KR20210092685A - System for managing billiard game of artificial intelligence based on image analysis technology - Google Patents

Abstract

The present invention relates to an image analysis technology-based artificial intelligence billiard game management system. An objective to be achieved is to minimize costs consumed for an image analyzer through the simplification of an image analysis algorithm, calculate a more accurate result by more precisely decoding a position change and a progressing path of a billiard ball, and provide a more variety of game information to players based on the calculated result. According to one embodiment, the image analysis technology-based artificial intelligence billiard game management system includes: an image photographing part installed in an upper part of a billiard table to photograph an upper side of the billiard table; an image analysis part receiving an image photographed through the image photographing part, recognizing billiard balls in the image in accordance with color values, analyzing a collision between the billiard balls and a collision with cushions by calculating position values of the billiard balls, calculating a score result in accordance with an analysis result and pre-defined game rules, and calculating and recording game record information by each player based on the calculated score result; and a display part receiving and outputting the game record information of the image analysis part.

Description

Artificial intelligence billiard game management system based on image analysis technology {SYSTEM FOR MANAGING BILLIARD GAME OF ARTIFICIAL INTELLIGENCE BASED ON IMAGE ANALYSIS TECHNOLOGY}

An embodiment of the present invention relates to an artificial intelligence billiard game management system based on image analysis technology.

Billiards is a game in which the score goes up or down according to a set rule depending on the type of game. The conventional billiard score calculation method was a method in which the player moved the score display eggs one by one at the score counter installed next to the billiard table to calculate the score. That is, the billiard player calculates a score by moving the score display eggs by the same number as the gain/loss number using a plurality of score display eggs moving left and right along the horizontal bar.

In such a conventional score calculation method, the player must directly count the score and move the score display egg according to the score. However, the player forgets the high score and the score gain or loss is unclear.

In addition, in billiards, handy points are applied according to skill, and the method of applying the player's handy points is different depending on the region or billiard room, so when a player you meet for the first time plays a billiards game, it is difficult to apply the handy score fairly. .

In particular, the three cushion is a method in which three balls are placed on the billiard table and a score is scored by hitting the cushion on the side of the billiard table three or more times before hitting the last of the two red balls.

Recently, a billiard game system that determines whether a cue ball collides with a first red ball, a second red ball, or a cushion by using a billiard table coordinate system has emerged.

However, since such a billiard game system cannot accurately calculate the center coordinates of a billiard ball due to an afterimage of the billiard ball remaining in the photographed image information, there is a problem in that it cannot accurately determine whether the billiard ball collides.

Registered Patent Publication No. 10-1938607 (Registration Date: January 09, 2019) Laid-Open Patent Publication No. 10-2013-0114512 (published date: October 18, 2013)

The embodiment of the present invention minimizes the cost of the image analysis apparatus through the simplification of the image analysis algorithm, reads the progress path and position change of the billiard ball more finely, calculates a more accurate result, and calculates the calculated result. It provides an artificial intelligence billiards game management system based on video analysis technology that provides more diverse and game information to players.

An artificial intelligence billiards game management system based on image analysis technology according to an embodiment of the present invention includes: an image capturing unit installed on an upper portion of a billiard table to photograph an upper surface of the billiard table; Receives an image captured through the image capturing unit, recognizes a billiard ball in the image according to a color value, calculates the position value of the billiard ball, analyzes the collision between billiard spaces and the cushion, and defines the result of the analysis in advance an image analysis unit that calculates a scoring result according to the established game rules, and calculates and records game record information for each player based on the calculated scoring result; and a display unit for receiving and outputting game record information from the image analysis unit.

In addition, the image analysis unit converts the image photographed through the image capturing unit into an alpha channel image, extracts a K value among CMYK values from the converted alpha channel image, identifies each billiard ball according to the extracted K value, , a billiard ball identification unit defining the water polo; The center coordinate value of the cue ball identified from the alpha channel image and the distance coordinate value between the cue ball and the cushion are respectively calculated, and the collision between the billiard space and the cushion is recognized according to the calculated center coordinate value and the distance coordinate value. Apparatus progress path analysis unit to analyze the progress path and location of the; a scoring result calculation unit for calculating a scoring result for each player by determining whether the path and position of the billiard ball analyzed through the water polo path analysis unit satisfy a predefined game rule; And, based on the scoring result calculated through the scoring result calculation unit, each player's scoring and non-scoring data and the number of plays are calculated, and the continuous scoring record, average score, batting average, and number of bats are calculated to generate game record information to the display unit. It may include a game record calculation unit to provide.

