Server, method and computer program

Abstract

To provide a server, a method and a computer program for allowing an AI chatbot including a character to increase a communication or a pleasure in a live streaming room, and also allowing the AI chatbot to monitor or cope with an atmosphere in a live streaming, and processing a communication in a live streaming platform, improved by a user experience.SOLUTION: In a live streaming system, a server 10 executes a function of receiving character data corresponding to a character, a function of inputting the character data to a machine learning model to generate a virtual chatbot in a live streaming room, and a function of setting the virtual chatbot to the live streaming room. The virtual chatbot provides a live streamer or a viewer in the live streaming room with a support.SELECTED DRAWING: Figure 9

Description

[Technical field]

[0001] The present disclosure relates to information and communication technology, and in particular to a server, a method, and a computer program for live streaming. [Background technology]

[0002] Some apps and platforms offer live streaming services that allow live streamers and viewers to interact with each other, either by making performances to show support for their viewers or by sending gifts to show support for the live streamer.

[0003] If viewers do not support the live streamer, the live streamer may become discouraged, and the interaction between the viewers and the live streamer may deteriorate. Patent Document 1 discloses a method for solving the problem of insufficient activity in a live streaming room by generating a virtual intelligent robot.

[0004] However, live streamers may have more interactions with their viewers, and current chatbots may not be able to meet the needs of live streamers. In addition, chatbot functions are always fixed and limited, which may lead to a poor user experience. Therefore, it is important to improve the user experience. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] China Patent Application Publication No. 110730390 Summary of the Invention

[0006] A server according to one embodiment of the present disclosure includes one or more processors, the one or more processors being configured to execute machine-readable instructions to perform functions of receiving character data corresponding to a character, inputting the character data into a machine learning model to generate a virtual chatbot in a live streaming room, and configuring the virtual chatbot in the live streaming room, such that the virtual chatbot provides assistance to a live streamer or a viewer in the live streaming room.

[0007] A method for processing interactions in a live streaming platform according to one embodiment of the present disclosure includes receiving character data corresponding to a character, inputting the character data into a machine learning model to generate a virtual chatbot in a live streaming room, and configuring the virtual chatbot in the live streaming room, wherein the virtual chatbot is configured to provide assistance to a live streamer or a viewer in the live streaming room.

[0008] A computer program according to an embodiment of the present disclosure causes a server to perform a function of receiving character data corresponding to a character, inputting the character data into a machine learning model to generate a virtual chatbot in a live streaming room, and setting the virtual chatbot in the live streaming room, such that the virtual chatbot is configured to provide assistance to a live streamer or a viewer in the live streaming room.

[0009] According to the present disclosure, the AI ​​chatbot equipped with the character can increase the interaction and enjoyment in the live streaming room. Furthermore, the monitoring and response of the atmosphere in the live streaming can be partially or entirely entrusted to the AI ​​chatbot. Therefore, the user experience can be improved. [Brief description of the drawings]

[0010] [Figure 1] 1 is a schematic diagram showing a configuration of a live streaming system 1 based on some embodiments of the present disclosure. [Diagram 2] FIG. 2 is a block diagram of a user terminal 20 according to some embodiments of the present disclosure. [Diagram 3] FIG. 1 is a block diagram of a server 10 according to some embodiments of the present disclosure. [Figure 4] 4 is a table showing an example data structure of the stream DB 320 of FIG. 3. [Diagram 5] 4 is a table showing an example data structure of the user DB 322 of FIG. 3. [Figure 6] 4 is a table showing an example data structure of the AI ​​chatbot DB324 of FIG. [Figure 7] 4 is a table illustrating an example data structure of the training data DB 326 of FIG. 3. [Figure 8] 4 is a table illustrating an example data structure of the personality DB 328 of FIG. 3. [Figure 9] 1 is a schematic diagram showing an example of a functional configuration of a live streaming system 1 based on some embodiments of the present disclosure. [Figure 10] 6 is an exemplary screen image of a live streaming room screen 600 displayed on the display of a live streamer's user terminal 20 or a viewer's user terminal 30. [Figure 11] 6 is an exemplary screen image of a live streaming room screen 600 displayed on the display of a live streamer's user terminal 20 or a viewer's user terminal 30. [Figure 12] 6 is an exemplary screen image of a live streaming room screen 600 displayed on the display of a live streamer's user terminal 20 or a viewer's user terminal 30. [Figure 13] 6 is an exemplary screen image of a live streaming room screen 600 displayed on the display of a live streamer's user terminal 20 or a viewer's user terminal 30. [Figure 14] 6 is an exemplary screen image of a live streaming room screen 600 displayed on the display of a live streamer's user terminal 20 or a viewer's user terminal 30. [Figure 15] 6 is an exemplary screen image of a live streaming room screen 600 displayed on the display of a live streamer's user terminal 20 or a viewer's user terminal 30. [Figure 16] 13 is a flowchart showing the steps of an application startup process in the user terminal 20, 30. [Figure 17] 1 is a schematic diagram showing an example of a functional configuration of a live streaming system 1 based on some embodiments of the present disclosure. [Figure 18] 1 illustrates an exemplary hardware configuration of an information processing device based on some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, the same or similar components, parts, steps, or signals shown in each drawing will be denoted by the same reference numerals in all drawings, and duplicated explanations will be omitted as appropriate. In addition, some parts that are not important in the explanation of each drawing will be omitted.

[0012] The live streaming system 1 according to some embodiments of the present disclosure provides enhanced functionality to facilitate communication and interaction between users, and more specifically, to entertain viewers and live streamers in a technological manner.

[0013] FIG. 1 shows a schematic diagram illustrating a configuration of a live streaming system 1 according to some embodiments of the present disclosure. The live streaming system 1 provides a live streaming service for a live streamer (also called a liver, streamer, or distributor) LV and a viewer (also called an audience) AU (AU1, AU2, ...) of streaming to interact with each other in real time. As shown in FIG. 1, the live streaming system 1 may include a server 10, a user terminal 20, and a user terminal 30 (30a, 30b, ...). The user terminal 20 may be a live streamer, and the user terminal 30 may be a viewer. In some embodiments, the live streamer and the viewer may be called users. The server 10 may include one or more information processing devices connected via a network NW. The user terminals 20 and 30 may be, for example, mobile terminals such as smartphones, tablets, notebook PCs, recorders, portable game consoles, and wearable terminals, or stationary computers such as desktop PCs. The server 10, the user terminal 20, and the user terminal 30 may be communicatively connected by any type of wired or wireless network NW.

[0014] The live streaming system 1 involves the live streamer LV, the viewer AU, and an app provider (not shown) that provides the server 10. The live streamer LV can record content such as his / her own singing, talking, performance, game streaming, etc. on his / her user terminal 20 and upload it to the server 10, thereby distributing the content in real time. In some embodiments, the live streamer LV can interact with the viewer AU through the live streaming.

[0015] The app provider may provide a platform for content to be live streamed on the server 10. In some embodiments, the app provider may be a media or manager that manages real-time communication between the live streamer LV and the viewer AU. The viewer AU may access the platform through the user terminal 30 and select and view the content that the viewer AU wants to view. The viewer AU may perform operations to interact with the live streamer, such as commenting on the live streamer or cheering on the live streamer, through the user terminal 30. The live streamer providing the content may respond to the comments or cheers. The live streamer's response may be transmitted to the viewer AU by video and / or audio. Thus, mutual communication between the live streamer and the viewer may be achieved.

