KR20200029923A - Method for processing user's data for game on computing devices and computing devices - Google Patents

Abstract

The present invention relates to a method for processing user data about a game in a computing device and a computing device. The purpose of the present invention is to learn log data of multiple users about a game with regard to a standard determining an engagement level of the game based on machine learning and provide engagement index information indicating the engagement level of the game about the multiple users by using a learning result. A method for operating a computing device includes: a step of obtaining the log data including action information of the multiple users about a first game; a step of learning the actions of multiple users through machine learning in regard with at least one standard used to determine the engagement level of the first game based on the action information of the multiple users extracted from the log data; a step of determining an engagement index indicating the engagement level about the first game of the multiple users based on the learning result; and a step of providing the engagement index in accordance with a predetermined category.

Description

A method of processing a user's data for a game on a computing device, and a computing device {METHOD FOR PROCESSING USER'S DATA FOR GAME ON COMPUTING DEVICES AND COMPUTING DEVICES}

A method of processing a user's data for a game on a computing device, and a computing device.

The type and amount of data that can be obtained from a given game is vast. For example, various data related to the game, such as the number of concurrent users of the game for a given game and information about purchasing items in the game, may be used for game development or marketing. Therefore, there is a need for a technique capable of processing data obtained from a given game more quickly and analyzing accurately.

Learning the log data of multiple users for a game in association with a criterion used to determine the immersion level of a game based on machine learning, and using the learning result to indicate the immersion level of the game for multiple users I would like to provide information on the Easy Index.

According to one side, obtaining log data including behavior information of a plurality of users for the first game; Based on the behavior information of the plurality of users extracted from the log data, the behaviors of the plurality of users are associated with at least one criterion used to determine the immersion level of the first game through machine learning. Learning; Determining an engagement index representing the immersion degree of the plurality of users for the first game based on a learning result; And providing the engagement index according to a predetermined category.

The learning of the actions of the plurality of users in association with the at least one criterion may include: performing operations through an artificial neural network to learn each of the actions of the plurality of users; And training the artificial neural network to determine whether each of the plurality of user actions is a significant action used to determine the immersion level of the first game, and is determined as a significant action based on the at least one criterion. And determining an immersion level of the first game for a predetermined action of a predetermined user.

Determining the degree of immersion of the first game with respect to a predetermined action of a predetermined user determined as a meaningful action based on the at least one criterion includes: determining a predetermined action of the predetermined user as a significant action; According to one criterion, it may include quantifying a predetermined behavior of the predetermined user.

Determining the immersion degree of the first game with respect to a predetermined action of a predetermined user determined as a meaningful action based on the at least one criterion includes: a first user's first action related to the first action of the first user determined as a meaningful action 2 detecting an action; And the result of determining whether the second action of the first user is a meaningful action used to determine the immersion level of the first game, immersing the first game in relation to the first action of the first user. And determining the degree.

The at least one criterion includes: a criterion for calculating immersion according to a user's connection duration, a criterion for calculating immersion according to a user's number of connections, a criterion for calculating immersion according to a cache used by a user in a game, and an in-game In may include at least one of the calculation criteria according to the user's activity.

The learning of the actions of the plurality of users in association with the at least one criterion may include determining an immersion level of the first game for each of the actions of the plurality of users based on the at least one criterion. Including, The step of determining the engagement index, Based on the learning result, determining a weight between items corresponding to each of the at least one criterion; And determining an engagement index of each of the plurality of users by applying weights between the items to the immersion of the first game for each of the actions of the plurality of users.

According to the predetermined category, the step of providing the engagement index may include displaying information corresponding to the predetermined category for each section of the engagement index.

According to the predetermined category, the providing of the engagement index may include: receiving a selection of a first category that is a reference for classifying the engagement index; And acquiring and displaying the engagement index for each detailed item in the first category.

The displaying of the engagement index for each detailed item in the first category may include displaying the number of the plurality of users and the engagement index corresponding to the plurality of users for each detailed item; And displaying an average engagement index for the plurality of users for each of the detailed items.

Providing the engagement index according to the predetermined category may include transmitting information on the engagement index classified according to the predetermined category to an external device managing the first game. have.

According to another side, the communication device; User interface devices; storage; Processor; And a memory for storing instructions executable by the processor, wherein the processor obtains log data including behavior information of a plurality of users for the first game by executing the instructions, and from the log data Based on the extracted behavior information of the plurality of users, the behaviors of the plurality of users are learned through machine learning in association with at least one criterion used to determine the immersion level of the first game, and learning Based on a result, a computing device for determining an engagement index indicating the immersion degree of the plurality of users for the first game, and displaying the engagement index on the user interface device according to a predetermined category Is provided.

According to another aspect, obtaining the log data including the behavior information of a plurality of users for the first game; Based on the behavior information of the plurality of users extracted from the log data, the behaviors of the plurality of users are associated with at least one criterion used to determine the immersion level of the first game through machine learning. Learning; Determining an engagement index representing the immersion degree of the plurality of users for the first game based on a learning result; And providing the Engagement Index according to a given category. A computer program stored in a medium is provided for executing a method in combination with hardware.

The computing device learns log data of a plurality of users for the game in association with a criterion used to determine the immersion level of the game based on machine learning, and uses the learning result to immerse the game for a plurality of users. It can provide information about the engagement index.

