Information processing apparatus, information processing method, and program

Abstract

To provide a technique capable of allowing a batter performing tee batting to grasp how a hitting posture of the batter himself / herself should be changed.SOLUTION: A processor (11) of an information processing device (10) executes a measurement step (M11) for continuously measuring the posture of a batter performing tee batting on the basis of one or both of output signals of a motion sensor (30) and a force plate (40), a timing specification step (M12) for specifying timing when the batter hits a ball placed on a tee (60) on the basis of an output signal of a force sensor (20) included in the tee (60), a posture specification step (M13) for specifying a posture of the batter at the specified timing as a hitting posture of the batter, and an output step (M14) for outputting a message to instruct a change in the hitting posture of the batter on the basis of information representing a hitting posture to be a model, and the information representing the specified hitting posture of the batter.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] Patent Document 1 describes a system that provides a bat speed radar device and a hitting ball speed radar device to a batting tee to detect bat speed and ball speed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art as described above, although it is possible to measure the motion information of the bat or ball and the kinetic energy of the player, a batter performing tee batting cannot grasp how to change his / her own batting posture.

[0005] One aspect of the present invention aims to realize a technique that enables a batter performing tee batting to grasp how to change his / her own batting posture.

Means for Solving the Problems

[0006] To solve the above problems, an information processing apparatus according to one aspect of the present invention includes one or more processors. The processor executes the following steps (1) to (4). (1) A measurement step of continuously measuring the posture of a batter performing tee batting based on an output signal of one or both of a motion sensor and a force plate. (2) A timing identification step of identifying the timing when the batter hits the ball placed on the tee based on the output signal of the force sensor built into the tee. (3) A posture identification step of identifying the posture of the batter at the timing identified in the timing identification step as the hitting posture of the batter. (4) An output step of outputting a message instructing a change in the hitting posture of the batter based on information representing a model hitting posture corresponding to the physical characteristics of the batter and information representing the hitting posture of the batter identified in the posture identification step.

Advantages of the Invention

[0007] According to one aspect of the present invention, a batter performing tee batting can grasp how to change his or her hitting posture.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Embodiments for Carrying Out the Invention

[0009] 〔Embodiment 1〕 〔System Overview〕 Hereinafter, an embodiment of the present invention will be described. FIG. 1 is a block diagram schematically showing the configuration of a batting system 1 according to an embodiment of the present invention, and FIG. 2 is a diagram schematically showing the appearance of the batting system 1. The batting system 1 is a system that outputs a message instructing a change in the batting posture of a batter who performs tee batting. The batting system 1 includes an information processing apparatus 10, a force sensor 20, a motion sensor 30, a force plate 40, and a tee 60.

[0010] The information processing apparatus 10 is a device that performs various calculations for outputting a message instructing a change in the batting posture of a batter who performs tee batting, and is, for example, a personal computer.

[0011] The force sensor 20 is a sensor built into the tee 60 where the ball is placed. The force sensor 20 detects the direction and magnitude of force and torque. The force sensor 20 is, for example, a six-axis force sensor that detects the force components Fx, Fy, Fz in the x-axis direction, y-axis direction, and z-axis direction, and the torque components Mx, My, Mz in the x-axis direction, y-axis direction, and z-axis direction in a three-dimensional space defined by the x-axis, y-axis, and z-axis. Note that the force sensor 20 is not limited to a six-axis force sensor, and may be other force sensors such as a four-axis force sensor.

[0012] The motion sensor 30 is a sensor for measuring the batter's posture by motion capture technology. As an example, the motion sensor 30 is a motion capture camera that detects a plurality of markers attached to the batter. In the example of FIG. 2, an example is shown in which the batting system 1 includes four motion sensors 30, but the number of motion sensors 30 may be more or less than four.

[0013] The force plate 40 is arranged on the floor surface where the batter performs a batting motion, and detects the floor reaction force and the center of gravity position of the batter.

[0014] The information processing device 10 includes a processor 11. The processor 11 executes an information processing method M1. FIG. 3 is a flowchart showing the flow of the information processing method M1 executed by the processor 11. The information processing method M1 includes a measurement step M11, a timing identification step M12, a posture identification step M13, and an output step M14.

[0015] The measurement step M11 is a step of continuously measuring the posture of the batter performing tee batting based on the output signal of one or both of the motion sensor 30 and the force plate 40. As an example, the processor 11 continuously measures the posture of the batter by motion capture technology based on the output signal of the motion sensor 30. Also, as an example, the processor 11 continuously measures the center of gravity position of the batter based on the output signal of the force plate 40.

[0016] Information indicating the batter's posture includes, as an example, the angles of the batter's shoulder joints, elbow joints, hip joints, knee joints, and part or all of the center of gravity position. In other words, the processor 11 calculates part or all of the angles of the batter's shoulder joints, elbow joints, hip joints, knee joints, and center of gravity position based on one or both of the output signals of the motion sensor 30 and the output signal of the force plate 40.

[0017] The timing identification step M12 is a step of identifying the timing at which the batter hits the ball placed on the tee 60 based on the output signal of the force sensor 20 built into the tee 60. As an example, the processor 11 identifies that the batter has hit the ball when the amount of change in the force and / or torque applied to the tee 60 exceeds a predetermined threshold value based on the output signal of the force sensor 20. The timing identified by the processor 11 in the timing identification step M12 is also referred to as the "ball hitting timing" hereinafter. Note that the method of identifying the ball hitting timing is not limited to the example described above. As an example, the processor 11 may identify that the batter has hit the ball when the vertical force applied to the tee 60, that is, the gravity of the ball, becomes equal to or less than the threshold value based on the output signal of the force sensor 20.