In addition, the billiard ball identification unit may define a billiard ball in which a position change according to a change in a straight path through the cue ball traveling path analysis unit is initially generated as a precursor.

In addition, the display unit may receive a ball designation from the user, transmit the designated ball information to the billiard ball identification unit to define the line ball, and transmit information about the ball defined by the billiard ball identification unit.

In addition, the cue ball progress path analysis unit defines a virtual rail area formed along a line spaced apart from the cushion of the billiard table by the radius of the billiard ball and a virtual field area that is an area inside the rail area, respectively, in the rail area. When at least one of the X and Y values among the center coordinate values for the cue ball is 0, or when at least one of the X and Y values among the distance coordinate values is 0, it is recognized as a cushion collision of the cue ball, and the field area If it detects a change in the linear travel path of the apparatus, it can be recognized as a collision of the apparatus.

In addition, the scoring result calculation unit includes information on the scoring success reading criteria including whether or not there is a collision between the cue ball and the billiard ball excluding the cue ball, the number and sequence of collisions with the billiard ball and the cushion, and the progress change of the billiard ball excluding the cue ball first occurs whether the cue ball and the cue ball collided, whether the cue ball and the cushion collide, whether there was a billiard ball in the shooting area, and whether at least one of the position and path of the billiard ball other than the first ball was changed first; Scoring failure reading reference information including whether a preset play time is observed and whether the scoring success reading criterion information is satisfied is defined, respectively, so that a scoring result can be calculated for each player.

In addition, a server unit for receiving the game record information of the image analysis unit through the Internet communication network, storing the input game record information, and accumulating game record information for each player to generate game statistical information; and a game information providing unit implemented in the form of at least one of a mobile application and a web site, and receiving and providing game record information and game statistics information from the server unit according to player login information.

According to the present invention, the cost of the image analysis apparatus is minimized through the simplification of the image analysis algorithm, the progress path and position change of the billiard ball are read more finely, the more accurate result is calculated, and based on the calculated result It is possible to provide an artificial intelligence billiards game management system based on image analysis technology that provides more diverse game information to players.

1 is a schematic diagram showing the overall configuration and configuration relationship of an artificial intelligence billiard game management system based on image analysis technology according to an embodiment of the present invention.
2 is a block diagram showing the overall configuration of an artificial intelligence billiard game management system based on image analysis technology according to an embodiment of the present invention.
3 is a block diagram illustrating a detailed configuration of an image analysis unit according to an embodiment of the present invention.
4 is a diagram illustrating an image captured image of an image capturing unit and an image captured image through an image analysis program of an image analyzing unit, respectively, according to an embodiment of the present invention.
5 is a view showing a captured image showing a virtual rail region and a field region defined in the image analysis program of the image analysis unit according to an embodiment of the present invention.
FIG. 6 is a view illustrating the rail area shown in FIG. 5 .
7 is a view showing a captured image for grasping location information of a billiard ball through an image analysis program of an image analysis unit according to an embodiment of the present invention.
8 is a view showing a captured image of the image analysis program of the image analysis unit for explaining the cushion collision detection principle and the progress path analysis method of the cue ball according to an embodiment of the present invention.
9 is a view showing a display unit for displaying various game record information according to an embodiment of the present invention.

Terms used in this specification will be briefly described, and the present invention will be described in detail.

The terms used in the present invention have been selected as currently widely used general terms as possible while considering the functions in the present invention, but these may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, and the like. In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term and the overall content of the present invention, rather than the name of a simple term.

When a part "includes" a certain element throughout the specification, this means that other elements may be further included, rather than excluding other elements, unless otherwise stated. In addition, terms such as "...unit" and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software. .