[0016] The term "live streaming" as used herein may refer to data transmission that allows the viewer AU to substantially play and view the content recorded by the live streamer LV via the user terminal 20 via the user terminal 30. In some embodiments, "live streaming" may refer to streaming realized by the above-mentioned data transmission. The live streaming may be realized by known technologies such as HTTP live streaming, CMAF (Common Media Application Format), WebRTC (Web Real-Time Communications), RTMP (Real-Time Messaging Protocol), and MPEG DASH. The live streaming may further include an embodiment in which the viewer AU can play or view the content with a certain delay while the live streamer is recording the content. It is desirable that the degree of the delay is small enough to at least allow the live streamer LV and the viewer AU to communicate with each other. However, live streaming is different from so-called on-demand distribution. More specifically, the on-demand distribution may refer to storing all data of the recorded content in a server and providing the data to the user from the server at random times in response to a user's request.

[0017] In this specification, "streaming data" may refer to data including image data and audio data. More specifically, the image data (which may be referred to as video data) may be generated by an image capture function of the user terminals 20 and 30. The audio data (which may be referred to as audio data) may be generated by an audio input function of the user terminals 20 and 30. The streaming data may be played on the user terminals 20 and 30 to enable viewing of content related to the user. In some embodiments, a process is envisioned in which the format, size, or standard of the data is changed, such as compression, expansion, encoding, decoding, or transcoding, between the time the streaming data is generated on the user terminal of the live streamer and the time it is played on the user terminal of the viewer. Before and after such processing, the content (video and audio) is not substantially changed, and therefore, in the current embodiment of the present disclosure, the streaming data before processing and the streaming data after processing are described as being the same. In other words, when the streaming data generated by the user terminal of the live streamer is played on the user terminal of the viewer via the server 10, the streaming data generated by the user terminal of the live streamer, the streaming data that has passed through the server 10, and the streaming data received and played by the user terminal of the viewer are all the same streaming data.

[0018] As shown in Fig. 1, the live streamer LV provides live streaming. The user terminal 20 of the live streamer generates streaming data by recording the video and / or audio of the streamer, and transmits the streaming data to the server 10 via the network NW. At the same time, the user terminal 20 displays the video VD on the display of the user terminal 20, so that the user can check the streaming content of the live streamer LV.

[0019] The viewers AU1, AU2 of the user terminals 30a, 30b that request the platform to provide live streaming of the live streamer can receive streaming data corresponding to the live streaming via the network NW, play the received streaming data to display the videos VD1, VD2 on a display, and output the audio from a speaker, etc. The videos VD1, VD2 displayed on the user terminals 30a, 30b, respectively, are substantially the same as the videos recorded by the user terminals of the live streamer LV, and the audio output from the user terminals 30a, 30b is substantially the same as the audio recorded by the user terminals of the live streamer LV.

[0020] The recording of the live streamer on the user terminal 20 may be simultaneous with the playback of the streaming data on the user terminals 30a, 30b of the viewers AU1, AU2. When the viewer AU1 inputs a comment on the content of the live streamer LV to the user terminal 30a, the server 10 displays the comment on the user terminal 20 of the live streamer in real time, and also on the user terminals 30a, 30b of the viewers AU1, AU2. When the live streamer LV responds to the comment, the response is output as text, image, video, or audio from the user terminals 30a, 30b of the viewers AU1, AU2, thereby realizing communication between the live streamer LV and the viewers AU1, AU2. Thus, the live streaming system can realize two-way live streaming.

[0021] 2 is a block diagram showing the functions and configuration of the user terminal 20 shown in FIG. 1 according to an embodiment of the present disclosure. The user terminal 30 has the same functions and configuration as the user terminal 20. The blocks depicted in the block diagrams in this specification are implemented by hardware such as a device or mechanical part, such as a computer CPU, and software such as a computer program that represents functional blocks implemented by the cooperation of these elements. Therefore, it will be understood by those skilled in the art that the functional blocks can be implemented in various ways by combining hardware and software.

[0022] The live streamer LV and the viewer AU can download and install the live streaming application (live streaming app) of the present disclosure from a download site to the user terminals 20 and 30 via the network NW. Alternatively, the live streaming app may be pre-installed in the user terminals 20 and 30. By executing live streaming by the user terminals 20 and 30, the user terminals 20 and 30 can communicate with the server 10 via the network NW and realize a plurality of functions. The functions realized by executing the live streaming app by the user terminals 20 and 30 (more specifically, a processor such as a CPU) are described below as functions of the user terminals 20 and 30. The functions are basically functions that the live streaming app causes the user terminals 20 and 30 to realize. In some embodiments, these functions may be realized by transmitting them from the server 10 to the web browsers of the user terminals 20 and 30 via the network NW and executing them by a computer program of the web browser. The computer program may be written in a programming language such as HTML (Hyper Text Markup Language).

[0023] The user terminal 20 includes a streaming unit 100 and a viewing unit 200. In some embodiments, the streaming unit 100 is configured to record a user's audio and / or video data and generate streaming data to send to the server 10. The viewing unit 200 is configured to receive and play streaming data from the server 10. In some embodiments, a user can activate the streaming unit 100 at the time of broadcasting or activate the viewing unit 200 when viewing a stream. In some embodiments, the user terminal that activates the streaming unit 100 can be referred to as a live streamer or the user terminal that generates streaming data. The user terminal that activates the viewing unit 200 can be referred to as a viewer or the user terminal that plays the streaming data.

[0024] The streaming unit 100 may include a video control unit 102, an audio control unit 104, a distribution unit 106, and a UI control unit 108. The video control unit 102 may be connected to a camera (not shown), and the video is controlled by the camera. The video control unit 102 can obtain the video data from the camera. The audio control unit 104 may be connected to a microphone (not shown), and the audio is controlled by the microphone. The audio control unit 104 can obtain the audio data from the microphone.

[0025] The delivery unit 106 receives streaming data including video data from the video control unit 102 and audio data from the audio control unit 104 and transmits the streaming data to the server 10 via the network NW. In some embodiments, the delivery unit 106 transmits the streaming data in real time, i.e., the generation of the streaming data from the video control unit 102 and the audio control unit 104 and the delivery by the delivery unit 106 are performed simultaneously.

[0026] The UI control unit 108 controls the UI of the live streamer. The UI control unit 108 is connected to a display (not shown) and configured to generate the streaming data for the distribution unit 106 to transmit, play and display on the display. The UI control unit 108 is configured to display an object to be operated or an object to be instructed on the display and to receive a tap input from the live streamer.

[0027] The viewing unit 200 may include a UI control unit 202, a rendering unit 204, and an input sending unit 206. The viewing unit 200 is configured to receive streaming data from the server 10 via a network NW. The UI control unit 202 controls the UI of the viewer. The UI control unit 202 is connected to a display (not shown) and / or a speaker (not shown) and configured to display a video on the display and output a sound from the speaker by playing the streaming data. In some embodiments, outputting a video on the display and outputting a sound from the speaker may be referred to as "playing streaming data". The UI control unit 202 is connected to an input unit such as a touch panel, a keyboard, a display, etc., and can obtain input from a user.

[0028] The rendering unit 204 may be configured to render streaming data from the server 10 and frame images. The frame images may include user interface objects for accepting input from a user, comments entered by a viewer, and data received from the server 10. The input sending unit 206 is configured to receive the user input from the UI control unit 202 and send it to the server 10 via the network NW.

