KR102095010B1 - Method for managing player of game - Google Patents

Abstract

Disclosed is a game player management method according to an embodiment of the present disclosure. The operations stored in the computer program for processing of the method include collecting first game data for the player; Determining the first game interest of the player by calculating the first game data using a game interest determination model including one or more network functions; And determining an event for increasing interest in the player's game to be provided to the player based on the player's first game interest.

Description

How to manage game players {METHOD FOR MANAGING PLAYER OF GAME}

The present invention relates to a game operating method using a computing device, and more particularly, to a solution for preventing a player from leaving the game.

As the online game market becomes active, the number of users accessing the game has rapidly increased. Accordingly, research is being conducted on a method for enhancing the interest of users in online games.

In online games, in general, users are provided with a difficulty adjustment with a certain difficulty graph or a certain game event. There have been technical challenges on how to adjust the difficulty level or provide game events.

Republic of Korea Patent No. 10-1372207 discloses a real-time control device of the game difficulty.

The present disclosure has been devised in response to the background art described above, and aims to provide a game operating method.

Disclosed is a computer program stored in a computer-readable storage medium in accordance with one embodiment of the present disclosure for realizing the above-described problems. The computer program, when executed on one or more processors of the computing device, performs the following operations for game player management, the operations comprising: collecting first game data for the player; Determining the first game interest of the player by calculating the first game data using a game interest determination model including one or more network functions; And determining an event for increasing the interest in the player's game to be provided to the player based on the player's first game interest.

In an alternative embodiment of computer program operations to perform the following operations for game player management, the first game data includes data related to the player's game play, and is determined from among data related to the player's game play. It may include data collected during a time period.

In an alternative embodiment of computer program operations to perform the following operations for game player management, determining an event to be provided to the player based on the player's first game interest comprises: the player's first game And if the interest level is below a predetermined threshold, determining to provide the event to the player.

In an alternative embodiment of computer program operations to perform the following operations for game player management, the event has an intensity of the event, and the intensity of the event is determined based on the player's first game interest, and the The intensity of the event may increase as the player's interest in the first game is lower.

In an alternative embodiment of computer program operations to cause the following operations for game player management, collecting second game data for the player; Determining the second game interest of the player by calculating the second game data using the game interest determination model; Determining whether a change amount is equal to or greater than a threshold value by comparing the player's first game interest with the player's second game interest; When the amount of change is greater than or equal to a threshold value, comparing the first game data with the second game data to determine game data comparison results; And determining the type of the event to be provided to the player by calculating the game data comparison result using an event determination model including one or more network functions.

In an alternative embodiment of computer program operations to cause the following operations for game player management, collecting third game data for the player that is collected after the event is provided to the player; Determining the third game interest of the player by calculating the third game data using the game interest determination model; Determining a change in game interest according to an event by comparing at least one of the player's first game interest and the player's second game interest and the player's third game interest; And updating the event determination model based on a change in game interest according to the event.

In an alternative embodiment of computer program operations to cause the following operations for game player management, collecting a learning data set consisting of game data for the entire player; Generating a subset of learning data by grouping game data of the learning data set by players based on player information included in the learning data set; Grouping game data of the subset of training data into predetermined criteria and labeling game interest to generate training data; The method may further include generating the game interest determination model to train the game interest determination model using the learning data and output the game interest based on the game data grouped by the predetermined criteria.

In an alternative embodiment of computer program operations to perform the following operations for game player management, the predetermined criterion may include a predetermined unit of time.

Disclosed is a method for preventing a player from leaving according to another embodiment of the present disclosure. The method includes collecting first game data for a player; Determining the first game interest of the player by calculating the first game data using a game interest determination model including one or more network functions; And determining an event for increasing interest in the player's game to be provided to the player based on the player's first game interest.

A computing device is disclosed in accordance with another embodiment of the present disclosure. The computing device includes a processor including one or more cores; And a memory, wherein the processor collects the first game data for the player and calculates the first game data by using the game interest determination model including one or more network functions to determine the player's first game interest And determining an event for increasing interest in the player's game to be provided to the player based on the player's first game interest.

The present disclosure can provide a game operating method.

1 is a block diagram of a computing device performing an operation for game player management according to an embodiment of the present disclosure.
2 is a configuration diagram of a neural network according to an embodiment of the present disclosure.
3 is an exemplary diagram of learning data according to an embodiment of the present disclosure.
4 is a flowchart of a game player management method according to an embodiment of the present disclosure.
5 is a block diagram illustrating logic for implementing a game player management method according to an embodiment of the present disclosure.
6 is a block diagram illustrating a module for implementing a game player management method according to an embodiment of the present disclosure.
7 is a block diagram illustrating a circuit for implementing a game player management method according to an embodiment of the present disclosure.
8 is a block diagram illustrating a means for implementing a game player management method according to an embodiment of the present disclosure.
9 is a block diagram of a computing device according to an embodiment of the present disclosure.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is apparent that these embodiments can be practiced without these specific details.

As used herein, the terms "component", "module", "system", and the like refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or execution of software. For example, a component can be, but is not limited to, a process executed on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both the application and the computing device running on the computing device can be components. One or more components can reside within a processor and / or thread of execution. One component can be localized in one computer. One component can be distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored therein. Components are, for example, signals having one or more data packets (e.g., data and / or signals from one component interacting with another component in a local system, distributed system, etc.) through other systems and networks such as the Internet. (Transmitted data) may be communicated through local and / or remote processes.

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless specified otherwise or unclear in context, "X uses A or B" is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or, if X uses both A and B, "X uses A or B" can be applied in either of these cases. It should also be understood that the term “and / or” as used herein refers to and includes all possible combinations of one or more of the listed related items.

In addition, the terms “comprises” and / or “comprising” should be understood as meaning that the corresponding feature and / or component is present. It should be understood, however, that the terms “comprises” and / or “comprising” do not exclude the presence or addition of one or more other features, elements, and / or groups thereof. In addition, unless otherwise specified or contextually unclear as indicating a singular form, the singular in the specification and claims should generally be construed to mean "one or more."

Those skilled in the art additionally describe various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein in electronic hardware, computer software, or a combination of both. It should be recognized that it can be implemented as To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or as software depends on the specific application and design limitations imposed on the overall system. Skilled technicians can implement the functionality described in various ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Descriptions of the presented embodiments are provided so that those skilled in the art of the present disclosure may use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art of the present disclosure. The general principles defined herein can be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present invention is not limited to the embodiments presented herein. The invention should be interpreted in its broadest scope consistent with the principles and novel features presented herein.

In one embodiment of the present disclosure, the server may include other configurations for performing the server environment of the server. The server can include any type of device. The server is a digital device, and may be a digital device equipped with a processor and having computing power, such as a laptop computer, a notebook computer, a desktop computer, a web pad, and a mobile phone. The server may be a web server that processes services. The above-mentioned types of servers are only examples, and the present disclosure is not limited thereto.

In this specification, network functions may be used interchangeably with artificial neural networks and neural networks. In this specification, the network function may include one or more neural networks, and in this case, the output of the network function may be an ensemble of the output of the one or more neural networks.

In the present specification, the model may include a network function. The model may include one or more network functions, in which case the output of the model may be an ensemble of the output of one or more network functions.

1 is a block diagram of a computing device performing an operation for game player management according to an embodiment of the present disclosure.

The configuration of the computing device 100 illustrated in FIG. 1 is merely an example for simplicity. In one embodiment of the present disclosure, the computing device 100 may include other configurations for performing the computing environment of the computing device 100.

The computing device 100 may include a network unit 110, a processor 120, and a memory 130. The computing device of the present disclosure may include a game server of a game service company.

The network unit 110 may transmit / receive data, etc. for performing a game player management method according to an embodiment of the present disclosure to other computing devices, servers, and the like. The network unit 110 may transmit / receive data necessary for an embodiment of the present disclosure, such as game data, to other computing devices, servers, and the like. For example, the network unit 110 may receive game data from a game database or the like. In addition, the network unit 110 may enable communication between a plurality of computing devices so that learning of a model is distributed in each of the plurality of computing devices. The network unit 110 may enable communication between a plurality of computing devices so that operations related to game interest determination or event determination using a model can be distributed.

