KR102619573B1 - System for providing racket sports management service using real time court assignment automation - Google Patents

Abstract

A racket sports game operation service provision system using real-time court allocation automation is provided, creating a racket sports bracket, creating a match list according to the bracket, entering the priority of each match list, and then setting a match court for each match. A user terminal that outputs the assigned results and a receiving unit that receives the bracket and match list from the user terminal, a mapping unit that extracts and maps the game rules and time required for at least one racket sport in the game list, and determines the priority in the game list. A priority unit assigned from the user terminal, an allocation unit that assigns matches in the match list to preset match courts according to priority, creates a waiting list for matches that are not assigned a match court, and when the match in the match court ends , It includes an operation service provision server that includes a real-time processing unit that allocates game courts according to priority among the waiting list.

Description

Racket sports game operation service provision system using real-time court assignment automation {SYSTEM FOR PROVIDING RACKET SPORTS MANAGEMENT SERVICE USING REAL TIME COURT ASSIGNMENT AUTOMATION}

The present invention relates to a racket sports game operation service provision system using real-time court allocation automation, and provides a system that can automate court allocation in real time.

A sports event is a destination-oriented, future-oriented, high-value event using sports as a medium. Sports events are a desirable blue ocean type and future-oriented sports business that serves as a sustainable growth engine for the sports industry and creates economic stimulation effects and job creation effects. However, the knowledge and experience mass-produced through sports events are not Due to systematic and inefficient management, unnecessary cost waste and trial and error are repeated when attracting and operating sports events. Problems in the management of sports events arise from the absence of a standardized process system and knowledge system that can serve as guidelines on what information should be turned into knowledge, at what level, and how in the preparation and operation of sports events. However, the operating environment of sports events varies depending on size, type, and region, tasks for each unit are not independent but form an organic relationship with each other, and complex stakeholders are structured in a matrix structure, making it difficult to build a generalized operating model. It's never easy.

At this time, a platform for automatically generating game schedules or operating sports competitions was researched and developed to match the timing of the badminton finish line. In this regard, Korean Patent Publication No. 2017-0099507 (September 1, 2017), which is a prior art, was researched and developed. published) and Korea Patent Publication No. 2021-0077120 (published on June 25, 2021), game information for multiple games of different types is obtained, and a bracket is created based on the game information and number of players. Based on the number of matches in the bracket, the preliminary round time for multiple games of different types is set, the interval time for each league in the tournament is set based on the preliminary round time, and the preliminary round time is set for multiple games of different types. After determining the start time for the finals, it supports the configuration of confirming the schedule for the finals, inputting information related to the progress of the sports competition, providing the match schedule according to the received information, updating the progress information so that it can be viewed, and Each configuration providing progress information is disclosed.

However, in the former case, only the timing for different games is set, and the structure of how to allocate game courts for different types of games is not disclosed, and in the latter case, the bracket and game results are also shared. In addition, the structure of how to allocate the game list to the game court is not disclosed. Generally, when drawing up a bracket and allocating playing courts, it is assumed that the time required for all games is the same, but when actual games are played, there are differences by sport such as singles and doubles, differences between genders such as men and women, differences in level, Depending on the game rules, such as differences in game scores, whether there is a deuce, whether there is a set, etc., the game time can vary dramatically. Accordingly, research and development of a process for allocating games to game courts when operating racket sports games is required.

One embodiment of the present invention is to prevent the phenomenon of overlapping game times or differences in game court status when operating a racket sports game, and to minimize confusion among game participants due to changes in game start time. The game court is assigned by measuring the time required according to the type, event, and rules of the game, and is assigned according to priority, but if any game ends on the game court, the game does not overlap with the players on the currently assigned game court. We will provide a racquet sports game operation service provision system using real-time court assignment automation that can ensure the status of the game court is even by assigning to the game court and automate the game operation of racquet sports by automatically assigning courts in real time. You can. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention prepares a bracket for racket sports, creates a match list according to the bracket, enters the priority of each match list, and then A user terminal that outputs the results of the match court assignment and a receiving unit that receives the bracket and game list from the user terminal, a mapping unit that extracts and maps at least one game rule and time required for a racket sport in the game list, in the game list A priority unit that receives priority from the user terminal, an assignment unit that assigns matches in the match list to preset match courts according to priority, creates a waiting list for matches that have not been assigned a match court, and matches in the match court In case of termination, it includes an operation service providing server including a real-time processing unit that allocates game courts according to priority among the waiting list.