[0029] In some embodiments, the user input may be clicking an object on the screen of the user terminal, such as selecting a live stream, entering a comment, sending a gift, following or unfollowing a user, voting in an event, playing a game, etc. For example, the input sending unit 206 may generate gift information and send it to the server 10 via the Internet NW when the user terminal of a viewer clicks a gift object on the screen to send a gift to the live streamer.

[0030] 3 is a block diagram of the server 10 according to some embodiments of the present disclosure. The server 10 may include a streaming information unit 302, a relay unit 304, a processing unit 306, a stream DB 320, a user DB 322, an AI chatbot DB 324, a training data DB 326, a personality DB 328, and a machine learning model 330. In some embodiments, the machine learning model 330 may be a language model 330, etc.

[0031] The streaming information unit 302 receives a request for live streaming from the user terminal 20 of the live streamer via the network NW. Upon receiving the request, the streaming information unit 302 registers the information of the live streaming in the stream DB 320. In some embodiments, the information of the live streaming may be a stream ID of the live streaming and / or a live streamer ID of the live streamer corresponding to the live streaming.

[0032] When a request for the information of the live streaming is received from the viewer via the network NW from the viewing unit 200 of the user terminal 30, the streaming information unit 302 refers to the stream DB 320 and generates a list of available live streaming.

[0033] Then, the streaming information unit 302 transmits the list to the user terminal 30 via the network NW. The UI control unit 202 of the user terminal 30 generates a live streaming selection screen based on the list, and displays the list on the display of the user terminal 30.

[0034] When the input sending unit 206 of the user terminal 30 receives the selection of live streaming by the viewer on the live streaming selection screen, it generates a delivery request including the stream ID of the selected live streaming, and sends it to the server 10 via the network. The streaming information unit 302 can start providing the live streaming specified by the stream ID in the delivery request to the user terminal 30. The streaming information unit 302 can update the stream DB 320 and add the viewer ID of the viewer of the user terminal 30 to the live streamer ID of the stream ID.

[0035] The relay unit 304 can relay transmission of live streaming from the user terminal 20 of the live streamer to the user terminal 30 of the viewer in the live streaming started by the streaming information unit 302. The relay unit 304 can receive a signal indicating a user input from the viewer during playback of streaming data from the input transmission unit 206. The signal indicating the user input may be an object designation signal indicating designation of an object to be displayed on the display of the user terminal 30.

[0036] The object designation signal may include a viewer ID of the viewer, a live streamer ID of a live streamer who delivers the live streaming that the viewer is watching, and an object ID designated by the object. If the object is a gift, the object ID may be a gift ID, etc. Similarly, the relay unit 304 may receive a signal indicating a user input of the live streamer, such as the object designation signal, from the streaming unit 100 of the user terminal 20 during playback of streaming data.

[0037] The processing unit 306 is configured to process the request according to the operation of the user terminal of the user. For example, the user may click a button to generate an AI chatbot in the live streaming room. The user may select a desired chatbot according to preferences. When the relay unit 304 receives the request, the processing unit 306 may refer to a corresponding database, such as the training data DB 326, based on the selection.

[0038] In some embodiments, the server 10 may provide the user with some default AI chatbots. The training data corresponding to the default AI chatbots may be stored in the training data DB 326 in advance. In some embodiments, the processing unit 306 may obtain data from inside or outside, and store related information as training data in the training data DB 326. For example, if the selected chatbot is a celebrity, the processing unit 306 may refer to social media sites such as Facebook and Instagram, and obtain the records as training data.

[0039] If the selected chatbot is a user of the live streaming platform, the processing unit 306 may refer to the user DB 322, the user's live streaming, archived streaming, the user's posts, or the user's social media sites to further obtain records as training data. If the selected chatbot is a cartoon character, the processing unit 306 may refer to the official website, etc. In some embodiments, the resources of the training data may be flexibly determined according to actual needs.

[0040] In some embodiments, the processing unit 306 may further input the training data into a machine learning model for generating an AI chatbot, etc. In some embodiments, the machine learning model may be an internally trained model or a model provided by a third-party service provider. In some embodiments, the machine learning model for generating an AI chatbot may be realized by a language model, etc. In some embodiments, the machine learning model may be an AI chatbot, such as ChatGPT or other LLMs (large-scale language models). In some embodiments, the machine learning method may be realized by any possible model according to actual needs.

[0041] FIG. 4 is a table showing an exemplary data structure of the stream DB 320 of FIG. 3. The stream DB 320 holds information about a live stream currently being performed. The stream DB 320 stores a stream ID for identifying a live stream on a live streaming platform provided by the live streaming system 1, a live streamer ID for identifying a live streamer providing the live stream, an AI chatbot ID for identifying an AI chatbot in the live streaming room, and a viewer ID for identifying a viewer of the live stream, in association with each other. In some embodiments, the AI ​​chatbot may be bound to a user as a creator. In some embodiments, the AI ​​chatbot may be bound to a live stream. In some embodiments, the AI ​​chatbot may be movable between different live streaming rooms.

[0042] 5 is a table showing an example data structure of the user DB 322 of FIG. 3. The user DB 322 holds information about users. The user DB 322 stores a user ID for identifying a user, a point for identifying points accumulated by the user, a level for identifying the level of the user, and a status for identifying the status of the user, in association with each other. The point is an electronic value circulating within the live streaming platform. The level may be an indicator of the amount of activity or engagement of the user on the live streaming platform. The status may be the identity or membership status of the user on the live streaming platform.

[0043] Fig. 6 is a table showing an example data structure of the AI ​​chatbot DB 324 in Fig. 3. The AI ​​chatbot DB 324 holds information about an AI chatbot on the live streaming platform. The AI ​​chatbot DB 324 stores a chatbot ID for identifying an AI chatbot provided by the live streaming system 1 or generated by the user, a stream ID for identifying a live stream in which the chatbot is currently placed, a character for identifying a character of the chatbot, a personality for identifying a personality of the chatbot, and an additional function for identifying an additional function of the chatbot, in association with each other.

[0044] In some embodiments, the app provider may provide some default chatbots in advance, or users may create chatbots in real time. The chatbots may be created in live streaming rooms and may move between different live streaming rooms. In some embodiments, one chatbot may appear in different live streaming rooms. In some embodiments, the characters may be celebrities, public figures, users of live streaming platforms, anime characters, or professions such as lawyers, or any possible characters.

[0045] The personality may be a characteristic of a human individual. For example, the chatbot may have personalities such as positive, negative, talkative, silent, impatient, patient, flashy, plain, kind, violent, sympathetic, ruthless, etc. In some embodiments, a character may have a default personality. For example, the famous scientist Albert Einstein is considered a genius who is thoughtful and imaginative. In some embodiments, the character may have no personality. For example, the chatbot may comment and respond in a robotic manner.

[0046] In some embodiments, the personality of the character may be set or changed. For example, the user may create Einstein with a personality of impatient, talkative, etc. In some embodiments, the character may have a personality that is the opposite of the normal impression. For example, an AI chatbot of a user who is considered to be a quiet person may be created with a talkative personality. In some embodiments, the contrast between the AI ​​chatbot and the user may bring fun to the live streaming room.

