Bot-based role-playing method, computer device and program
The bot-based role-playing method using AI models generates character bots and evaluates user suitability, addressing limitations in instant messenger platforms by enhancing engagement and diversity in open chat experiences.
Patent Information
- Application Number
- JP2024080788
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-22
- Filing Date
- 2024-05-17
- Publication Date
- 2024-12-04
AI Technical Summary
Existing instant messenger platforms lack the ability to effectively utilize artificial intelligence for generating character bots that can engage in role-playing scenarios and determine user suitability for character roles based on persona, limiting the diversity and engagement of open chat experiences.
A bot-based role-playing method utilizing an artificial intelligence language model to generate character bots, learn character personas from scripts, and determine user suitability through conversation analysis and external information integration, enabling dynamic role-playing scenarios and secondary content creation.
Enhances user engagement by providing dynamic role-playing experiences and generating secondary content based on AI-driven character interactions, improving the diversity and interactivity of open chat services.
Smart Images

Figure 2024167896000001_ABST
Abstract
Description
[Technical field]
[0001] The following description relates to techniques for providing role-playing games. [Background technology]
[0002] Instant messenger, a common communication tool, is software for sending and receiving messages and data in real time. Users can register chat partners on the messenger and exchange messages in real time with those registered on the chat list.
[0003] The use of such messenger functions is widespread not only in PCs (personal computers) but also in mobile environments such as mobile communication terminals.
[0004] For example, Patent Document 1 (published on September 30, 2002) discloses a mobile messenger service system and method for a mobile terminal that uses a wireless communication network and can provide a messenger service through a mobile messenger installed on the mobile terminal.
[0005] As instant messengers have become more widespread, the functions offered through them have also diversified rapidly, and an open chat function has been provided that allows users to join a chat using a link without needing personal information such as a phone number or ID. [Prior art documents] [Patent documents]
[0006] [Patent Document 1] Korean Patent Publication No. 10-2002-0074304 Summary of the Invention [Problem to be solved by the invention]
[0007] The aim is to use artificial intelligence (AI) models to generate character bots for role-playing on social platforms.
[0008] The aim is to use a character bot to push various role-playing situations based on the bot's learning content and actual offline information.
[0009] The aim is to determine the role-playing suitability of a user who plays the role of a character bot according to the persona of that character bot.
[0010] The aim is to generate secondary content from a series of conversations generated between a user playing the role of a specific character bot and other character bots. [Means for solving the problem]
[0011] The present invention provides a bot-based role-playing method executed on a computer device, the computer device including at least one processor configured to execute computer-readable instructions contained in a memory, the bot-based role-playing method including the steps of receiving, by the at least one processor, a script provided in an open chat, and learning, by the at least one processor, each character included in the script using an artificial intelligence language model to generate a plurality of character bots for role-playing in the open chat.
[0012] According to one aspect, the generating step may include learning the character from at least one of dialogue, interactions, or situational information in the script.
[0013] According to another aspect, the generating step may include learning the character from at least one of the character's profile information, a time period in which the script is set, or locale information.
[0014] According to another aspect, the bot-based role-playing method may further include providing, by the at least one processor, a role-playing game in the open chat in which a user participating in the open chat acts on behalf of the role of at least one of the plurality of character bots.
[0015] According to another aspect, the bot-based role-playing method may further include a step of pushing, by the at least one processor, a role-playing situation linked to external information based on a situation used in learning of a character bot among the plurality of character bots that participates in a conversation in the open chat.
[0016] According to another aspect, the bot-based role-playing method may further include a step of determining, by the at least one processor, the user's suitability for role-playing based on a specific character bot among the plurality of character bots.
[0017] According to another aspect, the determining step may determine the user's suitability for role-playing based on a response similarity obtained by comparing the user's response to a given situation with the response of the specific character bot.
[0018] According to another aspect, the determining step may determine the user's suitability for role-playing based on at least one of the following: the results of an evaluation by a role-playing master set in the open chat from the conversation message entered by the user, whether or not it matches information used when learning about the specific character bot, or the results of voting by other users participating in the open chat.
[0019] According to another aspect, the bot-based role-playing method may further include generating secondary content of the open chat based on a role-playing conversation included in the open chat by the at least one processor.
[0020] According to yet another aspect, the step of generating the secondary content may include selecting key messages from conversation messages included in the open chat based on the script and generating the key messages as the secondary content.
[0021] The present invention provides a program recorded on a non-transitory computer-readable recording medium for causing the computer device to execute the bot-based role-playing method. Also, a program for causing a computer to execute the bot-based role-playing method can be provided.
