KR20200072391A - Method and apparatus for predicting game indicator information - Google Patents

Abstract

Disclosed are a method and apparatus for predicting game indicator information. The method for predicting the game indicator information includes the steps of: generating statistical data based on log data of a plurality of games; generating training data for training a predictive model based on the statistical data; training the predictive model using the training data; and predicting the game index information of a target game using the learned predictive model, Therefore, even at the beginning of a game launch, it is possible to predict the future game index information of the game to support rapid decision-making of managing the game.

Description

METHOD AND APPARATUS FOR PREDICTING GAME INDICATOR INFORMATION

The embodiments below relate to techniques for predicting game indicator information.

Predicting game metric information is a major issue for any gaming company. For example, predicting game index information such as sales and the number of game users is an important issue for a company. Predicting such game index information can be a clue to the solution of what strategy to develop.

For example, in the case of the general sales prediction method, the process of estimating sales by humanistic social statistics and statistical techniques is performed. This seems to be an efficient method as a method of diagnosing the present based on past information, but there is a limit to practical application because the solution of how to prepare for the future sales target is not clearly presented. Even if the statistical explanatory power is high, there are problems that companies cannot use properly in the field work.

Therefore, there is a need to develop a technical means to solve the above problems and accurately and effectively predict game index information.

International application No. WO 2017/200234

A method for predicting game index information according to an embodiment includes generating statistical data based on log data of a plurality of games; Generating training data for training a predictive model based on the statistical data; Training the prediction model using the training data; And predicting game index information of the target game using the learned prediction model.

The generating of the statistical data may include classifying the plurality of games by game genre; And generating statistical data corresponding to each game genre based on the classification result.

The step of training the predictive model may include training a predictive model of a game genre corresponding to the statistical data based on the statistical data.

The prediction model may include a prediction model for predicting the number of game play users of the target game and a model for predicting daily sales of the target game.

The log data may include at least one of access information, payment information, product information, event information, and inspection information.

The step of predicting game index information of the target game may include predicting the number of game play users of the target game after N days and the daily sales of the target game through the prediction model, wherein N is , May be a natural number of 2 or more.

Prediction of game indicator information of the target game includes predicting game indicator information of the target game using the learned prediction model using at least one of basic general purpose statistical data and game state statistical data as input. can do.

The predicting game index information of the target game may include predicting game index information of the target game using a prediction model corresponding to the game genre of the target game.

The predicting game index information of the target game includes: calculating a similarity between the game genre of the target game and a plurality of different game genres; Selecting a prediction model corresponding to the game genre of the target game based on the calculated similarity or a user's selection; And predicting game index information of the target game using the selected prediction model.

In the calculating of the similarity, the similarity is calculated based on at least one of the game genre of the target game, the number of previous game play users of the target game, the previous sales information of the target game, and the previous game indicator of the target game. It may include the steps.

The prediction model may be based on at least one of a linear regression model, a neural network, and a long-term and short-term memory cyclic neural network.

A method for predicting game index information according to another embodiment includes classifying log data for a plurality of games by game genre; Generating statistical data corresponding to each game genre based on the classification result; Learning a prediction model for predicting game index information based on the statistical data; And predicting game index information of the target game using the learned prediction model.

The apparatus for predicting game index information according to an embodiment includes a memory and a processor, the memory stores instructions executable by the processor, and when the instructions are executed by the processor, the processor may include a plurality of games. Generate statistical data based on the log data of the data, generate training data for training a predictive model based on the statistical data, train the predictive model using the training data, and use the learned predictive model By doing so, it is possible to predict game index information of the target game.

The processor may classify the plurality of games for each game genre, and generate statistical data corresponding to each game genre based on the classification result.

The processor may train a prediction model of a game genre corresponding to the statistical data based on the statistical data.

The prediction model may include a prediction model for predicting the number of game play users of the target game and a model for predicting daily sales of the target game.

