KR102045566B1 - Apparatus for generating strategy of curling game and method thereof - Google Patents

Abstract

An apparatus and method for generating a curling match strategy, the apparatus including a memory for storing a curling match strategy analysis and generation program and a processor for executing a program stored in the memory, the processor according to the execution of the curling match strategy analysis and generation program Recognize preset game situation information by recognizing the image of the image of the ongoing curling game, and learn the data collected from the recorded data for the plurality of curling games that have been performed through preset machine learning to create a strategy generation model And generate one or more strategies corresponding to the recognized game situation information through a strategy generation model, output recommendation information for the generated strategy, and record data for a plurality of executed curling matches. At least one of information and text information.

Description

Curling match strategy generation device and method thereof {APPARATUS FOR GENERATING STRATEGY OF CURLING GAME AND METHOD THEREOF}

The present invention relates to an apparatus and method for automatically generating a strategy in a curling race, and more particularly, to generate a curling race strategy using a result of automatically analyzing the playing power and power in a curling race based on image recognition. An apparatus and method are provided.

Curling is a winter sport in which two teams decide whether to win or lose based on how accurately the curling stone is placed on the ice and placed on the target. Two teams of four players each take a total of 16 stones alternately, 10 per end, two per player at each end. A goal is scored when a stone enters the house and one point is scored for each stone closer to the center than the opposing team. You can also control the direction and speed of the curling stone by wiping the icy path through the stone with a broom brush.

Sliding the stone in curling is called delivery, and sweeping the ice in front of the path of the stone to reduce the amount of friction and rotation between the stone and the floor is called sweeping. Also, the player who devises the strategy in curling is called skip. In this case, the skip may be the captain of the corresponding team. Also, a player who throws a stone is called a thrower, and a player who performs sweeping using a broom is called a sweeper.

In these curling races, the operation is to decide how to use shots, which requires a pitching strategy that takes into account the speed, direction of rotation, and direction of the stone, and the path of the stone to reduce the friction between the stone and the floor and the amount of rotation of the stone. A sweeping strategy is also needed to clean the front ice. The slower the stone, the more it bends, so sweeping can increase the distance the stone travels and straighten the path. It is also important that you plan your operations against the ever-changing playing field conditions, such as the ice conditions of the curling seats (ie the ice face on which you are playing) and the location of your opponent's stones. That is, in curling, it is important to accurately recognize the state of each stone and to determine an optimal pitch position. However, in curling, the pitching position is almost infinite, so it is difficult to select the optimal pitching position and method.

Conventionally, although a person analyzes a curling game and establishes a game strategy, a means of providing an interface for recording curling game information in real time and allowing a person to analyze or presenting statistical data has been used. The conventional curling game analysis method has a high possibility of a strategy error due to human factors.

Korean Patent No. 10-1478097 (name of the invention: a mobile terminal for performing a curling simulation, a curling simulation method and a recording medium) Korean Patent No. 10-1499570 (name of the invention: a mobile terminal for curling analysis and a curling match analysis system using the same) Korea Patent Registration No. 10-1611431 (name of the invention: curling analysis method, recording medium and apparatus for performing the same)

An embodiment of the present invention is to obtain the data suitable for the culling strategy learning model through image recognition for the curling game, and to learn the culling strategies using the machine learning method to analyze the optimal strategy according to the game performance and game situation of curling players It is an object to provide a method and an apparatus thereof.

However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

According to an aspect of the present invention, there is provided an apparatus for generating a curling competition strategy, the memory storing a curling competition strategy analysis and generation program; And a processor for executing a program stored in the memory, wherein the processor recognizes preset game situation information by recognizing an image of an image of a curling game in progress according to execution of the curling game strategy analysis and generation program. Learning the data collected from the plurality of recorded curling races through a predetermined machine learning to construct a strategy generation model, and using the strategy generation model, one or more corresponding to the recognized game situation information. A strategy is generated, the recommendation information for the generated strategy is output, and the recorded data of the plurality of curling competitions performed includes at least one of image information and text information.

