WO2023277381A1 - Swing analysis apparatus and swing analysis method - Google Patents

Abstract

Presented are a swing analysis apparatus and a swing analysis method. The swing analysis apparatus according to an embodiment comprises: an input/output unit for obtaining a swing image obtained by photographing the appearance of a golfer; a memory storing a program for carrying out machine learning; and a control unit which executes the program to carry out machine learning for the swing image, wherein the control unit detects a swing error of the golfer from the swing image by using a trained machine learning model, recommends a drill image on the basis of the swing error, and recommends a mission corresponding to the drill image.

Description

Swing analysis device and swing analysis method

Embodiments disclosed herein relate to a swing analysis device and a swing analysis method, and more particularly, to analyze a swing image of a golfer's swing and provide a drill image and a mission according to the analysis result. and methods.

As the popularity of golf increases, the needs of golfers who want to improve their golf skills are growing.

On the other hand, golfer's swing posture is important to improve the distance, etc. In order to find and correct problems in swing posture, golf pros are located at the site when golfers play golf, so they receive lessons separately, or swing video recorded golf swings. It is possible to deliver this to professional golfers and receive correction accordingly.

However, since the prior art for posture correction as described above requires a professional golfer, there is a problem in that it is difficult to correct the posture when there is no professional golfer to be coached. There is a problem with being coached.

In relation to this, Korean Patent Publication No. 10-2001-0102751, which is a prior art document, takes a video of one's own swing form and sends the data to the Internet site founder via the Internet or by mail, and the Internet site creator who receives this information informs the professional golfer contracted with him/herself. It discloses a method of analyzing and requesting data and uploading the analyzed contents to the professional golfer's website.

The above published patent only allows the golfer to photograph the swing and sends the recorded video to the professional golfer for analysis, so it is difficult to contact the professional golfer or the cost incurred in receiving posture correction from the professional golfer is burdensome. Golfers have a problem in that it is difficult to correct their posture. Furthermore, there is a problem that it is difficult to know what kind of effort the golfer should make to correct the posture, only to receive posture correction.

Therefore, it is necessary to develop a technology to solve the above problems.

On the other hand, the above-mentioned background art is technical information that the inventor possessed for derivation of the present invention or acquired in the process of derivation of the present invention, and cannot necessarily be said to be known art disclosed to the general public prior to filing the present invention. .

Embodiments disclosed herein are aimed at presenting a swing analysis device and a swing analysis method.

In addition, the embodiments disclosed herein are aimed at presenting a device and method for analyzing a swing image using artificial intelligence.

In addition, the embodiments disclosed herein are intended to provide an apparatus and method for improving a golfer's swing ability by providing a drill image based on a swing image analysis result.

In addition, the embodiments disclosed herein are aimed at providing a device and method for improving a golfer's swing ability by providing a mission based on a swing image analysis result.

As a technical means for achieving the above-mentioned technical problem, according to an embodiment described in this specification, as a swing analysis device, an input/output unit for acquiring a swing image of a golfer and a program for performing machine learning are provided. A memory to be stored, and a controller that executes machine learning on the swing image by executing the program, wherein the controller detects a golfer's swing error from the swing image using the learned machine learning model, and detects the swing error. Based on this, a drill image may be recommended, and a mission corresponding to the drill image may be recommended.

In addition, as a technical means for achieving the above-described technical problem, according to an embodiment described in this specification, as a method for a swing analysis device to analyze a golfer's swing, a golfer's swing image from a swing image using a learned machine learning model. The method may include detecting a swing error, recommending a drill image based on the swing error, and recommending a mission corresponding to the drill image.

According to one of the above-described problem solving means, it is possible to present a swing analysis device and a swing analysis method.

According to one of the above-described problem solving means, it is possible to present a device and method for analyzing a swing image using artificial intelligence.

According to one of the above-described problem solving means, it is possible to propose an apparatus and method for improving a golfer's swing ability by providing a drill image based on a swing image analysis result.

According to one of the above-described problem solving means, it is possible to propose an apparatus and method for improving a golfer's swing ability by providing a mission based on a swing image analysis result.

Effects obtainable from the disclosed embodiments are not limited to those mentioned above, and other effects not mentioned are clear to those skilled in the art from the description below to which the disclosed embodiments belong. will be understandable.

1 is a configuration diagram for explaining a swing analysis device according to an embodiment disclosed herein.

2 and 3 are block diagrams for explaining a swing analysis device according to an embodiment disclosed herein.

4 is an exemplary view for explaining a swing analysis device according to an embodiment disclosed herein.

5 is a flowchart illustrating a swing analysis method according to an embodiment disclosed herein.

Hereinafter, various embodiments will be described in detail with reference to the accompanying drawings. Embodiments described below may be modified and implemented in various different forms. In order to more clearly describe the characteristics of the embodiments, detailed descriptions of matters widely known to those skilled in the art to which the following embodiments belong are omitted. And, in the drawings, parts irrelevant to the description of the embodiments are omitted, and similar reference numerals are attached to similar parts throughout the specification. Also in the following description, like components may be indicated by like reference numerals even though they are shown in different drawings.