The processor predicts the number of gameplay users of the target game after N days and the daily sales of the target game through the prediction model, and the N may be a natural number of 2 or more.

The processor may predict game index information of the target game using a prediction model corresponding to the game genre of the target game.

The processor calculates the similarity between the game genre of the target game and a plurality of different game genres, and selects a predictive model corresponding to the game genre of the target game based on the calculated similarity or user's selection, Game index information of the target game may be predicted using the selected prediction model.

An apparatus for predicting game index information according to another embodiment includes a memory and a processor, the memory stores instructions executable by the processor, and when the instructions are executed by the processor, the processor may include a plurality of games. Classify log data for each game genre, generate statistical data corresponding to each game genre based on the classification result, train a prediction model to predict game index information based on the statistical data, and train the learning It is possible to predict game index information of the target game using the predicted model.

The processor calculates the similarity between the game genre of the target game and a plurality of different game genres, and selects a predictive model corresponding to the game genre of the target game based on the calculated similarity or user's selection, Game index information of the target game may be predicted using the selected prediction model.

According to one embodiment, when a new game is launched (launching), even in the case of a cold start in which the game indicator information corresponding to the corresponding game is insufficient, it is possible to accurately and effectively predict the game indicator information related to the game.

According to an embodiment, the future game indicator information of the game may be predicted even at the beginning of the game based on the game indicator information predicted through the game indicator information prediction method to support rapid decision making for game operation.

According to an embodiment, when an operator of a game plans an update or event of a game, the game is updated by predicting game indicator information according to a game update or event event when the game is updated or a game event is performed. Alternatively, the expected effect through the event can be predicted in advance, and an operation strategy for the game can be established according to the prediction result.

1 is a diagram for providing an overview of a game system according to an embodiment.
2 is a flowchart illustrating an operation of a method for predicting game indicator information according to an embodiment.
3 is a diagram for explaining an example of a process of learning a prediction model of game index information according to an embodiment.
FIG. 4 is a flowchart illustrating an example of a process of predicting game index information of a game after N (N is a natural number) is a game index information prediction model of a game according to an embodiment.
5 is a diagram for explaining an example of a process of predicting game index information of a target game through an integrated prediction model for each game genre according to an embodiment.
6 is a diagram for explaining an example of a process of predicting game index information of a target game through a prediction model for each game according to an embodiment.
7 is a diagram illustrating a configuration of an apparatus for predicting game index information according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, various changes may be made to the embodiments, and the scope of the patent application right is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes for the embodiments are included in the scope of rights.

The terms used in the examples are for illustrative purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as “include” or “have” are intended to indicate that there are features, numbers, steps, operations, components, parts, or combinations thereof described on the specification, and one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person skilled in the art to which the embodiment belongs. Terms, such as those defined in a commonly used dictionary, should be interpreted as having meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Does not.

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of reference numerals, and redundant descriptions thereof will be omitted. In describing the embodiments, when it is determined that detailed descriptions of related well-known technologies may unnecessarily obscure the subject matter of the embodiments, detailed descriptions thereof will be omitted.

1 is a diagram for providing an overview of a game system according to an embodiment.

Referring to FIG. 1, the game system 100 provides a game service to a plurality of user terminals 130 through the game server 110. The game system 100 includes a game server 110, a network 120, and a plurality of user terminals 130, and the game server 110 and a plurality of user terminals 130 are connected to a network 120 (for example, , Internet communication network, wired/wireless local area network or wide area data communication network, etc.).

The server 110 may perform an authentication procedure for the user terminal 130 requesting access to execute the game program, and provide a game service to the user terminal 130 that has been authenticated.

The user who wants to play the game executes a game application (or game program) installed in the user terminal 130 and requests access to the server 110. The user terminal 130 is a computing device that enables a user to access a game through an online connection, for example, a cellular phone, smart phone, personal computer, laptop, notebook, netbook, tablet or personal digital assistant; PDA).

