis results and guidance information. Furthermore, when a measurement device 20, such as a camera without a display function, is used, another device owned by the user, such as a smartphone, tablet, watch, smart glasses, or computer, can be used as the display device 30.

[0042] The motion analysis device 100 is configured on a server capable of communicating with the measurement device 20 and the display device 30 via a communication network. Alternatively, data transfer between the motion analysis device 100 and the measurement device 20 / display device may be performed via a portable storage medium, rather than via a communication network. The motion analysis device 100 includes an activity data recording unit 110, a group classification unit 120, a representative data generation unit 130, a trend analysis unit 140, an instructional information generation unit 150, and a display control unit 160.

[0043] Activity data recording section 110 records the activity data of the benchmark data of the regulation that is recorded with the measurement data relevant to motor action and change in motion.Here, the measurement data relevant to motor action is the measured value of the parameter of the object that becomes the analysis of motion analysis device 100 and guidance information generation, illustrates the various biomechanical data (user's posture, waist or pelvic rotation angle, body center of gravity up and down movement, intensity or angle of stepping on, spacing, stride, contact time, contact position or angle, health, the impact of landing etc.) of being enumerated.And benchmark data is the data used as benchmark in the group classification process in the group classification section 120 of back section, measures in motion together with the measurement data relevant to motor action.As the example of benchmark data, can enumerate the biosignals such as time, number of steps, distance, position, speed, acceleration, height, inclination, brightness, air temperature, humidity, heartbeat etc. in motion. As mentioned above, the benchmark data is not limited to data such as time, number of steps, distance, and position that change monotonically with the progress of exercise, but can also use data such as speed, acceleration, altitude, inclination, brightness, temperature, humidity, and heart rate that increase or decrease during exercise.

[0044] The activity data recording unit 110 records the aforementioned measured data related to the exercise action and the baseline data that changes during the exercise as a set and associated form of activity data. In this case, the activity data recording unit 110 can record activity data for a single exercise or for multiple exercises. In the simplest example, when the measured data and the baseline data each consist of only one parameter, the activity data is represented as points on an xy plane, with the baseline data on the x-axis and the measured data on the y-axis.

[0045] Figure 2 (A) shows an example of activity data recording when "pace" (time per unit distance (the inverse of speed)) is selected as the baseline data and "pelvic rotation angle" is selected as the measured data. This example records activity data from approximately 20 runs, with the x-axis representing pace and the y-axis representing pelvic rotation angle. As shown in the figure, the series of activity data recorded during exercise forms a scatter plot formed by plotting points in a coordinate space with the baseline data and the measured data as the coordinate axes.

[0046] To summarize, when the measured data is represented by n parameters (y1, y2, ..., yn) and the reference data is represented by m parameters (x1, x2, ..., xm), the activity data forms a scatter diagram formed by points plotted in an m+n-dimensional coordinate space with m+n parameters as coordinate axes. Figure 2 The following describes a two-dimensional example (m, n=1) shown in (A).

[0047] The group classification unit 120 classifies the activity data recorded by the activity data recording unit 110 in a single exercise or a plurality of exercises into a plurality of groups based on the reference data. Figure 2 (B) indicates that Figure 2 (A) Example of group classification of activity data. In this example, assuming that the distribution of activity data relative to the pace as the baseline data is close to a normal distribution, the activity data is classified into the following three groups based on the mean μ of the baseline data for all activity data and its standard deviation σ.

[0048] Activity data that deviates from μ within ±2σ is classified as Group 1. When the activity data completely follows a normal distribution, approximately 95.4% of all activity data are classified into Group 1.

[0049] Activity data that deviates from μ by more than -2σ is classified as Group 2. In the case where the activity data completely follows a normal distribution, approximately 2.3% of the entire activity data is classified as Group 2.

[0050] Activity data that deviates from μ by more than +2σ is classified as Group 3. In the case where the activity data completely follows a normal distribution, approximately 2.3% of all activity data are classified as Group 3.

[0051] Furthermore, the ±2σ values ​​described above are illustrative; other values ​​can be used as the basis for group classification. Using the standard deviation σ as in the previous example, for any positive number k, ±kσ can be used as the base range for grouping. Furthermore, while the above example shows three groups for simplicity, more refined grouping is possible. For example, four values, μ-2σ, μ-σ, μ+σ, and μ+2σ, can be used as intervals to create five groups.

