Apparatus and method for providing chat service

Abstract

The display device according to the embodiments disclosed herein can display content, recognize a chatting message input by a user while the content is being displayed, change the recognized chatting message to a shortened message having the same or similar meaning as the recognized chatting message based on context information associated with the displayed content, and transmit the shortened message to a server capable of providing a chatting bot response.

Description

Technical Field

[0001] This disclosure relates to devices and methods for providing chat services. Background Technology

[0002] Display devices such as smart TVs can offer chat services. For example, a display device can provide a chat service that allows users to chat in real time while content is being displayed. Based on the chat service, users of the display device can be able to share emotions or information with other users watching the same content.

[0003] Chatbots can participate in chat rooms created by chat services. They can interact with users within the chat room based on artificial intelligence (AI) technology. For example, a chatbot can provide response messages based on user messages or conversations between users in the chat room. Summary of the Invention

[0004] Technical solution

[0005] Chatbots are typically used based on cloud technology. The response messages provided by the chatbot in the chat room can be generated by servers in the cloud, and costs can arise depending on the server usage of the display device. For example, the cost can be determined based on the amount of input (e.g., the number of user messages or conversations) sent by the display device to the server to obtain response messages. Therefore, there is a need for a method to operate chatbots efficiently without the burden of server usage costs.

[0006] If few users are using the chat service on the display device, chat between users may not be activated, and service usage may be low. With this in mind, there is a need to provide a chat service regardless of the number of users.

[0007] Embodiments of this disclosure may provide devices and methods for providing chat services.

[0008] Embodiments of this disclosure may provide an apparatus and method capable of reducing server usage costs associated with chatbots.

[0009] The embodiments of this disclosure can provide a device and method for efficiently operating a chatbot.

[0010] Embodiments of this disclosure may provide devices and methods capable of activating chat services.

[0011] A display device according to embodiments of the present disclosure may include a display, a transceiver, a memory for storing at least one program, and at least one processor electrically connected to the memory and including processing circuitry to execute at least one instruction of the at least one program when connected to the memory. The at least one processor may individually or in combination control the display to display content, identify chat messages input by a user while displaying content, transform the identified chat messages into abbreviated messages having the same or similar meaning as the identified chat messages based on contextual information associated with the content being displayed, and control the transceiver to send the abbreviated messages to a server capable of providing chatbot responses.

[0012] According to an embodiment, the abbreviated message may include a number of words that are less than the number of words in the identified chat message.

[0013] According to an embodiment, at least one processor may, individually or in combination, change the first text included in the identified chat message to a second text that includes fewer lexical units than the first text, based on a language model, and use the message including the second text as a shortened message.

[0014] According to an embodiment, at least one processor may individually or in combination detect the language of the identified chat message based on a language model, count a first number of lexical units as the number of lexical units in the identified chat message, translate the identified chat message into a language different from the detected language, count a second number of lexical units as the number of lexical units in the translated chat message, and, in response to the second number of lexical units being less than the first number of lexical units, use the translated chat message as an abbreviated message.

[0015] According to an embodiment, at least one processor can detect the language of the identified chat message based on a language model, either individually or in combination, count a first number of lexical units that constitute the number of lexical units in the identified chat message, determine a second number of lexical units that is less than the first number of lexical units, translate the identified chat message into a language different from the detected language based on the determined second number of lexical units, and use the translated chat message as a shortened message.

[0016] According to an embodiment, at least one processor can individually or in combination identify emoticons included in the identified chat message, obtain the name of the emoticon based on a language model, identify the meaning of the emoticon based on the obtained name and generate a first text indicating the identified meaning, generate a second text with fewer lexical units than the first text by abbreviating the first text based on context information, and use the message including the second text as the abbreviated message.

[0017] According to an embodiment, context information can be generated based on metadata. Meta information may include at least one of the following obtained from the Electronic Program Guide (EPG): broadcast time information, broadcast channel information, broadcast program title, broadcast program description, broadcast program type, broadcast program cast information, broadcast program staff information, or broadcast program video information.

[0018] According to an embodiment, contextual information can be generated based on metadata. Meta-information may include at least one of the following: information about people or objects appearing in the content or background information about the content obtained through screen analysis of the display device; speech or sound information obtained through audio analysis of the display device; text information obtained from the screen of the content through text detection operations; information about one or more chat participants, including the user; or conversation history information about one or more chat participants.

[0019] According to an embodiment, at least one processor can individually or in combination transform metadata into abbreviations having a similar meaning to the metadata, and control a transceiver to send the abbreviations to a server. The abbreviations may include a number of lexical units smaller than the number of lexical units in the metadata.

[0020] According to an embodiment, at least one processor can receive response messages to abbreviated messages from a server via a transceiver, either individually or in combination, and control a display to show the received response messages as chatbot responses.

[0021] According to embodiments of this disclosure, a method for providing a chat service by a display device may include: displaying content; identifying a chat message input by a user while displaying the content; changing the identified chat message into a shortened message having the same or similar meaning as the identified chat message based on contextual information associated with the content being displayed; and sending the shortened message to a server capable of providing chatbot responses.

[0022] According to an embodiment, the abbreviated message may include a number of words that are less than the number of words in the identified chat message.

[0023] According to an embodiment, changing to a shortened message may include: based on a language model, changing the first text included in the identified chat message to a second text that includes a smaller number of lexical units than the first text, and using the message including the second text as a shortened message.

[0024] According to an embodiment, changing the message to a shortened version may include: detecting the language of the chat message based on a language model; counting the number of first lexical units, which is the number of lexical units in the identified chat message; translating the identified chat message into a language different from the detected language; counting the number of second lexical units, which is the number of lexical units in the translated chat message; and using the translated chat message as a shortened message in response to the second lexical unit count being less than the first lexical unit count.

[0025] According to an embodiment, changing to a shortened message may include: detecting the language of the chat message based on a language model, counting the number of first lexical units in the identified chat message, determining the number of second lexical units less than the number of first lexical units, translating the identified chat message into a language different from the detected language based on the determined number of second lexical units, and using the translated chat message as a shortened message.

[0026] According to an embodiment, changing to a shortened message may include: identifying an emoji included in the identified chat message; obtaining the name of the emoji based on a language model; identifying the meaning of the emoji based on the obtained name and generating first text indicating the identified meaning; generating a second text with fewer lexical units than the first text by shortening the first text based on context information; and using the message including the second text as the shortened message.

[0027] According to an embodiment, context information can be generated based on metadata. Meta information may include at least one of the following obtained from the Electronic Program Guide (EPG): broadcast time information, broadcast channel information, broadcast program title, broadcast program description, broadcast program type, broadcast program cast information, broadcast program staff information, or broadcast program video information.

[0028] According to an embodiment, contextual information can be generated based on metadata. Meta-information may include at least one of the following: information about people or objects appearing in the content or background information about the content obtained through screen analysis of the display device; speech or sound information obtained through audio analysis of the display device; text information obtained from the screen of the content through text detection operations; information about one or more chat participants, including the user; or conversation history information about one or more chat participants.

[0029] According to an embodiment, the method may further include changing the meta-information into abbreviations having a similar meaning to the meta-information, and sending the abbreviations to a server. The abbreviations may include fewer lexical units than the number of lexical units in the meta-information.

