Apparatus, method, and program for evaluating performance

Abstract

To provide a motion evaluation device that can quantitatively evaluate the second motion by comparing the first motion of a first player with the second motion of a second player.SOLUTION: There is provided a device to evaluate the second motion which is the motion of a second player on the basis of the first motion which is the motion of a first player. The device comprises: an acquisition part that acquires a second motion value obtained by measuring the second motion; an extraction part that extracts the second cooperative motion data showing the characteristic behavior of the second motion by performing singular value decomposition of the second motion value; a first cooperative motion data storage part which stores the first cooperative motion data showing the characteristic behavior of the first motion; a comparison part that obtains the first comparison result 31 obtained by comparing the first cooperative operation data with the second cooperative operation data; and an output part that outputs the first comparison result 31 to a display device 12.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to an operation evaluation apparatus, method, and program.

Background Art

[0002] Conventionally, various operation analysis apparatuses used for analyzing operations such as a golf swing have been proposed (for example, see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, due to the increasing health consciousness, various exercises and the like have been widely carried out. A general exercise lesson is such that an instructor shows a model operation and the trainee simulates it. On the other hand, the evaluation of the trainee's operation has been performed solely based on the personal sense of the instructor, which is not quantitative and it has been difficult to grasp the points for improvement of the operation.

[0005] The present invention has been devised in view of the above actual situation, and a main object thereof is to provide an apparatus capable of quantitatively evaluating a second operation by comparing a first operation of a first player with a second operation of a second player.

Means for Solving the Problems

[0006] The present invention relates to an apparatus for evaluating a second action, which is the action of a second player, based on a first action, which is the action of a first player, and includes: an acquisition unit that acquires a second action value measured for the second action; an extraction unit that extracts second coordinated action data showing characteristic behavior of the second action by singular value decomposition of the second action value; a first coordinated action data storage unit that stores first coordinated action data showing characteristic behavior of the first action; a comparison unit that acquires a first comparison result obtained by comparing the first coordinated action data and the second coordinated action data; and an output unit that outputs the first comparison result to a display device. [Effects of the Invention]

[0007] The operation evaluation device of the present invention makes it possible to quantitatively evaluate the second operation by comparing the first operation of the first player with the second operation of the second player. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing a motion evaluation system including the motion evaluation device of this embodiment. [Figure 2] This is a block diagram of the operation evaluation device of this embodiment. [Figure 3] This flowchart shows the processing procedure for the operation evaluation method of this embodiment. [Figure 4] This diagram illustrates the positional data of each body part of the second player. (a) shows the positional data viewed from the X-axis direction (front), and (b) shows the positional data viewed from the Y-axis direction (side). [Figure 5] This graph compares the size of the spatial basis for the first cooperative action data with the size of the spatial basis for the second cooperative action data. [Figure 6] This figure shows an example of the first comparison result displayed on the display device. [Figure 7] This flowchart shows the processing procedure for the operation evaluation method of another embodiment of the present invention. [Figure 8]This graph compares the size of the spatial basis for the first cooperative action data with the size of the spatial basis for the third cooperative action data. [Figure 9] This figure shows an example of the second comparison result displayed on the display device. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described below with reference to the drawings. It should be understood that the drawings contain exaggerations and representations that differ from the actual dimensional ratios of the structures in order to aid in understanding the content of the invention. Furthermore, the same or common elements are denoted by the same reference numerals throughout each embodiment, and redundant explanations are omitted. Moreover, the specific configurations shown in the embodiments and drawings are for the purpose of understanding the content of the present invention, and the present invention is not limited to the specific configurations shown in the drawings.

[0010] [Motion Analysis System] In the operation evaluation system (operation evaluation device) of this embodiment, the second operation, which is the operation of the second player, is evaluated based on the first operation, which is the operation of the first player. Figure 1 is a conceptual diagram showing the operation evaluation system 1, including the operation evaluation device 2 of this embodiment.

[0011] The actions (first and second actions) are not particularly limited as long as they are actions performed by the player (human body). Examples of actions include the actions of a player performing exercises (exercise actions) and the actions of a player performing sports (sports actions). The actions in this embodiment include exercise actions. These exercise actions include, for example, actions in gymnastics, dance, yoga, and tai chi. Gymnastics actions are given as an example of exercise actions in this embodiment.

[0012] The first player (not shown) is not particularly limited as long as it is a player that performs the first action to be compared with the second action. An example of the first player in this embodiment is an instructor who gives an exercise lesson. In this case, the first action in this embodiment is a model action of the second action performed by the second player P2.

[0013] The first player is not limited to an instructor; for example, they may be a more skilled (advanced) exercise performer compared to the second player P2, or they may be a player competing against the second player P2 in terms of the quality of their exercise performance.

[0014] The second player P2 is a player whose second movement is evaluated by the movement evaluation system 1 (movement evaluation device 2). In this embodiment, the second player P2 is exemplified as a participant in an exercise movement lesson (for example, a beginner or intermediate level participant). In this case, the second movement is a movement that simulates the first movement performed by the first player (instructor). Note that the second player P2 is not limited to a participant; for example, it may be a player competing with the first player in terms of the quality of their exercise movement.

[0015] The operation evaluation system 1 of this embodiment comprises an operation evaluation device 2 and a measuring device 3. The operation evaluation system 1 (operation evaluation device 2) is used to perform the operation evaluation method described later.

[0016] [Measuring device] The measuring device 3 is for measuring the second action performed by the second player P2. In this embodiment, the measuring device 3 is configured as a motion capture system 3A. In this embodiment, the measuring device 3 (motion capture system 3A) is also used to measure the first action performed by the first player. Note that the measuring device 3 is not limited to the motion capture system 3A, and various devices can be used as long as they can measure both the first and second actions.

[0017] The motion capture system 3A of this embodiment includes multiple cameras 4. These cameras 4 are positioned to capture the second action performed by the second player P2 from various directions, enabling three-dimensional measurement of the second action. For example, a three-dimensional motion analysis system manufactured by VICON can be suitably employed in the motion capture system 3A.

[0018] The measuring device 3 is connected to the operation evaluation device 2 via a wired or wireless communication line (not shown) so as to be able to communicate. This allows the measured values ​​measured by the measuring device 3 to be transmitted to the operation evaluation device 2. However, the transmission of measured values ​​is not limited to such a communication line; for example, they may be transmitted via a communication network. Communication networks include, for example, WANs (Wide Area Networks) and LANs (Local Area Networks). Furthermore, if the measuring device 3 is not connected to the operation evaluation device 2, position data may be input to the operation evaluation device 2 via a storage medium such as flash memory (not shown), for example.

