Electronic device and method for controlling electronic device
The electronic device employs a chatbot model to analyze real-time chat room conditions and provide tailored suggestions, addressing the challenges of user participation by adapting chat suggestions to participant numbers and conversation volumes, thus enhancing engagement and interaction quality.
Patent Information
- Application Number
- PCT/KR2024/005584
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-19
- Filing Date
- 2024-04-25
- Publication Date
- 2024-11-28
AI Technical Summary
Existing chat services struggle to encourage user participation in chat rooms due to dynamic changes in participant numbers and conversation volumes, leading to difficulties in forming meaningful interactions, especially when participants are unfamiliar with each other or when conversation volumes are high, resulting in decreased willingness to engage.
An electronic device equipped with a processor and memory that uses a chatbot model to analyze real-time chat room situation information, such as participant numbers and conversation volumes, to provide tailored chat suggestion messages, including conversation topics, text inputs, or emoticon suggestions, to enhance user engagement.
The solution significantly improves user participation rates by providing context-specific chat suggestions that adapt to changing chat room dynamics, making interactions more engaging and readable, even in large or low-participation scenarios.
Smart Images

Figure KR2024005584_28112024_PF_FP_ABST
Abstract
Description
Electronic devices and methods of controlling electronic devices
[0001] The present disclosure relates to an electronic device and a method for controlling the electronic device, and more particularly, to an electronic device capable of providing a chat suggestion message and a method for controlling the same.
[0002] Recently, services have been provided that allow users to share their opinions on the content they are watching through real-time chat with multiple people while watching content on TV or smartphones.
[0003] However, these services are difficult to activate without participants' willingness to participate in conversation. Specifically, even if participants are watching the same content and participating in the same chatroom, they may not know each other, making it difficult to engage in conversation. Even if they willingly enter messages, their willingness to participate may decline if there's no meaningful response.
[0004] Furthermore, if a chat room has a small number of participants or a low volume of conversation, it can be difficult to establish topics of conversation among participants, making it difficult to expect participants to actively participate in the conversation. Conversely, if a chat room has a large number of participants or a high volume of conversation, many messages can disappear from the chat room screen at a rapid rate, making it difficult to check messages. Furthermore, even if users type messages, they may not receive a response.
[0005] Meanwhile, recent developments have focused on technologies that automatically provide messages suggesting users' participation in chats, aimed at stimulating participants' participation. However, existing technologies have been criticized for their inability to effectively provide chat suggestion messages tailored to real-time changing chat room conditions, such as the number of participants, the volume of conversation, and the content being viewed.
[0006] The present disclosure is intended to overcome the limitations of the prior art as described above, and an object of the present disclosure is to provide an electronic device and a control method thereof capable of providing a chat suggestion message in consideration of a chat room situation that changes in real time.
[0007] According to one embodiment of the present disclosure for achieving the above-described object, an electronic device includes a display, a memory storing at least one instruction, and a processor executing the at least one instruction, wherein the processor controls the display to display a user interface for a chat room in which a user of the electronic device has participated, obtains chat room situation information including at least one of information on the number of participants in the chat room and information on the volume of conversation in the chat room, inputs the chat room situation information into a chatbot model, obtains a different chat suggestion message according to at least one of the number of participants and the volume of conversation, and controls the display to display the chat suggestion message on the user interface.
[0008] Here, the chatbot model can obtain a chat suggestion message for suggesting a conversation topic of the chat room when the number of participants is less than the first threshold value, and can obtain a chat suggestion message for suggesting a response to at least one message of the chat room when the number of participants is greater than or equal to the first threshold value.
[0009] Meanwhile, the chatbot model can obtain a chat suggestion message for suggesting text input when the conversation volume is less than the second threshold value, and can obtain a chat suggestion message for suggesting emoticon input when the conversation volume is greater than the second threshold value.
[0010] Meanwhile, the user interface is displayed based on a user input for participating in the chat room while the content is displayed on the display, the chat room situation information further includes information about the situation included in the content, and the processor can obtain different chat suggestion messages depending on the situation included in the content.
[0011] Here, the processor can obtain a capture image of the content and input the capture image into an image analysis model to obtain information about the situation.
[0012] Meanwhile, the processor can obtain information about the situation by inputting the captured image into a text analysis model.
[0013] Meanwhile, when the user interface is displayed, the processor can input information about the chat room conversation content before the user input is received into a summary model to obtain summary information about the chat room conversation content, and control the display to display the summary information.
[0014] Meanwhile, when a participant of the chat room inputs a threshold number or more of messages within a threshold period, the processor controls the display to change the display method of the messages input by the participant after the threshold period and display them, and the display method may include at least one of the size, thickness, and color of the message.
[0015] Here, if the participant is a key participant, the processor can control the display to display a message entered by the key participant within the user interface for a preset period of time.
[0016] Meanwhile, the electronic device further includes a communication unit, and the chatbot model is a large language model included in an external server, and the processor controls the communication unit to obtain a query based on the chat room situation information and transmit the query to the external server, and receives a response to the query obtained by the chatbot model from the external server through the communication unit, and obtains the chat suggestion message based on the response.
[0017] According to one embodiment of the present disclosure for achieving the above-described purpose, a method for controlling an electronic device may include a step of displaying a user interface for a chat room in which a user of the electronic device has participated, a step of obtaining chat room situation information including at least one of information on the number of participants in the chat room and information on the volume of conversation in the chat room, a step of inputting the chat room situation information into a chatbot model to obtain a different chat suggestion message according to at least one of the number of participants and the volume of conversation, and a step of displaying the chat suggestion message on the user interface.
[0018] Meanwhile, the chatbot model may obtain a chat suggestion message for suggesting a conversation topic of the chat room when the number of participants is less than the first threshold value, and may obtain a chat suggestion message for suggesting a response to at least one message of the chat room when the number of participants is greater than or equal to the first threshold value.
[0019] The above chatbot model can obtain a chat suggestion message for suggesting text input when the conversation volume is less than the second threshold value, and can obtain a chat suggestion message for suggesting emoticon input when the conversation volume is greater than the second threshold value.
[0020] Meanwhile, the user interface is displayed based on a user input for participating in the chat room while the content is displayed on the display, the chat room situation information further includes information about the situation included in the content, and the step of obtaining the chat suggestion message can obtain different chat suggestion messages depending on the situation included in the content.
[0021] Here, the step of obtaining chat room situation information may include the step of obtaining a captured image of the content and the step of inputting the captured image into an image analysis model to obtain information about the situation.
[0022] Meanwhile, the step of obtaining chat room situation information may include a step of obtaining information about the situation by inputting the captured image into a text analysis model.
[0023] Meanwhile, the control method of the electronic device may further include a step of inputting information about the chat room conversation content before the user input is received into a summary model when the user interface is displayed, thereby obtaining summary information about the chat room conversation content, and a step of displaying the summary information.
[0024] Meanwhile, the control method of the electronic device further includes a step of changing the display method of a message input by the participant after the threshold period when the participant of the chat room inputs a threshold number or more of messages within the threshold period, and the display method may include at least one of the size, thickness, and color of the message.
[0025] Here, the method for controlling the electronic device may further include a step of displaying a message input by the participant within the user interface for a preset period of time if the participant is a designated important participant.
[0026] According to one embodiment of the present disclosure for achieving the above-described object, a non-transitory computer-readable recording medium including a program for executing a method for controlling an electronic device may include a step of displaying a user interface for a chat room in which a user of the electronic device has participated, a step of obtaining chat room situation information including at least one of information on the number of participants in the chat room and information on the volume of conversation in the chat room, a step of inputting the chat room situation information into a chatbot model to obtain a different chat suggestion message according to at least one of the number of participants and the volume of conversation, and a step of displaying the chat suggestion message on the user interface.