The game server 110 may include a game indicator information prediction device, and may collect information for predicting a game indicator from the user terminal 130 through the network 120. The information for predicting the game indicator may include, for example, connection information, payment information, product information, event information, inspection information, etc. related to the game (target game) to predict the game indicator of each user. In one embodiment, the game server 110 may collect log data of a plurality of games from the user terminal 130 and classify log data for a plurality of games by game genre. The game server 110 may generate statistical data corresponding to each game genre based on log data classified for each game genre as a result of the classification.

The game server 110 may generate learning data for training a predictive model of a game genre corresponding to statistical data based on statistical data corresponding to each game genre. Further, the game server 110 may train a prediction model of a game genre corresponding to the learning data based on the learning data. Here, the predictive model may include a predictive model for predicting the number of gameplay users of the target game to predict game indicator information and a predictive model for measuring daily sales of the target game.

In one embodiment, the shape of the prediction model may be at least one of a linear regression model, a neural network (NN), and a long short-term memory (LSTM) long-term memory system. For example, if the game server utilizes the neural network as a method for training the predictive model, the game server inputs X (natural numbers, for example, 7 days, 30 days, etc.) of training data to input a linear regression neural network model. Through this, you can train a predictive model. In addition, when predicting marketing effects and event effects that may affect game index information of a target game for a certain period of time, the game server may utilize a long-term and short-term memory-type circular neural network as a method of learning a prediction model. In this case, a long-term memory-type cyclic neural network may utilize a linear regression model based on a time series prediction model. Here, the time series means a series of observed values continuously observed over time, and the time series prediction is a prediction method that predicts what will happen in the future by creating a mathematical model based on a given time series.

The game server 110 may predict game index information of the target game using the learned prediction model. The game index information of the target game that can be predicted using the prediction model may include the number of gameplay users and the daily sales of the target game. In one embodiment, the learned prediction model may predict game index information of the target game by inputting basic general-purpose statistical data and game state statistical data.

The present invention as described above has an effect that can solve the problem of cold start, which is difficult to predict game index information related to the target game because the game index information corresponding to the target game is insufficient when the target game is launched. Based on the predicted game indicator information through the game indicator information prediction method, it is possible to predict future game indicator information of the target game even at the beginning of the target game launch. The predicted game index information may support rapid decision making for target game operation. The game server 110 may generate statistical models by classifying statistical data of a plurality of games for each game genre, thereby generating more various prediction models.

In addition, when the developer of the target game takes an action related to the operation of the game, such as an update and an event of the target game, the game server 110 includes the number of game play users of the game according to the action, the daily sales of the game, and business information. , BI) It is possible to predict game indicator information including indicators. Through this, the developer of the target game can predict the expected effect through the action related to the operation of the target game in advance. In addition, the developer of the target game can prepare for the operation of the game according to the predicted effect, and by providing the predicted information, it can also help to select the key performance indicator (KPI) of the game division or developer. Can be.

Hereinafter, a method for predicting game index information will be described in more detail with reference to the drawings.

2 is a flowchart illustrating an operation of a method for predicting game indicator information according to an embodiment. The game index information prediction method may be performed by the game index information prediction device described herein.

Referring to FIG. 2, in step 210, the game index information prediction apparatus may generate statistical data based on log data of a plurality of games. Here, the log data may be game access information, payment information, product information, event information, and inspection information. The apparatus for predicting game index information may collect log data of a plurality of games from a user terminal and classify log data of the plurality of games by game genre. The apparatus for predicting game index information may generate statistical data corresponding to each game genre based on log data classified for each game genre.

In step 220, the apparatus for predicting game index information may generate learning data for training a prediction model of a game genre corresponding to statistical data based on statistical data corresponding to each game genre.

In step 230, the game index information prediction apparatus may train a prediction model of a game genre corresponding to the training data based on the training data. Here, the predictive model may include a predictive model for predicting the number of gameplay users of the target game to predict game indicator information and a predictive model for measuring daily sales of the target game.