The computing device may provide engagement index information according to a predetermined category. In addition, the computing device may provide engagement index information for each predetermined period.

The computing device may provide engagement index information corresponding to a predetermined category for each section of the engagement index.

The present disclosure can be easily understood by the following detailed description and combinations of the accompanying drawings, and reference numerals refer to structural elements.
1 illustrates an online game providing system including a server and a client, according to an embodiment.
2 is a flowchart illustrating a method of operating a computing device according to an embodiment.
3 is a diagram schematically showing an artificial neural network having a plurality of hierarchical structures, which is used when a computing device processes logo data of a plurality of users, according to an embodiment.
4 is a diagram for explaining a process in which a computing device learns each of a plurality of actions of a plurality of users for a first game and determines an immersion level of the first game.
FIG. 5 is a diagram for explaining a process in which a computing device learns by correlating related activities.
6 is a diagram for explaining a process in which a computing device acquires an engagement index according to an embodiment.
FIG. 7 is a diagram for explaining a process in which a computing device provides an engagement index indicating the immersion degree of a first game for a given user.
8 is a diagram for describing a process in which a computing device provides an engagement index according to a predetermined category, according to an embodiment.
9 is a diagram for explaining a process in which a computing device provides a departure rate and a residual rate of a first game for each section of an engagement index, according to an embodiment.
10 is a diagram for explaining a process in which a computing device provides an engagement index according to the number of users according to an embodiment.
11 is a block diagram illustrating a configuration of a computing device according to an embodiment.

Hereinafter, various embodiments will be described in detail with reference to the drawings. The embodiments described below may be implemented by being modified in various different forms. In order to more clearly describe the features of the embodiments, detailed descriptions of the items well known to those of ordinary skill in the art to which the following embodiments belong will be omitted.

Meanwhile, in the present specification, when a component is "connected" to another component, this includes not only a case of 'directly connecting', but also a case of 'connecting with other components in between'. In addition, when it is said that a configuration "includes" another configuration, this means that other configurations may be included, not excluded, unless otherwise stated.

In addition, terms including an ordinal number such as 'first' or 'second' used in the present specification may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from other components.

Throughout the specification, "computing device" may mean a device that performs a function of inputting, controlling, storing, calculating, and outputting data or information of a game application. For example, “computing device” may be a special-purpose computer, a general-purpose computer, a supercomputer, a mainframe computer, or a personal computer. May be, but is not limited to.

Throughout the specification, the user's "log data" for a given game may be data that includes records of the user's activity within the given game. For example, in "log data", a record of a user logging into a given game, a record of a user purchasing an item in a given game, a record of a user playing within a given game, a record of a user logging out of a given game Information or data on the like may be included.

Throughout the specification, "machine learning" may refer to a technique for performing learning based on data about a game, performing prediction, and researching and constructing an algorithm for a system or a system that improves one's performance.

Throughout the specification, "engagement index" may mean an index indicating a user's immersion in a given game.

1 illustrates an online game providing system including a server and a client, according to an embodiment.

The online game providing system according to an embodiment may include a server 4000 and a plurality of clients 2000a, 2000b, 2000c, 2000d, 2000e, and 2000f, as shown in FIG. 1. The server 4000 can provide content to a plurality of clients 2000a, 2000b, 2000c, 2000d, 2000e, and 2000f by serving the content through a network.

1 is an example of a client used by a user, showing a desktop computer 2000a, a tablet 2000b, a mobile phone 2000c, a laptop 2000d, a smartphone 2000e, and a television 2000f, but the client Is not limited thereto, and may include various electronic devices such as PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), navigation, MP3 players, digital cameras, refrigerators, washing machines, and cleaners.

Content (eg, online games) can be executed on multiple clients (2000a, 2000b, 2000c, 2000d, 2000e, and 2000f). In order to execute the content, a program, for example, an application, or a launcher can be installed on clients 2000a, 2000b, 2000c, 2000d, 2000e, and 2000f, but is not limited thereto. Users can run the programs installed on the clients 2000a, 2000b, 2000c, 2000d, 2000e, and 2000f to enjoy the content provided by the server 4000. Various embodiments of the present disclosure described below may be implemented in a program for executing content, or may be implemented through a program separate from the program.

The server 4000 may be operated by a content provider, and the server 4000 may include, but is not limited to, a single server, a collection of servers, and a cloud server. The server 4000 may include a database that provides content to users and stores data of users. In addition, the server 4000 may further include a payment server or payment server that generates and processes payment events. The payment server or payment server may be a separate server from the server 4000 and may mediate payment or payment between the server 4000 and clients 2000a, 2000b, 2000c, 2000d, 2000e, and 2000f. The server 4000 may further include a database (DB) server for storing and managing user data, and the DB server may be a server separate from the server 4000.

In the server 4000, a program for servicing content may be driven. Various embodiments of the present disclosure described below may be implemented in a program for servicing content, or may be implemented through a program separate from the program.

A network means a connection established (or formed) using a predetermined communication method, and between clients 2000a, 2000b, 2000c, 2000d, 2000e, and 2000f, or clients 2000a, 2000b, 2000c, 2000d, 2000e. , And 2000f) and a server 4000 through a predetermined communication means for transferring data.