[0018] The posture identification step M13 is a step of identifying the posture of the batter at the timing identified in the timing identification step M12 as the batter's hitting posture.

[0019] The output step M14 is a step of outputting a message instructing a change in the batter's hitting posture based on information representing a exemplary hitting posture corresponding to the physical characteristics of the batter and information representing the batter's hitting posture identified in the posture identification step M13.

[0020] In the following description, the exemplary batting stance is also referred to as the "exemplary stance". Also, the batting stance of the batter to be evaluated is also referred to as the "stance to be evaluated". Further, in the following description, the information representing the exemplary stance is simply referred to as the exemplary stance. Also, the information representing the stance to be evaluated is simply referred to as the stance to be evaluated.

[0021] As an example, the information representing the exemplary stance includes some or all of the information indicating the positions of a plurality of markers attached to the batter detected by the motion sensor 30, the angle of the batter's shoulder joint, the angle of the elbow joint, the angle of the hip joint, the angle of the knee joint, and the angle of the center of gravity position.

[0022] As an example, the information indicating the physical characteristics of the batter includes some or all of the information indicating the batter's height, weight, BMI (Body Mass Index), age, gender, dominant hand, batting stance (right-handed batter or left-handed batter).

[0023] As an example, the information representing the exemplary stance is stored in a predetermined memory such as the secondary memory 13 in association with the physical characteristics of the batter. In this case, the information representing a plurality of exemplary stances is stored in association with the information representing the physical characteristics of the batter respectively. The information representing the exemplary stance and the information representing the physical characteristics may be associated one-to-one, or as an example, a plurality of pieces of information representing the physical characteristics may be associated with the information representing one exemplary stance.

[0024] As an example, the message instructing the change of the batting stance is a message representing the difference between the exemplary stance and the stance to be evaluated. Also, the message may be a message representing the content of improvement of the stance to be evaluated based on the difference between the exemplary stance and the stance to be evaluated. As an example, the message may be output as an image such as a still image or a moving image, or may be output as sound.

[0025] According to the above configuration, the information processing apparatus 10 identifies the timing when the batter hits the ball based on the output signal of the force sensor 20 built into the tee, and outputs a message instructing a change in the batting posture at the identified timing. As a result, the batter who performs tee batting can grasp how to change his / her own batting posture.

[0026] 〔System Configuration〕 Next, the configuration of the batting system 1 will be described with reference to FIG. 1. As shown in FIG. 1, the batting system 1 includes a display device 50 in addition to the information processing apparatus 10, the force sensor 20, the motion sensor 30, the force plate 40, and the tee 60.

[0027] 〔Configuration of Information Processing Apparatus 10〕 FIG. 4 is a block diagram showing the configuration of the information processing apparatus 10. The information processing apparatus 10 includes a processor 11, a primary memory 12, a secondary memory 13, an input / output IF 14, a communication IF 15, and a bus 16. The processor 11, the primary memory 12, the secondary memory 13, the input / output IF 14, and the communication IF 15 are interconnected via the bus 16.

[0028] The secondary memory 13 stores a program P1 and a model table TBL1. The processor 11 expands the program P1 stored in the secondary memory 13 onto the primary memory 12, and executes each step included in the information processing method M1 according to the instructions included in the program P1 expanded onto the primary memory 12. Examples of devices that can be used as the processor 11 include a CPU (Central Processing Unit). Examples of devices that can be used as the primary memory 12 include a semiconductor RAM (Random Access Memory). Examples of devices that can be used as the secondary memory 13 include a flash memory.

[0029] An input / output IF14 has an input device and / or an output device connected thereto. Examples of the input / output IF14 include a USB (Universal Serial Bus). In the information processing method M1, the information acquired from the force sensor 20, the motion sensor 30, and the force plate 40 is input to the information processing apparatus 10 via the input / output IF14. Also, the information provided to the batter in the information processing method M1 is output from the information processing apparatus 10 via this input / output IF14.

[0030] The communication IF15 is an interface for communicating with other computers. The communication IF15 may include an interface for communicating with other computers without going through a network, for example, a Bluetooth (registered trademark) interface. Also, the communication IF15 may include an interface for communicating with other computers via a LAN (Local Area Network), for example, a Wi-Fi (registered trademark) interface.

[0031] Note that in the present embodiment, a configuration is adopted in which the information processing method M1 is executed using a single processor (processor 11), but the present invention is not limited to this. That is, a configuration may be adopted in which the information processing method M1 is executed using a plurality of processors. In this case, the plurality of processors that execute the information processing method M1 in cooperation may be provided in a single computer and configured to be communicable with each other via a bus, or may be provided distributedly in a plurality of computers and configured to be communicable with each other via a network. As an example, a mode in which a processor incorporated in a computer constituting a cloud server and a processor incorporated in a computer owned by a user of the cloud server execute the information processing method M1 in cooperation can be considered.