[0019] [Operation evaluation device] The operation evaluation device 2 is composed of, for example, a computer 5. Examples of computer 5 include a desktop computer, a notebook computer, a tablet computer, a smartphone, and a cloud server. In this embodiment, a desktop computer is used as computer 5. Figure 2 is a block diagram of the operation evaluation device 2 in this embodiment.

[0020] The operation evaluation device 2 of this embodiment is configured to include, for example, an input device 11, a display device 12, a communication device 13, and a processing unit 14.

[0021] [Input devices and display devices] The input device 11 may include, for example, the keyboard 11a or mouse 11b shown in Figure 1. The display device 12 may include, for example, the display 12a shown in Figure 1.

[0022] [communication equipment] As shown in Figure 2, the communication device 13 of this embodiment is connected to the measurement device 3 (motion capture system 3A) via a communication line 23 so as to be able to communicate with it. This allows the communication device 13 (motion evaluation device 2) to acquire (receive) the measured values ​​of the measurement device 3 via the communication line 23. Furthermore, the communication device 13 (motion evaluation device 2) of this embodiment can, for example, transmit signals to the measurement device 3 via the communication line to control the measurement device 3.

[0023] [Arithmetic Processing Unit] The arithmetic processing unit 14 of this embodiment is configured to include, for example, an arithmetic unit (CPU) 15 that performs various calculations, a storage unit 16 that stores data, programs, etc., and a working memory 17.

[0024] [Storage] The storage unit 16 is a non-volatile information storage device, such as a magnetic disk, optical disk, or SSD. The storage unit 16 in this embodiment includes a data unit 18 and a program unit 19.

[0025] [Data Section] The data unit 18 stores data (information) necessary for evaluating the second operation by the second player P2 shown in Figure 1, as well as evaluation results, etc. In this embodiment, the data unit 18 includes a first operation value storage unit 18a, a second operation value input unit 18b, a cooperative operation data input unit 18c, and a comparison result input unit 18d. Note that the data unit 18 is not limited to this configuration, and some of these may be omitted, or a data unit for storing other data may be included. Details of the data input to these data units 18 will be described later.

[0026] [Programming Department] The program unit 19 is a program (computer program) necessary for evaluating the second action performed by the second player P2 as shown in Figure 1. The program unit (program) 19 is executed by the arithmetic unit 15, thereby enabling the computer 5 to function as a specific means.

[0027] The program unit 19 of this embodiment includes an acquisition unit 19a, an extraction unit 19b, a comparison unit 19c, an output unit 19d, and an evaluation unit 19e. However, the program unit 19 is not limited to this configuration and may include other program units with different functions. Details of the functions of these program units 19 will be described later.

[0028] [Operation Evaluation Method (First Embodiment)] Next, the operation evaluation method of this embodiment will be described. In the operation evaluation method of this embodiment, the second operation, which is the operation of the second player P2 shown in Figure 1, is evaluated based on the first operation, which is the operation of the first player. Figure 3 is a flowchart showing the processing procedure of the operation evaluation method of this embodiment. In this embodiment, each step of the operation evaluation method is executed by the operation evaluation device 2 (computer 5) shown in Figures 1 and 2.

[0029] [Get the second action value of the second player] In the motion evaluation method of this embodiment, first, a second motion value is obtained by measuring the second motion of the second player P2 shown in Figure 1 (step S1). The second motion value can be obtained as appropriate, as long as it can quantitatively represent the second motion. The second motion value in this embodiment includes positional data of each part of the second player P2's body.

[0030] In step S1 of this embodiment, first, the acquisition unit 19a included in the program unit 19 shown in Figure 2 is loaded into the working memory 17. The acquisition unit 19a is a program for acquiring a second operating value. When this acquisition unit 19a is executed by the calculation unit 15, the computer 5 can be made to function as a means for acquiring the second operating value.

[0031] In step S1 of this embodiment, first, the second action performed by the second player P2 shown in Figure 1 is measured. A measurement device 3 (motion capture system 3A) is used to measure the second action in this embodiment. The start and end of the measurement by the measurement device 3 may be controlled by the motion evaluation device 2 (computer 5) or by an operator or the like.

[0032] In this embodiment, prior to measuring the second action, multiple markers (not shown) are attached to predetermined parts of the body of the second player P2, as shown in Figure 1. The multiple markers in this embodiment are, for example, formed as light-reflective spheres. With such markers, the movements of the second player P2's body can be accurately captured by multiple cameras 4.

[0033] The markers in this embodiment (not shown) are attached to various parts of the body of the second player P2 (e.g., head, wrists, fingertips, elbows, shoulders, waist, knees, ankles, and toes, etc.), similar to those in Patent Document 1 mentioned above. In this embodiment, 53 markers are attached, but the embodiment is not limited to this configuration. For example, some markers may be omitted or other markers may be added depending on the body movements caused by the second action. Each marker is assigned a predetermined identification number (e.g., No. 1 to No. 53).

[0034] Next, from the start to the end of the second operation by the second player P2 shown in Figure 1, the second operation is continuously captured by multiple cameras 4. This results in the acquisition of a series of images (video) containing multiple images of the second operation captured continuously in time (multiple time points). The second operation is captured at time intervals corresponding to a predetermined sampling frequency. The sampling frequency can be set as appropriate; for example, it can be set to 500Hz.

[0035] Each image in the image sequence (video) is processed by, for example, image processing software included in the measurement device 3 (motion capture system 3A). This allows the second motion value in the time series of the second motion to be obtained.

[0036] In this embodiment, position data of multiple markers (not shown) are acquired as second motion values. These position data allow for the identification of the positions (position data of each body part) of the second player P2 to which the multiple markers are attached. Note that the position data of multiple markers (53 markers in this example) may be aggregated into the position data of some markers (23 markers in this example) by, for example, averaging the joint centers of the body parts 20 identified by these markers. This reduces the amount of position data and suppresses the increase in the number of modes of the coordinate motion data obtained by singular value decomposition described later. Alternatively, even without such aggregation, the position data of markers attached to body parts of interest when evaluating the second motion may be limited to those of the multiple markers (53 markers in this example).

[0037] Figure 4 illustrates the positional data of each body part 20 of the second player P2. In Figure 4, (a) is the positional data viewed from the X-axis direction (front of the second player P2), and (b) is the positional data viewed from the Y-axis direction (side of the second player P2).

