Customized avatar management method, computer device, and program

Abstract

To provide a method for managing an artificial intelligence-based customized avatar for social media, a computer device, and a program.SOLUTION: A customized avatar management method includes the steps of: generating an avatar with nature based on setting of a user as an avatar that acts social media activities on behalf of the user; and optimizing the nature of the avatar on the basis of user evaluation (rating) with respect to a dialogue of the avatar.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The following description relates to a technology for managing social media activities.

Background Art

[0002] Social media, such as social networking services (SNS) and messengers, collectively refers to services that connect people-to-people relationships, thereby forming relationships among users and supporting interactions through posts.

[0003] Social media provides users with information in different contexts. For example, social media provides update information on users' connection relationships, update information on posts, content recommendations, and various other types of information content.

[0004] For example, Patent Document 1 (registration date: June 29, 2017) discloses a technology for managing posts using SNS.

[0005] With the popularization of social media, as the functions provided by social media platforms diversify, a video platform service that distributes and shares short-form content created as short videos of 15 seconds to 10 minutes has come to be provided.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] Create a user-customized digital avatar according to the user's preferences and activity goals, and thereby substitute the user's social media activities.

[0008] Reflect the activity content on social media in learning, and continuously strengthen the avatar to meet the purposes set by the user.

[0009] Optimize the personality of the avatar in detail based on the responses in the basic dialogue set, the responses to the user's questions, and further the user's evaluation (rating) of the responses.

[0010] Specifically set and manage avatar activities such as the avatar's activity range and the ratio of activities for each concern.

[0011] Thoroughly manage the content generated by the avatar by setting the inspection of each detailed item regarding the content.

[0012] Group and summarize the comments created for the avatar's posts by theme, and then propose responses regarding each group.

Means for Solving the Problem

[0013] A customized avatar management method for a computer device including at least one processor, including the step of generating, by at least one processor, an avatar with a disposition based on user settings as an avatar that substitutes the user's social media activities, and the step of optimizing, by at least one processor, the disposition of the avatar based on the user evaluation (rating) of the avatar's dialogue, to provide a customized avatar management method.

[0014] According to one aspect, the generating step may include the step of determining the personality type and speaking style type assigned to the avatar based on the information input by the user.

[0015] According to another aspect, the generating stage may further include a stage of reinforcing the information input by the user through data augmentation using generative artificial intelligence.

[0016] According to yet another aspect, the optimizing stage may include a stage of collecting at least one of the avatar's answer in the basic dialogue set and the avatar's answer to the user's question, a stage of screening at least some of the avatar's answers based on the user evaluation of the avatar's answers, and a stage of modifying at least one of the personality type and the speaking style type assigned to the avatar based on the selected answers.

[0017] According to yet another aspect, the customized avatar management method may further include a stage of executing the avatar's social media activities within the activity range set by the user by at least one processor.

[0018] According to yet another aspect, the executing stage includes a stage of setting at least one concern corresponding to the activity field as the avatar activity range, and the setting stage may include a stage of setting the ratio of activities for each concern.

[0019] According to yet another aspect, the executing stage may include a stage of setting at least one of the activity type and the generated content type as the avatar activity range.

[0020] According to yet another aspect, the executing stage may include a stage of inspecting the generated content of the avatar based on the user's content inspection settings.

[0021] According to yet another aspect, the executing stage includes a stage of setting at least one concern corresponding to the activity field as the avatar activity range, and a stage of registering the generated content of the avatar as a comment or reaction to the post when the posts of other users match the concern.

[0022] According to yet another aspect, the customizable avatar management method may further include a step of grouping comments of other users on an avatar post by theme by at least one processor, and providing at least one of a summary of the comments of each group and a predicted response of the avatar.

[0023] Provided is a computer program recorded on a computer-readable recording medium for causing a computer device to execute a customizable avatar management method. Also provided is a computer program for causing a computer device to execute a customizable avatar management method.