[0032] The exemplary table TBL1 is a table that associates the physical characteristics of a batter with an exemplary posture. FIG. 5 is a diagram illustrating the content of the exemplary table TBL1. The exemplary table TBL1 is a table that associates physical characteristics with an exemplary posture. In the example of FIG. 5, in the exemplary table TBL1, the items of "physical characteristics" and "exemplary posture" are associated with each other. Among these items, in the item of "physical characteristics", identification information for identifying the physical characteristics of the batter is stored. In the item of "exemplary posture", identification information for identifying the exemplary posture, which is information indicating the exemplary posture, is stored. The exemplary table TBL1 is referred to when the processor 11 executes a process of specifying an exemplary posture to be used as an example for evaluating the batting posture of a batter to be evaluated.

[0033] The secondary memory 13 stores information representing a plurality of exemplary postures, and identification information is attached to each of the plurality of exemplary postures. That is, based on the identification information stored in the exemplary table TBL1, the physical characteristics of the batter and the exemplary posture are associated with each other.

[0034] The display device 50 displays a screen according to the data supplied by the information processing device 10. As an example, the display device 50 is a liquid crystal display connected to the input / output IF14 of the information processing device 10.

[0035] 〔Operation of Information Processing Device〕 FIG. 6 is a flowchart showing the flow of the information output operation performed by the processor 11 of the information processing device 10. In step S11, the processor 11 acquires body information representing the physical characteristics of a batter to be evaluated. As an example, the processor 11 may acquire the body information by the batter operating an input device such as a touch panel. Also, as an example, the processor 11 may acquire the body information by reading the body information from a storage medium in which the body information is stored. The body information includes, as an example, information indicating part or all of the height, weight, BMI, age, and gender of the batter.

[0036] In step S12, the processor 11 continuously measures the posture of the batter who performs tee-batting based on the output signal of one or both of the motion sensor 30 and the force plate 40. The posture of the batter measured by the processor 11 in step S12 includes, as an example, part or all of the angle of the batter's shoulder joint, the angle of the elbow joint, the angle of the hip joint, the angle of the knee joint, and the center of gravity position.

[0037] In step S13, the processor 11 determines whether the batter has hit the ball placed on the tee 60 based on the output signal of the force sensor 20. As an example, the processor 11 identifies that the batter has hit the ball when the amount of change in the force and / or torque applied to the tee 60, which is identified based on the output signal of the force sensor 20, exceeds a predetermined threshold. When it is determined that the batter has hit the ball (step S13; YES), the processor 11 proceeds to the process of step S14. On the other hand, when it is determined that the batter has not hit the ball yet (step S13; NO), the processor 11 returns to the process of step S12 and continues the measurement process of the batter's posture.

[0038] By repeatedly executing the process of step S12 by the processor 11 until the batter hits the ball, the posture of the batter is continuously measured, and the time-series information indicating the measured posture is stored in the secondary memory 13.

[0039] In step S14, the processor 11 identifies the posture of the batter measured at the timing identified in step S13 as the batting posture of the batter.

[0040] In step S15, the processor 11 identifies a reference posture corresponding to the physical characteristics of the batter. As an example, the processor 11 refers to the reference table TBL1 and identifies a reference posture corresponding to the physical characteristics of the batter to be evaluated. At this time, if the physical characteristics of the acquired batter are not registered in the reference table TBL1, the processor 11 may select, from among the plurality of physical characteristics registered in the reference table TBL1, the one with the smallest difference from the acquired physical characteristics, and identify the reference posture corresponding to the selected physical characteristics.

[0041] Note that the method for identifying the reference posture in step S15 is not limited to the method of referring to the reference table TBL1, and other methods may be used. The processor 11 may identify the reference posture by other rule-based processing using the physical characteristics of the batter. Also, as an example, the processor 11 may input the physical characteristics of the batter to a learned model constructed by machine learning, which takes the physical characteristics of the batter as input and outputs a label representing the pattern of the reference posture, to identify the reference posture.

[0042] In step S16 of FIG. 6, the processor 11 outputs a message instructing a change in the batting posture of the batter based on the information indicating the reference posture and the information indicating the posture to be evaluated of the batter. As an example, the processor 11 outputs a message representing the difference between the reference posture and the posture to be evaluated. In this example, the processor 11 outputs the message by displaying an image representing the message on the display device 50.

[0043] Figures 7 and 8 are diagrams showing an example of the screen displayed by the display device 50. Figure 7 is a screen representing the evaluation target posture of the batter to be evaluated. A plurality of dots d11, d12, … in the figure schematically show the appearance of the posture of the batter measured by the processor 11 based on the output signal of the motion sensor 30. "Shoulder joint", "elbow joint", "hip joint", "knee joint" on the screen of Figure 7 represent the angle of the shoulder joint, the angle of the elbow joint, the angle of the hip joint, and the angle of the knee joint measured by the processor 11 based on the output signal of the motion sensor 30, respectively. "Center of gravity position at impact" on the screen represents the center of gravity position of the batter measured by the processor 11 based on the output signal of the force plate 40.

[0044] Figure 8 is a screen representing the difference between the exemplary posture and the evaluation target posture. A plurality of dots d21, d22, … in the figure schematically represent the appearance of the exemplary posture. Also, in the example of Figure 8, the differences between the exemplary posture and the evaluation target posture for each of the shoulder joint, elbow joint, hip joint, knee joint, and center of gravity position are displayed. The difference between the exemplary posture and the evaluation target posture is information indicating how the batter should change the batting posture.