The processor 120 may be composed of one or more cores, a central processing unit (CPU) of a computing device, a general purpose graphics processing unit (GPGPU), and tensor processing (TPU) unit), and a processor for data analysis and deep learning. The processor 120 may read a computer program stored in the memory 130 and perform a game player management method according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 120 may perform calculation for learning a neural network. The processor 120 may perform processing of input data for learning in deep learning (DN), feature extraction from input data, error calculation, and weight update of a neural network using backpropagation. You can perform calculations for learning.

At least one of the CPU, GPGPU, and TPU of the processor 120 may process training of the model. For example, the CPU and the GPGPU may process the model learning, game interest calculation using the model, or event determination calculation according to the game interest. In addition, in one embodiment of the present disclosure, a processor of a plurality of computing devices may be used together to process a model learning, game interest calculation using a game interest determination model, and event determination calculation according to game interest using an event determination model. . Further, the computer program executed in the computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

In one embodiment of the present disclosure, the computing device 100 may distribute and process the model using at least one of a CPU, GPGPU, and TPU. Also, in one embodiment of the present disclosure, the computing device 100 may distribute and process a model together with other computing devices.

Hereinafter, a method for personalized difficulty control according to an embodiment of the present disclosure will be described.

A method of calculating game interest using a game interest determination model according to an embodiment of the present disclosure will be described.

The processor 120 may receive a game data set including one or more game data through the network unit 110. The game data set may be a concept corresponding to the learning data set. The game data set may include, for example, all game data collected in the game. That is, the game data set may mean game data of all players. The game data subset may be configured by grouping game data on an arbitrary basis. For example, game data can be grouped by player to form a subset of game data. In addition, in another example, if a game has a large patch that causes many changes, the game data may be grouped to form a subset of the game data before and after the large patch. The game data set may be a data set that groups game data for each player. The game data may include all data related to the player's game play. Game data may be data including all transactions in the game. The game data may include in-game data indicating how active the player is, and interaction data indicating how active the player is. The game data may include a plurality of items. In-game data may include achievements specific to the characters and players in the game. That is, the in-game data may include all information that the player performs only with his character in the game. Interaction data may include in-game characters and non-player achievements. That is, the interaction data may include all information about the interaction that the player performs with other players in the game. For example, in-game data includes the level of the stage that was cleared, the time it took to clear the stage, the number of times the quest was performed, the time it took to complete one quest, the type of item used to clear the stage, and the stage. It may include items such as the value of paid goods used to clear, the number of trials and errors experienced to level up, the number of attempts to strengthen, and the number of successes to strengthen. In addition, for example, the interaction data includes the number of chats with the guild member, the number of meetings with the guild member, the number of invites to the same game room, the number of players who cooperated to make a raid, the number of gifts exchanged with other players, and other players. It may include items such as the number of chats with the field, the number of times the character was killed by another player, the number of times the character was killed by another character, and the like. The items of in-game data and interaction data described above are only examples, and the present disclosure is not limited thereto. The game data may include data collected during a predetermined time period among data related to game play. For example, the game data may include data related to the game player collected for 24 hours, which is a predetermined time period. For example, the game data may include data related to game play of Player A on June 1, 2018. In one embodiment of the present invention, game data may include a plurality of items, and the value of each item may include the number of times performed during a predetermined time period. For example, when a user kills another player 5 times in 24 hours, the value of the player kill (PK) item of game data for the player may be 5. The above description of the game data is merely an example, and the present disclosure is not limited thereto.

The processor 120 may input game data into the game interest determination model and calculate the game interest using the game interest determination model. The game interest level may include information related to the player's interest level in the game. For example, a numerical value indicating interest in a game may be represented. Game interest may be determined based on the length of the time period from the point of view of the player's game data to the game exit. For example, if player A's game data of June 1, 2018 is input to the game interest determination model, game interest that player A may possibly leave the game after 3 months may be output. In addition, for example, if player A's game data of April 1, 2018 is input into the game interest judgment model, game interest that player A may possibly leave the game after 5 months may be output. Based on the game data of Player A's June 1, 2018, the output game interest may be higher. Further, in another example, game interest may indicate a probability of leaving the game after a predetermined time from the viewpoint of the player's game data. For example, if the game data of April 1, 2018 of Player A is calculated through the game interest determination model, a 50% probability that the player will leave the game after 3 months can be obtained. The probability that a person leaves the game after 3 months may be of interest to the game. The game interest determination model of the present disclosure may be a model that outputs a probability that a player will continue to play a game for a predetermined time or more by learning based on game data of a player who has left the game and a point of time when the player has left the game. Referring to FIG. 3, the game interest determination model may be a model learned by a method of generating a game interest determination model for calculating game interest according to an embodiment of the present disclosure. The above description of game interest is only an example, and the present disclosure is not limited thereto.

The processor 120 may determine to provide an event to the player based on the game interest, which is the output of the game interest determination model. The processor 120 may determine to provide an event to the player based on a comparison result of the game interest level and a predetermined threshold value, which are outputs of the game interest level determination model. The event may be an operation for changing a game data item having high correlation with game interest. The event may be a reward that can be provided on the game to lower the probability that the player will leave the game. When the interest in the game decreases due to one or more items of game data, an action corresponding to the corresponding game data may be provided as an event in order to increase the interest in the game. For example, the event may include a reinforced coupon, item offer, paid goods discount purchase notification, guild sign-up message, difficulty increase, difficulty decrease, boss mob level adjustment, raid condition change, item acquisition probability increase, and the like. For example, when an existing user returns after having no play record for a certain period of time, the processor 120 may determine that the game interest is low using the game interest determination model, and the event for the event temporarily lowers the difficulty level. It may be. For example, when the player's duel rate is low, the computing device 100 may determine that the player's game interest is low using the game interest determination model of an embodiment of the present disclosure, and in this case, analyze game data. If the player's win rate is less than 70% through, the event may be to match a virtual player similar to the player or having a lower skill than the player against the opponent. For example, in the case of a player with a small number of paid goods purchases, the processor 120 may determine that the game interest is low using a game interest determination model, and an event for the corresponding player generates a discount offer notification of a package paid item Can be The disclosure of the aforementioned event is merely an example, and the present disclosure is not limited thereto. For example, the predetermined threshold may be a game interest level indicating that the player is likely to drop out after 5 months, and a game interest level indicating that the player is likely to drop out after 3 months is to have a value lower than the threshold value when output is Therefore, it is possible to decide to provide an event, and if the game interest indicating that the player is likely to leave after 1 year is an output, it is possible to decide not to provide the event because it has a value greater than a threshold. For example, the game interest (eg, game data of player A, game data of March 1, 2018) for a predetermined time period of player A as an input of the game interest determination model (for example, game interest) , Player A is less than a predetermined threshold (e.g., a value indicating that the player is likely to leave after 4 months) if the Player A has a probability of churning after 2 months as of March 1, 2018. , You can decide to provide an event to Player A. The disclosure of the operation of deciding to provide the aforementioned event is merely an example, and the present disclosure is not limited thereto.

The processor 120 may determine the intensity of the event based on the game interest, which is the output of the game interest determination model. Events can have event strength. The intensity of the event may be a degree of providing an operation for changing a game data item that is highly related to game interest. Increasing the intensity of the event may be to increase the number of times of providing an operation for changing a game data item that is highly related to game interest, or to increase a level of an operation for changing a game data item that is highly related to game interest. The processor 120 determines to provide an event when the game interest, which is the output of the game interest determination model, is less than or equal to a predetermined threshold, and if the game interest has a value close to the threshold, the strength of the event is relatively weakened, and the game When the degree of interest has a value distant from the threshold, the intensity of the event can be made relatively strong. For example, if the predetermined threshold is game interest indicating that there is a possibility of dropping after 6 months, game interest indicating the value of dropping after 2 months is dropped after 4 months to the target player A of the outputted game data. An event of a higher intensity than the target player B of the game data output with the game interest indicating the value that there is a possibility may be provided. For example, in the dice game, two dice double items are provided to the target player A of the game data in which game interest indicating the possibility of departure after 2 months is output, and game interest indicating the value of possible departure after 4 months One dice double item may be provided to the target player B of the outputted game data. The description of the event intensity described above is merely an example, and the present disclosure is not limited thereto.

The processor 120 receives the first game data and the second game data for the player through the network unit 110, and uses the plurality of game data as the input of the game interest determination model to increase the game interest for the plurality of game data. Can output The processor 120 may output the first game interest based on the first game data and output the second game interest based on the second game data using the game interest determination model. The first game data and the second game data may include data collected during predetermined time periods of different time zones for the same player. For example, the game data of January 14 of Player A may be the first game data, and the game data of January 15 of Player A may be the second game data. The above description of the game data is merely an example, and the present disclosure is not limited thereto.