[0027] FIG. 1 is a block diagram briefly illustrating a configuration of an electronic device according to one or more embodiments of the present disclosure;
[0028] Figures 2 to 5 are drawings for explaining embodiments that provide different chat suggestion messages based on the number of participants and the amount of conversation.
[0029] FIG. 6 is a diagram illustrating embodiments of providing different chat suggestion messages based on information about a situation included in content.
[0030] FIG. 7 is a drawing for explaining an embodiment that provides a summary of the conversation before a user enters a chat room.
[0031] FIG. 8 is a drawing for explaining an embodiment of changing the display method of a message entered by a chat room participant.
[0032] FIG. 9 is a diagram illustrating a process for implementing one or more embodiments according to the present disclosure by a system including an electronic device, a first server, and a second server;
[0033] FIG. 10 is a block diagram detailing the configuration of an electronic device according to one or more embodiments of the present disclosure, and
[0034] FIG. 11 is a flowchart illustrating a method for controlling an electronic device according to one or more embodiments of the present disclosure.
[0035] The present embodiments may be modified and have various embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope to specific embodiments, but should be understood to encompass various modifications, equivalents, and / or alternatives of the embodiments of the present disclosure. In connection with the description of the drawings, similar reference numerals may be used for similar components.
[0036] In describing the present disclosure, if it is determined that a specific description of a related known function or configuration may unnecessarily obscure the gist of the present disclosure, a detailed description thereof will be omitted.
[0037] Additionally, the following embodiments may be modified in various other forms, and the scope of the technical concepts of the present disclosure is not limited to the following embodiments. Rather, these embodiments are provided to further faithfully and completely convey the technical concepts of the present disclosure to those skilled in the art.
[0038] The terminology used in this disclosure is for the purpose of describing specific embodiments only and is not intended to limit the scope of the rights. Singular expressions include plural expressions unless the context clearly dictates otherwise.
[0039] In this disclosure, expressions such as “has,” “can have,” “includes,” or “may include” indicate the presence of a corresponding feature (e.g., a component such as a number, function, operation, or part), and do not exclude the presence of additional features.
[0040] In this disclosure, expressions such as “A or B,” “at least one of A and / or B,” or “one or more of A or / and B” can include all possible combinations of the listed items. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” can all refer to (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.
[0041] The expressions “first,” “second,” “first,” or “second,” etc., used in this disclosure can describe various components, regardless of order and / or importance, and are only used to distinguish one component from another, but do not limit the components.
[0042] When it is said that a component (e.g., a first component) is “(operatively or communicatively) coupled with / to” or “connected to” another component (e.g., a second component), it should be understood that said component may be directly coupled to said other component, or may be coupled via another component (e.g., a third component).
[0043] On the other hand, when it is said that a component (e.g., a first component) is "directly connected" or "directly connected" to another component (e.g., a second component), it can be understood that no other component (e.g., a third component) exists between said component and said other component.
[0044] The expression "configured to" as used in the present disclosure may be used interchangeably with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." The term "configured to" may not necessarily mean only "specifically designed to" in terms of hardware.
[0045] Instead, in some contexts, the phrase "a device configured to" may mean that the device, in conjunction with other devices or components, is "capable of" performing A, B, and C. For example, the phrase "a processor configured (or set) to perform A, B, and C" may refer to a dedicated processor (e.g., an embedded processor) for performing those operations, or a general-purpose processor (e.g., a CPU or application processor) that can perform those operations by executing one or more software programs stored in a memory device.
[0046] In the embodiments, a 'module' or 'part' performs at least one function or operation, and may be implemented as hardware or software, or as a combination of hardware and software. Furthermore, a plurality of 'modules' or 'parts' may be integrated into at least one module and implemented as at least one processor, except for a 'module' or 'part' that needs to be implemented as a specific hardware.
[0047] Meanwhile, the various elements and areas in the drawings are schematically drawn. Therefore, the technical concept of the present invention is not limited by the relative sizes or spacing depicted in the attached drawings.
[0048] Hereinafter, with reference to the attached drawings, embodiments according to the present disclosure will be described in detail so that a person having ordinary knowledge in the technical field to which the present disclosure pertains can easily implement the present disclosure.
[0049] FIG. 1 is a block diagram briefly illustrating the configuration of an electronic device (100) according to one or more embodiments of the present disclosure.
[0050] An electronic device (100) according to the present disclosure is a device capable of providing a chatbot service, and in particular, the electronic device (100) can provide a chat suggestion message using a chatbot model, which is a neural network model for providing a chatbot service. The chatbot model according to the present disclosure may be implemented as an on-device included in the electronic device (100), or may be implemented in an external device connected to the electronic device (100). Meanwhile, the electronic device (100) may be implemented as various devices, such as a TV, a smartphone, a server, etc., and there is no particular limitation on the type of the electronic device (100).
[0051] As illustrated in FIG. 1, the electronic device (100) according to the present invention may include a display (110), a memory (120), and a processor (130).
[0052] The display (110) can output image data under the control of the processor (130). The display (110) can output an image previously stored in the memory (120) under the control of the processor (130). The display (110) can be implemented as an LCD (Liquid Crystal Display Panel), an OLED (Organic Light Emitting Diodes), etc., and in some cases, the display (110) can also be implemented as a flexible display (110), a transparent display (110), etc. However, the display (110) according to the present disclosure is not limited to a specific type.
[0053] In particular, in one or more embodiments, the display (110) may display a user interface for providing a chatbot service. Specifically, the user interface may be a chat interface capable of displaying messages entered by multiple participants, including the user of the electronic device (100). The user interface according to the present disclosure may be of the type illustrated in FIG. 2, but there are no particular limitations on the type of user interface according to the present disclosure.
[0054] At least one instruction regarding the electronic device (100) may be stored in the memory (120). In addition, an O / S (Operating System) for driving the electronic device (100) may be stored in the memory (120). In addition, various software programs or applications for operating the electronic device (100) according to various embodiments of the present disclosure may be stored in the memory (120). In addition, the memory (120) may include a semiconductor memory (120) such as a flash memory (120) or a magnetic storage medium such as a hard disk.
[0055] Specifically, the memory (120) may store various software modules for operating the electronic device (100) according to various embodiments of the present disclosure, and the processor (130) may control the operation of the electronic device (100) by executing the various software modules stored in the memory (120). That is, the memory (120) is accessed by the processor (130), and data reading / recording / modifying / deleting / updating, etc. may be performed by the processor (130).
[0056] Meanwhile, in the present disclosure, the term memory (120) may be used to mean a memory (120), a ROM (not shown), a RAM (not shown) in a processor (130), or a memory (120) card (not shown) (e.g., a micro SD card, a memory (120) stick) mounted on an electronic device (100).
[0057] In particular, in one or more embodiments, the memory (120) may provide information on chatbot models, user interface data, chat room context information, chat suggestion messages, etc. In addition, the memory (120) may store various information, such as threshold values for the number of participants, threshold values for the amount of conversation, summary information on chat room conversation content, etc.
[0058] In addition, various information necessary within the scope of achieving the purpose of the present disclosure may be stored in the memory (120), and the information stored in the memory (120) may be updated as received from an external device or input by a user.
[0059] The processor (130) controls the overall operation of the electronic device (100). Specifically, the processor (130) is connected to the configuration of the electronic device (100) including the display (110) and the memory (120), and can control the overall operation of the electronic device (100) by executing at least one instruction stored in the memory (120) as described above.
