KR102158014B1 - Method and apparatus for real - time monitoring of baseball game using artificial neural network - Google Patents

Abstract

In accordance with an embodiment of the present invention, in the method of providing a real-time prediction service for a baseball game based on an artificial intelligence engine, (a) providing a list of current and future baseball games and question information for which the game has not been completed, and And receiving game target information and question information for the selected baseball game in the user terminal; (b) estimating a result value corresponding to the game subject information and the question information through an artificial intelligence engine based on at least one of past play data and real-time play data of a team or player corresponding to the game subject information; And (c) providing the result value to the user terminal; including, wherein the game target information is team information or player information, and the question information is prediction of the game performance of a player who is participating in a baseball game or will participate in a baseball game for which the game has not been completed. It is a question about information and prediction information of the team's game performance, and step (b) is a method of deriving a result value per player at bat and inferring a result value corresponding to the question information based on this.

Description

Baseball game real-time prediction method and device using artificial neural network {METHOD AND APPARATUS FOR REAL-TIME MONITORING OF BASEBALL GAME USING ARTIFICIAL NEURAL NETWORK}

The present invention relates to a method and system for predicting the outcome of a baseball game through artificial intelligence.

In more detail, it relates to a method and a system capable of predicting hits/outs, goals/concessions of a corresponding match, and further predicting the final result of the match using data generated from a player's past match data and a match in real time.

Sabermetrics is a compound word of SABR (the society for American baseball research) and metrics, and refers to a study that mobilizes various mathematical/statistical methodologies to decompose the sport of baseball into molecular units.

Unlike other sports, baseball has been performing various analyzes of game results under the name of Sabermetrics from the past, and has had a great influence on the baseball world from the 1990s.

As such, many people have a high interest in predicting the outcome of a baseball game, and various methods have been studied accordingly. However, most of the previously studied methods of predicting game results are methods of inferring the current game by using data of past teams or players that have already been played and stored.

This method has a limitation in that the accuracy of the guess is deteriorated when the accumulated game information is small.

Unexamined Patent Publication No. 10-2015-0171189 (Name of invention: Big data-based real-time prediction method and system for sports events) Unexamined Patent Publication No. 10-2015-0171180 (Title of invention: Strategy simulation using big data and real-time win rate prediction method)

The present invention is to solve the above-described problems of the prior art, and aims to predict the outcome of a baseball game by artificial intelligence using data of a baseball game played in the past or data of a baseball game currently performed and generated in real time. do.

Explaining this in detail, the purpose is to learn artificial intelligence by extracting data from past game data held by players participating in a baseball game and data from a baseball game in real time, and to accurately predict the outcome of a baseball game currently in progress. do.

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.

As a technical means for achieving the above-described technical problem, in a method for providing a real-time prediction service for a baseball game based on an artificial intelligence engine performed by a server, (a) a current and future baseball game that has not been finished with a user terminal. Providing a game list and question information, and receiving game target information and question information for a baseball game selected from a user terminal; (b) estimating a result value corresponding to the game subject information and the question information through an artificial intelligence engine based on at least one of past play data and real-time play data of a team or player corresponding to the game subject information; And (c) providing the result value to the user terminal; including, wherein the game target information is team information or player information, and the question information is prediction of the game performance of a player who is participating in a baseball game or will participate in a baseball game for which the game has not been completed. It is a question regarding information and prediction information of the team's game performance, and step (b) may be a method of deriving a result value per player at bat, and inferring a result value corresponding to the question information based on this.