The processor 120 may compare the first game interest level with the second game interest level to determine whether a change amount of game interest level is greater than or equal to a threshold. For example, the threshold value of the amount of change for game interest is a probability of departure corresponding to one month, the value indicating that the first game interest is likely to deviate after one month, and the second game interest is likely to deviate after three months In the case of a value indicating, the change amount of the first game interest level and the second game interest level is likely to deviate corresponding to two months, so it can be determined that the change amount is greater than or equal to a threshold value. The description of comparison of the above-described amount of change is only an example, and the present disclosure is not limited thereto.

When the amount of change between the first game interest level and the second game interest level is greater than or equal to a threshold, the processor 120 may compare the first game data and the second game data to determine a comparison result. The game data comparison result may be generated by the processor 120 comparing the values of items included in the first game data and the second game data, respectively. The game data comparison result may include at least one of data related to a change amount of each item included in the first game data and the second game data and data related to items having a change amount greater than or equal to a threshold. For example, the processor 120 may compare game data items of in-game data and game data items of interaction data included in the first game data and the second game data. For example, the processor 120 may compare all data items, such as the cost of purchasing paid goods included in the first game data and the second game data, the number of chats with other players, and the number of items used to clear the stage. For example, when the cost of purchasing a paid good for the first game data is 10,000 won, the number of successful reinforcements is 3 times, and the cost of purchasing a good good for the second game data is 2,000 won, and the number of successful reinforcements is 0 times, The amount of change in the data item for the purchase cost of the paid goods included in the game data comparison result can be generated with a reduction of 80%, and the amount of change in the data item with respect to the number of successful reinforcements can be generated with a decrease of 100%. For example, the processor 120 may generate a comparison result of game data for an item having a change amount greater than or equal to a threshold value, and a comparison result of game data for an item that does not have a change amount greater than or equal to a threshold value. For example, if the threshold for the purchase cost of a paid good is 10,000 won and the threshold for the number of successful reinforcements is two times, the processor 120 pays because the change in the purchase cost of the paid good is less than the threshold of 8,000 won. The comparison result of the game data item against the purchase cost of the goods can be generated as 0, and since the change in the number of reinforcement successes is greater than the threshold value of 3 times, the comparison result of the game data item against the reinforcement success number is generated as 1. Can. That is, the comparison result may include a rate of change of each item included in the game data, a type of item that has changed more than a certain threshold, and the like. The disclosure of the above-described game data comparison result is only an example, and the present disclosure is not limited thereto.

The processor 120 may determine a cause of increasing a player's game departure probability based on a comparison result of game data, and determine to provide an event related to a cause of the player's game departure probability increase. The processor 120 may calculate a comparison result of the first game data and the second game data using an event determination model, and determine the type of event to be provided to the player. The processor 120 may output a score to each of the one or more candidate events by using the comparison result of the first game data and the second game data as an input in the event determination model. The event determination model of the processor 120 may determine an event based on a score for each candidate event. Specifically, the processor 120 relates to the result of comparing game data, which is a value generated by comparing the values of game data items included in the first game data and the second game data, that is, the amount of change of each item included in the game data. A value for at least one of data and data related to items having a change in a threshold or more may be input to the event determination model. The event determination model of the processor 120 compares each game data item and outputs a score to several candidate events corresponding to the generated value, and provides the player with an event whose score is the highest among the candidate events You can decide. For example, by comparing the values of the game data items of the first game data and the second game data, respectively, the number of times of using items with a variation over the threshold is 1, the number of enhancements is 1, and the number of purchases of paid goods without a variation over the threshold. Is 0, game data comparison result may be output. The result of the comparison is the input of the event determination model of the processor 120, and the output result is a score of 10 for a candidate event corresponding to the provision of a reinforced coupon, a score of 3 of a candidate event corresponding to the provision of a paid goods discount, and free items When the score of the candidate event corresponding to is 8, it may be determined to select the 10 with the highest score and provide the player with a reinforcement coupon that is the corresponding event. The above-mentioned scoring values are only examples, and the present disclosure is not limited thereto. The event decision model may relate to a policy that determines an action in reinforcement learning. That is, the processor 120 processes the observation result (that is, the environment), which is a result of comparing game data, with an event decision model (ie, policy) to determine the type of event (ie, action). have. The above-described event determination model may have a plurality of event candidates according to the result of comparing game data, and it may be selected by providing the player with the most appropriate event candidate among the plurality of event candidates using the calculation of the event determination model. The description of determining the above-described event type is only an example, and the present disclosure is not limited thereto. Descriptions of the details of the strong learning method are specifically discussed in US patent applications US15 / 091840 (2016.04.06) and US15 / 261579 (2016.09.09), which are incorporated herein by reference in their entirety.

The processor 120 may determine the intensity of an event to be provided to the player by comparing the first game interest level with the second game interest level. For example, the intensity of the event may be increased when the change amount of the first game interest level and the second game interest level is large, and the intensity of the event may be lowered when the change amount of the first game interest level and the second game interest level is small. For example, the first game interest for player A (e.g., the game interest level indicating the possibility of dropout after 6 months) and the second game interest level (e.g., value indicating the possibility of dropout after 2 months) The amount of change in game interest) is the likelihood of churn for 4 months, the first game interest for player B (for example, the game interest indicating the value that there is a possibility of churn after 6 months) and the second game interest (for example, If the amount of change in the game interest (which indicates the possibility of churning after 4 months) is churning for 2 months, the intensity of the event provided to player A may be higher. As described above, increasing the intensity of the event increases the number of times the operation is provided to change the game data item that is highly related to game interest, or increases the level of the operation for changing the game data item that is highly related to game interest. It can be raising. The description of the event intensity described above is merely an example, and the present disclosure is not limited thereto.

The processor 120 may receive the third game data after providing the event determined by using the calculation of the event determination model to the player through the network unit 110. The processor 120 may determine the third game interest for the third game data through calculation by using the third game data as an input of the event determination model. The processor 120 may determine a change in game interest according to the event by comparing at least one of the first game interest and the second game interest before providing the event to the player and the third game interest after providing the event to the player . For example, the processor 120 may have the second game interest of the second game data of February 5, 2015 of the player A before providing the enhanced coupon offer event to the player (for example, the possibility of game departure after 3 months) Game interest indicating this is present), and third game interest in the third game data of February 6, 2015 of the player A after providing the enhanced coupon offer event to the player (for example, game departure after one year) By comparing the game interest (which indicates the likelihood), it may be determined that the game interest has increased since the event was provided to the player. The description of the amount of change in game interest after providing the above-described event is only an example, and the present disclosure is not limited thereto. That is, it is possible to determine whether or not the provision of the event to the player improves the player's interest (ie, whether the third game interest increases) by determining the amount of change in game interest.

The processor 120 may update the event decision model based on the change amount of game interest. When the third game interest is higher than at least one of the first game interest and the second game interest, the processor 120 may update the event determination model to increase the probability of determining the event. When the third game interest is lower than at least one of the first game interest and the second game interest, the processor 120 may update the event determination model to decrease the probability of determining the event. The processor 120 may update the event determination model by updating the weight of the event determination model. For example, when the interest in the third game is increased when the interest in the second game is compared to the interest in the third game after providing the player with an event that provides paid goods at a discount value, the interest in the player's game is increased. That is, since the possibility of a player dropping out of the game has been reduced, it is determined that the action determined by the corresponding event is appropriate, and the event determination model of the processor 120 may update the event determination model to increase the probability that the corresponding event is selected. . In addition, when the interest in the third game is reduced when the second game interest is compared with the third game interest after providing the enhanced coupon offer event to the player, the interest in the player's game is reduced, that is, the player is allowed to leave the game. Since the likelihood has increased, it is determined that the operation for determining the event is inappropriate, and the event determination model of the processor 120 may update the event determination model so that the probability of selecting the event decreases. That is, the processor 120 may evaluate whether or not the event is appropriate by evaluating the player's game interest before and after providing the event, and update the event decision model to select a more appropriate event. The description of updating the event decision model based on the amount of game interest change described above is only an example, and the present disclosure is not limited thereto.