[0038] The positional data of each body part 20 of the second player P2 is acquired as three-dimensional (Cartesian coordinate system) coordinate values. The three-dimensional coordinate values ​​are determined, for example, in the front view of the second player P2 shown in Figure 4(a), based on the depth direction (X-axis direction), left-right direction (Y-axis direction), and height direction (Z-axis direction). The second motion value is acquired by determining the positional data of each body part 20 of the second player P2 in a time series.

[0039] The coordinate values ​​(position data) of each body part 20 of the second player P2 may be transformed (moved) so that, for example, the coordinate value of one body part 20 selected from multiple body parts 20 matches a predetermined reference position 21. This allows for the acquisition of second motion values ​​in which the coordinate values ​​of each body part 20 are aligned based on the reference position 21. Such second motion values ​​make it easy to compare them with motion values ​​of other players with different physiques (in this example, the first motion values ​​of the first player) or with motion values ​​of other players where the motion was measured at a different location. The reference position 21 is set, for example, at the origin of the X, Y, and Z axes, but is not particularly limited and can be set at any position. Also, the body part 20 to be matched to the reference position 21 is set to the left toe 20a, but is not particularly limited and can be selected at any body part 20.

[0040] The coordinate values ​​(position data) of each body part 20 of the second player P2 may be transformed, for example, so that the vector (not shown) from the position of the second player P2's right toe 20b to the position of the left toe 20a is parallel to the Y-axis direction (left-right direction). This allows for the acquisition of second motion values ​​with the second player P2's body orientation aligned, making it easier to compare them with, for example, the motion values ​​of other players (first motion values ​​of the first player).

[0041] The second action value is defined, for example, by the following equations (1) to (3). First, in equation (1), the position data (position vector relative to the origin) of the i-th marker (each body part 20) is identified at any time t from the first time to the Nth time. In this embodiment, the first time is the time when the second action begins. The Nth time is the time when the second action ends.

[0042]

number

[0043] In the above formula (1), x , i , , i , , , ,

[0048] , ,

[0046] , 23 , i ,

[0047] , ,

[0045] , , , , , , (t), y i (t) and z i (t) represent the coordinates in the X-axis direction, Y-axis direction, and Z-axis direction of the i-th marker (each body part 20) at time t. For this position data r i (t), it is created from the first time to the N-th time, and the matrix [r i arranged row by row is defined by the following formula (2).

[0044]

Number

[0045] In the matrix [r i of the above formula (2), it is a matrix of N rows and 3 columns. From the first row to the N-th row, in order along the time series, the three-dimensional coordinates r i (1), r i (2), ···, ri(N) are arranged. And the matrix [R] formed by arranging the 23 matrices [r1], [r2] ··· [r 23 for all markers (each body part 20) in this order in the column direction (horizontal direction) is defined by the following formula (3). The matrix [R] is a matrix of N rows and 69 (= 3 × 23) columns.

[0046]

Number

[0047] The matrix [R] of the above formula (3) is time-series behavior data representing the positions of 23 markers (each body part 20) from the first time to the N-th time in a time series. Note that the t-th row of the matrix [R] contains the three-dimensional coordinates of 23 markers (each body part 20) on the body of the second player P2 at the t-th time.

[0048] In the t-th row of this matrix [R], the position data (the posture of the second player P2) of each body part 20 of the second player P2 at the t-th time is represented. Such a matrix [R] can identify the second motion value.

[0049] In step S1 of this embodiment, a human body model (stick picture) M2 is set up, which includes bones 24 that connect multiple body parts 20 identified by matrix [R] as joints. These second motion values ​​and the human body model M2 are stored in the second motion value input unit 18b (shown in Figure 2).

[0050] [Extract second coordinated motion data from second motion value] Next, in the operation evaluation method of this embodiment, second coordinated operation data showing the characteristic behavior of the second operation is extracted (step S2). In step S2 of this embodiment, the second coordinated operation data is extracted by singular value decomposition of the second operation value.

[0051] In step S2 of this embodiment, first, the second operation value input to the second operation value input unit 18b shown in Figure 2 is loaded into the working memory 17. Furthermore, the extraction unit 19b included in the program unit 19 is loaded into the working memory 17. The extraction unit 19b is a program for extracting the second cooperative operation data. By executing this extraction unit 19b by the calculation unit 15, the computer 5 can be made to function as a means for extracting the second cooperative operation data.

[0052] In step S2 of this embodiment, prior to singular value decomposition, the matrix in equation (3) above is expanded. This expansion of the matrix is ​​intended to bring the reference point for singular value decomposition closer to the initial posture of the second movement (exercise movement).

[0053] The matrix extension first involves the coordinate values ​​(position vectors) of the initial posture of the i-th marker (20 body parts shown in Figure 4) r i (1) is obtained based on the above equation (1). Next, the obtained coordinate value (position vector) r i (1) A matrix ([r i (1)]) is created. At this time, [r i (1) All row-by-row elements are r i (1)

[0054] Next, the matrix above ([r i (1)]) is created for markers 1 to 23 (20 body parts), and the matrix ([R(1)]) formed by arranging them column by column is defined by the following equation (4).

[0055]

number

[0056] Furthermore, in order to increase the number of data points in the matrix and improve the resolution, the matrix in equation (3) above is inverted in the time series direction to form the matrix [R t ] is defined by the following equation (5). Then, the matrix [R] of the above equation (3) is given the matrix [R(1)] of the above equation (4), and the matrix [R] of the following equation (5). t The observation matrix [R] is a matrix formed by concatenating the two ]. a ] is defined by the following equation (6).

[0057]

number

number

[0058] Next, in step S2 of this embodiment, the time series data of the positions of the 23 markers (each body part 20) is obtained using the observation matrix [R] of the above equation (6). a The matrix [R0] represents the reference initial pose, and singular value decomposition is performed using the following equation (7). Note that the matrix [R0] is the observation matrix [R a It is defined as a matrix (6N rows x 69 columns = 3 x 23) obtained by taking the average in the time direction (row direction) of ] and arranging 6N of these averages in each row.

[0059]

number

[0060] Based on equation (7) above, the observation matrix [R a [R0] is the difference between [R0] and the initial pose matrix. a ]-[R0] is subjected to singular value decomposition, and for n=1,2,···,J (where J is an integer less than or equal to 69), U (n) , Γ (n) and V (n) You can obtain this.