Communication means include communication through a predetermined communication standard, a predetermined frequency band, a predetermined protocol or a predetermined channel, short-range communication, telecommunication, wireless communication, and wired communication. For example, the communication means may include Bluetooth, BLE, Wi-Fi, Zigbee, 3G, LTE, communication means through ultrasound, and the like, but is not limited thereto.

The short-range communication means may mean a communication means capable of communicating with each other only when devices performing communication are within a predetermined range, and may include, for example, Bluetooth and NFC, but are not limited thereto.

The long-distance communication means may mean a communication means through which devices performing communication can communicate with each other regardless of a distance. For example, the long-distance communication means uses a means capable of communicating even when two devices performing communication through a repeater such as an AP are over a predetermined distance, and a cellular network (3G, LTE) used for text transmission and phone calls. Communication means may be included, but is not limited thereto.

In the process of the server 4000 serving an online game using a network, communication between the server 4000 and the clients 2000a, 2000b, 2000c, 2000d, 2000e, and 2000f may be performed through any communication means. have.

Online games include RPG (Role Playing Game), TRPG (Tabletop RPG), MMORPG (Massively Multiplayer Online RPG), MOBA (Multiplayer Online Battle Arena), AOS (Aeon of Strife), RTS (Real Time Strategy), FPS (First- Person shooter), TCG (Trading Card Game), CCG (Collectible Card Game), sports, can be a game of various genres such as fighting, but is not limited thereto. The online game may be played through a battle between users or a battle between a user and a computer (for example, artificial intelligence), but is not limited thereto, and may be implemented in various forms.

The online game providing system shown in FIG. 1 can also function as an online platform providing system. Meanwhile, the server 4000 illustrated in FIG. 1 may correspond to the computing device 10 described with reference to FIGS. 2 to 11.

2 is a flowchart illustrating a method of operating a computing device according to an embodiment.

In step S210 of FIG. 2, the computing device 10 may obtain log data including behavior information of a plurality of users for the first game.

In step S220, the computing device 10 may extract behavior information of a plurality of users from log data. The computing device 10 may learn, through machine learning, a plurality of actions included in action information of a plurality of users in association with at least one criterion used to determine the immersion level of the first game.

For example, at least one criterion includes: a criterion for calculating immersion according to a user's connection duration, a criterion for calculating immersion according to a user's number of accesses, a criterion for calculating immersion according to a cache used by a user in a game, And it may include at least one of the calculation criteria according to the user's activity in the game, it is not limited to the above example.

Specifically, the computing device 10 may perform operations through an artificial neural network to learn each of a plurality of user actions. The computing device 10 may train an artificial neural network to determine whether each of a plurality of user actions is a meaningful action used to determine the immersion level of the first game. The computing device 10 may determine the immersion degree of the first game for a predetermined action of a predetermined user determined as a meaningful action based on at least one criterion.

In addition, the computing device 10 may quantify a predetermined action of a predetermined user according to a first criterion corresponding to a factor that determines a predetermined action of a predetermined user as a meaningful action. Here, "quantification" may mean that a predetermined action of a given user is numerically represented.

Also, the computing device 10 may detect the second behavior of the first user related to the first behavior of the first user determined as a meaningful behavior. The computing device 10 may determine whether the second action of the first user is a meaningful action used to determine the immersion level of the first game. If the second action is determined to be a meaningful action, the computing device 10 determines the immersion level of the first game with respect to the first action of the first user based on a criterion corresponding to a factor in which the second action is determined to be a meaningful action. You can.

In addition, the computing device 10 may determine the immersion degree of the plurality of users for the first game by applying the behavior information of the plurality of users to a predetermined learning model. Here, the predetermined learning model may be a model trained using information about a plurality of users' behavior and at least one criterion used to determine the immersion level of the first game.

The computing device 10 performs an operation through an artificial neural network to learn behavior information of a plurality of users and information about at least one criterion used to determine the immersion level of the first game, and to learn the result. On the basis of this, a learning model for determining the user's immersion in the first game may be prepared.

Further, the learning model may be a data recognition model used to determine the user's immersion in the first game. The data recognition model may be a model obtained through deep learning built on an artificial neural network (ANN). For example, the learning model may be a model such as a deep neural network (DNN), a recurrent neural network (RNN), or a bidirectional recurrent deep neural network (BRDNN), but is not limited thereto.

Also, the computing device 10 may determine the immersion degree of the first game for each of the actions of the plurality of users based on at least one.

On the other hand, the computing device 10 can acquire the game immersion of the user more quickly and accurately by applying and processing a large amount of log data of a plurality of users to the learned results.

In step S230, the computing device 10 may determine an engagement index indicating the immersion degree of the plurality of users for the first game based on the learning result.

The computing device 10 may determine a weight between items corresponding to each of the at least one criterion based on the learning result. The computing device 10 may determine the engagement index of each of the plurality of users by applying weights between items to the immersion of the first game for each of the actions of the plurality of users.

In operation S240, the computing device 10 may provide an engagement index according to a predetermined category.

The computing device 10 may display information corresponding to a predetermined category for each section of the engagement index.

In addition, the computing device 10 may receive a selection of a first category that is a basis for classifying an engagement index. The computing device 10 may obtain an engagement index for each detailed item in the first category. The computing device 10 may display an engagement index.