In addition, the curling game strategy generation method according to another aspect of the present invention, learning the data collected from the recorded data for the plurality of curling game carried out through a predetermined machine learning to build a strategy generation model; Recognizing preset game situation information by recognizing an image photographing an ongoing curling game; And generating one or more strategies corresponding to the recognized game situation information through the strategy generation model, and outputting recommendation information for the generated strategy, and recording the plurality of curling matches performed in advance. The data may include at least one of image information and text information, and the image information may include coordinate information and collision position information of a curling stone extracted from an image photographing a curling competition situation in a predetermined direction. At least one of an end number, a shot number, a strategy performed, and a direction of rotation of the curling stone.

According to an embodiment of the present invention, by collecting the curling game data using the image recognition technology to build a database for the machine learning, it is possible to learn the actual curling game content and strategy that occurs in a variety of situations.

In addition, according to an embodiment of the present invention, it is possible to reduce the error caused by human factors by securing the curling data required for strategy learning using a variety of methods and then learning a variety of strategies using a machine learning method.

In addition, according to an embodiment of the present invention, it is possible to establish and recommend a real-time strategy according to the curling game situation, it can be utilized as a game analysis / guidance tool for improving the performance of the general public and athlete team learning the curling sports, sports It can provide more reliable and accurate game contents analysis information when used as a broadcast relay tool.

1 is a block diagram of a curling game strategy generating device according to an embodiment of the present invention.
Figure 2 is a schematic diagram showing the entire process of analysis and generation of curling competition strategy according to an embodiment of the present invention.
FIG. 3 is a diagram illustrating a process of collecting training data and building a database for modeling a curling competition strategy generation model according to an embodiment of the present invention.
4 is a diagram illustrating information included in a curling match record according to an embodiment of the present invention.
FIG. 5 is a diagram for describing a process of extracting image information and recognizing stone coordinates of a curling race according to an exemplary embodiment of the present invention. FIG.
6 is a diagram illustrating a text information extraction process included in a curling game record according to an embodiment of the present invention.
7 is a view for explaining a game situation recognition process through the curling game image according to an embodiment of the present invention.
8 is a diagram illustrating a data expansion process according to an embodiment of the present invention.
9 is a diagram illustrating a strategy generation process according to a curling match situation using the curling match strategy generation model according to an embodiment of the present invention.
FIG. 10 is an example of a user interface providing a result of analyzing a performance of a curling competition player and a training method recommendation result according to an exemplary embodiment of the present invention.
11 is an example of a user interface for providing a curling match result analysis report according to an embodiment of the present invention.
12 is a diagram illustrating the curling match result analysis report of FIG. 11 in more detail.
13 is a flowchart illustrating a method of generating a curling match strategy according to an embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, which means that it may further include other components, except to exclude other components, unless specifically stated otherwise, one or more other features It is to be understood that the present disclosure does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, parts, or combinations thereof.

1 is a block diagram of a curling game strategy generating device according to an embodiment of the present invention. And Figure 2 is a schematic diagram showing the entire process of analysis and generation of curling competition strategy according to an embodiment of the present invention.

As shown in FIG. 1, the curling game strategy generating device 100 includes a communication module 110, a memory 120, a processor 130, and a database (DB) 140. Meanwhile, the curling game strategy generating device 100 may further include a display (not shown) means by itself, and various information processed through the processor 130 may be output through the display.

The communication module 110 receives image data continuously photographing the curling competition situation from one or more camera devices (not shown) installed in the curling stadium, and through the communication network 400, through the camera device (or the camera device) of the curling stadium. An external device for transmitting the captured image data).

In addition, when the curling match strategy generating apparatus 100 transmits information such as a result of analyzing the playing strength and strategy for the curling match to an external information requesting terminal (not shown), the communication module 110 transmits the communication network 400. It can communicate with the corresponding information request terminal (eg, user terminal).

In addition, the communication module 110 is connected to the Internet network through the communication network 400, under the control of the processor 130 collects data (ie learning data) for the existing curling competitions through the Internet network. To the processor 130.

The communication module 110 may be a device including hardware and software necessary for transmitting and receiving a signal such as a control signal or a data signal through a wired or wireless connection with another network device.

The memory 120 stores a curling game strategy analysis and generation program for analyzing a strategy for a curling game and generating a strategy for a currently running curling game based on the analysis result.