In an apparatus for providing a real-time prediction service for a baseball game based on an artificial intelligence engine, according to another embodiment of the present invention, receiving team selection information and question information selected by a user terminal, and responding to the question information through the artificial intelligence engine A memory in which a program for estimating the result of a game to be played is stored, and a processor that executes an operation for estimating the result of a baseball game by executing a program stored in the memory, wherein the processor is a current and future baseball game in which the game is not finished with a user terminal. Provides list and question information, receives game target information and question information for a baseball game selected from the user terminal, and artificially based on at least one of past play data and real-time play data of the team or player corresponding to the game target information. The intelligence engine infers the result value corresponding to the game target information and question information, and provides the result value to the user terminal, but the game target information is team information or player information, and the question information is for a baseball game that has not finished the game. It is a question about the game performance prediction information of the player who is participating or will be participating, and the game performance prediction information of the team, and it may be a device that derives the result value of the player at bat, and estimates a result value corresponding to the question information based on this.

The present invention collects baseball game data, and can predict the result of a baseball game in the future as well as the result of a real-time baseball game that is not finished based on artificial intelligence.

Explaining this in detail, it is possible to learn artificial intelligence by extracting data from past game data held by players participating in a baseball game and data from a baseball game in real time, and to accurately predict the result of a baseball game currently in progress.

1 is a diagram showing the configuration of a baseball game real-time prediction service system based on an artificial intelligence engine according to an embodiment of the present invention.
2 is a diagram showing the configuration of a baseball game real-time prediction service server based on an artificial intelligence engine according to an embodiment of the present invention.
3 is an operation flowchart showing a baseball game real-time prediction service method based on an artificial intelligence engine according to an embodiment of the present invention.
4A to 4C are exemplary views for explaining a driving principle of an artificial intelligence engine according to an embodiment of the present invention.
5 is a diagram illustrating an example of physical data received in real time according to an embodiment of the present invention.
6 to 7 are exemplary views showing an example of an interface screen provided through a user terminal according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" with another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a certain part "includes" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

The following examples are detailed descriptions to aid understanding of the present invention, and do not limit the scope of the present invention. Accordingly, the invention of the same scope performing the same function as the present invention will also belong to the scope of the present invention.

Throughout the specification, the server 100 may refer to an apparatus for providing a real-time baseball game prediction service based on an artificial intelligence engine.

1 is a diagram showing the configuration of a baseball game real-time prediction service system based on an artificial intelligence engine according to an embodiment of the present invention.

Referring to FIG. 1, a baseball game real-time prediction service system based on an artificial intelligence engine may include a server 100, a user terminal 200, and a baseball game data receiving equipment 300, which are mutually Can be connected.

The server 100 according to an embodiment of the present invention provides a real-time prediction service for a baseball game based on an artificial intelligence engine through a terminal application mounted on the user terminal 200. List and question information may be provided, and result values may be provided based on user selection.

The user terminal 200 checks the game list and question information provided from the server 100, selects game target information and question information for the information desired to be provided, and receives a result value based on the selection. do.

Here, the game target information may be a team or a player as information on an object desired to be provided by the user terminal 200, and the question information may be a type of question to know about the selected team or player.

Therefore, the question information may be a question about the game performance prediction information of a player who is participating in a baseball game or will be participating in a baseball game that has not yet finished, and the game performance prediction information of the team. Question information that can be selected by the user terminal 200 and transmitted to the server 100 is provided in the form of at least one of a result value per turn at bat, a result value per inning, and a prediction result value of game score, and is selected by the user, The server 100 may additionally receive detailed sub-information corresponding to each question information according to a user's selection.

For example, in the case of a question about the result value per turn at bat, game information, player and selection information on the at bat is additionally received from the user terminal 200, and in the case of a question about the result value per inning, the game information, team And selection information for innings, and if a question is about the result of predicting the game score, game information is additionally received from the user terminal 200.

Here, the game information may be a date on which a game selected by the user is performed or special information on a game from among the list of current and future baseball games for which the game selectable by the user is not finished.

Each of the question information may be provided by the user terminal 200 as an interface in a text format, but in an optional embodiment, the question information may be provided through an interface composed of an image or a video. For example, a method such as allowing a team to be selected through a mascot image of a team playing a match can be used.

