KR20210000181A - Method for processing game data - Google Patents

Abstract

The present disclosure is to provide a method for processing data. According to an embodiment of the present disclosure, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed on one or more processors to perform the following operations for processing game data. The operations may comprise: acquiring a game log; extracting an activity log and a result log from the game log; obtaining activity information by inputting at least one of the activity log and the result log into an activity information generation model; and providing the activity information based on a request from a user terminal.

Description

Game data processing method {METHOD FOR PROCESSING GAME DATA}

The present disclosure relates to a data processing method, and more specifically, to a method for processing game data.

With the development of electronic communication technology, as the number of people who enjoy games increases, various types of games such as strategy simulation games and role-playing games have been developed. These games can be played in both online and offline situations. In particular, online games have no time and space constraints, so a large number of users can easily gather and enjoy the game together.

As the number of users enjoying the game increases, the amount of accumulated game data also increases. In addition, as the number of users who enjoy games increases, competition among companies is fierce. There may be a demand in the art for a method of providing services to users by utilizing vast amounts of game data in order to survive the fierce competition.

Therefore, in recent years, various methods of providing necessary services to users through processing of vast amounts of game data have been researched and developed.

Korean Patent Publication No. 2019-0015441 discloses an apparatus and method for real-time reconfiguration of a user interface for manipulation of an online game character.

The present disclosure is conceived in response to the aforementioned background technology, and is to provide a method for processing data.

According to an embodiment of the present disclosure for realizing the above-described problem, a computer program is disclosed that includes instructions stored in a computer-readable storage medium to cause a computer to perform the following operations. The operations may include obtaining a game log; Extracting an activity log and a result log from the game log; Inputting at least one of the activity log or the result log into an activity information generation model to obtain activity information; And providing activity information based on the request of the user terminal.

In an alternative embodiment, the activity log may include at least one of a character activity record, character information, or game environment information on a game.

In an alternative embodiment, the result log may include a record of results caused by the character's activity in the game.

In an alternative embodiment, the activity information may include at least one of first activity information including the activity log or second activity information generated based on the activity log.

In an alternative embodiment, the activity information may be determined based on target information received from the user terminal.

In an alternative embodiment, the operation of generating result information based on the request of the user terminal may be further included, and the result information may include information predicting a result of the activity of the character in the game based on the activity information. have.

In an alternative embodiment, the activity information generation model may include a first sub-model including a probabilistic sequence model for obtaining first activity information.

In an alternative embodiment, the probabilistic sequence model may include a model that generates the activity information based on probability values of each of a plurality of activity patterns that are components included in the activity log.

In an alternative embodiment, the activity information generation model includes a second sub-model for obtaining second activity information, and the second sub-model for obtaining second activity information is based on the activity log. 2 A reinforcement learning model for acquiring activity information may be included.

In an alternative embodiment, the reinforcement learning model is for obtaining second activity information for obtaining a game state from the activity log and calculating the game state using a reinforcement learning model to derive predetermined result information. Can contain models.

In an alternative embodiment, the reinforcement learning model may include a model for obtaining second activity information using a value function approximator.

In an alternative embodiment, the approximate value function uses a parameter learned to reduce the difference between the actual value function and the approximate value function, and calculates a value approximating the actual value function by receiving the game state obtained from the activity log. May contain functions.

In an alternative embodiment, the operation of providing the activity information based on the request of the user terminal may include causing the user to select at least one or more skills based on the activity information on the game screen of the user terminal. .

In an alternative embodiment, it may further include an action for causing a character motion in the game based on the provided activity information.

A method for processing game data according to another embodiment of the present disclosure is disclosed. Obtaining a game log; Extracting an activity log and a result log from the game log; Obtaining activity information by inputting at least one of the activity log or the result log into an activity information generation model; And providing activity information based on the request of the user terminal.

A computing device is disclosed according to another embodiment of the present disclosure. The computing device may include one or more processors; And a memory storing instructions executable in the processor. Including, wherein the at least one processor acquires a game log, extracts an activity log and a result log from the game log, and inputs at least one of the activity log or the result log into an activity information generation model to provide activity information And provide activity information based on the request of the user terminal.

According to an embodiment of the present disclosure, a method of processing data may be provided.

In order that the features of the present disclosure mentioned above may be understood in detail, in a more specific description, with reference to the following embodiments, some of the embodiments are shown in the accompanying drawings. In addition, like reference numbers in the drawings are intended to refer to the same or similar functions over several aspects. However, the accompanying drawings are merely illustrative of specific exemplary embodiments of the present disclosure, and are not considered to limit the scope of the present disclosure, and other embodiments having the same effect may be sufficiently recognized. Be careful.
1 is a block diagram of a computing device for processing game data according to an embodiment of the present disclosure.
2 is a schematic diagram showing a network function for processing game data according to an embodiment of the present disclosure.
3 is an exemplary diagram for explaining a method of providing activity information according to an embodiment of the present disclosure.
4 is an exemplary diagram for describing a method of providing activity information based on character information according to an embodiment of the present disclosure.
5 is an exemplary diagram for explaining a method of providing activity information based on game environment information according to an embodiment of the present disclosure.
6A and 6B are exemplary diagrams for describing an approximate value function according to an embodiment of the present disclosure.
7 is a flowchart of a method of processing game data according to an embodiment of the present disclosure.
8 is a block diagram illustrating a module for processing game data according to an embodiment of the present disclosure.
9 is a simplified and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

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 clear that these embodiments may be implemented without this specific description.

The terms "component", "module", "system" and the like as used herein refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or execution of software. For example, a component may be, but is not limited to, a process executed on a processor, a processor, an object, an execution thread, a program, and/or a computer. For example, both an application running on a computing device and a computing device may be components. One or more components may reside within a processor and/or thread of execution. A component can be localized on a single computer. A component can be distributed between two or more computers. In addition, these components can execute from a variety of computer readable media having various data structures stored therein. Components can be, for example, via a signal with one or more data packets (e.g., data from one component interacting with another component in a local system, a distributed system, and/or a signal through another system and a network such as the Internet. Depending on the data being transmitted), it may communicate via 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 is not clear from the context, "X employs A or B" is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or, when X uses both A and B, “X uses A or B” can be applied to either of these cases. In addition, the term "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the listed related items.