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those of ordinary skill in the art can easily carry out the embodiments of the present invention. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

1 is a schematic diagram showing the overall configuration and configuration relationship of an artificial intelligence billiard game management system based on image analysis technology according to an embodiment of the present invention, and FIG. 2 is an image analysis technology-based artificial intelligence billiards according to an embodiment of the present invention. It is a block diagram showing the overall configuration of the game management system, Figure 3 is a block diagram showing the detailed configuration of the image analysis unit according to the embodiment of the present invention, Figure 4 is an image capture image of the image capturing unit according to the embodiment of the present invention, It is a view showing image captured images through the image analysis program of the image analysis unit, respectively, and FIG. 5 is a view showing captured images showing the virtual rail region and the field region defined in the image analysis program of the image analysis unit according to an embodiment of the present invention 6 is a view for explaining the rail region shown in FIG. 5, and FIG. 7 is a captured image for grasping the location information of the billiard ball through the image analysis program of the image analysis unit according to the embodiment of the present invention. 8 is a view showing a captured image of the image analysis program of the image analysis unit for explaining the cushion collision detection principle and progress path analysis method of the cue ball according to an embodiment of the present invention, and FIG. 9 is an embodiment of the present invention It is a view showing a display unit for displaying various game record information according to an example.

1 and 2 , the artificial intelligence billiard game management system 1000 based on image analysis technology according to an embodiment of the present invention includes an image capturing unit 100 , an image analyzing unit 200 , and a display unit 300 . , a server unit 400 and a game information providing unit 500 may be included.

The image capturing unit 100 is installed on the top of the billiard table 10 to photograph the upper surface of the billiard table 10, thereby generating images of the billiard table, water polo and object balls, and the game starts and At the same time, the shooting mode is activated and you can take a picture.

The image capturing unit 100 may include a camera module, and the camera module is installed at a location spaced apart from the billiard table 10 by a predetermined distance, and is located in the center of the billiard table 10 or the billiard table ( 10) It may be located at a predetermined distance from the central portion of the upper portion, but in this embodiment, the installation position of the camera module is not specifically limited.

Also, the camera module may capture an image at a number of frames greater than or equal to a predetermined reference number per second. For example, the camera module may capture an image at 60 frames per second or more in order to accurately capture the movement of the billiard ball. The image analysis unit 200 receives an image captured by the image capturing unit 100 in real time, recognizes a billiard ball in the image according to a color value, calculates the position value of the billiard ball, and It is possible to analyze the collision with the cushion, calculate a score result according to the analysis result and a predefined game rule, and calculate and record game record information for each player based on the calculated score result.

To this end, the image analysis unit 200 includes a billiard ball identification unit 210, a cue ball progress path analysis unit 220, a scoring result calculation unit 230, and a game record calculation unit 240 as shown in FIG. can do.

The billiard ball identification unit 210 converts the image captured by the image capturing unit 100 into an alpha channel image, and K (black) among CMYK (cyan, magenta, yellow, black) values in the converted alpha channel image. ) value, identify each billiard ball according to the extracted K value, and define water polo.

For example, an image taken at an illuminance of 1,800 lux to 2,000 lux or less is shown in (a) of FIG. 4 , and after converting it to the alpha channel of an image analysis program, CMYK (cyan, magenta, yellow, black) values Among them, the K (black) value is extracted. At this time, the red ball may be extracted as K97, the white ball as K3, and the yellow ball as K24.

4 (b) and (c), as a result of the extraction of the K value for each billiard ball, the ball with the highest K value (the ball with the least amount of light exposure) is defined as a red sphere (K97, H32), and K The ball with the lowest value (the ball with the most light exposure) can be defined as a white ball (K3, H98), and the remaining balls can be defined as a yellow ball (K24, H82).

A conventional image analysis program identifies a billiard ball through RGB color analysis of an image. As in this embodiment, a color analysis method of a billiard ball by extracting a K (black) value from CMYK (cyan, magenta, yellow, black) values Since the algorithm is relatively simpler than the conventional RGB color analysis method, there is less analysis error. For example, if the player wears yellow gloves and plays, there is a high possibility that an error will occur due to the color of the glove. In addition, in the case of conventional RGB color analysis, since the corresponding algorithm is quite complex, the CPU occupancy for the hardware is high. However, in this embodiment, the manufacturing cost of the hardware is also lower than the conventional one due to the relatively simple algorithm design, thereby reducing costs.