[0061] Γ (n) This is the singular value of the nth mode (the nth one), and [R a This represents the proportion of the nth mode (the nth one) relative to ]-[R0]. (n) is the observation matrix [R a This is the left singular vector of ], with 6N rows and 69 columns (=3 × 23). (n) is the observation matrix [R a It is the right singular vector of ] and has 69 dimensions.

[0062] Left singular vector U (n) This is the right singular vector V (n) This is a time basis that represents the time information of [the vector]. On the other hand, the right singular vector V (n) This is a spatial basis that represents the positional information of each marker (each body part 20) on the body of the second player P2. This spatial basis is a vector that indicates the direction of the nth mode (nth) of movement relative to the reference initial posture matrix [R0]. By using the values ​​of such a spatial basis, it becomes possible to quantify the movement of the second player P2 (the movement of each body part 20) in the second movement for each mode.

[0063] In step S2 of this embodiment, the spatial basis (right singular vector V) obtained by singular value decomposition of the second operating value is obtained. (n) This data is extracted as second coordinated operation data, which shows the characteristic behavior of the second operation. This second coordinated operation data is stored in the coordinated operation data input unit 18c shown in Figure 2, for each mode (in this example, for each mode from the 1st to the 69th mode).

[0064] [Retrieve the first comparison result] Next, in the evaluation method of this embodiment, a first comparison result is obtained by comparing the first cooperative operation data with the second cooperative operation data (step S3).

[0065] The first coordinated action data is an index that shows the characteristic behavior of the first action (in this example, the exemplary action of the second action), which is the action of the first player not shown in the diagram. It is preferable that this first coordinated action data is extracted prior to the implementation of the evaluation method.

[0066] The first coordinated motion data can be extracted using the same procedure (steps S1 and S2) as the second coordinated motion data. To extract this first coordinated motion data, first motion values ​​are obtained by measuring the first motion. These first motion values ​​include position data for each part of the first player's body and are pre-stored in the first motion value storage unit 18a shown in Figure 2.

[0067] Next, the first coordinated action data can be extracted by singular value decomposition of the first operating value. This first coordinated action data includes a spatial basis (right singular vector V (n) ) is included. The first cooperative operation data of this embodiment is stored in advance in the cooperative operation data input unit 18c shown in Figure 2 for each mode (in this example, for each mode from the 1st mode to the 69th mode).

[0068] In step S3 of this embodiment, first, the first cooperative operation data and the second cooperative operation data input to the cooperative operation data input unit 18c shown in Figure 2 are loaded into the working memory 17. Furthermore, the comparison unit 19c included in the program unit 19 is loaded into the working memory 17. The comparison unit 19c is a program for obtaining a first comparison result by comparing the first cooperative operation data and the second cooperative operation data. When this comparison unit 19c is executed by the calculation unit 15, the computer 5 can function as a means for obtaining the first comparison result.

[0069] A comparison between the first cooperative operation data and the second cooperative operation data may be performed as appropriate. In this embodiment, it is preferable that the first cooperative operation data and the second cooperative operation data are compared for each of the multiple modes included in these cooperative operation data (in this example, the first mode to the 69th mode).

[0070] In this embodiment, the spatial basis (right singular vector V) of the first cooperative operation data is used. (n) ) and the spatial basis (right singular vector V) of the second cooperative action data. (n) The degree of similarity with ) is obtained for each of the multiple modes. By obtaining such a degree of similarity as the first comparison result, it becomes possible to quantitatively evaluate how similar the second action of the second player P2 (movements of each body part 20) shown in Figure 4 is to the first action of the first player (movements of each body part) which is not shown.

[0071] Similarity can be obtained as appropriate by comparing the first cooperative operation data and the second cooperative operation data. The similarity in this embodiment includes cosine similarity or correlation coefficient. The cosine similarity of the nth mode is obtained by the following equation (8).

[0072]

number

[0073] In equation (8) above, V' ins(n) This is the spatial basis (right singular vector V) of the first cooperative operation data in the nth mode. (n) ) is normalized by the x, y, and z axis components of each body part (i.e., V' ins_1(n) ~V' ins_23(n) (components of) V' 1(n) This is the spatial basis (right singular vector V) of the second cooperative operation data in the nth mode. (n) ) is normalized by the x, y, and z axis components of each body part (i.e., V 1_1(n) ~V 1_23(n) It is an ingredient of [the substance].

[0074] In equation (8) above, |V' ins(n) | represents the spatial basis (right singular vector V) of all parts and all components of the first coordinate operation data for the nth mode. (n) This is the norm in |V'. ins(n) | represents the spatial basis (right singular vector V) of the first cooperative action data. (n) This is the value obtained by summing the squares of the values ​​obtained by ) and taking the square root of that sum. Such a norm |V' ins(n) This makes it possible to quantify the magnitude of the first player's movements (20 movements of various body parts) in the first action, which is not illustrated.

[0075] In equation (8) above, |V' 1(n) | represents the spatial basis (right singular vector V) of all parts and all components of the second coordinate operation data for the nth mode. (n) This is the norm in |V'. 1(n) | represents the spatial basis (right singular vector V) of the second cooperative action data. (n) This is the value obtained by finding the sum of the squared values ​​of ) and taking the square root of that sum. Such a norm |V' 1(n) This makes it possible to quantify the magnitude of the movement of the second player P2 (the movement of each body part 20) in the second action shown in Figure 4.

[0076] In step S3 of this embodiment, the cosine similarity of equation (8) above is used to normalize the spatial basis of each part in the nth mode of the first cooperative operation data, and a vector (V') is obtained for all modes (in this example, the 1st mode to the 69th mode). ins(n) ) and the vector (V') obtained by normalizing the spatial basis of each part in the nth mode of the second coordinated motion data. 1(n) The similarity to the first body part can be calculated for each of the 20 body parts. By obtaining such cosine similarity as the first comparison result, the second movement, which simulates the first movement, can be evaluated.

[0077] Furthermore, the cosine similarity may be calculated based on the following formula (9) for multiple body parts selected from the 20 body parts.

[0078]

number

[0079] In equation (9) above, the cosine similarity of multiple body parts that make up a specific range of body parts (for example, the lower body) is added up from the cosine similarity of the body part specified by variable m1 to the cosine similarity of the body part specified by variable m2. The similarity within a specific range of body parts can be determined using this cosine similarity.

[0080] Correlation coefficient C (n) This is obtained using the following formula (10).