[0047] In some embodiments, the personality may be exhibited by the AI ​​chatbot through the terminology, vocabulary, and wording of text messages, the tone, pitch, quality, tempo, speed, and wording of audio messages, or the facial features, gestures, movements, etc. of video messages from the virtual chatbot. For example, the AI ​​chatbot with a personality that has a sense of humor may occasionally tell jokes, while the AI ​​chatbot with a pessimistic personality may frown and say negative things.

[0048] In some embodiments, the additional function may be a function of the chatbot in the live streaming room. The additional function may be set by the user according to the context of the live streaming room. For example, the chatbot may be an event assistant. The event assistant may assist the streamer in an event if the streamer is currently involved in the event hosted by the live streaming platform. The AI ​​chatbot may provide hint messages to the live streamer or viewers to help the live streamer meet a reward threshold in the event.

[0049] During the event, the processing unit 306 may keep monitoring the status of the live streaming room and provide a hint message based on the status. The status may be a specific time point, such as 5 minutes before the end of the event. The status may also be a specific situation, such as the live streamer's received points decreasing. Such information may be regarded as a trigger for the processing unit 306 to provide a hint message based on the machine learning model.

[0050] In some embodiments, the chatbot may suggest the livestreamer to interact with the viewers, such as singing or playing guitar to liven up the viewers. In some embodiments, the chatbot may also inform the viewers of the goal for the livestreamer to win or meet the reward threshold in the event. For example, a hint message may be displayed through an AI chatbot, guiding the viewers to support the livestreamer, saying, "The livestreamer needs 2,000 points to win. Would you like to donate 4 small event gifts (500) or 1 big event gift (2,000)?"

[0051] The chatbot may be a mood maker of the live streaming room. When the atmosphere of the live streaming room becomes bad, the chatbot may give cues to the viewers or start a topic to increase the interaction between the live streamer and the viewers. In some embodiments, the atmosphere of the live streaming room may be determined by, for example, the number of viewers, the number of comments, the content of the comments, the number of gifts, the value of the gifts, etc. In some embodiments, when the level of interaction falls below a threshold, the chatbot may be activated to act as a mood maker to increase the atmosphere of the live streaming room.

[0052] In some embodiments, the AI ​​chatbot DB324 may further store a level for identifying the level of the chatbot, an interaction value for identifying the degree of interaction with the user, and a status for identifying the current state of the chatbot, which are associated with each other. The status may indicate the current state of the chatbot, such as "active", "inactive", "frozen", "destroyed", etc. The statuses of "active" and "inactive" may indicate whether the chatbot is currently activated or not. In some embodiments, the status of the chatbot may be flexibly designed and determined according to actual needs.

[0053] In some embodiments, the chatbot may have different levels and interaction values. The interaction value may be obtained by interacting with the user, such as tagging the user, commenting, responding to the user, providing hint messages, etc. The level may be upgraded by receiving sufficient interaction value. In some embodiments, the features of the chatbot may be unlocked depending on the level, etc. In some embodiments, the interaction from the chatbot may be changed based on the level.

[0054] In some embodiments, different levels correspond to different ages, and the comments or topics may be different based on the level. For example, an AI chatbot under 12 years old may behave like a child, while an AI chatbot over 40 years old may behave like a much older adult, etc. That is, training data may be changed or added depending on the level of the chatbot. In some embodiments, the processing unit 306 may further obtain training data based on the level of the AI ​​chatbot.

[0055] In some embodiments, the status of the AI ​​chatbot may change based on the interaction between the AI ​​chatbot and the user in the live streaming room. In some embodiments, the status may further include an emotional status, such as "happy", "unhappy", "sad", "depressed", "lonely", etc. For example, if the interaction between the AI ​​chatbot and the user is positive or negative, the status of the AI ​​chatbot may be positive or negative, such as "happy" or "sad". In some embodiments, the increase in the interaction value may change based on the status. For example, the interaction value may increase faster during a positive status than during a negative status.

[0056] In some embodiments, the status of the AI ​​chatbot may be referred to as the health points (HP) of the AI ​​chatbot. In some embodiments, the status of the AI ​​chatbot may change based on the interaction from the user. For example, if there is little or no interaction from the user, the status may be "lonely," "depressed," "weak," or "at risk." In some embodiments, if the status of the AI ​​chatbot remains negative for a certain period of time, the AI ​​chatbot may be rendered inoperable for the time being or forever. For example, if no user interacts with the AI ​​chatbot for more than an hour, the AI ​​chatbot may be destroyed forever.

[0057] In some embodiments, the status of the AI ​​chatbot may change the user's interaction with the AI ​​chatbot. For example, if the status of the AI ​​chatbot is negative, messages from the AI ​​chatbot may be negative, etc. In some embodiments, the status of the AI ​​chatbot may be displayed on the AI ​​chatbot's profile page, display image, or message. In some embodiments, the status of the AI ​​chatbot may be displayed on an icon in a live stream, such as icon 618 in FIG. 12. According to this embodiment, the user can understand the status of the AI ​​chatbot and interact with the AI ​​chatbot as necessary.

[0058] Fig. 7 is a table showing an example data structure of the training data DB 326 of Fig. 3. The training data DB 326 holds information about the training data of an AI chatbot. The training data DB 326 stores a character that identifies the character of the chatbot, a type that identifies the type of the character, and character data that identifies the training data of the character in association with each other.

[0059] In some embodiments, the character types may include "Charity", "User", "Animation", etc. The "Charity" type may refer to a famous celebrity. The person may be an actor, actress, scientist, politician, etc. The "User" type may refer to a user in the live streaming platform. The user may be a famous user in the live streaming platform or a follower, followee, or friend of another user in the live streaming room. The "Animation" type may refer to an animated virtual character, such as Doraemon, Super Mario, Pikachu, etc.

[0060] In some embodiments, the training data of the character may be obtained based on the type of the character. For example, the training data of a charity may be obtained from public information on social media sites such as Facebook, Instagram, twitter, etc. The training data of a user may be obtained from the user's information uploaded to the live streaming platform, the user's social media site, etc. This embodiment may motivate the user to post more information to the live streaming platform.

[0061] Furthermore, the training data of the animated character may be obtained from its official website, animation, online search results, etc. In some embodiments, the training data may be flexibly obtained according to actual needs. In some embodiments, the data may be downloaded in advance or obtained from the Internet in real time. The data may be stored in the training data DB 326 for training. In some embodiments, the training data may be classified based on, for example, the level of the AI ​​chatbot. In some embodiments, the training data may be flexibly added, deleted, adjusted, etc.

[0062] Figure 8 is a table showing an example data structure of the personality DB 328 of Figure 3. The personality DB 328 holds information about the personality data of an AI chatbot. The personality DB 328 stores a personality ID that identifies the personality of the chatbot, a description that identifies the description of the personality, and prompt data that identifies the prompt data of the personality in association with each other.

[0063] In some embodiments, the personality may be prompt data of a language model. The prompt may refer to input text or instructions provided to the language model to generate a response or perform a particular task. In some embodiments, the prompt data may be a sentence or a group of sentences to indicate a particular personality of the chatbot. For example, the prompt data may be "You are an educated, polite, patient person, you like to share with others, and you listen to others." The prompt data may be taken and input into the language model to give the chatbot a particular personality.