The billiard ball identification unit 210 may define the white balls (K3, H98) and the yellow balls (K24, H82) as the cue ball according to the image analysis result.

The billiard ball identification unit 210 defines a billiard ball in which a position change due to a change in a straight path through a cue ball traveling path analysis unit 220 to be described later as a precursor, and the billiard ball identification unit 210 It can deliver the precursor information defined as . That is, after the start of the game, the change of the straight path is caused by a collision with another ball among the balls identified as the cue ball, and the ball whose position change occurs first can be defined as the pioneer.

The cue ball progress path analysis unit 220 calculates the center coordinate value of the cue ball identified from the alpha channel image, and the distance coordinate value between the cue ball and the cushion, respectively, and according to the calculated center coordinate value and the distance coordinate value, the billiard ball By recognizing the collision between the two bodies and the collision with the cushion, the path and position of the apparatus can be analyzed.

More specifically, as shown in FIGS. 5 and 6, the cue ball progress path analysis unit 220 defines a virtual rail region formed along a line spaced apart from the cushion of the billiard table 10 by the radius of the billiard ball. and a virtual field area that is an area inside the rail area may be defined. The virtual rail area and the field area are virtual areas for detecting collision with the object ball according to the change of the previous course of the cue ball in the field area and for recognizing the cushion contact using the position value of the cue ball to the rail area, respectively.

As described above, the cue ball progress path analysis unit 220 stores the position information of each ball on the center coordinate value (center point coordinate value of the ball) and the distance coordinate value (X, Y axis separated from the center coordinate value between the cushion (rail area) distance) can be found. For example, as shown in Fig. 7, the center coordinate values of each ball are X1, Y1 = 525mm, 1333mm, and the distance coordinate values are X2, Y2=1475mm, 1373mm. It is possible to grasp the position information about the position and how far each ball is from the cushion part from the center.

When at least one of the X and Y values among the center coordinate values of the cue ball in the rail region is 0, or at least one of the X and Y values among the distance coordinate values is 0, the cue ball progress path analysis unit 220 It can be recognized as a collision of the cushion of the apparatus, and when a change in the straight path of the apparatus is detected in the field area, it can be recognized as a collision of the apparatus.

More specifically, when a contact point in the rail area occurs, it is recognized as a rail collision, and in the case of a three-ball game, it is possible to recognize whether or not more than three cushions of the water polo, which is a score satisfying condition, have occurred by the number of rail contact points.

For example, as shown in FIG. 8, when the X2 or Y2 value indicating the distance value between the virtual rail area (yellow line area) and the cue ball becomes '0', the cue ball can be recognized as colliding with the rail (cushion). can

On the other hand, collision detection between the cue ball and the object ball can be recognized by the presence or absence of a change in the straight path of the cue ball. For example, as shown in FIG. 8, point A and point B among the progress path of the cue ball (hwang ball) are field areas. It can be confirmed that the course change occurs within the field, and the occurrence of the course change within the field area at this time can be recognized as a collision of the apparatus. In addition, it can be confirmed that the water ball (hwanggu) collided with the white ball at point A and collided with the red ball at point B.

Looking at the progress path of the water polo shown in FIG. 8, the condition that the ball must collide with the ball except for the water polo among the rules or conditions of a general three-ball game is met, and the corresponding water polo is C, D, E, F, G, H It can be seen that the contact point (collision) with the rail or cushion occurs a total of 5 times at the point. Summarizing the history of these cue ball (hwanggu), we can see 'A point white ball collision', 'C point rail collision', 'D point rail collision' 'E point rail collision', 'F point rail collision', 'G point rail collision', It becomes 'Red ball collision at point B' and 'Rail collision at point H', and the cue ball in the history may be determined to have successfully scored through the scoring result calculator 230 .

Since the conventional method for determining the progress path of water polo determines whether to score by changing the coordinate value of the object ball, the result cannot be known quickly by deriving the result after all balls are completely stopped, but the water polo path analysis unit 200 according to this embodiment ) defines the collision of the object ball and the collision of the rail with the focus on the change of the course of the cue ball, so that the result of quick scoring is calculated and, at the same time, more precise and accurate results can be derived by calculating the distance from the rail in units of 1 mm.