[0022] A computer device is provided, the computer device including at least one processor configured to execute computer-readable instructions contained in a memory, the at least one processor processing a step of receiving a script provided in an open chat, and a step of learning each character contained in the script using an artificial intelligence language model to generate a plurality of character bots for role-playing in the open chat. [Brief description of the drawings]
[0023] [Figure 1] FIG. 1 illustrates an example of a network environment in accordance with an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram illustrating an example of a computing device according to an embodiment of the present invention. [Diagram 3] 4 is a flowchart illustrating an example of a method performed by a computing device in accordance with an embodiment of the present invention. [Figure 4] FIG. 13 is an exemplary diagram illustrating a step of generating a character bot for role-playing in one embodiment of the present invention. [Diagram 5] FIG. 2 is an illustrative diagram for explaining a role-playing conversation between a character bot and a user in one embodiment of the present invention. [Figure 6] 11 is an exemplary diagram for setting a processing stage according to a user's suitability for role-playing in an embodiment of the present invention; FIG. [Figure 7] 11 is an exemplary diagram for setting a processing stage according to a user's suitability for role-playing in an embodiment of the present invention; FIG. [Figure 8] FIG. 2 is an exemplary diagram illustrating a step of generating secondary content of an open chat in accordance with an embodiment of the present invention. [Figure 9] FIG. 2 is an exemplary diagram illustrating a step of generating secondary content of an open chat in accordance with an embodiment of the present invention. [Figure 10] FIG. 13 is an exemplary diagram illustrating a step of sharing secondary content of an open chat in an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0024] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
[0025] FIELD OF THE DISCLOSURE Embodiments of the present invention relate to techniques for providing role-playing games on a social platform.
[0026] Embodiments including those specifically disclosed in this specification can utilize artificial intelligence (AI) models to quickly generate role-playing bots on social platforms, and the role-playing bots can be utilized within the social platforms for a variety of purposes, such as determining role-playing suitability, generating role-playing situations, and generating secondary content.
[0027] The bot-based role-playing system according to the embodiment of the present invention may be realized by at least one computer device, and the bot-based role-playing method according to the embodiment of the present invention may be executed by at least one computer device included in the bot-based role-playing system. In this case, a computer program according to an embodiment may be installed and executed in the computer device, and the computer device may execute the bot-based role-playing method according to the embodiment according to the control of the executed computer program. The above-mentioned computer program may be recorded in a computer-readable recording medium in combination with the computer device to cause the computer to execute the bot-based role-playing method.
[0028] Fig. 1 is a diagram showing an example of a network environment in one embodiment of the present invention. The network environment in Fig. 1 shows an example including a plurality of electronic devices 110, 120, 130, 140, a plurality of servers 150, 160, and a network 170. Such Fig. 1 is merely an example for explaining the invention, and the number of electronic devices and the number of servers are not limited to those shown in Fig. 1. Furthermore, the network environment in Fig. 1 is merely an example of an environment applicable to this embodiment, and the environment applicable to this embodiment is not limited to the network environment in Fig. 1.
[0029] The electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals realized by computer devices. Examples of the electronic devices 110, 120, 130, and 140 include smartphones, mobile phones, navigation systems, personal computers (PCs), notebook PCs, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), and tablets. As an example, FIG. 1 shows a smartphone as an example of the electronic device 110, but in the embodiment of the present invention, the electronic device 110 may mean one of various physical computer devices that can communicate with other electronic devices 120, 130, and 140 and / or servers 150 and 160 via a network 170 using a substantially wireless or wired communication method.
[0030] The communication method is not limited, and may include not only a communication method using a communication network (for example, a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network) that the network 170 can include, but also short-range wireless communication between devices. For example, the network 170 may include any one or more of a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), the Internet, and the like. Furthermore, the network 170 may include any one or more of a network topology including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, and the like.
[0031] Each of the servers 150, 160 may be realized by one or more computing devices that communicate with the multiple electronic devices 110, 120, 130, 140 via the network 170 to provide instructions, code, files, content, services, etc. For example, the server 150 may be a system that provides a service (such as a role-playing service, for example) to the multiple electronic devices 110, 120, 130, 140 connected via the network 170.
[0032] 2 is a block diagram showing an example of a computer device according to an embodiment of the present invention. Each of the electronic devices 110, 120, 130, and 140 and the servers 150 and 160 described above may be realized by a computer device 200 shown in FIG.