[0030] According to an embodiment, the method may further include receiving a response message to the abbreviated message from a server and displaying the received response message as a chatbot response. Attached Figure Description

[0031] Figure 1 This is a view showing the output screen of a chat service provided by a display device according to an embodiment; Figure 2 This is a diagram illustrating a system for providing chat services according to an embodiment; Figure 3 This is a schematic view illustrating the configuration and operation of a display device and a chat server according to an embodiment; Figure 4 This is a flowchart illustrating the operation of a display device according to an embodiment; Figure 5 This is a flowchart illustrating the operation of a display device abbreviating chat messages based on a text replacement scheme according to an embodiment; Figure 6a This is a flowchart illustrating the operation of a display device translating and abbreviating chat messages according to an embodiment; Figure 6b This is a flowchart illustrating another operation of a display device translating and abbreviating chat messages according to an embodiment; Figure 7 This is a flowchart illustrating an operation in which a display device abbreviates chat messages using semantic compression of emojis, according to an embodiment; Figure 8 This is a view illustrating an example in which the meaning of emojis is compressed by the display device according to an embodiment; Figure 9 This is a flowchart illustrating the operation of a display device generating context information based on an EPG according to an embodiment; Figure 10 This is a flowchart illustrating the operation of a display device generating context information based on screen analysis or text detection operations according to an embodiment; Figure 11 This is a flowchart illustrating the operation of a server according to an embodiment; Figure 12 This is a block diagram illustrating the configuration of a display device according to an embodiment; and Figure 13 This is a block diagram illustrating the configuration of a server according to an embodiment.

[0032] In the following description, with reference to the accompanying drawings, certain examples for implementing the disclosed content are shown as examples in the drawings. Furthermore, other examples may be used and structural changes or modifications may be made without departing from the scope of the various examples. Detailed Implementation

[0033] Various embodiments of this disclosure will be described in detail below with reference to the accompanying drawings so that those skilled in the art to which this disclosure pertains can easily practice the disclosed content. However, this disclosure can be implemented in various different forms and is not limited to the embodiments described herein. In the description of the drawings, the same or similar components may be represented by the same or similar drawing terms. Furthermore, in the drawings and their related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and brevity.

[0034] Figure 1 This is a view showing the output screen of a chat service provided by a display device according to an embodiment.

[0035] refer to Figure 1 The display device can provide a chat service that enables real-time chatting while viewing content 102, such as streaming or broadcast images. The chat service can refer to a service that allows users to open or enter an existing chat room to communicate with other users to share emotions or information related to the content 102 they are viewing. According to embodiments, the chat service can be referred to by various terms such as "live chat service," "real-time chat service," "chat together service," or "watch together service."

[0036] According to an embodiment, the display device can output a chat window (or chat screen) 104 for chatting on the display while simultaneously displaying content 102 selected by the user. The chat window 104 can be displayed at a preset location. The preset location may include a location set by the user or the display device, and can be inside or outside the screen displaying the content 102. For example, when the chat window 104 is displayed within the screen displaying the content 102, it can be displayed in a location that does not interfere with the user's viewing of the content (e.g., the edge of the screen). Similarly, when the chat window 104 is displayed outside the screen displaying the content 102, it can be displayed at a location corresponding to any one of the top, bottom, left, or right sides of the screen.

[0037] According to an embodiment, the display device can display or output chat messages or session messages between users viewing content 102 on the chat window 104. According to an embodiment, the chat window 104 can be a chat window of a chat room opened by a user of the display device or a chat window of an existing chat room. Users can communicate with other users in real time through the chat window 104.

[0038] Based on the example, the chat service could be a chatbot-based chat service. The chatbot can provide response messages to user messages (e.g., user chat messages, or user statements or conversations) based on artificial intelligence (AI) technology. The chatbot can be based on a cloud server. For example, when a user enters a message, the input message can be sent to a chatbot server in the cloud. The chatbot server can analyze the input message and generate a response message based on the analysis results. The generated response message can be transmitted to a display device and displayed as a chatbot message on chat window 104.

[0039] According to embodiments, the chat service may include a text-based chat service and may support various types of input for chatting. For example, various types of input may include input using a remote control, input using a mobile device, input using a voice input device, input via a text input device, or input via touch on a touchscreen.

[0040] According to an embodiment, when the display device is a TV, input via a remote control can be supported. Users can input chat messages by operating one or more buttons on the remote control or by using the remote control to operate a virtual keyboard displayed on the TV screen. Infrared communication can be performed between the TV and the remote control, but various types of communication are possible and not limited to this.

[0041] According to an embodiment, when a mobile device is present to interact with the display device, input via the mobile device can be supported. For example, the mobile device can be an electronic device capable of wireless communication, such as a mobile phone, a tablet PC, or a wearable device. The display device and the mobile device can be connected based on various wireless communication technologies such as Wi-Fi or Bluetooth. When the display device and the mobile device are fully connected, they can perform operations such as information exchange, data sharing, screen mirroring, or remote control. According to an embodiment, when the mobile device remotely controls the display device, the user can input chat messages to the display device by manipulating a graphical user interface (GUI) displayed on the mobile device's screen or at least one button included in the mobile device. According to an embodiment, the user can input chat messages by manipulating a virtual keyboard displayed on the display device using the mobile device.

[0042] According to embodiments, input using a voice input device can be supported in the display device. For example, the voice input device can be any one of a voice input device embedded in the display device (e.g., a microphone of the display device) or a voice input device that interacts with the display device (e.g., a microphone embedded in a mobile device or a separate microphone device). Users can use the voice input device to input voice messages. The display device can convert the user-inputted voice message into a text message and display the text message, and can output the displayed text message as a chat message to chat window 104 according to the user's selection. According to embodiments, the display device can use a speech-to-text (STT) engine to convert the user-inputted voice message into a text message. The STT engine can be a system, application, or software that converts speech to text and can be included in the display device.

[0043] According to embodiments, input using a text input device can be supported in the display device. For example, the text input device can be a wired or wireless input device (e.g., a keyboard) connected to the display device. The text input device can be wired to the display device via a High Definition Multimedia Interface (HDMI) cable or a Universal Serial Bus (USB) cable, or wirelessly connected to the display device via wireless communication such as Wi-Fi or Bluetooth. Users can use the text input device connected to the display device to input chat messages.

[0044] According to embodiments, touch input via a touchscreen can be supported in a display device. For example, when the display of the display device is a touchscreen, chat messages can be entered based on the user's touch input. The user's touch input can be performed at a location associated with a GUI (e.g., a virtual keyboard) displayed on the touchscreen of the display device.

[0045] According to an embodiment, to facilitate the input of chat messages, the display device can display recommended message information 106. For example, recommended message information 106 may include one or more recommended chat messages based on the chat content (or chat context) of the chat window 104. When a user selects at least one of the one or more recommended chat messages, the display device can output the at least one chat message selected by the user to the chat window 104. According to an embodiment, a user can select at least one chat message based on at least one of the various types of input described above (e.g., input using a remote control, a mobile device, a voice input device, input using a text input device, or the user's touch input).

[0046] According to an embodiment, the display device can display recommended emoji information 108 to facilitate the input of chat messages. For example, the recommended emoji information 108 may include one or more recommended emojis based on the chat content (or chat context) of the chat window 104. When a user selects at least one of the one or more recommended emojis, the display device can output the at least one emoji selected by the user to the chat window 104. According to an embodiment, a user can select at least one emoji based on at least one of various types of input (e.g., input using a remote control, a mobile device, a voice input device, input using a text input device, or the user's touch input).

[0047] According to an embodiment, the display device may display a menu bar 110 for selectively using various types of input. For example, the menu bar 110 may include a menu associated with at least one of input using a remote control, input using a mobile device, input using a voice input device, or touch-based input (e.g., emoji or text input using a virtual keyboard). The menu bar 110 may initially be controlled by input using a remote control and may be changed to any of the at least one menu included in the menu bar 110 based on the user's selection.

[0048] Figure 2 This is a diagram illustrating a system for providing chat services according to an embodiment; refer to Figure 2 The system 200 that provides chat services may include a display device 202 and at least one server (e.g., a broadcast server 204 and / or a chat server 206).