[0060] The processor (130) may be implemented in various ways. For example, the processor (130) may be implemented as at least one of an application specific integrated circuit (ASIC), an embedded processor (130), a microprocessor (130), hardware control logic, a hardware finite state machine (FSM), and a digital signal processor (130) (Digital Signal Processor, DSP). Meanwhile, the term "processor (130)" in the present disclosure may be used to mean a central processing unit (CPU), a graphic processing unit (GPU), and a microprocessor unit (MPU).
[0061] In particular, in one or more embodiments, the processor (130) may provide different chat suggestion messages depending on chat room situation information. Various embodiments implemented through the processor (130) will be described below.
[0062] The processor (130) can control the display (110) to display a user interface for a chat room in which a user of the electronic device (100) has participated.
[0063] The user interface for a chat room refers to a user interface that displays the status of a chat room in which a user of the electronic device (100) has participated. For example, the processor (130) may display information about multiple participants in the chat room (e.g., nicknames, profile pictures, etc. for each participant) on the user interface. In addition, the processor (130) may receive messages entered by multiple participants in the chat room from an external server providing a chat service and display the received messages on the user interface. In addition, the processor (130) may display messages generated by a chatbot according to the present disclosure on the user interface, as described below, and the processor (130) may also display information about the number of chat room participants and content to be viewed on the user interface.
[0064] Meanwhile, the user interface for the chat room may be displayed based on the reception of a user input for joining the chat room, and may also be displayed based on the reception of a user input for viewing content. Here, at least one of the user input for joining the chat room and the user input for viewing content may be directly input to the electronic device (100), or may be received via an external device (e.g., a remote control, a smartphone, etc.) for controlling the electronic device (100).
[0065] Meanwhile, the electronic device (100) may display both a chat interface and content, but the device displaying the chat interface and the device displaying the content may be different from each other, such as when a user inputs a chat message through a smartphone while watching content through a TV.
[0066] The processor (130) can obtain chat room situation information. The processor (130) can periodically obtain the chat room situation information as described above and store it in the memory (120). For example, the processor (130) can obtain chat room situation information by periodically receiving the chat room situation information from an external server providing a chat service.
[0067] In the present disclosure, the term "chat room situation information" is used as a general term to refer to information about participants participating in a chat room, messages entered by participants, content to be viewed by participants, etc., and the chat room situation information may specifically include the following information.
[0068] First, chat room context information may include at least one of information about the number of chat room participants and information about the chat room's conversation volume. For example, chat room context information may include information about the current (i.e., at the time the chat room context information is acquired) number of chat room participants, the chat room's conversation volume, and the ratio of the number of participants to the conversation volume (i.e., the participants' conversation participation rate).
[0069] Second, chatroom context information can further include contextual information contained within the content. This contextual information can include information about the current situation of the content being viewed by chatroom participants. For example, if the content being viewed is a sports game, contextual information contained within the content can include information about which team is currently winning and the remaining game time. For another example, if the content being viewed is a drama, contextual information contained within the content can include information about the emotions expressed by characters' lines and facial expressions, and information about the remaining broadcast time.
[0070] Third, chat room context information may further include at least one of the following: content type, content title, at least one message entered in the chat room, the user's chat history, the user's content viewing history, the user's age, the user's gender, and the user's nationality. In other words, chat room context information may include not only information about the current chat room situation, but also information previously acquired and stored about participants in the chat room, messages entered by participants, and content viewed by participants.
[0071] The processor (130) inputs chat room situation information into a chatbot model to obtain different chat suggestion messages depending on at least one of the number of participants and the volume of conversation.
[0072] A chatbot model is a neural network model trained to obtain chat suggestion messages appropriate to the input chat room context information when chat room context information is input.
[0073] In this disclosure, the term "chat suggestion message" is used to collectively refer to guidance messages designed to encourage users to chat. The types of chat suggestion messages according to this disclosure may vary, and specific examples will be described below along with various embodiments.
[0074] In one or more embodiments, the chatbot model may obtain different chat suggestion messages depending on the number of participants in the chat room. For example, if the number of participants in the chat room is less than a first threshold, the chatbot model may obtain a chat suggestion message for suggesting a topic of conversation in the chat room. Conversely, if the number of participants in the chat room is greater than or equal to the first threshold, the chatbot model may obtain a chat suggestion message for suggesting a response to at least one message in the chat room.
[0075] In one or more embodiments, the chatbot model may obtain different chat suggestion messages depending on the chat room's conversation volume. For example, if the chat room's conversation volume is below a second threshold, the chatbot model may obtain a chat suggestion message suggesting text input. If the chat room's conversation volume is above the second threshold, the chatbot model may obtain a chat suggestion message suggesting emoticon input.
[0076] Meanwhile, while the above has described embodiments of obtaining a chat suggestion message based on the number of chat room participants or the chat room's conversation volume, the present disclosure is not limited thereto. That is, the processor (130) may also obtain a chat suggestion message by considering both the number of chat room participants and the chat room's conversation volume.
[0077] In one or more embodiments, the chatbot model may obtain different chat suggestion messages based on the conversation participation rate of the participants. If the conversation volume to the number of participants is below a third threshold, the chatbot model may obtain a chat suggestion message to suggest a conversation topic in the chat room. Conversely, if the conversation volume to the number of participants is above the third threshold, the chatbot model may obtain a chat suggestion message to suggest a response to at least one message in the chat room.
[0078] Meanwhile, the number of chat room participants, the chat room conversation volume, and the participants' conversation participation rate described above may refer to the number of chat room participants, the chat room conversation volume, and the participants' conversation participation rate during a critical period. For example, the processor (130) may calculate an average value for the number of chat room participants, the chat room conversation volume, and the participants' conversation participation rate over the past minute based on the time at which the number of chat room participants, the chat room conversation volume, and the participants' conversation participation rate are calculated, and use the calculated average value as input data for a chatbot model for acquiring chat suggestion messages.
[0079] The various types of chat room situation information and the various types of chat suggestion messages obtained accordingly are described in more detail with reference to FIGS. 2 to 6.
[0080] The processor (130) may control the display (110) to display a chat suggestion message on the user interface. Specifically, the processor (130) may control the display (110) to display the chat suggestion message on the user interface in a manner that distinguishes it from messages entered by chat room participants.
[0081] In one or more embodiments, the processor (130) may control the display (110) to display a chat suggestion message in a pop-up window. Additionally, the processor (130) may obtain a voice signal corresponding to the chat suggestion message and output the voice signal through a speaker.
[0082] The processor (130) may also display a chat suggestion message with a pre-designated nickname. Specifically, if a user pre-designates a chatbot nickname, the processor (130) may display a chat suggestion message with the chatbot nickname having the pre-designated nickname.
[0083] The processor (130) may provide the chat suggestion message only to the user of the electronic device (100), or may transmit the chat suggestion message to an external server for the chat service so that other participants in the chat room can also see the chat suggestion message.
[0084] According to the embodiments described above with reference to FIG. 1, the electronic device (100) can actively provide a chat suggestion message that changes in real time and adapts to the situation, thereby significantly improving the user's chat participation rate.
[0085] In the above, we have briefly described an embodiment of obtaining different chat suggestion messages according to information on the number of chat room participants, which can be considered quantitative information among chat room situation information, and the volume of chat room conversation. Hereinafter, the embodiments of FIG. 1 will be described in more detail with reference to FIGS. 2 to 5, and then an embodiment of obtaining chat suggestion messages using various chat room situation information other than information on the number of chat room participants and the volume of chat room conversation will be described with reference to FIGS. 6 to 8.
[0086] FIGS. 2 to 5 are diagrams illustrating embodiments that provide different chat suggestion messages based on the number of participants and the volume of conversation.