In addition, the terms "comprising" and/or "comprising" are to be understood as meaning that the corresponding features and/or components are present. However, it is to be understood that the terms "comprising" 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 when the context is not clear as indicating a singular form, the singular in the specification and claims should be interpreted as meaning "one or more" in general.

In addition, the term "at least one of A or B" should be interpreted as meaning "when including only A", "when including only B", and "when combined in a configuration of A and B".

Those of skill in the art would further describe the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein, including 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 restrictions imposed on the overall system. Skilled technicians can implement the described functionality 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.

A description of the presented embodiments is provided so that a person of ordinary skill in the art of the present disclosure can use or implement the present invention. Various modifications to these embodiments will be apparent to those of ordinary skill in the art. The general principles defined herein may 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 present invention is to be accorded the widest scope consistent with the principles and novel features presented herein.

1 is a block diagram of a computing device for processing game data according to an embodiment of the present disclosure.

The configuration of the computing device 100 illustrated in FIG. 1 is only an example simplified. In an embodiment of the present disclosure, the computing device 100 may include other components for performing the computing environment of the computing device 100, and only some of the disclosed components may configure the computing device 100.

The computing device 100 may include a processor 110, a memory 130, and a network unit 150.

Processor 110 may be composed of one or more cores, a central processing unit (CPU: central processing unit), a general purpose graphics processing unit (GPGPU: general purpose graphics processing unit), a tensor processing unit (TPU: tensor processing unit) of the computing device. unit) may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 130 to process data for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 processes input data for learning in deep learning (DL), extracts features from the input data, calculates errors, and uses backpropagation to learn neural networks such as updating parameters of neural networks. Can perform calculations. At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, the CPU and GPGPU can work together to learn network functions and classify data using network functions. In addition, in an embodiment of the present disclosure, learning of a network function and data classification using a network function may be processed by using processors of a plurality of computing devices together. In addition, a computer program executed in the computing device according to an embodiment of the present disclosure may be a CPU, a GPGPU, or a TPU executable program.

According to an embodiment of the present disclosure, the processor 110 may obtain a game log.

According to an embodiment of the present disclosure, the processor 110 may extract an activity log and a result log from the game log.

According to an embodiment of the present disclosure, the game log may include all records generated while a user plays a game. The game log may include at least one of an activity log or a result log.

The activity log may contain all records related to the character's activity in the game. All records related to a character's activity in the game may include records of interactions of the character in the game with components (e.g., game objects, characters, etc.) and/or components included in the game. have. The activity log may include at least one of a character's activity record, character information, or game environment information on the game. The result log may include a record of results caused by the character's activity in the game. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the activity record of a character in the game may include a record of all activities performed by the character in the game. In the game, the character's activity record is, for example, the skill used by the character, the skill sequence used by the character, the time interval between multiple skills used by the character, character play time, account play time, frequency of use by item, personal store transaction items, It can include activities such as item creation, item acquisition, item drop, item consumption, item creation, item destruction, item transaction, item enhancement, character movement, character death, character level up, character creation, character attack, character defense, etc. . The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the character information may include a record of a character existing in the game. The character information may include, for example, a character's ability value, a character's wearing item, a character's holding item, and a skill that the character can use. In addition, the character information may include, for example, a sequence of characters participating in the game play, and combinations of characters participating in the game play, when a plurality of characters play a game (eg, entering a stage). The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the game environment information may include information on an environment in which a character in a game plays a game. The game environment information may include, for example, stage information (eg, stage difficulty, a limited time required to clear the stage) or game object information played by a character on the game. The game object information may include, for example, a map through which the player can act in the game. In addition, the game object information may include, for example, an element in which a player character can move in a game environment, an element in which movement of a player's character is restricted in a game environment, an element that generates a predetermined effect on the player character, a character creation position, etc. have. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the result log may include a record of a result caused by the activity of a character in a game. The resulting log may contain one or more items. The result log is, for example, total damage, damage per unit time, damage per skill, damage per attack, damage compared to resource consumption, effect of the skill used by the character, effect of the skill sequence used by the character, whether the stage was cleared, or the stage was cleared. It may include the required time and a score calculated by performing game play. According to an embodiment of the present disclosure, the result log is the effect of the skill sequence acquired by the character A using the skill sequence (skill A, skill B, skill C) in stage 1, and whether the stage 1 is cleared (for example, clear In one case, it may include a time (for example, 15 minutes), when the stage 1 is cleared. Therefore, when the skill sequence (skill A, skill B, and skill C) is used through the character A in stage 1, the processor 110 may obtain a result log indicating that the time required for clearing stage 1 is 15 minutes. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the activity information may include information related to an activity of a character to achieve a game goal. The activity information may be determined based on target information received from the user terminal. For example, the activity information includes information for providing guide information on the activity of the character to the player, and includes at least one of first activity information including an activity log or second activity information generated based on the activity log. Can include. The activity information may include information for causing an activity of a character on the game. The information for causing the activity of the character on the game may include information for inducing the user to select the activity of the character. In addition, the information for causing the activity of the character in the game may include information that causes the game character to automatically play the game on the user terminal. For example, information for causing the attack, defense, and use of each skill of the game character, information for causing the player character to perform the skill sequence of the game character, information for causing movement of the character, and game simulation. It may contain information to perform. Information for causing the player character to perform the skill sequence of the game character is, for example, information for causing the player character to perform the skill sequence for clearing the stage, and the skill sequence for clearing the stage in the shortest time. Information for causing the player's character to perform, and information for causing the player's character to perform a skill sequence for clearing the stage with a target score may be included. The information for causing the character to move may include, for example, movement path information for clearing the stage. The information for performing the game simulation may include information for simulating a skill sequence of the game character, information for simulating a moving path of the game character, and information for simulating the play of the game character in a specific stage. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the first activity information may include information for causing use of an activity log included in the acquired game log. The activity log may include, for example, a skill sequence. The first activity information may include, for example, information for causing use of a skill sequence (eg, a skill sequence recorded through gameplay of users) included in the activity log. Accordingly, the processor 110 may generate information that causes the use of the skill sequence previously played by users by using the first sub-model. The first activity information may include, for example, information that causes the player's character to perform a skill sequence in which users have previously cleared a specific stage. Accordingly, the processor 110 may generate first activity information that causes the player's character to perform a skill sequence in which users have cleared a specific stage in the past by using the activity information generation model. The first activity information may include, for example, information that causes the player's character to perform a skill sequence that users have previously cleared a specific stage using a specific character. Accordingly, the processor 110 may generate first activity information that causes the player's character to perform a skill sequence previously cleared by users of a specific stage using a specific character using the first sub-model. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the second activity information may include activity information generated based on an activity log. The second activity information may be activity information newly generated based on an existing activity log. For example, the second activity information may include new information that is not included in an activity log performed by players of the game. That is, the second activity information may include activity information for achieving a game result, and the second activity information may include activity information of a new pattern that existing players did not perform. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the activity information may be determined based on target information received from the user terminal. The result log may include a record of results caused by the character's activity in the game. The target information may include information for identifying attributes of one or more items of the result log. For example, the result log may include whether the stage is cleared, damage per second, etc. as items. The target information may include information for identifying attributes of one or more items of the result log, including information such as stage clear, damage per second of 1000 or more. That is, in the case of selecting only the log as a result of clearing a certain stage, the target information may include information for identifying only the stage clear among the attributes of the stage clear item of the stage clear result log. The above-described target information is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 110 may generate activity information that helps the user to achieve a goal requested by the user based on the user terminal request. For example, when the target information is target information for clearing a stage, the activity information may include a skill sequence of a character for clearing the stage. When the target information is target information for clearing the stage in the shortest time, the activity information may include a skill sequence for clearing the stage in the shortest time. When the target information is target information for clearing the stage with the target score, the activity information may include a skill sequence for clearing the stage with the target score. The foregoing is only an example, and the present disclosure is not limited thereto.