Such a curling match strategy analysis and generation program may be used to build a curling match strategy generation model based on data collected for an existing curling match, and may be applied to an analysis target curling match that is currently in progress (or to analyze a game situation). Recognizing the game situation by image recognition and information analysis of the relevant data, and includes a algorithm for generating and recommending a curling game strategy suitable for the game situation recognition information through the curling game strategy generation model. In addition, the curling match strategy analysis and generation program analyzes the curling match situation after applying the curling match strategy selected by the user among the recommended curling match strategies, and analyzes the suitability of the curling match strategy and the degree of performance for each participating player. It also includes an algorithm for evaluating the performance analysis to evaluate and recommending training methods based on the results of the performance analysis.

The memory 120 may be referred to as a nonvolatile storage device that maintains stored information even when power is not supplied, or a volatile storage device that requires power to maintain stored information.

On the other hand, the curling game strategy generating device 100 is a curling game strategy generation model and various information related to the analysis and generation of the curling game strategy (ie, learning data collected in relation to the curling game and image data of the analysis target curling game, etc.) It may further include a database 140 for storing. The database 140 may be built as a separate component on the curling game strategy generating device 100, or may be included in the memory 120.

The processor 130 executes a program stored in the memory 120, and processes the following operations according to the execution of the curling game strategy analysis and generation program. For reference, the processor 130 may refer to a data processing apparatus embedded in hardware, for example, having a physically structured circuit for performing a function represented by a code or an instruction included in a program. As an example of a data processing device embedded in hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, and an application-specific integrated device (ASIC) It may include a processing device such as a circuit, a field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

The processor 130 recognizes preset game situation information by recognizing an image of an image of an ongoing curling game, and learns data collected from recorded data about a plurality of pre-set curling games through preset machine learning. By constructing a strategy generation model, and generating one or more strategies corresponding to the recognized game situation through the strategy generation model, and outputs the recommendation information for the generated strategy on the display. At this time, the recorded data for the plurality of curling competitions carried out includes at least one of image information and text information.

Referring to FIG. 2, the processor 130 automatically analyzes the performance and strategy of the participating players according to the game situation based on the curling game image recognition, and provides a report on the performance and strategy through the user interface as a result of the analysis. do. In addition, the processor 130 recommends a training method suitable for the athlete based on the performance analysis result, and generates and recommends a strategy optimized for an analysis target curling race (eg, a current curling race) based on the strategy analysis result. .

For example, curling strategies include slow stones, including draw, front, guard, raise, wick, and freeze, and take out. And quick stones including hot and roll, clearing, double take out and promotion take out. In this case, the draw refers to a shot that accurately sends the stone to a desired position inside the house without touching another stone. The front means a shot that sends the stone in front of the house, and the guard means placing the stone in front of the house to protect another team's stone. Wick means a shot that places a stone different from the stone in a desired position, and freeze means a shot that sends the stone as close as possible to another stone. Take out means to keep the stone in the playing field and send the other team's stone off the playing field, and hit and roll means to send the stone to the desired position and to send the other team's stone out. Also, clearing is a shot that sends out both the stone and the stones of other teams, and double take-out is a shot that sends out the stones of two other teams. Promotional take-out means pushing your team's stone out to get another team's stone out.

The processor 130 collects data (ie, learning data) required for culling game strategy learning in advance, and builds a culling game strategy generation model by machine learning the collected learning data.

FIG. 3 is a diagram illustrating a process of collecting training data and building a database for modeling a curling competition strategy generation model according to an embodiment of the present invention.

The processor 130 collects existing curling race records (eg, data provided by Curling Information Technology (CURLIT), etc.) through web crawling to obtain data necessary for learning a curling strategy. . Web crawling is an organized and automated way of browsing the World Wide Web. Web crawling is a technique that collects a large number of distributed and stored document data and includes it as an index of a search target. Which class of technologies is included in a search target and how quickly it is determined is an advantage factor.