[0045] The method by which the processor 11 presents the difference between the exemplary posture and the evaluation target posture in step S16 is not limited to the method described above, and other methods may be used. As an example, the processor 11 may change the content of the message to be output according to the combination of the exemplary posture and the evaluation target posture. As an example, instead of directly outputting the information representing the difference between the exemplary posture and the evaluation target posture, the processor 11 may output a difference smaller than the actual one, or may output a difference larger than the actual one, that is, may correct and output one or both of the exemplary posture and the evaluation target posture. As an example, when the difference between the exemplary posture and the evaluation target posture is larger than a predetermined threshold value, the processor 11 may output a message representing a difference smaller than the actual difference.

[0046] Also, as an example, the processor 11 may output different messages according to the physical characteristics of the batter. As an example, when the physical characteristics such as the age of the batter satisfy a predetermined condition, the processor 11 may correct the exemplary posture so that the difference to be output is smaller than the actual difference. Also, as an example, when the physical characteristics of the batter satisfy a predetermined second condition, the processor 11 may correct the exemplary posture so that the difference to be output is larger than the actual difference.

[0047] Also, as an example, among a plurality of items (shoulder joint angle, elbow joint angle, center of gravity position, etc.) included in the information representing the posture, for a predetermined item, the processor 11 may correct the exemplary posture so that the difference to be output is smaller than the actual difference. Also, as an example, among a plurality of items included in the information representing the posture, for a predetermined item, the processor 11 may correct the exemplary posture so that the difference to be output is larger than the actual difference. In this way, the processor 11 may correct the information of each of the plurality of items included in the information representing the posture according to the type of the item.

[0048] As described above, according to this embodiment, the information processing apparatus 10 outputs a message representing the difference between the exemplary batting posture and the batter's batting posture. Thereby, the batter performing tee batting can grasp how to change his / her own batting posture.

[0049] Also, according to this embodiment, the information processing apparatus 10 outputs a message instructing a change in part or all of the shoulder joint angle, elbow joint angle, hip joint angle, knee joint angle, and center of gravity position of the batter, and presents to the user how to change his / her own batting posture. Thereby, the batter using the batting system 1 can grasp how to change part or all of the shoulder joint angle, elbow joint angle, hip joint angle, knee joint angle, and center of gravity position.

[0050] [Embodiment 2] Other embodiments of the present invention will be described below. For convenience of explanation, members having the same functions as those described in the above embodiments are denoted by the same reference numerals, and the description thereof will not be repeated.

[0051] In the present embodiment, the processor 11 of the information processing apparatus 10 measures the impact strength and the impact angle based on the output signal of the force sensor 20. That is, in the present embodiment, the batting posture of the batter includes the impact strength and the impact angle in addition to the angles of the batter's shoulder joint, elbow joint, hip joint, knee joint, and the center of gravity position.

[0052] The impact strength is the magnitude of the force applied to the ball at the hitting timing. As an example, the processor 11 measures the magnitude of the force applied to the tee 60 as the impact strength based on the output signal of the force sensor 20.

[0053] The impact angle is the angle of the force applied to the ball at the hitting timing. As an example, the processor 11 measures the angle of the force applied to the tee 60 as the impact angle based on the output signal of the force sensor 20.

[0054] The items included in the information indicating the batting posture of the batter are not limited to those described above, and the information indicating the batting posture may include other items. As an example, the information indicating the batting posture may include the initial velocity of the ball at the hitting timing or the angle of the bat.

[0055] In the present embodiment, in the process of measuring the posture of the batter (step S12 in FIG. 6), the processor 11 measures the impact strength and the impact angle in addition to the shoulder joint, elbow joint, hip joint, knee joint, and the center of gravity position of the batter. Further, in the process of outputting a message (step S16 in FIG. 6), the processor 11 outputs a message indicating how the impact strength and the impact angle should be changed in addition to the shoulder joint, elbow joint, hip joint, knee joint, and the center of gravity position of the batter.

[0056] FIGS. 9 and 10 are diagrams showing an example of a screen displayed by the display device 50. In the example of FIG. 9, in addition to the angle of the batter's shoulder joint, the angle of the elbow joint, etc., "impact strength" and "impact angle" are displayed. The "impact strength" and "impact angle" respectively indicate the impact strength and impact angle measured by the processor 11 based on the output signals of the force sensor 20.

[0057] FIG. 10 is a screen showing the difference between the exemplary posture and the posture to be evaluated. In the example of FIG. 10, in addition to the angle of the batter's shoulder joint, the angle of the elbow joint, etc., information indicating how the impact strength and impact angle should be changed is displayed.

[0058] As described above, according to the present embodiment, the information processing apparatus 10 presents to the user information indicating how the batter should change the impact strength and impact angle in addition to the angle of the batter's shoulder joint and the angle of the elbow joint. The batter using the batting system 1 can grasp how to change his / her batting posture by visually recognizing the screen displayed on the display device 50.

[0059] 〔Embodiment 3〕 Another embodiment of the present invention will be described below. For the sake of convenience of explanation, members having the same functions as the members described in the above embodiment are denoted by the same reference numerals, and the description thereof will not be repeated.