[0049] According to an embodiment, display device 202 may be a device that displays live broadcast images based on a broadcast channel or streaming images provided from a content server or another device. Display device 202 may be a device capable of performing various computing and display functions, such as input functions (e.g., voice input), output functions (e.g., voice or audio output), or communication functions. For example, display device 202 may be a TV, smart TV, mobile device (e.g., tablet PC, wearable device, smartphone, or mobile phone), PC, desktop computer, laptop computer, personal digital assistant (PDA), laptop computer, media player, e-book terminal, digital broadcasting terminal, navigation device, kiosk, digital camera, or home appliance. Display device 202 is not limited to the above-described devices and may be another type of electronic device.

[0050] According to embodiments, display device 202 can perform communication using any of a variety of wired or wireless communication protocols, such as Ethernet, Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Long Term Evolution (LTE), Advanced LTE (LTE-A), New Radio (NR), Wi-Fi, or Bluetooth. For example, display device 202 can communicate with broadcast server 204 and / or chat server 206 based on wired or wireless communication protocols.

[0051] According to an embodiment, the display device 202 may be an on-device AI device or an edge AI device capable of performing AI functions. According to an embodiment, the display device 202 may use AI functions to perform operations that optimize user-inputted chat messages (e.g., shorten or compress chat messages) to reduce costs associated with the chat server 206, and analyze the displayed screen to generate metadata.

[0052] According to an embodiment, display device 202 can be wired or wirelessly connected to one or more electronic devices 210 that can be used for various types of input. For example, display device 202 can be wired or wirelessly connected to at least one of remote control 212, mobile device 214, voice input device 216, or text input device 218. A user of display device 202 can use at least one of remote control 212, mobile device 214, voice input device 216, or text input device 218 to perform input operations (e.g., entering chat messages). According to an embodiment, the display of display device 202 can be a touchscreen, and a user of display device 202 can control display device 202 or perform input operations by touch.

[0053] According to an embodiment, broadcast server 204 may provide various broadcast information to display device 202. For example, broadcast server 204 may provide electronic program guide (EPG) 220 to display device 202. EPG 220 is information associated with one or more broadcast programs and may include at least one of the following: broadcast time information (e.g., broadcast start time and / or broadcast end time), broadcast channel information (e.g., channel name, channel logo, or channel number), broadcast program title, broadcast program description, broadcast program type (e.g., drama, sports, documentary, or entertainment), broadcast program cast information, broadcast program staff information, or broadcast program screen information.

[0054] According to an embodiment, the display device 202 may receive the EPG 220 periodically or non-periodically. According to an embodiment, the display device 202 may receive the EPG 220 at a set time or a random time. According to an embodiment, when the content being displayed (or the content the user is watching) is a broadcast program, the display device 202 may use the EPG to generate context information associated with the broadcast program.

[0055] According to embodiments, chat server 206 may be a server in the cloud and may be a server capable of communicating with display device 202 to provide chat service 222 to users. Chat server 206 may be a standalone server or may include two or more servers. According to embodiments, chat server 206 may include a language model and may provide a paid service, wherein costs are charged based on the usage of the language model. For example, chat server 206 may be a server that provides chatbot responses to input messages based on a language model. The service cost associated with chat server 206 may be determined based on the size, length, or message volume of messages (e.g., user chat messages) input from display device 202 to chat server 206.

[0056] According to an embodiment, the display device 202 can perform a compression operation on messages input to the chat server 206 to reduce the usage cost of the chat server 206. For example, the display device 202 can perform a compression operation by replacing words or sentences included in the user's chat messages with shorter words or sentences that have the same or similar meaning, or by reducing the size, length, or quantity of the user's chat messages through translation. If a compression operation is performed, the user's chat messages can be shortened, and the shortened messages can be sent to the chat server 206, thereby saving the usage cost of the chat server 206.

[0057] In the following description, for ease of description, an example is given of display device 202 using lexical units, which are the smallest semantic units of a language model, as units for checking the size, length, or quantity of a message. However, the unit used by display device 202 to check the size, length, or quantity of a message is not limited to lexical units, and other units (e.g., bits or bytes) may be used.

[0058] Figure 3 This is a schematic view illustrating the configuration and operation of a display device and a chat server according to an embodiment; refer to Figure 3The display device 202 can be connected, either wired or wirelessly, to one or more electronic devices that can be used for various types of input (e.g., at least one of a remote control 212, a mobile device 214, a voice input device 216, or a text input device 218). According to an embodiment, the display device 202 may include an STT engine 219 that converts voice messages input by a user via the voice input device 216 into text messages.

[0059] According to an embodiment, the display device 202 may include a context database (DB) 230 for storing context information. According to an embodiment, the display device 202 may generate context information based on metadata. For example, the metadata may include information based on EPG 220 (e.g., at least one of broadcast time information, broadcast channel information, broadcast program title, broadcast program description, broadcast program type, broadcast program cast information, broadcast program staff information, or broadcast program screen information); information obtained through screen analysis of the display device 202 (e.g., at least one of information about people or objects appearing in the content or background information about the content); information obtained through audio analysis of the display device 202 (e.g., voice information or sounds, such as the tone of voice of a person in the content); text information obtained from the screen of the content through text detection operations; chat participant information (e.g., the number of participants, participant nationality, participant gender, participant age, or participant account information); or chat history information about chat participants.

[0060] According to an embodiment, the information obtained through screen analysis of display device 202 can be obtained through non-periodic screen analysis of display device 202 using computer vision, and can be used to identify the type or atmosphere of the content or information about the content. For example, when the content is a broadcast image of a sports game, information about the type of sports game (e.g., football, baseball, or basketball), the names of the teams participating in the sports game, score information, or win / loss information can be obtained through screen analysis results.

[0061] According to an embodiment, the display device 202 may include a chat service unit 240 and a chat compressor 242. According to an embodiment, the chat service unit 240 may include an application for providing chat services. For example, the chat service unit 240 may provide a user interface (UI) associated with the chat service, and may receive chat messages from a user through the UI, or output response messages to a user's chat messages (e.g., chatbot responses or chat messages from another user) to a chat window.

[0062] According to an embodiment, chat compressor 242 may include a language model (LM) that can be used for AI functions on the device. Chat compressor 242 can use the LM to compress chat messages or metadata entered by the user. For example, chat compressor 242 can use the LM to perform compression operations that abbreviate chat messages or metadata transmitted to chat server 206.

[0063] According to an embodiment, the compression operation may include replacing or changing text (or words or sentences) included in a chat message or meta-information with other text. The other text may be text with the same or similar meaning as the existing text but with a smaller number of lexical units.

[0064] Table 1 below shows the chat messages between chat participants watching a sports broadcast. The chat messages shown in Table 1 can be included in the metadata as dialogue history information between the chat participants and can be compressed through a compression operation. Any of the chat messages shown in Table 1 can be a message entered by the user of display device 202 and can be compressed similarly to the compression of metadata.

[0065] [Table 1]

[0066] Referring to Table 1, the number of tokens in participant 1's chat message "(Can't wait any longer)" can be 3, the number of tokens in participant 2's chat message "(Why so nervous?)" can be 4, and the number of tokens in participant 3's chat message "(Should be a good game)" can be 5. Therefore, the total number of tokens in the chat messages in the chat room can be 12. Chat compressor 242 can abbreviate at least one of the chat messages in the chat room. For example, chat compressor 242 can change the chat messages of participants 1 to 3 into abbreviated messages as shown in Table 2 below.