[0033] Such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input / output interface 240, as shown in FIG. 2. The memory 210 is a computer-readable recording medium and may include a random access memory (RAM), a read only memory (ROM), and a permanent mass storage device such as a disk drive. Here, a permanent mass storage device such as a ROM or a disk drive may be included in the computer device 200 as a separate permanent storage device separate from the memory 210. The memory 210 may also store an operating system and at least one program code. Such software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, a memory card, etc. In another embodiment, the software components may be loaded into the memory 210 through a communication interface 230 that is not a computer-readable recording medium. For example, the software components may be loaded into the memory 210 of the computing device 200 based on a computer program installed by a file received over the network 170 .
[0034] The processor 220 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. The instructions may be provided to the processor 220 by the memory 210 or the communication interface 230. For example, the processor 220 may be configured to execute instructions received according to program code stored in a storage device such as the memory 210.
[0035] The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (for example, the above-mentioned recording device) via the network 170. For example, requests, instructions, data, files, etc. generated by the processor 220 of the computer device 200 according to program codes recorded in a recording device such as the memory 210 may be transmitted to other devices via the network 170 under the control of the communication interface 230. Conversely, signals, instructions, data, files, etc. from other devices may be received by the computer device 200 via the communication interface 230 of the computer device 200 via the network 170. The signals, instructions, data, etc. received via the communication interface 230 may be transmitted to the processor 220 or the memory 210, and the files, etc. may be recorded on a recording medium (the above-mentioned permanent recording device) that the computer device 200 may further include.
[0036] The input / output interface 240 may be a means for interfacing with the input / output device 250. For example, the input device may include a device such as a microphone, a keyboard, or a mouse, and the output device may include a device such as a display and a speaker. As another example, the input / output interface 240 may be a means for interfacing with a device in which functions for input and output are integrated into one, such as a touch screen. The input / output device 250 may be configured as a single device together with the computer device 200.
[0037] Also, in other embodiments, computing device 200 may include fewer or more components than those of Figure 2. However, most prior art components need not be explicitly illustrated. For example, computing device 200 may be implemented to include at least some of the input / output devices 250 described above, and may further include other components such as a transceiver, a database, etc.
[0038] Hereinafter, a specific embodiment of a method and apparatus for providing a bot-based role-playing service on a social platform will be described.
[0039] In this specification, a social platform may refer to a service platform that provides various services utilizing resources such as user profile information and friendships within a social network service, as well as social network services such as messengers and various communities.
[0040] In the following embodiment, a messenger will be described as a representative example of a social platform.
[0041] In this embodiment, a role-playing game using a chatbot is provided through open chat.
[0042] In this specification, the term "open chat" refers to a chat service where multiple users can enjoy conversations on themes of interest, and a community service where users can chat immediately through a link such as a URL without going through a friend addition process using a phone number, ID, etc. The open chat link may include a function whereby a messenger is automatically launched and a user can enter a corresponding chat room so that a chat can be started immediately by clicking the link.
[0043] The computer device 200 according to the present embodiment may provide a role-playing service to a client by connecting to a dedicated application installed on the client or a web / mobile site related to the computer device 200. A bot-based role-playing system implemented by a computer may be configured in the computer device 200. As an example, the bot-based role-playing system may be implemented in the form of a program that operates independently, or may be configured in the form of an in-app of a specific application so as to be operable on the specific application.
[0044] The processor 220 of the computer device 200 may be realized by components for executing the bot-based role-playing method described below. Depending on the embodiment, the components of the processor 220 may be selectively included or excluded from the processor 220. Also, depending on the embodiment, the components of the processor 220 may be separated or combined to express the functions of the processor 220.
[0045] Such processor 220 and components of processor 220 may control computing device 200 to perform steps included in the bot-based role-playing method described below. For example, processor 220 and components of processor 220 may be implemented to execute instructions from operating system code and at least one program code contained in memory 210.
[0046] Here, the components of the processor 220 may represent different functions that are performed by the processor 220 according to instructions provided by program code stored in the computing device 200 .
[0047] The processor 220 may read the necessary instructions from the memory 210, which is loaded with instructions related to the control of the computing device 200. In this case, the read instructions may include instructions for controlling the processor 220 to perform the steps described below.
[0048] The steps included in the bot-based role-playing method described below may be performed in an order different from that shown in the figures, some of the steps may be omitted, or additional processes may be included.
[0049] The steps involved in the bot-based role-playing method may be performed on the server 150, although in some embodiments at least some of the steps may be performed on the client.