The memory 130 may store a computer program for performing a personalized difficulty adjustment method according to an embodiment of the present disclosure, and the stored computer program may be read and driven by the processor 120.

The memory 130 according to embodiments of the present disclosure may store a program for the operation of the processor 120 and temporarily or permanently store input / output data (eg, game data, event type, etc.). It might be. The memory 130 may store data related to a display and sound. The memory 130 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory, etc.), RAM (Random Access Memory, RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), magnetic memory, magnetic It may include at least one type of storage medium among disks and optical disks.

2 is a configuration diagram of a neural network according to an embodiment of the present disclosure.

Throughout this specification, neural networks, network functions, and neural networks may be used in the same sense. A neural network may consist of a set of interconnected computational units, which may generally be referred to as "nodes." These “nodes” may also be referred to as “neurons”. The neural network comprises at least one node. The nodes (or neurons) that make up the neural networks can be interconnected by one or more "links"

Within a neural network, one or more nodes connected through a link may form a relationship between input and output nodes. The concept of an input node and an output node is relative, and any node in an output node relationship with respect to one node may be in an input node relationship in relation to another node, and vice versa. As described above, the input node to output node relationship can be generated around the link. One or more output nodes may be connected to one input node through a link, and vice versa.

In the relationship between the input node and the output node connected through one link, the output node may be determined based on data input to the input node. Here, the node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be varied by a user or algorithm to perform a desired function of the neural network. For example, when more than one input node is interconnected by each link to one output node, the output node is set to values input to input nodes connected to the output node and a link corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form input node and output node relationships within the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association relationship between the nodes and the links, and a weight value assigned to each link. For example, when the same number of nodes and links exist and two neural networks having different weight values between the links exist, the two neural networks may be recognized as different from each other.

As shown in Fig. 2, a neural network may be configured by including one or more nodes. Some of the nodes constituting the neural network may configure one layer based on distances from the initial input node. For example, a set of nodes with a distance n from the initial input node may be: You can configure n layers. The distance from the first input node can be defined by the minimum number of links that must go through to reach the node from the first input node. However, the definition of this layer is arbitrary for explanation, and the order of the layers in the neural network may be defined in a different way from the above. For example, the layer of nodes may be defined by the distance from the final output node.

The initial input node may mean one or more nodes to which data is directly input without going through a link in relation to other nodes among nodes in the neural network. Or, in a neural network, in a relationship between nodes based on a link, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may mean one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network. Also, the hidden node may refer to nodes constituting a neural network other than the first input node and the last output node. 2, the output node is omitted. The neural network according to an embodiment of the present disclosure may have more nodes in the input layer than nodes in the hidden layer close to the output layer, and may be a neural network in a form in which the number of nodes decreases as it progresses from the input layer to the hidden layer.

In one embodiment of the present disclosure, the neural network may include a recurrent neural network (RNN) to enable processing of time series data. The neural network may be configured with long short-term memory (LSTN) or continuous-time RNN (CTRNN). In addition, in an embodiment of the present disclosure, the neural network of the present disclosure is a long short-term memory (LSTM) so as to prevent performance degradation due to a long range dependency vanishing gradient that may occur as the length of an event increases. ). The processor 120 may perform calculation for learning a neural network including a weight update of the neural network using a backpropagation through time (BPTT) in the RNN.

The RNN may be an artificial neural network that recognizes a pattern from data in the form of a sequence, such as text, genes, handwriting, voice signals, data sensed by sensors, stock prices, and biometric data. RNN can process images as well as time series. Unlike a normal feed-forward neural network, RNN may have a hidden layer output again as an input of the same hidden layer. RNN is a neural network that has a memory capability by calculating and calculating the current input data and the data input in the past at the same time. Therefore, RNN can be trained to interpret current data according to the meaning of previous data in time series data. LSTM, one of RNNs, is also called a long short term memory network and can learn long-term dependencies. In one embodiment of the present disclosure, the neural network may include any one neural network capable of processing time series data, such as a deep gated RNN, a clockwork circular neural network, as well as LSTM, which is one of the RNNs. Can

The neural network 200 of FIG. 2 may include one or more hidden layers. The hidden node of the hidden layer may use the output of the previous layer and the output of the surrounding hidden node as input. The number of hidden nodes for each hidden layer may be the same or different. The number of nodes of the input layer may be determined based on the number of data fields of the input data, and may be the same as or different from the number of hidden nodes. The input data input to the input layer may be calculated by a hidden node of the hidden layer and may be output by a fully connected layer (FCL), which is an output layer.

3 is an exemplary diagram of learning data according to an embodiment of the present disclosure.

A method of generating a game interest determination model for preventing a player from leaving is described according to an embodiment of the present disclosure.

The subset of training data corresponds to a game data set, and the training data is a concept to correspond to game data.

The computing device 100 may collect a learning data set 300 including game data of all players through the network unit 110. Game data may be data including all transactions in the game. The game data may include all data related to the player's game play. The game data may include in-game data indicating how active the player is, and interaction data indicating how active the player is. In-game data may include achievements specific to the characters and players in the game. Interaction data may include in-game characters and non-player achievements. For example, in-game data includes the level of a cleared stage, the time taken to clear the stage, the number of times the quest was performed, the time taken to complete one quest, the type of item used to break the stage, and the stage. It may include items such as the value of paid goods used to break, and the number of trials and errors that have been experienced to level up. Also, for example, interaction data includes items such as the number of chats with the guild member, the number of meetings with the guild member, the number of invites to the same game room, the number of players who cooperated to make a raid, and the number of gifts exchanged with other players. It may include. The above description of the game data is merely an example, and the present disclosure is not limited thereto.

The processor 120 may generate a subset of training data by grouping the training data sets for each player based on player information included in the training data set 300 including game data of all players. If the training data set 300 is game data for all players for many years, the processor 120 may classify game data for each player by grouping game data for each player to generate a subset of training data. For example, when the game data of all players includes game data from the release of the game to the present, the processor 120 groups game data for each player based on information capable of distinguishing the players included in the data. To create a subset of training data. The training data set may consist of one or more subsets of training data. The subset of training data may be grouped by player, as in the above example, and based on arbitrary criteria such as time units, game version units, and specific events in the game (for example, an item providing event for all players). Can be grouped. For example, if the training data set 300 includes game data for all players including player A and player B, the processor 120 groups game data for player A to group the training data subset 1 ( 310), and the processor 120 may group the game data for the player B to generate the training data subset 2 320. The description of generating the above-described data subset is merely an example, and the present disclosure is not limited thereto.

The processor 120 may generate game data by separating game data from a subset of the training data on a predetermined basis. For example, the processor 120 may generate game data by separating game data of a subset of the training data in a predetermined time unit. The processor 120 separates game data included in a subset of training data generated by grouping game data for each player into predetermined time units, and groups game data for each player into game data for each predetermined time unit to generate training data. can do. That is, in order to observe how much the player enjoys the game, the training data may be composed of game data of individual players, and the game data of individual players constituting the training data may be grouped in a specific unit to determine the game data of individual players. It can be configured to track changes. For example, a player's game data for 24 hours may constitute learning data, and the entire game data of the player (ie, game data until a player starts a game and leaves the game) serves as a training data sub. You can make a set. The total game data of all players may constitute a learning data set.

When the target player of the subset of learning data is a player who has left the current game, the processor 120 separates game data for a period from the time when the corresponding player starts the game to the time when the game has left the game in a predetermined time unit. The value grouped with game data may be included in the learning data. When the target player of the subset of learning data is a player who has not left the current game, the processor 120 groups game data by separating game data from a time when the player starts the game into a predetermined time unit. Values can be included in the training data. For example, if the training data set 300 includes training data subset 1 310 for player A and training data subset 2 320 for player B, the processor 120 may subset the training data. Game data included in 1 310 and training data subset 2 320 may be separated into predetermined time units to generate training data. If Player A started the game in June 2017 and left the game in January 2018, the processor 120 will retrieve the game data for Player A for the period from June 2017 to January 2018. It can be divided into units to generate game data included in the learning data. The game data of each date generated by the processor 120 separating and grouping game data for the player A on a day-by-day basis may be game data included in each one learning data. Game data of October 1, 2017 for player A may be game data included in one learning data 311, and game data of November 16, 2017 is included in another learning data 312 It may be game data. When Player B starts the game in May 2016 and is using the game up to the present point in time, the processor 120 separates game data for Player A for a period from May 2016 to the present by dividing the game into units per day. Data can be generated. The game data of each date generated by the processor 120 separating and grouping game data for the player B on a daily basis may be game data included in each one learning data. The game data of March 28, 2017 for the player B may be game data included in one learning data 321. The description of game data included in the above-described learning data is only an example, and the present disclosure is not limited thereto.