In addition, the server 100 may further provide additional information on a baseball game selected by the user or detailed profile information on a player in addition to the game target information and question information to the user terminal 200 as another optional embodiment. . For example, additional information on a baseball game may include information such as the location or size of a stadium in which the baseball game is played, and detailed profile information on a player may provide a win rate or main position of the corresponding player.

The user terminal 200 may display data provided from the server 100 through a baseball game real-time prediction service application based on an artificial intelligence engine.

The baseball game real-time prediction service application based on the artificial intelligence engine may be an application embedded in the user terminal 200 or an application downloaded from an application distribution server and installed in the user terminal 200.

The plurality of user terminals 200 refer to communication terminals capable of using a terminal application in a wired or wireless communication environment. Here, the user terminal 200 may be a user's portable terminal. In FIG. 1, the user terminal 200 is shown as a smart phone, which is a kind of portable terminal, but the spirit of the present invention is not limited thereto, and as described above, there is no limitation on a terminal capable of mounting a terminal application. Can be borrowed.

To explain this in more detail, the user terminal 200 may include a handheld computing device (e.g., PDA, email client, etc.), any form of a mobile phone, or any form of another kind of computing or communication platform. However, the present invention is not limited thereto.

The baseball game data receiving equipment 300 may collectively refer to equipment that is installed in an actual baseball stadium to acquire real-time play data of a baseball game performed in real time, and transmits the data to the server 100.

Here, the real-time play data is a value related to the player's play result and includes physical data, which is a physical element including at least one of speed, position, and time, and performance data including progress information for each team participating in the baseball game. Can be.

Physical data can be the speed or angle at which the pitcher throws the ball, the speed at which the runner steals, and the like, and the performance data can include at-bats, innings, and scores in real time.

The physical data may collect various physical data generated in a game through a camera installed in the baseball field, but as an optional embodiment, a multimedia input device other than the camera may be included in the baseball game data receiving device 300. For example, a video reading system may be typically included here, and any other equipment capable of acquiring physical data may be used as the baseball game data receiving device 300.

The performance data may be directly received by the server 100 in the field of the baseball field through the baseball game data receiving equipment 300, but may be collected from the server of an official baseball-related institution. In the case of collecting performance data from the server of an official baseball-related institution, it is possible to additionally collect past play data.

Meanwhile, the communication network serves to connect the server 100 and the user terminal 200. That is, the communication network refers to a communication network that provides an access path so that the user terminals 200 can transmit and receive data after accessing the server 100. Communication networks are wired networks such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks), ISDNs (Integrated Service Digital Networks), and wireless networks such as wireless LANs, CDMA, Bluetooth, and satellite communications. However, the scope of the present invention is not limited thereto.

2 is a diagram showing the configuration of a baseball game real-time prediction service server based on an artificial intelligence engine according to an embodiment of the present invention.

Referring to FIG. 2, the server 100 according to an embodiment of the present invention includes a communication unit 110, a memory 120, a processor 130, and a database 140.

In detail, the communication unit 110 provides a communication interface necessary to provide a transmission/reception signal between the server 100, the user terminal 200, and the baseball game data receiving device 300 in the form of packet data in connection with a communication network. Further, the communication unit 110 may receive a data request from the user terminal 200 and the baseball game data receiving device 300 and transmit data as a response thereto.

Here, the communication unit 110 may be a device including hardware and software necessary to transmit and receive signals such as control signals or data signals through wired/wireless connection with other network devices.

The memory 120 records a program for performing a baseball game real-time prediction service based on an artificial intelligence engine. In addition, it performs a function of temporarily or permanently storing data processed by the processor 130. Here, the memory 120 may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto.

The processor 130, as a kind of central processing unit, controls the entire process of providing a baseball game real-time prediction service based on an artificial intelligence engine. Each step performed by the processor 130 will be described later with reference to FIG. 3.

Here, the processor 130 may include all types of devices capable of processing data, such as a processor. Here, the'processor' may refer to a data processing device embedded in hardware, which has a circuit physically structured to perform a function represented by a code or command included in a program. As an example of a data processing device built into the hardware as described above, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, and an application-specific integrated (ASIC) circuit) and processing devices such as field programmable gate arrays (FPGAs), but the scope of the present invention is not limited thereto.