[0024] Provided is a computer device including at least one processor that executes instructions readable by the computer device, wherein the at least one processor generates an avatar with a propensity based on user settings as an avatar that substitutes for the user's social media activities, and the at least one processor optimizes the propensity of the avatar based on user evaluation of the avatar's interaction.

Effects of the Invention

[0025] A digital avatar can be created according to the user's preferences and activity goals, thereby enabling the avatar to substitute for the user's social media activities.

[0026] Also, based on the activity content on social media, the avatar can be continuously enhanced to meet the purpose set by the user.

Brief Description of the Drawings

[0027]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Best Mode for Carrying Out the Invention

[0028] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0029] Embodiments of the present invention relate to a technology for creating and managing an avatar that substitutes for a user's social media activities.

[0030] Embodiments including the matters specifically disclosed in this specification can generate a user-customized digital avatar that substitutes for a user's social media activities in a generative artificial intelligence (AI) environment, thereby enhancing the management and operation efficiency of social media.

[0031] The customizable avatar management system according to an embodiment of the present invention may be implemented by at least one computer device, and the customizable avatar management method according to an embodiment of the present invention may be executed by at least one computer device included in the customizable avatar management system. At this time, in the computer device, a computer program according to an embodiment of the present invention may be installed and executed, and the computer device may execute the customizable avatar management method according to an embodiment of the present invention according to the control of the executed computer program. The above-described computer program may be recorded on a computer-readable recording medium in combination with the computer device to cause the computer to execute the customizable avatar management method.

[0032] FIG. 1 is a diagram showing an example of a network environment in an embodiment of the present invention. The network environment of 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 a FIG. 1 is merely an example for explaining the invention, and the number of electronic devices and the number of servers are not limited as in FIG. 1. Further, the network environment of FIG. 1 is merely an example for explaining an environment applicable to the present embodiment, and the environment applicable to the present embodiment should not be limited to the network environment of FIG. 1.

[0033] The plurality of electronic devices 110, 120, 130, 140 may be fixed terminals or mobile terminals realized by a computer device. Examples of the plurality of electronic devices 110, 120, 130, 140 include smartphones, mobile phones, navigation devices, PCs (personal computers), notebook PCs, digital broadcast terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablets, and the like. As an example, in FIG. 1, a smartphone is shown as an example of the electronic device 110. However, in the embodiments of the present invention, the electronic device 110 may mean one of various physical computer systems that substantially utilize a wireless or wired communication method and can communicate with other electronic devices 120, 130, 140 and / or servers 150, 160 via the network 170.

[0034] The communication method is not limited, and it includes not only a communication method that utilizes a communication network that the network 170 can include (for example, a mobile communication network, a wired Internet, a wireless Internet, a broadcast network), but also short-range wireless communication between devices. For example, the network 170 may include any one or more of networks such as a PAN (personal area network), a LAN (local area network), a CAN (campus area network), a MAN (metropolitan area network), a WAN (wide area network), a BBN (broadband network), and the Internet. Further, the network 170 may include any one or more of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, etc., but is not limited thereto.

[0035] Each of the servers 150 and 160 may be implemented by one or more computer devices that communicate with a plurality of electronic devices 110, 120, 130, and 140 via a network 170 to provide instructions, code, files, content, services, and the like. For example, the server 150 may be a system that provides services (such as, for example, a social media service) to a plurality of electronic devices 110, 120, 130, and 140 connected via the network 170.

[0036] FIG. 2 is a block diagram showing an example of a computer device in one embodiment of the present invention. Each of the plurality of electronic devices 110, 120, 130, and 140 and each of the servers 150 and 160 described above may be implemented by the computer device 200 shown in FIG. 2.