The activity information will be described later with reference to FIG. 3.

According to an embodiment of the present disclosure, the processor 110 may acquire activity information by inputting at least one of the activity log or the result log into an activity information generation model. The activity information generation model may include at least one of a first sub-model for obtaining first activity information or a second sub-model for obtaining second activity information. The first sub-model and the second sub-model will be described later. The above-described activity information generation model is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 110 may generate result information based on the request of the user terminal. The result information may include information predicting a result of an activity of a character in a game based on the activity information. For example, when the user terminal requests result information based on the provided activity information, the processor 110 may generate result information based on the activity information. The processor 110 may predict a result of the character's activity by performing a game simulation based on the activity information. For example, when using the skill sequence (skill B, skill A, and skill C) for stage 1 as the character A, the processor 110 may generate the time required to clear stage 1 as result information. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the activity information generation model may include a first sub-model including a probabilistic sequence model for obtaining the first activity information. After inputting a sequence of components to the probabilistic sequence model, the processor 110 may obtain a probability value of the occurrence of the next component using the probabilistic sequence model. The probabilistic sequence model is a unigram model used when a plurality of input components are independent, a bigram model used when a plurality of input components correlate with the previous component of each component, and a plurality of components each It may include an N-gram model used when there is a correlation with all components that appear before the component (for example, when the nth component has a correlation with the 1st to n-1th components). The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the probabilistic sequence model may include a model that generates the activity information based on probability values of each of a plurality of activity patterns that are components included in the activity log. The activity pattern may include components included in the activity log. For example, if the activity pattern is a skill, and the skill sequence input to the probabilistic sequence model is skill A, skill B, or skill C, the processor 110 calculates a probability value for the next skill using the probabilistic sequence model. Can be obtained. For example, the processor 110 acquires a probability value of 0.3, the probability of skill D is 0.6, and the probability of skill E is 0.1, after the input skill sequence (skill A, skill B, skill C). can do. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the activity information generation model may include a second sub-model for obtaining second activity information. The second sub-model for obtaining the second activity information may include a reinforcement learning model for obtaining the second activity information based on the activity log. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the reinforcement learning model is for obtaining second activity information for obtaining a game state from an activity log and calculating the game state using a reinforcement learning model to derive predetermined result information. Can contain models. The process of calculating the game state using the reinforcement learning model includes determining the activity of the character from the game state through a policy network, and determining the game state through a value network from the game state. can do. The foregoing is only an example, and the present disclosure is not limited thereto.

In an embodiment of the present disclosure, the policy network may be a network for determining an activity of a character that can be taken in a current game state when a game state is given as an input. Accordingly, when the current state is given, the policy network may learn the probability of a character's activity for obtaining the maximum reward in the current state, and store probability data for each character activity that can be taken in the current state. The foregoing is only an example, and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the value network may be a network that predicts a value function value when a current state and/or policy is given as input. The value function may be an average of the sum of expected future rewards based on the input current state and policy. Rewards can be rewards earned when a policy is taken in the current state. The policy may be a strategy for selecting an activity of a character to obtain the maximum reward in the current state. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the second activity information for deriving the predetermined result information may include activity information generated based on a strategy for selecting an activity of a character for obtaining the maximum reward in a current state. have. The pre-determined outcome may include the outcome at which the reward is maximized. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 110 may generate second activity information using the second sub-model. The processor 110 may generate second activity information including unscene data (data not included in the acquired game log) by using the second sub-model. For example, when the unscene data includes a skill sequence (skill B, skill A, skill C), the processor 110 uses a second sub-model to obtain a skill sequence (skill B, skill A, skill C) can be acquired. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, in order to reinforce the second sub-model, the processor 110 may determine a state, an action, and a reward for reinforcement learning.

The state may include, for example, the current game state. The current game state can be obtained from the game log. The current game state may include, for example, a skill sequence used, a stage performing a current game play, a current state of a character (eg, a character's wearing item, a character's physical strength, a horsepower), etc. Not limited.

Actions may include in-game actions that a player's character can perform, for example, skills that a character can use, movement of a character, attack of a character, defense, etc., but the present disclosure is not limited thereto. Does not.