[0067] [Table 2]

[0068] Referring to Table 2, Participant 1's chat message changed from "Can't wait any longer" to "Excited," and due to this change, the number of morphemes corresponding to Participant 1's chat message decreased from 3 to 1. Participant 2's chat message changed from "Why so nervous?" to "Feeling anxious?", and the number of morphemes corresponding to Participant 2's chat message decreased from 4 to 2. Participant 3's chat message changed from "Should be a good game" to "Looking forward to an exciting match," and the number of morphemes corresponding to Participant 3's chat message decreased from 5 to 4. As a result, the total number of morphemes in Participants 1 to 3's chat messages decreased from 12 to 7, and the meta-information (e.g., the conversation history between chat participants) decreased by 32% compared to the meta-information before the change. Thus, the chat compressor 242 can reduce the number of morphemes while maintaining the meaning of chat messages or meta-information based on the operation of replacing text. According to an embodiment, when there are multiple texts with overlapping meanings in a chat message or meta-information, the compression operation may include operations such as abbreviating multiple texts into one text or deleting at least one of multiple texts.

[0069] According to an embodiment, the compression operation may include removing unnecessary text from chat messages or metadata that is irrelevant to the context of the conversation in the chat room or to contextual information about the content.

[0070] According to an embodiment, the compression operation may include the operation of abbreviating chat messages or metadata through translation. For example, chat compressor 242 may detect the language of the chat message (e.g., Korean) and count the number of tokens in the chat message. Chat compressor 242 may use LM to translate the language of the chat message into another language (e.g., English) and count the number of tokens in the translated chat message. Chat compressor 242 may compare the number of tokens in the chat message before translation with the number of tokens in the translated chat message. Chat compressor 242 may use or not use the translated chat message as abbreviated message based on the comparison result.

[0071] According to an embodiment, when the number of tokens in the translated chat message is less than the number of tokens in the original chat message, the chat compressor 242 can use the translated chat message as a shortened message. Table 3 below shows the chat messages before and after translation.

[0072] [Table 3]

[0073] Referring to Table 3, the chat compressor 242 can detect that the language of the chat messages before translation is English and count the number of morphemes in each or all chat messages. For example, the chat compressor 242 counts the number of morphemes in participant 1's chat message (They play soccer really well today) as 7, the number of morphemes in participant 2's chat message (They are the best) as 5, and the number of morphemes in participant 3's chat message (It would be niceto score just one more goal) as 10. The chat compressor 242 can count the total number of morphemes in the chat messages of participants 1 to 3 as 22.

[0074] As shown in Table 3, chat compressor 242 can translate English chat messages into Korean. Chat compressor 242 can count the number of each or all of the lexical units in the translated Korean chat message. For example, chat compressor 242 can translate participant 1's chat message "They play soccer really well today" into " "And count the number of lexical units corresponding to Participant 1's translated chat message as 6. Chat compressor 242 can translate Participant 2's chat message "They are the best!!" into " !!”, and counts the number of morphemes corresponding to Participant 2's translated chat message as 3. Chat compressor 242 can translate Participant 3's chat message “It would be nice to score just onemore goal” into “ The chat compressor 242 can count the total number of morphemes corresponding to the translated chat message of participant 3 as 5.

[0075] Chat compressor 242 can identify a further reduction in the number of tokens in each or all chat messages from participants 1 to 3 after translation compared to before translation. For example, chat compressor 242 can identify a reduction in the number of tokens corresponding to a chat message from participant 1 from 7 to 6, the number of tokens corresponding to a chat message from participant 2 from 5 to 3, and the number of tokens corresponding to a chat message from participant 3 from 10 to 5. As a result, chat compressor 242 can identify a reduction in the total number of tokens in the chat messages from participants 1 to 3 from 22 to 14, a reduction of approximately 36%. Therefore, chat compressor 242 can use the translated chat messages as abbreviated messages based on the number of tokens reduced through translation.

[0076] According to an embodiment, when the number of tokens in the translated chat message is equal to or greater than the number of tokens in the chat message before translation, the chat compressor 242 can perform a compression operation using another method (e.g., a text replacement scheme) without using the translated chat message. Table 4 below shows the chat messages before and after translation.

[0077] [Table 4]

[0078] Referring to Table 4, the chat compressor 242 can detect that the language of the chat messages before translation is English and count the number of morphemes in each or all chat messages. For example, the chat compressor 242 can count the number of morphemes in participant 1's chat message (can't wait) as 3, the number of morphemes in participant 2's chat message (Why so nervous?) as 4, and the number of morphemes in participant 3's chat message (should be a good game.) as 5. The chat compressor 242 can count the total number of morphemes in the chat messages from participants 1 to 3 as 12. As shown in Table 4, the chat compressor 242 can translate English chat messages into Korean. The chat compressor 242 can count the number of each or all morphemes in the chat messages translated into Korean. For example, the chat compressor 242 can translate participant 1's chat message "can't wait" into " The chat compressor 242 can translate the chat message "Why so nervous?" and count the number of morphemes corresponding to Participant 1's translated chat message as 5. Participant 2 enters " The chat compressor 242 can translate the chat message "should be a good game." which is part of participant 3's chat message into "...". The number of lexical units corresponding to participant 2's translated chat message is counted as 7. " and count the number of morphemes corresponding to the translated chat message of participant 3 as 7. Chat compressor 242 can count the total number of morphemes in the chat messages of participants 1 to 3 as 19.

[0079] Chat compressor 242 can identify an increase in the number of lexical units in each or all chat messages from participants 1 to 3 after translation compared to before translation. For example, chat compressor 242 can identify an increase in the number of lexical units corresponding to the chat message of participant 1 from 3 to 5 after translation, an increase in the number of lexical units corresponding to the chat message of participant 2 from 4 to 7 after translation, and an increase in the number of lexical units corresponding to the chat message of participant 3 from 5 to 7 after translation. As a result, chat compressor 242 can identify an increase in the total number of lexical units in the chat messages of participants 1 to 3 from 12 to 19, an increase of approximately 58%. Therefore, chat compressor 242 can perform a compression operation of another method (e.g., a text replacement scheme) without using the translated chat messages. According to embodiments, the compression operation may include operations that compress the meaning of non-textual elements (e.g., emojis). If an emoji is input, chat compressor 242 can obtain the name of the input emoji based on LM. For example, the name of an emoji that can be obtained by LM may represent the emotion or facial expression expressed as an emoji in the text (e.g., a smiling face with an open mouth or a crying face with tears). Chat compressor 242 can shorten the meaning of an emoji by changing its name to another text that has a substantially the same or similar meaning and corresponds to a smaller number of lexical units. Chat compressor 242 can further shorten the meaning of an emoji by taking into account contextual information such as conversation context, content type, or scene.

[0080] According to the embodiments, the chat service unit 240 and the chat compressor 242 may be integrated hardware components or software included in or controlled by at least one processor of the display device 202, or physically separate hardware components or software.

[0081] According to an embodiment, chat server 206 may include multiple servers, such as open application programming interface (API) server 244, chat service server 246, and chatbot server 248.

[0082] According to an embodiment, the open API server 244 can be a server that the display device 202 (or another electronic device) can access to use a chat service or chatbot service. For example, the display device 202 can communicate with the open API server 244 to request information associated with the chat service or to receive a chatbot response. The open API server 244 and the display device 202 can perform communication based on, for example, the Hypertext Transfer Protocol (HTTP).

[0083] According to an embodiment, the chat service server 246 can manage information associated with the chat service (e.g., user account information, chat room information, chat messages, or cost information associated with the use of the chatbot server 248), and can be a server that performs operations for providing chatbot services between the open API server 244 and the chatbot server 248. For example, the chat service server 246 can receive compressed messages (or abbreviated messages) from the open API server 244 and can request the chatbot server 248 to provide a response message for the compressed messages.

