KR20210062403A - Online game play propensity analysis and coaching system through video analysis and big data analysis - Google Patents

Abstract

The present invention relates to an online game play tendency analysis and coaching system through video analysis and big data analysis, wherein in a player computer, a player records a video of a specific player using a user interface (UI) that is linked to a corresponding online game; is configured to analyze and provide metadata including the player's methods, strategies, tactics, tendencies, and the like through artificial intelligence learning by analyzing the recorded video; and through an external player statistical server, comprises a received statistical data for each character of the corresponding player, a client app (100) to provide image data, a video recording part (200), a metadata analysis part (300), a data storage part (400), and a client web (500) as the main configuration. Therefore, the present invention is capable of saving the investment time in order to achieve a high rank.

Description

Online game play propensity analysis and coaching system through video analysis and big data analysis {ONLINE GAME PLAY PROPENSITY ANALYSIS AND COACHING SYSTEM THROUGH VIDEO ANALYSIS AND BIG DATA ANALYSIS}

The present invention relates to an online game play propensity analysis and coaching system through video analysis and big data analysis, and more specifically, analyzes the video of an online game, and the player's play method, strategy, and tactics through artificial intelligence-based video analysis. , By extracting metadata including propensity, providing objective data to online game players using player-specific statistical data received through an external search server, and providing coaching services for each player, the player's ability can be improved. It relates to an online game play tendency analysis and coaching system through video analysis and big data analysis.

Recently, as Internet or general computer communication has rapidly developed, online games using these communication technologies have become common.

In such an online game, multiple players can access simultaneously, and players can compete with each other in a confrontation. In this competition of online games, players are investing a lot of time to measure each other's skills and reach a higher ranking (ranking). There is a trend in the development of private academies, coaching, etc., and accordingly, there has been a problem that additional costs are incurred by paying for individual coaching and academy in order to improve skills.

Here, a ranking service is provided that allows players to evaluate their proficiency level in online games, and the intention of providing such a ranking service is to enable the player to select an appropriate opponent for him and to increase the achievement accordingly.

In addition, in online games where ranking service is provided, except for personal coaching and academy, players directly search for videos of online game players or high-rank players in Internet broadcasting as a learning method to improve ranking, and the propensity and play of high-rank players. They are learning by looking at methods and tactics.

However, compared to the market size of these online games, it is difficult for players to find data to improve their game skills due to lack of meta data or statistical data such as game propensity, trend, strategy, and tactics that are popular in online games. to be.

On the other hand, as described above, there are websites that provide online game related data such as online game records that provide statistical data that players want, and such websites search for the player's ID and rank the player. It provides services such as play record and game play video replay.

However, the above-described conventional website provides only basic data, such as basic records, simple statistics, and downloads and replays of player images, and performs coaching services for improving players' skills, meta-analysis of the corresponding online game, and the like. There is a problem that it cannot provide meaningful coaching services that players want.

Accordingly, the present invention was conceived to solve the above problems, and in more detail, a client app equipped with a user interface (UI) in which the player's computer is linked with an online game client, and a video of the player are recorded. And, based on the recorded video, a metadata analysis unit that analyzes metadata including the player's play method, strategy, tactics, and propensity, and through an external player statistics server, receive statistical data and video data for each character of a specific player. It includes a data storage unit that stores and stores online game metadata, statistics data, and video data, and consists of a client web capable of providing the player's location and movement path as a mini-map image. Its purpose is to provide an online game play propensity analysis and coaching system through image analysis and big data analysis that provide data for improvement.

According to a preferred embodiment of the present invention, a user interface (UI, User Interface) is provided in the form of an app that is linked with an online game client in a player computer, and allows the player to record a game image and replay the recorded image. A client app equipped with; A video recording unit connected to the client app to record a play video of an online game; A metadata analysis unit for extracting metadata including a player's play method, strategy, tactics, and propensity based on the recorded image extracted through the video recording unit and analyzing the metadata for each time unit; A data storage unit for receiving and storing statistical data and image data for each character of a specific player through an external player statistics server, and storing and managing the metadata obtained through the metadata extraction unit; The metadata analysis unit and the data storage unit are connected to classify and provide the metadata, statistical data, and video data to the player, and the location and movement path of each character type selected by the player are clustered in a minimap image of a preset size. It characterized in that it includes a client web provided to the player.

According to another embodiment of the present invention, the client web provides the player with the metadata, statistical data, and video data, and provides a coaching service for each context.

According to another embodiment of the present invention, the metadata analysis unit is characterized in that the analysis and artificial intelligence are learned by clustering based on the player character set in advance based on the metadata and the statistical data.

According to another embodiment of the present invention, the data storage unit stores expert data based on an expert interview of the online game, and is provided to the player through the client web.

According to another embodiment of the present invention, the metadata analysis unit is interlocked with the video recording unit to operate a client of the online game to extract a specific game image, It is characterized in that the metadata is extracted through processing and deep learning.