[0087] In one or more embodiments, the processor (130) may obtain different chat suggestion messages based on the number of participants in a chat room through the chatbot model. Specifically, if the number of participants in the chat room is less than a first threshold, the chatbot model may obtain a chat suggestion message for suggesting a topic of conversation in the chat room to the user. If the number of participants in the chat room is greater than or equal to the first threshold, the chatbot model may obtain a chat suggestion message for suggesting a response to at least one message in the chat room to the user. In the present disclosure, for convenience of explanation, chat suggestion messages and the like are described as being provided to the user. However, it should be understood that the chat suggestion messages according to the present disclosure are not limited to specific users.
[0088] The processor (130) can obtain information on the number of chat room participants as chat room context information. For example, the processor (130) can calculate the number of participants at the time of obtaining the information on the number of chat room participants, or can calculate the average number of participants over the past minute based on the time of obtaining the information on the number of chat room participants. Meanwhile, the first threshold value may be determined differently depending on the user or developer's settings. In the following description, it is assumed that the first threshold value is 100 (people), as an example.
[0089] In the example of FIG. 2, since the number of participants in the chat room is 110, which is greater than the first threshold of 100, the processor (130) may provide the user with a chat suggestion message for suggesting a response to at least one message in the chat room. As illustrated in FIG. 2, the chat suggestion message for suggesting a response may be a message such as, “Let’s cheer together! Please respond to other participants’ messages.” In response, the user may input a message such as, “The selection list just came out, and XXX is selected!!” as illustrated in FIG. 2.
[0090] A chat suggestion message for suggesting a response may also be intended to suggest a response to a specific participant's message. For example, a chat suggestion message might suggest a response to the most recent message from a specific participant, such as "How about responding to Participant A's message?"
[0091] Meanwhile, the processor (130) may not only provide a chat suggestion message suggesting a response to at least one message in the chat room, but may also obtain at least one response to at least one message in the chat room and provide the obtained at least one response to the user. In this case, the processor (130) may display the selected response based on a user input selecting one or more of the provided at least one response. Here, the process of obtaining at least one response to at least one message in the chat room may be performed through an external server including a search engine.
[0092] In the example of FIG. 3, since the number of participants in the chat room is 15, which is less than the first threshold of 100, the processor (130) may provide the user with a chat suggestion message to suggest a conversation topic in the chat room. As illustrated in FIG. 3, the chat suggestion message for suggesting a conversation topic may be, "Let's have more fun together! Let's talk freely about various topics in the chat room." In response, the user may input a message such as, "I'm here! Who will win today?", as illustrated in FIG. 3.
[0093] According to the embodiment described above with reference to FIGS. 2 and 3, the electronic device (100) can encourage chatting by suggesting new conversation topics to the user, considering that it is difficult for conversation topics to be formed among the participants when the number of participants in the chat room is small. On the other hand, when the number of participants in the chat room is large, the electronic device (100) can encourage chatting by suggesting that the user respond to messages of other participants, considering that it is difficult to check messages because many messages disappear from the chat room screen at a high speed, and also it may be difficult to expect responses to messages entered by the participants.
[0094] In one or more embodiments, the chatbot model may obtain different chat suggestion messages depending on the chat room's conversation volume. Specifically, if the chat room's conversation volume is below a second threshold, the chatbot model may obtain a chat suggestion message suggesting text input to the user. If the chat room's conversation volume is above the second threshold, the chatbot model may obtain a chat suggestion message suggesting emoticon input to the user.
[0095] The processor (130) can obtain information on the volume of conversations in a chat room as chat room situation information. For example, the processor (130) can calculate the number of messages displayed on the user interface at the time of obtaining the information on the volume of conversations in the chat room as the volume of conversations, or can calculate the number of messages displayed on the user interface over the past minute based on the time of obtaining the information on the volume of conversations in the chat room as the volume of conversations. Meanwhile, the second threshold value can be determined differently depending on the settings of the user or developer, and the following example assumes that the second threshold value is 7 (numbers).
[0096] In the example of FIG. 4, since the number of messages entered less than 1 minute ago is 7, which is equal to the second threshold of 7, the processor (130) may provide a chat suggestion message to the user through the chatbot model to suggest emoticon input. As illustrated in FIG. 4, the chat suggestion message to suggest emoticon input may be a message such as "Enter an emoticon to join the conversation." In response, the user may enter an emoticon as illustrated in FIG. 4 to participate in the chat.
[0097] As illustrated in FIG. 4, the processor (130) may display a plurality of emoticons along with a chat suggestion message for suggesting a response, in which case the processor (130) may display the emoticons based on a user input selecting at least one of the plurality of emoticons.
[0098] In the example of FIG. 5, since the number of messages entered less than 1 minute ago is 1, which is less than the second threshold of 7, the processor (130) may provide a chat suggestion message to the user through the chatbot model to suggest text input. As illustrated in FIG. 5, the chat suggestion message to suggest text input may be the message "Please leave a cheering message!". In response, the user may participate in the chat by entering the text "Let's win first!" as illustrated in FIG. 5.
[0099] According to the embodiment described above with reference to FIGS. 4 and 5, when the volume of conversation in a chat room is small, the electronic device (100) can encourage the user to chat by entering text, and in this case, the chat room can be made more active based on the text entered by the user. On the other hand, when the volume of conversation in a chat room is large, the electronic device (100) can encourage the user to chat by entering emoticons, and thus, the chat room can be made active while preventing the readability of messages from being reduced due to an increase in the volume of conversation caused by the user's participation in the chat.
[0100] Meanwhile, in one or more embodiments, the chatbot model may obtain different chat suggestion messages depending on the conversation participation rate of the participants. Specifically, if the ratio of the number of participants to the conversation volume is below a third threshold, the chatbot model may obtain a chat suggestion message to suggest a conversation topic in the chat room to the user. If the ratio of the number of participants to the conversation volume is above the third threshold, the chatbot model may obtain a chat suggestion message to suggest a response to at least one message in the chat room to the user.
[0101] The processor (130) can obtain information on the participant's conversation participation rate as chat room context information. For example, the processor (130) can calculate the participant's conversation participation rate based on the ratio of the number of messages displayed on the user interface over the past minute, based on the time point at which the information on the participant's conversation participation rate is obtained relative to the number of participants. Meanwhile, the third threshold value may be determined differently depending on the user or developer's settings. The following example assumes a third threshold value of 5.000 (%).
[0102] When calculating the conversation participation rate of the participants using the method described above, in the example of Fig. 2, the conversation participation rate is 3 / 110, i.e., 2.727%, in the example of Fig. 3, the conversation participation rate is 0 / 15, i.e., 0.000%, in the example of Fig. 4, the conversation participation rate is 7 / 110, i.e., 6.364%, and in the example of Fig. 5, the conversation participation rate is 1 / 15, i.e., 6.667%.
[0103] The processor (130) may provide a chat suggestion message to suggest a conversation topic to the user in the examples of FIGS. 2 and 3 where the conversation participation rate of the participant is lower than the third threshold value of 5.000 (%), and may provide a chat suggestion message to suggest a response to at least one message in the chat room to the user in the examples of FIGS. 4 and 5 where the conversation participation rate of the participant is higher than the third threshold value of 5.000 (%).
[0104] In the above, information on the number of participants, the amount of conversation, and the conversation participation rate were given as examples of chat room situation information. However, other information that can provide quantitative criteria for measuring the level of activity in a chat room, such as the rate of increase in the number of participants in a chat room, the amount of data corresponding to messages sent and received, etc., may be included in the chat room situation information according to the present disclosure.
[0105] FIG. 6 is a diagram illustrating embodiments that provide different chat suggestion messages based on information about a situation included in content.
[0106] In one or more embodiments, the chat room situation information may further include information about the situation included in the content, and the processor (130) may obtain different chat suggestion messages depending on the situation included in the content through the chatbot model.