For reference, international curling notation (curling notation) is a document that records the content of the international curling competitions hosted by the World Curling Federation is published in a pdf format data file, a document that the culling experts observe the actual game recorded. It contains a total of 1,321 match records from 2014 to 2017. The information included in the curling game notation includes game image information continuously recording the arrangements of stones, and text information such as end number, shot number, strategy performed, stone rotation direction, and the like.

4 is a diagram illustrating information included in a curling match record according to an embodiment of the present invention.

Referring to FIG. 4, the curling match notation includes an end number, a shot number, a name of a country, a name of a player, a performed strategy, and a rotation direction. Direction of curl, Score of current stategy and Current state of stones.

The processor 130 collects curling match information that has been previously performed by web crawling, and extracts and stores information necessary when the strategy generation model learns through template matching in the database 140. Template matching is a pattern matching technique using a predetermined template (template), and is a method of extracting an object matching a given figure from an image.

5 is a diagram illustrating a process of extracting image information and stone coordinates of a curling game according to an embodiment of the present invention, and FIG. 6 is a process of extracting text information included in a curling game record according to an embodiment of the present invention. A diagram for explaining.

Referring to FIG. 5, the processor 130 converts a document file (eg, pdf) of the collected curling game record data into an image file, and extracts a predetermined required area (ie, a stadium area) through outline recognition, and extracts it. Image recognition processing is performed on the extracted image to extract image information such as a coordinate of a curling stone and a collision position coordinate present on the image. The processor 130 stores the extracted image information and the curling match record image file in the curling match database.

In addition, referring to FIG. 6, the processor 130 converts the document file (eg, pdf) of the collected curling game record data into a text file format (txt), and then includes an end number, a shot number, a strategy performed, and a stone. Extracts text information such as the direction of rotation. The processor 130 stores the extracted text information and the curling match record text file in a curling match database.

Meanwhile, the processor 130 restores a screen viewed from the vertical direction of the stadium by performing image reconstruction on a game image taken at an actual curling stadium. An image reconstruction process is an operation method which synthesize | combines an object or its cross-sectional image by the image conversion technique from the combination of the imaging data lower than that by one dimension. The processor 130 performs image recognition processing on the restored screen (ie, image) to obtain data (ie, game situation information) required for culling strategy learning.

7 is a view for explaining a game situation recognition process through the curling game image according to an embodiment of the present invention.

Referring to FIG. 7, the processor 130 restores images of two or more cameras (eg, a stadium side camera, a stadium top (ceiling) camera, etc.) installed in a curling stadium to an image taken in the vertical top direction through image reconstruction. do. The processor 130 matches the recovered image with the position coordinates of a preset curling simulator, extracts information (ie, game situation information) necessary for the strategy generation model to learn through template matching, and then extracts the database 140. ).

In this case, the processor 130 reproduces the movement of the curling stone and the collision between the curling stones using a physics engine-based curling simulator, and sets the curling sheet, which is an infinite space, as the coordinate space to coordinate the position of the curling stone. Represented by For reference, the physics engine may be implemented with computer software capable of maximizing simulation of simple specific physics systems such as rigid body dynamics (including collision detection), soft body dynamics, and flow dynamics.

For example, the processor 130 may process matching of the photographed game image with a curling simulator in real time, recognize a current curling game situation, and provide a strategy generation and analysis of a game performance optimized thereto. . That is, the processor 130 extracts an image captured in a predetermined direction from image data of an ongoing curling match (ie, an analysis target curling match), and continuously processes matching with the position coordinates of the curling simulator in real time. It can recognize and analyze the game situation of the ongoing curling game in real time.

As described above, the processor 130 databases the curling game record data collected through web crawling and the curling game situation data recognized based on image recognition, so as to be learned using a machine learning technique. In addition, the processor 130 learns data (ie, various game contents) stored in a database, and objectively analyzes a user's game performance evaluation and vulnerability by automatically analyzing game contents such as a pitching strategy and a pitching accuracy.

Meanwhile, the processor 130 uses the data augmentation techniques to learn the existing curling match information collected through web crawling and the curling match situation recognition data collected through a camera-based match image using data augmentation techniques. Acquire positive data. The processor 130 builds a curling game strategy generation model by learning the data (that is, learning data) obtained through this using a predetermined machine learning technique. The data expansion process arbitrarily expands the input data. For example, image data is a method of increasing the number of data by artificially making small changes such as rotating, cropping, tilting, and adjusting brightness of an image.