The processor 120 may generate learning data by labeling game interest in game data grouped in a predetermined time unit. In one embodiment of the present disclosure, the processor 120 may train a neural network in a supervised learning method. The processor 120 may generate learning data by labeling each learning data with the date the player has left the game. That is, in the example of FIG. 3, the first learning data 311 of the learning data subset 1 310 includes the game from October 1, 17, when the first learning data 311 is collected, until January 2018. Since you have been playing and exiting, game interest based on 3 months until exiting can be labeled. In a similar manner, the second training data 312 of the training data subset 1 310 has a collection time of the second training data 312 is November 16, 17, and the player then plays the game until January 2018. Since you've been playing and churning, game interest based on 1.5 months until churn can be labeled.

The labeled learning data may consist of an ordered pair of input data and correct answers. Here, the input data may include game data grouped in a predetermined unit of time as described above, and the correct answer (ie, label) may include game interest. The game interest level may represent a numerical value indicating an interest level in the game. Game interest may be determined based on the length of the time interval from the point of view of the game data to the player leaving the game. For example, if the subset of learning data is about the first player who has played and left the game for 6 months (eg, from June 17 to December 17), the game collected in June 17 The first game interest matching data (in this example, the first learning data) may be a value greater than the second game interest matching game data (in this example, the second learning data) collected in November 17th. . In the above example, in the case of June 17, the player has played the game for 6 months thereafter, and in the case of November 17, the player has only played the game for 1 month thereafter and then leaves, so the first player 17 years 6 May's game interest may be higher than November's game interest. Accordingly, in this example, the first game data may be matched with a first game interest determined based on 6 months, and the second study data may be matched with a second game interest determined based on 1 month.

Game interest may be a value indicating how likely it is to escape the game. The higher the degree of interest in the game, the lower the probability of dropping out of the game, and the lower the degree of interest in the game, the higher the probability of dropping out. For example, if the player is still playing the game to the present, the game interest matched with the game data grouped in a predetermined unit of time may be 100, and if the player has not left the game and is not playing the game, the predetermined unit of time Game interest matched with game data at a point in time grouped with may be 30. For example, the input data included in one training data 311 of the training data subset 1 310 may be game data for the day of October 1, 2017 of Player A, and the game interest labeled thereto is It may be 40, indicating that you are likely to leave the game after 3 months. Also, for example, the input data included in the other training data 312 of the training data subset 1 310 may be game data for the day of November 16, 2017 of the player A, and the game interest labeled thereto is It may be 20, indicating the possibility of leaving the game after 2 months. In addition, for example, input data included in one training data 321 of the training data subset 2 320 may be game data for one day of March 28, 2017 of the player B, and the game interest labeled therein May be 0 indicating that there is no possibility of departure. The description of the learning data described above is merely an example, and the present disclosure is not limited thereto.

When generating the learning data, the processor 120 may normalize the item values included in the game data. The processor 120 may normalize the item values in order to reduce the calculation amount of the game interest determination model and to reduce the error due to the unit of item and item difference. For example, the processor 120 may normalize the item values included in the game data using a jet score (Z-score). Also, the processor 120 may set the missing item value as an average value of the entire item. For example, if the paid goods purchase item of the game data for player A is missing and the paid goods purchase item of player A is not known, it may be set as the overall average value for the paid goods purchase item. In addition, the processor 120 may set the missing item value as an intermediate value of the entire item, set it to 0, or set the missing item value as a value included in the past game data using the past game data of the target player. . The above-described normalization method is only an example, and the present disclosure is not limited thereto.

The processor 120 may generate a game interest determination model that trains the game interest determination model using the labeled learning data to output a game interest based on the game data. In an embodiment of the present disclosure, the processor 120 may obtain game interest based on the input data by calculating game data grouped by a predetermined time unit using a game interest determination model.

The processor 120 inputs game data grouped in a predetermined time unit into a game interest determination model to generate a game interest determination model, and compares the game interest level, which is the output data calculated by the game interest level determination model, and the labeling value of the input data. The error can be calculated. The processor 120 may adjust the weight of the game interest determination model based on the error in a reverse propagation method. The processor 120 may set a drop out so that a part of the output of the hidden node is not transmitted to the next hidden node in order to prevent overfitting in learning the game interest determination model. The processor 120 may set the learning rate high in the early stage of learning for learning efficiency, and set the learning rate to be low as the learning progresses. The initial weight of the game interest determination model may be set based on a random or continuous uniform distribution. The description of the learning method described above is merely an example, and the present disclosure is not limited thereto.

The processor 120 may determine whether to stop learning using the verification data when the learning is performed over a predetermined epoch. Here, the predetermined epoch may be part of the total learning target epoch. The processor 120 may test the performance of the game interest determination model generated using the test data, and determine whether to activate the game interest determination model based on the performance. The verification data may include labeled multi-year game data. The test data may include labeled multi-year game data. The processor 120 performs learning of the game interest determination model using the learning data, and after learning of the game interest determination model is repeated more than a predetermined epoch, the learning effect of the game interest determination model is predetermined using verification data. You can judge whether it is above the level. For example, if the processor 120 performs learning with a target repetition number of times of 100,000 using 1 million pieces of training data, after performing 10000 iterations of a predetermined epoch, and using 1000 pieces of verification data By performing 10 iterative learning, if the change in game interest determination model output is less than or equal to a predetermined level during 10 iterative learning, further learning may be determined as meaningless and the learning may be terminated. That is, the verification data may be used to determine completion of learning based on whether the effect of learning by epoch in the iterative learning of the game interest determination model is greater than or equal to a certain level. The above-described learning data, the number of verification data, and the number of repetitions are only examples, and the present disclosure is not limited thereto.

The test data can be used to verify the performance of the game interest determination model. The processor 120 may determine whether to activate the game interest determination model based on whether or not the test performance is greater than or equal to a predetermined performance criterion by inputting test data and measuring errors in a neural network where learning is completed. The processor 120 verifies the performance of the completed game interest determination model by using test data in the game interest determination model for which learning has been completed, and if the performance of the learned game interest determination model is greater than a predetermined criterion, the game interest determination model is applied to other applications. Can be activated for use in In addition, the processor 120 may deactivate and discard the corresponding game interest determination model when the performance of the learned game interest determination model is below a predetermined criterion. For example, the processor 120 may determine the performance of the generated neural network model based on factors such as accuracy, precision, and recall. The above-mentioned performance evaluation criteria are only examples, and the present disclosure is not limited thereto. According to an embodiment of the present disclosure, the processor 120 may independently learn each game interest determination model to generate a plurality of game interest determination models, and evaluate the performance, and only game interest determination models having a predetermined performance or higher are game interest Can be used for measurement. In addition, in one embodiment of the present disclosure, in order to measure game interest, the game interest determination model may include one or more network functions, and when a plurality of network functions are included, game interest is obtained by combining outputs of a plurality of network functions. You can generate output.

According to an embodiment of the present disclosure, a game interest determination model for calculating a game interest based on game data for all players for many years may be generated.

4 is a flowchart of a game player management method according to an embodiment of the present disclosure.

The computing device 100 may collect 410 first game data for the player. The game data may include all data related to the player's game play. The game data may include data collected during a predetermined time period among data related to the player's game play. The computing device 100 may determine 420 the first game interest of the player by calculating the first game data using a game interest determination model including one or more network functions. The game interest level may represent a numerical value indicating an interest level in the game. Game interest may be determined based on the length of the time period from the point of view of the player's game data to the game exit. The computing device 100 may determine 430 an event for increasing the interest in the player's game to be provided to the player based on the player's first game interest. The event may be an operation for changing a game data item having high correlation with game interest. When the interest in the game decreases due to one or more items of game data, an action corresponding to the corresponding game data may be provided as an event in order to increase the interest in the game.

The computing device 100 may determine to provide the event to the player when the player's first game interest is below a predetermined threshold. The event may have an intensity of the event. The computing device 100 may determine the intensity of the event based on the player's interest in the first game. The computing device 100 may determine that the intensity of the event increases as the player's interest in the first game is low. The intensity of the event may be a degree of providing an operation for changing a game data item that is highly related to game interest.