[0052] In addition, the present invention is not limited to this statistical classification method, and the user or computer can arbitrarily set the boundaries of each group. For example, the overall distribution of the measured data relative to the reference data can be approximated by an arbitrary dimensional function, and its inflection point can be used as the basis for grouping. In addition, classification using supervised learning such as regression analysis and decision trees or clustering using unsupervised learning can also be used. As a clustering method, hierarchical clustering such as the sum of squared deviations method can be used, and non-hierarchical clustering such as the k-means method can also be used.

[0053] exist Figure 2 In the example (B), Group 1 represents the group whose baseline data is within the normal range, while Groups 2 and 3 represent groups whose baseline data deviates from the normal range. Here, using pace as the baseline data, Group 1 includes activity data from a normal pace (approximately 290-400 sec / km), Group 2 includes activity data from a faster-than-normal pace (approximately less than 290 sec / km), and Group 3 includes activity data from a slower-than-normal pace (approximately greater than 400 sec / km). As described above, the majority (approximately 95.4%) of the activity data falls within Group 1, which is within the normal range. By forming Groups 2 and 3 separately from these, appropriate exercise analysis can be performed without neglecting the small amount of activity data (approximately 2.3% each) belonging to each of these groups.

[0054] The representative data generating unit 130 generates representative data of the activity data in each group. Figure 2 (C) indicates Figure 2 (A) and Figure 2(B) Example of generating representative data of activity data. The representative data R1 to representative data R3 of each of groups 1 to 3 can be obtained by calculating the average value of all activity data belonging to each group. More specifically, when the i-th activity data belonging to each group is expressed as (xi, yi), the x-coordinate of the representative data is the average value of xi, and the y-coordinate of the representative data is the average value of yi. In addition, the average value is illustrated here as the representative data, but other representative values ​​such as the central value or the mode can also be used. Moreover, in group 1 of the normal range where a large amount of data is evenly distributed to a certain extent, instead of finding the average value of the reference data xi, the center of the group range can be used as the x-coordinate of the representative data.

[0055] The trend analysis unit 140 analyzes the trend of the representative data in the plurality of groups with respect to the reference data. Specifically, the trend analysis unit 140 finds the correlation between the plurality of representative data and the reference data. Figure 2 (D) indicates Figure 2 (A)~ Figure 2 (C) is an example of trend analysis of activity data. The trend analysis unit 140 performs regression analysis on the representative data R1 to R3 of each of Groups 1 to 3. The illustrated regression line L is a line represented by the regression equation obtained as a result of the regression analysis.

[0056] The regression line L0 shown here as a comparative example was obtained through regression analysis of all activity data and is independent of group. Comparing these two regression lines, L0 and L, reveals that the slope of regression line L0 is approximately zero, indicating no significant trend relative to changes in the baseline pace. In contrast, regression line L has a negative slope, indicating that as the pace increases from right to left in the figure, the pelvic rotation angle, which is the measured data, increases accordingly. As described above, this embodiment allows for the identification of trends not captured by the overall regression analysis (L0), enabling more accurate exercise analysis and improvement guidance.

[0057] The reason for the aforementioned difference between regression line L0 and regression line L is that, in the simple regression analysis used to solve for L0, the influence of group 1, to which the majority (approximately 95.4%) of the activity data belongs, is dominant, and thus the influence of groups 2 and 3 is barely apparent. In this regard, in the present embodiment, representative data for each group is first generated and then regression analysis is performed on this representative data, thereby also not neglecting the tendencies of groups 2 and 3, which have smaller amounts of data. In particular, in the analysis of sports such as running, when performing exercises that deviate from the normal range, such as running at a faster / slower pace than normal or running a longer / shorter distance than normal, often results in a disordered posture or a heavy burden on various parts of the body. Therefore, it is extremely important to understand the tendencies of these groups that deviate from the normal range and incorporate them into improvement guidance.

[0058] In the above example, the regression analysis performed by the trend analysis unit 140 is a linear regression analysis for finding a regression line. However, a nonlinear regression analysis for finding a regression curve using an appropriate nonlinear model may be performed.