[0037] As shown in FIG. 2, such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input / output interface 240. The memory 210 is a computer-readable recording medium and may include a RAM (random access memory), a ROM (read only memory), 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 another separate permanent recording device from the memory 210. Also, an operating system and at least one program code may be recorded in the memory 210. Such software components may be loaded into the memory 210 from another computer-readable recording medium different from the memory 210. Such another computer-readable recording medium may include computer-readable recording media such as a floppy (registered trademark) drive, a disk, a tape, a DVD / CD-ROM drive, and a memory card. In other embodiments, the software components may be loaded into the memory 210 through the communication interface 230 which is not a computer-readable recording medium. For example, the software components may be loaded into the memory 210 of the computer device 200 based on a computer program installed by a file received via the network 170.

[0038] 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 recorded in a recording device such as the memory 210.

[0039] The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (for example, the recording device described above) via the network 170. As an 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 through the communication interface 230 of the computer device 200 via the network 170. Signals, instructions, data, etc. received through the communication interface 230 may be transmitted to the processor 220 and the memory 210, and files, etc. may be recorded in a recording medium (the permanent recording device described above) that the computer device 200 can further include.

[0040] The input / output interface 240 may be means for interfacing with the input / output device 250. For example, the input device may include devices such as a microphone, a keyboard, or a mouse, and the output device may include devices such as a display and a speaker. As another example, the input / output interface 240 may be 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 one device with the computer device 200.

[0041] Also, in other embodiments, the computer device 200 may include fewer or more components than the components shown in FIG. 2. However, it is not necessary to clearly show most of the conventional components in the figure. For example, the computer device 200 may be implemented to include at least a part of the input / output device 250 described above, or may further include other components such as a transceiver and a database.

[0042] Hereinafter, specific embodiments of a method and an apparatus for managing an artificial intelligence-based customized avatar for social media will be described.

[0043] As used herein, social media may include not only social network services such as messengers and various communities, but also an integrated media platform that provides various services that utilize resources such as user profile information and friendship relationships within the social network service.

[0044] The computer device 200 according to this embodiment may provide a social media 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. The computer device 200 may be configured with a customized avatar management system implemented by a computer. As an example, the customized avatar management system may be implemented in the form of an independently operating program, or may be configured in the in-app form of a specific application and implemented to be operable on the specific application.

[0045] The processor 220 of the computer device 200 may be implemented by components for executing the following customized avatar management method. Depending on the embodiment, the components of the processor 220 may be selectively included in the processor 220 or excluded from the processor 220. Also, depending on the embodiment, the components of the processor 220 may be separated or combined for expressing the functions of the processor 220.

[0046] Such a processor 220 and the components of the processor 220 may control the computer device 200 to execute the steps included in the following customized avatar management method. For example, the processor 220 and the components of the processor 220 may be implemented to execute instructions by the code of the operating system included in the memory 210 and the code of at least one program.

[0047] Here, the components of the processor 220 may be representations of different functions that are executed by the processor 220 according to the instructions provided by the program code recorded in the computer device 200.

[0048] The processor 220 may read the necessary instructions from the memory 210 in which the instructions related to the control of the computer device 200 are loaded. In this case, the read instructions may include instructions for controlling the processor 220 to execute the steps described below.

[0049] The steps included in the customized avatar management method described below may be executed in an order different from that shown in the figure, or some of the steps may be omitted, or additional processes may be further included.

[0050] The steps included in the customized avatar management method may be executed on the client, and in some embodiments, at least some of the steps may also be executed on the server 150.

[0051] FIG. 3 is a flowchart showing an example of a method that can be executed by a computer device in an embodiment of the present invention.

[0052] Referring to FIG. 3, at stage 310, the processor 220 may generate a user-customized digital avatar based on the user's settings and evaluations. The processor 220 generates a virtual avatar in the form of a chatbot that can communicate with other users on behalf of the user on social media, and may generate an avatar with user-customization settings. At this time, as basic settings for the avatar from the user, the processor 220 may receive input of basic information such as name, age, gender, region, personality, speaking style, and interests, and generate the initial personality and speaking style of the avatar based on the basic information input by the user through generative artificial intelligence. After that, the processor 220 may obtain the avatar's responses in the pre-prepared basic dialogue set based on the basic information input by the user, and then optimize while correcting the avatar's personality and speaking style based on the user's evaluation of the avatar's responses.