The computing device 100 may collect second game data for the player. The computing device 100 may determine the second game interest of the player by calculating the second game data using the game interest determination model. The computing device 100 may determine whether the amount of change is greater than or equal to a threshold by comparing the player's first game interest with the player's second game interest. When the amount of change is greater than or equal to a threshold, the computing device 100 may compare the first game data and the second game data to determine a result of game data comparison. The game data comparison result may be generated by the computing device 100 comparing the values of items included in the first game data and the second game data, respectively. The game data comparison result may include at least one of data related to a change amount of each item included in the first game data and the second game data and data related to items having a change amount greater than or equal to a threshold. The computing device 100 may determine the type of the event to be provided to the player by calculating the game data comparison result using an event determination model including one or more network functions. The event determination model of the computing device 100 may determine an event based on a score for each candidate event.

The computing device 100 may collect second game data for the player. The computing device 100 may determine the second game interest of the player by calculating the second game data using the game interest determination model. The computing device 100 may determine the strength of an event to be provided to the player by comparing the player's first game interest with the player's second game interest. Increasing the intensity of the event may be to increase the number of times of providing an operation for changing a game data item that is highly related to game interest, or to increase a level of an operation for changing a game data item that is highly related to game interest.

The computing device 100 may collect third game data for the player that is collected after the event is provided to the player. The computing device 100 may determine the player's third game interest by calculating the third game data using the game interest determination model. The computing device 100 may determine a change in game interest according to an event by comparing at least one of the player's first game interest and the player's second game interest with the player's third game interest. By determining the amount of game interest change, it may be determined whether or not the provision of the event to the player improves the player's interest (ie, whether the third game interest increases). The computing device 100 may update the event determination model based on the change in game interest according to the event. The computing device 100 may update the event determination model for determining an event by updating the weight of the event determination model.

The computing device 100 updates the event determination model to increase the probability of determining the event when the player's third game interest is higher than at least one of the player's first game interest and the player's second game interest can do. The computing device 100 updates the event determination model to decrease the probability of determining the event when the player's third game interest is lower than at least one of the player's first game interest and the player's second game interest can do.

The computing device 100 may collect a set of learning data composed of game data for all players. The computing device 100 may generate a subset of learning data by grouping game data of the learning data set for each player based on player information included in the learning data set. The computing device 100 may generate game data by grouping game data of the subset of training data into predetermined criteria and labeling game interest. The predetermined criterion may include a predetermined unit of time. The computing device 100 may generate a game interest determination model that trains a game interest determination model using the learning data and outputs game interest based on the game data grouped by the predetermined criteria.

5 is a block diagram illustrating logic for implementing a game player management method according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a game player management method may be implemented by the following logic.

A game player management method according to an embodiment of the present disclosure includes logic 510 for collecting first game data for a player; Logic 520 for determining the first game interest of the player by calculating the first game data using a game interest determination model including one or more network functions; And logic 530 for determining an event to be provided to the player based on the player's first game interest.

In an alternative embodiment of the game player management method, a logic 530 for determining an event for increasing the interest in the player's game to be provided to the player based on the player's first game interest is provided by the player's first game interest. If the game interest level is less than or equal to a predetermined threshold, it may be implemented by logic determining to provide the event to the player.

In an alternative embodiment of the game player management method, the method further includes logic for collecting second game data for the player; Logic for determining the second game interest of the player by calculating the second game data using the game interest determination model; Logic for determining whether the amount of change is greater than or equal to a threshold value by comparing the first game interest of the player with the second game interest of the player; Logic for comparing the first game data and the second game data and determining a game data comparison result when the amount of change is greater than or equal to a threshold value; And by calculating the game data comparison result using an event determination model including one or more network functions, it may be implemented by logic for determining the type of the event to be provided to the player.

In an alternative embodiment of the game player management method, the method further includes logic for collecting third game data for the player that is collected after the event is provided to the player; Logic for determining the third game interest of the player by calculating the third game data using the game interest determination model; Logic for determining a change in game interest according to an event by comparing at least one of the player's first game interest and the player's second game interest and the player's third game interest; And logic for updating the event decision model based on a change in game interest according to the event.

In an alternative embodiment of the game player management method, the method further includes logic for collecting second game data for the player; Logic for determining the second game interest of the player by calculating the second game data using the game interest determination model; And logic for determining the intensity of an event to be provided to the player by comparing the player's first game interest with the player's second game interest.

In an alternative embodiment of the game player management method, the method further determines the probability of determining the event when the player's third game interest is higher than at least one of the player's first game interest and the player's second game interest Update the event determination model to increase this, or if the player's third game interest is lower than at least one of the player's first game interest and the player's second game interest, the probability of determining the event decreases It may also be implemented by logic for updating the event determination model.

In an alternative embodiment of the game player management method, the method further includes logic for collecting a set of learning data consisting of game data for the entire player; Logic for generating a subset of learning data by grouping game data of the learning data set for each player based on player information included in the learning data set; Logic for grouping game data in the subset of training data into predetermined criteria, and labeling game interest to generate training data; It may be implemented by logic for generating a game interest determination model that trains a game interest determination model using the learning data and outputs a game interest based on game data grouped by the predetermined criteria.

6 is a block diagram illustrating a module for implementing a game player management method according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a game player management method may be implemented by the following modules.

A game player management method according to an embodiment of the present disclosure includes a module 610 for collecting first game data for a player; A module 620 for determining the first game interest of the player by calculating the first game data using a game interest determination model including one or more network functions; And a module 630 for determining an event for increasing the interest in the player's game to be provided to the player based on the player's first game interest.

In an alternative embodiment of the game player management method, the module 630 for determining an event to be provided to the player based on the player's first game interest is when the player's first game interest is below a predetermined threshold, It can be implemented by a module that determines to provide the event to the player.

In an alternative embodiment of the game player management method, the method further comprises a module for collecting second game data for the player; A module for determining the second game interest of the player by calculating the second game data using the game interest determination model; A module for comparing whether the player's first game interest and the player's second game interest are greater than or equal to a threshold; A module for comparing the first game data and the second game data and determining a game data comparison result when the change amount is greater than or equal to a threshold value; And a module for determining the type of the event to be provided to the player by calculating the game data comparison result using an event determination model including one or more network functions.

In an alternative embodiment of the game player management method, the method further includes a module for collecting third game data for the player collected after the event is provided to the player; A module for determining the third game interest of the player by calculating the third game data using the game interest determination model; A module for determining a change in game interest according to an event by comparing at least one of the player's first game interest and the player's second game interest and the player's third game interest; And a module for updating the event decision model based on a change in game interest according to the event.

In an alternative embodiment of the game player management method, the method further comprises a module for collecting second game data for the player; A module for determining the second game interest of the player by calculating the second game data using the game interest determination model; And it may be implemented by a module for determining the intensity of the event to be provided to the player by comparing the first game interest of the player with the second game interest of the player.

In an alternative embodiment of the game player management method, the method further determines the probability of determining the event when the player's third game interest is higher than at least one of the player's first game interest and the player's second game interest Update the event determination model to increase this, or if the player's third game interest is lower than at least one of the player's first game interest and the player's second game interest, the probability of determining the event decreases It may be implemented by a module for updating the event determination model.

In an alternative embodiment of the game player management method, the method further includes a module for collecting a set of learning data consisting of game data for all players; A module for generating a subset of learning data by grouping game data of the learning data set for each player based on player information included in the learning data set; A module for grouping game data of the training data subset into predetermined criteria, and labeling game interest to generate training data; It may be implemented by a module for generating the game interest determination model that trains the game interest determination model using the learning data and outputs the game interest based on the game data grouped by the predetermined criteria.

7 is a block diagram illustrating a circuit for implementing a game player management method according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a game player management method may be implemented by the following circuit.

According to one embodiment of the present disclosure, a game player management method includes: a circuit 710 for collecting first game data for a player; A circuit 720 for determining the first game interest of the player by calculating the first game data using a game interest determination model including one or more network functions; And a circuit 730 for determining an event for increasing the interest in the player's game to be provided to the player based on the player's first game interest.

In an alternative embodiment of the game player management method, the circuit 730 for determining an event to be provided to the player based on the player's first game interest is when the player's first game interest is below a predetermined threshold, It can be implemented by circuitry that determines to provide the event to the player.

