KR102441032B1 - Artificial intelligence user operation system that works in a group connection game - Google Patents

Abstract

According to the present invention, an AI user who has created a game participation and content play method with artificial intelligence by analyzing the pattern played by a real user with an AI user accesses the game with the general user's play pattern and chats with the general user, participates in content, and competes for ranking It relates to an artificial intelligence user operating system that is active in group access games that can activate games and lead user acquisition.

Description

Artificial intelligence user operation system that works in a group connection game}

The present invention relates to an artificial intelligence system for a game, and in detail, an AI user who made a game participation and content play method with artificial intelligence by analyzing big data on a pattern played by an actual user accesses the game with the play pattern of a general user. It relates to an artificial intelligence user operating system that can chat, participate in content, and compete for rankings with general users to activate games and lead user acquisition.

Recently, due to the increase in the spread of mobile devices and the development of the Internet network, the number of online games that are played through an online network such as the Internet and that multiple users can enjoy the game at the same time has greatly increased.

The popularity of these online games is usually expressed through the number of visitors, a concept similar to the number of viewers of TV broadcast programs or movies.

In particular, immediately after the game service is published, the more users play, the greater the chance of success of the game, so many game companies not only spend a lot of money on marketing to recruit early users, but also reward them through various events or even the number of users. is over-inflated and advertised.

As such, as many users play, the popularity rises, and as a result, competitive marketing is being conducted centered on large developers with a circular structure that can secure more users. There is a problem that not only is there not enough opportunity to publicize the game, but also all early users have a problem that they quickly read interest and quit the game because competition is not activated during the game.

Republic of Korea Patent Registration No. 10-2013327 (2019.08.16)

The present invention was created to solve the above problems, and an object of the present invention is to analyze the patterns played by real users with Victor Eater so that the game can be activated by increasing the number of users. It is to provide an artificial intelligence user operating system that works in group access games that can access games with patterns and compete with general users.

For the above purpose, the present invention provides an in-game artificial intelligence user operating system, comprising: a collection module for collecting play data of real users accessing the game; an analysis module that analyzes the play data, but divides and analyzes the level section, character type, content and ranking, and play method; a classification module for classifying the analysis result of the analysis module by type of user's access time zone; a learning module for learning the analysis result of the analysis module and the classification result of the classification module to generate play pattern data for each time zone type; a generation module for generating database fields of AI users including login information for the selected game; an execution module for allowing AI users to play against a set target to which the generated pattern data is applied; characterized in that it consists of

In this case, the execution module preferably includes a resetting unit for resetting the target through a set algorithm as the ranking of the AI user is changed due to other users.

In addition, the execution module preferably includes a setting unit that can adjust the priority and growth rate of the AI user's participation content.

In addition, the selected game is a team-versus online battle game genre, and the analysis module preferably analyzes the player's content play count, average play time, access time zone, foster character occupation group, and game cache consumption information.

In addition, the execution module preferably includes an authentication unit to which a pass algorithm according to a telecommunication company agreement is applied for game login of the generated AI user.

Through the present invention, even when the initial number of users of the game service is insufficient, AI users are introduced to promote in-game competition, induce active play by connected users, and activate the game at a low cost.

In addition, it is possible to prevent users who newly enter the game with insufficient knowledge from losing interest and fun and leaving the game even if they cannot form a relationship with other users and proceed with game play. You can motivate yourself to play the game by playing and growing with AI users with game character levels.

1 is a block diagram showing the configuration and connection relationship according to an embodiment of the present invention;
2 is a flowchart illustrating an AI user creation process according to the present invention.

Hereinafter, the configuration of the artificial intelligence user operating system active in the present invention group access game will be described in detail with reference to the accompanying drawings.

1 is a block diagram showing a configuration and connection relationship according to an embodiment of the present invention, and FIG. 2 is a flowchart showing an AI user creation process according to the present invention. It is an artificial intelligence user operating system in a group access game where play takes place, and when the initial number of users of the game service is not sufficient, AI users are added to increase the number of connected users and naturally promote in-game competition to activate the game.

These AI users are active in the game in a form very similar to the actual user's play based on the game data of the conventional real user, and it is difficult for the connected user to distinguish whether the object they are playing with is an AI user or a real user. need to be operated.

The present invention for this purpose is provided with a collection module 110, an analysis module 120, a classification module 130, a learning module 140, a generation module 150, and an execution module 160 as a main configuration. do.

The collection module 110 is configured to collect play data of real users who have access to the game, and it is desirable to collect user play data of the game for inputting AI users, but the user play data of the game may not be sufficient. In this case, it is also possible to collect play data, that is, activity records of all users who accessed and played games with similar genres and characteristics.

The present invention can be applied to various types of online games, and as an embodiment, big data is applied to 5 million global users of the League of Masters game, which is a Multiplayer Online Battle Arena (MOBA).

The analysis module 120 analyzes the play data collected through the collection module 110, but divides the play data into level sections, character types, contents and rankings, and play methods to analyze detailed play patterns.

The level section may be different depending on the setting conditions of the game, but in the embodiment of the present invention, users of levels 1 to 50 are divided into 10 level units, and the number of plays of various contents provided in the game, average play time, access time zone , it is desirable to analyze the character occupation group, game cash consumption information.

As mentioned above, as the main application target is the team-versus online battle game genre, the characters to be fostered can be divided into warriors, wizards, physical dealers, healers, etc. Collect and analyze.

In the case of ranking content analysis, it analyzes the ranking content in arenas where players usually compete with each other (PVP) or with monsters in the game (PVE). Collect and analyze.