[0081]

number

[0082] In equation (9) above, for each nth mode (in this example, modes 1 to 69), a vector (V') is obtained by normalizing the spatial basis of each part of the first coordinated motion data. ins(n) The correlation coefficients between the first mode and the second coordinated motion data are calculated, along with the vector (V'1(n)) which is the normed spatial basis of each part of the second coordinated motion data. The average value of the correlation coefficients may be obtained by averaging the correlation coefficients of all these modes, or a weighted average value may be obtained by setting different weights for each mode.

[0083] Furthermore, the correlation coefficient may be calculated based on the following formula (11) for multiple body parts selected from the 20 body parts.

[0084]

number

[0085] In equation (11) above, the correlation coefficients of multiple body parts that make up a specific area of ​​the body (e.g., the lower body) are added together from the correlation coefficient of the body part specified by variable m1 to the correlation coefficient of the body part specified by variable m2. The similarity within a specific area of ​​the body can be determined by these correlation coefficients. By determining these correlation coefficients, the strength of the linear correlation between the first movement and the second movement can be determined, and the second movement, which simulates the first movement, can be evaluated.

[0086] In this embodiment, cosine similarity is obtained as the first comparison result, but the correlation coefficient may be obtained instead of cosine similarity, or both may be obtained. In addition, other parameters other than cosine similarity and the correlation coefficient may be obtained as the first comparison result. Furthermore, in this embodiment, the spatial vector norm was used to calculate the cosine similarity and the correlation coefficient, but the embodiment is not limited to this configuration. For example, the cosine similarity and the correlation coefficient may be calculated based on a spatial vector (right singular vector).

[0087] In this embodiment, a mode with a relatively low similarity may be selected from among multiple modes (in this example, modes 1 to 69). Such a mode may be identified as a mode that the second player P2 should focus on improving. This mode is obtained as the first comparison result.

[0088] The first comparison results may include, for example, a graph comparing the spatial vector norm of the first coordinated movement data with the spatial vector norm of the second coordinated movement data for each marker (20 body parts). Figure 5 is a graph 25 comparing the spatial vector norm of the first coordinated movement data with the spatial vector norm of the second coordinated movement data.

[0089] In Figure 5, the horizontal axis represents the body parts (markers) 20 shown in Figure 4. On this horizontal axis, "(L)" indicates the left side of the body part (marker), and "(R)" indicates the right side of the body part (marker). On the other hand, the vertical axis represents the spatial vector norm, which indicates the magnitude of movement of each body part (marker) 20. Also in Figure 5, "Instructor" represents the magnitude of movement of each body part of the first player (first coordinated movement data), and "Participant" represents the magnitude of movement of each body part of the second player (second coordinated movement data).

[0090] Graph 25 in Figure 5 allows for a comparison of the magnitude of movement by the first player and the magnitude of movement by the second player P2 for each body part 20. Note that Figure 5 shows graph 25 for the first mode. The first comparison results are stored in the comparison result input unit 18d shown in Figure 2.

[0091] [Show first comparison results] Next, in the evaluation method of this embodiment, the first comparison result is output to the display device 12 shown in Figures 1 and 2 (step S4). In step S4 of this embodiment, first, the first comparison result input to the comparison result input unit 18d shown in Figure 2 is read into the working memory 17. Furthermore, the output unit 19d included in the program unit 19 is read into the working memory 17. The output unit 19d is a program for outputting the first comparison result to the display device 12. By executing this output unit 19d by the calculation unit 15, the computer 5 can be made to function as a means for outputting the first comparison result.

[0092] Figure 6 shows an example of the first comparison result 31 displayed on the display device 12. In step S4 of this embodiment, the similarity 26 between the spatial basis of the first cooperative operation data and the spatial basis of the second cooperative operation data is displayed on the display device 12 as the first comparison result 31. In this embodiment, the cosine similarity is displayed as the similarity 26, but it may also be a correlation coefficient or other similarity measures. Furthermore, although the cosine similarity of the first mode is shown as the similarity 26 in this embodiment, it is not particularly limited, and cosine similarity may be displayed for each of multiple modes.

[0093] As described above, in the motion evaluation method (motion evaluation device 2) of this embodiment, second coordinated motion data showing the characteristic behavior of the second motion of the second player P2 (shown in Figure 1) is extracted, and this second coordinated motion data is compared with the first coordinated motion data of the first player. Then, the first comparison result 31 comparing the first motion and the second motion is output to the display device 12. This allows the second motion of the second player (in this example, the student) P2 to be quantitatively evaluated without depending on the perception of the person evaluating the second motion (in this example, the first player, who is the instructor). As a result, areas for improvement in the second motion of the second player P2 can be easily grasped, and for example, appropriate guidance on the second motion to the second player P2 becomes possible, and the second motion can be further improved (exercise motion can be established).

[0094] In step S4 of this embodiment, the display device 12 may display graph 25 (shown in Figure 5) obtained as the first comparison result 31. Details of graph 25 are as described above. Such graph 25 allows for a comparison of the magnitude of the movement of the first action and the magnitude of the movement of the second action for each body part of the first player and the second player P2, making it possible to identify the movements of each body part that should be improved in particular.

[0095] In this embodiment, it is preferable that the graph 25 can be switched for each of the multiple modes (mode 1 to mode 69) using, for example, a pull-down menu 27. This makes it possible to compare the magnitude of movement of each part of the body for each of the multiple modes.

[0096] In step S4 of this embodiment, the display device 12 may display the human body model M1 of the first player and the human body model M2 of the second player P2. These human body models M1 and M2 make it possible to visually compare the first action and the second action.

[0097] In this embodiment, the human body models M1 and M2 represent the first and second actions at four time points from the first to the Nth time point, but the embodiment is not limited to this configuration. For example, the first and second actions at one time point may be represented, or the first and second actions at five or more time points may be represented.

[0098] In this embodiment, for human body models M1 and M2, as shown in Figures 4(a) and (b), the coordinate values ​​of one body part 20 selected from a plurality of body parts 20 (in this example, the left toe 20a) are matched to the reference position 21. As a result, as shown in Figure 6, even if there is a difference in physique between the first player and the second player P2, or a discrepancy in the positions where the first and second movements were measured, it becomes easy to compare the first and second movements. In this embodiment, it is preferable that human body models M1 and M2 can be switched for each of the multiple modes (1st mode to 69th mode) using, for example, a pull-down menu 28. This makes it possible to visually compare the first and second movements for each of the multiple modes.