According to one of the means for solving the problems of the present invention described above, the phenomenon of overlapping game times or differences in game court status when operating a racket sports game is prevented in advance, and confusion of game participants is minimized by changing the game start time. In order to do so, the game courts are assigned by measuring the time required according to the type, event, and rules of the racket sports game, and assigned according to priority. However, if any game ends on the game court, the player on the currently assigned game court By assigning games that do not overlap with each other to game courts, the status of the game courts can be maintained evenly, and game operations in racket sports can be automated by automatically assigning courts in real time.

1 is a diagram illustrating a racket sports game management service providing system using real-time court allocation automation according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an operating service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment of a racket sports game operation service using real-time court allocation automation according to an embodiment of the present invention.
Figure 5 is an operation flowchart illustrating a method of providing a racket sports game operation service using real-time court allocation automation according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' 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 code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

1 is a diagram illustrating a racket sports game management service providing system using real-time court allocation automation according to an embodiment of the present invention. Referring to FIG. 1, the racket sports game operation service provision system 1 using real-time court allocation automation includes at least one user terminal 100, an operation service provision server 300, and at least one player terminal 400. It can be included. However, since the racket sports game operation service providing system 1 using real-time court allocation automation shown in FIG. 1 is only an embodiment of the present invention, the present invention is not limited to FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one user terminal 100 may be connected to the operation service providing server 300 through the network 200. In addition, the operation service providing server 300 may be connected to at least one user terminal 100 and at least one player terminal 400 through the network 200. Additionally, at least one player terminal 400 may be connected to the operation service providing server 300 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), 5G New Radio (NR), 6th Generation of Cellular Networks (6G), and Long Term Evolution (LTE). , WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network) ), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc., but are not limited to these.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one user terminal 100 inputs the bracket and priority using a web page, app page, program, or application related to a racket sports game operation service using real-time court allocation automation, and assigns a game court to correspond thereto. It may be a terminal of a racket sports operator or manager that outputs.

Here, at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The operation service providing server 300 may be a server that provides a racket sports game operation service web page, app page, program, or application using real-time court allocation automation. In addition, the operation service providing server 300 may be a server that receives the bracket and priority of racket sports and allocates each game to each game court.

Here, the operation service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one player terminal 400 is a player and his/her officials, such as coaches and managers, who receive a game schedule using a web page, app page, program, or application related to a racket sports game operation service using real-time court assignment automation. It may be a terminal such as:

Here, at least one player terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one player terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one player terminal 400 is, for example, a wireless communication device that ensures portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

Figure 2 is a block diagram for explaining the operation service providing server included in the system of Figure 1, and Figures 3 and 4 are implementations of a racket sports game operation service using real-time court allocation automation according to an embodiment of the present invention. This is a drawing to explain one embodiment.

Referring to FIG. 2, the operation service providing server 300 includes a receiving unit 310, a mapping unit 320, a priority unit 330, an assignment unit 340, a real-time processing unit 350, and a type selection unit 360. ), order setting unit 370, construction unit 380, prediction unit 390, guidance unit 391, bracket creation unit 393, recording unit 395, tracking unit 397, and movement analysis unit 399 ) may include.

The operation service providing server 300 or another server (not shown) operating in conjunction with an embodiment of the present invention automates real-time court allocation with at least one user terminal 100 and at least one player terminal 400. When transmitting a racket sports game operation service application, program, app page, web page, etc., at least one user terminal 100 and at least one player terminal 400 operate a racket sports game using real-time court allocation automation. You can install or open service applications, programs, app pages, web pages, etc. Additionally, a service program may be run on at least one user terminal 100 and at least one player terminal 400 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Chrome. , Microsoft Edge, Safari, FireFox, Whale, UC Browser, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, the receiver 310 may receive the bracket and game list from the user terminal 100. The user terminal 100 can create a racket sports bracket and generate a game list according to the bracket.

The mapping unit 320 may extract and map at least one game rule and time required for a racket sport in the game list. The game rules at this time refer to all conditions under which the time required, that is, the game time, may vary. For example, differences between men's doubles, women's doubles, mixed doubles, men's singles, and women's singles, differences in grades such as A, B, C, and D, differences in match scores such as 15 points, 21 points, and 25 points, and others. This may include whether it is a deuce or whether it is a set. At this time, the time required is also stored as described above. The time required can be stored as 17 minutes for 25 points in men's doubles group A, 12 minutes for 21 points in women's doubles group D, etc.

