Learning data generating system and learning system

Abstract

To provide a learning data generating system and a learning system that can obtain a high learning effect.SOLUTION: A learning data generating system comprises: action data acquisition means of acquiring action data as information showing the action of a learner; corrective data acquisition means 322 of acquiring corrective data showing a corrective action for correcting an action shown by the action data; and learning data generation means 32 of generating learning data based on the action data acquired by the action data acquisition means and the corrective data acquired by the corrective data acquisition means 322.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a learning data generation system and a learning system that support learning of movements. [Background technology]

[0002] Conventionally, various systems have been provided for supporting the acquisition of movements. For example, Patent Document 1 discloses a system that uses animation to represent the physical movements of a learner so that the difference between the learner's movements and model movements can be seen. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2014-133015 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-mentioned conventional systems, the physical movements of a model (expert) are used as model movements, so that the model movements may not suit the learner and a high learning effect may not be obtained.

[0005] In view of the above circumstances, an object of the present invention is to provide a learning data generation system and a learning system that can achieve a high learning effect. [Means for solving the problem]

[0006] The training data generation system of the present invention comprises: A motion data acquisition means for acquiring motion data which is information representing a motion of a learner; a correction data acquisition means for acquiring correction data representing a correction operation for correcting the operation represented by the operation data; The computer-readable storage device further includes a learning data generating means for generating learning data based on the motion data acquired by the motion data acquiring means and the correction data acquired by the correction data acquiring means.

[0007] The learning data generation system having the above configuration is configured to generate learning data by modifying movement data representing the learner's own movements, so that learning data representing the movements that the learner wishes to emulate can be generated to suit the learner's individual characteristics, thereby achieving a high learning effect.

[0008] In the training data generation system of the present invention, a correction part generating means for generating correction part information indicating a part to be corrected of the motion data acquired by the motion data acquiring means, The correction data acquisition means acquires correction data for the correction portion indicated by the correction portion information, The learning data generating means may be configured to generate the learning data by combining the correction data with a correction portion in the motion data indicated by the correction portion information.

[0009] In this way, since learning data can be generated using correction data suited to the portion of the motion data that needs to be corrected, it becomes possible to generate learning data that is likely to provide a high learning effect.

[0010] In the learning data generation system and learning system of the present invention, the motion data acquisition means acquires the motion data based on an output of a motion sensor attached to the learner; The correction part generating means may generate the correction part information based on an output of the motion sensor.

[0011] In this way, learning data can be generated by appropriately identifying and correcting the parts of the learner's movements that need to be corrected to suit the learner, making it possible to generate learning data that is more likely to produce a high learning effect.

[0012] The learning system of the present invention comprises: A motion data acquisition means for acquiring motion data which is information representing a motion of a learner; a correction data acquisition means for acquiring correction data representing a correction operation for correcting the operation represented by the operation data; a learning data generating means for generating learning data based on the motion data acquired by the motion data acquiring means and the correction data acquired by the correction data acquiring means; The display processing means may be provided for displaying the learning data and current action data regarding the current action of the learner in a manner that allows comparison between the learning data and current action data regarding the current action of the learner.

[0013] According to the learning system configured as above, learning data representing the learner's own movements is modified to generate learning data representing the movements that the learner wishes to model, thereby generating learning data suitable for the learner. Furthermore, the learner can learn movements while comparing the learning data representing the model movements with his or her own current movements, thereby achieving a high learning effect. Effect of the Invention

[0014] As described above, the learning data generation system and learning system of the present invention can provide the excellent effect of achieving a high learning effect. [Brief description of the drawings]

[0015] [Figure 1] FIG. 1 is a block diagram of a training data generation system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is an explanatory diagram of an operation screen of the learning data generation system according to the embodiment. [Diagram 3] FIG. 3 is an explanatory diagram of an operation screen of the learning data generation system according to the embodiment, and is an explanatory diagram of a display mode of a synchronization model and a learning model. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, a learning system according to an embodiment of the present invention will be described with reference to the accompanying drawings. In the learning system, learning data representing model movements are generated based on the movements of the learner himself, and the learner can learn the movements he wants to master while checking the learning data and his own movements.