Throughout the specification, when a component is said to be “connected” to another component, this includes not only the case of being “directly connected” but also the case of being “connected with another component intervening therebetween”. In addition, when a certain component "includes" a certain component, this means that other components may be further included without excluding other components unless otherwise specified.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.

1 is a configuration diagram for explaining a swing analysis device according to an embodiment disclosed herein, and FIGS. 2 and 3 are block diagrams for explaining a swing analysis device according to an embodiment disclosed herein.

The swing analysis device 100 acquires and analyzes a swing image of a golfer's swing, and recommends a drill image and mission based on the obtained swing image.

The swing analysis device 100 may be implemented in any form of a user terminal or a server-client system, and when implemented as a server, components constituting the swing analysis device 100 are physically separated from a plurality of servers. or can be performed on a single server.

According to one embodiment, as shown in FIG. 1, the swing analysis device 100 may be implemented as a server-client system, and includes a user terminal 10 and a server 20 for this purpose, and the user terminal 10 and server 20 may communicate over network N.

The user terminal 10 may be implemented as a computer, portable terminal, television, wearable device, etc. capable of accessing a remote server through a network N or connecting to other terminals and servers. Here, the computer includes, for example, a laptop, desktop, or laptop equipped with a web browser, and the portable terminal is, for example, a wireless communication device that ensures portability and mobility. , PCS(Personal Communication System), PDC(Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), GSM(Global System for Mobile communications), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet), Smart Phone, Mobile WiMAX (Mobile Worldwide Interoperability for Microwave Access), etc. (Handheld)-based wireless communication device may be included. In addition, television may include IPTV (Internet Protocol Television), Internet TV (Internet Television), terrestrial TV, cable TV, and the like. Furthermore, a wearable device is a type of information processing device that can be worn directly on the human body, such as, for example, a watch, glasses, accessories, clothes, shoes, etc. can be connected with

The server 20 may be implemented as a computer capable of communicating with the user terminal 10 on which an application for interaction with a golfer or a web browser is installed and a network, or implemented as a cloud computing server. In addition, the server 20 may include a storage device capable of storing data or may store data through a third server.

Additionally, the swing analysis device 100 may further include a kiosk (not shown). A kiosk (not shown) may communicate with the server 20 via a network N.

According to an embodiment, such a kiosk (not shown) may provide information on a recommended mission, determine whether or not the mission has been performed, whether the mission is successful, increase the golfer's level, and provide a reward accordingly. In addition, the kiosk (not shown) may output a swing error obtained by analyzing a swing image, and also output ball data (eg, spin value, flight distance, etc.) obtained by analyzing the movement of a detected golf ball or golf club, or Club data (for example, the type of golf club, etc.) related to the golf club used by the golfer may be output.

As shown in FIG. 2 , the swing analysis device 100 may include an input/output unit 210, a control unit 220, a communication unit 230, and a memory 240.

The input/output unit 210 may include an input unit for receiving an input from a golfer and an output unit for displaying information such as a work result or a state of the swing analysis device 100 . For example, the input/output unit 210 may include an operation panel for receiving a golfer's input and a display panel for displaying a screen.

Specifically, the input unit may include devices capable of receiving various types of user inputs, such as a keyboard, a physical button, a touch screen, a camera, or a microphone. Also, the output unit may include a display panel or a speaker. However, the input/output unit 210 is not limited thereto and may include a configuration supporting various input/output.

Accordingly, according to an embodiment, when a golfer's swing is captured by a camera as an input unit, the output unit may output a recommended drill image or mission by analyzing the captured swing image.

Meanwhile, the control unit 220 controls the overall operation of the swing analysis device 100, and may include a processor such as a CPU or GPU. The control unit 220 may control other components included in the swing analysis device 100 to perform an operation corresponding to a user input received through the input/output unit 210 .

For example, the controller 220 may execute a program stored in the memory 240, read a file stored in the memory 240, or store a new file in the memory 240.

Operations of the control unit 220 will be described in more detail with reference to FIG. 4 , and FIG. 4 is an exemplary diagram for explaining the swing analysis device 100 according to an embodiment disclosed herein.

The communication unit 230 may perform wired/wireless communication with other devices or networks. To this end, the communication unit 230 may include a communication module supporting at least one of various wired/wireless communication methods. For example, the communication module may be implemented in the form of a chipset.

The wireless communication supported by the communication unit 230 may be, for example, Wireless Fidelity (Wi-Fi), Wi-Fi Direct, Bluetooth, Ultra Wide Band (UWB), or Near Field Communication (NFC). In addition, wired communication supported by the communication unit 230 may be, for example, USB or High Definition Multimedia Interface (HDMI).

Various types of data such as files, applications, and programs may be installed and stored in the memory 240 . The controller 220 may access and use data stored in the memory 240 or may store new data in the memory 240 . Also, the controller 220 may execute a program installed in the memory 240 . 2, for example, a program for performing a swing analysis method may be installed in the memory 240, or a program for performing machine learning may be installed, or a learned machine learning model program. can be installed.