The database 140 may store past play data of a team or player for learning of the artificial intelligence engine and providing to the user terminal 200, and real-time play data may be received and stored as needed.

In addition, as an optional embodiment, the database 140 may further include information for providing a separate page when requesting information on a specific player, team, or game from the user terminal 200.

3 is an operation flowchart showing a baseball game real-time prediction service method based on an artificial intelligence engine according to an embodiment of the present invention.

Referring to FIG. 3, first, a list of current and future baseball games and question information for which the game has not been completed is first provided from a user terminal, and game target information and question information for a baseball game selected from the user terminal are received (S310). .

Based on at least one of past play data and real-time play data of a team or player corresponding to the game target information, a result value corresponding to the game target information and question information is estimated through an artificial intelligence engine (S320).

In step S320, the server 100 derives a result value per turn at bat of the player using an artificial intelligence engine, and estimates a result value corresponding to the question information based on this. In this case, a process in which the artificial intelligence engine estimates the result value for the question information will be described with reference to FIG. 4A to be described later.

The result value estimated through step S320 is provided to the user terminal (S330).

The interface of the result value provided to the user terminal 200 provides the result of the game performance prediction information for the player or team selected by the user in a single sentence through numbers and text. More can be added.

A detailed description of the interface provided to the user terminal 200 will proceed through FIGS. 6 to 7 to be described later.

4A to 4C are exemplary views for explaining a driving principle of an artificial intelligence engine according to an embodiment of the present invention.

First, referring to FIG. 4A, a baseball game real-time prediction service based on an artificial intelligence engine estimates a result value through a hierarchical structure.

To explain this in detail, past play data on past teams or players are collected, and the data is set as an input layer. In addition, if at least one of the result value per turn at bat, the result value per inning, and the predicted game score is set as the output layer, the algorithm for the hidden layer between the input layer and the output layer on the neural network is established by performing multiple learning. It becomes.

When the above explanation is applied to explain the process of estimating the result value for the question information, the artificial intelligence engine estimates the result value per player at bat through play data collected in the past or collected in real time.

If the question information selected by the user terminal 200 is the result value per turn at bat, the guessing through the artificial intelligence engine ends at the step of estimating the result value per turn at bat. However, if the question information is the result value per inning, the AI engine predicts the result value per inning based on the result value per turn at bat, and if the question information is the result value of the game score prediction, it is a kind of layer that estimates the result value of the game score prediction through the result value per inning. The enemy prediction method is applied.

At this time, the result value per at-bat is about one of a plurality of performance data (e.g., hits, walks, strikeouts, deadballs, etc.) including on-base cases and outings, and the result per inning is karate. It includes any one of a plurality of performance data including the case of shift (for example, first inning A: B = 1:0, first inning A: B = 1:1).

To explain this easily, based on the data of the batter and the opponent pitcher, the hit or out of the corresponding at-bat batter is predicted, and the score per inning can be predicted by gathering this. In addition, if the prediction of the score per inning is completed, it is finally possible to predict the win or loss of the game through this.

This method can train an artificial intelligence engine to predict various outcomes of a baseball game, and has the strength of delivering flexible answers to user questions. In addition, since real-time data can be delivered as an input value, more clear and reliable conclusions can be drawn.

In addition, it is possible to additionally learn about the artificial intelligence engine while comparing the estimated result value and actual performance data by applying the artificial intelligence engine.

Referring to FIG. 4B, it can be seen that the present invention can apply an algorithm based on recurrent neural networks (RNN).

A representative algorithm that can be applied to an artificial intelligence engine to implement the service of the present invention may be a recurrent neural networks (RNN) series.

Fig. (a) shows a standard RNN module with a single layer. The RNN algorithm is characterized by a structure in which past data can affect the future because it contains loops.