[0050] FIG. 3 is a flow chart illustrating an example method that may be performed by a computing device in accordance with an embodiment of the present invention.
[0051] Referring to FIG. 3, in step 310, when a script is provided by an administrator of the open chat, the processor 220 may generate a bot by learning each character included in the script using a language model. Here, the script may refer to a primary content that is a bundle of texts including lines of a plurality of characters, such as a screenplay or a novel. The processor 220 may receive the script provided by the administrator through another administrator channel in the open chat. In some embodiments, the processor 220 may receive a script inputted together with an administrator tag (e.g., bot#, etc.) requesting the generation of a bot through a chat room of the open chat. In this case, the processor 220 may receive character profile information (e.g., age, personality, nationality, introduction, etc.) and information on the era or region that is the background of the script as additional information together with the script. After that, the processor 220 may input the script into an artificial intelligence language model capable of understanding and generating natural language, such as a GPT (generative pre-trained transformer) model specialized for conversation, and may generate a chatbot (hereinafter referred to as a "character bot") reflecting the persona of each character by analyzing and learning the lines of each character using this language model. The language model may learn the characters based on the script, including not only the lines of the characters but also the interactions and situations in the script, and may further perform learning that reflects profile information, era information, area information, and the like given as additional information for each character or script. Thus, the processor 220 can generate multiple character bots for role-playing in open chat by learning the script given by the administrator using the artificial intelligence language model.
[0052] In step 320, the processor 220 may generate a specific situation based on external information in relation to a character bot (hereinafter referred to as a "first character bot") participating in the conversation of the open chat, and push the situation to the chat room of the open chat as a conversation message of the first character. In this embodiment, a role-playing game in which the role of at least one of the multiple character bots is played by a user participating in the open chat may be provided through the open chat, and at this time, some of the multiple character bots may also participate in the conversation. In role-playing, the situation given to the character is also extremely important. The role-playing bot learns various situations in the script along with the lines of the character based on the script, which is the primary content. The processor 220 may generate a conversation message of the first character by associating external information such as actual offline weather, season, location, time, and recent issues with the situation used in learning about the first character bot. In other words, the processor 220 can automatically suggest a specific situation generated by combining the learned situation of the first character bot with external information that can be obtained as actual offline information, as conversation material for role-playing using the first character bot.
[0053] In step 330, when a user participating in an open chat plays the role of a specific character bot (hereinafter, referred to as a "second character bot") among a plurality of character bots and participates in a conversation in the open chat, the processor 220 may determine the user's suitability for role-playing with respect to the second character based on the second character bot. The processor 220 may determine how much the human user's imitation matches the actual character based on the character bot generated using an artificial intelligence language model. As an example, the processor 220 may compare the content of the user's answer to a conversation message of the other party in the conversation (another character bot or another user playing the role of another character bot), i.e., a given situation, with the content of the answer of the second character bot, and determine how much the user is suitable for role-playing based on the similarity of the answers. As another example, the processor 220 may determine how much the user is suitable for role-playing based on a score given to the user's answer by a role-playing master (e.g., an administrator of the open chat) set in the open chat. As another example, the processor 220 may determine the user's suitability for role-playing by weighting the similarity of the user's answer compared to the answer of the second character bot according to the role-playing master's score. For example, even if the user's answer is not similar to the answer of the second character bot, if the master judges that the answer shows a high level of understanding of the character, the suitability may be evaluated high. As another example, the processor 220 may determine the user's suitability for role-playing based on whether the user's answer matches additional information such as profile information, period information, and area information given to the second character bot. For example, if the second character is a person who appeared in a historical drama set in the Joseon period, such period information may be used as a standard, and if the user's answer contains a foreign word, it may be determined to be a mismatch with the period information and a low suitability score may be assigned.As yet another example, the processor 220 may vote for the answers of the user playing the role of the second character among other users participating in the open chat, and determine the user's suitability for role-playing the second character based on the voting results.
[0054] The processor 220 may then determine the casting of the user for the second character based on the user's role-playing suitability. For example, if the user's role-playing suitability for the second character is below a threshold, the user may be removed from the role of the second character, and the second character bot or another user participating in the open chat may be cast as a role-playing participant for the second character.