[0017] As shown in FIG. 1, the learning system 1 of this embodiment has a movement measurement device 2 capable of measuring the movement state of a learner, a learning device 3 that generates learning data using information about the movement state of the learner measured by the movement measurement device 2, and an output device 4 that displays a 3D model (hereinafter referred to as a synchronization model) that operates in synchronization with the movement state of the learner and a 3D model (hereinafter referred to as a learning model) that operates in accordance with the movement state indicated by the learning data.

[0018] The movement measurement device 2 is a means for acquiring movement data, which is information representing the movements of a learner.

[0019] The movement measurement device 2 may be configured, for example, to create movement data from images or videos, or may be configured to have a motion sensor that is used while being attached to a learner.

[0020] The motion sensor is configured to be able to obtain information such as position change information, acceleration, angular velocity, and direction by moving with the learner. The movement measurement device 2 can be configured using, for example, optical markers, sensor devices such as acceleration sensors and angular velocity sensors, GPS, etc.

[0021] The learning device 3 has an action data receiving means 30 that receives action data indicating the learner's action state measured by the action measurement device 2 as action measurement information, a synchronization output means 31 that outputs the action measurement information received by the action data receiving means 30 as synchronization action information for operating the synchronization model, a learning data generating means 32 that executes a process of generating learning data, a display processing means 33 that executes a process of displaying and operating the synchronization model and the learning model on the output device 4, and a playback operation means 34 for performing an operation to play back the learning data.

[0022] The learning device 3 is composed of a computer. The computer has a control device C1 that processes information and a storage device C2 that stores information. Programs that cause the computer (control device C1) to function as an action data receiving means 30, a synchronous output means 31, a learning data generating means 32, and a display processing means 33 may be stored in the storage device C2.

[0023] In the learning device 3, the action data receiving means 30 and the learning data generating means 32 may be configured as a learning data generating system for generating learning data.

[0024] The movement measurement information received by the movement data receiving means 30 from the movement measurement device 2 is acquired by the synchronous output means 31 and base data acquiring means 320 and correction data acquiring means 322 of the learning data generating means 32, which will be described later.

[0025] The synchronous output means 31 is configured to repeatedly execute a process of receiving motion measurement information from the motion measurement device 2 and a process of transmitting the received motion measurement information to the synchronous display means while outputting (displaying) the synchronous model to the output device 4.

[0026] The synchronization operation information output by the synchronization output means 31 is used as an operation command for operating the synchronization model.

[0027] The learning data generation means 32 includes base data acquisition means 320 which acquires movement measurement information when the learner is performing a movement that the learner wishes to learn (learning movement) and stores this movement measurement information as base data, correction point generation means 321 which identifies a correction point in the base data that makes it possible to correct the movement state and generates the identification result as correction point identification information, correction data acquisition means 322 which stores as correction data the movement measurement information acquired from the movement data receiving means 30 in order to correct the movement state of the correction point identified by the correction point generation means 321 in the base data, and generation process execution means 323 which generates learning data in which the movement state of the base data has been corrected based on the correction point identification information and the correction data.

[0028] The movement measurement information acquired as base data by the base data acquisition means 320 is information indicating a series of movement states from when the learner starts to perform the learning movement he or she wishes to master to when he or she finishes performing the learning movement, and indicates the current series of movement states of the learner before any correction is made.

[0029] The correction part generating means 321 has a correction part identifying means 3210 that identifies the correction part and generates correction part identifying information indicating the correction part, and a correction part associating means 3211 that associates the correction part identifying information generated by the correction part identifying means 3210 with the base data.

[0030] The correction part identification means 3210 executes a process of using motion characteristic information indicating the characteristics of the motion state of the correction part to identify, as the correction part, a part of the base data whose motion state matches or nearly matches the characteristics of the motion state indicated by the motion characteristic information.

[0031] The characteristics of the motion state can be determined by the body part and the static motion information (position, etc.) and dynamic motion information (speed, acceleration, rotation speed, etc.) of the body part.