[0053] At stage 320, the processor 220 may automatically execute the social media activities of the user account on behalf of the user using the avatar generated at stage 310 within the activity range set by the user. The avatar may automatically execute social media activities such as communication with other users and content upload (i.e., posting) according to the personality and speaking style given by the user-customization settings within the range permitted by the user. The avatar activity range may be set by the user, and at this time, it may include the activity types and fields (interests) in which the avatar can act, the content types that can be generated for the activity, the information to be transmitted through the avatar, and the like. The processor 220 may automate the social media activities within the range permitted by the user on behalf of the user using the avatar.

[0054] In stage 330, the processor 220 may provide a report on the avatar's social media activities to the user. By providing the user with activity reports at regular intervals, statistical and analytical information regarding avatar activities can be informed. The processor 220 may provide activity statistical information for each unit period (e.g., day, week, month, etc.), and for example, visualize and show the responsiveness of other users to each piece of content generated by the avatar. Also, the processor 220 may support the re - setting of a personality and speaking style suitable for the user's purpose by repeating the adjustment of detailed avatar settings based on user evaluations of avatar activities such as content generated by the avatar. Furthermore, after extracting the reactions of other users to avatar activities and organizing them into items for which common answers are possible, the processor 220 may provide a theme (category), summary, predicted answers, etc. based on the organized results. For example, the processor 220 may group and classify the comments registered on the posts uploaded by the avatar by theme, and then provide, as an item for which a common answer is possible, the content summarizing the comments of the corresponding group for each group. When generating and providing predicted answers for comments made on the avatar's posts, the processor 220 may reflect the avatar's personality and speaking style in the predicted answers.

[0055] Figure 4 is an example showing the procedure for basic avatar settings. Figure 4 is an interface screen for user settings and shows the basic avatar setting screen 400.

[0056] Referring to FIG. 4, the basic avatar setting screen 400 includes an interface for inputting basic setting values of a character as information necessary to endow the avatar with characteristics. The processor 220 may receive, through the basic avatar setting screen 400, input of basic information such as name, age, gender, region (nationality), personality, speaking style, and interests as basic settings for the avatar. At this time, in order to reflect the personality and speaking style, a personality description and example sentences are required. For example, the personality information may receive input of the personality to be reflected in the avatar described in at least 5 paragraphs or more, and the speaking style information may receive input of the speaking style to be reflected in the avatar with 50 or more example sentences. Also, for interests, one or more items may be input or selected with reference to social media categories (for example, fashion, media, food, dance, games, sports, etc.).

[0057] Since it is not easy for the user to directly input all the characteristics of the avatar, in some embodiments, based on the personality and speaking style information input by the user on the basic avatar setting screen 400, it is also possible to additionally generate personality and speaking style information by data expansion using generative artificial intelligence to reinforce the user input.

[0058] The processor 220 may determine and provide a personality type 401 and a speaking style type 402 that the user wants to reflect in the avatar based on the information input by the user on the basic avatar setting screen 400. As an example, the processor 220 may extract main keywords from the personality description input by the user and show this as the personality type 401, and may grasp and show the speaking style type 402 such as the quirks, attitudes, and manners that can be read from the example sentences input by the user. The user can confirm whether the personality and speaking style desired by the user are set in the avatar through the personality type 401 and the speaking style type 402. However, if there is a type that goes against the properties desired by the user in the process of confirming the personality type 401 and the speaking style type 402, for example, the user may be able to request to modify the user input or exclude it so that the type is not reflected in the avatar.

[0059] FIG. 5 is an example showing a detailed avatar setting procedure. FIG. 5 shows a detailed avatar setting screen 500 using a basic dialogue set.