Rewards may include result information. The reward may be determined based on, for example, whether the stage has been cleared, whether the stage clearing time has been shortened, and whether the score obtained through game play has increased. For example, when a stage is cleared through an input state or action, the reward can be increased. Also, if the time to clear the stage through the input state or action is shortened, the reward can be increased. Rewards can be increased when the number of points acquired through game play increases through the input state and action. The foregoing is only an example, and the present disclosure is not limited thereto.

For example, when the processor 110 receives a skill sequence (skill B, skill A, skill C) in a game state, selectable skills may be skill A, skill D, and skill E. When the concept of reinforcement learning is applied, skill sequences (Skill B, Skill A, and Skill C) correspond to a state, and each Skill A, Skill D, and Skill E corresponds to an action. The processor 110 may select a skill whose reward is maximized through reinforcement learning, and when skill D is a skill that maximizes a reward (eg, damage per second), skill D may be selected as the next skill. The processor may synthesize these skill sequences and generate second activity information. The foregoing is only an example, and the present disclosure is not limited thereto.

According to the present disclosure, since the second sub-model includes the reinforcement learning model, unscene data that is not included in the game log obtained by the processor 110 may be generated, and a result of optimal activity information may be obtained. Therefore, by generating more diverse and rich activity information using the reinforcement learning model, it is possible to increase the user's interest in the game by providing activity information suitable for the user's game situation.

According to an embodiment of the present disclosure, the reinforcement learning model may include a model for obtaining second activity information by using an approximate value function. According to an embodiment of the present disclosure, the approximate value function uses a parameter learned to reduce the difference between the real value function and the approximate value function, receives the game state obtained from the activity log, and calculates a value approximating the real value function. It may include a function to calculate. The foregoing is only an example, and the present disclosure is not limited thereto.

The approximate value function will be described later with reference to FIGS. 6A and 6B.

According to an embodiment of the present disclosure, the processor 110 may provide activity information based on a request from a user terminal.

According to an embodiment of the present disclosure, the processor 110 may provide activity information based on a request from a user terminal. The activity information may cause a graphic expression that allows the user to select at least one skill based on the activity information on the game screen of the user terminal. The foregoing is only an example, and the present disclosure is not limited thereto.

An operation of causing the user to select at least one skill based on the activity information on the game screen of the user terminal will be described later with reference to FIG. 3.

According to an embodiment of the present disclosure, the processor 110 may cause a character motion in a game to be performed on the user terminal by transmitting the activity information to the user terminal. The user terminal may enable a character in the game to automatically perform game play without a user's input signal based on the provided activity information. For example, a game played in the user terminal may be a game capable of automatically playing (eg, automatic hunting, etc.) for some content of the game. For example, if the provided activity information includes information that causes the player's character to perform the skill sequence, the user terminal automatically plays the game character in the game according to the corresponding skill sequence based on the provided activity information. You can make it play. When the provided activity information includes information that causes the character to move, the processor 110 may cause the game character in the game to move based on the information that causes the movement. (For example, moving along the shortest path for clearing the stage) The above is only an example, and the present disclosure is not limited thereto.

In the game, the skillful use of skills is an important factor that makes the game progress smoothly. The win or loss of the game may be determined according to the skillful use of the skill, and further, the user's interest in the game may be increased. Therefore, by analyzing the skillful use sequence and providing it to the user, users who are not familiar with the game can smoothly play the game, thereby increasing the interest in the game.

According to the present disclosure, by providing activity information (eg, skill sequence) to a user using an activity information generation model, users who are not familiar with the game can smoothly play the game. In addition, since the activity information acquired through the activity information generation model is generated based on an analysis result based on a vast amount of game data, the reliability of the activity information of users may be high. In addition, by allowing all users to share efficient activity information not only in a closed community, it is possible to verify whether the shared activity information is effective through clear standards, so that activity information without distortion and bias Can be provided to the user.

2 is a schematic diagram showing a network function for processing game data according to an embodiment of the present disclosure.

Throughout this specification, a computational model, a neural network, a network function, and a neural network may be used with the same meaning. 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 includes at least one or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more links.

In a neural network, one or more nodes connected through a link may relatively form a relationship between an input node and an output node. The concepts of an input node and an output node are relative, and any node in an output node relationship with respect to one node may have an input node relationship in a relationship with another node, and vice versa. As described above, the relationship between the input node and the output node may be created around a 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 value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have parameters. The parameters may be variable and may be varied by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node includes values input to input nodes connected to the output node and a link corresponding to each input node. The output node value may be determined based on the parameter.

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

A neural network can be configured 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 having a distance n from an initial input node may constitute n layers. The distance from the first input node may be defined by the minimum number of links that must be traversed to reach the node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of the layer in the neural network may be defined in a different way than that described above. For example, the layer of nodes may be defined by the distance from the last output node.

The first input node may mean one or more nodes to which data is directly input without going through a link in a relationship with other nodes among nodes in the neural network. Alternatively, in a relationship between nodes in a neural network network 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. In addition, the hidden node may refer to nodes constituting a neural network other than the first input node and the last output node. In the neural network according to an embodiment of the present disclosure, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the input layer proceeds to the hidden layer. I can. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of an input layer is less than the number of nodes of an output layer, and the number of nodes decreases as the number of nodes progresses from the input layer to the hidden layer. have. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of an input layer is greater than the number of nodes of an output layer, and the number of nodes increases as the number of nodes progresses from the input layer to the hidden layer. I can. A neural network according to another embodiment of the present disclosure may be a neural network in the form of a combination of the aforementioned neural networks.

A deep neural network (DNN) may mean a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can be used to identify potential structures in data. In other words, it is possible to grasp the potential structure of photos, texts, videos, voices, and music (e.g., what objects are in photos, what are the content and emotions of the text, what are the contents and emotions of the voice, etc.) . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, Generative Adversarial Networks (GANs), and restricted Boltzmann machines (RBMs). boltzmann machine), deep belief network (DBN), Q network, U network, and Siam network. The foregoing description of the deep neural network is only an example, and the present disclosure is not limited thereto.