In one embodiment, the prediction model may be trained based on at least one of a linear regression model, a neural network (NN), and a long short-term memory (LSTM) long-term memory system. . For example, when the game indicator information prediction device utilizes the neural network as a method for training the prediction model, the game indicator information prediction device inputs X (natural numbers, for example, 7 days, 30 days, etc.) of training data. Therefore, the prediction model can be trained through a linear regression neural network model. In addition, when predicting a marketing effect and an event effect that may affect game indicator information of a target game for a certain period of time, the game indicator information prediction apparatus may utilize a long-term and short-term memory-type cyclic neural network as a method of training the prediction model. In this case, a long-term memory-type cyclic neural network may utilize a linear regression model based on a time series prediction model. Here, the time series means a series of observed values continuously observed over time, and the time series prediction is a prediction method that predicts what will happen in the future by creating a mathematical model based on a given time series.

In step 240, the game index information prediction apparatus may predict game index information of the target game using the learned prediction model. The game index information of the target game that can be predicted using the prediction model may include the number of gameplay users and the daily sales of the target game. In one embodiment, the learned prediction model may predict game index information of the target game by inputting basic general-purpose statistical data and game state statistical data.

The basic general-purpose statistical data includes, for example, the conversion rate of the payment on the aggregated date, the average sales per subscriber on the aggregated date, the average revenue per payer on the aggregated date, and the past X (natural number) days, including the aggregated date, related to the game corresponding to the prediction model Includes average daily play users, average daily sales over the past X days including aggregated days, average daily payment conversion rates over the past X days including aggregated days, and standard deviation of average daily player counts over the past X days including aggregated days. can do. In addition, the game status statistical data includes, for example, game code, game play time average, game play time standard deviation, user level average, user level standard deviation, N (N is a natural number), primary game revisit rate, and aggregated payment product. It may include the presence or absence of an update, the number of updates to the payment product on the aggregation date, whether to check the aggregation date, and the inspection time on the aggregation date.

The game index information prediction apparatus may predict game index information including the number of game play users and daily sales of the target game after N (N is a natural number of 2 or more) days by using a prediction model corresponding to the game genre of the target game. The game index information prediction apparatus may calculate a similarity between the game genre of the target game and a plurality of different game genres, and select a prediction model corresponding to the game genre of the target game based on the calculated similarity or the user's selection. The similarity between the game genre of the target game and a plurality of different game genres may be calculated based on the game genre of the target game and the plurality of different games, the number of users who played the previous game, the previous sales information, and the previous game index.

3 is a diagram for explaining an example of a process of learning a prediction model of game indicator information according to an embodiment.

Referring to FIG. 3, in step 320, log data 310 of a plurality of games may be classified by game genre or by game. Here, the log data may be game access information, payment information, product information, event information, and inspection information. In step 330, the game index information prediction apparatus may generate statistical data corresponding to each game genre or game based on log data classified for each game genre or for each game. In step 340, the game index information predicting apparatus may generate learning data for training the predictive model of the game genre or game corresponding to the statistical data based on the statistical data corresponding to each game genre or game.

In step 350, the game index information prediction apparatus may generate a prediction model based on the learning data generated in step 340. In one embodiment, the game indicator information prediction device generates a first prediction model for predicting the number of game play users of the target game to predict game indicator information and a second prediction model for measuring daily sales of the target game. Can be. The first prediction model and the second prediction model each have at least one form of a linear regression model, a neural network (NN), and a long short-term memory (LSTM) long-term memory system. , It can be learned based on the learning data.

4 is a flowchart illustrating an example of a process of predicting game index information of a game after N (N is a natural number) is a game index information prediction model of a game according to an embodiment. The prediction process of the game indicator information performed in this embodiment may be performed by the game indicator information prediction apparatus.