In particular, Figure (b) shows a special type of long short-term memory models (LSTM) among the RNN series. The four layers included in the LSTM have a form in which interactions are repeated. Through this, the part using a single layer among the repeated network chains in the RNN is formed in a special structure that allows four interactions, so that the long-term dependency problem of the standard RNN model can be solved.

However, describing the service of the present invention through an RNN-based algorithm is an example, and an artificial intelligence engine such as a random forest and a support vector machine can be used.

In addition, since the number of hidden layers of the simple regression model may be increased, the scope of the present invention is not limited to which algorithm is applied, if implementation is possible.

Referring to FIG. 4C, the independent variables required for real-time prediction of a baseball game based on an artificial intelligence engine are shown as an example.

To explain this in detail, past play data and real-time play data used to predict a baseball game may be composed of independent and dependent variables, and the following is a list of independent variables that can be used representatively.

In order for the artificial intelligence engine to perform learning, it must be aware of the variables of each team. For example, as shown in the drawing, the information collected by the artificial intelligence engine has four categories, which can include "pitching stats", "batter stats", "defensive stats", and "baseball stats", and each stats Each can have lower stats.

In addition, as for the lower stats, for example, "Pitching stats" include average ERA, game, victory, defeat, save, hold, odds, innings, hits, home runs, walks, four pitches, strikeouts, runs, own runs, and on-base allowance per inning. May be included, and the "battery ability" may include average batting average, game, at bat, at bats, goals, hits, doubles, triples, home runs, bases, RBIs, sacrifice bunts, and sacrifice fly. "Defensive stats" can include position, game, starting game, defensive innings, errors, checkers, suicide, bodhisattva, side by side, defense ratio, foil, stealing allowance, stealing failure, and stealing blocking rate. Finally, "base base stats" It may include games, attempted steals, allowable steals, failed steals, jurors, and checkers.

5 is a diagram illustrating an example of physical data received in real time according to an embodiment of the present invention.

Referring to FIG. 5, it shows the types of physical data that can be collected by the baseball game data receiving equipment 300 in a pitching situation.

Physical data is measured through a camera provided in a baseball stadium as described above. Typical physical data that can be measured when throwing are pitch speed, rotation (speed/axis/tilt), release angle (horizontal/vertical), release point (horizontal/height), extension perceived speed, movement (horizontal/vertical). Stop), plate location (height/face), approach angle (horizontal/vertical stop), zone speed, zone time.

In addition, although not shown in FIG. 5, various physical data can be obtained from the batter, the stealing situation, and the defending players. In the case of a batter, the vector, the projected hang time, the expected hitting distance, the exit speed, the angle of view (vertical/horizontal), and the hitting point (horizontal/height) can be included. speed), extra bases, home run trot, lead distance, secondary lead (distance when ball is released to pitcher), first step (when bat-on-ball contact) Elapsed time), stealing first step (the pitcher's first movement time). Finally, the defending player is the first step (time elapsed), first step efficiency (angle deviation from the first step's linear distance), maximum speed, acceleration, linear distance, total distance, and outfield route. You can get outfield route efficiency (straight line/total distance), swap, pivot, maximum throwing speed, gunner swap, and so on.

In an optional embodiment, information on the environment of the stadium or equipment used for the game may be additionally collected to increase the accuracy of guessing the result value.

The measured physical data is transmitted to the server 100 through the baseball game data receiving device 300, and the server 100 applies real-time data to the artificial intelligence engine to increase the accuracy of the service.

6 to 7 are exemplary views showing an example of an interface screen provided through the user terminal 200 according to an embodiment of the present invention.

Referring to FIG. 6, question information 610 and lower selection information 620 may be included as a question selection screen for a real-time baseball game prediction service based on an artificial intelligence engine.

On the first screen of the interface, the question information 610 desired by the user may be composed of a button on which text is written. Examples shown in FIG. 6 include "What is the result per Q at-bat?", "What is the result per Q inning?", "What is the prediction of Q game scores?" An interface is provided so that the question information 610 can be selected with three buttons on which the text of is written.