[0059] The guidance information generating unit 150 generates guidance information for improving exercise movements based on the analysis performed by the tendency analyzing unit 140. Figure 2 In the example of (D), although the pelvic rotation angle increases with the increase in pace, if the pelvic rotation should be further increased in order to run faster (i.e., the pelvic rotation angle should be further increased), Figure 2 In the case of the absolute value of the slope of the straight line L of (D), guidance information that makes the rotation of the pelvis highly conscious can be generated, especially when the pace is fast.

[0060] The display control unit 160 displays the analysis results obtained by the trend analysis unit 140 and the guidance information generated by the guidance information generation unit 150 on the display device 30 used by the user. When displaying the analysis results of the trend analysis unit 140, the display control unit 160 displays the regression line L between the plurality of representative data R1 to representative data R3 and the reference data. For example, Figure 2 The content of (D) is analyzed and the guidance information is displayed together. Figure 2 The regression line L0 as a comparative example is shown in (D). In addition, instead of displaying the points of each activity data that are the basis of the representative data R1 to R3, only the representative data R1 to R3 and the regression line L may be displayed.

[0061] The display control unit 160 may display the analysis results of the trend analysis unit 140 in a visually different form for each group. For example, the display control unit 160 may change the display mode for each group. Figure 2 In (D), the color or shape of each point representing the data R1 to the data R3 is shown. Furthermore, when displaying the points of each activity data that is the basis of each representative data R1 to the data R3, these points can be displayed in different colors or shapes for each group. Figure 2 As shown in (D), labeling each group with different labels such as "normal," "fast," and "slow" also includes displaying in different forms. As described above, by changing the display form for each group, there is an advantage in being able to emphasize the group that particularly requires improvement.

[0062] Figures 3 to 5Specific display examples are shown for the analysis results obtained by the tendency analysis unit 140 and the guidance information generated by the guidance information generation unit 150. These three display examples 30A, 30B, and 30C show images displayed on the display screen of the display device 30 used by the user.

[0063] Figure 3 The screen 30A shown is the main screen for the user to obtain analysis results and guidance information for private lessons. The user can switch to the corresponding screen 30B ( Figure 4 )、Image 30C( Figure 5 ). Button 31B is labeled "Run Faster," and allows users to switch to target screen 30B and confirm the analysis results using the running pace as the benchmark data and the coaching information derived therefrom. Button 31C is labeled "Long Distance Running," and allows users to switch to target screen 30C and confirm the analysis results using the running distance as the benchmark data and the coaching information derived therefrom.

[0064] In the analysis result display area at the top of the screen 30B that is transitioned from the "Run Faster" button 31B, the measured data of the issues to be improved identified in the analysis using the running pace as the reference data is displayed as the "focus score". In the example shown in the figure, the analysis result of "left-right symmetry" related to the user's posture is displayed as the focus score. Figure 2 As in example (D), activity data consisting of the baseline data "Pace" and the measured data "Bilateral Symmetry (Posture)" is categorized into three groups based on pace: "Slow," "Normal," and "Fast." As shown by the regression curve formed by the representative data for each group, the "Bilateral Symmetry" score tends to decrease as the pace increases.

[0065] Therefore, in the guidance information display area at the bottom of screen 30B, guidance information for improvement is displayed. At the bottom of screen 30B, three buttons, "Analysis 1," "Analysis 2," and "Analysis 3," are arranged to display analysis results from different perspectives, as well as an "Improvement Plan" button that allows for more detailed guidance information. The example of "Bilateral Symmetry" shown in the figure shows the content of "Analysis 1." Pressing "Analysis 2" or "Analysis 3" displays measurement data other than bilateral symmetry, such as Figure 2 The analysis results and guidance information related to the "pelvic rotation angle" represented by (D) are shown. As described above, for the same benchmark data "pace", the analysis results and guidance information of different measurement data can be displayed, so the user can seek to improve the exercise action from various perspectives.

[0066] The analysis result display area at the top of the screen 30C that is transitioned from the "Long Distance Running" button 31C displays the measured data of the issues that need to be improved in the analysis using the distance during running as the reference data as the "focus score". In the example shown in the figure, the analysis result of "light ground contact" related to the landing impact is displayed as the focus score. Figure 2 As in example (D), activity data consisting of a group of baseline data "distance" and measured data "lightly burdened ground contact (landing impact)" is classified into two groups, "short" and "long," based on distance. In the illustrated example, the region encompassing the medium distance in the center of the graph is classified into the "long" group because there is no significant difference in attention scores between these medium and long distance regions, allowing them to be treated as the same group. As described above, the group classification unit 120 of this embodiment can perform optimal group classification for motion analysis by referring to the trends in the activity data.