The scoring result calculation unit 230 determines whether the traveling path and position of the billiard ball analyzed through the water polo path analysis unit 220 meet the predefined game rules, respectively, and calculates the scoring result for each player. can

To this end, the scoring result calculation unit 230 may calculate the scoring result for each player by comparing the scoring success reading reference information and the scoring failure reading reference information respectively with the analysis result of the water polo progress path analysis unit 220 .

The scoring success reading reference information may include game rule information regarding whether or not a ball collides with a billiard ball other than a lead ball, and the number and sequence of collisions with the billiard ball and the cushion.

For example, the scoring result calculation unit 230 reads whether the ball designated by the user is a leading ball in order to read the scoring success, and if the user designates the yellow ball as the leading ball, the course change of the yellow ball must occur first, the ball except the leading ball Reads whether all collisions have occurred (when a collision occurs, the path of the pioneer changes), whether both the white ball and the red ball collide in the rail area, the contact point (distance 0) in the rail area is 3 Whether or not more than 1 collision occurs, whether collision occurs with balls except for the cue ball and rail collision 3 times or more, when the method specified in the board system is met (ex. When the finish is set to 2 cushion, the rail contact must occur 2 times first) Success in scoring can be judged by checking whether the conditions such as all collisions with the ball other than the apparatus) are satisfied.

The scoring failure reading reference information includes whether a change in the progress of the billiard ball excluding the cue ball occurs first, whether the cue ball and the billiard ball excluding the cue ball collide, whether the cue ball and the cushion collide, whether the billiard ball exists in the shooting area, the precedent ball In addition, it may include game rule information regarding whether at least one of the location and progress path of the billiard ball is changed first, whether a preset play time is complied with, and whether or not the scoring success reading criterion information is satisfied.

For example, the scoring result calculation unit 230 may first cause a change in the course of a ball other than the ball designated by the user in order to read the scoring failure, and if it does not correspond to the above-described scoring success reading reference information, the collision of the ball In the event of a change in the path of the lead, whether there are 3 balls in the rail area or not, if there is a change in the position and path of the ball except for the lead in the user's turn, the play set in the board system It is possible to determine whether or not a score has failed by checking whether conditions such as time compliance or when the method is not specified by the user in the board system are satisfied.

The game record calculation unit 240 calculates each player's scoring and non-scoring data and the number of plays based on the scoring result calculated through the scoring result calculation unit 230 to record continuous scoring, average score, batting average, and ball The game record information may be generated by calculating the number of strokes and provided to the display unit 300 .

The display unit 300 may receive the game record information of the image analysis unit 200 and output it through a preset interface.

For example, the display unit 300 records HR (High run) consecutive scores/ AVG (Average) score/batting average/ through calculation and calculation of the player's score, non-scoring data, and the number of plays from the game record calculation unit 240 . The number of empty bats can be displayed, and the game record information can be checked in real time by the player.

More specifically, as shown in Fig. 9, end the game (A1), call (A2), view menu (A3), number of goals (A4), view record (AVG, batting average, HR, batting) (A6) , handy score (A7), inning record (A8), inning time reset (A9), and replay view (A10) can provide various functions and information.

On the other hand, the display unit 300 may receive a ball designation from the user and transmit the designated ball ball information to the billiard ball identification unit 210 to arbitrarily define the ball ball through a manual method.

The server unit 400 receives the game record information of the image analysis unit 200 through the Internet communication network, stores the input game record information, and accumulates game record information for each player to generate game statistics information. there is.

The game information providing unit 500 is implemented in the form of at least one of a mobile application and a web site, and requests information inquiry to the server unit 400 according to the player login information, and the server unit 400 according to the request contents. It can receive and provide game record information and game statistics information from In this way, after storing the game record in the server unit 400, it is possible to provide a service for inquiring and outputting statistical data of records for several years through a mobile application or website in the future.

What has been described above is only one embodiment for implementing the artificial intelligence billiard game management system based on the image analysis technology according to the present invention, and the present invention is not limited to the above embodiment, and is claimed in the claims below. As such, without departing from the gist of the present invention, it will be said that the technical spirit of the present invention exists to the extent that various modifications can be made by anyone with ordinary knowledge in the field to which the present invention belongs.