In an embodiment of the present disclosure, the network function may include an auto encoder. The auto encoder may be a kind of artificial neural network for outputting output data similar to input data. The auto encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between input/output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called a bottleneck layer (encoding), and then reduced and expanded symmetrically from the bottleneck layer to an output layer (symmetric with the input layer). In this case, in the example of FIG. 2, the dimensionality reduction layer and the dimensional restoration layer are illustrated as being symmetrical, but the present disclosure is not limited thereto, and nodes of the dimensionality reduction layer and the dimensional restoration layer may or may not be symmetrical. Auto encoders can perform nonlinear dimensionality reduction. The number of input layers and output layers may correspond to the number of sensors remaining after pre-processing of input data. In the auto-encoder structure, the number of nodes of the hidden layer included in the encoder may have a structure that decreases as it moves away from the input layer. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and the decoder) is too small, a sufficient amount of information may not be delivered, so more than a certain number (e.g., more than half of the input layer, etc.) ) May be maintained.

The neural network may be learned by at least one of supervised learning, unsupervised learning, and semi supervised learning. Learning of neural networks is to minimize output errors. In learning of a neural network, iteratively inputs training data to the neural network, calculates the output of the neural network for the training data and the error of the target, and reduces the error from the output layer of the neural network to the input layer. This is a process of updating the parameters of each node of the neural network by backpropagation in the direction. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (ie, labeled learning data), and in the case of non-satellite learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning related to data classification, the learning data may be data in which a category is labeled with each learning data. Labeled training data is input to a neural network, and an error may be calculated by comparing an output (category) of the neural network with a label of the training data. As another example, in the case of comparative history learning regarding data classification, an error may be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the neural network in the reverse direction (ie, from the output layer to the input layer), and connection parameters of each node of each layer of the neural network may be updated according to the backpropagation. The amount of change in the connection parameter of each node to be updated may be determined according to a learning rate. The computation of the neural network for the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of repetitions of the learning cycle of the neural network. For example, a high learning rate is used in the early stages of learning of a neural network, so that the neural network quickly secures a certain level of performance to increase efficiency, and a low learning rate can be used in the later stages of learning to increase accuracy.

In the learning of a neural network, in general, the training data may be a subset of actual data (that is, data to be processed using the learned neural network), and thus, errors in the training data decrease, but errors in the actual data occur. There may be increasing learning cycles. Overfitting is a phenomenon in which errors in actual data increase due to over-learning on learning data. For example, a neural network learning a cat by showing a yellow cat may not recognize that it is a cat when it sees a cat other than yellow, which may be a kind of overfitting. Overfitting can cause an increase in errors in machine learning algorithms. Various optimization methods can be used to prevent such overfitting. In order to prevent overfitting, methods such as increasing training data, regularization, and dropout in which some of the nodes of the network are omitted during the training process may be applied.

3 is an exemplary diagram for explaining a method of providing activity information according to an embodiment of the present disclosure.

In FIG. 3, reference numeral 310 denotes an area where the skill button is located. A skill A button 311, a skill B button 313, a skill C button 315, and a skill D button 317 are shown in the area where the skill button is located.

According to an embodiment of the present disclosure, the computing device 100 may generate activity information using an activity information generation model. The computing device 100 may provide activity information based on a request from the user terminal. The activity information may include information for causing an activity of a character on the game. The information for causing the activity of the character on the game may include information for inducing the user to select the activity of the character. The user can play the game based on the provided activity information. For example, the activity information may include information that causes the skill sequence to be used. The information that causes the skill sequence to be used may include information that induces the user to select the corresponding skill sequence. For example, the corresponding skill sequence may include skill A, skill B, skill D, and skill C. The user terminal has a skill A button 311, a skill B button 313, and a skill D button 317 in order to induce the user to sequentially select a skill sequence skill A, skill B, skill D, and skill C based on the activity information. ), the skill C button 315 may be sequentially displayed in a manner of stimulating the user's vision (eg, highlighting the button). The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the computing device 100 may generate activity information using an activity information generation model. The computing device 100 may provide activity information based on a request from the user terminal. The activity information may include information related to the activity of the character to achieve the game result. The activity information may include information for causing an activity of a character on the game. The information for causing the activity of the character in the game may include information that causes the game character to automatically play the game on the user terminal. For example, the activity information may include information that causes a character of a player to perform a skill sequence. The information causing the player's character to perform the skill sequence may include information causing the character to automatically perform game play using the corresponding skill sequence without a user's input signal. The activity information that causes the skill sequence to be used may include a command for performing automatic game play by using the skill sequence. Therefore, if the skill sequence included in the activity information is skill A, skill B, skill D, and skill C, the user terminal uses skill A, skill B, skill D, and skill C in the game based on the activity information. It can be controlled to automatically perform gameplay. When the game play is automatically performed, the automatic battle 330 is displayed on the game screen on the user terminal to indicate that the user terminal is in the automatic battle mode. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the computing device 100 may generate result information. The result information may include information predicting a result of an activity of a character in a game based on the activity information. The computing device 100 may predict a result of the character's activity by performing a game simulation based on the activity information. For example, the activity information may include information that causes the game character to use skill A, skill B, skill D, and skill C in order. Through this, the computing device 100 may obtain result information when the character uses Skill A, Skill B, Skill D, and Skill C in order. If the simulation result using skill A, skill B, skill D, and skill C in order is 585, 590, 591, and 576, respectively, as shown in reference number 350, the computing device 100 is skill A, skill Using B, Skill D, and Skill C, you can generate result information including predictions that damage will cause 585, 590, 591, and 576, respectively. The foregoing is only an example, and the present disclosure is not limited thereto.

4 is an exemplary diagram for describing a method of providing activity information based on character information according to an embodiment of the present disclosure.

4 shows a plurality of characters and each character information.