[0107] Specifically, the electronic device (100) can obtain information about a situation included in the content by inputting a captured image of the content into at least one of an image analysis model and a text analysis model.
[0108] For example, the processor (130) can input a captured image as illustrated in FIG. 6 into an image analysis model to obtain information indicating that the content is a soccer game, that Team A is on offense, and that Team B is on defense. In addition, the processor (130) can input a captured image (610) as illustrated in FIG. 6 into a text analysis model to obtain information included in the text information (620) of the captured image (610), that is, that Team A is Korea, Team B is Japan, that the score is 1 to 0, and that the remaining regulation time is 4 minutes and 53 seconds.
[0109] When information about a situation included in the content is obtained as in the example described above, the processor (130) can input the information about the situation included in the content into the chatbot model to obtain and provide a chat suggestion message such as "Time is running out. Please cheer on the defense of the Republic of Korea."
[0110] Meanwhile, the processor (130) may additionally utilize information regarding the user's nationality and the nationalities of chat room participants, among the information regarding the chat room situation. For example, if the user's nationality is South Korea and the percentage of participants with South Korean nationalities exceeds a threshold, the processor (130) may provide a chat suggestion message in Korean, such as "Time is running out. Please support South Korea's defense."
[0111] On the other hand, if the user's nationality is Japanese and the percentage of participants' nationalities is higher than a threshold, the processor (130) may translate a chat suggestion message into Japanese, such as "Time is running out. Please support Japan's attack." In addition to information about the participants' nationalities, various other information, such as information about the participants' ages and genders, may also be utilized.
[0112] While various embodiments have been described above, each type of chatroom context information, with reference to Figures 2 through 6, the embodiments described above can be combined depending on how the type of chatroom context information is set for training the chatbot model. For example, a chatbot model can be trained to acquire chat messages corresponding to information about the number of chatroom participants and context information contained in the content.
[0113] Figure 7 is a drawing for explaining an embodiment that provides a summary of conversation content before a user enters a chat room.
[0114] As described above, when a user input for joining a chat room is received, the processor (130) may display a user interface for the chat room. Furthermore, the processor (130) may display a guidance message, such as "You have entered chat room ABC!", on the user interface, as illustrated in the example of FIG. 7 . Furthermore, although not illustrated in FIG. 7 , the user interface may also display messages indicating that the chatbot is in operation, messages providing guidance on chatting methods, and the like.
[0115] In one or more embodiments, when a user interface is displayed on the display (110), the processor (130) may input information about the chat room conversation content before receiving user input into a summary model, thereby obtaining summary information about the chat room conversation content, and control the display (110) to display the summary information. Here, the summary model refers to a neural network model trained to obtain summary information about the content of messages or documents.
[0116] Specifically, the processor (130) can store messages entered in the chat room in the memory (120). Furthermore, when a user enters the chat room, the messages entered in the chat room during a critical period prior to the user's entry can be input into a summary model. Furthermore, the processor (130) can control the display (110) to display summary information obtained through the summary model on the user interface.
[0117] Referring to the example of FIG. 7, the processor (130) can control the display (110) to display summary information such as, "28 out of 29 participants in the chat are predicting a victory for South Korea. The starting lineup includes players XXX and YYY, who have recovered from injuries." In response, the user can participate in the chat by entering a message such as, "Player YYY is appearing! Let's not get hurt anymore," as shown in FIG. 7. Accordingly, users who join the chat room after the viewing of the content has begun can also participate in the chat as if they were continuously participating in the conversation.
[0118] The embodiment described in FIG. 7 can be combined with the embodiments described with reference to FIGS. 1 to 6. That is, as described in FIG. 7, when a user enters a chat room, a summary of the conversation prior to the user entering the chat room may be provided, and then, as described with reference to FIGS. 1 to 6, a chat suggestion message may be provided by considering chat room context information.
[0119] FIG. 8 is a drawing for explaining an embodiment of changing the display method of a message entered by a chat room participant.
[0120] In one or more embodiments, if a participant in a chat room inputs a threshold number of messages or more within a threshold period of time, the processor (130) may control the display (110) to change the display method of the messages input by the participant and display them. Here, the display method may include at least one of the size, boldness, and color of the message.
[0121] As illustrated in FIG. 8, if a participant A inputs a critical number of 5 or more messages during a critical period of 1 minute, the processor (130) can control the display (110) to display the text and speech bubbles of the messages by reducing their size, starting from the 6th message input by the participant A. In the example of FIG. 8, the text and speech bubble sizes are displayed by reducing them to a predetermined size smaller than the default value, but the text and speech bubble sizes may be gradually reduced and displayed, and the text thickness and color may be changed for display.
[0122] At this time, the changed display method may revert to its original state after a certain amount of time has elapsed. Furthermore, if a participant continues to input messages even after the display method has been changed, their chat privileges may be restricted.
[0123] Meanwhile, in one or more embodiments, if the participant is a designated important participant, the processor (130) may control the display (110) to maintain a message entered by the important participant within the user interface for a designated period of time. Here, the important participant may be designated by the chat room manager, or may be a participant who has made a paid payment or subscription to the chat service.
[0124] For example, in the example of FIG. 8, if B is a key participant, the message "Please be polite while chatting" entered by B may remain within the user interface for a preset period of time even if multiple messages are subsequently entered by multiple participants. Retaining a message within the user interface for a preset period of time may mean that the message is displayed fixedly at a specific location within the user interface for a preset period of time, or may mean that the message is displayed by slowing down the rate at which it moves to the top of the chat interface so that it remains within the user interface for a preset period of time.
[0125] According to the embodiment described above with reference to FIG. 8, when a specific user inputs an excessive number of messages, the electronic device (100) can differentially apply the visibility of messages input by that participant, thereby blocking elements that hinder chat activation by other participants.
[0126] Meanwhile, the embodiment described in FIG. 8 can be combined with the embodiments described with reference to FIGS. 1 to 7. That is, the embodiments described with reference to FIG. 8 can be applied to a case where a specific participant inputs an excessive number of messages during a chat according to the embodiments of FIGS. 1 to 7.
[0127] FIG. 9 is a diagram illustrating a process for implementing one or more embodiments according to the present disclosure by a system including an electronic device (100), a first server, and a second server.
[0128] As described above, the processor (130) can acquire a captured image of the content and input the captured image into at least one of an image analysis model and a text analysis model to acquire information about the situation contained in the content. The description of FIG. 9 describes one or more embodiments according to the present disclosure, assuming that the image analysis model and the text analysis model are included in the first server.
[0129] Meanwhile, as described above, the chatbot model may be implemented as an on-device included in the electronic device (100), or may be implemented in an external device connected to the electronic device (100). The description of FIG. 9 assumes that the chatbot model is included in the second server.
[0130] Meanwhile, the third server for providing the chat service according to the present disclosure may be implemented integrated with the first or second server, or as a separate server. However, for convenience of explanation, the description of the third server is omitted in FIG. 9.
[0131] Referring to FIG. 9, the electronic device (100) can display content (S910) and a user interface for a chat room in which a user has participated (S915). As described above, the device displaying the chat interface and the device displaying the content may be different from each other, but the embodiment of FIG. 9 assumes that both devices are electronic devices (100). When the user interface is displayed, the electronic device (100) can obtain information about the number of participants in the chat room and the volume of conversation in the chat room (S920).
[0132] Meanwhile, the electronic device (100) can obtain a captured image of the content (S925) and transmit the obtained captured image to the first server (S930). When the captured image is received, the first server can input the captured image into an image analysis model and a text analysis model to obtain information about the context of the content (S935) and transmit the obtained information about the context of the content to the electronic device (100) (S940).