1000: artificial intelligence billiards game management system
100: video recording unit
200: image analysis unit
210: billiard ball identification unit
220: water polo path analysis unit
230: scoring result calculation unit
240: game record calculation unit
300: display unit
400: server unit
500: game information providing unit
10: Billiard Table
20: Internet communication device

Claims (7)

an image capturing unit installed on the billiard table to photograph an upper surface of the billiard table;
Receives an image captured through the image capturing unit, recognizes a billiard ball in the image according to a color value, calculates the position value of the billiard ball, analyzes the collision between billiard spaces and the cushion, and defines the result of the analysis in advance an image analysis unit that calculates a scoring result according to the established game rules, and calculates and records game record information for each player based on the calculated scoring result; and
Artificial intelligence billiards game management system based on image analysis technology, characterized in that it comprises a display unit for receiving and outputting the game record information of the image analysis unit.
According to claim 1,
The image analysis unit,
A billiard ball that converts an image photographed through the image capturing unit into an alpha channel image, extracts a K value among CMYK values from the converted alpha channel image, identifies each billiard ball according to the extracted K value, and defines a cue ball identification unit;
The center coordinate value of the cue ball identified from the alpha channel image and the distance coordinate value between the cue ball and the cushion are respectively calculated, and the collision between the billiard space and the cushion is recognized according to the calculated center coordinate value and the distance coordinate value. Apparatus progress path analysis unit to analyze the progress path and location of the;
a scoring result calculation unit for calculating a scoring result for each player by determining whether the path and position of the billiard ball analyzed through the water polo path analysis unit satisfy a predefined game rule; and
Based on the scoring result calculated through the scoring result calculation unit, each player's scoring and non-scoring data and the number of plays are calculated, and the continuous scoring record, average score, batting average, and number of bats are calculated, and game record information is generated and provided to the display unit. An artificial intelligence billiards game management system based on image analysis technology, characterized in that it comprises a game record calculation unit.
3. The method of claim 2,
The billiard ball identification unit,
An artificial intelligence billiards game management system based on image analysis technology, characterized in that a billiard ball, which first generated a position change according to a change in a straight path through the water polo progress path analysis unit, is defined as a pioneer.
3. The method of claim 2,
The display unit,
An artificial intelligence billiards game management system based on image analysis technology, characterized in that receiving a designation of a ball from a user, delivering the designated ball information to the billiard ball identification unit, defining the ball, and delivering the information defined as a cue ball to the billiard ball identification unit.
3. The method of claim 2,
The water polo progress path analysis unit,
An imaginary rail region formed along a line spaced apart from the cushion of the billiard table by the radius of the billiard ball and an imaginary field region that is an region inside the rail region are respectively defined, and X of the center coordinate values for the cue ball in the rail region and when at least one of the Y values is 0 or at least one of the X and Y values among the distance coordinate values is 0, it is recognized as a cushion collision of the cue ball, and the straight path of the cue ball is changed in the field area An artificial intelligence billiards game management system based on image analysis technology, characterized in that it is recognized as a collision of water polo when it detects.
3. The method of claim 2,
The scoring result calculation unit,
Scoring success reading standard information including whether there is a collision between the ball and billiard balls excluding the cue ball, the number and sequence of collisions with the billiard ball and cushion, whether the change in the progress of the billiard ball excluding the cue ball occurred first, and the cue ball and the cue ball excluding the cue ball Whether the billiard ball collides, whether the cue ball and the cushion collide, whether there is a billiard ball in the shooting area, whether at least one of the location and path of the billiard ball other than the first ball is changed first, whether the preset play time is observed, and An artificial intelligence billiard game management system based on image analysis technology, characterized in that the scoring failure reading criterion information including whether the scoring success reading criterion information is satisfied or not is defined, respectively, and calculating the scoring result for each player.
According to claim 1,
a server unit for receiving the game record information of the image analysis unit through an Internet communication network, storing the input game record information, and accumulating game record information for each player to generate game statistical information; and
Video analysis technology-based, implemented in the form of at least one of a mobile application and a web site, and further comprising a game information providing unit that receives and provides game record information and game statistics information from the server unit according to player login information of artificial intelligence billiards game management system.

Images