If the user selects the question information 610, the user terminal 200 additionally presents the lower selection information 620 mapped to the question information 610 provided from the server 100 to the user to receive detailed information. can do.

For example, if the user selects and enters "Q What is the result per at-bat?", an interface is additionally provided to select the sub-selection information 620 so that the game information such as the game date and game name, and player or at-bat can be selected. Is done.

In addition, as described above, the lower selection information 620 that can be selected by the user varies according to the selection of the question information 610 presented through the user terminal 200.

7 is a result screen of a baseball game real-time prediction service based on an artificial intelligence engine, and may include a result value 710, another question selection function button 720, and a past prediction confirmation function button 730.

As described above, the interface providing the result value 710 may be provided as a single sentence through numbers or text.

In addition, the interface displaying the result value 710 may further include a different question selection function button 720 and a last prediction confirmation function button 730.

First, when another question selection function button 720 is input, a choice is provided so that the user can select another one of the questions provided through the question information 610 selected by the user, or the first question information 610 selection screen is returned. I can.

At this time, when a user is given a choice to select a question other than the previously selected question information 610, some sub-selection information 620, such as "match information", is identically mapped and the result value 710 for the user's convenience. ) Can be provided.

When the last prediction confirmation function button 730 is input, the result value 710 of another game corresponding to the question information 610 selected by the user is provided.

For example, after checking the result per inning 710 of game A and pressing the last prediction check function button 730, a list of verifiable matches including game A is provided, and when the user selects game B, results per inning of game B A value 710 is provided.

An embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable 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 above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that it can be easily modified into 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 illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

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

100: server
110: communication unit of the server 120: memory of the server
130: server's processor 140: server's database
200: user terminal 300: baseball game data receiving device

Claims (13)