[0133] The electronic device (100) can obtain a query based on chat room context information (S945) and transmit the obtained query to a second server (S950). In particular, the chatbot model included in the second server may be a neural network model that provides responses to queries as a large-scale language model included in an external server.
[0134] In one or more embodiments, the electronic device (100) may generate a query by combining various types of chat room situation information, such as information about the type of content, information about the situation of the content, and information about the number of participants, and transmit the generated query to a second server. For example, if the content being viewed in the chat room is a soccer match between Team A and Team B, the match has not yet started, and a keyword that is repeated in messages from chat room participants is player XXX, the electronic device (100) may generate a query saying, “Tell me if player XXX will appear in the soccer match between Team A and Team B today,” and transmit the query to the second server.
[0135] The second server can input the received query into the chatbot model to obtain a response to the query (S955). The electronic device (100) can obtain a chat suggestion message based on the obtained response (S960) and can provide the obtained chat suggestion message (S965). As in the example described above, if a query such as “Tell me if player XXX will be playing in the soccer match between Team A and Team B today” is transmitted to the second server, the electronic device (100) can obtain a response such as “Player XXX is included in the starting lineup for the soccer match between Team A and Team B today” from the second server. In this case, the electronic device (100) can obtain and provide a chat suggestion message such as “As a result of the verification, player XXX is included in the starting lineup for the soccer match between Team A and Team B today. How about letting other users in the chat room know as well?”
[0136] In the above, FIG. 9 has described embodiments in which the image analysis model and the text analysis model are included in the first server and the chatbot model is included in the second server. However, there is no particular limitation on the number and type of devices for implementing various embodiments according to the present disclosure, such as when the image analysis model and the text analysis model are implemented in different servers, or when the image analysis model, the text analysis model, and the chatbot model are all implemented in one server.
[0137] FIG. 10 is a block diagram detailing the configuration of an electronic device (100) according to one or more embodiments of the present disclosure.
[0138] As illustrated in FIG. 10, the electronic device (100) may further include a display (110), a memory (120), and a processor (130), as well as a communication unit (140), an interface unit (150), an input unit (160), and an output unit (170). However, the configurations illustrated in FIGS. 1 and 10 are merely exemplary, and it is to be understood that new configurations may be added or some configurations may be omitted in addition to the configurations illustrated in FIGS. 1 and 10 when implementing the present disclosure.
[0139] The communication unit (140) includes a circuit and can perform communication with an external device. Specifically, the processor (130) can receive various data or information from an external device connected via the communication unit (140) and can also transmit various data or information to the external device.
[0140] The communication unit (140) may include at least one of a WiFi module, a Bluetooth module, a wireless communication module, an NFC module, and a UWB module (Ultra Wide Band). Specifically, the WiFi module and the Bluetooth module may each perform communication in the WiFi or Bluetooth manner. When using a WiFi module or a Bluetooth module, various connection information, such as an SSID, may be first transmitted and received, and then communication may be established using this, after which various pieces of information may be transmitted and received.
[0141] In addition, the wireless communication module can perform communication according to various communication standards such as IEEE, Zigbee, 3G (3rd Generation), 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), 5G (5th Generation), etc. And, the NFC module can perform communication in the NFC (Near Field Communication) method using the 13.56MHz band among various RF-ID frequency bands such as 135kHz, 13.56MHz, 433MHz, 860~960MHz, 2.45GHz, etc. In addition, the UWB module can accurately measure ToA (Time of Arrival), which is the time it takes for a pulse to reach a target, and AoA (Ange of Arrival), which is the pulse arrival angle at the transmitting device, through communication between UWB antennas, and accordingly, precise distance and location recognition is possible within an error range of several tens of centimeters indoors.
[0142] In particular, in various embodiments according to the present disclosure, the processor (130) may receive data related to a chat service from an external server providing a chat service through the communication unit (140). The processor (130) may receive messages entered by multiple participants from the external server providing the chat service through the communication unit (140).
[0143] In addition, when the chatbot model is included in an external server, the processor (130) controls the communication unit (140) to transmit chat room situation information to the external server including the chatbot model, and can receive a chat suggestion message from the external server including the chatbot model. In addition, the processor (130) can receive various information / data, such as the type of content, the title of the content, and information about the situation included in the content, from the external server.
[0144] The interface unit (150) can transmit and receive video data and / or audio data in relation to an external device. Specifically, the interface unit (150) may include an input port capable of receiving video data and / or audio data from an external device and an output port capable of transmitting video data and / or audio data to the external device. In particular, when the interface unit (150) can transmit and receive both video data and audio data, input / output ports capable of transmitting and receiving video data and audio data may be implemented separately. The interface unit (150) may connect the electronic device (100) and the external device wiredly via a cable, but may also connect the electronic device (100) and the external device wirelessly.
[0145] For example, the interface unit (150) may include an HDMI (High-Definition Multimedia Interface) module, a USB (Universal Serial Bus) module, etc. The HDMI module is one of the uncompressed digital video / audio interface standards and may provide an interface between the electronic device (100) and an external device providing content. The USB module may provide a communication system between the electronic device (100) and the external device providing content using a predefined input / output standard protocol. In addition to the HDMI module and the USB module, the interface unit (150)(150) may of course be implemented with various modules for providing input / output of video / audio data between the electronic device (100) and an external device, such as a DP (Display Port) module, an RGB module, a DVI (Digital Visual Interface) module, and a Thunderbolt module.
[0146] In particular, in one or more embodiments, the processor (130) may receive data about content from an external device and control the display (110) to display the content based on the received data. In addition, the interface unit (150) may transmit and receive various information / data, including control signals, between the electronic device (100) and the external device in various embodiments according to the present disclosure.
[0147] The input unit (160) includes a circuit, and the processor (130) can receive a user command for controlling the operation of the electronic device (100) through the input unit (160). Specifically, the input unit (160) can include a microphone, a camera, a keyboard input unit (160), a remote control signal receiving unit, etc. In addition, the input unit (160) can be implemented in a form included in the display (110) as a touch screen. In particular, the microphone can receive a voice signal and convert the received voice signal into an electrical signal.
[0148] The output unit (170) includes a circuit, and the processor (130) can output various functions that the electronic device (100) can perform through the output unit (170). In addition, the output unit (170) can include at least one of a speaker and an indicator. The output unit (170) can include a display (110), but since the display (110) has been described above in the description of FIG. 1, a duplicate description of the same content will be omitted. The speaker can output audio data under the control of the processor (130), and the indicator can be turned on under the control of the processor (130).
[0149] In one or more embodiments, when a user's chat message is input through a keyboard connected to the electronic device (100), the processor (130) may receive the user's chat message by receiving a signal corresponding to the characters input by the user through the keyboard input unit (160).
[0150] In one or more embodiments, when a user's chat message is input through a keypad of a user terminal connected to an electronic device (100), the processor (130) may receive the user's chat message by receiving a signal corresponding to the characters input by the user through the communication unit (140).
[0151] In one or more embodiments, when a chat message is input through a button on a remote control connected to an electronic device (100), the processor (130) may receive a signal corresponding to the chat message through a module (e.g., a Bluetooth module) different from a communication module (e.g., a WiFi module) for performing communication with an external server.
[0152] In one or more embodiments, when a user speaks a user voice corresponding to a chat message, the user voice corresponding to the chat message may be received through a microphone of the electronic device (100), a microphone of a remote control connected to the electronic device (100), and / or a microphone of a user terminal connected to the electronic device (100) and then transmitted to the electronic device (100). In this case, an analog voice signal received through the microphone of the electronic device (100), the microphone of the remote control connected to the electronic device (100), and / or the microphone of the user terminal connected to the electronic device (100) may be converted into a digital signal and then transmitted to the electronic device (100). The processor (130) may obtain a chat message by receiving the user voice converted into a digital signal through the communication unit (140).