According to one embodiment, upon receiving an input requesting a swing posture analysis from a golfer through the input/output unit 210, the controller 220 may execute a program for a swing analysis method stored in the memory 240.

Meanwhile, referring to FIG. 3 , the control unit 220 may include a pre-processing unit 310, an error detection unit 320, a drill recommendation unit 330, and a mission recommendation unit 340.

The pre-processing unit 310 according to an embodiment may acquire a swing image in order to extract a swing error of a golfer's posture from the swing image, and may perform pre-processing on the obtained swing image.

For example, the pre-processing unit 310 may obtain a swing image through the input/output unit 110 .

Also, for example, the pre-processing unit 310 may perform pre-processing on the swing image by correcting brightness, resolution, size, etc. of the swing image. When golf play is played outdoors, the brightness and resolution of the swing video may vary depending on the amount of sunlight, etc. Resolution, size, etc. may vary for each screen golf system. Reflecting this reality, it is possible to perform pre-processing on the swing image so that the learned machine learning model can effectively output the result value.

Also, for example, the pre-processing unit 310 may perform pre-processing by extracting a region including a golfer from a swing image. When the golfer's swing is photographed, a person or a feature other than the golfer may be photographed. Therefore, a region to be analyzed can be extracted as a swing image in the photographed image.

To this end, the pre-processing unit 310 may use a machine learning model. For example, using YOLO (You Only Look Once), a bounding box may be set for an object in a swing image and an image within the bounding box may be extracted, Alternatively, the object may be detected using a deep learning model in which feature points such as golf clubs are learned.

Meanwhile, the error detection unit 320 may detect a swing error by analyzing the swing image. At this time, the error detection unit 320 may detect a swing error by analyzing the preprocessed swing image.

The error detection unit 320 may input a swing image using the learned machine learning model and obtain an error related to the input swing image.

According to an embodiment, the error detection unit 320 may train a machine learning model to output a swing error when a swing image is input.

For example, when a swing image is input, a machine learning model may be trained to output a swing error indicating a problem in a golfer's posture when swinging.

According to another embodiment, the error detection unit 320 may train a machine learning model to output a reference image marked with a reference line when a swing image is input.

For example, a machine learning model is trained to output a reference image when a swing image is input, and when a reference image with a reference line is collected by crawling through the web and an image from which the reference line is deleted is input as a swing image, the reference image is displayed. A machine learning model can be trained to output this.

In addition, for example, when a swing image is input, a machine learning model may be trained to extract a golfer's skeleton from the swing image, and accordingly, the error detection unit 320 extracts and identifies the golfer's joints and body parts. Reference lines connecting the affected joints or body parts can be displayed on the swing image. Accordingly, the error detection unit 320 may output a reference image in which a reference line is displayed for identifying problems in the golfer's posture.

In relation to this, as shown in (a) of FIG. 4, when the swing image 400 is input, the error detection unit 320, as shown in (b) of FIG. A reference image 401 in which each reference line 410 connecting the crown and the pelvis is displayed may be output.

In addition, the error detection unit 320 may analyze swing errors of the golfer based on the reference lines, and may determine possible swing errors by considering angles between a plurality of reference lines, distances between reference lines, and relative positions between reference lines. . For example, the error detection unit 320 may analyze that an early extension phenomenon has occurred as a swing error through an angle between the reference line 410 and the reference line 411 .

The error detection unit 320 may provide a reference image 401 in which reference lines 410 and 411 are displayed on the swing image, as shown in FIG. 4 , while outputting a swing error related to the swing image. Referring to the reference image 401, the golfer can check the basis for the swing error.

In addition, the error detection unit 320 may obtain golfer's feedback on the reference image, and when the feedback is obtained, a machine learning model may be trained again based on the feedback.

For example, the golfer may determine that the reference lines 410 and 411 in the reference image 401 are incorrectly displayed and correct the reference line, and the error detection unit 320 may output the reference image reflecting the corrected reference line. You can retrain the running model.

Meanwhile, the error detection unit 320 may extract one or more swing errors from the swing image.

That is, the error detection unit 320 may extract a plurality of swing errors from the swing image, and when the plurality of swing errors are extracted, one swing error may be selected from among the extracted swing errors.

On the other hand, if one swing error is extracted from the swing image, the error detection unit 320 may transmit the one error to the drill recommendation unit 330 so that it can be used as an error for recommending a drill image.

Hereinafter, for convenience of description, the swing error extracted from the swing image is referred to as a 'first swing error', and the swing error selected from among the first swing errors for recommending a drill image is referred to as a 'second swing error'.

According to an embodiment, the error detection unit 320 may select a second swing error from among one or more first swing errors based on swing errors extracted from past swing images of the golfer.

For example, among the first swing errors extracted from the current swing image, one of the remaining first swing errors excluding the first swing errors extracted from the past swing image may be selected as the second swing error. That is, when the error detection unit 320 diagnoses the slide and sway phenomena as the first swing error in the current swing image, the sway has been extracted as the first swing error in the golfer's past swing image. If so, the slide excluding the sway can be determined as the second swing error.