In addition, the meaning of the terms described in the present invention should be understood as follows. Terms such as “first” and “second” are used to distinguish one element from other elements, and the scope of rights is not limited by these terms. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

Furthermore, when a component is referred to as being “connected” to another component, it should be understood that although it may be directly connected to the other component, another component may exist in the middle. On the other hand, it should be understood that no component exists. On the other hand, other expressions that describe the relationship between the constituent elements, such as “between” and “between” or “neighbor to” and “directly adjacent to” should be interpreted as well.

Singular expressions are to be understood as including plural expressions unless the context clearly indicates otherwise, and terms such as “include” or “have” refer to the specified features, numbers, steps, actions, components, parts, or these. It is to be understood that it is intended to designate that a combination exists and does not preclude the presence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

According to the above configuration and operation, the present invention provides objective data such as player's play propensity ability, performance, etc. to extract metadata and provide intuitive online game data in more detail. By providing coaching services according to their propensity, players' skills can be improved, investment time to achieve a high rank can be saved, and player coaching or academy expenses are not incurred, providing personalized low-cost services based on data. There is an effect that can be done.

1 and 2 are reference diagrams for explaining an online game play propensity analysis and coaching system through image analysis and big data analysis according to the present invention.
3 is a block diagram of an online game play tendency analysis and coaching system through image analysis and big data analysis according to the present invention.
4 is a reference diagram for explaining game data, propensity data, and coaching services using an online game play propensity analysis and coaching system through image analysis and big data analysis according to the present invention.
Figure 5 is a reference diagram for explaining the provision of the location and movement path for each player character using the online game play propensity analysis and coaching system through image analysis and big data analysis according to the present invention.
6 is a reference diagram for explaining an experience service of an online game play tendency analysis and coaching system through image analysis and big data analysis according to the present invention.
7 is a reference diagram for explaining an analysis process applying a client app according to the present invention.
8 is a reference diagram showing an online game analysis providing screen using a client web according to the present invention.
9 is a reference diagram showing a download and replay screen of recorded video data in an online game according to the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to FIGS. 1 to 9.

The present invention relates to an online game play propensity analysis and coaching system through image analysis and big data analysis, and this is a video of a specific player using a user interface (UI) in which the player is linked with the online game in the player computer. Is configured to provide metadata including player method, strategy, tactics, propensity, etc. through artificial intelligence learning by recording the recorded video and analyzing the recorded video. In order to provide statistical data and image data for each character, the main components include a client app 100, an image recording unit 200, a metadata analysis unit 300, a data storage unit 400, and a client web 500. Done.

Here, the online game according to the present invention refers to the League of Legends of RioT games of the MOBA (Multiplayer Online Battle Arena) genre in which a plurality of players cooperate with battles, and each player selects various characters and fights. , Refers to an online game in which a ranking (rank) service according to player wins or loses is introduced.

The client app 100 according to the present invention is provided in the form of an app linked with a client of an online game on a player computer, and a user interface is provided so that the player can record a game image and execute a replay of the recorded image.

The video recording unit 200 is connected to the client app 100 to record a play image of an online game, and the player can record an image of a specific player through manipulation of a user interface.

The metadata analysis unit 300 extracts metadata as data including the player's method, strategy, tactics, disposition, etc. using artificial intelligence learning based on the recorded image extracted through the video recording unit 200 And analyzing, and analyzing metadata for each progression time unit of the online game.

The data storage unit 400 is linked with an external player statistics server to receive and store statistical data and image data for each character of a specific player through the external player statistics server, and store the metadata obtained through the metadata extraction unit. To manage.

Here, the external player statistics server interlocked with the data storage unit 400 is an online game total search server or a website, typically OP.GG.

The client web 500 is provided with a user interface (UI) so that a player can search for online game data, and is connected to the metadata analysis unit 300 and the data storage unit 400 to provide the metadata and statistical data. And the video data recorded through the video recording unit 200 may be classified and provided to the player, and the location and movement path for each character type selected by the player are clustered in a minimap image set on the corresponding online game and provided to the player. have.

In addition, the client web 500 may provide the player with the metadata, statistics data, and video data as a basis, and analyzes the player's own play video and provides player-customized feedback and feedback based on the metadata and statistics data. , Can provide context-specific coaching services.

The metadata analysis unit 300 clusters and analyzes the metadata and statistical data based on a preset character, and is learned using artificial intelligence (AI), and the metadata analysis unit 300 It is configured to provide data on play style, strategy, tactics, and propensity to players through 500.

The data storage unit 400 may store and manage expert data based on an expert interview of the online game, and may be provided to the player through the client web 500.

Here, the metadata analysis unit 300 is interlocked with the video recording unit 200 to extract the game image of a specific player when the player manipulates the client of the online game, and an API (Application Program Interface) of the online game, It is configured to extract the metadata through image processing and deep learning.

As described above, the present invention can provide a player-customized coaching service and play propensity analysis by using image analysis and big data, and can present the objective game propensity and degree of cooperation of the corresponding player.