In an alternative embodiment of the game player management method, the method further comprises circuitry for collecting second game data for the player; A circuit for determining the second game interest of the player by calculating the second game data using the game interest determination model; A circuit for comparing whether the player's first game interest and the player's second game interest are greater than or equal to a threshold; A circuit for comparing the first game data and the second game data and determining a game data comparison result when the amount of change is equal to or greater than a threshold value; And a circuit for determining the type of the event to be provided to the player by calculating the game data comparison result using an event determination model including one or more network functions.

In an alternative embodiment of the game player management method, the method further includes circuitry for collecting third game data for the player that is collected after the event is provided to the player; Circuitry for determining the third game interest of the player by calculating the third game data using the game interest determination model; A circuit for determining a change in game interest according to an event by comparing at least one of the player's first game interest and the player's second game interest and the player's third game interest; And a circuit for updating the event decision model based on the change in game interest according to the event.

In an alternative embodiment of the game player management method, the method further comprises circuitry for collecting second game data for the player; A circuit for determining the second game interest of the player by calculating the second game data using the game interest determination model; And a circuit for determining the intensity of an event to be provided to the player by comparing the player's first game interest with the player's second game interest.

In an alternative embodiment of the game player management method, the method further determines the probability of determining the event when the player's third game interest is higher than at least one of the player's first game interest and the player's second game interest Update the event determination model to increase this, or if the player's third game interest is lower than at least one of the player's first game interest and the player's second game interest, the probability of determining the event decreases It may also be implemented by circuitry for updating the event determination model.

In an alternative embodiment of the game player management method, the method further comprises circuitry for collecting a set of learning data consisting of game data for the entire player; Circuitry for generating a subset of learning data by grouping game data of the learning data set for each player based on player information included in the learning data set; Circuitry for grouping game data in the subset of training data into predetermined criteria and labeling game interest to generate training data; It may be implemented by a circuit for generating the game interest determination model that trains the game interest determination model using the learning data and outputs game interest based on the game data grouped by the predetermined criteria.

8 is a block diagram illustrating a means for implementing a game player management method according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a game player management method may be implemented by the following means.

A game player management method according to an embodiment of the present disclosure includes means (810) for collecting first game data for a player; Means (820) for determining the first game interest of the player by calculating the first game data using a game interest determination model including one or more network functions; And means 830 for determining an event for increasing the interest in the player's game to be provided to the player based on the player's first game interest.

In an alternative embodiment of the game player management method, the means 830 for determining an event to be provided to the player based on the player's first game interest is when the player's first game interest is below a predetermined threshold, It can be implemented by means of deciding to provide the event to the player.

In an alternative embodiment of the game player management method, the method further comprises means for collecting second game data for the player; Means for determining the second game interest of the player by calculating the second game data using the game interest determination model; Means for determining whether a change amount is greater than or equal to a threshold by comparing the player's first game interest with the player's second game interest; Means for determining game data comparison results by comparing the first game data and the second game data when the amount of change is greater than or equal to a threshold value; And by calculating the game data comparison result using an event determination model including one or more network functions, a means for determining the type of the event to be provided to the player.

In an alternative embodiment of the game player management method, the method further comprises means for collecting third game data for the player that is collected after the event is provided to the player; Means for determining the third game interest of the player by calculating the third game data using the game interest determination model; Means for determining a change in game interest according to an event by comparing at least one of the player's first game interest and the player's second game interest and the player's third game interest; And a means for updating the event decision model based on the change in game interest according to the event.

In an alternative embodiment of the game player management method, the method further comprises means for collecting second game data for the player; Means for determining the second game interest of the player by calculating the second game data using the game interest determination model; And means for determining the intensity of an event to be provided to the player by comparing the player's first game interest with the player's second game interest.

In an alternative embodiment of the game player management method, the method further determines the probability of determining the event when the player's third game interest is higher than at least one of the player's first game interest and the player's second game interest Update the event determination model to increase this, or if the player's third game interest is lower than at least one of the player's first game interest and the player's second game interest, the probability of determining the event decreases It may be implemented by means for updating the event determination model.

In an alternative embodiment of the game player management method, the method further comprises means for collecting a set of learning data consisting of game data for the entire player; Means for generating a subset of learning data by grouping game data of the learning data set for each player based on player information included in the learning data set; Means for grouping game data in the subset of training data into predetermined criteria and labeling game interest to generate training data; It may be implemented by means for generating the game interest determination model that trains the game interest determination model using the learning data and outputs the game interest based on the game data grouped by the predetermined criteria.

9 is a block diagram of a computing device according to an embodiment of the present disclosure.

9 shows a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure can be implemented.

Although the present disclosure has been described above in general with respect to computer-executable instructions that can be executed on one or more computers, those skilled in the art will appreciate that the present disclosure can be implemented in combination with other program modules and / or as a combination of hardware and software. will be.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those of ordinary skill in the art may find that the methods of the present disclosure include single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like (each of which is It will be appreciated that it may be implemented in other computer system configurations, including one that may operate in conjunction with one or more associated devices.

The described embodiments of the present disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer readable media. Any computer-accessible medium can be a computer-readable medium. Computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-removable media. By way of example, and not limitation, computer readable media may include computer readable storage media and computer readable transmission media. Computer-readable storage media are volatile and non-volatile media, temporary and non-transitory media, removable and non-removable, implemented in any method or technology for storing information such as computer readable instructions, data structures, program modules or other data Includes media. Computer storage media include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, Or any other medium that can be accessed by a computer and used to store desired information.

Computer readable transmission media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and Includes all information delivery media. The term modulated data signal means a signal in which one or more of the characteristics of the signal are set or changed to encode information in the signal. By way of example, and not limitation, computer readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above-described media are also intended to be included within the scope of computer-readable transmission media.

An exemplary environment 1100 is shown that implements various aspects of the present disclosure, including a computer 1102, and the computer 1102 includes a processing device 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 connects system components, including, but not limited to, system memory 1106 to processing device 1104. The processing device 1104 can be any of a variety of commercial processors. Dual processor and other multiprocessor architectures may also be used as the processing unit 1104.

The system bus 1108 can be any of several types of bus structures that can be further interconnected to a memory bus, peripheral bus, and local bus using any of a variety of commercial bus architectures. System memory 1106 includes read-only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input / output system (BIOS) is stored in a non-volatile memory 1110 such as ROM, EPROM, EEPROM, etc., and this BIOS is basic to help transfer information between components in the computer 1102 at the same time as during startup. Contains routines. The RAM 1112 may also include high-speed RAM, such as static RAM for caching data.

Computer 1102 is also an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA)-this internal hard disk drive 1114 can also be configured for external use within a suitable chassis (not shown). Yes, magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to removable diskette 1118), and optical disk drive 1120 (e.g., CD-ROM Disc 1122, or for reading from or writing to other high-capacity optical media such as a DVD). The hard disk drive 1114, the magnetic disk drive 1116, and the optical disk drive 1120 are the system bus 1108 by the hard disk drive interface 1124, the magnetic disk drive interface 1126, and the optical drive interface 1128, respectively. ). The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of computer 1102, drives and media correspond to storing any data in a suitable digital format. Although the above description of computer-readable media refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those of ordinary skill in the art can use a zip drive, magnetic cassette, flash memory card, cartridge, etc. It will be appreciated that other types of media readable by a computer, etc., may also be used in the exemplary operating environment and any such media may include computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in the drive and RAM 1112, including the operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or part of the operating system, applications, modules and / or data may also be cached in RAM 1112. It will be appreciated that the present disclosure can be implemented in various commercially available operating systems or combinations of operating systems.

The user may input commands and information to the computer 1102 through one or more wired / wireless input devices, for example, pointing devices such as a keyboard 1138 and a mouse 1140. Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, etc. These and other input devices are often connected to the processing unit 1104 through an input device interface 1142 connected to the system bus 1108, but the parallel port, IEEE 1394 serial port, game port, USB port, IR interface, And other interfaces.

The monitor 1144 or other type of display device is also connected to the system bus 1108 through an interface such as a video adapter 1146. In addition to the monitor 1144, the computer generally includes other peripheral output devices (not shown) such as speakers, printers, and the like.