[0084] According to an embodiment, chatbot server 248 can generate a response message to a compressed message based on a request from chatbot service server 246, and can provide the generated response message as a chatbot response to open API server 244. Chatbot server 248 may include a large language model (LLM) and may be referred to as an LLM server. An LLM is a language model trained on a large amount of data and may be larger than the language model included in the chat compressor 242 of display device 202. An LLM can be used to generate answers or responses based on a given dialogue or message. An LLM can implement language-based processing based on deep learning and natural language processing techniques, and can also perform functions to infer the meaning of non-verbal messages (e.g., emojis) based on a given context. According to an embodiment, chatbot server 248 can use a compressed message as input to an LLM to generate a response message to the compressed message.

[0085] According to an embodiment, chat server 206 may not include open API server 244, chat service server 246, and chatbot server 248, and may be a single server performing the functions of open API server 244, chat service server 246, and chatbot server 248. The operation of open API server 244, chat service server 246, and chatbot server 248 is described below, but the operation of open API server 244, chat service server 246, and chatbot server 248 may also be performed by a single server.

[0086] According to an embodiment, the display device 202 and the chat server 206 can perform the following operations.

[0087] In operation 302, the chat service unit 240 of the display device 202 can obtain user input messages as chat messages entered by the user. According to an embodiment, when a user uses the chat service while displaying content, the chat service unit 240 can obtain user input messages. The user can use the chat service by entering or opening a chat room associated with the content being displayed.

[0088] According to an embodiment, the user input message may be a message entered using at least one of a remote control 212, a mobile device 214, a voice input device 216, or a text input device 218, or a message entered by the user via touch on the touchscreen of the display device 202. According to an embodiment, the user input message may include text and / or emoticons (or emojis) entered or selected by the user. The chat service unit 240 may provide the user input message to the chat compressor 242, and the chat compressor 242 may receive the user input message from the chat service unit 240.

[0089] In operation 304, the chat compressor 242 can count the number of tokens corresponding to the received user input message. According to an embodiment, the chat compressor 242 may include a token counter for counting the number of tokens. The token counter can calculate how many tokens are used to process a natural language sentence such as a user input message.

[0090] In operation 306, chat compressor 242 may perform a message compression operation. For example, chat compressor 242 may convert or change user input messages into compressed messages based on an LM that can be used for AI functions on the device. According to an embodiment, the compressed message is a shortened message with the same or similar meaning as the user input message and may include fewer lexical units than the number of lexical units in the user input message counted in operation 304. According to an embodiment, chat compressor 242 may use context information stored in context DB 230 to convert or change user input messages into compressed messages. According to an embodiment, chat compressor 242 may change user input messages into compressed messages based on any of the compression operations of the various methods described above (e.g., text replacement operation, translation operation, emoji compression operation, or operation to remove unnecessary or overlapping text). Chat compressor 242 may provide the compressed message to chat service unit 240.

[0091] In operation 308, the chat service unit 240 can receive compressed messages and send them to the chat server 206, and can display the sent compressed messages in the chat window. According to an embodiment, the chat service unit 240 can first display the compressed messages, and then transmit the compressed messages to the chat server 206 according to the user's selection. According to an embodiment, the chat service unit 240 can include the compressed messages in a request message and send the request message to the chat server 206. According to an embodiment, the request message can be an HTTP request message, or it can be a message requesting a response message for the compressed messages.

[0092] According to one embodiment, chat service unit 240 can receive and store the number of tokens in compressed messages transmitted from chat compressor 242 to chat server 206. According to one embodiment, chat service unit 240 can use the stored number of tokens in the compressed messages to calculate costs associated with chat server 206 (e.g., chatbot response generation costs). According to one embodiment, chat service unit 240 can send information about the calculated costs to chat server 206 (or chat service server 246). According to one embodiment, chat service unit 240 may not send information about the calculated costs. In this case, chat server 206 (or chat service server 246) can calculate the costs by counting the number of tokens in the compressed messages.

[0093] In operation 310, the open API server 244 can receive request messages and send compressed messages included in the received request messages to the chat service server 246. According to an embodiment, when it is determined that the number of tokens in the compressed message is greater than or equal to a set number, the open API server 244 may not send the compressed message to the chat service server 246. In this case, the open API server 244 can send an indication message to the display device 202 indicating that the number of tokens in the compressed message is too large. If the indication message is received, the chat service unit 240 of the display device 202 can send the compressed message to the chat compressor 242, causing additional compression operations to be performed to reduce the number of tokens in the compressed message.

[0094] According to an embodiment, when the cost of using chat server 206 increases by a set amount or more, at least one of the chat servers 206 can stop the operation used to generate chatbot responses and can send a notification message to display device 202. For example, the notification message may include information indicating that the cost of using the server is too high.

[0095] In operation 312, the chat service server 246 can receive compressed messages from the open API server 244 and can request the chatbot server 248 to generate a response message to the compressed messages. The chat service server 246 can send the compressed messages along with the request to the chatbot server 248. According to an embodiment, the chat service server 246 can send to the chatbot server 248 compression instruction information indicating compression or abbreviation of the chatbot response and / or token count indication information indicating the number of tokens or a range of token counts in the chatbot response.

[0096] In operation 314, the chatbot server 248 can receive compressed messages from the chatbot service server 246. According to an embodiment, the chatbot server 248 can receive compression instruction information and / or token count indication information.

[0097] In operation 316, chatbot server 248 may generate a chatbot response in response to a request from chatbot service server 246. This chatbot response is a response message to a compressed message. According to an embodiment, chatbot server 248 may use LLM to generate chatbot responses based on compressed messages. For example, in response to a compressed message including any one of the chat messages from participants 1 to 3, chatbot server 248 may generate chatbot responses as shown in Table 5 below.

[0098] [Table 5]

[0099] Referring to Table 5, the chatbot response may include 15 tokens. According to an embodiment, the chatbot server 248 may receive compression instruction information and / or token count indication information. For example, the chatbot server 248 may, based on the compression instruction information, abbreviate the chatbot response shown in Table 5 to the following Table 6.

[0100] [Table 6]

[0101] Referring to Table 6, a chatbot response may include up to 10 tokens, as shown in Table 5. For example, the chatbot server 248 may abbreviate the chatbot response shown in Table 5 to the following Table 7 based on compression instructions and token numbering instructions.

[0102] [Table 7]

[0103] Referring to Table 7, when the token count indication information indicates a token count of five or fewer, the chatbot response may include five tokens based on the token count indication information. According to an embodiment, the chatbot server 248 may use exclamation marks or emoticons, or it may perform translation to shorten the chatbot response.

[0104] In operation 318, if a chatbot response is generated, the chatbot server 248 can send the generated chatbot response to the chatbot service server 246.

[0105] In operation 320, the chat service server 246 can receive chatbot responses sent from the chatbot server 248. The chat service server 246 can store the chatbot responses in message DB 252 and send the chatbot responses to the open API server 244.

[0106] According to an embodiment, operations 312 and 320 may be performed by a chat room manager 250 included in the chat service server 246. For example, the chat room manager 250 may store and manage messages of chat rooms opened in association with the chat service in a message database 252, control the generation of chatbot responses by the chatbot server 248, or calculate or manage the costs associated with the generation of chatbot responses. According to an embodiment, the costs associated with generating chatbot responses may be based on the number of tokens in the compressed message used to generate the chatbot response and / or the number of tokens in the chatbot response. According to an embodiment, the chat room manager 250 may correspond to at least one processor of the chat service server 246, or may be a separate component controlled by at least one processor.

[0107] In operation 322, the open API server 244 can obtain a chatbot response from the chat service server 246 and provide the obtained chatbot response to the display device 202. According to an embodiment, the open API server 244 can include the chatbot response in a response message and send it to the display device 202. For example, the response message can be an HTTP response message, and it can be a response message to a request message sent by the display device 202 in operation 308.