The priority unit 330 may receive priorities within the game list from the user terminal 100. The user terminal 100 may input the priority of each game list and then output the result of the game court being assigned to each game. At this time, the priority may be specified by the user terminal 100, or the priority may be assigned by setting at least one condition.

The allocation unit 340 may assign games in the game list to preset game courts according to priority. If the total number of games is do.

The real-time processing unit 350 creates a waiting list for games for which a game court is not assigned, and when the game in the game court ends, it can assign a game court according to priority in the waiting list.

When the game type selection unit 360 allocates a game court according to priority among the games in the waiting list when the game in the game court has ended, the game is a game that does not overlap with the players in the currently assigned game court and is given priority. You can have it extract and assign the highest match from the list.

The order setting unit 370 sets the number of game courts to N, and if the game that ended on the game court is the Kth game, the game assigned to the game court where the Kth game ended is assigned to the K+N-1th game. can do. In this way, each time a random game ends, a game can be extracted from the waiting list and assigned to the game court.

The construction unit 380 may measure and create a database of the time required for each game according to at least one game rule of at least one racket sport. In the case of badminton among racket sports, a database on the time required can be accumulated based on events that occur for each score-loss technical factor, score-loss situation factor, and score-loss timing factor that occur in a badminton game situation. At this time, after setting the time required according to technical factors, situational factors, and timing factors, a prediction model for the time required can be built. For each game video data, competitions hosted by the Badminton World Federation (BWF) can be used as data, and the collected game videos can be analyzed into six prediction models using I-Minton (program registration number: C-2018-005553). Events for each necessary factor can be quantified. Afterwards, a prediction model can be built by setting the time required for each event. Of course, it is obvious that various events, variables, or conditions can be used in addition to the events below.

factor Events that can occur during the game technology Drop, clear, smash, drive, smash cut, smash receive, hairpin, push, under clear. situation No touch of racket, touch of racket, opponent's mistake, other situations point of view After 0-5 points, 6-10 points, 11-15 points, 16-20 points, 21 points Skill-Situation Combination Drop - opponent's mistake, drop - racket touch, drop - racket no touch, drop - other situations, clear - opponent's mistake, clear - racket touch, clear - racket no touch, clear - other situations, smash - opponent's mistake, smash - racket touch, Smash - Racket No Touch, Smash - Other Situations, Drive - Opponent Mistake, Drive - Racquet Touch, Drive - Racquet No Touch, Drive - Other Situations, Smash Cut - Opponent Mistake, Smash Cut - Racquet Touch, Smash Cut - Racket No Touch, Smash Cut -Other situations, smash receive - opponent's mistake, smash receive - racket touch, smash receive - racket no touch, smash receive - other situations, hairpin - opponent's mistake, hairpin - racket touch, hairpin - racket no touch, hairpin - other situations, push - Opponent error, push - racket touch, push - racket no touch, push - other situations, under clear - opponent's mistake, under clear - racket touch, under clear - racket no touch, under clear - other situations, service - opponent's mistake, service - racket Touch, Service-Racket No Touch, Service-Other Situations Technology - Point of View
Combination Drop - 0-5 points, Drop - 6 - 10 points, Drop - 11 - 15 points, Drop - 16 - 20 points, Drop - after 21 points, Clear - 0 - 5 points, Clear - 6 - 10 points, Clear - 11-15 points, Clear-16-20 points, Clear-21 points later, Smash-0-5 points, Smash-6-10 points, Smash-11-15 points, Smash-16-20 points, Smash-21 points Afterwards, Drive-0-5 points, Drive-6-10 points, Drive-11-15 points, Drive-16-20 points, After Drive-21 points, Smash Cut-0-5 points, Smash Cut-6-10 points, smash cut - 11-15 points, smash cut - 16 - 20 points, smash cut - after 21 points, smash receive - 0 - 5 points, smash receive - 6 - 10 points, smash receive - 11 - 15 points, smash Receive-16-20 points, Smash Receive-after 21 points, Hairpin-0-5 points, Hairpin-6-10 points, Hairpin-11-15 points, Hairpin-16-20 points, Hairpin-after 21 points, Push- 0-5 points, push-6-10 points, push-11-15 points, push-16-20 points, push-after 21 points, underclear -0-5 points, underclear-6-10 points, underclear -11-15 points, Underclear-16-20 points, Underclear-after 21 points, Service-0-5 points, Service-6-10 points, Service-11-15 points, Service-16-20 points, Service After -21 points

The prediction unit 390 can predict the time required for a game assigned to the game court. At this time, various prediction models can be used, but in one embodiment of the present invention, the following LSTM model can be used. This predicted time can be used when assigning the next game to the game court.