[0064] For example, a "talkative" personality may be realized by providing inputs such as "You are talkative" and "Answers must be at least 6 sentences or 100 words." The app provider may provide some default personality data for the user to choose from. In some embodiments, the prompt data may be input and set by the user. For example, the user may select no personality or a default personality. The user may also input a block of text as prompt data to assign a personality to the AI ​​chatbot.

[0065] FIG. 9 is a schematic diagram showing an example of a functional configuration of a live streaming system 1 according to some embodiments of the present disclosure. As shown in FIG. 9, an AI chatbot may be generated and configured in response to a user input from a user terminal of a user. In some embodiments, the generation of the AI ​​chatbot may be automatically performed by the server 10. The user may set information of the chatbot, such as a character. In some embodiments, the user may further set a personality, additional functions, and the like. Depending on the settings from the user, the server 10 may collect the training data internally or externally, such as from the Internet. For example, if the user sets the character as his / her follower, the server 10 may collect the public information of the follower stored in the server 10 or externally, such as from a social media site.

[0066] In some embodiments, if the user sets a specific personality for the AI ​​chatbot, the server 10 may generate a chatbot for the follower with the specific personality by referring to the personality DB 328, etc. When the training data and personality data are collected, the server 10 may further input the training data and personality data into the language model 330 and generate a chatbot based thereon. The chatbot may be placed and displayed in a live streaming room of a live streamer, etc.

[0067] In some embodiments, the processing unit 306 may monitor the status of the live streaming room. For example, the processing unit 306 may monitor comments, event information, the live streamer's received points or ranking in an event, etc. The processing unit 306 may further input related information into the language model 330. The language model 330 may further generate a response based on the related information to help the live streamer process the atmosphere of the event or the live streaming room, etc. For example, if a user tags the chatbot and asks the chatbot to tell a joke, the processing unit 306 may input the comment into the language model 330 and generate a joke for the user.

[0068] 10 to 15 are exemplary screen images of a live streaming room screen 600 displayed on the display of the live streamer's user terminal 20 or the viewer's user terminal 30. When a viewer selects and enters a live streaming room, the live streaming room screen 600 of the live streamer may be displayed on the display. The live streaming room screen 600 may include a live streamer information object 602, a live streamer image 604, a message zone 606, a message input box 608, a gift object 610, a sharing object 612, and the like.

[0069] In some embodiments, the screen 600 may further include an invite button 614. The invite button 614 is configured to generate an AI chatbot in the live streaming room so as to invite the user to the live streaming room. When the invite button 614 is clicked as shown in FIG. 10, a UI 616 for setting an AI chatbot may be displayed to the user as shown in FIG. 11. In some embodiments, the UI 616 may include a form with options for the user to determine a character, personality, additional features, and the like.

[0070] In some embodiments, the UI 616 may include a field (not shown) for the user to input a block of text as a prompt to generate a customized AI chatbot. For example, the user may input "I want a crazy personality Super Mario AI chatbot to be the mood maker in my live streaming room," and the processing unit 306 may extract keywords and generate an AI chatbot based on the input. In some embodiments, the design and configuration of the AI ​​chatbot may be flexibly determined.

[0071] Once the user has selected the AI ​​chatbot, the processing unit 306 may input the AI ​​chatbot's information into a machine learning model. Here, the language model 330 is taken as an example. In some embodiments, the language model may be any possible or available model, such as ChatGPT. In some embodiments, the machine learning model may infer possible outputs based on the input, and the procedure of generating the AI ​​chatbot may refer to providing the inference from the model to the user.

[0072] In some embodiments, the processing unit 306 may obtain training data for the AI ​​chatbot from a database in the server 10 or the Internet. After generating the AI ​​chatbot, the processing unit 306 may display the AI ​​chatbot in the live streaming room, as shown in FIG. 12. In some embodiments, there may be an icon 618 indicating the presence of an AI chatbot in the live streaming room. In some embodiments, a mark (not shown) indicating the ID of the AI ​​chatbot may be displayed on a display image of the AI ​​chatbot, etc.

[0073] As shown in Figure 12, the AI ​​chatbot may interact with the live streamer and viewers. For example, the viewers may tag the AI ​​chatbot and ask the AI ​​chatbot to tell jokes, etc. The processing unit 306 may further monitor the status of the live streaming room and input comments into the language model 330 to generate responses based on comments from the viewers.

[0074] The AI ​​chatbot may tag the viewer and motivate the viewer to interact with the live streamer. For example, the processing unit 306 may refer to the viewer's posts on the live streaming platform or social media sites. If the viewer has just returned from a trip to Japan, the processing unit 306 may tag the viewer and ask the viewer about his / her trip in Japan via the AI ​​chatbot. In some embodiments, the AI ​​chatbot may cue, tag, etc., a viewer who is joining the live streaming room for the first time. According to this embodiment, new users may feel welcomed and involved in the live streaming room, which may improve the user experience.

[0075] In some embodiments, the AI ​​chatbot may be able to perform similar or identical operations to other users in the live streaming room, as shown in FIG. 13. For example, the AI ​​chatbot may have a group call, a PK battle, a game battle, etc. with the live streamer. In some embodiments, the AI ​​chatbot may have a voice message AM to interact with the user. According to this embodiment, the AI ​​chatbot may make it easier for the live streamer to control the atmosphere in the live streaming room, which may improve the user experience.

[0076] As shown in FIG. 14, the AI ​​chatbot may have a profile page 620. The profile page 620 may be accessible, for example, by clicking on a display image of the AI ​​chatbot. In some embodiments, the profile page 620 of the AI ​​chatbot may include detailed information about the AI ​​chatbot, such as character, personality, level, age, interaction value, additional features, etc. In some embodiments, an add button 622 may be provided on the user's profile page 620 to add or follow the AI ​​chatbot. In some embodiments, other users may tag, gift, send PK invites, block, send direct messages to the AI ​​chatbot, etc.

[0077] In some embodiments, the AI ​​chatbot may be displayed on the thumbnail of the live streaming. As shown in FIG. 15, the user may request information of live streaming from the server 10, and the streaming information unit 302 may refer to the stream DB 320 and generate a list of available live streaming. Upon receiving the list, the UI control unit 202 of the user terminal 30 may generate a live streaming selection screen 622 based on the list and display it on the display of the user terminal 30. In some embodiments, the live streaming selection screen 622 may include thumbnails TN of each live streaming for the user to select.

[0078] In some embodiments, the thumbnail TN of the live streaming may include a mark 624 indicating whether or not an AI chatbot exists in the live streaming. The user may receive detailed information about the AI ​​chatbot by, for example, clicking the mark 624. According to this embodiment, each live streamer can create their own AI chatbot and use it as a selling point to motivate more viewers to participate in the live streaming.

[0079] FIG. 16 is a flowchart showing the steps of an application startup process in the user terminal 20, 30. The user may generate an AI chatbot in the live streaming room. Upon receiving a selection of the AI ​​chatbot from the user terminal of the user (S502), the server 10 may obtain training data for the selected AI chatbot based on the user's selection (S504). In some embodiments, the training data may be character data corresponding to a character. The character may be a celebrity, a user, an anime character, etc. The processing unit 306 may refer to a corresponding database in the server 10 or a resource on the Internet, such as a social media site or an official website.