[0032] For example, if the learning motion is a golf swing, motion characteristic information indicating the characteristics of the motion state at address, motion characteristic information indicating the characteristics of the motion state at top, motion characteristic information indicating the characteristics of the motion state at impact, and motion characteristic information indicating the characteristics of the motion state at finish are used.

[0033] In this case, the movement characteristic information indicating the characteristics of the movement state at address, the movement characteristic information indicating the characteristics of the movement state at the top, and the movement characteristic information indicating the characteristics of the movement state at the finish can be represented by information indicating the rotational speed of the learner's body and hips.

[0034] The motion characteristic information indicating the characteristics of the motion state at the time of impact can be expressed by information indicating the angular velocity and acceleration of the learner's hand.

[0035] The correction portion specifying information may include information such as the playback time or the number of playback frames of the base data corresponding to the correction portion.

[0036] The correction part relating means 3211 is configured to store the correction part specifying information in the storage device C2 in a state where the correction part specifying information is related to the base data.

[0037] The correction data acquisition means 322 includes correction target acquisition means 3220 which selects and acquires base data to be used for correcting the operating status, correction point selection means 3221 which selects the correction point that has been set (specified) for the base data acquired by the correction target acquisition means 3220, and correction acquisition processing means 3222 which acquires, from the operating data receiving means 30, operation measurement information to be used as correction data for correcting the operating status of the correction point selected by the correction point selection means 3221.

[0038] The correction target acquisition means 3220 is configured to be able to select an object to be corrected for the operational state from the base data stored in the storage device C2, and to acquire the selected base data.

[0039] The correction part selection means 3221 is configured by a selection operation button B1 displayed on the operation screen U, as shown in FIG.

[0040] The number of selection operation buttons B1 displayed on the operation screen U is the same as the number of corrections set in the base data.

[0041] The correction portion selection means 3221 is configured to output, to the operation screen U, an operation display B2 that indicates the operating state of the correction portion to be corrected together with the selection operation button B1.

[0042] The motion display B2 is configured to show the motion state of the part to be corrected by text and icons. When the learning motion is a golf swing, for example, it is configured by text such as address, top, impact, finish, etc.

[0043] As shown in FIG. 1, when the selection operation button is selected, the correction acquisition processing means 3222 is configured to execute a process of acquiring operation measurement information from the operation data receiving means 30, a process of converting the operation measurement information acquired from the operation data receiving means 30 into correction data for correcting the operation state of the correction part corresponding to the selection operation button (correction part identification information), and a process of storing the correction data in association with the correction part identification information.

[0044] The correction data is operation measurement information for correcting the operation state of the correction portion indicated by the correction portion specifying information in the base data.

[0045] The correction acquisition processing means 3222 in this embodiment is configured to acquire the movement state of the learner at the time when the correction point selection means 3221 is selected, so that the movement measurement information indicates the posture of the learner while moving or stationary as the movement state.

[0046] The generation process execution means 323 includes a processing target acquisition means 3230 that acquires base data to be used for generating learning data, a processing location confirmation means 3231 that confirms correction location identification information associated with the base data selected by the processing target acquisition means 3230, correction data confirmation means 3232 that confirms whether or not there is correction data associated with the correction location identification information confirmed by the processing location confirmation means 3231, and a correction process execution means 3233 that, when the correction data confirmation means 3232 determines that there is correction data associated with the correction location identification information, synthesizes the correction data at the location indicated by the correction location identification information in the base data.

[0047] When the processing target acquisition means 3230 acquires base data used for generating learning data, the processing target acquisition means 3230 acquires the base data associated with the correction portion identification information and the correction data. Since the learning device 3 of this embodiment is configured so that the base data is stored in the storage device C2, the processing target acquisition means 3230 is configured to acquire the base data from the storage device C2.

[0048] When a plurality of pieces of correction portion specifying information are associated with base data, the correction data confirmation means 3232 performs a process of confirming the presence or absence of correction data associated with all of the base data.