According to an embodiment of the present disclosure, the computing device 100 may provide activity information based on a request from a user terminal. The request of the user terminal may include target information. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the request of the user terminal may include a request for generating activity information based on a character selected by the user. That is, for example, the target information may be stage clear using a character selected by the user. For example, the request from the user terminal may include a request for activity information generated based on the Thor 410 character. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the request of the user terminal may include a request for generating activity information regarding an operation to be performed in a game in order to clear a stage. Accordingly, when the request of the user terminal is a request for generating activity information for clearing the stage with the character Tor 410, the computing device 100 may generate activity information for clearing the stage with the character Tor 410. As described above, the activity information may include information causing the player's character to perform the activity pattern of the activity information. For example, the skill sequence for clearing the stage with the character Thor 410 may be sequential use of skill A, skill B, skill D, and skill C. In this case, the computing device 100 may generate activity information including the above-described skill sequence and provide it to the user terminal. The user terminal may provide visual effects for skill buttons in order to induce the user's sequential use of skill A, skill B, skill D, and skill C based on activity information including the above-described skill sequence. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the computing device 100 may provide activity information based on a request from a user terminal. The request of the user terminal may include a request for generating activity information for automatic battle. For example, the request from the user terminal may include a request for activity information on an operation to be performed in order to clear the stage using the Hella 430 character. Accordingly, the computing device 100 may generate activity information for performing an automatic battle for clearing a stage using the Hella 430 character and provide it to the user terminal. The user terminal may perform an automatic battle based on the activity information. For example, if the activity information includes information that causes the player's character to perform the skill sequence, the skill sequence for clearing the stage with the Hella 430 character includes skill A, skill F, skill D, and skill C. Can include. Accordingly, the user terminal can perform an automatic battle of the player's character using a skill sequence (skill A, skill F, skill D, skill C) based on the activity information for clearing the stage. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the computing device 100 may provide activity information based on a request from a user terminal. The request from the user terminal may include a request for activity information generated based on a plurality of character combinations selected by the user. For example, the request from the user terminal may include a request for generating activity information for performing a stage clear using the character Thor 410, the character Hella 430, and the character Angela 450. Depending on the combination of characters, the activity information of each character may vary. Accordingly, when the character combination is the Thor 410 character, the Hella 430 character, and the Angela 450 character, activity information of the Thor 410 character for clearing the stage may be changed. For example, when the Thor 410 character plays a game alone, the optimal skill sequence may be skill A, skill B, skill D, and skill C. However, if the character combination is Thor 410 character, Hella 430 character, and Angela 450 character, the optimal skill sequence of Thor 410 character can be changed to Skill A, Skill C, Skill B, and Skill D. have. Accordingly, the computing device 100 may generate activity information in consideration of a character combination. Through this, activity information that is more suitable for a game situation in which a number of various cases exist may be generated to help the user competently play the game, thereby increasing the user's interest in the game.

5 is an exemplary diagram for describing a method of providing activity information based on game environment information according to an embodiment of the present disclosure.

5 shows a stage included in the game environment information.

According to an embodiment of the present disclosure, the user terminal may receive action information to be performed to achieve the goal from the computing device 100 by transmitting goal information to be achieved in the game to the computing device 100. . The user terminal may request a goal to be achieved in the game from the computing device. The goal to be achieved in the game may be information identifying the attribute of an item in the result log. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the request for activity information from the user terminal may include a request for activity information for achieving target information in a game environment selected by the user. For example, the activity information request may include an activity information request based on target information. For example, the target information may include a character, a stage, and a difficulty level. That is, in this example, for example, the request for activity information from the user terminal is activity information when using a specific character (eg, clearing a stage using a character A), activity information for clearing a specific stage (for example, , A and B characters entering the stage, etc.).

According to an embodiment of the present disclosure, when the request of the user terminal includes a request for generating activity information for clearing the stage 2 510 using the Tor 410 character, the computing device 100 is the Tor 410 Activity information for clearing the stage 2 510 may be generated using the character. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, when the request of the user terminal includes a request for generating activity information for clearing the stage 5 530 in the shortest time using the Hella 430 character, the computing device 100 (430) Using a character, activity information for clearing the stage 5 530 in the shortest time may be generated. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, when the request of the user terminal is a request for generating activity information for obtaining the highest score through game play on the stage 7 550 using the Angela 450 character, the computing device 100 ) May generate activity information for clearing the stage 7 550 in the shortest time using the Angela 450 character. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the activity information may be changed based on the stage difficulty. For example, when the stage 2 510 is under the difficulty level, the stage 5 530 is under the difficulty level, and the stage 7 550 is over the difficulty level, the computing device 100 may generate activity information according to the difficulty level. When the user request is a request for clearing the difficulty level merchant stage 7 (550), the computing device 100 enters the stage using the characters Hella 430 and Angela 450, and the optimal Activity information including skill sequences can be created. If the user request is a request for clearing the stage 5 (530) in difficulty in the shortest time, using the Hella 430 character to enter the stage and activity information including the optimal skill sequence and movement path of the Hella character Can be generated. The foregoing is only an example, and the present disclosure is not limited thereto.

According to the present disclosure, by varying the generation of activity information according to the stage, it is possible to generate activity information suitable for the stage difficulty, which has a great influence on the user playing the game. Accordingly, by providing appropriate activity information to the user even in various game environments, even a user who is unfamiliar with the game and is at risk of leaving the game can competently play the game, thereby maintaining or increasing the number of users enjoying the game play.

6A and 6B are exemplary diagrams for explaining an approximate value function according to an embodiment of the present disclosure.

6A shows the actual value function value 610 for a state and action pair. The computing device 100 may store an actual value function value 610 for all state and action pairs in the memory 130. The foregoing is only an example, and the present disclosure is not limited thereto.

6B shows an approximate value function value 751 for a state and action pair. In the graph of reference number 700, the x-axis may represent a state, an action pair, and the y-axis may represent a value function value. In the graph of reference number 700, reference number 710 may represent an actual value function value 610 for a state and action pair. Reference number 730 may represent a graph of an approximate value function. The computing device 100 may store only the parameter w 755, not the actual value function values 610 for all state and action pairs in the memory 130. The foregoing is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the approximate value function inputs the game state acquired from the activity log using the learned parameter w 755 to reduce the difference between the true value function and the approximate value function. It can contain a function that takes the actual value and calculates an approximate value. For example, if the approximate value function is f(x) = ax ⁴ +bx ³ + cx ² + dx + e, then x is the state, action pair, f(x) is the approximate value function value, a, b, c , d, e may be parameters included in parameter w755. The computing device 100 repeatedly updates the values of a, b, c, d, and e through the learning process (eg, updating using gradient descent) to provide an approximate value function value f(x) and an actual value function value. The difference can be reduced. Through this, the computing device 100 may obtain an approximate value function value through the parameter w 755 even if the value function values for all state and action pairs are not stored in the memory 130. The foregoing is only an example, and the present disclosure is not limited thereto.