<LSTM model>

Deep learning has a structure that can solve complex nonlinear problems. The structure of deep learning is an artificial neural network (ANN), which consists of an input layer, a hidden layer, and an output layer, and has several hidden layers between the input layer and the output layer. Representative deep learning models include Convolutional Neural Network (CNN) and Recurrent Neural Networks (RNN). CNN was developed to effectively process images. It extracts the features of the image, expresses it as a matrix, and classifies the image by learning the features through a convolution layer and a pooling layer. and recognize it.

RNN is a model that adds the concept for processing sequential data in the structure of Neural Networks, and is a model suitable for analyzing time series data with temporal order. However, as the RNN sequence becomes longer, the information in the input data is not transmitted well to the next step, so the learning weight decreases and eventually disappears. This problem is called the Vanishing Gradient Problem, and the model to solve this problem is the LSTM (Long Short-Term Memory) model. RNN consists of a module that repeatedly performs one Hyperbolic Tangent layer, but LSTM has a structure with 3 gates and 4 layers. The Forget Gate determines what information to discard, the Input Gate determines what value to update, and the Output Gate determines the output value. Cell state, an important part of LSTM, plays a conveyor belt-like role and controls three gates, the forget gate, the input gate, and the output gate, preventing gradient loss and allowing information to flow effectively.

<LSTM model design>

Learning can be performed using data already accumulated in the platform according to an embodiment of the present invention, and normalization can be performed to a value between 0 and 1 to improve stability and convergence speed in the model optimization process. . In order to optimize the performance of deep learning models, finding the optimal hyper-parameter values used in the algorithm is most important in design. There is no set method for the hyperparameter tuning process, and the optimal hyperparameters can be found through repeated experimentation and trial and error. There is no absolute best value for hyperparameters, but appropriate values can be found depending on the data and model used. Accordingly, in order to find the optimal hyperparameter, experiments can be repeatedly conducted on hyperparameter input values. By measuring the loss rate of the training dataset and validation dataset for each epoch, hyperparameters that perform well in learning can be selected.

<Analysis of prediction results>

To verify the performance of the prediction model, predicted values and actual measurements can be compared. Representative prediction accuracy verification methods, such as Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE), can be used. RMSE is a generalized measure of standard deviation and is a measure of how much the difference is between the actual value and the predicted value. MAPE is an intuitively understandable evaluation measure that calculates the difference between the actual value and the predicted value as a percentage. The smaller the value, the higher the value. This means that the error is small. In the preprocessing process of time series data, the prediction error rate can be calculated by converting log transformation and normalizing values between 0 and 1 back to the original time series data units. Of course, various prediction algorithms may be used in addition to the prediction methods described above.

If a game in the waiting list is assigned to a game court after the game ends on the game court, the information unit 391 may guide the game court assignment event to the player terminal 400 of the player in the assigned game.

When the bracket generator 393 does not receive a bracket input from the user terminal 100, the bracket generator 393 may generate the bracket in a round-robin method. At this time, in a sports game consisting of N teams, there is a case in which each team takes turns playing against the remaining N-1 teams once in the same number of games, and the ranking is determined based on their performance in a league match. This is called the round-robin method, and a bracket can be created using this. At this time, because the round-robin sports game scheduling problem is close to NP-HARD, the polynomial time algorithm is not known. Accordingly, assuming that a polynomial time algorithm does not exist, metaheuristic techniques and greedy techniques that can be solved in polynomial time can be used. As metaheuristic techniques, for example, Genetic Algorithm (GA) and Tabu Search (TS) can be used, and polynomial time greedy algorithms can be used to color distance pattern edges and the Exhuastive Repair Method. , 2SAT (2-Satisfiability Problem) method, Max Cut method, etc. can be used.