The client app 100 uses Window 10 OS, implements a click event necessary for video recording using Win API, parses API information provided by the developer of League of Legends, and a minimap of the corresponding online game. It detects the presence or absence of an image object, and can extract the player's movement path and location on the mini-map using deep learning.

The online game play propensity analysis and coaching system through image analysis and big data analysis according to the present invention uses image processing and deep learning to extract metadata other than the online game API to derive the play propensity of the player, and to cooperate between players, The degree of consideration can be measured, objective data on skill, performance, and disposition can be provided, and a coaching service for each disposition can be provided compared to a higher rank cluster of the same disposition, and the coaching service is play data for each disposition. Clusters and provides coaching services after learning the context of in-game events by disposition.

To explain in detail, the online game (League of Legends) client is manipulated to extract a specific game image, and the game metadata is extracted through game company API, image processing and deep learning technology, and for fast JSON storage and analysis. It builds a Mongo DB optimized for JSON, distributes all of the above functions as a Windows App, and performs automatic data gathering by running 20 apps in parallel on AWS through GCP (Google Cloud Platform). Extract the data.

In addition, the overall information and play propensity information of the API-based online game can be intuitively provided, the situational response of the player and the upper group can be intuitively provided, and a large amount of information can be concisely and intuitively provided by the player. In-game icon is used to deliver to, and profile image caching is used for UI that is not affected by online game updates.

In addition, as a game coaching service by disposition, time-based data normalization for JSON analysis of 200,000 lines per game, 140 characters of online games (League of Legends) based on statistical data are clustered according to three criteria, and based on expert interviews. It defines 19 events related to the movement tendency of each character, and the collected data is clustered based on the event to determine the play tendency. In addition, it is possible to grasp the intention of the player in each situation through analysis or learning of the clustered data.

According to the present invention, it is possible to solve the problem of having to go to an academy to improve online game skills, it is possible to provide a general game coaching service as many times as the player wants, and increase the skills of the low-ranking players and the high-rank players In addition to being able to use it for analysis of the play of the online game, data can be provided to analysts and commentators of the online game.

Meanwhile, since the description of the technology disclosed in the present specification is merely an embodiment for structural or functional description, the scope of the rights of the disclosed technology should not be construed as being limited by the embodiments described in the text.

That is, since the embodiments can be variously changed and have various forms, the scope of the rights of the disclosed technology should be understood to include equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the disclosed technology does not mean that a specific embodiment should include all or only such effects, the scope of the rights of the disclosed technology should not be understood as being limited thereto.

In addition, the meaning of the terms described in the present invention should be understood as follows. Terms such as “first” and “second” are used to distinguish one element from other elements, and the scope of rights is not limited by these terms. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

Furthermore, when a component is referred to as being “connected” to another component, it should be understood that although it may be directly connected to the other component, another component may exist in the middle. On the other hand, it should be understood that no component exists. On the other hand, other expressions that describe the relationship between the constituent elements, such as “between” and “between” or “neighbor to” and “directly adjacent to” should be interpreted as well.

Singular expressions are to be understood as including plural expressions unless the context clearly indicates otherwise, and terms such as “include” or “have” refer to the specified features, numbers, steps, actions, components, parts, or these. It is to be understood that it is intended to designate that a combination exists and does not preclude the presence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

As described above, although the present invention has been described by the limited embodiments and drawings, the present invention is not limited to the above embodiments, which is, if one of ordinary skill in the field to which the present invention belongs, various modifications and Transformation is possible. Therefore, the idea of the present invention should be grasped only by the claims set forth below, and all equivalent or equivalent modifications thereof will be said to belong to the scope of the idea of the present invention.

100: client app
200: video recording unit
300: metadata analysis unit
400: data storage unit
500: client web

Claims (3)

A client app 100 provided in the form of an app linked to a client of an online game on a player computer, and having a user interface (UI) so that the player can record a game video and execute a replay of the recorded video;
An image recording unit 200 connected to the client app to record a play image of an online game;
Metadata that extracts metadata including player's play method, strategy, tactics, and propensity based on the recorded image extracted through the video recording unit 200 using artificial intelligence, and analyzes the metadata for each time unit. A data analysis unit 300;
A data storage unit 400 for receiving and storing statistical data and image data for each character of a specific player through an external player statistics server, and storing and managing the metadata obtained through the metadata extraction unit;
The metadata analysis unit and the data storage unit 400 are connected to classify and provide the metadata, statistical data, and video data to the player, and the position and movement of each character type selected by the player on a minimap image of a preset size Online game play propensity analysis and coaching system through image analysis and big data analysis, comprising: a client web 500 provided to players by clustering paths.
The method of claim 1,
The client web 500 provides the player with the metadata, statistical data, and video data, and provides a coaching service for each situation, an online game play tendency analysis and coaching system through video analysis and big data analysis. .
The method of claim 1,
The metadata analysis unit 300 clusters and analyzes and artificial intelligence learning based on preset player characters based on the metadata and statistical data. Coaching system.

Images