Specifically, the computing device 10 may display the number of the plurality of users and the engagement index corresponding to the plurality of users for each detailed item. Also, the computing device 10 may display an average engagement index for a plurality of users for each detailed item.

The computing device 10 may transmit information on an engagement index classified according to a predetermined category to an external device managing the first game.

Meanwhile, the engagement index information for a given game generated by the computing device 10 may be used for development or marketing of a given game.

3 is a diagram schematically showing an artificial neural network having a plurality of hierarchical structures, which is used when a computing device processes logo data of a plurality of users, according to an embodiment.

Referring to FIG. 3, the artificial neural network may include an input layer 310, at least one hidden layer 320, 330 and an output layer 340. In addition, computation through an artificial neural network may be performed on a processor in computing device 10.

In addition, the weight between each layer and the node may be learned through learning and training performed in the hidden layers 320 and 330. For example, the processor in the computing device 10 may obtain values of weights of items of each category in at least one criterion, which are applied to determine the immersion degree of each of a plurality of user's actions through repetitive learning. Can be obtained.

In addition, the computing device 10 applies the value of the obtained weight to the index corresponding to the items of each category in at least one criterion again to determine the user's immersion in the trained artificial neural network for the first game. Can create a learning model.

4 is a diagram for explaining a process in which a computing device learns each of a plurality of actions of a plurality of users for a first game and determines an immersion level of the first game.

The computing device 10 may obtain log data including behavior information of a plurality of users for the first game. For example, as illustrated in FIG. 4, the computing device 10 may acquire log data 401 of the first user and log data 402 of the second user. The computing device 10 may acquire log data of users other than the first user and the second user. For convenience of description, FIG. 4 will be described using log data 401 of the first user and log data 402 of the second user as examples.

Referring to operation 410 of the computing device 10, the computing device 10 may perform operations through an artificial neural network and learn each of the actions of the plurality of users based on log data of the plurality of users.

Referring to FIG. 4, the computing device 10 may extract information of actions performed by the first user in the first game within the log data 401 of the first user. For example, the computing device 10 may extract information about the first action, the second action, and the third action of the first user. Based on the extracted behavior information of the first user, the computing device 10 is configured to operate within a predetermined time interval, the time the first user logged in to the first game, the time logged out, the duration of accessing the first game, and the like. It is possible to distinguish and learn each of the behaviors related to the number of times the game is accessed, the specific activity of the first user in the first game, and the cache used by the first user in the first game.

The computing device 10 may learn each of the actions of the first user in association with at least one criterion used to determine the immersion level of the first game. For example, the computing device 10 may determine whether each of the actions of the first user is related to a criterion for connection used to determine the immersion of the first game. The computing device 10 may learn, if a predetermined action is related to a criterion for a connection, if the predetermined action is associated with items within a criterion for the connection.

Referring to operation 420 of the computing device 10, the computing device 10 trains an artificial neural network to determine whether each of a plurality of user actions is a significant action used to determine the immersion level of the first game. You can.

For example, the computing device 10 is immersed in the first game by the first action of the first user indicating "logging in to the first game at OO month OO day, OO hour, OO level increase for 1 hour" It may be determined that it is related to "access" and "achievement", which are criteria used to determine the degree, and the first action of the first user may be determined as a meaningful action.

In addition, the computing device 10 determines the immersion degree of the first game by the second action of the first user indicating "purchase the first item by logging in to the first game on OO month OO day, OO hour XX". It is possible to determine that it is related to the "access" and "cache", which are the criteria used to use it, and the second action of the first user may be determined as a meaningful action.

In addition, the computing device 10 determines that the third action of the first user indicating "logging in to the first game on OO month OO day, XX hour YY, event participation" determines the immersion level of the first game. It may be determined that the criteria used are "connection", "achievement" and "community", and the third action of the first user may be determined as a meaningful action.

Referring to operation 430 of the computing device 10, the computing device 10 may determine the immersion level of the first game for a predetermined action of a predetermined user determined as a meaningful action based on at least one criterion. Specifically, the computing device 10 may quantify a predetermined behavior of a given user according to a first criterion corresponding to a factor that determines a predetermined behavior of a given user as a meaningful behavior.

For example, the at least one criterion may include a criterion for calculating immersion according to game access, a criterion for calculating immersion according to achievement in the game, a criterion for calculating cache in the game, a criterion for calculating according to community, and the like. , Other calculation criteria.

Specifically, the standard for calculating immersion according to game access is charged 0.1 every time a connection is made, 0.5 point is charged if the number of connections is 5 or more in 24 hours, 0.2 point is charged if the connection duration is 2 hours or more, etc. It may include the same criteria, but is not limited to the above example.

The standard for calculating immersion according to the achievements in the game is 0.1 points for every 1 level increase in the game, 0.1 points for each battle win, 0.1 points for each stage achievement, Each increase of 1 type may include criteria such as 0.1 point charge, 0.1 point charge when participating in an in-game event, and the like.

The calculation criteria according to the cache in the game may include a criterion such as 0.5 points charged when the cache used at the time of one game connection exceeds a predetermined cache, and 0.1 points charged for each item purchased, etc. Does not work.