There can be countless pairs of states and actions that can be entered into the game. For example, the state can be determined based on the number of skill sequences. When the number of skills is 100 and the length of the skill sequence is 10 ¹⁰ , the states may include 10 or ¹² states. In addition, there can be 10 or ¹⁰ actions including character's attack, defense, movement, and skill. In sum, there are 10 ²² pairs of states and actions, and the memory 130 may store 10 ²² value functions. The foregoing is only an example and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, by using the approximate value function, the computing device 100 stores parameters other than value function values for all states and action pairs in the memory 130 to achieve high storage space efficiency. I can. Therefore, due to the nature of the game in which there are many cases, reinforcement learning may be performed using large-scale data. When reinforcement learning is performed using large-scale data, desired activity information can be obtained in a short time using an approximate value function. The foregoing is only an example, and the present disclosure is not limited thereto.

In the game, there are numerous game states and numerous actions to choose from. According to the present disclosure, by using an approximate value function, it is possible to efficiently process a vast amount of game data to obtain activity information with a small amount of computation.

7 is a flowchart of a method of processing game data according to an embodiment of the present disclosure.

The computing device 100 may obtain (810) a game log.

The computing device 100 may extract (820) an activity log and a result log from the game log.

In an embodiment of the present disclosure, the activity log may include at least one of a character activity record, character information, or game environment information in a game.

In one embodiment of the present disclosure, the result log may include a record of a result caused by a character's activity in a game.

In an embodiment of the present disclosure, the activity information may include at least one of first activity information including the activity log or second activity information generated based on the activity log.

In an embodiment of the present disclosure, the activity information may include activity information determined based on the target information, and the target information may include a value determined based on a request from a user terminal.

The computing device 100 may acquire activity information 830 by inputting at least one of the activity log or the result log into an activity information generation model.

In an embodiment of the present disclosure, the activity information generation model may include a first sub-model including a probabilistic sequence model for obtaining first activity information.

In an embodiment of the present disclosure, the probabilistic sequence model may include a model that generates the activity information based on probability values of each of a plurality of activity patterns that are components included in the activity log.

In an embodiment of the present disclosure, the activity information generation model includes a second sub-model for obtaining second activity information, and the second sub-model for obtaining second activity information is based on the activity log Thus, a reinforcement learning model for acquiring the second activity information may be included.

In an embodiment of the present disclosure, the reinforcement learning model acquires the game state from the activity log, and obtains second activity information to derive predetermined result information by calculating the game state using the reinforcement learning model. It can include a model for doing.

In an embodiment of the present disclosure, the reinforcement learning model may include a model for obtaining second activity information using an approximate value function.

The computing device 100 may provide 840 activity information based on a request from the user terminal.

In an embodiment of the present disclosure, the approximate value function uses a parameter learned to reduce the difference between the real value function and the approximate value function, receives the game state obtained from the activity log, and calculates a value approximating the real value function. It may include a function to calculate.

According to the present disclosure, by providing the user with the first activity information included in the acquired activity log and the second activity information generated based on the acquired activity log, the user smoothly performs the game and does not leave the game. It can make you feel more interested in the game.

8 is a block diagram illustrating a module for processing game data according to an embodiment of the present disclosure.

Game data processing according to an embodiment of the present disclosure may be implemented by the following modules.

According to an embodiment of the present disclosure, a module 910 for obtaining a game log, a module 920 for extracting an activity log and a result log from the game log, and at least one of the activity log or the result log are activated. It may be implemented by a module 930 for obtaining activity information by inputting it into an information generation model and a module 940 for providing activity information based on a request from a user terminal.

In an alternative embodiment of processing game data, it may further include a module for generating result information based on the request of the user terminal. The result information may include information predicting a result of an activity of a character in a game based on the activity information.

In an alternative embodiment of game data processing, the module 940 for providing activity information based on the request of the user terminal causes the user to select at least one or more skills on the game screen of the user terminal based on the activity information. It may include a module for doing.

In an alternative embodiment of game data processing, it may further include a module for causing a character motion on the game based on the provided activity information.

According to an embodiment of the present disclosure, a module for processing game data may be implemented by means, circuits, or logic for implementing a computing device. Those of skill in the art would further describe the various illustrative logical blocks, configurations, modules, circuits, means, logics and algorithm steps described in connection with the embodiments disclosed herein, in electronic hardware, computer software, or combinations 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 restrictions imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

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

While the present disclosure has been described above as generally capable of being implemented by the computing device 100, those skilled in the art will find that the disclosure is combined with computer-executable instructions and/or other program modules that can be executed on one or more computers and/or It will be appreciated that it can be implemented as a combination of software and software.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Further, to those skilled in the art, the method of the present disclosure is not limited to single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable household appliances, and the like (each of which It will be appreciated that it may be implemented with other computer system configurations, including one or more associated devices).

The described embodiments of the present disclosure may also be practiced in a distributed computing environment where certain tasks are performed by remote processing devices that are connected through a communication 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. Computer-readable media can be any computer-readable media, including volatile and non-volatile media, transitory and non-transitory media, removable and non-transitory media. Includes 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 include volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Includes the medium. Computer-readable storage media include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage, 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 implement computer-readable instructions, data structures, program modules, or other data on a modulated data signal such as a carrier wave or other transport mechanism. Includes all information transmission media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal is set or changed to encode information in the signal. By way of example, and not limitation, computer-readable transmission media include 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, which includes a processing device 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to, system memory 1106 to processing device 1104. The processing unit 1104 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing unit 1104.

The system bus 1108 may be any of several types of bus structures that may be additionally interconnected to a memory bus, a peripheral bus, and a 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 non-volatile memory 1110 such as ROM, EPROM, EEPROM, etc. This BIOS is a basic input/output system that helps transfer information between components in the computer 1102, such as during startup. Includes routines. RAM 1112 may also include high speed RAM such as static RAM for caching data.