[0099] In step S4 of this embodiment, advice data 29 may be displayed on the display device 12. Such advice data 29 allows for a concrete understanding of areas for improvement in the second operation, enabling appropriate learning by the second player P1 (shown in Figure 1).

[0100] To create the advice data 29, first, in the graph 25 shown in Figure 5, markers (body parts) with a large difference between the size of the spatial base of the first coordinated movement data and the size of the spatial base of the second coordinated movement data are identified. Then, if these identified parts are concentrated, for example, in the lower body, advice data 29 is created that indicates increasing (or decreasing) the movement of the lower body. This allows for a more concrete understanding of areas for improvement in the second movement. Note that the creation of the advice data 29 is not limited to this method.

[0101] In step S4 of this embodiment, video data (not shown) of the first operation may be further output to the display device 12. This allows the second player P2 to learn the first operation that should be improved intensively, and to improve the second operation. Preferably, this video data is from a mode with relatively low similarity among multiple modes (in this example, the first to 69th modes). This allows the second player P2 to learn the first operation of the mode that should be improved intensively. The display device 12 of this embodiment displays a link 30 to the video data. This makes it easy to access the video data.

[0102] In step S4 of this embodiment, for example, in the graph 25 shown in Figure 5, video data (not shown) may be displayed that partially extracts the movements of various body parts where the difference between the size of the spatial base of the first coordinated movement data and the size of the spatial base of the second coordinated movement data is large. This allows the second player P2 to focus on confirming the first movement necessary for improving the second movement and to practice that movement intensively.

[0103] [Operation Evaluation Method (Second Embodiment)] In previous embodiments, the process of the motion evaluation method was completed when a first comparison result 31, obtained by comparing the first cooperative motion data and the second cooperative motion data, was output. However, the invention is not limited to this embodiment. For example, a second comparison result may be output, obtained by comparing the first cooperative motion data with third cooperative motion data that shows the characteristic behavior of the second player P2 (shown in Figure 1), which was learned by observing the first comparison result 31. Figure 7 is a flowchart showing the processing procedure of the motion evaluation method in another embodiment of the present invention.

[0104] [Evaluate the second action] In the operation evaluation method of this embodiment, prior to the output of the third cooperative operation data, the second operation performed by the second player P2 (shown in Figure 1) is evaluated to determine whether it is good or not (step S5). The second operation can be evaluated as appropriate. For example, the second operation may be evaluated based on whether the first comparison result 31 meets predetermined criteria. The criteria can be set as appropriate, for example, according to the skill level of the second player P2.

[0105] In step S5 of this embodiment, first, the first comparison result 31 (such as the similarity score 26 shown in Figure 6) input to the comparison result input unit 18d shown in Figure 2 is loaded into the working memory 17. Furthermore, the evaluation unit 19e included in the program unit 19 is loaded into the working memory 17. The evaluation unit 19e is a program for evaluating whether the second operation is good or not. By executing this evaluation unit 19e by the calculation unit 15, the computer 5 can be made to function as a means for evaluating the second operation.

[0106] In step S5 of this embodiment, the second operation is evaluated as good if the similarity score 26 (cosine similarity in this example), obtained as the first comparison result 31 shown in Figure 6, is equal to or greater than a predetermined threshold. The threshold can be set appropriately according to the skill level of the second player P2 (shown in Figure 2).

[0107] In step S5, if the similarity is above the threshold ("Yes" in step S5), the second action performed by the second player P2 (shown in Figure 1) has reached the required level of proficiency. Therefore, the series of processes for the action evaluation method is terminated. On the other hand, in step S5, if it is determined that the similarity is below the threshold ("No" in step S5), the second action performed by the second player P2 has not reached the required level of proficiency. In this case, the following steps S6 to S9 are performed.

[0108] [Extract data for the third cooperative operation] Next, in the operation evaluation method of this embodiment, third cooperative operation data is extracted (step S6) that shows the characteristic behavior of the operation of the second player P2 (shown in Figure 1) which has learned by looking at the first comparison result 31 shown in Figure 6. The third cooperative operation data is extracted based on the same procedure as steps S1 to S2 of the previous embodiment. Therefore, the acquisition unit 19a and the extraction unit 19b included in the program unit 19 shown in Figure 2 are executed by the calculation unit 15, thereby enabling the computer 5 to function as a means for extracting the third cooperative operation data.

[0109] To extract the third cooperative action data, first, the third action value is obtained, which is the action of the second player P2 (shown in Figure 1) that learned from the first comparison result 31 shown in Figure 6. Then, the third cooperative action data is extracted by singular value decomposition of the third action value. This third cooperative action data includes the spatial basis (right singular vector V (n) ) is included. The third cooperative operation data is stored in the cooperative operation data input unit 18c shown in Figure 2.

[0110] [Second comparison results obtained] Next, in the operation evaluation method of this embodiment, a second comparison result is obtained by comparing the first cooperative operation data and the third cooperative operation data (step S7). In step S7 of this embodiment, first, the first cooperative operation data and the third cooperative operation data input to the cooperative operation data input unit 18c shown in Figure 2 are loaded into the working memory 17. Furthermore, the comparison unit 19c included in the program unit 19 is loaded into the working memory 17. The comparison unit 19c is a program for obtaining a second comparison result by comparing the first cooperative operation data and the third cooperative operation data. By executing this comparison unit 19c by the calculation unit 15, the computer 5 can be made to function as a means for obtaining the second comparison result.

[0111] The second comparison result of this embodiment includes the similarity (cosine similarity in this example) between the spatial basis of the first coordinated motion data and the spatial basis of the third coordinated motion data. Furthermore, the second comparison result may include, for example, a graph comparing the size of the spatial basis of the first coordinated motion data and the size of the spatial basis of the third coordinated motion data for each marker (each body part 20). Figure 8 is a graph 34 comparing the size of the spatial basis of the first coordinated motion data and the size of the spatial basis of the third coordinated motion data.

[0112] In Figure 8, the horizontal axis represents each body part (marker) 20, similar to graph 25 in Figure 5. The vertical axis represents the spatial vector norm, indicating the magnitude of movement of each body part (marker) 20. In Figure 8, "Instructor" shows the magnitude of movement of each body part of the first player (first cooperative motion data). "Before" shows the magnitude of movement of each body part of the second player (second cooperative motion data) before learning. "After" shows the magnitude of movement of each body part of the second player (third cooperative motion data) after learning.