The recording unit 395 may capture video to record a game taking place on at least one game court, analyze the captured video, and provide a game report. In the case of badminton, assuming that major variables for recording are selected, it would be appropriate to organize them based on the six-down principle. In other words, each badminton point can be organized to indicate which player handled which technique at which point in time and in which position. Badminton games involve continuous rallies, so scoring points can be recorded. In addition, the players subject to recording can be divided into serve players and return players, and scorers and players who concede goals. Since the data structure of a badminton game is dyadic data, that is, data with corresponding characteristics, such as when one side wins and the other loses, there is no need to enter both serve and return players. It can be replaced by recording only the scorer. In addition, the time variable according to the game flow corresponding to the time can be set to distinguish between set, score situation, and whether or not a score is scored within 3 balls.

Sets for badminton matches can be entered as 1 set, 2 sets, and 3 sets, and the score situation refers to the current score. Because the score is accumulated by entering the scoring player, it has an automatic input value. Additionally, the scoring situation can be divided into scoring within the 3-ball and scoring outside the 3-ball, focusing on the 3-ball. If scoring outside of the 3-ball can be considered as an important consideration for strategy in the rally, scoring within the 3-ball can be said to reflect more skill in the serve and return than in the rally, so this situation can be distinguished. The locations, actions and processes for badminton records may be as shown in Table 2 below.

category Record contents variable of record who player to record Sub and return players
Scorers and Concedors when Time according to the flow of the game Set and score situation
Scoring within 3 balls where Player position to record Starting position of the batted ball
End position of batted ball what Actions of players subject to recording Scoring type of scoring player how The player's course of action to be recorded Results based on the player's actions to be recorded why Reasons for the athlete's actions to be recorded Record of special information

<Start position of batted ball>

The starting position of the shuttle ball refers to the position of the player being recorded. The location of the player to be recorded is connected to the problem of how to define the court to record badminton games. In a scoring situation, the position of the player scoring or conceding the goal and the throwing position of the shuttle can be recorded. Since the court is divided into nine when recording the positions of players or shuttles in badminton records, in one embodiment of the present invention, the positions of the players (scoring or conceding goals) of the last rally point can also be divided into nine.

<End position of batted ball>

The ending position of a shuttle ball refers to the throwing point in a situation where the player being recorded scores or concedes a goal. The throwing point of a player's scoring or conceding points to be recorded can be defined as the location where the act of scoring or conceding a point occurs. In other words, in the badminton shuttle rally process, the actions of the last rallyer are defined as rally points that cause scoring or conceding goals, and the throwing location of the scoring or conceding points can be distinguished.

<Scoring player’s scoring type>

As a way to record the scorer's scoring type, you can consider recording the badminton technique type and recording which technique was used to score the score. However, in the case of badminton, it is possible to estimate badminton skills by combining the starting position of the batted ball and the throwing position, so the types can be distinguished according to the situation of the scoring player rather than based on badminton skills. Scoring situations in badminton can be roughly divided into situations where the scoring player attacks or situations where the scoring player makes a mistake. It can also include elements of luck, including cases where a shuttle comes over the net, and an opponent's error in judgment. The scoring types of scoring players can be classified as shown in Table 3 below.

Scoring type technical success opponent's mistake etc detail Technical success - Touching opponent's racket
Technical success - no touch of opponent's racket serve mistake
Opponent mistake - attack situation
Opponent mistake - rally situation luck
Opponent judgment mistake

If we classify the types of goals based on the scoring player, they can be roughly divided into three categories: successful technique, opponent's mistake, and others (luck or opponent's error in judgment). First, cases where the technique is successful can be divided into cases where the shuttle touches the opponent's racket and scores a point, and cases where the opponent does not touch the racket. Scoring due to an opponent's mistake is divided into an attack mistake in an attack situation, including an opponent's serve error, and a mistake in a simple rally situation. Additionally, other situations include elements of luck, such as a shuttle crossing the net, and scoring due to an opponent's judgment error. In a sports recording system, it is very important to apply a logical model to systematically record the contents of the game without difficulty. In one embodiment of the present invention, in order to implement a badminton recording system, the Sportscode program and the Visual Basic program, which are widely used as sports video analysis programs developed in Australia, can be used. Of course, it is also possible to use other programs. Analyzing the scoring type in this way can help you understand the game, and automatically recording game records is also possible without the need for editing manpower or time, so it can be used for various analyses.

The tracking unit 397 can store a video of a game taking place on at least one game court and track the player's location using a pre-built deep learning model. To this end, the process of creating a learning dataset, deep learning model, and model evaluation is performed, as shown in Table 4 below.