[0060] The processor 220 may use generative artificial intelligence to execute a basic dialogue set prepared in advance based on the personality and speaking style of the avatar set through the basic avatar setting environment. Referring to FIG. 5, the processor 220 may show, on the detailed avatar setting screen 500, the avatar whose personality and speaking style are given through the basic avatar setting and the dialogue content exchanged in the basic dialogue set. The processor 220 may collect the answers of the avatar whose personality and speaking style are given in the basic dialogue set, and in addition to the basic dialogue set prepared in advance, the answers of the avatar may be additionally collected by a method in which the user directly asks questions to the avatar and the avatar answers the user's questions. The answers of the avatar in the basic dialogue set and the answers of the avatar to the user's questions may be generated by generative artificial intelligence reflecting the personality and speaking style of the avatar.

[0061] In this embodiment, an interface 501 for direct user rating of avatar responses in the basic dialogue set and avatar responses to user questions may be provided. At this time, the user may assign a score to each avatar response. After the processor 220 executes iterative dialogues using the basic dialogue set and user questions to collect avatar responses, the avatar responses may be screened based on the user's evaluation. For example, responses with scores above a threshold given by the user may be selected from the avatar responses to reinforce the user input for the personality and speaking style information in the basic avatar setting screen 400. That is, the responses of the avatar selected based on the user's evaluation will be additionally reflected in the personality and speaking style of the avatar. By repeating the collection and evaluation of responses in the dialogue with the avatar and modifying or supplementing the personality type 401 and speaking style type 402 of the avatar, avatar learning may be repeated until the personality and speaking style desired by the user are defined. The processor 220 can optimize the prompt by refining the prompt for extracting consistent behavior with generative artificial intelligence through the above-described detailed avatar settings for the avatar given personality and speaking style according to the user's settings.

[0062] FIG. 6 is an example showing the procedure of avatar activity setting.

[0063] In this embodiment, an explanation will be given of the avatar acting on behalf of the user's social media activities and automating avatar activities within the range permitted by the user. Referring to FIG. 6, the avatar activity setting screen 600 includes an interface for setting, as the avatar activity range, a basic activity range 601, a detailed activity range 602, target information 603, and the like.

[0064] The basic activity range 601 may include activity goals, generated content, activity functions, etc. The user may freely input, as the avatar activity theme, the activity goal of using the avatar on social media. In the case of users who operate official accounts such as companies, influencers, and artists, they may set, as the activity goals, strengthening the brand image, communication with customers (fans), publicity, product advertising, status reports, etc. For communication and posting on social media, various types of content such as text, stamps, photos, videos, and voices will be generated. At this time, the basic activity range 601 can set the content types allowed to be generated for the avatar. In the case of stamps, a list of stamps available for the user account can be created, and keywords can be extracted from each stamp included in the list and utilized for social media activities. Also, the activity functions classified into activity types on social media may include posting, comments on other users' posts, reactions (e.g., "like", etc.), mentions, chats with other users, following other users, etc. At this time, as the basic activity range 601, the activity functions allowed for the avatar may be set.

[0065] The detailed activity range 602 may include an activity ratio, an automatic mode, the number of interactions, etc. Areas of interest are activity fields classified as social media categories and may be set through the basic avatar setting screen 400. The user may set an activity ratio for each area of interest set through the basic avatar setting screen 400 as one of the detailed activity ranges 602. That is, by setting an activity weighting value for each area of interest set for the avatar, the category in which the avatar mainly engages is defined. Also, by selecting an automatic mode for social media activities, the range within which the avatar can generate content for activities may be set. The automatic mode may be classified into a fully automatic mode that allows all the avatar's generated content for social media activities, a partial approval mode (semi-automatic mode) that censors the avatar's generated content according to user settings and uses it after user approval for content that deviates from the set conditions, and a full approval mode (manual mode) that uses all the avatar's generated content after user approval. Also, in order to limit the maximum number of interactions of the avatar for the same post, the number of interactions may be set as one of the detailed activity ranges 602.