[0108] In operation 324, the chat service unit 240 of the display device 202 can receive chatbot responses from the open API server 244, and can display them on the screen (e.g., ...). Figure 1 The received chatbot response is displayed in the chat window (104) as a response message to the user's input message.

[0109] According to an embodiment, the display device 202 may perform the following operations: providing metadata to the chat server 206 (or chatbot server 248) in order to obtain a more appropriate chatbot response.

[0110] According to an embodiment, the chat service unit 240 of the display device 202 can obtain metadata. For example, the metadata includes information based on EPG 220 (e.g., at least one of broadcast time information, broadcast channel information, broadcast program title, broadcast program description, broadcast program type, broadcast program cast information, broadcast program staff information, or broadcast program screen information), information obtained through screen analysis (or scene analysis) of the display device 202 (e.g., at least one of information about people or objects appearing in the content or background information about the content), and information obtained through audio analysis of the display device 202 (e.g., the tone of voice of people in the content). It may include at least one of voice information or sound information, text information obtained from the screen of the content through text detection operations, chat participant information (e.g., the number of participants, participant nationality, participant gender, participant age, or participant account information), or conversation history information about chat participants.

[0111] According to an embodiment, the chat service unit 240 can transmit metadata to the chat compressor 242. The chat compressor 242 can count the number of tokens corresponding to the received metadata. The chat compressor 242 can compress the metadata based on the counted number of tokens. For example, the chat compressor 242 can compress or abbreviate the metadata based on any of the various compression operations described above (e.g., text replacement, translation, emoji compression, or deletion of unnecessary or overlapping text). The chat compressor 242 can provide the abbreviated metadata to the chat service unit 240.

[0112] According to an embodiment, the chat service unit 240 can send abbreviated metadata to the chat server 206. For example, the abbreviated metadata may not be displayed in the chat window and may be sent to the chat server 206 without user confirmation.

[0113] According to an embodiment, the open API server 244 can receive abbreviated metadata and send it to the chat service server 246. The chat service server 246 can receive the abbreviated metadata from the open API server 244 and transmit it to the chatbot server 248. The chatbot server 248 can use the abbreviated metadata to generate a chatbot response to user input messages (or compressed messages).

[0114] According to the embodiment, the above-described operations associated with the display device 202 and the chat server 206 can be repeatedly performed.

[0115] According to an embodiment, the display device 202 can measure the amount of chat (or chat messages) in the chat room and the chat speed between participants, and can adjust the activation level of chatbot responses (e.g., the amount and / or speed of chatbot response generation) based on the measurement results. For example, when the amount of chat in the chat room is less than a threshold or the chat speed is slow, the display device 202 can increase the access frequency of the chat server 206, causing more or faster chatbot responses to be generated. When the amount of chat in the chat room is greater than or equal to the threshold or the chat speed is fast, the display device 202 can decrease the access frequency of the chat server 206, causing fewer or slower chatbot responses to be generated. Therefore, if the conversation between participants is stable, the chatbot response generation speed can be reduced, and relatively fewer chatbot responses can be output; conversely, if the conversation between participants is infrequent, the chatbot response generation speed can be increased, and relatively more chatbot responses can be output.

[0116] According to an embodiment, when a user is watching a broadcast program, the display device 202 can adjust the activation level of the chatbot response so that the chatbot response is output less or slower as the broadcast program approaches its end time.

[0117] According to an embodiment, the display device 202 can calculate the elapsed time from the broadcast start time or the remaining time until the broadcast end time based on information about the broadcast start time or broadcast end time obtained from the EPG. The display device 202 can adjust the activation level of the chatbot response based on the elapsed time from the broadcast start time or the remaining time until the broadcast end time.

[0118] For example, when the time elapsed since the start of the broadcast (e.g., 12 minutes) is less than a threshold time (e.g., 50 minutes), the display device 202 may increase the activation level of the chatbot response. When the time elapsed since the start of the broadcast (e.g., 51 minutes) is greater than or equal to the threshold time (e.g., 50 minutes), the display device 202 may decrease the activation level of the chatbot response.

[0119] For example, when the remaining time until the broadcast ends (e.g., 48 minutes) is greater than or equal to a threshold time (e.g., 10 minutes), the display device 202 may increase the activation level of the chatbot response. When the remaining time until the broadcast ends (e.g., 8 minutes) is less than the threshold time (e.g., 10 minutes), the display device 202 may decrease the activation level of the chatbot response.

[0120] According to an embodiment, the display device 202 can calculate a first ratio or a second ratio, where the first ratio is the ratio of elapsed time to total broadcast time, and the second ratio is the ratio of remaining time to total broadcast time. The display device 202 can compare the first ratio or the second ratio with a threshold ratio and can determine the activation level of the chatbot response based on the comparison result.

[0121] For example, when the first ratio is less than the first threshold ratio or the second ratio is greater than or equal to the second threshold ratio, the display device 202 can increase the activation level of the chatbot response. Conversely, when the first ratio is greater than or equal to the first threshold ratio or the second ratio is less than the second threshold ratio, the display device 202 can decrease the activation level of the chatbot response.

[0122] Figure 4 This is a flowchart illustrating the operation of a display device according to an embodiment; refer to Figure 4 In operation 402, display device 202 can display content. According to an embodiment, display device 202 can display images streamed from an external electronic device or content server, or images from a broadcast channel, on the display screen according to the user's selection. According to an embodiment, display device 202 can provide a chat service, allowing users to chat in real time while viewing content. When it is determined that a user has opened a chat room or entered an existing chat room, display device 202 can allow a chatbot to participate in the chat room the user has entered. According to an embodiment, display device 202 can provide guidance to the chat room regarding the chatbot. For example, display device 202 can output information to the chat room indicating that an AI-based chatbot is participating in the chat and / or a warning about the presence of a non-human participant (chatbot).

[0123] In operation 404, display device 202 can recognize chat messages entered by the user while displaying content. For example, a chat message can be a user-input message entered by the user using at least one of a remote control 212, a mobile device 214, a voice input device 216, a text input device 218, or a touch on a touchscreen.

[0124] In operation 406, display device 202 can change the recognized chat message into a thumbnail message (e.g., Figure 3(Compressed messages). For example, display device 202 can transform an identified chat message into a shortened chat message with the same or similar meaning as the identified chat message based on contextual information associated with the displayed content. According to an embodiment, display device 202 may include a module (LM) for transforming an identified chat message into a shortened chat message. For example, the LM may be used to obtain similar words or sentences that can replace words or sentences included in the chat message, or to translate the chat message into another language. When using contextual information, the meaning of words or sentences included in the chat message can be grasped by considering the conversational context between chat participants or the context associated with the content, and thus clearer similar words or sentences can be obtained. According to an embodiment, the shortened chat message may include fewer lexical units than the number of lexical units in the identified chat message.

[0125] In operation 408, display device 202 may send thumbnail messages to a server (e.g., Figure 3 The chatbot server 206 or open API server 244). According to embodiments, the server can directly generate chatbot responses to compressed messages based on LLM, or it can include a separate server for generating chatbot responses (e.g., Figure 3 Chatbot server 248).

[0126] In operation 410, display device 202 can receive a response message from the server. According to an embodiment, display device 202 can display the received response message as a chatbot response in a chat room.

[0127] According to an embodiment, operation 406 can be performed based on various compression schemes. See also... Figures 5 to 7 This will be described.

[0128] Figure 5 This is a flowchart illustrating the operation of a display device abbreviating chat messages based on a text replacement scheme according to an embodiment.

[0129] refer to Figure 5 In operation 502, the display device 202 can recognize first text included in the chat message. According to an embodiment, the first text may include at least one first word or at least one first sentence.

[0130] In operation 504, display device 202 may, based on LM, change the first text into a second text having a smaller number of lexical units. According to an embodiment, the second text may include at least one second word or at least one second sentence having the same or similar meaning as at least one first word or at least one first sentence.