[0113] Graph 34 in Figure 8 makes it possible to compare the magnitude of the first movement performed by the first player with the magnitude of the movement performed by the second player P2 after learning, for each body part 20. Furthermore, since Graph 34 also shows the magnitude of the second movement performed by the second player P2 before learning, it is possible to compare the changes in the second player P2's movements before and after learning for each body part 20. The second comparison results are stored in the comparison result input unit 18d shown in Figure 2.

[0114] [Show second comparison results] Next, in the operation evaluation method of this embodiment, the second comparison result is output to the display device 12 shown in Figure 1 (step S8). In step S8 of this embodiment, first, the second comparison result input to the comparison result input unit 18d shown in Figure 2 is read into the working memory 17. Furthermore, the output unit 19d included in the program unit 19 is read into the working memory 17. The output unit 19d is a program for outputting the second comparison result to the display device 12. By executing this output unit 19d by the calculation unit 15, the computer 5 can be made to function as a means for outputting the second comparison result.

[0115] Figure 9 shows an example of the second comparison result 32 displayed on the display device 12. In step S8 of this embodiment, the similarity 33 between the spatial basis of the first cooperative operation data and the spatial basis of the third cooperative operation data is displayed on the display device 12 as the second comparison result 32. In this embodiment, the cosine similarity is displayed as the similarity 33, but it may be a correlation coefficient or other similarity measures.

[0116] Thus, in the operation evaluation method (operation evaluation device 2) of this embodiment, the second comparison result 32 is displayed on the display device 12, making it possible to quantitatively evaluate the third operation of the second player P2, which has learned by looking at the first comparison result 31 shown in Figure 6. As a result, the improvement effect of the third operation can be easily grasped, which enables, for example, appropriate guidance of the third operation to the second player P2 and further improvement of the third operation.

[0117] The similarity score of 26 between the spatial basis of the first cooperative action data and the spatial basis of the second cooperative action data may also be displayed. This allows for a comparison of the similarity score of 26 before learning and the similarity score of 33 after learning, enabling an accurate understanding of the improvement effect of the third action.

[0118] In step S8 of this embodiment, the display device 12 may display the graph 34 obtained as the second comparison result 32. Details of the graph 34 are as described above. Such a graph 34 allows for a comparison of the magnitude of the movements of the first to third movements for each body part of the first player and the second player P2, and the improvement effect of the third movement can be accurately grasped.

[0119] In this embodiment, it is preferable that the graph 34 can be switched for each of the multiple modes (mode 1 to mode 69) using, for example, a pull-down menu 35. This makes it possible to compare the magnitude of movement of each body part for each of the multiple modes, and to grasp the improvement effect.

[0120] In step S8 of this embodiment, the display device 12 may display the human body model M1 of the first player and the human body model M2 of the second player. By using these human body models M1 and M2, it becomes possible to visually compare the first action and the third action and grasp the improvement effect. Preferably, the human body models M1 and M2 can be switched between multiple modes (1st mode to 69th mode) using a pull-down menu 36 or the like.

[0121] In step S4 of this embodiment, advice data 29 may be displayed on the display device 12. Details of the advice data 29 are as described above. In this embodiment, if the similarity 33 is good in all modes, the suggestion of areas for improvement may be omitted, or a message indicating that it is good may be displayed.

[0122] [Evaluate the third action] Next, in the operation evaluation method of this embodiment, the third operation performed by the second player P2 (shown in Figure 1) is evaluated as to whether it is good or bad (step S9). The evaluation of the third operation is based on the same procedure as step S5 of the previous embodiment, and the quality of the third operation is evaluated. If it is determined that the third operation is not good ("No" in step S9), steps S6 to S9 are performed again.

[0123] Thus, in this embodiment of the motion evaluation method (motion evaluation device 2), repeated learning (practice) is performed by the second player P2 (shown in Figure 1) until the required level of proficiency is reached. This makes it possible for the motion evaluation method to ensure that the second player P2 improves (establishes) the exercise movements.

[0124] Although particularly preferred embodiments of the present invention have been described in detail above, the present invention is not limited to the illustrated embodiments and can be implemented in various modified forms.

[0125] [Note] The present invention includes the following embodiments.

[0126] [Invention 1] A device for evaluating a second action, which is the action of a second player, based on a first action, which is the action of a first player, An acquisition unit that acquires a second operation value measured during the second operation, An extraction unit extracts second coordinated operation data that shows the characteristic behavior of the second operation by performing singular value decomposition on the second operation value, A first cooperative operation data storage unit stores first cooperative operation data that exhibits characteristic behavior of the first operation, A comparison unit that obtains a first comparison result by comparing the first coordinated operation data and the second coordinated operation data, Includes an output unit that outputs the first comparison result to a display device, Performance evaluation device. [2nd Invention] The operation evaluation device according to the present invention 1, wherein the first operation is a model operation of the second operation. [Invention 3] The first motion value obtained by measuring the first motion includes position data of each part of the first player's body, The motion evaluation device according to the present invention 1 or 2, wherein the second motion value includes position data of each body part of the second player. [4th Invention] The first coordinated motion data includes a spatial basis obtained by singular value decomposition of the first motion values ​​measured for the first motion, The motion evaluation device according to any one of inventions 1 to 3, wherein the second coordinated motion data includes a spatial basis obtained by singular value decomposition of the second motion value. [5th ​​Invention] The comparison unit obtains the degree of similarity between the spatial basis of the first coordinated motion data and the spatial basis of the second coordinated motion data as the first comparison result, in the motion evaluation device according to the present invention, as described in the fourth invention. [Invention 6] The operation evaluation apparatus according to the present invention, wherein the similarity includes cosine similarity or correlation coefficient. [7th Invention] The similarity is obtained for each of the multiple modes included in the first coordinated operation data and the second coordinated operation data, according to the operation evaluation device according to item 5 or 6 of the present invention. [8th Invention] The comparison unit selects a mode from among the multiple modes in which the similarity is relatively small. The operation evaluation device according to the present invention, wherein the output unit further outputs video data of the first operation in the selected mode. [Invention 9] The comparison unit further obtains a second comparison result by comparing the first cooperative operation data with a third cooperative operation data that shows characteristic behavior of the second player's operation learned from the first comparison result, The output unit further outputs the second comparison result, wherein the operation evaluation device is according to any one of claims 1 to 8 of the present invention. [Invention 10] The motion evaluation device according to any one of claims 1 to 9 of the present invention, wherein the first and second actions include exercise actions. [Invention 11] A method for evaluating a second action, which is the action of a second player, based on a first action, which is the action of a first player, The computer obtains a second operation value measured from the second operation, A step of extracting second coordinated operation data that shows the characteristic behavior of the second operation by singular value decomposition of the second operation value, A step of obtaining a first comparison result by comparing first coordinated operation data showing characteristic behavior of the first operation with second coordinated operation data, The process involves outputting the first comparison result to a display device. Performance evaluation method. [Invention 12] A computer program for evaluating a second action, which is the action of a second player, based on a first action, which is the action of a first player, Computers, Means for obtaining a second operation value measured during the second operation, A means for extracting second coordinated operation data that shows the characteristic behavior of the second operation by performing singular value decomposition of the second operation value, Means for obtaining a first comparison result by comparing first coordinated operation data showing characteristic behavior of the first operation with second coordinated operation data, This is configured to function as a means for outputting the first comparison result to a display device. Computer program. [Explanation of symbols]