[0080] In some embodiments, the processing unit 306 may further input the training data into a machine learning model, such as a language model, and generate an AI chatbot based on the training data (S506). In some embodiments, if the user sets a personality for the AI ​​chatbot, the processing unit 306 may further refer to the personality DB 328 and add corresponding prompt data to set the personality of the AI ​​chatbot. After generating the AI ​​chatbot, the processing unit 306 may set the AI ​​chatbot in the live streaming room (S508) and allow the AI ​​chatbot to interact with the user in the live streaming room. In some embodiments, the virtual chatbot may provide assistance to a live streamer or a viewer in the live streaming room.

[0081] According to the present disclosure, the AI ​​chatbot equipped with the character can increase the interaction and enjoyment in the live streaming room. Furthermore, the monitoring and response of the atmosphere in the live streaming can be partially or entirely entrusted to the AI ​​chatbot. Therefore, the user experience can be improved.

[0082] In some embodiments, the selection of the character, personality, additional function, etc. may be realized by a random button. For example, the user may click the random button to randomly generate an AI chatbot having a random character, personality, additional function, etc. According to this embodiment, an AI chatbot having a random character, personality, additional function, etc. is generated, which can improve the atmosphere in the live streaming room.

[0083] In some embodiments, the user may cue or tag the AI ​​chatbot by text, voice, video message, etc. For example, the live streamer may cue the AI ​​chatbot by clicking a button, typing a specific message, saying a specific message, making a specific gesture, etc. According to this embodiment, the live streamer may cue the AI ​​chatbot for help when the atmosphere in the live streaming room is not exciting, thereby improving the atmosphere in the live streaming room.

[0084] In some embodiments, there may be more than one AI chatbot in a live streaming room. One AI chatbot in the live streaming room may interact with another AI chatbot. In some embodiments, the user may signal one AI chatbot to interact with another AI chatbot. The user may signal different AI chatbots to interact with each other. For example, the user may signal Street Fighter and Nintendo character AI chatbots to interact, PK, etc. According to this embodiment, the fun in the live streaming room can be improved.

[0085] In some embodiments, the AI ​​chatbot may be a guide in the live streaming room. The AI ​​chatbot may guide the live streamer or the viewer to do live streaming, watch live streaming, interact with the live streamer, play games, etc. In some embodiments, when a new feature such as a game is released, the AI ​​chatbot may experience the new feature in one live streaming room and share the experience in another live streaming room. According to this embodiment, the barrier for the user to experience the new feature may be reduced, and the user experience may be improved.

[0086] In some embodiments, the AI ​​chatbot may mute, ban, or block a user if the user violates the rules of the live streaming platform. For example, if a user's comments contain inappropriate language or illegal point information, the AI ​​chatbot may mute or ban the user from the live streaming room. In some embodiments, the AI ​​chatbot may perform the above actions automatically or upon request from the live streamer or other users. According to this embodiment, the AI ​​chatbot can help the live streamer respond to the atmosphere in the live streaming room.

[0087] In some embodiments, the AI ​​chatbot may be generated, such as by spending points within the live streaming platform. In some embodiments, the AI ​​chatbot may be generated only by users with a certain level or status, such as level 80 or above or VIP status. In some embodiments, the points for generating the AI ​​chatbot may be paid by one user or shared by multiple users. In some embodiments, the points for generating two or more AI chatbots may be the same or may be increased based on the number of AI chatbots, etc.

[0088] In some embodiments, the chatbot's character, personality, and characteristics may be learned through input from the user in the live streaming room. The user may provide input as prompt data to give the AI ​​chatbot a new personality, etc. In some embodiments, each user may have their own AI chatbot with customized character, personality, and characteristics. In some embodiments, a campaign may be held in which users can show off their AI chatbots and compete against each other.

[0089] The AI ​​chatbot may respond to interactions from the user in the live streaming room. In some embodiments, the AI ​​chatbot may automatically provide topics or generate conversations, such as periodically or when the atmosphere in the live streaming room becomes unfriendly. For example, the AI ​​chatbot may provide hourly news updates or provide horoscope information when there is no interaction in the live streaming room.

[0090] In some embodiments, the AI ​​chatbot may receive user information from within the live streaming platform or from an external social media site and send a cue to the user based on the information. For example, a user may post an article about a trip to Thailand on a live streaming platform, and the AI ​​chatbot may obtain information from the article. When the user enters a live streaming room, the AI ​​chatbot may send a cue to the user and ask questions about the trip to Thailand. This embodiment may help create a conversation between the live streamer and the user, and may motivate the user to interact more with users in the live streaming room.

[0091] In some embodiments, the AI ​​chatbot may collect interaction history information between the user and the live streamer and provide the information to the live streamer. For example, if the live streamer had a conversation with the user three days ago or clicked "like" on the user's post yesterday, the AI ​​chatbot may provide a hint message to the live streamer to help the live streamer remember the interaction with the user. This embodiment may make it easier for the live streamer to remember the user, improving the user experience.

[0092] In some embodiments, the AI ​​chatbot may store information about the user from interactions with the user. For example, if the user tells the AI ​​chatbot that he or she is a Taurus, the AI ​​chatbot may receive the information and store the information in the training data DB, user DB, etc. More specifically, the processing unit 306 may further obtain interactions in the live streaming room and update the training data DB and user DB in real time. According to this embodiment, the interaction between the AI ​​chatbot and the user may be smooth, and the user experience may be improved.

[0093] In some embodiments, the AI ​​chatbot may start live streaming, etc. In some embodiments, the AI ​​chatbot may provide information related to its character. For example, if the AI ​​chatbot is a fortune teller or astrologer, the AI ​​chatbot may provide horoscope information through live streaming, etc. In some embodiments, the design and functions of the AI ​​chatbot may be flexibly determined according to actual needs.

[0094] In some embodiments, the AI ​​chatbot may receive interactions between the live streamer and the viewer and learn how the live streamer interacts with the viewer. In some embodiments, the AI ​​chatbot may be trained to talk, interact, and play games with the viewer in the same way as the live streamer. In some embodiments, the live streamer may set the AI ​​chatbot as a substitute live streamer while the live streamer is unavailable. For example, the live streamer or viewer may set the AI ​​chatbot as a substitute player to leave an online mahjong game, such as to go to the bathroom. In some embodiments, a switch button may be provided to set an auto-play mode or an auto-interaction mode and have the AI ​​chatbot play games or interact with the viewer.

[0095] In some embodiments, natural language processing techniques such as TTS (Text-to-Speech) and STT (Speech-to-Text) may also be introduced. For example, audio data such as voice from the live streamer may be converted into text information and input into a machine learning model, or the text output may be converted into voice, and the AI ​​chatbot may respond to the user via the voice data. In some embodiments, the tone, pitch, quality, tempo, and speed of the voice message may change depending on emotions. For example, the AI ​​chatbot may speak at a high pitch and at a high speed when it is very excited.

[0096] In some embodiments, the AI ​​chatbot may have an avatar or virtual skin. In some embodiments, the avatar or virtual skin may be provided by a platform provider, customized by the user, etc. In some embodiments, the AI ​​chatbot's facial features, gestures, and movements may change based on emotions. For example, the AI ​​chatbot may smile when receiving a gift and show an angry face when receiving a negative message. In some embodiments, the avatar or virtual skin may be provided by the server 10 or by third-party software such as Live2D, VRoid Hub, etc.