Referring to FIG. 4, in step 410, the apparatus for predicting game index information may receive an input value D in the form of a natural number indicating a period to be predicted. In addition, there may be a variable N to be used in the process of repeatedly predicting game index information of the target game for the received prediction period. The variable N is a natural number with an initial value of 1, meaning primary. After the game index information prediction value of the target game is stored, an iterative process in which a natural number 1 is added to the variable N may be performed, and when the value of the variable N is equal to the input value D, this process may be stopped.

In step 420, a predictive model for predicting the number of gameplay users and daily sales of the target game may exist, and in step 430, a predicted value for the number of gameplay users corresponding to day N and the daily sales is calculated. Can be saved. In operation 440, the apparatus for predicting game index information may check whether the values of the input value D and the variable N are the same. If the value of the input value D and the variable N are not the same, the value of the variable N is updated to N+1 through step 460 to determine the number of N primary gameplay users corresponding to the updated variable N and the predicted value for daily sales. The seeking process can be repeated. In this process, in order to obtain a predicted value for the number of N+1 day gameplay users and daily sales, the predicted value for the Nth day may be used as an input value of the prediction model again. The prediction model in which the prediction value for the N day is input may provide a prediction value for the N+1 day. If the values of the input value D and the variable N are not the same, in step 450, the game indicator information prediction device may be provided with prediction information for the number of gameplay users and daily sales for the target game in the D day period. .

5 is a diagram for explaining an example of a process of predicting game index information of a target game through an integrated prediction model for each game genre according to an embodiment.

In one embodiment, the apparatus for predicting game index information may generate training data 520 for training the predictive model using the statistical data 510 for games A and B classified by game genre as input values. The game classified by game genre may generate statistical data 510 based on game index information and game log data, including the number of play users or daily sales of each past game corresponding to game A and game B. Also, DAU (Daily Active User) may mean the number of gameplay users of the game. The game index information and game log data of the A game and the B game may have a label that is a standard that is classified according to each game.

The game index information prediction apparatus may train the prediction model 530 using the training data 520 generated based on the statistical data 510. The learned prediction model 530 uses the game index information 550 of the target game, including the number of users who play the game early in the target game and daily sales as input values of the prediction model 530, and the game index information corresponding to the target game ( 540) can be calculated. The predicted value of game index information after N (N is a natural number) may be calculated by repeating the process of calculating the game index information 540 by the prediction model 530 N times.

6 is a diagram for explaining an example of a process of predicting game index information of a target game through a prediction model for each game according to an embodiment.

In one embodiment, the apparatus for predicting game index information may generate training data 630 for training a prediction model corresponding to each game by using statistical data 610 classified for each game as an input value for each game. Statistical data 610 for each game may be generated based on game index information and game log data, including the number of gameplay users or daily sales of past games corresponding to each game. In addition, DAU may mean the number of gameplay users of the game. The apparatus for predicting game index information may train the prediction model 640 using the training data 630 generated based on the statistical data 610. The learned prediction model 640 uses the game indicator information 620 of the target game including the number of game players and the initial game play number of the target game as input values of the prediction model 640, and the game indicator information corresponding to the target game ( 650).

According to an embodiment, prediction models corresponding to different games or different game genres may exist. For example, the prediction model 640 may include a prediction model corresponding to the C game, a prediction model corresponding to the D game, and a prediction model corresponding to the E game. Here, each prediction model may be learned based on statistical data of a corresponding game. The game indicator information prediction device determines the similarity between the target game and each game (C game, D game, E game) based on the recorded game indicator information such as game genre, DAU, sales change, and other game indicator values of the target game. Can be calculated. The game index information prediction apparatus may calculate the similarity based on the comparison result between the recorded game index information of the target game and the recorded game index information of each game (C game, D game, E game). The game index information prediction apparatus selects a prediction model suitable as a prediction model of the target game from among prediction models corresponding to C games, prediction models corresponding to D games, and prediction models corresponding to E games based on the calculated similarity. , The game index information of the target game may be predicted using the selected prediction model. In one example, the game index information prediction apparatus selects a prediction model having the highest similarity (eg, a prediction model corresponding to E game), and applies the game index information 620 of the target game to the selected prediction model to determine the target game The predicted value of game index information can be obtained.