[0127] 12 Display device 31 First comparison result

Claims

1. A device for evaluating a second action, which is the action of a second player, based on a first action, which is the action of a first player, An acquisition unit that acquires a second operation value measured during the second operation, An extraction unit extracts second coordinated operation data that shows the characteristic behavior of the second operation by singular value decomposition of the second operation value, A first cooperative operation data storage unit stores first cooperative operation data that shows characteristic behavior of the first operation, A comparison unit that obtains a first comparison result obtained by comparing the first coordinated operation data and the second coordinated operation data, It includes an output unit that outputs the first comparison result to a display device, The acquisition unit further acquires a third operation value, which is the operation of the second player learned by observing the first comparison result, The extraction unit further extracts third coordinated operation data that shows characteristic behavior of the third operation by performing singular value decomposition on the third operation value. The comparison unit further obtains a second comparison result obtained by comparing the first coordinated operation data and the third coordinated operation data. The output unit further outputs the second comparison result, The first coordinated motion data includes a spatial basis obtained by singular value decomposition of the first motion values ​​measured for the first motion, The second coordinated operation data includes a spatial basis obtained by singular value decomposition of the second operation value, The third coordinated operation data includes a spatial basis obtained by singular value decomposition of the third operation value, The second comparison result includes a graph comparing the spatial vector norm obtained by normalizing the spatial basis of the first cooperative motion data, the spatial vector norm obtained by normalizing the spatial basis of the second cooperative motion data, and the spatial vector norm obtained by normalizing the spatial basis of the third cooperative motion data. A device for evaluating performance.

2. The operation evaluation device according to claim 1, wherein the first operation is a model operation of the second operation.

3. The first motion value obtained by measuring the first motion includes position data of each part of the first player's body, The motion evaluation device according to claim 1 or 2, wherein the second motion value includes position data of each body part of the second player.

4. The motion evaluation device according to claim 1 or 2, wherein the comparison unit obtains the degree of similarity between the spatial basis of the first coordinated motion data and the spatial basis of the second coordinated motion data as the first comparison result.

5. The operation evaluation apparatus according to claim 4, wherein the similarity includes cosine similarity or correlation coefficient.

6. The operation evaluation device according to claim 4, wherein the similarity is acquired for each of the multiple modes included in the first coordinated operation data and the second coordinated operation data.

7. The comparison unit selects a mode from among the plurality of modes in which the similarity is relatively small, The operation evaluation device according to claim 6, wherein the output unit further outputs video data of the first operation in the selected mode.

8. The motion evaluation device according to claim 1 or 2, wherein the first motion and the second motion include an exercise motion.

9. The first player is an instructor who gives lessons on the exercise movements, The motion evaluation device according to claim 8, wherein the second player is a participant in the exercise motion lesson.

10. A method for evaluating a second action, which is the action of a second player, based on a first action, which is the action of a first player, The computer obtains a second operation value measured from the second operation, A step of extracting second coordinated operation data that shows the characteristic behavior of the second operation by singular value decomposition of the second operation value, A step of obtaining a first comparison result by comparing first coordinated operation data showing characteristic behavior of the first operation with second coordinated operation data, The process of outputting the first comparison result to a display device, The process involves obtaining a third action value, which is the operation of the second player learned from the first comparison result, and extracting third cooperative action data that shows the characteristic behavior of the third action by performing singular value decomposition on the third action value, A step of obtaining a second comparison result obtained by comparing the first cooperative operation data and the third cooperative operation data, The process involves outputting the second comparison result to the display device, The first coordinated motion data includes a spatial basis obtained by singular value decomposition of the first motion values ​​measured for the first motion, The second coordinated operation data includes a spatial basis obtained by singular value decomposition of the second operation value, The third coordinated operation data includes a spatial basis obtained by singular value decomposition of the third operation value, The second comparison result includes a graph comparing the spatial vector norm obtained by normalizing the spatial basis of the first cooperative motion data, the spatial vector norm obtained by normalizing the spatial basis of the second cooperative motion data, and the spatial vector norm obtained by normalizing the spatial basis of the third cooperative motion data. Performance evaluation method.

11. A computer program for evaluating a second action, which is the action of a second player, based on a first action, which is the action of a first player, Computers, Means for acquiring a second operation value obtained by measuring the second operation, A means for extracting second coordinated operation data that shows the characteristic behavior of the second operation by singular value decomposition of the second operation value, Means for obtaining a first comparison result obtained by comparing first coordinated operation data showing characteristic behavior of the first operation with second coordinated operation data, Means for outputting the first comparison result to a display device, A means for obtaining a third action value, which is the operation of the second player learned from the first comparison result, and extracting third cooperative operation data that shows the characteristic behavior of the third operation by singular value decomposition of the third action value, Means for obtaining a second comparison result obtained by comparing the first cooperative operation data and the third cooperative operation data, The second comparison result is configured to function as a means for outputting it to the display device. The first coordinated motion data includes a spatial basis obtained by singular value decomposition of the first motion values ​​measured for the first motion, The second coordinated operation data includes a spatial basis obtained by singular value decomposition of the second operation value, The third coordinated operation data includes a spatial basis obtained by singular value decomposition of the third operation value, The second comparison result includes a graph comparing the spatial vector norm obtained by normalizing the spatial basis of the first cooperative motion data, the spatial vector norm obtained by normalizing the spatial basis of the second cooperative motion data, and the spatial vector norm obtained by normalizing the spatial basis of the third cooperative motion data. Computer program.

Images