[0060] FIG. 11 is a block diagram showing the configuration of the information processing apparatus 10C according to the present embodiment. The information processing apparatus 10C includes a message table TBL21 in the secondary memory 13C.

[0061] FIG. 12 is a diagram illustrating the contents of a message table TBL21 stored in the secondary memory 13. The message table TBL21 is a table that associates combinations of a reference posture and a posture to be evaluated with messages. In the example of FIG. 12, in the message table TBL21, items of "reference posture", "posture to be evaluated", and "message" are associated with each other. Among these items, identification information for identifying the reference posture is stored in the item of "reference posture". Identification information for identifying the posture to be evaluated is stored in the item of "posture to be evaluated".

[0062] In the item of "message", a message indicating the content of the change in the batting posture of the batter is stored. The information processing apparatus 10C may display a message for an item in which the difference in joint angles is large between the reference posture and the posture to be evaluated. As an example, the message may be a message such as "Please *** at the impact". For example, when the sides are too open with respect to the imitated posture, the information processing apparatus 10C may display "Please close the sides at the impact".

[0063] The flow of the information output operation performed by the processor 11 of the information processing apparatus 10C according to the present embodiment is the same as the flowchart of FIG. 6 described in the above-described embodiment 1. However, the processor 11 of the information processing apparatus 10C according to the present embodiment outputs a message different from the message output in the message output process (the process of step S16 in FIG. 6) according to the first embodiment.

[0064] In this embodiment, the processor 11 refers to the message table TBL21 and identifies the message to be output based on the exemplary posture and the posture to be evaluated. Specifically, the processor 11 first searches the message table using the combination of the hitting posture identified in step S14 of FIG. 6 and the exemplary posture identified in step S15 as a key, and identifies the message corresponding to the searched key as the message to be output. When the hitting posture identified in step S14 is not registered in the message table TBL21, the processor 11 selects, from among the plurality of hitting postures registered as postures to be evaluated in the message table TBL21, the one with the smallest difference from the identified hitting posture. The processor 11 searches the table using the combination of the selected hitting posture and the exemplary posture identified in step S15 as a key.

[0065] The processor 11 outputs the message identified by referring to the message table TBL2 to the display device 50 or the like. The batter can grasp how to change his / her hitting posture based on the message output to the display device 50 or the like.

[0066] As described above, according to this embodiment, the information processing apparatus 10C refers to the table associating the combination of the exemplary posture and the posture to be evaluated with the message, and outputs the message specified based on the exemplary posture and the posture to be evaluated. Thereby, the batter who performs tee batting can grasp how to change his / her hitting posture.

[0067] [Embodiment 4] Other embodiments of the present invention will be described below. For the sake of convenience of explanation, members having the same functions as those described in the above embodiment are denoted by the same reference numerals, and the description thereof will not be repeated.

[0068] The information processing apparatus 10D according to this embodiment is different from the information processing apparatus 10C according to the above-described Embodiment 3 in the content of the message table. FIG. 13 is a diagram illustrating the content of the message table TBL22 according to this embodiment. The message table TBL22 is a table that associates the difference between the exemplary posture and the posture to be evaluated with a message. In the example of FIG. 13, in the message table TBL22, the items of "difference information" and "message" are associated with each other. Among these items, information representing the difference between the exemplary posture and the posture to be evaluated is stored in the item of "difference information". In the item of "message", a message indicating the content of the change in the batting posture of the batter is stored.

[0069] The flow of the information output operation performed by the processor 11 of the information processing apparatus 10D according to this embodiment is the same as the flowchart of FIG. 6 described in the above-described Embodiment 1. However, the processor 11 of the information processing apparatus 10D according to this embodiment executes different processing from that in Embodiment 1 in step S16 of FIG. 6 to output a message.

[0070] In this embodiment, the processor 11 refers to the message table TBL22 and specifies the message to be output based on the exemplary posture and the posture to be evaluated. Specifically, first, the processor 11 calculates the difference between the batting posture specified in step S14 of FIG. 6 and the exemplary posture specified in step S15. As an example, the processor 11 calculates the difference between the posture to be evaluated and the exemplary posture for each of a plurality of items such as the angle of the batter's shoulder joint, the angle of the elbow joint, the angle of the hip joint, the angle of the knee joint, and the center of gravity position, and sets the set of the calculated difference values for each item as the difference information.

[0071] Next, the processor 11 searches the message table TBL22 using the generated difference information as a key. If the generated difference information is not registered in the message table TBL22, the processor 11 selects the one with the smallest difference from the generated difference information among the plurality of batting postures registered in the message table TBL22. The processor 11 outputs the message associated with the selected difference information to the display device 50 or the like.

[0072] The batter can grasp how to change his / her batting posture according to the message output to the display device 50 or the like.

[0073] As described above, according to the present embodiment, the information processing apparatus 10D refers to a table in which the difference between the exemplary posture and the posture to be evaluated is associated with the message, and outputs a message specified based on the exemplary posture and the posture to be evaluated. Thereby, the batter who performs tee batting can grasp how to change his / her batting posture.

[0074] [Embodiment 5] Another embodiment of the present invention will be described below. For convenience of explanation, members having the same functions as those described in the above embodiment are denoted by the same reference numerals, and the description thereof will not be repeated.

