JP2018099452A - Selection support device, selection support system, and selection support method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a selection support technique characterized in determination of club characteristics suitable for a golfer.SOLUTION: A selection support device includes acquisition means for acquiring a measurement result for a golf swing action of a golfer, and selection means for selecting club characteristics suitable for the golfer from a plurality of golf club characteristics on the basis of swing information. The selection means selects club characteristics suitable for the golfer on the basis of a result of machine learning of teaching data showing club characteristics suitable for the golf swing action of each of a plurality of testers.SELECTED DRAWING: Figure 7

Description

  The present invention relates to a technique for assisting a golfer in selecting a golf club.

  Techniques for analyzing a golfer's swing and the like have been proposed (for example, Patent Documents 1 to 7). Such analysis techniques may help golfers select a golf club that suits them.

Special table 2014-530047 gazette Special table 2014-500078 gazette JP 2013-165808 A Special table 2011-502602 gazette Special table 2008-523384 gazette Japanese Patent Laid-Open No. 04-117972 Japanese Patent Laid-Open No. 01-125628

  One method of selecting a golf club suitable for a golfer is to classify golf swings by extracting specific features of the golf swing. For example, the classification is based on the angle of the swing trajectory. However, human golf swings are complex, and just because certain features are common does not mean that a golf club with the same characteristics is suitable for all golfers.

  An object of the present invention is to provide a selection support technique that is characterized by discriminating club characteristics suitable for a golfer.

According to the present invention, for example,
An acquisition means for acquiring a measurement result of the golf swing movement of the golfer;
Selecting means for selecting a club characteristic suitable for the golfer from a plurality of types of club characteristics of the golf club based on the measurement result;
The selection means includes
For a plurality of testers, based on the result of machine learning of teacher data indicating club characteristics adapted to the golf swing motion of each tester, club characteristics suitable for the golfer are selected.
A selection support device is provided.

  ADVANTAGE OF THE INVENTION According to this invention, the selection assistance technique characterized by the discrimination | determination of the club characteristic suitable for a golfer can be provided.

1 is a schematic diagram of a selection support system according to an embodiment of the present invention. The flowchart which shows the procedure for making artificial intelligence learn. (A) is explanatory drawing of the range of the swing operation | movement used for teacher data etc., (B) is a schematic diagram which shows the classification example of a club characteristic. The figure which shows the example of measurement data and swing information of swing operation | movement. The figure which shows the example of the result of a hit test, and applicable club information. The figure which shows the example of the data used for machine learning. The figure which shows the example of the flowchart which shows the example of a selection assistance process, and information. The figure which shows another example of a system.

<System configuration>
FIG. 1 is a schematic diagram of a selection support system 1 according to an embodiment of the present invention. The system 1 includes a measuring device 2, an information processing device 3, a display device 4, and an input device 5.

  The measuring device 2 is a device that measures the golf swing motion of the golfer 100. In the present embodiment, the apparatus is a device for measuring the behavior of the golf club 101 and is a device that is attached to the shaft (or grip) of the golf club 101, and includes an acceleration sensor and an angular velocity sensor. As the measuring device 2, for example, ATR-Promotions TSND121 or Seiko Epson M-tracer can be used. Based on the detection result of the measuring device 2, the time-series data of the three-dimensional acceleration and the three-dimensional angular velocity of the golf club 101 during the swing can be obtained.

  In the present embodiment, the information processing device 3 is a computer that functions as a selection support device that recommends a golf club suitable for the golfer 100. In the present embodiment, it is assumed that the recommended golf club is a driver club. However, it can also be applied to other types of golf clubs. The information processing apparatus 3 includes a processing unit 31, a storage unit 32, and an I / F unit (interface unit) 33 that are electrically connected to each other. The processing unit 31 is a processor such as a CPU. The storage unit 32 includes one or a plurality of storage devices. The storage device is, for example, a RAM, a ROM, a hard disk, or the like. The storage unit 32 stores programs executed by the processing unit 31 and various data. The program executed by the processing unit 31 can be composed of a plurality of instructions that can be read by the processing unit 31.