[0097] In some embodiments, the AI ​​chatbot's emotions may change based on the live streamer's status in the live streaming room. For example, the AI ​​chatbot may show positive emotions, such as happiness, when the live streamer receives a gift or a reward at an event that exceeds a certain number of points. In some embodiments, a lookup table may be provided that stores the relationship between a certain achievement and a corresponding emotion. For example, the AI ​​chatbot may be happy when the live streamer receives more than 1,000 points, dance when the live streamer receives more than 10,000 points, etc.

[0098] In some embodiments, the server 10 may further include an emotion unit for processing emotions of the AI ​​chatbot. The emotion unit may be configured to process emotions of the AI ​​chatbot, such as information of text, voice, video messages from the AI ​​chatbot. In some embodiments, the emotions of the AI ​​chatbot may change randomly or periodically. For example, the AI ​​chatbot may change emotions every day, etc. The information of emotions may be received from the Internet, etc.

[0099] In some embodiments, the emotion unit may refer to an internal database or an external resource such as an astrology website to receive an individual horoscope, and further determine the emotion based on the horoscope. For example, if the AI ​​chatbot is set to be a Taurus astrologer, the emotion unit may refer to an astrology website to obtain the Taurus horoscope for that day. If the Taurus horoscope indicates that it is a lucky day, the emotion unit may set a positive emotion for the AI ​​chatbot, and so on.

[0100] In some embodiments, the server 10 may further include a storage unit for processing the interaction between the AI ​​chatbot and the user in the live streaming room. The storage unit may be configured to store information of the user in the live streaming room. For example, if a user says that he is a Gemini, the storage unit may extract the information from the message and store the information in, for example, the user DB 322 or the training data DB 326. When the user interacts with the AI ​​chatbot, the information may be further used as a topic, etc. For example, if the user enters the live streaming room on another day, the AI ​​chatbot may say "Nice to meet you again" or provide this week's Gemini horoscope for reference.

[0101] FIG. 17 is a schematic diagram illustrating an example of a functional configuration of a live streaming system 1 according to some embodiments of the present disclosure. In some embodiments, the live streaming system 1 may further include an inference system. The inference system may be configured to infer a mood or emotion set for the AI ​​chatbot. As shown in FIG. 17, the AI ​​chatbot may be implemented with different functions. In some embodiments, the customized virtual skin, text-to-speech, speech-to-text conversion, character data, prompt data, etc. may be implemented in the AI ​​chatbot. In some embodiments, the above-mentioned techniques may be used individually or in combination.

[0102] In some embodiments, the interaction between the AI ​​chatbot and the user may also be input to the AI ​​chatbot. Data in the AI ​​chatbot may further be sent to the inference system. In some embodiments, the AI ​​chatbot may also act as an assistant, and corresponding data may also be sent to the inference system. Furthermore, the environmental status of the live streaming room may also be input to the inference engine in real time.

[0103] In some embodiments, the environment status may include knowledge and status of the live streaming room. Here, the "knowledge" may refer to topics in the live streaming room. In some embodiments, the AI ​​chatbot may collect topics that the user is interested in based on the character data and personality data of the AI ​​chatbot. The "status" may refer to the current status in the live streaming room. For example, the status of the live streaming room may be the live streamer's reception points, broadcast time length, number of followers, number of subscribers, etc.

[0104] In some embodiments, all the above information may be sent to the inference system. Based on the above input, the inference system may infer a possible mood index from the emotion unit. Here, the mood index may refer to the mood of the AI ​​chatbot. For example, if the character of the AI ​​chatbot is Aquarius, the inference engine may use today's horoscope for Aquarius to generate a mood index. Furthermore, interactions in the live streaming room and topics that users are interested in may also be used as inputs to generate a mood index. Furthermore, the index may be input to a machine learning model, such as a large-scale language model (LLM). Furthermore, the interaction information stored by the storage unit may also be input to the machine learning model.

[0105] In some embodiments, the procedure may be performed randomly or periodically, such as once a day. In some embodiments, the mood of the AI ​​chatbot may be determined based on the procedure. According to the embodiment, the interaction between the AI ​​chatbot and the user may be different based on the mood of the AI ​​chatbot. Even if the interaction from the user is the same, the AI ​​chatbot may generate different outputs based on different moods. Therefore, the fun in the live streaming room may be increased, and the user experience may be improved.

[0106] According to the embodiment, the original AI chatbot may be trained by the inference system, memory unit, emotion unit, etc. Thus, a unique AI chatbot with added prompt data can be obtained. In some embodiments, the output from the LLM may be provided as the status of the live streaming room and further input to the inference engine again as a loop. Thus, the AI ​​chatbot may have different characters, personalities, emotions, moods on different days, and the interaction between the AI ​​chatbot and the user may be unpredictable and more interesting. Thus, the user experience may be improved.

[0107] Fig. 18 is a schematic block diagram of a system configuration and computer hardware for executing processing according to some embodiments of the present disclosure. The information processing device 900 in Fig. 18 is configured to realize, for example, the server 10 and the user terminals 20 and 30 according to some embodiments of the present disclosure.

[0108] The information processing device 900 includes a CPU 901, a read-only memory (ROM) 903, and a random access memory (RAM) 905. The information processing device 900 may further include a host bus 907, a bridge 909, an external bus 911, an interface 913, an input unit 915, an output unit 917, a storage unit 919, a drive 921, a connection port 925, and a communication unit 929. The information processing device 900 may include an imaging device (not shown) such as a camera. The information processing device 900 may include a processing circuit such as a digital signal processor (DSP) or an application specific integrated circuit (ASIC) instead of or in addition to the CPU 901.

[0109] The CPU 901 functions as an arithmetic processing device and a control device, and controls the overall operation of the information processing device 900 or a part of the operation according to various programs recorded in the ROM 903, the RAM 905, the storage unit 919, or the removable recording medium 923. For example, the CPU 901 controls the overall operation of each functional unit included in the server 10 and the user terminals 20 and 30 of the above-mentioned embodiment. The ROM 903 stores programs and operation parameters used by the CPU 901. The RAM 905 transiently stores programs used when the CPU 901 executes programs and parameters that change appropriately when the programs are executed. The CPU 901, the ROM 903, and the RAM 905 are connected to each other via a host bus 907 consisting of an internal bus such as a CPU bus. The host bus 907 is connected to an external bus 911 such as a peripheral component interconnect / interface (PCI) bus via the bridge 909.

[0110] The input unit 915 is a device operated by a user, such as a mouse, a keyboard, a touch panel, a button, a switch, or a lever. The input unit 915 may be a device that converts a physical quantity into an electric signal, such as an audio sensor (such as a microphone), an acceleration sensor, a tilt sensor, an infrared sensor, a depth sensor, a temperature sensor, or a humidity sensor. The input unit 915 may be, for example, a remote control device that uses infrared rays or another type of radio wave. Alternatively, the input unit 915 may be an external connection terminal 927 such as a mobile phone that supports the operation of the information processing device 900. The input unit 915 includes an input control circuit that generates an input signal based on information input by a user and outputs the generated input signal to the CPU 901. The user operates the input unit 915 to input various data and instruct the information processing device 900 to perform a processing operation.

[0111] The output unit 917 includes a device that can visually or audibly notify the user of the acquired information. The output unit 917 may be, for example, a display device such as an LCD, a PDP, or an OLED, an audio output device such as a speaker or a headphone, a printer, etc. The output unit 917 outputs the results obtained by the processing executed by the information processing device 900 in the form of text, video such as an image, or sound such as voice.