Alternatively, for example, among the first swing errors extracted from the current swing image, the number of times extracted from the past swing image is counted, the first swing errors are sorted according to the number of extractions, and the first swing error extracted with the highest number of times can be selected as the second swing error. When the error detection unit 320 diagnoses a reverse pivot and a slide phenomenon as the first swing error in the current swing image, the reverse pivot phenomenon 2 times and the slide phenomenon 5 times from 5 past swing images of the golfer If extracted twice, the slide can be determined as the second swing error. At this time, the past swing image selected for selection of the second swing error may be a swing image that was not used for recommendation of the drill image.

According to another embodiment, the error detection unit 320 may select a second swing error from one or more first swing errors based on the golfer's past mission performance information. At this time, the past mission performance information is information about the golfer's reaction to the mission assigned to the golfer in the past, and may include, for example, information about whether or not the mission was accomplished, the degree of performance when the mission was performed, and the like.

Therefore, for example, when a golfer performed a mission assigned in the past, the error detection unit 320 stores mission performance information as past mission performance information, and among the first swing errors, by referring to the past mission performance information, the past mission performance information is stored. A second swing error may be selected as one of the first swing errors other than the swing errors related to the mission achieved by the golfer. The error detection unit 320 receives a squat exercise mission as a past mission and if 'squat exercise mission complete' is stored as past mission performance information as the golfer performs the mission, the first swing error in which the mission related to the squat exercise is matched It is possible to select the second swing error from among the remaining first swing errors except for .

Meanwhile, the error detection unit 320 may determine a third swing error based on the second swing error. In this case, the third swing error is information indicating a golfer's body problem, and may include, for example, lack of flexibility for each body part, lack of muscle strength for each body part, lack of rotational power for each body part, lack of stability, and lack of balance.

To this end, the error detection unit 320 may store body problems that cause the second swing error as a table. For example, 'pelvic distortion' and 'lack of pelvic flexibility' may be stored as body problems in response to the second swing error of 'sway'.

According to an embodiment, the error detection unit 320 may provide the golfer with a body problem that causes the second swing error, and determine the problem selected by the golfer as the third swing error. For example, when 'lack of hip muscles' is selected as 'left and right arm imbalance', 'pelvic distortion', and 'lack of hip muscles', which cause the second swing error, the error detection unit 320 detects 'hip muscles' Insufficient' can be determined as the third swing error.

As another embodiment, the error detection unit 320 may determine, as a third swing error, a body problem selected by another golfer determined to be similar to the golfer among body problems that cause the second swing error. At this time, other golfers similar to the golfer have the same profile as the golfer (for example, gender, age, place of residence, etc.), have the same golf playing period, or have a geographical location where analysis of swing images is requested (for example, country club name, screen golf location, etc.) may be the same golfer. Therefore, for example, when the matched body problems as the cause of the golfer's second swing error are 'pelvic distortion' and 'lack of back flexibility', the problem selected by other golfers of the same age as the golfer is 'lack of back flexibility' When , the error detection unit 320 may determine 'insufficient waist flexibility' as the third swing error.

As described above, the error detection unit 320 can diagnose the golfer's body problem by amplifying the second swing error.

The drill recommendation unit 330 may recommend a drill image corresponding to the swing error.

To this end, the drill recommendation unit 330 may store a drill image. At this time, the 'drill image' refers to an image including explanations or precautions for golf posture correction, or descriptions of exercises for golf posture correction, and the drill recommendation unit 330 is the swing analysis device 100 A plurality of drill images may be stored by crawling the images posted on the third server, which is an external server. At this time, the third server is a server that stores a plurality of images, and may be, for example, a portal site server, an OTT (Over The Top) server, and the like.

In addition, the drill recommendation unit 330 may match and store a drill image with a swing error.

According to an embodiment, the drill recommendation unit 330 may analyze which swing error the drill image is matched with, match the drill image to the corresponding swing error, and store the drill image as a table.

To this end, the drill recommendation unit 330 analyzes the title of the image collected as the drill image, the frame included in the drill image, or the audio included in the drill image to determine which swing error the corresponding image is related to. . For example, if 'slide' is included in the title of the collected image, the corresponding image is determined as an image for correcting the slide, and the drill recommendation unit 330 may store the corresponding image as a drill image in 'slide' as a swing error. . Alternatively, for example, if the word 'pelvis twist' is collected from the audio included in the collected image, the drill recommendation unit 330 may store the corresponding image as a drill image in 'pelvis twist' as a swing error.

Accordingly, when a golfer's swing error is acquired from the error detection unit 320, a drill image corresponding to the swing error may be retrieved and output.

According to another embodiment, the drill recommendation unit 330 may train a machine learning model to output a drill image when a swing error is input.

In addition, when the golfer's swing error is obtained from the error detection unit 320, the drill recommendation unit 330 may determine a drill image to be recommended according to input of the swing error using the learned machine learning model.

If there are a plurality of drill images whose output is determined as described above, the drill recommendation unit 330 may additionally calculate a drill preference for each of the plurality of drill images, align the plurality of drill images, and provide the drill images to the golfer.

The 'drill preference' is a score representing a golfer's preference for a drill image.