[0067] As shown by the regression line formed by the representative data of these two groups, the score for "light ground contact" tends to decrease as the distance increases. Therefore, guidance for improving this situation is displayed in the guidance information display area at the bottom of screen 30C. Similar to screen 30B, the bottom of screen 30C features three buttons: "Analysis 1," "Analysis 2," and "Analysis 3," which display analysis results from different perspectives, and an "Improvement Plan" button for obtaining more detailed guidance information.

[0068] Through the display screen above, users can obtain analysis results related to various benchmark data such as "pace" and "distance", and can receive accurate suggestions on areas that need improvement, such as "left-right symmetry", "pelvic rotation angle", and "light ground contact".

[0069] Figure 6 The following is a flow chart of a motion analysis process performed by the motion analysis device 100. In the following description, "S" means a step.

[0070] In S10, the user performs measurement during exercise using the measurement device 20. As described above, the measurement device 20 measures both measurement data related to exercise motion and reference data that serves as a reference for group classification in the group classification unit 120.

[0071] In S20, the measurement device 20 transmits the measurement data (measurement data related to the exercise motion and reference data) to the motion analysis apparatus 100. In this case, when the exercise measurement in S10 is performed using multiple measurement devices 20, the measurement data of all measurement devices 20 are transmitted to the motion analysis apparatus 100. Furthermore, when multiple data are measured using a single measurement device 20, all measurement data are transmitted to the motion analysis apparatus 100.

[0072] In S30, the activity data recording unit 110 associates the measurement data related to the exercise action with the reference data and records them as activity data ( Figure 2 Here, in S30, activity data may be recorded in one or more exercises.

[0073] In S40, the group classification unit 120 classifies the activity data recorded in one or more exercises in S30 into a plurality of groups ( Figure 2 (B)).

[0074] In S50, the representative data generating unit 130 generates representative data ( Figure 2 (C)).

[0075] In S60, the trend analysis unit 140 analyzes the correlation between the representative data in the plurality of groups and the reference data, and obtains a relational expression ( Figure 2 (D)).

[0076] In S70 , the guidance information generating unit 150 generates guidance information for improving exercise movements based on the trend analysis in S60 .

[0077] In S80, the display control unit 160 sends the trend analysis result in S60 and the guidance information generated in S70 to the display device 30 used by the user and displays them on its display screen ( Figures 3 to 5 ).

[0078] As mentioned above, although this embodiment has been described based on its structure, in addition to the above-described contents, this embodiment has the following operations and effects, for example.

[0079] In this embodiment, by classifying a series of activity data recorded during exercise into multiple groups and analyzing the trends between the groups of the representative data, it is possible to appropriately analyze exercise actions based on the overall trend of exercise and generate guidance information for their improvement.

[0080] In this embodiment, exercise analysis can be performed based on activity data recorded during a single exercise or multiple exercises, so that improvement points that consistently appear during the recording period can be effectively discovered, and appropriate improvement guidance can be provided.

[0081] Furthermore, the regression curve L generated by the trend analysis unit 140 in this embodiment not only allows for accurate understanding of trends in groups with less data, but also allows for pre-estimation of areas where data is not yet available, effectively utilizing this information for goal setting and exercise guidance. For example, if the goal is to complete a full marathon of 42.195 km, even if the current maximum running distance is 30 km, using the regression curve L allows for estimation of measured data for the remaining 30 km to 42.195 km, allowing for the selection of hypothetical tasks and exercise guidance to address these tasks before they occur. Furthermore, if running a full marathon within the target time of 4 hours requires running 1 km at a pace faster than 5 minutes, but if data at this fast pace is currently unavailable or significantly scarce, training at a faster pace may be recommended to achieve the goal. In this case, using the regression curve L related to pace, as with distance, allows for the selection of hypothetical tasks and exercise guidance even when data for the faster pace is not available.