[0153] In one or more embodiments, when a chat message is received in the form of a voice signal, the processor (130) may obtain the chat message by obtaining text information corresponding to the voice signal using an automatic speech recognition model (ASR model) included in the electronic device (100) or a voice recognition model included in an external server.
[0154] In one or more embodiments, the processor (130) may obtain a voice signal corresponding to a participant's chat message using a text-to-speech model (TTS model) and output the voice corresponding to the chat message through a speaker. In addition, the processor (130) may obtain a voice signal corresponding to a chat suggestion message using a voice synthesis model and output the voice corresponding to the chat suggestion message through a speaker.
[0155] FIG. 11 is a flowchart illustrating a method for controlling an electronic device (100) according to one or more embodiments of the present disclosure.
[0156] As illustrated in FIG. 11, the electronic device (100) may display a user interface for a chat room in which a user of the electronic device (100) has participated (S1110). The electronic device (100) may also display content along with the chat interface, but the device displaying the chat interface and the device displaying the content may be different from each other.
[0157] When the user interface is displayed, the electronic device (100) can obtain chat room context information, including information about the number of chat room participants and the volume of conversation in the chat room (S1120). At least some of the chat room context information may be obtained using an external server.
[0158] In particular, the chat room context information may include at least one of information regarding the number of chat room participants and information regarding the volume of conversation in the chat room. Furthermore, the chat room context information may further include information regarding the context contained in the content. The chat room context information may include information regarding the current context of the content being viewed by chat room participants. Furthermore, the chat room context information may further include at least one of the following: the type of content, the title of the content, at least one message entered in the chat room, the user's chat history, the user's content viewing history, the user's age, the user's gender, and the user's nationality.
[0159] When chat room situation information is obtained, the electronic device (100) inputs the chat room situation information into a chatbot model, thereby obtaining different chat suggestion messages according to the number of participants and the amount of conversation (S1130).
[0160] In one or more embodiments, the chatbot model may obtain different chat suggestion messages depending on the number of participants in the chat room. For example, if the number of participants in the chat room is less than a first threshold, the chatbot model may obtain a chat suggestion message to suggest a topic of conversation in the chat room to the user. Conversely, if the number of participants in the chat room is greater than or equal to the first threshold, the chatbot model may obtain a chat suggestion message to suggest a response to at least one message in the chat room to the user.
[0161] In one or more embodiments, the chatbot model may obtain different chat suggestion messages depending on the chat room's conversation volume. For example, if the chat room's conversation volume is below a second threshold, the chatbot model may obtain a chat suggestion message suggesting text input to the user. If the chat room's conversation volume is above the second threshold, the chatbot model may obtain a chat suggestion message suggesting emoticon input to the user.
[0162] In one or more embodiments, the chatbot model may obtain different chat suggestion messages based on the conversation participation rate of the participants. If the ratio of the number of participants to the conversation volume is below a third threshold, the chatbot model may obtain a chat suggestion message to suggest a topic of conversation in the chat room to the user. Conversely, if the ratio of the number of participants to the conversation volume is above the third threshold, the chatbot model may obtain a chat suggestion message to suggest a response to at least one message in the chat room to the user.
[0163] When a chat suggestion message is obtained, the electronic device (100) can display the chat suggestion message on the user interface (S1140). In particular, the electronic device (100) can control the display (110) to display the chat suggestion message on the user interface in a manner that distinguishes it from messages entered by chat room participants.
[0164] Meanwhile, the control method of the electronic device (100) according to the above-described embodiment may be implemented as a program and provided to the electronic device (100). In particular, the program including the control method of the electronic device (100) may be stored and provided in a non-transitory computer readable medium.
[0165] Specifically, in a non-transitory computer-readable recording medium including a program for executing a method for controlling an electronic device (100), the method for controlling an electronic device (100) may include a step of displaying a user interface for a chat room in which a user of the electronic device (100) has participated, a step of obtaining chat room situation information including at least one of information on the number of participants in the chat room and information on the volume of conversation in the chat room, a step of inputting the chat room situation information into a chatbot model and obtaining a different chat suggestion message according to at least one of the number of participants and the volume of conversation, and a step of displaying the chat suggestion message on the user interface.
[0166] In the above, a method for controlling an electronic device (100) and a computer-readable recording medium including a program for executing the method for controlling an electronic device (100) have been briefly described, but this is only to omit redundant descriptions, and it goes without saying that various embodiments of the electronic device (100) can also be applied to a method for controlling an electronic device (100) and a computer-readable recording medium including a program for executing the method for controlling an electronic device (100).
[0167] According to various embodiments of the present disclosure as described above, the electronic device (100) can actively provide a chat suggestion message that changes in real time and adapts to the situation by considering the situation of the chat room, and thus the user's chat participation rate can be significantly improved.
[0168] The artificial intelligence-related function according to the present disclosure is operated through the processor (130) and memory (120) of the electronic device (100).
[0169] The processor (130) may be composed of one or more processors (130). At this time, the one or more processors (130) may include at least one of a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), and an NPU (Neural Processing Unit), but is not limited to the examples of the processors (130) described above.
[0170] The CPU is a general-purpose processor (130) capable of performing not only general calculations but also artificial intelligence calculations. Its multi-layer cache structure allows for the efficient execution of complex programs. The CPU is advantageous in a serial processing method, enabling organic linking of previous and subsequent calculation results through sequential calculations. The general-purpose processor (130) is not limited to the aforementioned examples, except in cases where it is specifically designated as a CPU.
[0171] A GPU is a processor (130) for large-scale operations such as floating-point operations used in graphic processing, and can perform large-scale operations in parallel by integrating a large number of cores. In particular, a GPU may be advantageous compared to a CPU in parallel processing methods such as convolution operations. In addition, a GPU may be used as a co-processor (130) to supplement the functions of a CPU. The processor (130) for large-scale operations is not limited to the examples described above, except in cases where it is specified as a GPU as described above.
[0172] An NPU is a processor (130) specialized in artificial intelligence operations using an artificial neural network, and each layer constituting the artificial neural network can be implemented with hardware (e.g., silicon). At this time, since the NPU is designed specifically according to the required specifications of the company, it has a lower degree of freedom compared to a CPU or GPU, but it can efficiently process the artificial intelligence operations requested by the company. Meanwhile, as a processor (130) specialized in artificial intelligence operations, the NPU can be implemented in various forms such as a TPU (Tensor Processing Unit), an IPU (Intelligence Processing Unit), a VPU (Vision processing unit), etc. The artificial intelligence processor (130) is not limited to the above-described examples, except in cases where it is specified as the above-described NPU.
[0173] Additionally, one or more processors (130) may be implemented as a SoC (System on Chip). In this case, the SoC may further include, in addition to one or more processors (130), a memory (120), and a network interface such as a bus for data communication between the processor (130) and the memory (120).
[0174] When a plurality of processors (130) are included in a SoC (System on Chip) included in an electronic device (100), the electronic device (100) may perform operations related to artificial intelligence (e.g., operations related to learning or inference of an artificial intelligence model) by using some of the plurality of processors (130). For example, the electronic device (100) may perform operations related to artificial intelligence by using at least one of a GPU, an NPU, a VPU, a TPU, and a hardware accelerator specialized in artificial intelligence operations such as convolution operations and matrix multiplication operations among the plurality of processors (130). However, this is merely an example, and it is of course possible to process operations related to artificial intelligence by using a CPU or a general-purpose processor (130).