  In the case of the present embodiment, the program executed by the processing unit 31 includes an artificial intelligence program for estimating the characteristics of a golf club suitable for the golfer 100, and the storage unit 32 includes a database 32a for machine learning of artificial intelligence. Is included.

  The I / F unit 33 inputs and outputs data between the external device and the processing unit 31. The I / F unit 33 can include an I / O interface and a communication interface. The measurement device 2 is connected to the information processing device 3 so as to be communicable by wired communication or wireless communication, and these measurement results are acquired by the information processing device 3.

  A display device 4 and an input device 5 are connected to the information processing device 3. The display device 4 is an electronic image display device such as a liquid crystal display device, for example, and displays the processing result of the information processing device 3. The input device 5 is a mouse or a keyboard, and receives data input and operation instructions for the information processing device 3.

<Overview of club selection support>
In the present embodiment, the swing motion of the golfer 100 is measured by the measuring device 2, and the information processing device 3 that functions as artificial intelligence identifies the club characteristics of the golf club that matches the golfer 100. As a preparatory step, a club characteristic that matches the characteristics of the golf swing motion is given to the artificial intelligence as teacher data for learning. If teacher data is not provided, enormous input data is required. However, by providing teacher data and learning to artificial intelligence, the amount of data required to form an algorithm can be reduced. <Artificial intelligence learning>
FIG. 2 is a flowchart showing a procedure related to learning of artificial intelligence. In S <b> 1, measurement of swing motions of a plurality of testers and a hit test of a plurality of types of golf clubs using these testers are performed. For example, the number of testers is preferably 100 or more in terms of improving the accuracy of machine learning. First, the measurement of the swing motion will be described.

  The swing motion is measured using the same device as the measuring device 2 constituting the system 1 in FIG. 1 or a device having an equivalent function. The measurement result of the swing motion extracted as the feature amount may be the whole from the address to the finish, or may be a part of the range. In the present embodiment, the range from the top to the impact where golfer characteristics are likely to appear is targeted. FIG. 3A is an explanatory diagram thereof.

  FIG. 3A shows a state in which the tester T swings with the golf club GC and has an impact. A measuring device 2 is attached to the golf club GC, and its swing motion is measured. The golf club GC may be a club that is usually used by the tester T as long as it is a type of club (a driver in this embodiment) that is subject to selection support. In FIG. 3A, the trajectory BS indicates the trajectory of the golf head during the backswing, and the trajectory DS indicates the trajectory of the golf head from the top (TOP) to the impact (IP).

  The measuring device 2 measures the behavior of the golf club GC from the address to the follow-through after impact, and uses the measurement result from the top (TOP) to the impact (IP) as the swing feature data. FIG. 4 illustrates the measurement result D0 and the swing information Din generated from the measurement result D0. The swing information Din constitutes swing characteristic data of the golf swing operation. In the example of the figure, a measurement result of a tester “A” is shown.

  The measurement result D0 is time-series data representing the behavior of the golf club GC in a predetermined time unit (here, 0.001 second). In the case of the present embodiment, the acceleration in the three-axis directions of X, Y, and Z, Including angular velocity around these three axes. That is, it is data of three-dimensional acceleration and angular velocity of the golf club GC. At this time, the X-axis is a shaft vertical axis direction, the Y-axis is a hitting ball direction (parallel to the face vertical surface), and the Z-axis is a right-handed coordinate system in which the direction from the head toward the hand is positive. From these data, top data and impact data are specified. For example, at the top, the angular velocity around the X-axis or Y-axis tends to change from negative to positive, so this can be specified as the top data. In the impact, since the acceleration in the Y-axis direction tends to decrease rapidly, the minimum value of the Y-axis acceleration can be specified as the impact data. In the case of the example in the figure, 0.968 second data is the top, and 1.364 second data is the impact. Therefore, data D1 from 0.968 seconds to 1.364 seconds is used as the swing feature data.