8 is a diagram illustrating a data expansion process according to an embodiment of the present invention.

Referring to FIG. 8, the processor 130 may include left and right inversion processing, scale reduction or enlargement processing, left and right rotation processing, and image information extracted from recording data of an existing curling race and image data photographing an ongoing curling race. At least one data expansion process of noise addition processing for the position coordinate of the curling stone is used as the learning data of the machine learning.

In addition, the processor 130 may further secure data by extracting information required when the strategy generation model is trained by using self-matching game information between curling simulators learning different strategies based on machine learning.

As such, the processor 130 extracts predetermined image information from the recorded data of the previously performed curling race and the image data of the ongoing curling race (or any curling race to be analyzed), and extracts the extracted image information. After performing at least one data expansion process among left and right inversion processing, scale reduction or enlargement processing, left and right rotation processing, and noise addition processing for the position coordinates of the curling stone, it is set as learning data and game situation information of the machine learning.

The processor 130 may analyze and generate a strategy for an analysis target curling match (ie, a current curling match) through a curling match strategy generation model constructed based on the collected data.

9 is a diagram illustrating a strategy generation process according to a curling match situation using the curling match strategy generation model according to an embodiment of the present invention.

As shown in FIG. 9, the processor 130 models a strategy generation model by performing machine learning based on a curling database constructed by analyzing data of a curling match that has been previously performed, and accordingly, various curling match strategies are applied. Learn. At this time, the training data includes pitching strategies (Draw, Guard, Take out, etc.) used by actual curlers according to the game situation, stone coordinates, pitch accuracy, end number, shot number, direction of stone rotation, etc. It includes. The processor 130 learns the information stored in the curling database constructed by recognizing the game situation of the analysis target curling game through a strategy generation model in which various curling game strategies have been learned in advance, and corresponds to at least the corresponding game situation information. Create a strategy.

In addition, the processor 130 automatically classifies the contents of the game (balling strategy, pitching accuracy, etc.) through the machine learning from the curling database, and processes the game performance evaluation and vulnerability analysis of the user (ie, curling player) to provide training methods for each user. I recommend you.

FIG. 10 is an example of a user interface providing a result of analyzing a performance of a curling competition player and a training method recommendation result according to an exemplary embodiment of the present invention. FIG. 11 is an example of a user interface for providing a curling match result analysis report according to an embodiment of the present invention, and FIG. 12 is a view showing the curling match result analysis report of FIG. 11 in more detail.

Referring to FIG. 10, the processor 130 evaluates suitability for a strategy selected by a user among recommended strategies, evaluates the performance of the selected strategy for each player participating in an ongoing curling match, and evaluates the result of the evaluation. On the basis of this, the performance and strategic fitness of each player are indexed. In addition, the processor 130 analyzes the weakness for each athlete based on the indexed evaluation result, and outputs, through the display, training method information according to the analysis result among a plurality of preset training method information.

At this time, the performance of the players may be an indicator indicating how well performed the necessary strategy according to the game situation, and may be expressed as an integer between 0 and 4 points used in the existing curling game notes. Do. In addition, the suitability of the strategy analysis may be a value obtained by evaluating which necessary strategy was selected according to the game situation, and in which direction the stone was pitched. For example, after selecting and applying a recommended strategy, the higher the score, the higher the degree that the game has progressed to the scoring situation or the more the stone's direction of rotation coincides with the strategic direction. In addition, the vulnerability for each player participating in the actual game, for example, after applying the selected strategy can be analyzed according to whether the player successfully performed the pitch according to the strategy. If it is determined that the pitching accuracy according to the athlete's strategy is statistically low, the pitching method and error information for the success of the strategy may be provided as the training method information.

Referring to FIG. 11, the processor 130 may provide an analysis result by separating a case in which a user is an expert such as a professional player and a general person who is not an expert when analyzing a game performance. In addition, the processor 130 may provide a curling game strategy and performance analysis result report in the form of a mobile application.