According to an embodiment, drill preference may be determined when collecting drill images. For example, based on at least one of the number of views, the number of recommendations, and the number of likes in a third server platform on which the collected drill images are posted. It may be determined, and for example, drill preference may increase in proportion to the number of views, recommendations, or likes. Through this, you can provide popular videos to golfers online.

According to another embodiment, drill preference may be determined according to feedback from other golfers who have watched drill images.

For example, when a drill image is provided to a golfer, the drill preference of the corresponding drill image may be calculated according to the number of views by counting the number of views. Alternatively, for example, when a drill image is provided to a golfer, the viewing time may be counted, and the drill preference of the corresponding drill image may be calculated according to the viewing time. Alternatively, for example, when a drill image is provided to a golfer, the drill preference of the corresponding drill image may be calculated by counting the number of times 'likes' are obtained from the golfer or recommendations to other golfers are input.

Or, for example, a swing error derived by acquiring and analyzing a swing image of a golfer who has been provided with a drill image after a predetermined period of time has elapsed since the provision of the drill image is irrelevant to the provided drill image If this is determined, it is determined that the posture of the golfer is corrected or the swing skill is improved due to the corresponding drill image, and the drill preference can be set high. Alternatively, for example, when a drill image is provided and a mission matched to the drill image is provided, the drill preference may be calculated according to the mission achievement rate. For example, the higher the mission achievement rate, the higher the drill preference.

As the drill preference is calculated as described above, the drill recommendation unit 330 may arrange and recommend drill images. At this time, if a predetermined condition is satisfied, some of the drill images may not be recommended.

For example, as a predetermined condition, based on information about the model of the golfer's user terminal registered in the golfer's account and the usage fee plan (for example, whether it is a volume-based system or a flat-rate system) of the golfer's user terminal, among the drill images sorted , drill images having a predetermined capacity or more may be excluded and only the remaining drill images may be provided.

Alternatively, for example, based on the golfer's disease record registered in the golfer account as a predetermined condition, drill images that may aggravate the disease may be excluded from the aligned drill images and the remaining drill images may be provided. For a golfer with a limb, a drill video containing the contents of bending the waist can be excluded. At this time, the determination of whether the drill image may aggravate the disease record is determined by analyzing the comments, comments, audio, images, etc. included in the drill image when collecting the drill image for a predetermined motion, and the content related to the corresponding motion. For the drill image containing this, a positive disease (ie, a disease that improves related to the content in the image) and a negative disease (ie, a disease that worsens related to the content in the image) can be classified, matched to the corresponding drill image, and stored. For example, in a drill video that strengthens the back muscles, if the motion demonstrator made the audio comment, 'Do not do this motion for those with a herniated disc', the drill video to be provided to a golfer with a herniated disc You can exclude from the video and recommend it.

Drill preference can be used to relearn a machine learning model. For example, drill images are sorted according to drill preference, and when a swing error is input, machine learning outputs drill images within a predetermined rank according to the sorted order. The model can be retrained.

Meanwhile, the mission recommendation unit 340 may recommend a mission based on the drill image.

At this time, the mission is information requesting the golfer to perform a predetermined action, and may include information about a specific action, the number of actions, and an action execution period. In addition, the mission may be additionally stored, for example, one or more levels are matched, and even if the operation is the same, the strength of the operation may be changed according to the number of operations or operation duration for each level. Therefore, if the level of the same mission increases, the number of times may increase even if the same body part is trained. .

Therefore, for example, the mission recommendation unit 340 recommends performing the 'squat' operation in 3 sets of 20 times for 2 weeks as a mission, or as a level 1 squat, the basic squat in 3 sets of 20 times, 2 You can recommend a mission to do during the week.

These missions may be preset in the swing analysis device 100 or may be collected by crawling through the web. When a mission is stored by being preset or collected, intensity may be stored differently according to the level of each mission.

Therefore, for example, missions may be matched with drill images and stored as a table, and thus the mission recommendation unit 340 may recommend missions matched with the drill images recommended by the drill recommendation unit 330 .

Alternatively, for example, by using a machine learning model learned to output a mission when a drill image is input, the mission recommendation unit 340 may recommend a mission matched to the drill image recommended by the drill recommendation unit 330. can Accordingly, the drill recommendation unit 330 may output a recommended mission by inputting a drill image to the learned machine learning model.

The mission recommendation unit 340 may calculate the mission preference for each of the plurality of missions for which the recommendation is determined as described above, arrange the plurality of missions in the order of highest mission preference, and provide the golfer with the mission preference.

At this time, the mission preference may be calculated based on the mission recommended to the golfer in the past, and the mission recommendation unit 340 may calculate the mission preference according to the degree in which the corresponding mission is related to the previously recommended mission. For example, mission preference may be calculated low when the corresponding mission is related to a mission recommended in the past, and mission preference may be calculated high if the corresponding mission is unrelated to a mission recommended in the past. Accordingly, for example, if a mission is related to lower body training and a previously recommended mission is related to upper body training or flexibility, the mission preference for the corresponding mission may be set high.