The calculation criteria according to the community may include a score charging criterion according to the number of posts and comments left on the bulletin board in the game, a scoring criterion based on participation in events in the game, and the like.

For example, the computing device 10 may determine the immersion of the first game according to at least one criterion for each first user's action. 0.6 points may be imposed on the first action of the first user by increasing the level 5 once per connection. 0.2 points may be imposed on the second act of the first user through one access and one item purchase. The third act of the first user may be charged 0.3 points for one access and participation in the event. In addition, the computing device 10 may determine the immersion degree of the first game of the first user by summing the immersion degree of the first game calculated for each first user's action.

Meanwhile, the computing device 10 repeatedly learns each of the behavior information of the plurality of users in operation 410 to operation 430, and generates a learning model that determines the user's immersion in the first game based on the learned results. can do.

FIG. 5 is a diagram for explaining a process in which a computing device learns by correlating related activities.

The computing device 10 may consider the influence of other actions related to the predetermined action on the predetermined action in determining the immersion degree of the first game for the predetermined action of the predetermined user.

Specifically, the computing device 10 may detect a second action of the predetermined user related to the first action of the predetermined user determined as a meaningful action. The computing device 10 is immersed in the first game with respect to the first behavior of the predetermined user based on the result of determining whether the second behavior of the predetermined user is a meaningful behavior used to determine the immersion in the first game Can decide.

For example, the computing device 10 extracts action information including the first action 501, the second action, and the third action 502 of the first user from the log data 401 of the first user. You can. The computing device 10 may use the result learned through the artificial neural network to determine that the third action 502 of the first user is related to the first action 501 of the first user.

Referring to a specific process, the computing device 10 may acquire a condition in which the first user must play the first game in order to participate in the event of the first game. Since the computing device 10 performed the first action 501 on the same date before the third action 502 was performed, the third action 502 may affect the first action 501. Can decide. That is, the computing device 10 may determine that the third action 502 of the first user can reduce the engagement index indicating the immersion degree of the first action 501 of the first user.

The computing device 10 represents the immersion degree of the first action 501 of the first user by considering the third action 502 of the first user affecting the first action 501 of the first user The Engagement Index can be calculated more precisely.

6 is a diagram for explaining a process in which a computing device acquires an engagement index according to an embodiment.

Referring to the table 610 of FIG. 6, the computing device 10 may determine the immersion degree of the first game according to at least one criterion for each first user's action. As described above as examples, at least one criterion may include a calculation criterion for immersion according to game access, a calculation criterion for immersion based on achievements in the game, a calculation criterion for cache in game, and a calculation criterion according to community. You can. That is, items of at least one criterion may include access, achievement, cache, and community.

In the first act of the first user, 0.1 point may be imposed on the "access" item once per connection, and 0.5 point may be imposed on the "achievement" item by increasing the level 5. In the second act of the first user, 0.1 points may be imposed on the "access" item once per connection and 0.1 points on the "cache" item by purchasing one item. In the third act of the first user, 0.1 points may be imposed on each of the "access" item and the "achievement" item and "community" item by participating in the event.

Meanwhile, the computing device 10 may determine the weight of each item used when determining the engagement index based on the relationship between items corresponding to each of the at least one criterion. The computing device 10 may determine an engagement index by applying a weight of each item.

Referring to Equation 620 of FIG. 6, the computing device 10 may determine an engagement index for each first user's action. Explaining the meaning of the characters used in the equation, Yab represents the engagement index for the b-th action of the a-th user. Wn represents the weight for the n-th item of the criterion used to determine the immersion level of the game. Xabc represents the index of the item c in the criterion for the action b of the user a.

For example, the computing device 10 multiplies the weight (W1) of the "access" item by the index (X111) of the "access" item of the first action, the weight (W2) of the "achievement" item and the first action Multiplied by the exponent (X112) of the "achievement" item, the weight (W3) of the "cache" item multiplied by the exponent (X113) of the "cache" item of the first action, and the weight of the "community" item (W4) ) And a value multiplied by the index (X114) of the “community” item of the first action, to determine the engagement index (Y11) of the first action of the first user.

Referring to Equation 630 of FIG. 6, the computing device 10 may determine an engagement index for each item of the behavior of the first user. Explaining the meaning of the characters used in the equation, Zab represents the engagement index for the b item of the a user. Wn represents a weight for the n-th item of the criterion used to determine the immersion level of the game. Xabc represents the index of the item c in the criterion for the action b of the user a.

For example, the computing device 10 multiplies the weight (W1) of the "connection" item by the exponent (X111) of the "connection" item of the first action, the weight (W1) of the "connection" item and the second action The value multiplied by the exponent (X121) of the "access" item of and the multiplied by the weight (W1) of the "access" item and the multiplied by the exponent (X131) of the "access" item of the third action, the first user's " Connection "Engagement Index can be determined.

Referring to Equation 640 of FIG. 6, the computing device 10 may determine the engagement index of the first user. Explaining the meaning of the characters used in the equation, Ya represents the engagement index of the a user. Yab represents the engagement index for the b-th action of the a-th user.

For example, the computing device 10 may determine the engagement index of the first user by summing the engagement index for each of the first user's actions calculated through the equation 620.

In FIG. 6, a process in which the computing device 10 determines an engagement index is an example, and the computing device 10 may determine an engagement index by another process.