In the method of providing a real-time prediction service for a baseball game based on an artificial intelligence engine performed by a server,
(a) providing a list of current and future baseball games and question information for which the game has not been completed to a user terminal, and receiving game target information and question information for the selected baseball game by the user terminal;
(b) estimating a result value corresponding to the game target information and question information through an artificial intelligence engine based on at least one of past play data and real-time play data of a team or player corresponding to the game target information; And
(c) providing the result value to the user terminal;
Including,
The competition target information is team information or player information,
The above question information is a question about the game performance prediction information of the players participating in or planning to participate in the baseball game for which the game has not been finished and the game performance prediction information of the team,
Before step (a),
The past play data for the past team or player is collected, the past play data is set as an input value of the input layer, and at least one of a result value per at bat, a result value per inning, and a prediction result value of game score is output to the output layer. Setting an output value and performing learning a plurality of times to establish an algorithm for a hidden layer between the input layer and the output layer on the neural network; further including, the artificial intelligence engine is operated based on the algorithm. ,
When the baseball game selected by the user terminal is performed in real time, the real-time play data generated in the baseball game is received and reflected in the result value estimate, but the play data is a value related to the player's play result, including speed, position, and By including physical data, which is a physical element including at least one of the time, and performance data including game progress information for each team participating in the baseball game, the past play data and real-time play data are configured as independent variables and dependent variables. ,
The step (b),
The result value per turn at bat of the player is derived, and based on this, the result value corresponding to the question information is estimated, and an additional analysis operation is performed based on the result value per turn at bat according to the question information, but the question information is per inning. If it is a result value, the artificial intelligence engine predicts the result value per inning based on the result value per turn at bat, and if the question information is the result value of the game score prediction, the artificial intelligence engine predicts the game score based on the result value per inning. A method of providing a real-time prediction service for a baseball game based on an artificial intelligence engine, which performs a hierarchical prediction method for predicting a result value. The method of claim 1,
The question information is provided in the form of at least one of a result value per at bat, a result value per inning, and a game score prediction result value. A method for providing a baseball game real-time prediction service based on an artificial intelligence engine. The method of claim 2,
When the question information is a question about the result value per player at bat, additionally receives game information, player and at-bat selection information from the user terminal,
When the question information is a question about the result value per inning of the team, game information, selection information for the team and innings are additionally received from the user terminal,
When the question information is a question about the result of predicting the game score of the team, the method for providing a baseball game real-time prediction service based on an artificial intelligence engine is further receiving selection information for the game information from the user terminal. The method of claim 1,
Step (c)
Based on the interface providing the result value, the result of the game performance prediction information for the player or team selected by the user is provided in a single sentence through numbers and text. Baseball game real-time based on artificial intelligence engine How to provide prediction services. The method of claim 4,
The interface for displaying the result value further includes another question selection function button and a last prediction confirmation function button,
When the other question selection function button is input, providing an option to select another one of the questions provided through the question information,
When the last prediction confirmation function button is input, providing a result value of another game corresponding to the question information selected by the user is provided, a baseball game real-time prediction service based on an artificial intelligence engine. delete The method of claim 1
The physical data is analyzed and collected from information measured by the camera of the stadium,
The performance data and past play data are collected from a server of an official baseball-related institution, a baseball game real-time prediction service providing method based on an artificial intelligence engine. delete The method of claim 1
The result value per turn at bat relates to any one of a plurality of performance data including an on-base case and an out case,
The result value per inning includes any one of the plurality of performance data including the case of alternating karate,
The performance data includes game progress information for each team participating in the baseball game. A method for providing a baseball game real-time prediction service based on an artificial intelligence engine. The method of claim 7
Comparing the result value and the performance data, and further learning about an artificial intelligence engine based on the comparison, the method for providing a real-time prediction service for a baseball game based on an artificial intelligence engine. delete In the apparatus for providing a real-time prediction service for a baseball game based on an artificial intelligence engine,
A memory in which a program for receiving team selection information and question information selected by the user terminal and estimating the match result corresponding to the question information through an artificial intelligence engine is stored;
Including a processor for executing an operation of estimating the result of the baseball game by executing the program stored in the memory,
The processor provides a list of current and future baseball games and question information for which the game has not been completed to the user terminal, receives game target information and question information for the baseball game selected by the user terminal, and corresponds to the game target information. Based on at least one of past play data and real-time play data of a team or player, a result value corresponding to the game target information and question information is estimated through an artificial intelligence engine, and the result value is provided to the user terminal,
The game target information is team information or player information, and the question information is a question about game performance prediction information and team game performance prediction information of players who are participating in or will be participating in a baseball game for which the game has not been completed,
Before receiving game target information and question information for the above baseball game,
The past play data for the past team or player is collected, the past play data is set as an input value of the input layer, and at least one of a result value per at bat, a result value per inning, and a prediction result value of game score is output to the output layer. Setting an output value and performing learning a plurality of times to establish an algorithm for a hidden layer between the input layer and the output layer on the neural network; further including, the artificial intelligence engine is operated based on the algorithm. ,
When the baseball game selected by the user terminal is performed in real time, the real-time play data generated in the baseball game is received and reflected in the result value estimate, but the play data is a value related to the player's play result, including speed, position, and By including physical data, which is a physical element including at least one of the time, and performance data including game progress information for each team participating in the baseball game, the past play data and real-time play data are configured as independent variables and dependent variables. ,
A player's turn at bat result value is derived, and based on this, the result value corresponding to the question information is estimated, and an additional analysis operation is performed based on the result value per turn at bat according to the question information, but the question information is the result per inning. If it is a value, the artificial intelligence engine predicts a result per inning based on the result per turn at bat, and if the question information is a game score prediction result, the artificial intelligence engine predicts the game score based on the result per inning. An apparatus for providing a real-time prediction service for a baseball game based on an artificial intelligence engine that performs a hierarchical prediction method of predicting a value. A computer-readable record in which a program for performing a real-time prediction service providing method for a baseball game based on an artificial intelligence engine according to any one of claims 1 to 5, 7 and 9 to 10 is recorded media.

Images