The computer 1102 also includes an internal hard disk drive (HDD) 1114 (e.g., 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 (for example, to read from or write to removable diskette 1118), and optical disk drive 1120 (for example, CD-ROM To read the disk 1122 or read from or write to other high-capacity optical media such as DVD). The hard disk drive 1114, the magnetic disk drive 1116 and the optical disk drive 1120 are each connected to the system bus 1108 by a hard disk drive interface 1124, a magnetic disk drive interface 1126, and an optical drive interface 1128, respectively. ) Can be connected. The interface 1124 for implementing an external drive includes at least one or both of USB (Universal Serial Bus) 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 description of the computer-readable medium above refers to a removable optical medium such as a HDD, a removable magnetic disk, and a CD or DVD, those skilled in the art may use a zip drive, a magnetic cassette, a flash memory card, a cartridge, etc. It will be appreciated that other types of computer-readable media, such as the like, may also be used in the exemplary operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

A number of program modules, including the operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136, may be stored in the drive and RAM 1112. 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 may be implemented on a number of commercially available operating systems or combinations of operating systems.

A user may input commands and information to the computer 1102 through one or more wired/wireless input devices, for example, a pointing device 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, and the like. These and other input devices are often connected to the processing unit 1104 through the input device interface 1142, which is connected to the system bus 1108, but the parallel port, IEEE 1394 serial port, game port, USB port, IR interface, It can be connected by other interfaces such as etc.

A 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, etc.

Computer 1102 may 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, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other common network node, and is generally connected to the computer 1102. Although it includes many or all of the components described for simplicity, only memory storage device 1150 is shown. The logical connections shown include wired/wireless connections to a local area network (LAN) 1152 and/or to a larger network, eg, a wide area network (WAN) 1154. Such LAN and WAN networking environments are common in offices and companies, and facilitate an enterprise-wide computer network such as an intranet, all of which can be connected to a worldwide computer network, 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. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed therein to communicate with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158, connected to a communications computing device on the WAN 1154, or through the Internet, to establish communications over the WAN 1154. Have other means. Modem 1158, which may be an internal or external and a 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 communication links between computers may be used.

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

Wi-Fi (Wireless Fidelity) allows you to connect to the Internet, etc. without wires. Wi-Fi is a wireless technology such as a cell phone that allows such devices, for example computers, to transmit and receive data indoors and outdoors, ie anywhere within the coverage area of a base station. 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 a data rate of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band). .

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

A person of ordinary skill in the art of the present disclosure includes various exemplary logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein, electronic hardware, (convenience). For the sake of clarity, it will be appreciated that it may be implemented by various types of programs or design code or a combination of both (referred to herein as software). To clearly illustrate this interchangeability 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. A person of ordinary skill in the art of the present disclosure may implement the described functions in various ways for each specific application, but such implementation decisions should not be interpreted as being outside the scope of the present disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CD, DVD, etc.), smart cards, and flash Memory devices (eg, EEPROM, cards, sticks, key drives, etc.), but are not limited thereto. In addition, the various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. Based on the design priorities, it is to be understood that within the scope of the present disclosure a specific order or hierarchy of steps in processes may be rearranged. The appended 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.

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

Claims (16)

A computer program stored in a computer-readable storage medium, wherein the computer program performs the following operations for processing game data when executed on one or more processors, the operation comprising:
Obtaining a game log;
Extracting an activity log and a result log from the game log;
Inputting at least one of the activity log or the result log into an activity information generation model to obtain activity information; And
Providing activity information based on the request of the user terminal;
Containing,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
The activity log,
Including at least one of a character's activity record, character information, or game environment information on the game,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
The result log is,
Containing a record of the consequences of a character's activity in the game,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
The above activity information,
Including at least one of first activity information including the activity log or second activity information generated based on the activity log,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
The above activity information,
Determined based on the target information received from the user terminal,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
Generating result information based on the request of the user terminal;
Including more,
The result information is,
Including information predicting a result of the activity of the character in the game based on the activity information,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
The activity information generation model,
Including a first sub-model including a probabilistic sequence model for obtaining the first activity information,
A computer program stored on a computer-readable storage medium.
The method of claim 7,
The probabilistic sequence model,
A model that generates the activity information based on probability values of each of a plurality of activity patterns that are components included in the activity log,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
The activity information generation model,
Including a second sub-model for obtaining second activity information,
The second sub-model for obtaining the second activity information,
Including a reinforcement learning model for obtaining second activity information based on the activity log,
A computer program stored on a computer-readable storage medium.
The method of claim 9,
The reinforcement learning model,
Comprising a model for acquiring a game state from the activity log, and obtaining second activity information to derive predetermined result information by calculating the game state using a reinforcement learning model,
A computer program stored on a computer-readable storage medium.
The method of claim 9,
The reinforcement learning model,
Including a model for obtaining second activity information using an approximate value function (value function approximator),
A computer program stored on a computer-readable storage medium.
The method of claim 11,
The approximate value function,
Including a function that calculates an approximate value to the actual value function by receiving the game state obtained from the activity log using parameters learned to reduce the difference between the true value function and the approximate value function,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
The operation of providing the activity information based on the request of the user terminal,
Causing a user to select at least one skill based on the activity information on the game screen of the user terminal;
Containing,
A computer program stored on a computer-readable storage medium.
The method of claim 1,
Causing a character motion in the game based on the provided activity information;
Further comprising,
A computer program stored on a computer-readable storage medium.
Game data processing method,
Obtaining a game log;
Extracting an activity log and a result log from the game log;
Obtaining activity information by inputting at least one of the activity log or the result log into an activity information generation model; And
Providing activity information based on the request of the user terminal;
Containing,
How to process game data.
A computing device for processing game data, comprising:
One or more processors; And
A memory storing instructions executable in the one or more processors;
Including,
The one or more processors,
Get the game log,
Extracting the activity log and result log from the game log,
Acquiring activity information by inputting at least one of the activity log or the result log into an activity information generation model, and
Providing activity information based on the request of the user terminal
A computing device for processing game data.

Images