In addition, the mission preference may be calculated in proportion to the number of selections by the golfer or other golfers, and the mission recommendation unit 204 determines the number of times a mission related to the mission is selected by the golfer, or other golfers for whom drill images such as the golfer are recommended. The mission preference for the corresponding mission can be calculated based on the number of times the corresponding mission is selected. For example, if the number of missions related to 'Plank' selected by golfers in the past is higher than other missions, the mission preference for the 'Plank for 2 weeks, 1 minute every day' mission may be determined to be the highest among the plurality of missions. Alternatively, for example, when there are a plurality of other golfers who have been recommended the same drill image as the golfer, the highest mission preference may be set for a mission selected by the highest number of golfers.

In addition, the mission preference may be calculated based on past mission performance information of a mission related to the corresponding mission. The mission recommendation unit 340 may calculate a mission preference low when it is determined that the golfer's achievement level for the mission related to the corresponding mission is low, and a mission preference high when it is determined that the golfer's achievement level is high. Therefore, for example, for the mission of 'Plank for 2 weeks, 1 minute every day', if it is determined that the past golfer performed the plank for 1 minute once a week for the mission 'Plank for 2 weeks, 3 times a week for 1 minute', the golfer for that mission It is determined that the degree of achievement of is low, and the mission preference may be calculated to have a lower value than the mission preference of other missions.

In this way, the mission recommendation unit 340 may arrange missions according to mission preference, select and recommend missions within a predetermined rank.

In addition, the mission recommendation unit 340 recommends a mission to the golfer and then determines whether or not the golfer has performed the mission.

That is, the mission recommendation unit 340 may determine whether the golfer performs the mission selected by the golfer from among the recommended missions.

Whether or not the mission is performed can be determined using the function of the electronic terminal 10 included in the swing analysis device 100 implemented as a server-client system.

For example, it can be judged by analyzing mission performance video obtained by filming a golfer performing a mission. For example, when a golfer who has been given 20 squats as a mission takes a squat exercise video and uploads it as a mission performance video , The mission recommendation unit 340 may analyze the mission performance video and count the number of squats performed by the golfer. Alternatively, for example, as the golfer performing the mission carries out the mission carrying the user terminal, the golfer's movement may be detected by a gyro sensor built in the user terminal, and the number of squats performed by the golfer may be counted accordingly.

Alternatively, whether or not the mission is performed may be determined using a kiosk (not shown) included in the swing analysis device 100 .

Alternatively, whether or not the mission is performed may be determined through, for example, a sensor installed in the screen golf system. For example, whether or not the mission is performed may be determined by detecting a golfer's motion through a vision sensor.

Alternatively, whether or not the mission is performed can be determined, for example, through a sensor built into the golf club, and therefore, to determine whether or not to perform a mission such as a barbell squat or deadlift in which a golf club is used like a barbell to exercise, the golfer It is possible to determine whether the mission is performed by detecting whether the golf club is moved while holding the golf club horizontally.

By determining whether the golfer has performed the mission in this way, the mission recommendation unit 340 may provide a reward according to the achievement of the mission.

For example, when a golfer achieves a mission, the mission recommendation unit 340 may provide a virtual currency such as a predetermined point or an item as a reward, or increase the level of the golfer. Examples of compensation are not limited to the examples described above.

On the other hand, for example, the mission recommendation unit 340 may impose a penalty if the golfer fails to achieve the mission, and for example, may demote the golfer's level or deduct the golfer's points by more than a predetermined value. Also, for example, the mission recommendation unit 340 may provide a comment for encouraging mission performance.

In addition, the mission recommendation unit 340 may increase a mission level to be matched with the golfer by determining whether the golfer has performed the mission.

For example, if the mission recommendation unit 340 determines that the golfer has performed level 1 of the mission, the level of the mission corresponding to the golfer is raised by one level, and the next time the same mission is recommended to the golfer, a level 2 mission is provided. can do.

Or, for example, if the mission recommendation unit 340 determines that the golfer has performed level 1 of the mission, it provides a mission of the next level in succession so that the golfer can perform the mission of level 2, and the mission accordingly. Through this, you can repeatedly train the body part you want to train.

On the other hand, the mission recommendation unit 340 may additionally set a lesson curriculum suitable for the golfer based on the drill image or mission, and provide the golfer with lesson contents according to the curriculum. The lesson content may be, for example, a lesson image, or may provide a virtual golf course to practice a predetermined shot and simulate a golfer's shot accordingly on the golf course.

The controller 220 including the mission recommendation unit 340 may further include a chatting unit (not shown) that provides an interface for chatting with golfers, and the chatting unit (not shown) is an artificial intelligence chatbot. can be implemented In other words, an artificial intelligence chatbot capable of processing text or voice in natural language and providing output values accordingly, for example, the degree to which the golfer watched the drill video, whether the golfer performed the mission, information about the golfer progress rate in the lesson curriculum, etc. can be provided as text or audio.

Meanwhile, the machine learning model of each component constituting the control unit 220 may be implemented as a network model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), or a deep neural network (DNN), for example. . At this time, the machine learning models in each of the preprocessing 310, the error detection unit 320, the drill recommendation unit 330, and the mission recommendation unit 350 may be implemented in different networks or the same network.