In addition, when the game is played by forming a team, the team play data may be collected as the AI user belongs to the team or the team may be formed only by the AI user.

The classification module 130 is configured to classify the analysis result of the analysis module 120 by user's access time zone type. That is, the access time zone may vary according to the characteristics of the actual user, and accordingly, the user play pattern for each time zone may also vary.

In the embodiment of the present invention, such access time zone is divided into core type, light type, and night type based on the amount of content play in general, and this primary classification is further classified into A and B types according to the amount of content play.

That is, core type A is AM 8:00~AM 12:00 (maximum content play), core type B is AM 12:00 ~ PM 10:00 (minimum content play, 1 content participation per hour), light A is AM 12 :00~ PM 8:00 (maximum content play), 12:00 PM 8:00 PM for Light B (minimum content play, 1 content participation per hour), 10:00 PM to AM 10:00 for Night Type A (maximum content play), night type B was classified into PM 10:00 ~ AM 10:00 (minimum content play, participation in content once per hour). Through this classification, the play characteristics of AI users who are active in time zones can be realized more realistically, and the specific time conditions presented can be modified as examples.

The learning module 140 learns the analysis result of the analysis module 120 and the classification result of the classification module 130 to generate play pattern data for each time zone type. That is, the data collected from the collection module 110 and analyzed and classified through the analysis module 120 and the classification module 130 is learned as big data to generate specific play pattern data to be applied to the AI user. Basically, the access time zone By creating each type, the play pattern can be varied for each time period in which the AI user is input, and in addition, a play pattern reflecting level conditions and character occupation groups can be created.

The generation module 150 is configured to generate a database field of an AI user including login information for a selected game. Basically, after selecting a game to which a play pattern generated through the learning module 140 is applied, the corresponding game system By adding the AI user-related database fields to be put into the

AI users are given IDs for game access just like real users. In addition, normal users usually use telecommunication companies, portals, and SNS linked logins for game access, but in the case of AI users, it is difficult to apply such a login method. For this, including the authentication unit 151 to which the pass algorithm according to the communication company agreement is applied, it supports the smooth login of AI users, and communication with the game server after login is made equally for general users and AI users.

The execution module 160 is configured to allow an AI user to play a set target to which the generated pattern data is applied, and the generated AI user basically accesses the game at a set time and plays game content for a set time. , the basic content and time content are performed according to the pattern, and then repeated play is performed to enter the target ranking in the ranking content.

This execution module 160 is provided with a reset unit 161, a setting unit 162, and a chat unit 163 as a detailed configuration.

The reset unit 161 is configured to reset the target through a set algorithm as the ranking of the AI user is changed due to other users. It is desirable to change the detailed settings in units of ranking, but to modify the settings under conditions with a good win rate.

The setting unit 162 is a configuration for adjusting the priority and growth rate of the AI user's participation content, and provides a separate selection window for the administrator to adjust the detailed settings of the AI user and adjusts the parameters, so that the game is unbalanced. play can be prevented. In order to access multiple AI users, methods such as running multiple apps on a PC or running multiple IDs simultaneously with one app can be applied.

The chat unit 163 is configured to allow AI users to participate in in-game chatting, and it is preferable to operate in a manner that provides conversations with content closely related to game play in response to the situation, and each situation in the game or the user It is necessary to have basic chatting contents to respond to the inputted contents.

Through this, even in situations where new entrants to the game cannot form relationships with other users due to lack of knowledge and skills or have no friends to play with, AI users of a similar level can play together and help them grow. You can activate the game.

The right of the present invention is not limited to the above-described embodiments, but is defined by the claims, and a person of ordinary skill in the art can make various modifications and adaptations within the scope of the claims. it is self-evident

110: collection module 120: analysis module
130: classification module 140: learning module
150: generation module 151: authentication unit
160: execution module 161: reset unit
162: setting unit 163: chat unit

Claims (5)

In an artificial intelligence user operating system in an online battle game against a team having a character that is nurtured into a group including a warrior, a wizard, a physical dealer, and a healer,
a collection module 110 for collecting play data and team play data of real users who have accessed the game;
Analyze the play data, but divide it into level section, character type and training job group, content and ranking, and play method, and analyze the number of times the player plays the content, average play time, access time, training character job group, game cache consumption information analysis module 120;
The analysis result of the analysis module 120 is divided into a core type, a light type, and a night type based on the user's access time zone type and the amount of content play, but the core type A is from 8:00 AM to 12:00 AM, core Type B is AM 12:00 ~ PM 10:00, Light A is AM 12:00 ~ PM 8:00, Light B is PM 12:00 ~ PM 8:00, Night Type A is PM 10:00 ~ AM 10 :00, the night type B is a classification module 130 for classifying the PM 10:00 ~ AM 10:00;
a learning module 140 for learning the analysis result of the analysis module 120 and the classification result of the classification module 130 to generate play pattern data for each time zone type, level condition, and character occupation group;
a generation module 150 including an authentication unit 151 to which a pass algorithm according to a telecommunication company agreement is applied to generate an AI user's database field including login information for the selected game, for the generated AI user's game login;
A reset unit 161 for resetting the target in units of 10 ranks through a set algorithm so that the AI user plays the set target to which the generated pattern data is applied, but the rank of the AI user decreases due to other users; A setting unit 162 that can adjust the priority and growth rate of AI users' participation content, and basic chat contents to respond to in-game situations or user input so that AI users can participate in in-game chat an execution module 160 including a chatting unit 163; Artificial intelligence user operating system, characterized in that consisting of. delete delete delete delete

Images