  The swing tempo varies from person to person. Therefore, the time (number of data) from the top to the impact is different. In terms of improving the accuracy of machine learning, the number of data is preferably uniform. In the case of this embodiment, the specified number of data is 1000 frames, and excess or deficiency is thinned out or interpolated by a known data processing technique. In the example of FIG. 4, the number of data D1 is 396, but this is interpolated to obtain 1000 frames of swing information Din. Although the data sequence of the swing information Din is not data in a predetermined time unit, it can be referred to as time-series data because it represents a temporal change in the acceleration and angular velocity of the golf club GC.

  In the present embodiment, the swing information Din is configured as a data string of the acceleration and angular velocity of the golf club. As an example, waveform data) is not questioned. The swing information Din may be anything as long as a series of behaviors of the tester or golf club during the swing can be specified.

  Next, the impact test will be described. In the hitting test, a tester tests a plurality of types of golf clubs having different club characteristics, and measures the behavior of the golf club and the ball. FIG. 5 shows the hit test data D10 and the suitable club information Dout. The suitable club information Dout constitutes teacher data. In the example of the figure, the test result of the tester “A” is shown.

  The hit test data D10 is roughly classified into information on the golf club used in the hit test and information on the hit result. In the example of the figure, it is shown that the hit test was performed on 14 clubs (drivers) # 01 to # 14. The 14 clubs are clubs in which at least one of a plurality of types of club feature values is different. The club feature amount is a design value that characterizes the golf club. In the case of the example of FIG. 5, shaft flex (R, SR, S, X, etc.) indicating the hardness of the shaft, the weight of the shaft, and the center of gravity distance of the head (the distance between the center of gravity of the head and the shaft axis) are illustrated. In addition to this, the club feature amount includes, for example, the head weight, the head centroid angle, the head centroid depth, the head centroid height, the head loft angle, the head lie angle, the head face angle, the shaft torque, The rigidity of the shaft, the moment of inertia of the head, the moment of inertia of the entire club, the position of the center of gravity of the entire club, the shaft length, the weight of the grip, etc. can be mentioned.

  The club characteristic is a classification of the golf club based on the club feature amount. In the present embodiment, there are four types of club characteristics 1 to 4, but there may be five or more types. Three or less types may be used, but two types do not contribute much to narrowing down the recommended golf club.

  In the present embodiment, the club characteristics are classified based on a plurality of types of club feature amounts. Club characteristics classified by one type of club feature amount can also be applied, but the suitability of a recommended golf club to a golfer may be reduced. If there are too many types of club features that classify club characteristics, the classification becomes complicated. Therefore, principal component analysis may be performed on a plurality of types of club feature amounts, and dimension compression may be performed. FIG. 3B is a schematic diagram showing an example.

  FIG. 3B has three classification axes U, V, and W, and the club characteristics 1 to 4 are classified by dividing the space defined by these three axes into four. At least one of the three axis values can be a dimension-compressed value obtained by subjecting a plurality of types of club feature amounts to principal component analysis.

For example, the value of the U axis is
U = coefficient 1 × club weight + coefficient 2 × center of gravity position of the whole club + coefficient 3 × shaft flex, (shaft flex expresses R, SR, etc.)
The V-axis value is
V = coefficient 4 × center of gravity of head + coefficient 5 × shaft torque,
The value of the W axis is the moment of inertia of the entire club,
It can be. In this case, the U axis and the V axis are values subjected to dimension compression, and the W axis is a value not subjected to dimension compression.

  Returning to FIG. 5, the impact result will be described. The hitting result is an evaluation standard of the golf club that matches the swing motion of the tester. In the example of FIG. 5, four criteria of head speed, golf ball flight distance, face angle at impact, and sensory evaluation are illustrated. The face angle at the time of impact is the orientation of the face surface of the head at the time of impact, and is measured as 0 degree when it is perpendicular to the flying ball direction on a plane parallel to the horizontal plane. Head speed, flight distance, and face angle at impact can be measured with various measuring devices. For example, it is a ballistic measuring device disposed behind the flying ball line with respect to the hit golf ball. For example, TRACKMAN manufactured by TRACKMAN can be used as such a measuring instrument.