As described above, the input/output unit 110 for obtaining a swing image of a golfer, the memory 140 storing a program for performing machine learning, and machine learning for the swing image by executing the program The swing analysis device 100 including a control unit 120 that performs detects a golfer's swing error from a swing image using a learned machine learning model, recommends a drill image based on the swing error, and A mission corresponding to the drill image may be recommended. Accordingly, the swing analysis device 100 may contribute to improving the golfer's golf skills by correcting the golfer's swing posture.

At this time, the swing analysis device 100 may analyze the golfer's swing as the golfer's golfer's play in the golf field is photographed, and may also analyze the golfer's swing as the golfer's golfer's play is photographed in the screen golf system. can

When the camera detects at least one of the golfer, the golf ball, and the golf club, the camera may generate a swing image as the camera captures the golfer's swing motion, or the camera may continuously photograph the golfer, and the swing motion may be framed. A swing image can be generated by extracting .

In relation to this, the screen golf system may include a camera installed so that a golfer can photograph a turn at bat where a golfer can hit a golf ball, and the camera is installed in a simulator in which all data necessary for virtual golf simulation is stored and processed, or , or installed in a sensor that communicates with the simulator, or may be implemented as a separate device. When the camera or simulator detects at least one of the golfer, the golf ball, and the golf club through the sensor, the camera may generate a swing image as the camera captures the golfer's swing motion, or the camera may continuously photograph the golfer, A swing image may be generated by extracting a frame having a swing motion.

Although the swing analysis device 100 according to an embodiment described in this specification is described in detail as being performed by analyzing a swing image as a golfer's swing is photographed in a screen golf system or a golf field, it is not necessarily limited thereto, and the golfer's swing It can be applied to all types of systems or devices that analyze the swing image when the swing image is obtained by shooting.

On the other hand, Figure 5 is a flow chart for explaining a swing analysis method according to an embodiment. The swing analysis method shown in FIG. 5 includes steps of time-sequential processing in the swing analysis device 100 shown in FIGS. 1 to 4 . Therefore, even if the content is omitted below, the information described above regarding the swing analysis device 100 may also be used in the swing analysis method according to the embodiment shown in FIG. 5 .

As shown in Figure 5, the swing analysis device 100 may receive a swing analysis request from the golfer (S510).

For example, when obtaining a request for analysis of a swing image uploaded by a golfer or detecting at least one motion among the motions of the golfer, the golf ball, and the golf club, the swing analysis device 100 considers that the swing analysis has been requested. can judge

The swing analysis device 100 may detect a swing error by analyzing the swing image (S520).

For example, the swing analysis device 100 may extract one or more first swing errors and select one of the one or more first swing errors as the second swing error. At this time, the swing analysis device 100 selects a second swing error from among the one or more first swing errors based on a swing error extracted from a golfer's past swing image, or selects a first swing error based on the golfer's past mission performance information. You can select the second swing error from among them.

Also, for example, the swing analysis device 100 may determine a third swing error indicating a physical problem of the golfer based on the second swing error.

As described above, when a swing error is detected, the swing analysis device 100 may recommend a drill image based on the detected swing error (S530).

For example, the swing analysis device 100 may recommend a drill image based on at least one of a first swing error, a second swing error, and a third swing error.

Based on the recommended drill image, the swing analysis device 100 may recommend a mission (S540) and monitor whether the golfer performs the recommended mission. Accordingly, if it is determined that the golfer has performed the mission (S550), the swing analysis device 100 may provide a reward to the golfer (S560).

According to the swing analysis method according to an embodiment described in this specification, a golfer can easily find a problem in his/her swing pose and make efforts to improve it.

The virtual golf simulation method described above may be implemented in the form of a computer-readable medium storing instructions and data executable by a computer. In this case, instructions and data may be stored in the form of program codes, and when executed by a processor, a predetermined program module may be generated to perform a predetermined operation. Also, computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, a computer-readable medium may be a computer recording medium, which is a volatile and non-volatile memory implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. It can include both volatile, removable and non-removable media. For example, the computer recording medium may be a magnetic storage medium such as HDD and SSD, an optical recording medium such as CD, DVD, and Blu-ray disc, or a memory included in a server accessible through a network.

The virtual golf simulation method described above may be implemented as a computer program (or computer program product) including instructions executable by a computer. A computer program includes programmable machine instructions processed by a processor and may be implemented in a high-level programming language, object-oriented programming language, assembly language, or machine language. . Also, the computer program may be recorded on a tangible computer-readable recording medium (eg, a memory, a hard disk, a magnetic/optical medium, or a solid-state drive (SSD)).

The virtual golf simulation method described above may be implemented by executing the computer program as described above by a computing device. A computing device may include at least some of a processor, a memory, a storage device, a high-speed interface connected to the memory and a high-speed expansion port, and a low-speed interface connected to a low-speed bus and a storage device. Each of these components are connected to each other using various buses and may be mounted on a common motherboard or installed in any other suitable manner.