[0082] The present invention has been described above based on the embodiments. The embodiments are merely examples, and those skilled in the art will appreciate that various modifications may be made to the combinations of these components or processing steps, and that such modifications are also within the scope of the present invention.

[0083] In the present embodiment, pace is used as the benchmark data for group classification, but one or more benchmark data other than pace can also be used. As also illustrated in the present embodiment, benchmark data such as time, number of steps, distance, position, speed, acceleration, altitude, inclination, brightness, temperature, humidity, heartbeat and other biological signals can be used. For example, if information on altitude or inclination is used as benchmark data, it is possible to effectively discover problems in sports movements that occur at a specific altitude or inclination. Moreover, if biological signals such as heartbeat are used as benchmark data, it is possible to effectively discover problems in sports movements that occur according to the user's physical condition. Furthermore, if multiple types of benchmark data are used, it is possible to discover the essential issues from the perspectives of multiple angles as described above.

[0084] In this embodiment, the group classification in the group classification unit 120 is performed based on statistical values ​​such as the mean value μ and the standard deviation σ, but the group classification may be performed without using the statistical values. Figure 2 In (B), the groups can be formed within the same predetermined range, for example, at intervals of 100 sec / km.

[0085] In this embodiment, running is used as an example of exercise, but the present invention can also be applied to other sports, such as various land athletics, swimming, gymnastics, training or exercise in road cycling, dance, and ball games such as football.

[0086] Furthermore, the functional configurations of the various devices described in the embodiments may be implemented using hardware resources, software resources, or a combination of hardware and software resources. Hardware resources include processors, read-only memory (ROM), random access memory (RAM), and other large-scale integrated circuits (LSI). Software resources include operating systems, applications, and other programs, or cloud services.

[0087] Industrial applicability

[0088] The present invention relates to a motion analysis device for analyzing motion movements.

Claims

1. A motion analysis device, comprising: a group classification unit that classifies activity data recording a plurality of measurement data related to exercise movements and a plurality of predetermined reference data that changes during exercise into a plurality of groups based on an average value and a standard deviation of the plurality of reference data, wherein the plurality of groups include a group in which the reference data is within a normal range that differs from the average value by at least one standard deviation and a group in which the reference data is outside the normal range; a representative data generating unit for generating representative data of the activity data in each group; as well as The trend analysis unit analyzes a trend of the representative data in the plurality of groups with respect to the reference data.

2. The motion analysis device according to claim 1, wherein The trend analysis unit obtains a plurality of relationship expressions that hold true between the representative data and the reference data.

3. The motion analysis device according to claim 1 or 2, wherein The group classification section classifies the activity data recorded in a plurality of sports into the groups.

4. The motion analysis device according to claim 1 or 2, comprising: The guidance information generating unit generates guidance information for improving exercise movements based on the analysis performed by the tendency analyzing unit.

5. The motion analysis device according to claim 1 or 2, comprising: The display control unit displays the analysis result obtained by the trend analysis unit.

6. The motion analysis device according to claim 5, wherein The display control unit displays a plurality of relational expressions established between the representative data and the reference data.

7. The motion analysis device according to claim 5, wherein The display control unit displays the analysis result obtained by the tendency analysis unit in a visually different form for each of the groups.

8. A motion analysis method comprising: a group classification step of classifying activity data recording a plurality of measurement data related to exercise movements and a plurality of predetermined baseline data that changes during exercise into a plurality of groups based on an average value and a standard deviation of the plurality of baseline data, wherein the plurality of groups include a group in which the baseline data is within a normal range that differs from the average value by at least one standard deviation and a group in which the baseline data is outside the normal range; a representative data generating step of generating representative data of the activity data in each group; as well as The trend analysis step is to analyze the trend of the representative data in the plurality of groups relative to the reference data.

9. A computer-readable storage medium storing a motion analysis program for causing a computer to execute: a group classification step of classifying activity data recording a plurality of measurement data related to exercise movements and a plurality of predetermined baseline data that changes during exercise into a plurality of groups based on an average value and a standard deviation of the plurality of baseline data, wherein the plurality of groups include a group in which the baseline data is within a normal range that differs from the average value by at least one standard deviation and a group in which the baseline data is outside the normal range; a representative data generating step of generating representative data of the activity data in each group; as well as The trend analysis step is to analyze the trend of the representative data in the plurality of groups relative to the reference data.

Images