[0131] In operation 506, display device 202 may use a message including a second text as a shortened message.

[0132] Figure 6a This is a flowchart illustrating the operation of a display device translating and abbreviating chat messages according to an embodiment; refer to Figure 6a In operation 602, display device 202 can detect the language of chat messages (e.g., Korean) based on LM.

[0133] In operation 604, the display device 202 can count the number of first tokens, which is the number of tokens in the chat message.

[0134] In operation 606, display device 202 can translate chat messages into a language different from the detected language (e.g., English).

[0135] In operation 608, the display device 202 can count the number of second lexical units, which is the number of lexical units in the translated chat message.

[0136] In operation 610, the display device 202 can determine whether the number of second word tokens is less than the number of first word tokens.

[0137] In operation 612, when the number of second tokens is less than the number of first tokens, the display device 202 can use the translated message as a shortened message.

[0138] In operation 614, when the number of second tokens is equal to or greater than the number of first tokens, the display device 202 may reduce the chat message based on another compression scheme (e.g., a text replacement scheme).

[0139] Figure 6b This is a flowchart illustrating another operation of a display device translating and abbreviating chat messages according to an embodiment.

[0140] like Figure 6b As shown, display device 202 can shorten chat messages by limiting the number of tokens in the translation.

[0141] refer to Figure 6b In operation 622, display device 202 can detect the language of chat messages (e.g., Korean) based on LM.

[0142] In operation 624, the display device 202 can count the first number of words (e.g., 15 words) that constitute the number of words in a chat message.

[0143] In operation 626, display device 202 may determine a second number of lexical units (e.g., 10 lexical units) that is less than the first number of lexical units. According to embodiments, a range of lexical units (e.g., 10 or fewer) may be determined instead of a second number of lexical units.

[0144] In operation 628, display device 202 can translate the chat message into a language different from the detected language (e.g., English) based on the determined second number of tokens. For example, display device 202 can perform the translation such that the translated message includes the same or fewer tokens than the second number.

[0145] In operation 630, display device 202 can use the translated message as a shortened message.

[0146] Table 8 below shows an example of how display device 202 uses lexical number limit conversion to abbreviate chat messages.

[0147] [Table 8]

[0148] Referring to Table 8, a chat message with 19 tokens before translation can be transformed into a chat message with 16 tokens after translation. Since the number of tokens in the translated chat message does not meet the predetermined number of tokens (e.g., 10 tokens) or the range of token numbers (e.g., 10 tokens or less), the display device 202 can compress the translated message. For example, the display device 202 can replace or briefly abbreviate the text of the translated chat message with another text to have 10 or fewer tokens. Therefore, the token count code restricts the translated message to be used as a shortened message that meets the determined token count code or the range of token count codes. Figure 7 This is a flowchart illustrating an operation in which a display device abbreviates chat messages using semantic compression of emojis, according to an embodiment; refer to Figure 7 In operation 702, the display device 202 can recognize emoticons included in chat messages.

[0149] In operation 704, display device 202 can obtain the name of the emoji based on LM.

[0150] In operation 706, display device 202 can generate first text indicating the meaning of an emoji based on the obtained emoji name.

[0151] In operation 708, display device 202 can generate second text by abbreviating the first text based on context information.

[0152] In operation 710, the display device 202 may use a message including a second text as a shortened message.

[0153] Figure 8 This is a view illustrating an example in which the meaning of emojis is compressed by the display device according to an embodiment; refer to Figure 8 The display device 202 can obtain the name of the emoticon 802 based on the recognition of the emoticon 802 included in the chat message. For example, the name of the emoticon 802 could be "smiling face with open mouth and tears 804" which includes 9 words.

[0154] Typically, since the name of an emoji indicates the emotion, facial expression, or state expressed by the emoji, the display device 202 can identify the meaning of the emoji 802 based on its name. Based on the identified meaning of the emoji 802, a first text indicating the meaning of the emoji 802 can be generated. For example, the display device 202 can generate a four-word phrase "laughing-crying 806" as the first text, in the form of a compressed version of the emoji 802's name, "open-mouthed smiling face with tears 804".

[0155] Display device 202 can take contextual information into account to perform semantic compression of the first text. For example, when the user is watching a comedy show, display device 202 can compress the meaning of the first text and change it into second text, such as the three-word phrase "laughing 808". Similarly, when the user is watching a sports game, display device 202 can compress the meaning of the first text and change it into second text, such as the two-word phrase "so painful 810". Display device 202 can use a message that includes the second text as a shortened message.

[0156] Figure 9 This is a flowchart illustrating the operation of a display device generating context information based on an EPG according to an embodiment; refer to Figure 9 In operation 902, display device 202 can obtain EPG 220 from broadcast server 204.

[0157] In operation 904, display device 202 can obtain information from EPG 220. According to an embodiment, display device 202 can obtain text information included in EPG 220. For example, display device 202 can obtain at least one of the following from EPG 220 as information associated with one or more broadcast programs: broadcast time information (e.g., broadcast start time and / or broadcast end time), broadcast channel information (e.g., channel name, channel logo, or channel number), broadcast program title, broadcast program description, broadcast program type (e.g., drama, sports, documentary, or entertainment), broadcast program cast information, broadcast program staff information, or broadcast program screen information.

[0158] In operation 906, display device 202 can generate metadata based on the obtained information.

[0159] In operation 908, the display device 202 can generate context information based on metadata. According to an embodiment, the display device 202 can receive EPG 220 periodically or aperiodically, and can update the context information based on the received information about EPG 220.

[0160] Figure 10 This is a flowchart illustrating the operation of a display device generating context information based on screen analysis or text detection operations according to an embodiment; refer to Figure 10 In operation 1002, the display device 202 may obtain a content screen (e.g., a still screen and / or a video screen).

[0161] In operation 1003, in response to obtaining the content screen, the display device 202 can determine whether to perform a screen analysis operation or a text detection operation.

[0162] When it is determined in operation 1003 that a screen analysis operation will be performed, the display device 202 may perform operations 1004 to 1014.

[0163] In operation 1004, display device 202 may use visual information processing functions such as computer vision to analyze the acquired screen. According to an embodiment, screen analysis by display device 202 may be performed periodically and may be used to obtain atmosphere, status, or information about the content.

[0164] In operation 1006, the display device 202 can detect objects, object features, or object movement or manipulation based on the results of screen analysis. For example, an object may include at least one of a person, an animal, or a physical object.

[0165] In operation 1008, display device 202 can generate metadata based on the detection results.

[0166] In operation 1014, display device 202 can generate context information based on metadata.

[0167] When it is determined in operation 1003 that a text detection operation will be performed, the display device 202 may perform operations 1010 to 1014.

[0168] In operation 1010, the display device 202 can detect text on the obtained screen. According to an embodiment, the display device 202 can detect text based on the obtained screen using a predetermined text detection algorithm.

[0169] In operation 1012, display device 202 can generate metadata by analyzing the detected text.

[0170] In operation 1014, display device 202 can generate context information based on metadata.

[0171] Figure 11 This is a flowchart illustrating the operation of a server according to an embodiment; refer to Figure 11 In operation 1102, the server (e.g., chat server 206) can receive abbreviated (or compressed) messages from display device 202. According to an embodiment, operation 1102 can be performed by open API server 244. In this case, open API server 244 can transmit the abbreviated message to chat service server 246, so that the abbreviated message is provided to chatbot server 244.

[0172] In operation 1104, the server can generate a chatbot response to the abbreviated message based on the LLM. According to an embodiment, operation 1104 can be performed by the chatbot server 244. In this case, the chatbot server 244 can generate a chatbot response based on a request from the chatbot service server 246.