In addition, referring to FIG. 12, the processor 130 is a strategy and performance analysis result report, and includes detailed analysis including game result information including strategy and pitching accuracy for each end or player, strategy for each shot, and pitching accuracy analysis for each shot. Information, graphs including end-to-end odds trends and player-specific pitching accuracy / error, and statistical information, and feedback information including a comprehensive analysis of the above information may be generated and provided.

Hereinafter, a method of generating a curling match strategy according to an embodiment of the present invention will be described in detail with reference to FIG. 13. The curling match strategy generation method described with reference to FIG. 13 may be performed through the operation of the processor 130 described above.

13 is a flowchart illustrating a method of generating a curling match strategy according to an embodiment of the present invention.

First, collect the recording data for the plurality of curling competition has been carried out (S131), the collected data is learned through a predetermined machine learning to build a strategy generation model (S132).

At this time, through the web crawling (web crawling) can collect the recording data for the plurality of the curling game carried out, extract the predetermined image information and text information by template matching for each collected recording data, The strategy generation model may be constructed by machine learning image information and text information.

The recorded data of the plurality of curling competitions carried out include at least one of image information and text information, and the image information includes the coordinate information and the collision position information of the curling stone extracted from the image photographing the curling competition situation in a predetermined direction. Wherein the text information includes at least one of an end number, a shot number, a strategy performed, and a rotation direction of the curling stone.

Next, by recognizing the image of the image of the ongoing curling game to recognize the predetermined game situation information (S133).

At this time, the video data photographing the curling competition situation is received from a plurality of camera devices installed in the curling stadium, the image of the curling competition situation photographed from the vertical upper part is received from the received video data, and the reconstructed image of the preset simulator After matching with the position coordinates, predetermined image information may be extracted through template matching, and the extracted image information may be recognized as game situation information.

Then, at least one strategy corresponding to the recognized game situation information is generated through a strategy generation model, and recommendation information for the generated strategy is output (S134).

At this time, the suitability of the strategy selected by the user among the recommended strategies is evaluated, the performance of the selected strategy is evaluated for each player who participated in the ongoing curling match, and the performance and strategy suitability of each player based on the evaluation results are evaluated. It may further comprise the step of indexing. In addition, it is also possible to analyze the vulnerability for each athlete based on the indexed evaluation results, and output the training method information according to the result of analyzing the vulnerability among a plurality of preset training method information on a display.

In the above, after the predetermined image information is extracted from the recorded data of the previously performed curling race and the image data of the ongoing curling race, the extracted image information is subjected to left and right inversion processing, scale reduction or enlargement processing, left and right rotation processing, and After performing at least one data augmentation process among the noise addition processing for the position coordinate of the culling stone, it may be used as learning data of machine learning.

One embodiment of the present invention can also be implemented in the form of a recording medium containing instructions executable by a computer, such as a program module executed by the computer. Computer readable recording 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. In addition, the computer readable recording medium may include a computer storage medium. Computer storage media includes both volatile and nonvolatile, 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.

Although the methods and systems of the present invention have been described in connection with specific embodiments, some or all of their components or operations may be implemented using a computer system having a general purpose hardware architecture.

The foregoing description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are exemplary 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 of the present invention is shown by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. do.

100: curling match strategy generating device 400: network
110: communication module 120: memory
130: Processor 140: Database

Claims (13)