  The sensory evaluation is obtained by quantifying the tester's bodily sensation items such as hitting sound, hitting feeling, and ease of swinging. 1 is the worst and 5 is the best. The sensory evaluation may be composed of one type of bodily sensation item, or may be composed of a plurality of bodily sensation items. A plurality of bodily sensation items may be values obtained by dimension compression by principal component analysis. For example, sensory evaluation = coefficient 6 × sounding sound value + coefficient 7 × hitting feeling value + coefficient 8 × easy to swing may be set.

  The evaluation criteria are not limited to the four types in FIG. 5, and may be, for example, the side spin amount of the golf ball, the back spin amount of the golf ball, or the like. In this embodiment, a plurality of types of evaluation criteria are used, but one type may be used.

  The suitable club information Dout is created from the hit test data D10. The suitable club information Dout is information indicating the club characteristics of the golf club having the highest evaluation for each evaluation criterion. In the hit test data D10 of FIG. 5, club # 03 has the fastest head speed. Since the club characteristic of club # 03 is “2”, the suitable club characteristic regarding the head speed of tester A is “2”. Club # 09 has the longest flight distance. Since the club characteristic of the club # 09 is “1”, the suitable club characteristic regarding the flight distance of the tester A is “1”. Club # 12 has the face angle at the time of impact closest to the square (0 degree), and the suitable club characteristic regarding the face angle at the time of impact of tester A is “4”. The club # 02 has the best sensory evaluation, and the club characteristic that matches the sensory evaluation of the tester A is “5”. Although the conforming club characteristics for each evaluation standard are basically one type, when the scores are the same, a plurality of types of club characteristics may be associated with each other.

  In the case of the present embodiment, the conforming club information Dout indicates the relationship between the evaluation criteria and the club characteristics. This means that the golf club used for the hit test may be different for each tester. That is, in the example of FIG. 5, the tester A performed the hit test with 14 clubs (drivers) # 01 to # 14, but another tester does not need to use the same 14 clubs. It is only necessary that the hit test is performed on a plurality of types of golf clubs having different club characteristics.

  Returning to FIG. A combination of the swing information Din and the suitable club information Dout is prepared for each tester by the hit test of S1 described above. In S2, data used for machine learning is created. As shown in FIG. 6, the data Dt is a combination of swing information Din and matching club information Dout which is teacher data. That is, FIG. 6 exemplifies a combination of swing feature data and teacher data of the swing motion related to the tester A, and this is created for the tester. The swing information Din and the suitable club information Dout have a relationship in which the former is input and the latter is output. These data are input to the information processing apparatus 3 and accumulated in the database 32a of the storage unit 32.

  In S3, machine learning is executed in the information processing apparatus 3. The processing unit 31 reads out the data Dt stored in the database 32a, performs machine learning, and generates an artificial intelligence algorithm that derives the suitable club information Dout from the swing information Din. The generated algorithm is stored in the storage unit 32. Even after the algorithm is generated, new swing feature data and teacher data may be periodically added to perform machine learning again to update the algorithm.

<Selection support processing>
Next, assistance processing when a golfer selects a golf club using the system 1 shown in FIG. 1 will be described. The information processing apparatus 3 of the system 1 has been machine-learned by the above-described procedure. FIG. 7 is a flowchart illustrating an example of the selection support process, which is a process executed by the processing unit 31 of the information processing apparatus 3.

  In S <b> 11, the swing motion of the golfer is measured by the measuring device 2. Here, the golfer 100 is actually hit with a golf ball by the golf club 101, and the behavior of the golf club 101 is measured by the measuring device 2. The golf club 101 may be a club that golfers usually use.