[0112] The storage unit 919 is a data storage device and is an example of a storage unit of the information processing device 900. The storage unit 919 includes, for example, a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, a magneto-optical storage device, etc. The storage unit 919 stores programs and various data executed by the CPU 901, and various data acquired from the outside.

[0113] The drive 921 is a reader / writer of a removable recording medium 923 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and is built into or externally attached to the information processing device 900. The drive 921 reads out information recorded on the attached removable recording medium 923, and outputs it to the RAM 905. The drive 921 writes information to the attached removable recording medium 923.

[0114] The connection port 925 is a port used for directly connecting a device to the information processing device 900. The connection port 925 may be, for example, a USB (Universal Serial Bus) port, an IEEE1394 port, or a SCSI (Small Computer System Interface) port. The connection port 925 may be an RS-232C port, an optical audio terminal, an HDMI (High Definition Multimedia Interface (registered trademark)) port, or the like. By connecting an external connection terminal 927 to the connection port 925, various data can be exchanged between the information processing device 900 and the external connection terminal 927.

[0115] The communication unit 929 is, for example, a communication interface including a communication device for connecting to a communication network NW. The communication unit 929 may be, for example, a communication card for a wired or wireless local area network (LAN), Bluetooth (registered trademark), or Wireless USB (WUSB).

[0116] The communication unit 929 may be, for example, a router for optical communication, a router for ADSL (asymmetric digital subscriber line), or a modem for various types of communication. For example, the communication unit 929 transmits and receives signals on the Internet and transmits and receives signals with other communication devices using a predetermined protocol such as TCP / IP. The communication network NW to which the communication unit 929 is connected is a network established by a wired connection or a wireless connection. The communication network NW is, for example, the Internet, a home LAN, infrared communication, radio wave communication, or satellite communication.

[0117] The imaging device (not shown) is a device that captures real space and generates a captured image using an imaging element such as a CCD (charge-coupled device) or a CMOS (complementary metal-oxide semiconductor) and various members such as a lens for controlling the formation of a subject image on the imaging element. The imaging device may capture still images or moving images.

[0118] The live streaming system 1 of the present disclosure has been described above with reference to the embodiments. The above-mentioned embodiments are described merely for the purpose of explanation. Rather, those skilled in the art can easily conceive of various combinations of the above-mentioned components and processes of the embodiments and various modifications, which are also included in the technical scope of the present disclosure.

[0119] The steps described in this specification, particularly the steps described using flow charts or flow charts, may include some of the steps constituting the steps, may include steps not explicitly included in the steps constituting the steps, and / or may rearrange the order of the steps. Such omissions, additions, and rearrangements of steps are also included in the scope of the present disclosure as long as they do not deviate from the gist of the present disclosure.

[0120] In some embodiments, at least a part of the functions performed by the server 10 may be performed by a device other than the server 10, for example, the user terminal 20 or 30. In some embodiments, at least a part of the functions performed by the user terminal 20 or 30 may be performed by a device other than the user terminal 20 or 30, for example, the server 10. In some embodiments, rendering of frame images may be performed by the user terminal of a viewer, a server, a live streamer, or the like.

[0121] Furthermore, the system or method described in the above embodiments may be provided in a non-transitory computer-readable storage device such as a solid-state storage device, an optical disk storage device, a magnetic disk storage device, or a computer program product. Alternatively, the program may be downloaded from a server via the Internet.

[0122] In the embodiment of the present disclosure, the method can be applied to the server, the viewer side, the streamer side, but is not limited thereto. The implementation terminal can include, but is not limited to, electronic terminals such as smartphones, desktop computers, laptops, tablet computers, etc.

[0123] Although the technical contents and features of the present disclosure have been described above, those skilled in the art can still make many variations and modifications without departing from the teachings and disclosure of the present disclosure. Therefore, the scope of the present disclosure is not limited to the embodiments already disclosed, but is within the scope of the following claims, including other variations and modifications that do not depart from the present disclosure. [Explanation of symbols]

[0124] 1. Live Streaming System 10 Server 20 User terminal 100 Streaming Units 102 Video control unit 104 Audio control unit 106 Delivery Unit 108 UI control unit 200 viewing units 202 UI control unit 204 Rendering Units 206 Input Transmission Unit 30, 30a, 30b User terminal 302 Streaming Information Unit 304 Relay unit 306 Processing Unit 320 Stream DB 322 User DB 324 AI Chatbot DB 326 Training Data DB 328 Personality DB 330 Language Models 600 screens 602 Object 604 images 606 Message Zone 608 Message input box 610 Gift Object 612 Shared Objects 614 Button 900 Information processing device 901 CPU 903 ROM 905 RAM 907 Host Bus 909 Bridge 911 External Bus 913 Interface 915 Input Unit 917 Output Unit 919 Storage Unit 921 Drive 923 Removable Recording Media 925 Connection Port 927 External connection terminal 929 Communication Unit LS Live Streaming LV Live Streamer NW Network SP Specific part AU1, AU2 viewers S502, S504, S506, S508 process VD, VD1, VD2 Video

Claims

1. 1. A server for processing interactions in a live streaming platform, comprising: one or more processors, the one or more processors executing machine-readable instructions to: A function to receive character data corresponding to the character, A function of inputting the character data into a machine learning model to generate a virtual chatbot in a live streaming room; and configuring the virtual chatbot in the live streaming room; The virtual chatbot is configured to provide assistance to a live streamer or a viewer in the live streaming room. A server comprising:

2. receiving a selection of the character from a first user; The character data of the character is obtained from a database within the server or from an external resource on the Internet related to the character; The character is a celebrity, a user of the live streaming platform, or an animated character; 2. The server according to claim 1 .

3. and receiving a personality selection from the first user; obtaining prompt data corresponding to the personality; and inputting the prompt data into the machine learning model to generate the personality on the virtual chatbot; 2. The server according to claim 1 .

4. receiving a status of said live streaming room while the live streamer is participating in the event; and displaying a hint message via the virtual chatbot in response to detecting a trigger during the event. The server of claim 1 , wherein the hint message includes information for guiding the live streamer or other users at the event.

5. A function of acquiring information of users in the live streaming room; tagging the user via the virtual chatbot based on the information of the user; The server of claim 1 further comprising:

6. receiving interactions from users in the live streaming room; inputting said interactions into said machine learning model; generating an output from the machine learning model; transmitting said output to said live streaming room via said virtual chatbot; The server of claim 1 further comprising:

7. The virtual chatbot includes a level and an interaction value; the level and the interaction value are increased based on a user's past interactions with the virtual chatbot; a real-time interaction from the virtual chatbot to the user varies based on the level and the interaction value of the virtual chatbot; 2. The server according to claim 1 .

8. The server according to claim 1 , wherein information of the virtual chatbot is further displayed on a thumbnail of the live streaming room.

9. 1. A method for processing interactions on a live streaming platform, comprising: receiving character data corresponding to a character; inputting the character data into a machine learning model to generate a virtual chatbot in a live streaming room; and configuring the virtual chatbot in the live streaming room; The virtual chatbot is configured to provide assistance to a live streamer or a viewer in the live streaming room. A method comprising:

10. A computer program comprising: A function to receive character data corresponding to the character, A function of inputting the character data into a machine learning model to generate a virtual chatbot in a live streaming room; and configuring the virtual chatbot in the live streaming room. The virtual chatbot is configured to provide assistance to a live streamer or a viewer in the live streaming room. A computer program comprising:

Images