In the curling competition strategy generating device,
A memory storing a curling match strategy analysis and generation program; And
A processor for executing a program stored in the memory;
The processor according to the execution of the curling game strategy analysis and generation program,
By recognizing the image of the image of the ongoing curling game, it recognizes the preset game situation information, and learns the data collected from the recorded data of the plurality of curling games which have been carried out through preset machine learning to develop a strategy generation model. Constructing, generating one or more strategies corresponding to the recognized game situation information through the strategy generation model, outputting recommendation information for the generated strategy,
The recorded data of the plurality of curling competitions carried out include at least one of image information and text information.
And the data collected from the recorded data includes data extracted from self-matching game information between curling simulators learning different strategies based on machine learning.
The method of claim 1,
The image information includes the coordinate information and the collision position information of the curling stone extracted from the image photographed in the preset direction of the curling competition situation,
And the text information includes at least one of an end number, a shot number, a strategy performed, and a rotation direction of the curling stone.
The method of claim 1,
The processor,
Collects historical data about the plurality of curling matches carried out through web crawling,
Extracting predetermined image information and text information through template matching for each record material;
And machine learning the extracted image information and text information to build the strategy generation model.
The method of claim 1,
Further comprising a communication module,
The processor,
Receive image data of the curling competition situation from a plurality of camera devices installed in the curling stadium through the communication module,
Reconstruct the image taken from the vertical data of the curling competition situation from the image data,
After matching the reconstructed image with the position coordinates of the preset curling simulator, the predetermined image information is extracted through template matching,
And recognizing the extracted image information as game situation information.
The method of claim 4, wherein
The processor,
Extracting the image taken in a predetermined direction from the image data of the ongoing curling game, and continuously processing the position coordinates and matching of the curling simulator in real time to recognize the game situation of the ongoing curling game in real time Curling match strategy generating apparatus.
The method of claim 1,
The processor,
Extracting predetermined image information from the recorded data of the previously performed curling match and the image data of the ongoing curling match,
Learning the machine learning after performing at least one data augmentation process of the extracted image information from left and right inversion processing, scale reduction or enlargement processing, left and right rotation processing, and noise addition processing to the position coordinates of the curling stone; A curling race strategy generating device to set as data.
The method of claim 1,
The processor,
Assess suitability for the strategy selected by the user among the recommended strategies,
Evaluating the performance of the selected strategy for each player participating in the ongoing curling match,
Curling game strategy generating device for indexing the game performance and strategic fitness for each player based on the result of the evaluation.
The method of claim 7, wherein
The processor,
Analyze the vulnerability for each player based on the result of the indexed evaluation,
Curling game strategy generating device for outputting a training method information according to the result of analyzing the vulnerability of a plurality of preset training method information on the display.
In the curling match strategy generating method using a curling match strategy generating device,
Constructing a strategy generation model by learning data collected from recorded data about a plurality of previously performed curling races through predetermined machine learning;
Recognizing preset game situation information by recognizing an image photographing an ongoing curling game; And
Generating at least one strategy corresponding to the recognized game situation information through the strategy generation model, and outputting recommendation information for the generated strategy;
The recorded data of the plurality of curling competitions carried out include at least one of image information and text information,
The image information includes the coordinate information and the collision position information of the curling stone extracted from the image photographed in the preset direction of the curling competition situation,
The text information includes at least one of an end number, a shot number, a strategy performed, and a rotation direction of the curling stone,
And the data collected from the recorded data includes data extracted from self-matching game information between curling simulators learning different strategies based on machine learning.
The method of claim 9,
Building the strategy generation model,
Collects historical data about the plurality of curling competitions carried out through web crawling,
Extracting predetermined image information and text information through template matching for each record material;
And machine learning the extracted image information and text information to build the strategy generation model.
The method of claim 9,
Recognizing the game situation information,
Receive video data photographing the curling competition situation from a plurality of camera devices installed in the curling arena,
Reconstruct the image taken from the vertical data of the curling competition situation from the image data,
After matching the reconstructed image with the position coordinates of the preset curling simulator, the predetermined image information is extracted through template matching,
And recognizing the extracted image information as game situation information.
The method of claim 9,
Extracting at least one predetermined image information from the recorded data of the previously performed curling match and the image data of the ongoing curling match,
Learning the machine learning after performing at least one data augmentation process of the extracted image information from left and right inversion processing, scale reduction or enlargement processing, left and right rotation processing, and noise addition processing to the position coordinates of the curling stone; A curling match strategy generation method set as data.
The method of claim 9,
After outputting the recommendation information for the generated strategy,
Evaluating suitability for the strategy selected by the user among the recommended strategies;
Evaluating the performance of the selected strategy for each player participating in the ongoing curling match;
Indexing performance and strategic fitness of each player based on the result of the evaluation;
Analyzing the vulnerability for each player based on the result of the indexed evaluation; And
And outputting, through a display, training method information according to a result of analyzing the vulnerability among a plurality of preset training method information.

Images