  In S <b> 12, the measurement result is acquired from the measurement device 2. The information processing device 3 acquires data similar to the measurement result D0 of FIG. In S13, swing information D11 is created from the measurement result acquired in S12. The swing information D11 is created in the same manner as the swing information Din in FIG.

  In S14, the artificial intelligence selects the club characteristic suitable for the golfer for each evaluation criterion from the swing information D11 created in S13, and generates the club characteristic information D12. In the example of FIG. 7, the characteristic 3 is selected for the head speed and the flight distance, the characteristic 2 is selected for the face angle at the time of impact, and the characteristic 4 is selected for the sensory evaluation.

  In S15, product information D13 of the golf club is acquired. The product information D13 is stored in the storage unit 32. The product information D13 includes information on the type of golf club, club characteristics, and specifications. In the example of the figure, club characteristics and specifications are recorded for nine types of golf clubs A to I. The specification corresponds to the club feature amount. When viewed in terms of head speed and flight distance, golf clubs E and G are suitable for golfers. Further, when viewed from the face angle at the time of impact, the golf clubs C and D are suitable for the golfer. From the viewpoint of sensory evaluation, the golf clubs B and H are suitable for the golfer.

  In S16, information such as a recommended golf club is displayed on the display device 4. Here, information on golf clubs suitable for golfers may be displayed for each of the four evaluation criteria, or information on golf clubs suitable for golfers may be displayed for one or more evaluation criteria desired by the golfer. May be. In addition to the golf club information, a golfer's swing measurement result may be displayed.

  Thus, the selection support process ends. Thereafter, the golfer can actually experience whether or not the golf club fits himself / herself by making a trial hit with the recommended golf club displayed in S16. In this embodiment, by using artificial intelligence, it is possible to analyze a wider range of a series of swing motions and discriminate suitable club characteristics. For this reason, more versatile judgments can be made, and the club characteristics suitable for the golfer can be discriminated more accurately.

<Other embodiments>
In the system of FIG. 1, the measurement device 2 and the information processing device 3 are disposed at a relatively short distance and can be installed at a store or the like. However, other configuration examples can be employed. In addition, a measuring device other than that shown in FIG.

  FIG. 8 illustrates another configuration example of the selection support system 1. In the configuration example shown in the figure, the information processing apparatus 3 can communicate with a communication device (such as the portable terminal 112 or the personal computer 115) via the network 110 as a server, and distributes information regarding a golf club. The network 110 is the Internet, for example.

  The configuration example EX1 on the measurement side is a system including the mobile terminal 112 and the measurement device 2. The mobile terminal 112 is, for example, a smartphone, and includes a short-range wireless communication function with the measurement device 2 and a wireless communication function via the network 110 and a base station (not shown). The measurement result of the measurement device 2 is transmitted to the mobile terminal 112. The portable terminal 112 transmits the received measurement result to the information processing device 3 as it is or as data in a predetermined format that can be processed on the information processing device 3 side. The information processing device 3 specifies a recommended golf club and transmits the information to the mobile terminal 112. The mobile terminal 112 displays the received information. That is, S11 of FIG. 7 is performed by the measuring device 2, S12 is performed by the portable terminal 112 and the information processing device 3, S13 and S14 are performed by the information processing device 3, and S15 is performed by the portable terminal 112 and the information processing device 3. Execute S16 on the portable terminal 112. The execution method is not limited to this. For example, S14 may be executed by the information processing apparatus 3, the information generated in S14 may be transmitted to the mobile terminal 112, and the recommended golf club may be specified by the mobile terminal 112.