[0049] The correction processing execution means 3233 is configured to, when the processing location confirmation means 3231 determines that there is correction data associated with the correction location identification information, execute a process of acquiring the correction location identification information and the correction data, and a process of correcting the base data based on the correction location identification information and the correction data.

[0050] In the process of correcting the base data based on the correction portion specifying information and the correction data, the correction process execution means 3233 combines the correction data with the correction portion in the base data that is indicated by the correction portion specifying information.

[0051] The correction process execution means 3233 may be configured to synthesize the correction data with the base data by replacing the operating state of the correction portion with the operating state indicated by the correction data, or may be configured to synthesize the correction data with the base data by changing the operating state of the correction portion based on the operating state indicated by the correction data.

[0052] Moreover, the modification process execution means 3233 is configured to modify (correct) the operating states before and after the modification portion in accordance with the operating state of the modification portion after the modification.

[0053] More specifically, when the location of the base data is expressed by the number of frames, the correction process executing means 3233 sets the correction range of the base data by selecting the correction location and a frame before or after the correction location. Note that the correction process executing means 3233 may select another correction location before or after the correction location used as the correction reference as a frame before or after the correction location.

[0054] Next, the correction process execution means 3233 acquires information representing the frame number and the posture of the motion state (specifically, quaternion, or angles of the X-axis, Y-axis, and Z-axis) for each of the correction location and the location selected in the frame after or before the correction location (hereinafter referred to as the selected location).

[0055] Then, the correction process execution means 3233 calculates the difference between the posture of the movement state of the correction location and the posture of the movement state of the selected location, and the difference between the number of frames of the correction location and the number of frames of the selected location, and then derives the amount of change in posture per frame from the frame of the correction location to the frame of the selected location based on this difference information, and replaces (corrects) the posture of the movement state in each frame from the correction location to the selected location based on the derived amount of change in posture.

[0056] The correction process execution means 3233 of this embodiment is configured to execute a process of generating learning data when an execution button B3 displayed on the operation screen U is pressed (see FIG. 2).

[0057] The display processing means 33 has a synchronization display means 330 that executes processing for displaying the synchronization model on the output device 4 while it is operating, and a learning display means 331 that executes processing for displaying the learning model on the output device 4 while it is operating.

[0058] The synchronization display means 330 includes a synchronization model display means 3300 that executes a process of displaying the synchronization model on the output device 4, a synchronization action receiving means 3301 that receives synchronization action information output from the synchronization output means 31, and a synchronization action reflection means 3302 that operates the synchronization model based on the operation state indicated by the synchronization action information received by the synchronization action receiving means 3301.

[0059] The learning display means 331 has a learning model display means 3310 that executes a process of displaying the learning model on the output device 4, a learning data acquisition means 3311 that acquires learning data, and a learning operation reflection means 3312 that operates the learning model based on the learning data acquired by the learning data acquisition means 3311.

[0060] The learning model display means 3310 is configured to be able to display the learning model M2 on the output device 4 (operation screen U) simultaneously with the synchronization model M1 (see FIG. 3).

[0061] Moreover, the learning model display means 3310 is configured to be able to display the learning model M2 on the output device 4 by superimposing it on the synchronization model M1.

[0062] In this way, the display processing means 33 is configured to be able to display the synchronization action information on the output device 4 as current action data representing the learner's current action in a state that can be compared with the learning data.

[0063] The learning data reproducing means 34 is configured with a reproducing operation button (not shown) displayed on the operation screen. When the learning data reproducing means 34 is pressed, the learning data reproducing means 34 is configured to transmit a command to the learning operation reflecting means 3302 to execute a process of operating the learning model based on the learning data.

[0064] The output device 4 may be configured with a monitor or the like.

[0065] The configuration of the learning system 1 according to this embodiment is as described above. Next, a method of using the learning system 1 will be described.

[0066] In the learning system 1 of this embodiment, a learner can check his / her own movements, create learning data, and learn (practice) movements using the learning data.