The computer 1102 can operate in a networked environment using logical connections to one or more remote computers, such as remote computer (s) 1148 via wired and / or wireless communication. The remote computer (s) 1148 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, typically in computer 1102. It includes many or all of the components described with respect to, but for simplicity, only the memory storage device 1150 is shown. The illustrated logical connections include wired / wireless connections to a local area network (LAN) 1152 and / or a larger network, such as a wide area network (WAN) 1154. Such LAN and WAN networking environments are common in offices and companies, and facilitate enterprise-wide computer networks such as intranets, all of which can be connected to computer networks around the world, for example, the Internet.

When used in a LAN networking environment, the computer 1102 is connected to the local network 1152 via a wired and / or wireless communication network interface or adapter 1156. The adapter 1156 may facilitate wired or wireless communication to the LAN 1152, which also includes a wireless access point installed therein to communicate with the wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158, connect to a communication computing device on the WAN 1154, or establish communication over the WAN 1154, such as through the Internet. Have other means. The modem 1158, which may be an internal or external and wired or wireless device, is connected to the system bus 1108 through a serial port interface 1142. In a networked environment, program modules described for the computer 1102 or portions thereof may be stored in the remote memory / storage device 1150. It will be appreciated that the network connections shown are exemplary and other means of establishing a communication link between computers may be used.

The computer 1102 is associated with any wireless device or object that is deployed and operates in wireless communication, such as a printer, scanner, desktop and / or portable computer, a portable data assistant (PDA), communication satellite, or wireless detectable tag. It operates to communicate with any equipment or place and telephone. This includes at least Wi-Fi and Bluetooth wireless technology. Accordingly, the communication may be a predefined structure as in a conventional network or simply ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) enables a connection to the Internet or the like without a wired connection. Wi-Fi is a wireless technology such as a cell phone that allows a device, for example, a computer to transmit and receive data indoors and outdoors, ie anywhere within the base station's coverage area. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide a secure, reliable and high-speed wireless connection. Wi-Fi can be used to connect computers to each other, to the Internet, and to a wired network (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz radio bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11 b) data rates, or in products that include both bands (dual band). have.

One of ordinary skill in the art of the present disclosure will understand that information and signals can be represented using any of a variety of different technologies and techniques. For example, data, instructions, instructions, information, signals, bits, symbols and chips that can be referenced in the above description are voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields Or particles, or any combination thereof.

Those of ordinary skill in the art of the present disclosure may use various examples of logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein in electronic hardware, (convenience For this, it will be understood that it may be implemented by various forms of program or design code (referred to herein as "software") or a combination of both. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. Those skilled in the art of the present disclosure may implement the functions described in various ways for each particular application, but such implementation decisions should not be interpreted as being outside the scope of the present disclosure.

Various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term "manufactured article" includes a computer program, carrier, or media accessible from any computer-readable device. For example, computer-readable media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash memory Devices (eg, EEPROMs, cards, sticks, key drives, etc.), but are not limited to these. Also, various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

It is understood that the specific order or hierarchy of steps in the processes presented is an example of exemplary approaches. Based on design priorities, it is understood that within the scope of the present disclosure, a specific order or hierarchy of steps in the processes may be rearranged. The accompanying method claims provide elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

Descriptions of the presented embodiments are provided to enable any person of ordinary skill in the art to use or practice the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art of the present disclosure. The general principles defined herein can be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure should not be limited to the embodiments presented herein, but should be interpreted in the broadest scope consistent with the principles and novel features presented herein.

Claims (13)

A computer program stored on a computer-readable storage medium, the computer program, when executed on one or more processors of a computing device, performs the following operations for game player management, the operations comprising
Collecting at least one of first game data and second game data for a player, wherein the first game data and second game data are collected during a predetermined time period of different time periods for the same player;
The first game data and the second game data are calculated by using a game interest determination model including one or more network functions to include the probability of the player leaving the game after a predetermined time. Determining at least one of a first game interest level and a second game interest level;
Determining an event for increasing interest in the player's game to be provided to the player based on the player's first game interest;
Determining whether a change amount is equal to or greater than a threshold value by comparing the player's first game interest with the player's second game interest;
When the amount of change is greater than or equal to a threshold value, comparing the first game data with the second game data to determine game data comparison results; And
Determining a type of the event to be provided to the player by calculating the game data comparison result using an event determination model including one or more network functions;
Containing,
A computer program stored on a computer readable storage medium.
According to claim 1,
The first game data,
Contains data related to the player's gameplay, and includes data collected during a predetermined time period among data related to the player's gameplay,
A computer program stored on a computer readable storage medium.
According to claim 1,
Determining an event to be provided to the player based on the player's first game interest,
Determining that the event is to be provided to the player when the player's first game interest is below a predetermined threshold;
Containing,
A computer program stored on a computer readable storage medium.
The method of claim 3,
The event has the intensity of the event,
The intensity of the event is determined based on the player's interest in the first game, and the intensity of the event increases as the player's interest in the first game decreases.
A computer program stored on a computer readable storage medium.
delete According to claim 1,
Collecting third game data for the player that is collected after the event is provided to the player;
Determining the third game interest of the player by calculating the third game data using the game interest determination model;
Determining a change in game interest according to an event by comparing at least one of the player's first game interest and the player's second game interest and the player's third game interest; And
Updating the event decision model based on a change in game interest according to the event;
Containing more,
A computer program stored on a computer readable storage medium.
According to claim 1,
Determining an intensity of an event to be provided to the player by comparing the player's first game interest with the player's second game interest;
Containing more,
A computer program stored on a computer readable storage medium.
According to claim 1,
The game data comparison result,
As generated by comparing the values of items included in the first game data and the second game data,
And at least one of data related to a change amount of each item included in the first game data and the second game data and data related to a change amount of a threshold value or more,
A computer program stored on a computer readable storage medium.
The method of claim 6,
The operation of updating the event determination model based on the change in game interest according to the event may include:
If the player's third game interest is higher than at least one of the player's first game interest and the player's second game interest, update the event determination model to increase the probability of determining the event, or
Updating the event determination model to decrease the probability of determining the event when the player's third game interest is lower than at least one of the player's first game interest and the player's second game interest;
Containing,
A computer program stored on a computer readable storage medium.
According to claim 1,
Collecting a learning data set consisting of game data for all players;
Generating a subset of learning data by grouping game data of the learning data set by players based on player information included in the learning data set;
Grouping game data of the subset of training data into predetermined criteria and labeling game interest to generate training data;
Generating the game interest determination model to train the game interest determination model using the learning data and output the game interest based on the game data grouped by the predetermined criteria;
Containing more,
A computer program stored on a computer readable storage medium.
The method of claim 10,
The predetermined criterion includes a predetermined unit of time,
A computer program stored on a computer readable storage medium.
A method for preventing departure of a player performed on one or more processors of a computing device,
In the processor, the first game data and the second game data for the player through the network unit, the first game data and the second game data, at least one of data collected during a predetermined time period of different time zones for the same player Collecting;
The processor includes a probability of the player leaving the game after a predetermined time by calculating at least one of the first game data and the second game data using a game interest determination model including one or more network functions. Determining at least one of a player's first game interest and a second game interest;
Determining an event for increasing interest in the player's game to be provided to the player based on the player's first game interest in the processor;
Determining, by the processor, whether the amount of change is greater than or equal to a threshold by comparing the player's first game interest with the player's second game interest;
Determining, by the processor, a result of comparing game data by comparing the first game data with the second game data when the amount of change is greater than or equal to a threshold value; And
Determining, by the processor, the type of the event to be provided to the player by calculating the game data comparison result using an event determination model including one or more network functions;
Containing,
A method for preventing departure of players performed on one or more processors of a computing device.
As a computing device for game player management,
A processor comprising one or more cores; And
Memory;
Including,
The processor,
First game data and second game data for the player-the first game data and the second game data collect at least one of data collected during a predetermined time period of different time periods for the same player,
The first game data and the second game data are calculated by using a game interest determination model including one or more network functions to include the probability of the player leaving the game after a predetermined time. Determine at least one of the first game interest and the second game interest,
Determine an event for increasing interest in the player's game to be provided to the player based on the player's first game interest,
Compare the first game interest of the player with the second game interest of the player to determine whether the change amount is greater than or equal to a threshold value,
When the amount of change is greater than or equal to a threshold value, the first game data and the second game data are compared to determine a game data comparison result, and
Determining the type of the event to be provided to the player by calculating the game data comparison result using an event determination model including one or more network functions,
Computing device for game player management.

Images