[0075] The content of the process of selecting a message (the process of step S16 in FIG. 6) performed by the information processing apparatus 10E according to the present embodiment is different from that of the information processing apparatus 10 according to the above-described Embodiment 1. The information processing method performed by the information processing apparatus 10E according to the present embodiment is referred to as an information processing method M4.

[0076] FIG. 14 is a block diagram showing the configuration of the information processing apparatus 10E according to the present embodiment. The information processing apparatus 10E includes a learned model LM1 in a secondary memory 13E. The processor 11 deploys the learned model LM1 stored in the secondary memory 13D onto the primary memory 12. The learned model LM1 deployed on the primary memory 12 is used when the processor 11 executes the output process of the message. Note that the fact that the learned model LM1 is stored in the secondary memory 13 means that the parameters defining the learned model LM1 are stored in the secondary memory 13.

[0077] In addition, in this embodiment, the learned model LM1 is stored in a memory (secondary memory 13) built into the same computer as the processor (processor 11) that executes the information processing method M4. However, the present invention is not limited to this. That is, a configuration may be adopted in which the learned model LM1 is stored in a memory built into a computer different from the processor that executes the information processing method M4. In this case, the computer in which the memory storing the learned model LM1 is built is configured to be able to communicate with each other via a network with the computer in which the processor that executes the information processing method M4 is built. As an example, a mode in which the learned model LM1 is stored in a memory built into a computer constituting a cloud server, and a processor built into a computer owned by a user of the cloud server executes the information processing method M4 can be considered.

[0078] Also, in this embodiment, a configuration is adopted in which the learned model LM1 is stored in a single memory (secondary memory 13). However, the present invention is not limited to this. That is, a configuration may be adopted in which the learned model LM1 is distributed and stored in a plurality of memories. In this case, the plurality of memories storing the learned model LM1 may be provided in a single computer (which may or may not be the computer in which the processor that executes the information processing method M4 is built), or may be distributed and provided in a plurality of computers (which may or may not include the computer in which the processor that executes the information processing method M4 is built). As an example, a configuration in which the learned model LM1 is distributed and stored in memories built into each of a plurality of computers constituting a cloud server can be considered.

[0079] The learned model LM1 is a learned model constructed by machine learning that takes as input a combination of a reference posture and a posture to be evaluated and outputs a message. As the learned model LM1, for example, a neural network model such as a convolutional neural network or a recurrent neural network, a regression model such as linear regression, or an algorithm such as a decision tree model can be used.

[0080] FIG. 15 is a diagram schematically showing an example of the learned model LM1 according to the present embodiment. As shown in the figure, input data is input to the learned model LM1. The learned model LM1 is composed of, for example, a convolutional layer, a pooling layer, and a combining layer. In the convolutional layer, the input data is subjected to convolution of information by filtering. The data after convolution is subjected to pooling processing in the pooling layer. Thereby, the recognition ability of the model with respect to the positional change of the features in the data is improved. The data after the pooling processing is processed in the combining layer, and is thereby converted into the output data of the learned model LM1, that is, a label for discriminating a message, and output.

[0081] That is, by passing the input data input to the learned model LM1 through each layer shown in FIG. 15 in this order, an estimation result of the message is output. Note that the output format of the estimation result is not particularly limited. For example, the message may be represented by text data.

[0082] The flow of the information output operation performed by the processor 11 of the information processing apparatus 10E according to the present embodiment is the same as the flowchart of FIG. 6 described in the above-described Embodiment 1. However, the processor 11 of the information processing apparatus 10E according to the present embodiment executes processing different from that in Embodiment 1 in step S16 of FIG. 6.

[0083] In the present embodiment, the processor 11 specifies a message to be output using the learned model LM1. In other words, the processor 11 inputs a combination of a reference posture and a posture to be evaluated to the learned model LM1, and outputs a message corresponding to the label output from the learned model LM1 to the display device 50 or the like.

[0084] 〔Generation of Teacher Data and Construction of Learned Model〕 Next, the construction operation of the learned model LM1 and the generation operation of the teacher data used in the construction process will be described. In the present embodiment, the information processing apparatus 10E executes the construction process of the learned model LM1 and the generation process of the teacher data. Note that the construction process of the learned model LM1 and the generation process of the teacher data may be executed by another apparatus other than the information processing apparatus 10E.

[0085] The teacher data used in the construction of the learned model LM1 includes a set of an evaluation target posture and a reference posture, and a label indicating the type of message.

[0086] First, the processor 11 acquires the evaluation target posture and also acquires the reference posture corresponding to the evaluation target posture. As an example, the processor 11 acquires the evaluation target posture and the reference posture from an input device or another apparatus via the input / output IF 14 or the communication IF 15. Next, the acquired evaluation target posture and reference posture are associated with a label to generate teacher data. The label is data indicating the type of message. The label is input to the information processing apparatus 10E via the input / output IF 14, for example.

[0087] The processor 11 constructs the learned model LM1 by supervised learning using the teacher data. As the learned model LM1, for example, a neural network model such as a convolutional neural network or a recurrent neural network, a regression model such as linear regression, or an algorithm such as a decision tree can be used.

[0088] According to the present embodiment, the information processing apparatus 10E uses the learned model LM1 constructed by machine learning, which takes as input a combination of a reference posture and an evaluation target posture and outputs a message, to specify the message to be output. Thereby, a batter who performs tee batting can grasp how to change his / her batting posture.