  The measurement-side configuration example EX2 is a system including a personal computer 115 and a plurality of measurement devices 2A. The measuring device 2A is a photographing device such as a video camera. The personal computer 115 has a processing function for images taken by the photographing apparatus 2A and a wireless communication function via the network 110. The golfer makes a test shot in a test chamber or the like. A golfer is photographed from multiple directions by a plurality of photographing devices 2 </ b> A in a test hit room or the like, and the three-dimensional behavior of the golf club 101 is photographed. The captured image is captured and analyzed by the personal computer 115 and transmitted to the information processing apparatus 3 as data in a predetermined format that can be processed on the information processing apparatus 3 side. The information processing device 3 identifies the recommended golf club and transmits the information to the personal computer 115. The personal computer 115 displays the received information. That is, S11 in FIG. 7 is performed by the measuring device 2A, S12 is performed by the personal computer 115 and the information processing device 3, S13 and S14 are performed by the information processing device 3, and S15 is performed by the personal computer 115112 and the information processing device 3. , S16 is executed on the personal computer 115. The execution method is not limited to this. For example, S14 may be executed by the information processing apparatus 3, the information generated in S14 may be transmitted to the personal computer 115, and the recommended golf club may be specified by the personal computer 115.

1 selection support system, 2 measuring device, 3 information processing device

Claims (11)

An acquisition means for acquiring a measurement result of the golf swing movement of the golfer;
Selecting means for selecting a club characteristic suitable for the golfer from a plurality of types of club characteristics of the golf club based on the measurement result;
The selection means includes
For a plurality of testers, based on a machine learning result of teacher data indicating club characteristics adapted to the golf swing motion of each tester, club characteristics suitable for the golfer are selected.
A selection support apparatus characterized by that. The selection support apparatus according to claim 1,
The plurality of types of club characteristics are classified based on a plurality of types of club features.
A selection support apparatus characterized by that. The selection support apparatus according to claim 1,
The plurality of types of club characteristics are classified based on a dimensional compression value of a plurality of types of club features.
A selection support apparatus characterized by that. The selection support apparatus according to claim 1,
The measurement result includes time-series data of acceleration and angular velocity of a golf club during a swing,
A selection support apparatus characterized by that. The selection support apparatus according to claim 1,
The selection means selects a club characteristic suitable for the golfer based on the measurement result from the top to the impact.
A selection support apparatus characterized by that. The selection support apparatus according to claim 1,
The selection means selects the club characteristics for each of a plurality of types of evaluation criteria,
The teacher data is data indicating club characteristics adapted to the golf swing motion of each tester for the plurality of testers for each of the plurality of types of evaluation criteria.
A selection support apparatus characterized by that. The selection support apparatus according to claim 6,
The plurality of types of evaluation criteria includes at least one of head speed, golf ball flight distance, face angle at impact, and sensory evaluation.
A selection support apparatus characterized by that. The selection support apparatus according to claim 6,
The selection means selects the club characteristics using sensory evaluation as an evaluation criterion,
The teacher data is data indicating club characteristics adapted to a swing operation of each tester with respect to the plurality of testers using the sensory evaluation as an evaluation criterion,
The sensory evaluation is a numerical value of a plurality of bodily sensation items and is defined by a dimension-compressed value.
A selection support apparatus characterized by that. A measuring device for measuring the golf swing movement of the golfer;
An information processing apparatus that selects a club characteristic suitable for the golfer from a plurality of types of club characteristics of the golf club based on the measurement result of the measurement apparatus;
The information processing apparatus includes:
For a plurality of testers, based on a machine learning result of teacher data indicating club characteristics adapted to the golf swing motion of each tester, club characteristics suitable for the golfer are selected.
A selection support system characterized by that. A measurement process for measuring the golf swing movement of the golfer;
Selecting a club characteristic suitable for the golfer from a plurality of types of club characteristics of the golf club based on the measurement result of the measurement step,
In the selection step,
For a plurality of testers, based on a machine learning result of teacher data indicating club characteristics adapted to the golf swing motion of each tester, club characteristics suitable for the golfer are selected.
A selection support method characterized by that. It is the selection assistance method of Claim 10, Comprising:
The teacher data is generated based on a result of the plurality of testers testing a plurality of types of golf clubs.
A selection support method characterized by that.

Images