FIG. 7 is a diagram for explaining a process in which a computing device provides an engagement index indicating the immersion degree of a first game for a given user.

Referring to the graph 710 of FIG. 7, the computing device 10 may display an engagement index corresponding to each item of criteria used to determine the immersion level of the first game for a given user. have. For example, the computing device 10 may display an engagement index corresponding to the “Access” item, “Achievement” item, “Cache” item, and “Community” item. The computing device 10 may receive an input for selecting an “achievement” item from among the “access” item, “achievement” item, “cache” item, and “community” item.

Referring to the image 720 of FIG. 7, as the computing device 10 receives an input for selecting an “achievement” item, the computing device 10 engages corresponding to sub-items within the “achievement” item. You can get an index. The computing device 10 may obtain an engagement index corresponding to each of the “level” item, “win rate” item, “ranking” item, and “item” item. The computing device 10 may display the obtained engagement index.

8 is a diagram for describing a process in which a computing device provides an engagement index according to a predetermined category, according to an embodiment.

Referring to the graph 810 of FIG. 8, the computing device 10 may receive an input for selecting a category that is a criterion for classifying an engagement index. For example, computing device 10 may receive an input to select "character". The computing device 10 may acquire and display an engagement index for each "character" in the first game.

Specifically, the computing device 10 may classify each of the plurality of users for each character, and sum the engagement index corresponding to each of the plurality of users for each character based on the classified result. For example, the computing device 10 may determine the engagement index of the first character by adding up the engagement index for the user using the first character.

Referring to the graph 820 of FIG. 8, the computing device 10 may display an engagement index classified according to a predetermined category according to a period. For example, the computing device 10 may display an engagement index for each character at weekly intervals. Also, the computing device 10 may display trend information in which the engagement index is changed. In this case, the computing device 10 may display information on the character with the largest change in the Engagement Index, and information on the character with the smallest change in the Engagement Index, based on a predetermined period.

9 is a diagram for explaining a process in which a computing device provides a departure rate and a residual rate of a first game for each section of an engagement index, according to an embodiment.

The computing device 10 may display information corresponding to a predetermined category for each section of the engagement index. For example, as illustrated in the graph 910 of FIG. 9, the computing device 10 may display information of the departure rate and the residual rate with the engagement index at 0.2 intervals.

10 is a diagram for explaining a process in which a computing device provides an engagement index according to the number of users according to an embodiment.

The computing device 10 may display the number of users and the engagement index corresponding to the plurality of users for each detailed item. Also, the computing device 10 may display an average engagement index for a plurality of users for each detailed item.

Referring to the graph 1010 of FIG. 10, the computing device 10 may display an engagement index according to the level of the user of the first game. The computing device 10 may display the number of users belonging to each level and the user's engagement index. For example, the engagement index of the first level may be a sum of the engagement index of each user belonging to the first level.

Also, referring to the graph 1010 of FIG. 10, the computing device 10 may display an average engagement index according to a user's level of the first game. For example, the computing device 10 may determine the average engagement index of the first level by dividing the number of users belonging to the first level from the sum of each user's engagement index belonging to the first level. . As shown in the graph 1010 of FIG. 10, the computing device 10 may display the average index of each level superimposed on the level of the index of each level.

11 is a block diagram illustrating a configuration of a computing device according to an embodiment.

The computing device 10 illustrated in FIG. 11 may include a communication device 1110, a user interface device 1120, a storage 1130, a memory 1140, and a processor 1150. However, the illustrated component mode is not required. The computing device 10 may be implemented by more components than the illustrated components, and the computing device 10 may also be implemented by fewer components. Hereinafter, the components will be described. The computing device 10 illustrated in FIG. 11 may correspond to the server 4000 described with reference to FIG. 1.

The communication device 1110 may communicate with an external device. Specifically, the communication device 1110 may be connected to a network by wire or wirelessly to perform communication with an external device. Here, the external device may be a server, a smartphone, a tablet, or a PC. The communication device 1110 may include a communication module supporting one of various wired and wireless communication methods. For example, the communication module may be in the form of a chipset, or may be a sticker / barcode (e.g. a sticker including an NFC tag) containing information necessary for communication. Further, the communication module may be a short-range communication module or a wired communication module.

For example, the communication device 1110 is a wireless LAN (Wireless LAN), Wi-Fi (Wireless Fidelity), WFD (Wi-Fi Direct), Bluetooth (Bluetooth), Bluetooth Low Energy (BLE), Wired Lan, NFC ( It can support at least one of Near Field Communication (Zigbee), infrared data association (IrDA), 3G, 4G, and 5G.

The user interface device 1120 may mean a device that receives data to control the computing device 10 from a user. The processor 1150 may control the user interface device 1120 to generate and output a user interface screen for receiving a predetermined command or data from the user. The user interface device 1120 is an input unit for receiving an input for controlling the operation of the computing device 10 and information such as a result of the operation of the computing device 10 or a state of the computing device 10. It may include an output. For example, the user interface device 1120 may include an operation panel receiving a user input, a display panel displaying a screen, and the like.

Specifically, the input unit may include devices capable of receiving various types of user input, for example, a keyboard, a physical button, a touch screen, a camera, or a microphone. Also, the output unit may include, for example, a display panel or a speaker. However, the present invention is not limited thereto, and the user interface device 1120 may include a device supporting various input / output.