[0066] Target information 603 is the range of information to be conveyed by the avatar's activities. In social media activities using the avatar, items that require accurate information transmission may be pre-entered as target information 603 and constructed as a database. Such target information 603 may be utilized when generating the avatar's content. For example, schedule information may be set in advance as target information 603 for an idle account, and sale product information may be set in advance as target information 603 for a product brand account and used for avatar activities.

[0067] In addition to the avatar activity range described above, the user may set the costs related to avatar activities. The costs due to the avatar's generated content and activity functions (activity types) may be informed, and the quota for each period may be set.

[0068] FIG. 7 is an example showing the procedure of content censorship settings.

[0069] The processor 220 may apply a censorship system to the content generated for social media activities to check whether there are any policy violations or inappropriate content. Referring to FIG. 7, the content censorship setting screen 700 may include an interface for setting content censorship for each censorship target item 701. The user can set the applicable range of the censorship function for the content generated by the avatar. At this time, the applicable range of the censorship function of the Open AI Moderation API may be applied. The processor 220 can perform censorship not only on the content generated by the avatar based on the user's content censorship settings, but also on comments and reactions left by other users on the avatar's activities.

[0070] In addition to content censorship based on user settings, in some embodiments, in order to prevent false information from being included in the content generated by the avatar, it is also possible to perform verification regarding the presence or absence of false information in conjunction with the search function.

[0071] FIG. 8 is an example showing the social media activities of the avatar.

[0072] The processor 220 may execute the social media activities of the avatar when the conditions are met for each avatar while monitoring all the content registered on the social media.

[0073] Referring to FIG. 8, the processor 220 may analyze the posts registered on the accounts of other users in the social media (S801). At this time, the processor 220 may analyze the category to which the post belongs based on the content and attributes of the posts of other users.

[0074] The processor 220 may select an activatable avatar based on the analysis result of the post (S802). The processor 220 may check whether the analysis result of the post matches the interests set for the avatar. The processor 220 may analyze the attributes of all posts and continuously make judgments on the activity fields of the avatar.

[0075] When the analysis result of the post matches the interests set for the avatar, the processor 220 may generate content for avatar activities (S803). When a post that matches the interests of the avatar is registered, the avatar may generate content that can be registered as a comment or reaction to the post.

[0076] The processor 220 may execute an inspection process for the generated content of the avatar (S804). The processor 220 checks through the content inspection settings that the generated content of the avatar is content that conforms to the conditions allowed by the user. At this time, for content that deviates from the user's content inspection settings, this may be discarded and the content may be regenerated.

[0077] When the content conforms to the user's content inspection settings, the processor 220 may register it as avatar activity on the social media (S805). When a post that matches the interests of the avatar is registered, the avatar may generate content that suits the content inspection settings and register it as a comment or reaction to the post.

[0078] When the user inputs a new item of the target information 603 through the avatar activity setting screen 600, it may be automated so that a post is created and uploaded based on the content of the new item as one of the avatar activities. For example, if the condition that a photo or video is attached to the new item is met, a new post created with the attached photo or video may be automatically uploaded as avatar activity.

[0079] In addition, when content related to the avatar is searched, such as when the avatar's name is mentioned in the posts or comments of other users, comments and reactions may be created and registered by utilizing the information set for the avatar. For example, as shown in FIG. 9, the information set for the avatar may be used as a hashtag, and an answer from the avatar may be registered for the user who created the post or comment, or the user who mentioned the avatar's name. At this time, the answer from the avatar may be generated by utilizing the existing conversation with the corresponding user and the information set for the avatar.

[0080] In addition, the avatar may perform an activity of requesting to follow other users who satisfy conditions such as mentioning the avatar a certain number of times or more, or leaving comments on the avatar's posts a certain number of times or more.

[0081] Therefore, by analyzing all the content registered on the social media to determine whether each avatar is active, communication with other users can be achieved through avatar activities such as posts, comments, and reactions.