Generate learning data → deep learning model → Model evaluation ① Collection of game videos
② Video slicing
③ Create label image
④ JSON file conversion

① Final Dataset Composition
② Establishment of deep learning environment
③ Setting learning options ① Recognition and accuracy
② mAP evaluation

In video slicing and learning data selection, video slicing means dividing the video into frames and saving them as images to obtain images to be used for actual learning. For example, it may be 30 frames per second, and when converted to an image, it is converted to 30 images per second. For video slicing, you can use the OpenCV library for Python. The MASK R-CNN algorithm can be used to learn badminton player tracking based on supervised learning. CNN is one of the deep learning algorithms that represent supervised learning in image processing fields such as image analysis and motion analysis. In addition, CNN-based image analysis methods include R-CNN, Fast R-CNN, Faster R-CNN, and Mask R-CNN. Basically, R-CNN uses a selective search algorithm to find the bounding box. do. MASK R-CNN is a type of object segmentation algorithm, and its core is a method of masking segmented images. It has the advantage of being able to segment objects of the same type into different objects even if they overlap. Accordingly, the above-described algorithm can be used, and various other models can also be used. In the field of sports, data analysis of athletes is used as important data to improve athlete performance and establish team strategies, but the data used for analysis The conventional method of manually recording requires a lot of time and effort. In particular, in badminton, it is nearly impossible for a person to directly record in real time due to the rapid progress of the game, and it takes a long time to directly watch the game video and input data. In addition, in one embodiment of the present invention, since a bracket must be created and each game time must be equally allocated to the game court, data analysis of each player is necessary to predict the time required for each game. Accordingly, the most important player tracking model can be modeled and used as described above.

The movement analysis unit 399 may collect movement data from a wearable device worn by at least one player, map it to an image, and store it. For example, in order to develop an application that provides feedback on whether the movements of the forehand swing, backhand swing, and round swing in badminton are correct movements, reference data can be prepared and evaluation data for this can be provided. For this purpose, an application can be developed based on an Arduino board with an acceleration sensor, machine learning techniques, and a smartphone. For this purpose, the data on each axis collected from the acceleration sensor attached to the badminton racket utilizes the characteristic of having different patterns for each swing type. The classification technique used in the application can be SVM (Support Vector Machine), which has shown excellent performance in operation performance and classification ability in existing research. This application does not require a separate facility or location, and can improve the accuracy of the classification model by continuously storing data generated from exercise practice.

Hereinafter, the operation process according to the configuration of the operation service providing server of FIG. 2 described above will be described in detail using FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to FIG. 3, (a) the operation service providing server 300 may receive priorities and brackets from the user terminal 100 when creating a game list. At this time, the type, time required, game rules, etc. can be mapped and stored for each game in each game list. And, as shown in (b), the operation service providing server 300 can assign games to the game court according to priority. At this time, (c) the remaining list is placed in a waiting state as a waiting list. In addition, when any one game is finished, the game with the highest priority is extracted from the waiting list and assigned to the game court, even though the type of game is different from the finished game (AND condition). (d) The automatically assigned results are delivered to the player terminal 400. The left side of Figure 4 is an expected timetable according to the prior art, and the right side is a game progress record according to an embodiment of the present invention.

The method according to the prior art is to prepare and proceed with a bracket assuming that the time required for all games is the same, but in actual game progress, the time required for all games is different, especially for men's doubles, women's doubles, mixed doubles, and men's singles. , differences between events in women's singles, differences in grades such as A, B, C, and D, differences in game scores such as 15 points, 21 points, and 25 points, and other game times depending on game rules such as deuce or set, etc. It may be different. When applying the method according to an embodiment of the present invention, even when predicting the visual time for each game by measuring the customized game time according to the event (type) and game rules for each game, the prediction can be made as close to the actual game start time as possible. This can minimize confusion and confusion among game participants due to changes in game start times.

In addition, it is possible to prevent in advance the phenomenon of game time overlapping that occurs during the game and the phenomenon in which the progress status of some game courts is very different, and through this, the work and manpower of the game management team can be minimized. In addition, even when an exception occurs where a problem occurs in some of the game courts and the game court can no longer be used, it is possible to respond flexibly by not assigning the game to the game court where the problem occurred, unlike the prior art. . In addition, in the method according to the prior art, there may be a difference between the expected start time and the actual game start time for each game court due to a forfeit or player tardiness, but in the method according to an embodiment of the present invention, all game courts are used for play. Because the slowdown and acceleration of progress are shared, the gap between the expected game start time and the actual game start time can be minimized.