[0089] [Embodiment 6] Other embodiments of the present invention will be described below. For convenience of explanation, members having the same functions as those described in the above embodiments are denoted by the same reference numerals, and their descriptions will not be repeated.

[0090] FIG. 15 is a block diagram showing the configuration of an information processing apparatus 10F according to the present embodiment. The information processing apparatus 10F includes a learned model LM2 in a secondary memory 13F. The processor 11 expands the learned model LM2 stored in the secondary memory 13F onto the primary memory 12. The learned model LM2 expanded on the primary memory 12 is used when the processor 11 executes message output processing.

[0091] The learned model LM2 is a learned model constructed by machine learning that takes as input the difference between a reference posture and a posture to be evaluated and outputs a message. As the learned model LM1, for example, a neural network model such as a convolutional neural network or a recurrent neural network, a regression model such as linear regression, or an algorithm such as a decision tree can be used.

[0092] The flow of the information output operation performed by the processor 11 of the information processing apparatus 10F according to the present embodiment is the same as the flowchart of FIG. 6 described in the above Embodiment 1. However, the processor 11 of the information processing apparatus 10F according to the present embodiment executes processing different from that in Embodiment 1 in step S16 of FIG. 6.

[0093] In the present embodiment, the processor 11 specifies the message to be output using the learned model LM2. Specifically, first, the processor 11 calculates the difference between the hitting posture specified in step S14 of FIG. 6 and the reference posture specified in step S15. As an example, the processor 11 calculates the difference between the posture to be evaluated and the reference posture for each of a plurality of items such as the angle of the batter's shoulder joint, the angle of the elbow joint, the angle of the hip joint, the angle of the knee joint, and the center of gravity position, and sets the set of difference values for each calculated item as difference information.

[0094] Next, the processor 11 inputs the generated difference information into the learned model LM2, and outputs a message corresponding to the label output from the learned model LM2 to a display device or the like.

[0095] According to the present embodiment, the information processing apparatus 10E uses the learned model LM1 constructed by machine learning, which takes the difference between the exemplary posture and the posture to be evaluated as an input and outputs a message, to specify the message to be output. Thereby, the batter who performs tee batting can grasp how to change his / her batting posture.

[0096] 〔Embodiment 7〕 Other embodiments of the present invention will be described below. For convenience of explanation, members having the same functions as those described in the above embodiments are denoted by the same reference numerals, and the description thereof will not be repeated.

[0097] In the above-described Embodiment 1, the information processing apparatus 10 specified the exemplary posture to be compared with the posture to be evaluated by referring to the exemplary table TBL1 (step S15 in FIG. 6). On the other hand, the information processing apparatus 10G according to the present embodiment specifies the exemplary posture using the learned model LM3.

[0098] The learned model LM3 is a learned model constructed by machine learning, which takes one or both of the physical characteristics of the batter and the posture to be evaluated as an input and outputs a label for identifying the exemplary posture. As the learned model LM1, for example, a neural network model such as a convolutional neural network or a recurrent neural network, a regression model such as linear regression, or an algorithm such as a decision tree can be used.

[0099] The flow of the information output operation performed by the processor 11 of the information processing apparatus 10G according to the present embodiment is the same as the flowchart of FIG. 6 described in the above Embodiment 1. However, the processor 11 of the information processing apparatus 10G according to the present embodiment executes a process different from that of Embodiment 1 in the process of specifying the exemplary posture in step S15 of FIG. 6.

[0100] In this embodiment, the processor 11 identifies a reference posture using the learned model LM3. In other words, the processor 11 inputs one or both of the physical characteristics of the batter and the posture to be evaluated into the learned model LM3, and identifies the reference posture corresponding to the label output from the learned model LM3 as the reference posture to be compared.

[0101] The input data of the learned model LM3 is not limited to the information representing the physical characteristics of the batter and the information representing the posture to be evaluated, and may include other information. As an example, the input data of the learned model LM3 may include time-series data representing the postures of the batter measured in a predetermined period before and after the hitting timing of the batter.

[0102] The teacher data used in constructing the learned model LM3 includes a set of the posture to be evaluated and the reference posture, and a label indicating the type of message. In the learning phase, first, the processor 11 acquires information representing the physical characteristics of the batter and information representing the posture to be evaluated of the batter. As an example, the processor 11 acquires such information from an input device or another device via the input / output IF14 or the communication IF15. Next, teacher data is generated by associating a label with the acquired set of information. The label is identification information for identifying the reference posture. The label is input to the information processing device 10G via the input / output IF14, for example.

[0103] The processor 11 constructs the learned model LM3 by supervised learning using the teacher data. As the learned model LM3, for example, neural network models such as convolutional neural networks and recurrent neural networks, regression models such as linear regression, or algorithms such as decision trees can be used.

[0104] 〔Supplementary Note 1〕 Each process described in the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI may operate in the above control device, or may operate in another device (for example, an edge computer or a cloud server, etc.).