[0082] Referring to FIG. 8 again, the processor 220 may analyze the avatar's social media activities and provide an activity report (S806). The processor 220 may provide activity statistical values for each period, and visualize and show the responsiveness by other users for each avatar activity. The responsiveness of other users may be utilized for avatar learning to modify or complement the avatar's personality and way of speaking.

[0083] Furthermore, in this embodiment, after grouping and summarizing the comments of other users registered in the avatar's post by theme, an answer to each group can be proposed.

[0084] FIG. 10 is an example of providing a summary of comments.

[0085] Referring to FIG. 10, the processor 220 may analyze comments of other users registered for an avatar's post and group them by theme. At this time, through the avatar management screen 1000, a summary 1001 for each comment group may be provided. For each group, the theme of each group and the number of comments related thereto may be displayed together. Further, the processor 220 may propose a predicted response 1002 of the avatar for each comment group. The predicted response 1002 may reflect the personality and speaking style of the avatar, and the approval or disapproval of the predicted response 1002 may be determined according to the automatic mode (fully automatic mode, semi-automatic mode, manual mode) setting. As a result of querying and summarizing a certain history of comments on the avatar's post, when the comments on a specific theme reach a threshold, by setting the avatar to react thereto, it is possible to support timely and natural communication.

[0086] As described above, according to an embodiment of the present invention, in a generative artificial intelligence environment, a user-customized digital avatar that substitutes for a user's social media activities can be generated, thereby improving the efficiency of social media management and operation.

[0087] The apparatus described above may be implemented by hardware components, software components, and / or combinations of hardware components and software components. For example, the apparatus and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as a processor, a controller, an ALU (arithmetic logic unit), a digital signal processor, a microcomputer, an FPGA (field programmable gate array), a PLU (programmable logic unit), a microprocessor, or various apparatuses capable of executing instructions and responding. The processing device may execute an operating system (OS) and one or more software applications running on the OS. Further, the processing device may access data, record, manipulate, process, and generate data in response to the execution of the software. For the sake of convenience of understanding, it may be described as if one processing device is used, but those skilled in the art will understand that the processing device may include a plurality of processing elements and / or a plurality of types of processing elements. For example, the processing device may include a plurality of processors or one processor and one controller. Also, other processing configurations, such as a parallel processor, are possible.

[0088] Software may include a computer program, code, instruction, or a combination of one or more of these, and may configure a processing device to operate as desired or instruct the processing device independently or collectively. Software and / or data may be embodied in any kind of machine, component, physical device, computer recording medium or device for being interpreted by the processing device or providing instructions or data to the processing device. Software may be distributed on a computer system connected by a network and recorded or executed in a distributed state. Software and data may be recorded on one or more computer-readable recording media.

[0089] 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. At this time, the medium may continuously record a program executable by a computer, or may temporarily record it for execution or download. Further, the medium may be various recording means or storage means in a form in which a single or a plurality of hardware are combined, and may be not only a medium directly connected to a certain computer system but also one that exists distributed on a network. Examples of the medium include magnetic media such as hard disks, floppy (registered trademark) disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, magneto-optical media such as floptical disks, and those configured to record program instructions such as ROMs, RAMs, flash memories, etc. Further, as examples of other media, it also includes an app store that distributes applications, and recording media and storage media managed by sites, servers, etc. that supply and distribute other various software.

[0090] As described above, the embodiments have been described based on limited embodiments and drawings. However, those skilled in the art will be able to make various modifications and variations from the above description. For example, even if the described technology is executed in an order different from the described method, and / or the components such as the described system, structure, device, circuit, etc. are combined or combined in a form different from the described method, or opposed or replaced by other components or equivalents, appropriate results can be achieved.

[0091] Therefore, even if it is different from the above-described embodiments, as long as it is equivalent to the claims, it belongs to the appended claims.

[0092] This application claims priority based on Patent Application No. 10-2023-168258 filed with the Korean Intellectual Property Office on November 28, 2023, and incorporates the entire contents of Application No. 10-2023-168258 into this international application.