[0067] When the movement measurement device 2 is measuring the learner's movement and the synchronization model display processing means 33 is displaying a synchronization model on the output device 4, the synchronization output means 31 outputs the movement measurement information acquired from the movement data receiving means 30 as synchronization movement information, and this synchronization movement information is received by the synchronization movement receiving means 3301.

[0068] Then, the synchronization operation reflecting means 3302 operates the synchronization model based on the synchronization operation information received by the synchronization operation receiving means 3301 .

[0069] Therefore, the learner can learn the movements while checking his / her own movements by looking at the synchronized model displayed on the output device 4, or by recognizing the difference between the learning data and his / her own movements as information through sound, vibration, etc.

[0070] When creating learning data, base data is generated by a base data acquisition means 320, correction part identification information is generated by a correction part generation means 321, correction data is acquired by a correction data acquisition means 322, and learning data is generated based on the base data, the correction part identification information, and the correction data by a generation process execution means 323.

[0071] The base data acquiring means 320 continues to acquire the movement measurement information from the movement data receiving means 30 from the time the learner starts to perform the learning movement he / she wishes to learn to the time he / she finishes the learning movement, and stores this movement measurement information in the storage device C2 as base data.

[0072] The correction part generating means 321 executes a process of generating correction part specifying information based on the base data generated by the base data acquiring means 320, and stores the generated correction part specifying information in the storage device C2 in a state in which the information is associated with the base data.

[0073] When the correction target acquisition means 3220 is in a state where it is acquiring base data, the correction data acquisition means 322 can acquire correction data for correcting the operating state of the correction portion by operating the correction portion selection means 3221.

[0074] The correction part selection means 3221 in this embodiment has a selection operation button and an action display B2 displayed together with the selection operation button, so that a learner can look at the action display B2, take the action state shown in the action display B2, and while looking at the synchronization model M1, adjust his / her posture so that the action state is correct, and then another person can operate the selection operation button to obtain correction data (see Figure 2).

[0075] When acquiring the correction data, if the learner is unable to move correctly by himself, the instructor corrects the learner's movement and then acquires the correction data.

[0076] When multiple pieces of correction location identification information are associated with the base data, correction data may be obtained for each of the multiple pieces of correction location identification information, or correction data may be obtained only for those pieces of correction location identification information that require correction.

[0077] When acquisition of the correction data is completed, the generation process execution means 323 generates learning data based on the base data, the correction portion specifying information, and the correction data.

[0078] When a learner operates the learning data replay means 34, the learning data replay means 34 sends a command to the learning operation reflection means 3302 to execute a process to operate the learning model based on the learning data, and the learning model displayed on the output device 4 operates in accordance with the learning data (the operating state indicated by the learning data).

[0079] Therefore, the learner can learn the movements by watching the movements of the learning model displayed on the output device 4 and imitating the movements.

[0080] Furthermore, if the learning model is displayed on the output device 4 by the learning model display means 3310 so as to be superimposed on the synchronous model, the learner can learn the movements while comparing his / her own current movements with the movements in the learning data.

[0081] As described above, the learning system 1 according to this embodiment is configured to generate learning data by modifying movement data representing the learner's own movements, so that learning data representing the movements that the learner wishes to model can be generated according to the learner's individual characteristics (such as habits of how to use their body), thereby achieving a high learning effect.

[0082] Furthermore, the learning system can generate learning data using correction data suitable for the portions of the motion data that need to be corrected by the learning data generation system, making it possible to generate learning data that is likely to provide a high learning effect.

[0083] Furthermore, in the learning system of this embodiment, the learning data generation system generates both the base data and the correction data from the learner's movements, so that learning data can be generated by appropriately identifying and correcting the parts of the learner's movements that need to be corrected to suit the learner, making it possible to generate learning data that is likely to produce a high learning effect.

[0084] In addition, since the system is configured to acquire and use information representing the learner's posture as correction data, when learning movements that include a stationary movement state in a series of movements, such as a golf swing, it becomes easier to acquire correction data and also easier to obtain learning data suitable for learning.