Matters that are not explained about the method of providing racket sports game operation services using real-time court allocation automation in FIGS. 2 to 4 are explained in detail in Figure 1 regarding the method of providing racket sports game operation services using real-time court allocation automation. Since the content is the same or can be easily inferred from the explained content, the description below will be omitted.

FIG. 5 is a diagram illustrating a process in which data is transmitted and received between components included in the racket sports game management service providing system using real-time court allocation automation of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to Figure 5, the operation service providing server receives the bracket and game list from the user terminal (S5100).

Then, the operation service providing server extracts and maps at least one game rule and time required for a racket sport in the game list (S5200), and receives priority in the game list from the user terminal (S5300).

In addition, the operation service providing server assigns the games in the game list to the preset game courts according to priority (S5400), creates a waiting list for games that have not been assigned a game court, and when the game in the game court ends , Game courts are assigned according to priority among the waiting list (S5500).

The sequence between the above-described steps (S5100 to S5500) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5500) may be changed, and some of the steps may be executed simultaneously or deleted.

Matters that are not explained regarding the method of providing racket sports game operation services using the real-time court allocation automation of FIG. 5 are explained previously in FIGS. 1 to 4 regarding the method of providing racket sports game operation services using real-time court allocation automation. Since the content is the same or can be easily inferred from the explained content, the description below will be omitted.

The method of providing a racket sports game operation service using real-time court allocation automation according to an embodiment described with reference to FIG. 5 is in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. It can also be implemented as: Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing a racket sports game operation service using real-time court allocation automation according to an embodiment of the present invention described above includes an application installed by default on a terminal (this may include a program included in a platform or operating system, etc., installed by default on the terminal). It may be executed by an application (i.e., a program) that the user installs directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing a racket sports game operation service using real-time court allocation automation according to an embodiment of the present invention described above is implemented as an application (i.e., program) installed by default on the terminal or directly installed by the user and installed on the terminal. It may be recorded on a computer-readable recording medium, such as a computer-readable recording medium.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (10)

A user terminal that creates a bracket for racket sports, generates a match list according to the bracket, inputs the priority of each match list, and then outputs the results of the match court being assigned to each match; and
A receiving unit that receives the bracket and game list from the user terminal, a mapping unit that extracts and maps at least one game rule and time required for a racket sport in the game list, and a priority that receives priority in the game list from the user terminal. A ranking unit, an allocation unit that allocates the matches in the match list to preset match courts according to the priority, creates a waiting list for matches that are not assigned to the match court, and when the match in the match court ends, the An operation service providing server including a real-time processing unit that allocates the game court according to priority among the waiting list;
A racket sports game operation service provision system using real-time court assignment automation that includes.
According to claim 1,
The operating service providing server is,
When the game in the game court is completed and the game court is assigned according to priority among the games in the waiting list, the game is of a type that is not the same as that of the game that was completed and the priority is the highest in the waiting list. A type selection unit that extracts and assigns games;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:
According to claim 2,
The operating service providing server is,
If the number of game courts is N, and the game that ended on the game court is the Kth game, an order setting unit that ensures that the game assigned to the game court where the Kth game ended is assigned to the K+N-1th game;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:
According to claim 1,
The operating service providing server is,
a construction unit that measures and databases the time required for each game according to at least one game rule of at least one racket sport;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:
According to claim 1,
The operating service providing server is,
a prediction unit that predicts the time required for a game assigned to the game court;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:
According to claim 1,
The operating service providing server is,
When a game in the waiting list is assigned to a game court after the game ends on the game court, an information unit that guides the game court allocation event to the player terminal of the player of the assigned game;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:
According to claim 1,
The operating service providing server is,
When the bracket is not input from the user terminal, a bracket generator that generates the bracket in a round-robin method;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:
According to claim 1,
The operating service providing server is,
a recording unit that captures video to record a game taking place on at least one game court, analyzes the captured video, and provides a game report;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:
According to claim 8,
The operating service providing server is,
A tracking unit that stores a video of a game taking place on at least one game court and tracks the player's location using a pre-built deep learning model;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:
According to clause 9,
The operating service providing server is,
A motion analysis unit that collects movement data from a wearable device worn by at least one athlete, maps it to the image, and stores it;
A racket sports game operation service provision system using real-time court assignment automation, further comprising:

Images