[0055] In step 340, the processor 220 may generate secondary content for the open chat based on the role-playing conversation messages included in the open chat. The processor 220 may divide a series of conversations between the character bot and the user cast as a role-playing participant into episodes based on a theme and use the episodes as secondary content. As an example, the processor 220 may generate, as secondary content, the conversation content of a section selected by an administrator of the open chat or a user with a predetermined authority among users participating in the open chat. As another example, the processor 220 may compare the conversation between the character bot and the user cast as a role-playing participant with a script that is the primary content, and generate secondary content based on similarity. For example, the processor 220 may generate, as secondary content, the conversation content of a section whose similarity with the primary content has fallen below a certain level, i.e., different from the content of the primary content. As another example, the processor 220 may select major messages with high involvement, popularity, or informationality from messages included in the chat room of the open chat, and generate the selected messages as secondary content. At this time, processor 220 may select the main message using information that can be derived from the chat room of the open chat, such as the number of simultaneous participants and the number of messages, the duration of stay (e.g., the time value obtained by subtracting the time of entering the chat room from the time of leaving the chat room), and keywords included in the message. As an example of selecting the main message, processor 220 may compare the messages included in the chat room with the primary content, and select as the main message a message that contains a large number of significant words among words that do not exist in the primary content. In other words, a message that contains newer content than the primary content may be selected as the main message.As another example, the processor 220 may select at least one message as a key message based on the point in time when the number of users participating (connecting) in the chat room in the same time period is equal to or greater than a threshold, the point in time when the number of messages in the chat room in the same time period is greater than or equal to a threshold, or the point in time when the average stay time of each user participating in the chat room is greater than or equal to a threshold. As another example, the processor 220 may select a message including a keyword set in advance by an administrator of the open chat as a message that is likely to be useful to users in terms of information. At least one or more keywords of interest to the administrator may be set in advance by settings for the chat room of the open chat, and the processor 220 may select a message including a specific keyword set by the administrator as a key message from among the messages included in the chat room. In addition to the keywords set by the administrator of the open chat, it is also possible to select a key message using a keyword that matches the category of the chat room. As another example, the processor 220 may analyze conversation patterns in the chat room to extract a topic that is highly topical, and may select a message that matches this topic as a key message. After extracting at least one word that has become a topic in the chat room in a unit time period, the processor 220 may determine, for each message in the chat room, a word exceeding a certain level as a topic having high topicality using a probability distribution of the topic. The processor 220 may select, as a main message, a message that includes a keyword that is the same as or similar to each theme from among the messages in the chat room. As another example, the processor 220 may track the view time of users participating in the chat room and select, as a main message, a message in an area that has a view that is higher than the average by a certain percentage or more. As another example, the processor 220 may select a main message based on the reaction of other users participating in the chat room.For example, the processor 220 may select as key messages from among messages included in an open chat room those messages that have received positive reactions from other users, such as “likes,” “mentions,” “replies,” “comments,” “shares,” “captures,” and “keeps,” that meet predefined conditions.
[0056] Thereafter, the processor 220 may generate the key message selected from the chat room of the public chat as a secondary content in a form that can be shared through various screens (e.g., chat room, main screen, etc.) of this or another public chat. As an example, the processor 220 may convert the key message into content in the form of an image by, for example, taking a screen capture of an area in the chat room of the public chat that includes the key message. As another example, the processor 220 may convert the key message into content in the form of a video by, for example, recording a screen of an area in the chat room that includes the key message. The secondary content in the form of a video may be generated in various types of content such as GIF (graphics interchange format) in which the key messages are displayed in chronological order using graphic techniques such as animation and effects, in addition to the screen recording method. The secondary content may be shared with users who have never experienced role-playing in the public chat, which may not only stimulate interest but also induce subscription and service activation of the public chat.
[0057] Therefore, by utilizing the artificial intelligence language model, the processor 220 can more easily and quickly generate a role-playing bot for use in an open chat, and the role-playing bot generated using the artificial intelligence language model can be used for various functions within the open chat.
[0058] FIG. 4 is an exemplary diagram illustrating a process of generating a character bot for role-playing in an embodiment of the present invention.
[0059] Referring to FIG. 4, the processor 220 may receive a script 40 provided by an administrator through another administrator channel in the open chat, and input it into an artificial intelligence language model 400 .
[0060] The script 40 may mean a bundle of texts such as a screenplay or a novel that includes lines of multiple characters, and multiple character bots 401, 402, and 403 may be generated from the script 40. Depending on the embodiment, it is also possible to individually give each character a script 40 that is generated based on the lines of that character.