The user interface device 1120 may display engagement index information indicating the immersion degree of the game for a plurality of users. For example, the user interface device 1120 may display engagement index information according to a predetermined category. Also, the user interface device 1120 may display engagement index information for each predetermined period. The user interface device 1120 may display engagement index information corresponding to a predetermined category for each section of the engagement index.

The storage 1130 may store information related to programs, applications, and the like used by the computing device 10 to determine the immersion of the game. The storage 1130 may store programs, applications, and various data used on the platform executed on the computing device 10.

The storage 1130 learns each of the actions of the plurality of users based on the log data of the plurality of users in the computing device 10 and uses each of the actions of the plurality of users to determine the immersion level of the game. It can store the results of learning in connection with at least one of the criteria.

The memory 1140 may store software or programs. The memory 1140 stores at least one program for executing a method of determining an engagement index of a predetermined game of a plurality of users by learning each of the plurality of user actions of the game on the computing device 10. You can. At least one program stored in the memory 1140 may be classified into a plurality of modules according to functions.

The processor 1150 controls the overall operation of the computing device 10, and may include at least one processor such as a CPU. The processor 1150 may include at least one specialized processor corresponding to each function, or may be a processor integrated into one.

The processor 1150 may execute a program stored in the memory 1140, read data or a file stored in the memory 1140, or store a new file in the memory 1140. The processor 1150 may execute instructions stored in the memory 1140.

The processor 1150 may obtain log data including behavior information of a plurality of users for the first game.

The processor 1150 may extract behavior information of a plurality of users from log data. The processor 1150 may learn, through machine learning, each of a plurality of actions included in action information of a plurality of users in association with at least one criterion used to determine the immersion level of the first game. .

For example, at least one criterion includes: a criterion for calculating immersion according to a user's connection duration, a criterion for calculating immersion according to a user's number of accesses, a criterion for calculating immersion according to a cache used by a user in a game, And it may include at least one of the calculation criteria according to the user's activity in the game, it is not limited to the above example.

Specifically, the processor 1150 may perform operations through an artificial neural network to learn each of a plurality of user actions. The processor 1150 may train an artificial neural network to determine whether each of a plurality of user actions is a meaningful action used to determine the immersion level of the first game. The processor 1150 may determine the immersion degree of the first game for a predetermined action of a predetermined user determined as a meaningful action based on at least one criterion.

In addition, the processor 1150 may quantify the predetermined behavior of the predetermined user according to a first criterion corresponding to a factor that determines the predetermined behavior of the predetermined user as a meaningful behavior.

Also, the processor 1150 may detect the second behavior of the first user related to the first behavior of the first user determined as a meaningful behavior. The processor 1150 may determine whether the second action of the first user is a meaningful action used to determine the immersion level of the first game. If the second action is determined to be a meaningful action, the processor 1150 may determine the immersion level of the first game with respect to the first action of the first user based on a criterion corresponding to a factor in which the second action is determined to be a meaningful action. have.

Also, the processor 1150 may determine the immersion level of the first game for each of the actions of the plurality of users based on at least one.

The processor 1150 may determine an engagement index indicating the immersion degree of the plurality of users for the first game based on the learning result.

The processor 1150 may determine weights between items corresponding to each of the at least one criterion based on the learning result. The processor 1150 may determine the engagement index of each of the plurality of users by applying weights between the items to the immersion of the first game for each of the actions of the plurality of users.

The processor 1150 may provide an engagement index according to a predetermined category.

The processor 1150 may control the user interface device 1120 such that information corresponding to a predetermined category is displayed on the user interface device 1120 for each section of the engagement index.

Also, the processor 1150 may receive an input for selecting a first category that is a reference for classifying an engagement index. The processor 1150 may obtain an engagement index for each detailed item in the first category. The user interface device 1120 may display an engagement index.

Specifically, the processor 1150 may control the user interface device 1120 such that the number of users and the engagement index corresponding to the plurality of users are displayed on the user interface device 1120 for each detailed item. Further, the processor 1150 may control the user interface device 1120 such that the average engagement index for a plurality of users is displayed on the user interface device 1120 for each detailed item.

The processor 1150 may transmit information about the engagement index classified according to a predetermined category through the communication device 1110 to an external device that manages the first game.

The computing device 10 described above may be implemented with hardware components, software components, and / or combinations of hardware components and software components. For example, the devices and components described in the embodiments include, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors (micro signal processors), microcomputers, field programmable gate arrays (FPGAs). , A programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose computers or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

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

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

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

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

Claims (20)