[0175] In addition, the electronic device (100) can perform operations related to functions related to artificial intelligence by utilizing multiple cores (e.g., dual cores, quad cores, etc.) included in one processor (130). In particular, the electronic device (100) can perform artificial intelligence operations such as convolution operations, matrix multiplication operations, etc. in parallel by utilizing multiple cores included in the processor (130).
[0176] One or more processors (130) are controlled to process input data according to predefined operation rules or artificial intelligence models stored in the memory (120). The predefined operation rules or artificial intelligence models are characterized by being created through learning.
[0177] Here, "created through learning" means that a predefined set of behavioral rules or an AI model with desired characteristics is created by applying a learning algorithm to a large number of learning data. This learning may be performed on the device itself, where the AI according to the present disclosure is implemented, or through a separate server / system.
[0178] An artificial intelligence model may be composed of multiple neural network layers. At least one layer has at least one weight value and performs its operation through the operation result of the previous layer and at least one defined operation. Examples of neural networks include a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), deep Q-networks, and a transformer. The neural networks in the present disclosure are not limited to the above-described examples unless otherwise specified.
[0179] A learning algorithm is a method for training a target device (e.g., a robot) using a large amount of learning data, enabling the target device to make decisions or predictions on its own. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Unless otherwise specified, the learning algorithms in this disclosure are not limited to the aforementioned examples.
[0180] A device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, the term "non-transitory storage medium" simply means a tangible device that does not contain signals (e.g., electromagnetic waves). This term does not distinguish between cases where data is permanently stored in the storage medium and cases where data is temporarily stored. For example, a "non-transitory storage medium" may include a buffer in which data is temporarily stored.
[0181] According to one embodiment, the method according to various embodiments disclosed in the present document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smartphones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product (e.g., downloadable app) may be at least temporarily stored or temporarily created in a device-readable storage medium, such as a manufacturer's server, an application store's server, or a memory (120) of an intermediary server.
[0182] Each of the components (e.g., modules or programs) according to the various embodiments of the present disclosure as described above may be composed of a single or multiple entities, and some of the sub-components described above may be omitted, or other sub-components may be further included in the various embodiments. Alternatively or additionally, some components (e.g., modules or programs) may be integrated into a single entity, which may perform the same or similar functions as those performed by each of the respective components prior to integration.
[0183] According to various embodiments, operations performed by a module, program or other component may be executed sequentially, in parallel, iteratively or heuristically, or at least some operations may be executed in a different order, omitted, or other operations may be added.
[0184] Meanwhile, the terms "part" or "module" used in the present disclosure include units composed of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A "part" or "module" may be an integrally composed component, a minimum unit performing one or more functions, or a portion thereof. For example, a module may be composed of an application-specific integrated circuit (ASIC).
[0185] Various embodiments of the present disclosure may be implemented as software including instructions stored in a machine-readable storage medium that can be read by a machine (e.g., a computer). The device may include an electronic device (e.g., an electronic device (100)) according to the disclosed embodiments, which is a device capable of calling instructions stored in the storage medium and operating according to the called instructions.
[0186] When the above instruction is executed by the processor, the processor may perform the function corresponding to the instruction directly or by using other components under the control of the processor. The instruction may include code generated or executed by a compiler or interpreter.
[0187] Although the preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications may be made by a person having ordinary skill in the art to which the present disclosure pertains without departing from the gist of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present disclosure.
Claims
1. In electronic devices, display; a memory storing at least one instruction; and a processor executing at least one instruction; The above processor, Controlling the display to display a user interface for a chat room in which a user of the electronic device has participated; Obtain chat room situation information including at least one of information on the number of participants in the chat room and information on the volume of conversation in the chat room; By inputting the above chat room situation information into the chatbot model, different chat suggestion messages are obtained according to at least one of the number of participants and the conversation volume. An electronic device controlling said display to display said chat suggestion message on said user interface.
2. In paragraph 1, The above chatbot model is, If the number of participants is less than the first threshold, a chat suggestion message is obtained to suggest a conversation topic for the chat room, An electronic device that obtains a chat suggestion message for suggesting a response to at least one message in the chat room if the number of said participants is greater than or equal to the first threshold value.
3. In paragraph 1, The above chatbot model is, If the above conversation volume is less than the second threshold, obtain a chat suggestion message to suggest text input, An electronic device that obtains a chat suggestion message for suggesting emoticon input when the above conversation volume is greater than or equal to the second threshold value.
4. In paragraph 1, The above user interface is displayed based on user input for participating in the chat room while content is displayed on the display, The above chat room situation information further includes information about the situation included in the above content, The above processor, An electronic device that obtains different chat suggestion messages depending on the context contained in the above content.
5. In paragraph 4, The above processor, Obtain a capture image of the above content, An electronic device that inputs the above captured image into an image analysis model to obtain information about the above situation.
6. In paragraph 4, The above processor, An electronic device that inputs the above captured image into a text analysis model to obtain information about the above situation.
7. In paragraph 1, The above processor, When the above user interface is displayed, information about the chat room conversation before the user input is received is input into the summary model to obtain summary information about the chat room conversation. An electronic device controlling said display to display said summary information.
8. In paragraph 1, The above processor, If a participant of the above chat room inputs a threshold number of messages or more within a threshold period, the display is controlled to change the display method of messages input by the participant after the threshold period and display them; An electronic device wherein the display method includes at least one of the size, boldness and color of the message.
9. In paragraph 8, The above processor, An electronic device that controls the display to display a message entered by the important participant within the user interface for a preset period of time, if the participant is a key participant.
10. In paragraph 1, including the Department of Communications; The above chatbot model is a very large language model contained in an external server. The above processor, Obtain a query based on the above chat room situation information, Controlling the communication unit to transmit the above query to the external server; Receive a response to the query obtained by the chatbot model from the external server through the communication unit, An electronic device that obtains the chat suggestion message based on the above response.
11. In a method for controlling an electronic device, A step of displaying a user interface for a chat room in which a user of the electronic device has participated; A step of obtaining chat room situation information including at least one of information on the number of participants in the chat room and information on the volume of conversation in the chat room; A step of inputting the chat room situation information into the chatbot model to obtain different chat suggestion messages according to at least one of the number of participants and the conversation volume; and A method for controlling an electronic device, comprising: displaying the chat suggestion message on the user interface; 12. In paragraph 11, The above chatbot model is, If the number of participants is less than the first threshold, a chat suggestion message is obtained to suggest a conversation topic for the chat room, A control method of an electronic device for obtaining a chat suggestion message for suggesting a response to at least one message in the chat room when the number of said participants is greater than or equal to the first threshold value.
13. In paragraph 11, The above chatbot model is, If the above conversation volume is less than the second threshold, obtain a chat suggestion message to suggest text input, A control method of an electronic device for obtaining a chat suggestion message for suggesting emoticon input when the above conversation volume is greater than or equal to the second threshold value.
14. In paragraph 11, The above user interface is displayed based on user input for participating in the chat room while content is displayed on the display, The above chat room situation information further includes information about the situation included in the above content, The step of obtaining the above chat suggestion message is a control method of an electronic device for obtaining different chat suggestion messages depending on a situation included in the above content.
15. In paragraph 14, The steps to obtain chat room situation information are: A step of obtaining a capture image of the above content; and A method for controlling an electronic device, comprising: a step of inputting the captured image into an image analysis model to obtain information about the situation;
Citation Information
Patent Citations
Automated generation of suggestions for personalized reactions in a social network
KR101627025B1
System and method for providing user customized content
KR1020170068379A
Polyethylene terephthalate tire cord and tire using same
KR1020240109759A
Ai based job matching method and apparatus
KR1020240162890A
Interactive chatbot operation method and system based on natural language processing for activation of messenger group chat room
KR102050244B1