[0085] Furthermore, in the learning data of this embodiment, the movements before and after the correction portion can be corrected according to the motion state of the correction portion, so that learning data that is less likely to cause a learner to feel uncomfortable and is easy to learn can be generated.

[0086] The learning system can generate learning data suitable for the learner by the learning data stilling system as described above, and is further configured to enable the learner to learn movements while comparing the learning data representing model movements with his or her own current movements, thereby achieving a higher learning effect.

[0087] It should be noted that the learning data generation system and learning system according to the present invention are not limited to the above-described embodiments, and various modifications can of course be made within the scope of the gist of the present invention.

[0088] In the explanation of the learning system of the above embodiment, a golf swing has been given as an example of a learning motion, but the learning system and learning data generation system can also be used for motions other than a golf swing.

[0089] In the description of the training data generation system of the above embodiment, the training data generation means 32 is described as being included in the training device 3. However, for example, the training data generation means 32 can also be configured as an independent training data generation system.

[0090] Although not specifically mentioned in the description of the correction part specifying means 3210 in the above embodiment, the correction part specifying means 3210 may be configured so that a part to be corrected in the base data can be manually specified.

[0091] The correction data acquisition means 332 (correction acquisition processing means 3222) in the above embodiment is configured to acquire correction data from the learner's actions, but it may also be configured to acquire correction data obtained from the actions of a person other than the learner, for example.

[0092] The correction acquisition processing means 3222 in the above embodiment is configured to acquire the motion state of the learner at the time when the correction part selection means 3221 is selected, but is not limited to this configuration. The correction acquisition processing means 3222 may be configured to continue acquiring the motion state of the learner for a predetermined time from the time when the correction part selection means 3221 is selected.

[0093] In this case, the movement measurement information indicates the movement of the learner during the movement as the movement state. [Explanation of symbols]

[0094] 1... learning system, 2... movement measuring device, 3... learning device, 4... output device, 30... movement data receiving means, 31... synchronous output means, 32... learning data generating means, 33... display processing means, 34... playback operation means, 320... base data acquiring means, 321... correction part generating means, 322... correction data acquiring means, 323... generation processing execution means, 330... synchronization display means, 331... learning display means, 332... correction data acquiring means, 3210... correction part identifying means, 3211... correction part associating means, 3220... correction target acquiring means, 3221... correction part selection means, 3222...correction acquisition processing means, 3230...processing target acquisition means, 3231...processing location confirmation means, 3232...correction data confirmation means, 3233...correction processing execution means, 3300...synchronization model display means, 3301...synchronization operation receiving means, 3302...synchronization operation reflection means, 3310...learning model display means, 3311...learning operation receiving means, 3312...learning operation reflection means, B1...selection operation button, B2...operation display, B3...execution button, C1...control device, C2...storage device, M1...synchronization model, M2...learning model, U...operation screen

Claims

1. A motion data acquisition means for acquiring motion data which is information representing a motion of a learner; a correction data acquisition means for acquiring correction data representing a correction operation for correcting the operation represented by the operation data; a learning data generating means for generating learning data based on the motion data acquired by the motion data acquiring means and the correction data acquired by the correction data acquiring means, Training data generation system.

2. a correction part generating means for generating correction part information indicating a part to be corrected of the motion data acquired by the motion data acquiring means, The correction data acquisition means acquires correction data for the correction portion indicated by the correction portion information, the learning data generation means is configured to generate the learning data by synthesizing the correction data with a correction portion in the motion data indicated by the correction portion information. The training data generation system according to claim 1 .

3. the motion data acquisition means acquires the motion data based on an output of a motion sensor attached to the learner; The correction part generating means generates the correction part information based on an output of the motion sensor. The training data generation system according to claim 2 .

4. A motion data acquisition means for acquiring motion data which is information representing a motion of a learner; a correction data acquisition means for acquiring correction data representing a correction operation for correcting the operation represented by the operation data; a learning data generating means for generating learning data based on the motion data acquired by the motion data acquiring means and the correction data acquired by the correction data acquiring means; a display processing means for displaying the learning data and current action data regarding the current action of the learner in a comparative manner; Learning system.

Images