[0061] The artificial intelligence language model 400 may generate character bots 401, 402, and 403 reflecting the persona of each character by analyzing and learning the lines of each character included in the script 40. At this time, the artificial intelligence language model 400 may learn not only the lines of the characters but also interactions and situations in the script 40, and may further execute learning by reflecting profile information, era and region information, and the like of each character given as additional information.
[0062] Therefore, the processor 220 can generate multiple character bots 401, 402, 403 for role-playing in open chat by utilizing the artificial intelligence language model 400 to learn the conversation of each character based on the script 40 provided by the administrator.
[0063] In the following, it is assumed that role-playing bots, character A, character B, and character C, have been generated for open chat I.
[0064] FIG. 5 is an exemplary diagram illustrating a role-playing conversation between a character bot and a user in one embodiment of the present invention.
[0065] In open chat I, a role-playing game may be provided in which the role of at least one of characters A, B, and C is taken on by a user participating in open chat I.
[0066] 5 shows a chat room 500 of an open chat I displayed on an electronic device of a user X who has been cast in the role of character B. In the chat room 500 of the open chat I, the user X may take on the role of character B and input a conversation message 501 in which the user X plays character B.
[0067] In the chat room 500 of the open chat I, the character A bot may directly participate in the conversation, and at this time, the character A bot may generate a conversation message for the role-playing situation by associating external information such as the actual offline weather, season, location, time, and recent issues with the situation used for learning. For example, on the morning of a day when light rain is predicted according to the weather forecast, the character A bot may push a specific situation based on external information as a conversation topic, such as "I left home this morning without an umbrella and arrived at the bus stop, but suddenly it started to rain lightly," taking into account the situation learned in advance.
[0068] In the chat room 500 of the open chat I, a user X playing the role of character B can carry on a role-playing conversation with the character A bot, suggesting various situations as topics of conversation to each other.
[0069] 6 and 7 are exemplary diagrams for setting a process according to a user's suitability for role-playing in an embodiment of the present invention.
[0070] Processor 220 may use conversation message 501 of user X playing the role of character B to determine the role-playing suitability of user X for character B. After acquiring the answer of character B bot to a situation given as a conversation message of character A bot, processor 220 may compare the answer of character B bot with conversation message 501 input as the answer of user X, and determine the role-playing suitability of user X based on the similarity of the answers.
[0071] Depending on the embodiment, the role-playing suitability of user X, who plays the role of character B, may be determined based on the evaluation results of a role-playing master (e.g., an administrator of the open chat) set in open chat I for the conversation message 501, whether it matches with additional information such as profile information, era information, and region information given to character B, and the voting results of other users participating in open chat I.
[0072] If the role-playing suitability determined based on the conversation messages 501 of user X playing the role of character B is below a threshold, the processor 220 may remove user X from the role of character B and have a character B bot join open chat I, or cast another user participating in open chat I as a role-playing participant for character B in place of user X.
[0073] When user X is removed from the role of character B, processor 220 may provide user X with a notification of exclusion 610 due to incompatibility with role-playing through open chat I chat room 500 as shown in Fig. 6. Meanwhile, referring to Fig. 7, a notification of exclusion 720 to user X, who is a participant in the previous role-playing for character B, may be displayed in chat room 700 of open chat I displayed on the electronic devices of other users participating in open chat I. After user X is removed, other users participating in open chat I may request role-playing participation for character B.
[0074] 8 and 9 are exemplary diagrams illustrating a process of generating secondary content of an open chat according to an embodiment of the present invention.
[0075] In chat room 500 of Open Chat I, a character A bot and a character C bot are participating in a role-playing conversation with user X who is playing the role of character B.
[0076] Referring to FIG. 8, the processor 220 may select key messages 801 that have high engagement, popularity, or informationality from among the messages contained in the chat room 500 of the open chat I (i.e., conversation messages exchanged between the character A bot, the character C bot, and the user X).
[0077] The processor 220 may compare messages contained in a chat room with a script that is the primary content, and select as the main message 801 a message that contains a certain number or more of significant words that are not present in the primary content.
[0078] As another example, the processor 220 may select the main message 801 using the number of simultaneous participants, the number of messages, the duration of stay, or keywords included in the message. For example, the processor 220 may determine, as the main message 801, a message at a moment when there were many instantaneous connections in the same time period, when there was a sudden increase in messages in the same time period, or when the average duration of stay of each user was long.
[0079] As another example, the processor 220 may use keywords included in conversation messages to select the main messages 801. For example, a message including a keyword set by an administrator of the open chat I or a keyword matching a category of the open chat I may be classified as a main message 801.