7 is a diagram illustrating a configuration of an apparatus for predicting game index information according to an embodiment.

Referring to FIG. 7, the game index information prediction apparatus 700 may include a communication interface 710, a processor 720, and a memory 730. According to an embodiment, the game index information prediction apparatus 700 may further include a database 740.

The memory 730 may be connected to the processor 720 and store instructions executable by the processor 720, data to be processed by the processor 720, or data processed by the processor 720. Memory 730 may be, for example, a non-transitory computer-readable medium, such as high-speed random access memory and/or non-volatile computer-readable storage medium (eg, one or more disk storage devices, flash memory devices, or other non-volatile solid state) Memory device).

The communication interface 710 provides an interface for communicating with an external device (eg, a user's terminal and/or game server). The communication interface 710 may communicate with an external device through a wired or wireless network.

The database 740 may store data necessary for the game index information prediction apparatus 700 to operate. For example, the database 740 may store log data of a plurality of games, log data classified by game genre, statistical data such as basic general-purpose statistical data and game state statistical data, learning data, and predicted game index information. .

The processor 720 executes functions and instructions for executing in the game indicator information prediction apparatus 700, and controls the overall operation of the game indicator information prediction apparatus 700. The processor 720 may perform one or more operations related to the operation of the game index information prediction apparatus 700 described in FIGS. 1 to 6.

For example, the processor 720 may collect log data for a plurality of games from the user terminal through the communication interface 710 and generate statistical data based on the collected log data. The processor 720 may classify a plurality of games for each game genre, and generate statistical data corresponding to each game genre based on the classification result.

The processor 720 may generate training data for training the prediction model based on the generated statistical data, and train the prediction model using the generated training data. In one embodiment, the processor 720 may train a prediction model of a game genre corresponding to the statistical data based on the statistical data. The processor 720 classifies log data for a plurality of games by game genre, generates statistical data corresponding to each game genre based on the classification result, and then predicts game index information based on the statistical data. Can be learned.

The processor 720 may predict game index information of the target game using the learned prediction model. In one embodiment, the processor 720 may predict game index information of the target game using a prediction model corresponding to the game genre of the target game. For example, the processor 720 calculates the similarity between the game genre of the target game and a plurality of different game genres, and selects a predictive model corresponding to the game genre of the target game based on the calculated similarity or the user's selection. Can be. The processor 720 may predict game index information of the target game using the selected prediction model.

In another embodiment, the processor 720 may predict the number of game play users of the target game after N (two or more natural numbers) days and the daily sales of the target game through the prediction model. The processor 720 repeatedly predicts game index information after several days by repeatedly applying the input data configured based on the output data of the prediction model to the prediction model to obtain output data.

The device described above may be implemented with hardware components, software components, and/or combinations of hardware components and software components. For example, the devices and components described in the embodiments include, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors (micro signal processors), microcomputers, field programmable gate arrays (FPGAs). , A programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose computers or special purpose computers. The processing device may run an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and/or data may be interpreted by a processing device, or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodied in the transmitted signal wave. The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, or the like alone or in combination. The program instructions recorded in the medium may be specially designed and configured for the embodiments or may be known and usable by those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, and magnetic media such as floptical disks. -Hardware devices specifically configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described by a limited embodiment and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques are performed in a different order than the described method, and/or the components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or other components Alternatively, even if replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (1)

In the game indicator information prediction method,
Generating statistical data based on log data of a plurality of games;
Generating training data for training a predictive model based on the statistical data;
Training the prediction model using the training data; And
Predicting game index information of the target game using the learned prediction model
Containing,
How to predict game indicator information.

Images