Obtaining log data including behavior information of a plurality of users for the first game;
Based on the behavior information of the plurality of users extracted from the log data, the behaviors of the plurality of users are associated with at least one criterion used to determine the immersion level of the first game through machine learning. Learning;
Determining an engagement index representing the immersion degree of the plurality of users for the first game based on a learning result; And
And, according to a certain category, providing the engagement index. According to claim 1,
Learning the behavior of the plurality of users in association with the at least one criterion,
Performing an operation through an artificial neural network to learn each of the actions of the plurality of users; And
The artificial neural network is trained to determine whether each of the plurality of user actions is a significant action used to determine the immersion level of the first game, and is determined as a significant action based on the at least one criterion And determining an immersion level of the first game for a user's predetermined action. According to claim 2,
Determining the immersion degree of the first game for a predetermined action of a predetermined user determined as a meaningful action based on the at least one criterion,
And quantifying the predetermined action of the predetermined user according to a first criterion corresponding to a factor that determines the predetermined action of the predetermined user as a meaningful action. According to claim 2,
Determining the immersion degree of the first game for a predetermined action of a predetermined user determined as a meaningful action based on the at least one criterion,
Detecting a second action of the first user related to the first action of the first user determined as a meaningful action; And
Based on the result of determining whether the second action of the first user is a meaningful action used to determine the immersion level of the first game, the immersion level of the first game with respect to the first action of the first user And determining the operating method of the computing device. According to claim 1,
The at least one criterion,
Criteria for calculating immersion according to the user's connection duration, criteria for calculating immersion according to the number of times the user has accessed, calculation criteria for immersion according to the cache used by the user in the game, and calculation according to user's activity in the game A method of operating a computing device, comprising at least one of the criteria. According to claim 1,
Learning the behavior of the plurality of users in association with the at least one criterion,
Determining an immersion level of the first game for each of the plurality of user actions based on the at least one criterion,
Determining the engagement index,
Determining a weight between items corresponding to each of the at least one criterion based on the learning result; And
And determining an engagement index of each of the plurality of users by applying a weight between the items to an immersion degree of the first game for each of the actions of the plurality of users. According to claim 1,
According to the predetermined category, the step of providing the engagement index,
And displaying information corresponding to the predetermined category for each section of the engagement index. According to claim 1,
According to the predetermined category, the step of providing the engagement index,
Receiving a selection of a first category that is a basis for classifying the engagement index; And
And acquiring and displaying the engagement index for each detailed item in the first category. The method of claim 8,
The step of displaying the engagement index for each detailed item in the first category,
Displaying the number of the plurality of users and the engagement index corresponding to the plurality of users for each of the detailed items; And
And displaying the average engagement index for the plurality of users for each of the detailed items. According to claim 1,
According to the predetermined category, the step of providing the engagement index,
And transmitting information on the Engagement Index classified according to the predetermined category to an external device managing the first game. Communication device;
User interface devices;
storage;
Processor; And
And a memory for storing instructions executable by the processor,
The processor, by executing the instructions,
Acquire log data including behavior information of a plurality of users for the first game,
Based on the behavior information of the plurality of users extracted from the log data, the behaviors of the plurality of users are associated with at least one criterion used to determine the immersion level of the first game through machine learning. Learning,
Based on the learning result, an engagement index indicating the immersion degree of the plurality of users for the first game is determined,
Computing device, according to a predetermined category, to display the engagement index on the user interface device. The method of claim 11,
The processor, by executing the instructions,
Performing calculations through an artificial neural network to learn each of the plurality of user actions,
The artificial neural network is trained to determine whether each of the plurality of user actions is a significant action used to determine the immersion level of the first game, and is determined as a significant action based on the at least one criterion A computing device that determines the immersion level of the first game for a user's predetermined action. The method of claim 12,
The processor, by executing the instructions,
Computing device for quantifying a predetermined action of the predetermined user according to a first criterion corresponding to a factor that determines the predetermined action of the predetermined user as a meaningful action. The method of claim 12,
The processor, by executing the instructions,
Detecting a second behavior of the first user related to the first behavior of the first user determined as a meaningful behavior,
Based on the result of determining whether the second action of the first user is a meaningful action used to determine the immersion level of the first game, the immersion level of the first game with respect to the first action of the first user To determine, computing device. The method of claim 11,
The at least one criterion,
Criteria for calculating immersion according to the user's connection duration, criteria for calculating immersion according to the number of times the user has accessed, calculation criteria for immersion according to the cache used by the user in the game, and calculation according to user's activity in the game A computing device comprising at least one of the criteria. The method of claim 11,
The processor, by executing the instructions,
Based on the at least one criterion, determining immersion of the first game for each of the plurality of user actions,
Based on the learning result, weights between items corresponding to each of the at least one criterion are determined,
A computing device for determining an engagement index of each of the plurality of users by applying a weight between the items to the immersion of the first game for each of the actions of the plurality of users. The method of claim 11,
The processor, by executing the instructions,
Computing device for displaying, on the user interface device, information corresponding to the predetermined category for each section of the engagement index. The method of claim 11,
The processor, by executing the instructions,
Receiving a selection of a first category that is a basis for classifying the engagement index through a user interface device,
Computing device for acquiring the engagement index for each sub-category in the first category, and displaying the engagement index on the user interface device. The method of claim 11,
The processor, by executing the instructions,
A computing device that transmits information on the engagement index classified according to the predetermined category through the communication device to an external device managing the first game. Obtaining log data including behavior information of a plurality of users for the first game;
Based on the behavior information of the plurality of users extracted from the log data, the behaviors of the plurality of users are associated with at least one criterion used to determine the immersion level of the first game through machine learning. Learning;
Determining an engagement index representing the immersion degree of the plurality of users for the first game based on a learning result; And
A computer program stored in a medium for executing a method in combination with hardware, comprising providing the engagement index, according to a certain category.

Images