[0080] In some embodiments, the view times of users participating in the chat room 500 of Open Chat I may be tracked, and messages in an area that have views that are higher than the average by a certain percentage or more may be classified as key messages 801 .
[0081] 9, the processor 220 may generate the main message 801 selected from the chat room 500 of the open chat I as the content 910 in the form of an image or video. For example, the processor 220 may generate the secondary content 910 of the open chat I by making the area including the main message 801 in the chat room 500 of the open chat I into a content by a method such as screen capture or screen recording.
[0082] Therefore, the processor 220 can produce secondary content 910 of the open chat I by selecting the main messages 801 from among the messages in the chat room 500 of the open chat I.
[0083] FIG. 10 is an exemplary diagram illustrating a process of sharing secondary content in an open chat according to an embodiment of the present invention.
[0084] FIG. 10 shows a chat room 1000 of open chat II that has a relationship with open chat I.
[0085] The administrator of the public chat may set subscriptions to other public chats of similar themes or interests in relation to his / her own public chat. For example, the administrator of the chat room of the public chat II may input permission to subscribe to other public chats in the chat room settings of the public chat. According to such settings, the computer device 200 or another computer device electrically connected to the computer device 200 may select the public chat I of similar theme or included in the same category as the chat room of the public chat II, and the processor 220 may provide the secondary content 910 of the public chat I subscribed to the public chat II through the chat room 1000 of the public chat II. As another example, the administrator of the chat room of the public chat II may input a theme of interest in the chat room settings of the public chat. According to such settings, the computer device 200 or another computer device electrically connected to the computer device 200 may select the public chat I related to the input theme of interest, and the processor 220 may provide the secondary content 910 of the public chat I subscribed to the public chat II through the chat room 1000 of the public chat II. As another example, an administrator of Open Chat II may set up a subscription for Open Chat I in Open Chat II, at which time the processor 220 may provide the secondary content 910 of Open Chat I that has been subscribed to in Open Chat II through the chat room 1000 of Open Chat II.
[0086] At this time, the secondary content 910 of the open chat I may be displayed in the form of a conversation message of the administrator of the open chat II or a content bot (a bot dedicated to providing secondary content of other open chats) participating in the open chat II, and may be provided together with the open chat information 1020 which is the source of the content. The open chat information 1020 may include link information for linking to a cover concept page associated with the open chat I which is the source of the content, in order to induce participation in the open chat.
[0087] Users participating in Open Chat II can share secondary content 910 of Open Chat I through the chat room 1000 of Open Chat II, and can identify this content as content of Open Chat I based on the open chat information 1020.
[0088] In this manner, according to an embodiment of the present invention, an artificial intelligence model can be used to quickly generate role-playing bots on a social platform, and the role-playing bots can be utilized for various purposes within the social platform, such as determining role-playing suitability, creating role-playing situations, and creating secondary content.
[0089] The above-mentioned devices may be realized by hardware components, software components, and / or a combination of hardware and software components. For example, the devices and components described in the embodiments may be realized using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or various devices capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications that run on the OS. The processing device may also respond to the execution of the software to access, record, manipulate, process, and generate data. For convenience of understanding, a single processing device may be described as being used, but one skilled in the art will understand that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, the processing device may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.
[0090] The software may include computer programs, codes, instructions, or a combination of one or more of these, and may configure a processing device to operate as desired or instruct the processing device, either independently or collectively. The software and / or data may be embodied in any type of machine, component, physical device, computer storage medium, or device to be interpreted by the processing device or to provide instructions or data to the processing device. The software may be distributed and stored or executed in a distributed manner on computer systems connected by a network. The software and data may be stored on one or more computer-readable storage media.
[0091] The method according to the embodiment may be realized in the form of program instructions executable by various computer means and recorded on a computer-readable medium. In this case, the medium may be one that continuously records a computer-executable program or one that temporarily records the program for execution or download. The medium may be one of various recording means or storage means in the form of a single or multiple hardware devices combined, and may be one that is directly connected to a computer system, as well as one that is distributed on a network. Examples of the medium include magnetic media such as hard disks, floppy (subscription trademark) disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and those configured to record program instructions such as ROMs, RAMs, flash memories, etc. Examples of other media include recording media and storage media managed by app stores that distribute applications, sites that supply or distribute various other software, and servers.
[0092] Although the embodiments have been described based on the limited embodiments and drawings as above, those skilled in the art will be able to make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from that described, and / or the components of the described systems, structures, devices, circuits, etc. may be combined or combined in a manner different from that described, or may be counterbalanced or replaced by other components or equivalents, and still achieve suitable results.