Here, the processor may process commands within the computing device, for example, to display graphic information for providing a GUI (Graphic User Interface) on an external input/output device, such as a display connected to a high-speed interface. Examples include instructions stored in memory or storage devices. As another example, multiple processors and/or multiple buses may be used along with multiple memories and memory types as appropriate. Also, the processor may be implemented as a chipset comprising chips including a plurality of independent analog and/or digital processors.

Memory also stores information within the computing device. In one example, the memory may consist of a volatile memory unit or a collection thereof. As another example, the memory may be composed of a non-volatile memory unit or a collection thereof. Memory may also be another form of computer readable medium, such as, for example, a magnetic or optical disk.

Also, the storage device may provide a large amount of storage space to the computing device. A storage device may be a computer-readable medium or a component that includes such a medium, and may include, for example, devices in a storage area network (SAN) or other components, such as a floppy disk device, a hard disk device, an optical disk device, or a tape device, flash memory, or other semiconductor memory device or device array of the like.

The term '~unit' used in the above embodiments means software or a hardware component such as a field programmable gate array (FPGA) or ASIC, and '~unit' performs certain roles. However, '~ part' is not limited to software or hardware. '~bu' may be configured to be in an addressable storage medium and may be configured to reproduce one or more processors. Therefore, as an example, '~unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program patent code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

Functions provided within components and '~units' may be combined into smaller numbers of components and '~units' or separated from additional components and '~units'.

In addition, components and '~units' may be implemented to play one or more CPUs in a device or a secure multimedia card. The above-described embodiments are for illustrative purposes, and those skilled in the art to which the above-described embodiments belong can easily transform into other specific forms without changing the technical spirit or essential features of the above-described embodiments. It should be understood. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope to be protected through this specification is indicated by the following claims rather than the detailed description above, and should be construed to include all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof. .

Claims (16)

1. As a swing analysis device,

   an input/output unit for obtaining a swing image of a golfer;

   a memory in which a program for performing machine learning is stored; and

   And a control unit for performing machine learning on the swing image by executing the program,

   The control unit,

   A swing analysis device that detects a golfer's swing error from a swing image using a learned machine learning model, recommends a drill image based on the swing error, and recommends a mission corresponding to the drill image.
2. According to claim 1,

   The control unit,

   A swing analysis device that extracts one or more first swing errors from the swing image, selects one of the first swing errors as a second swing error, and recommends a drill image based on the second swing error.
3. According to claim 2,

   The control unit,

   Swing analysis device for selecting a second swing error from among the first swing errors based on the swing errors extracted from the past swing images of the golfer.
4. According to claim 2,

   The control unit,

   Swing analysis device for selecting a second swing error from among the first swing errors based on the past mission performance information of the golfer.
5. According to claim 2,

   The control unit,

   Based on the second swing error, a third swing error indicating a physical problem of the golfer is determined, and a drill image is recommended based on the third swing error.
6. According to claim 1,

   The swing analysis device communicates with a third server,

   The control unit,

   A drill image to be recommended is selected from drill images collected by crawling images stored in the third server, and the drill image is selected based on at least one of the number of views, recommendations, and likes for each drill image in the third server. Swing analysis device.
7. According to claim 1.

   The control unit,

   A swing analysis device that recommends a mission corresponding to the drill image and recommends a mission selected based on a mission previously recommended to the golfer.
8. According to claim 1,

   The control unit,

   Swing analysis device for determining whether the golfer has performed the mission and providing a reward to the golfer as a result of the determination.
9. As a method for a swing analysis device to analyze a golfer's swing,

   Detecting a golfer's swing error from a swing image using a learned machine learning model;

   recommending a drill image based on the swing error; and

   Swing analysis method comprising the step of recommending a mission corresponding to the drill image.
10. According to claim 9,

    The step of detecting the swing error,

    Extracting one or more first swing errors from the swing image; and

    Selecting one of the first swing errors as a second swing error,

    The step of recommending the drill image,

    Swing analysis method comprising the step of recommending a drill image based on the second swing error.
11. According to claim 10,

    The step of selecting as the second swing error,

    And selecting a second swing error from among the first swing errors based on a swing error extracted from a past swing image of the golfer.
12. According to claim 10,

    The step of selecting as the second swing error,

    And selecting a second swing error from among the first swing errors based on the past mission performance information of the golfer.
13. According to claim 10,

    The step of detecting the swing error,

    Further comprising determining a third swing error indicating a physical problem of the golfer based on the second swing error,

    The step of recommending the drill image,

    Swing analysis method comprising the step of recommending a drill image based on the third swing error.
14. According to claim 9,

    The swing analysis device communicates with a third server,

    The step of recommending the drill image,

    A drill image to be recommended is selected from drill images collected by crawling images stored in the third server, and the drill image is selected based on at least one of the number of views, recommendations, and likes for each drill image in the third server. Swing analysis method comprising the step of doing.
15. According to claim 9.

    The step of recommending the mission is,

    A swing analysis method comprising the step of recommending a mission corresponding to the drill image, but recommending a mission selected based on a mission previously recommended to the golfer.
16. According to claim 9,

    determining whether the golfer performs the mission; and

    As a result of the determination, further comprising the step of providing a reward to the golfer, the swing analysis method.

Images