Description of Reference Numerals

[0093] 110, 120, 130, 140: Electronic devices 150, 160: Servers 170: Network

Claims

1. 1. A method for managing customized avatars on a computer device including at least one processor, comprising: generating, by the at least one processor, an avatar representing the user's social media activity, the avatar having tendencies based on the user's settings; and A method for managing customized avatars, comprising optimizing, by the at least one processor, tendencies of the avatar based on a user's evaluation of the avatar's interactions.

2. The generating step includes: The method of claim 1 , further comprising the step of determining a personality type and a speech type to be assigned to the avatar based on information input by the user.

3. The generating step includes: The method of claim 2 , further comprising: augmenting the information input by the user with data augmentation using generative artificial intelligence.

4. The optimizing step includes: collecting at least one of the avatar's responses in a basic dialogue set and the avatar's responses to questions from the user; selecting at least a portion of the avatar responses based on user ratings of the avatar responses; and The method of claim 1 , further comprising the step of modifying at least one of a personality type and a speech type assigned to the avatar based on the selected answer.

5. The method of claim 1 , further comprising: executing, by the at least one processor, social media activities for the avatar within activity ranges set by the user.

6. The performing step includes: Setting at least one interest corresponding to an activity field as an activity range of the avatar; The setting step includes: The method of claim 5 , further comprising the step of setting a ratio of activity for each of the interests.

7. The performing step includes: The method of claim 5, further comprising the step of setting at least one of an activity type and a generated content type as the activity range of the avatar.

8. The performing step includes:

6. The method of claim 5, further comprising: accepting the generated content of the avatar based on the user's content acceptance setting.

9. The performing step includes: Setting at least one interest corresponding to an activity field as an activity range of the avatar; and The method of claim 5 , further comprising the step of: registering generated content of the avatar as a comment or reaction to a post of another user when the post matches the interest.

10. The method of claim 5, further comprising a step of: grouping, by the at least one processor, other users' comments on the avatar's post by theme and providing at least one of a summary of the comments in each group and a predicted response for the avatar.

11. A program for causing a computer device to execute the customized avatar management method according to any one of claims 1 to 10.

12. at least one processor that executes computer readable instructions; by said at least one processor, An avatar with tendencies based on the user's settings is generated as an avatar that represents the user's social media activities; A computer device, characterized in that the tendency of the avatar is optimized based on a user's evaluation of the avatar's interaction.

13. by said at least one processor, 13. The computer device of claim 12, wherein the personality type and speech type to be assigned to the avatar are determined based on information input by the user.

14. by said at least one processor, At least one of the avatar's responses to a basic dialogue set and the avatar's responses to questions from the user is collected; selecting at least a portion of the answers from the avatar based on user ratings of the answers from the avatar; 13. The computer device according to claim 12, wherein at least one of the personality type and the speech type assigned to the avatar is modified based on the selected answer.

15. by said at least one processor, The computer device of claim 12, wherein the social media activity of the avatar is carried out within an activity range set by the user.

16. by said at least one processor, At least one interest corresponding to an activity field is set as the activity range of the avatar; 16. The computer device of claim 15, wherein a ratio of activity is set for each of the interests.

17. by said at least one processor, The computer device according to claim 15, wherein at least one of an activity type and a generated content type is set as the activity range of the avatar.

18. by said at least one processor, The computer device of claim 15, wherein the generated content of the avatar is accepted based on the user's content acceptance setting.

19. by said at least one processor, At least one interest corresponding to an activity field is set as the activity range of the avatar; 16. The computer device of claim 15, wherein if a post of another user matches the interest, generated content of the avatar is registered as a comment or reaction to the post.

20. by said at least one processor, 16. The computer device of claim 15, wherein other users' comments on the avatar's post are grouped by theme, and a summary of the comments in each group and / or a predicted response by the avatar is provided.

Images