[0093] Therefore, different embodiments are within the scope of the appended claims provided that they are equivalent to the claims. [Explanation of symbols]
[0094] 40: Script 400: Artificial Intelligence Language Model 401, 402, 403: Character
Claims
1. A bot-based role-playing method executed on a computer device, comprising: The computing device includes at least one processor configured to execute computer-readable instructions contained in a memory; The bot-based role-playing method includes: receiving, by the at least one processor, a script provided in the public chat; and and generating, by the at least one processor, a plurality of character bots for role-playing in the open chat by learning each character included in the script using an artificial intelligence language model. Including, bot-based role-playing methods.
2. The generating step includes: learning said character from at least one of dialogue, interaction, or situational information in said script; The bot-based role-playing method of claim 1 , comprising:
3. The generating step includes: learning the character from at least one of the character's profile information, the time period or the region information of the background of the script; The bot-based role-playing method of claim 1 , comprising:
4. The bot-based role-playing method includes: providing a role-playing game in which a user participating in the open chat plays a role of at least one of the plurality of character bots in the open chat by using the at least one processor; The bot-based role-playing method of claim 1 , further comprising:
5. The bot-based role-playing method includes: A step of pushing a role-playing situation linked to external information based on a situation used for learning of the character bot by using a character bot participating in the conversation in the open chat among the plurality of character bots by the at least one processor. The bot-based role-playing method of claim 1 , further comprising:
6. The bot-based role-playing method includes: determining, by the at least one processor, the role-playing suitability of a user who plays a role of a specific character bot among the plurality of character bots, based on the specific character bot; The bot-based role-playing method of claim 1 , further comprising:
7. The determining step includes: Determining the user's suitability for role-playing based on a response similarity obtained by comparing the response of the user with a response of the specific character bot for a given situation. The bot-based role-playing method according to claim 6 .
8. The determining step includes: The role-playing suitability of the user is determined based on at least one of the following: the result of evaluation by a role-playing master set in the open chat from the conversation message input by the user, whether or not it matches with information used at the time of learning about the specific character bot, and the result of voting by other users participating in the open chat. The bot-based role-playing method according to claim 6 .
9. The bot-based role-playing method includes: generating, by the at least one processor, secondary content for the public chat based on role-playing conversations included in the public chat; The bot-based role-playing method of claim 1 , further comprising:
10. The step of generating the secondary content includes: Selecting major messages from conversation messages included in the open chat based on the script, and generating the major messages as the secondary content. The bot-based role-playing method according to claim 9 .
11. A program for causing a computer device to execute the bot-based role-playing method according to any one of claims 1 to 10.
12. 1. A computing device comprising: At least one processor configured to execute computer-readable instructions contained in the memory. Including, The at least one processor receiving a script given in an open chat; and generating a plurality of character bots for role-playing in the open chat by learning each character included in the script using an artificial intelligence language model; A computer device that processes.
13. The at least one processor learning said character from at least one of dialogue, interactions, or situational information in said script; 13. The computer device of claim 12.
14. The at least one processor Learning the character from at least one of the character's profile information, the time period in which the script is set, or locale information.
13. The computer device of claim 12.
15. The at least one processor To provide a role-playing game in which a user participating in the open chat plays a role of at least one of the plurality of character bots in the open chat.
13. The computer device of claim 12.
16. The at least one processor Using a character bot participating in a conversation in the open chat among the plurality of character bots, a role-playing situation linked to external information is pushed based on a situation used in the learning of the character bot.
13. The computer device of claim 12.
17. The at least one processor For a user who plays a role of a specific character bot among the plurality of character bots, determining the role-playing suitability of the user based on the specific character bot.
13. The computer device of claim 12.
18. The at least one processor Determining the user's suitability for role-playing based on a response similarity obtained by comparing the response of the user with a response of the specific character bot for a given situation.
20. The computer device of claim 17,
19. The at least one processor The role-playing suitability of the user is determined based on at least one of the following: the result of evaluation by a role-playing master set in the open chat from the conversation message input by the user, whether or not it matches with information used at the time of learning about the specific character bot, and the result of voting by other users participating in the open chat.
20. The computer device of claim 17,
20. The at least one processor Generating secondary content of the open chat based on role-playing conversations included in the open chat.
13. The computer device of claim 12.
Citation Information
Patent Citations
Service system and method for mobile messenger ofmobile phone using wireless communication network
KR1020020074304A