[0105] [Supplementary Note 2] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope shown in the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

Explanation of Reference Numerals

[0106] 1 Batting System 10, 10C, 10D, 10E, 10F, 10G Information Processing Device 11 Processor 12 Primary Memory 13, 13C, 13D, 13E, 13F Secondary Memory 20 Force Sensor 30 Motion Sensor 40 Force Plate 50 Display Device M1, M4 Information Processing Method M11 Measurement Step M12 Timing Identification Step M13 Posture Identification Step M14 Output Step

Claims

1. A plurality of markers attachable to a batter, at least one motion sensor for detecting the plurality of markers, a primary memory for storing instructions, a secondary memory for storing a reference table associating the physical characteristics of the batter with a exemplary batting posture, comprising one or more processors for executing the instructions, wherein the processor performs a measurement step of continuously measuring the posture of the batter performing tee batting based on the output signal of one or both of the motion sensor and the force plate, a timing identification step of identifying the timing at which the batter performing the tee batting hits the ball placed on the tee based on the output signal of the force sensor built into the tee, a posture identification step of identifying the posture of the batter performing the tee batting at the timing identified in the timing identification step as the batting posture of the batter based on the output signals from the motion sensor and the force plate, and an output step of outputting a message instructing a change in the batting posture of the batter based on information representing an exemplary batting posture corresponding to the physical characteristics of the batter performing the tee batting and information representing the batting posture of the batter identified in the posture identification step, wherein the batting posture of the batter includes an impact strength and an impact angle measured based on the output signal of the force sensor, wherein the processor, in the output step, identifies information representing an exemplary batting posture corresponding to the physical characteristics of the batter performing the tee batting with reference to the reference table, and when the physical characteristics of the batter performing the tee batting are not registered in the reference table, selects the one with the smallest difference from the physical characteristics of the batter performing the tee batting among the plurality of physical characteristics registered in the reference table, and identifies the exemplary batting posture corresponding to the selected physical characteristics with reference to the reference table An information processing apparatus characterized by the above.

2. The processor outputs, in the output step, a message representing the difference between the exemplary batting posture and the batting posture of the batter identified in the posture identification step. The information processing apparatus according to claim 1, characterized by the above.

3. When using the exemplary batting posture as the reference posture and the batting posture to be evaluated as the posture to be evaluated, In the output step, the processor refers to a table associating the combination of the reference posture and the posture to be evaluated, or the difference between the reference posture and the posture to be evaluated, stored in the secondary memory with the message, and identifies the message to be output based on the reference posture and the posture to be evaluated. The information processing apparatus according to claim 1, characterized in that.

4. When using the exemplary batting posture as the reference posture and the batting posture to be evaluated as the posture to be evaluated, In the output step, the processor uses a learned model constructed by machine learning, taking the combination of the reference posture and the posture to be evaluated, or the difference between the reference posture and the posture to be evaluated as the input and the message as the output, and identifies the message to be output. The information processing apparatus according to claim 1, characterized in that.

5. The information representing the posture includes at least part or all of the angles of the batter's shoulder joint, elbow joint, hip joint, knee joint, and the center of gravity position specified by at least one of the output signals of the motion sensor and the force plate. The information processing apparatus according to any one of claims 1 to 4, characterized in that.

6. One or more processors A measurement step of continuously measuring the posture of the batter performing tee batting based on the output signal of one or both of the motion sensor and the force plate; A timing identification step of identifying the timing at which the batter hits the ball placed on the tee based on the output signal of the force sensor built into the tee; A posture identification step of identifying the posture of the batter at the timing identified in the timing identification step as the batting posture of the batter based on the output signals from the motion sensor and the force plate; An output step of outputting a message instructing a change in the batting posture of the batter based on the information representing the exemplary batting posture corresponding to the physical characteristics of the batter stored in the memory and the information representing the batting posture of the batter identified in the posture identification step. The batting stance of the batter includes the impact strength and impact angle measured based on the output signal of the force sensor, In the output step, the processor identifies information representing a exemplary batting stance corresponding to the physical characteristics of the batter by referring to an exemplary table that associates the physical characteristics of the batter with the exemplary batting stance, When the physical characteristics of the batter performing the tee batting are not registered in the exemplary table, among the multiple physical characteristics registered in the exemplary table, the one with the least difference from the physical characteristics of the batter performing the tee batting is selected, and the exemplary batting stance corresponding to the selected physical characteristics is identified by referring to the exemplary table characterized by the information processing method.

7. Causing a computer to perform a measurement step of continuously measuring the stance of a batter performing tee batting based on the output signal of one or both of a motion sensor and a force plate, a timing identification step of identifying the timing at which the batter hits a ball placed on the tee based on the output signal of a force sensor built into the tee, a stance identification step of identifying the stance of the batter at the timing identified in the timing identification step as the batting stance of the batter based on the output signals from the motion sensor and the force plate, and an output step of outputting a message instructing a change in the batting stance of the batter based on the information representing the exemplary batting stance corresponding to the physical characteristics of the batter stored in the memory and the information representing the batting stance of the batter identified in the stance identification step. The batting stance of the batter includes the impact strength and impact angle measured based on the output signal of the force sensor, In the output step, identifies information representing a exemplary batting stance corresponding to the physical characteristics of the batter by referring to an exemplary table that associates the physical characteristics of the batter with the exemplary batting stance, When the physical characteristics of the batter who performs the tee batting are not registered in the exemplary table, select, from among the plurality of physical characteristics registered in the exemplary table, the one with the smallest difference from the physical characteristics of the batter who performs the tee batting, and specify, with reference to the exemplary table, the exemplary batting posture corresponding to the selected physical characteristic A program characterized by the above.

Images