[0173] According to an embodiment, when the server receives metadata from the display device 202, the server can consider the received metadata to generate a chatbot response to the abbreviated message. The received metadata can be compressed or abbreviated metadata by the display device 202.

[0174] In operation 1106, the server (e.g., chat server 206 or open API server 244) can send the generated chatbot response to display device 202.

[0175] Figure 12 This is a block diagram illustrating the configuration of a display device according to an embodiment; and

[0176] refer to Figure 12The display device 202 may include a display 1200, a transceiver 1202, a memory 1204, and a processor 1206. According to an embodiment, the display device 202 may include additional components besides those shown (e.g., a communication interface for communicating with an electronic device, such as an audio input unit, an audio output unit, or a remote control, or a tuner unit for receiving broadcast signals), or at least one of the shown components may be omitted.

[0177] According to an embodiment, the display 1200 can perform functions for outputting information in the form of numbers, characters, images, and / or graphics. The display 1200 may include at least one hardware module for output. The at least one hardware module may include at least one of, for example, a liquid crystal display (LCD), a light-emitting diode (LED), a light-emitting polymer display (LPD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), or a flexible LED (FLED). The display 1200 can display a screen corresponding to data received from the processor 1206. The display 1200 may be referred to as an "output unit," a "display unit," or other terms with equivalent technical meanings.

[0178] According to an embodiment, transceiver 1202 can perform communication with external electronic devices (e.g., mobile device 214) and / or at least one server (e.g., broadcast server 204, chat server 206, or open API server 244). For example, transceiver 1202 can perform communication with at least one server based on various wired / wireless communication technologies.

[0179] According to an embodiment, memory 1204 may store various information or data associated with the operation of display device 202, and may store at least one program. For example, memory 1204 may store metadata, context information, chat messages input by the user, information about the number of tokens, metadata, or LM for compressing chat messages.

[0180] According to an embodiment, processor 1206 may be electrically or operatively connected to display 1200, transceiver 1202, and memory 1204. Processor 1206 may be a processing circuit that executes at least one instruction of a program stored in memory 1204. Processor 1206 may perform control and / or perform communication-related operations or data processing on at least one of the other components of display device 202. Processor 1206 may include at least one of a central processing unit (CPU), neural processing unit (NPU), graphics processing unit (GPU), microprocessor unit (MPU), microcontroller unit (MCU), application processor (AP), communication processor (CP), system-on-a-chip (SoC), integrated circuit (IC), sensor hub, auxiliary processor, communication processor, application processor, application-specific integrated circuit (ASIC), or field-programmable gate array (FPGA), and may include multiple cores. Processor 1206 may control Figure 3 The chat service unit 240 or chat compressor 242 can perform functions corresponding to the operation of the chat service unit 240 or chat compressor 242. The processor 1206 can perform the above-described operations of the display device 202 (for example, refer to...). Figures 1 to 10 (The operation of the display device 202 is described).

[0181] Figure 13 This is a block diagram illustrating the configuration of a server according to an embodiment.

[0182] refer to Figure 13 The server (e.g., chat server 206 or any of the servers included in chat server 206) may include transceiver 1302, memory 1304, and processor 1306. According to embodiments, server 130 may include additional components besides those shown (e.g., a communication module for communicating with another server or another electronic device), or at least one of the shown components may be omitted.

[0183] According to an embodiment, transceiver 1302 can communicate with display device 202. For example, transceiver 1302 can perform communication with display device 202 based on various wired / wireless communication technologies.

[0184] According to an embodiment, memory 1304 may store various information or data associated with the operation of the server, and may store at least one program. For example, memory 1304 may store compressed messages, abbreviated messages, metadata, cost information based on the number of tokens, or LLMs used to generate chatbot responses received from display device 202.

[0185] According to an embodiment, processor 1306 may be electrically or operatively connected to transceiver 1302 and memory 1304. Processor 1306 may be processing circuitry that executes at least one instruction of a program stored in memory 1304. One or more processors 1306 may be present, capable of performing the aforementioned operations of the server (e.g., Figure 2 and Figure 3 The operation of chat server 206, or Figure 3 The operation of either the open API server 244 or the chatbot server 248, and the combination of Figure 11 (Description of server operations).

[0186] According to various embodiments of this disclosure, chatbot responses that are substantially the same or similar to those based on uncompressed chat messages can be provided to users, while reducing server costs based on compressed (or abbreviated) messages.

[0187] According to various embodiments of this disclosure, display device 202 can control chatbot activation to enhance the user experience of the chat service and increase its usage.

[0188] According to various embodiments of this disclosure, since the display device 202 and / or chat server 206 (or chatbot server 248) can grasp content information, information about chat participants, or the context of the session based on metadata, they can efficiently provide chat services corresponding to the user's viewing environment or chat environment.

[0189] The various embodiments and terms used herein are not intended to limit the technical features described herein to the particular embodiments and should be understood to include various modifications, equivalents, or substitutions of the embodiments. In conjunction with the description of the accompanying drawings, the same figure terms may be used for similar or related parts. In this document, each phrase such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B, or C,” “at least one of A, B, and C,” and “at least one of A, B, or C” may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as “first,” “second,” or “first” or “second” may be used only to distinguish the corresponding component from another corresponding component and do not limit the corresponding component in other respects (e.g., importance or order). It will be understood that, whether the terms “operably” or “communically” are used or not, if an element (e.g., a first element) is referred to as “combined with another element (e.g., a second element),” “combined to another element (e.g., a second element),” “connected to another element (e.g., a second element),” or “attached to another element (e.g., a second element)”, it means that the element can be directly (e.g., wiredly) connected to the other element, wirelessly connected to the other element, or connected to the other element via a third element.

[0190] The term "module" as used in the various embodiments of this document can include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as, for example, logic, logic block, component, assembly, or circuit. A module or unit can be an integrated configuration of components or the smallest unit or part of a component that performs one or more functions. For example, according to an embodiment, a module or unit may be implemented as an application-specific integrated circuit (ASIC).

[0191] According to various embodiments of this disclosure, each of the above-described components (e.g., a module or program) may include a single entity or multiple entities, and some of the multiple entities may be separately disposed in different components. According to various embodiments of this disclosure, one or more of the above-described components may be omitted, or one or more other components may be added. Alternatively or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In this case, according to various embodiments of this disclosure, the integrated component can still perform one or more functions of each of the multiple components in the same or similar manner as the corresponding components in the multiple components before integration. According to various embodiments of this disclosure, operations performed by a module, program, or other component may be performed sequentially, in parallel, repeatedly, or heuristically, or may be performed in a different order or one or more operations may be omitted, or one or more other operations may be added.

Claims

1. A display device, comprising: monitor; transceiver Memory, used to store at least one program; and At least one processor, the at least one processor being electrically connected to the memory, and including processing circuitry for executing at least one instruction of the at least one program when connected to the memory, wherein the at least one processor is configured individually or in combination to: Control the display to show content; When the content is displayed, identify chat messages entered by the user; Based on contextual information associated with the content being displayed, the identified chat message is transformed into a shortened message with the same or similar meaning as the identified chat message; and The transceiver is controlled to send the abbreviated message to a server capable of providing a chatbot response.

2. The display device according to claim 1, wherein the abbreviated message includes a number of lexical units that are less than the number of lexical units in the identified chat message.

3. The display device according to claim 1, wherein, At least one processor is configured individually or in combination as follows: Based on a language model, the first text included in the identified chat message is transformed into a second text, which includes fewer lexical units than the first text. The message including the second text is used as the abbreviated message.

4. The display device according to claim 1, wherein, At least one processor is configured individually or in combination as follows: Language in chat messages detected and identified based on language models; The number of the first word element is counted, which is the number of words in the identified chat message; Translate the identified chat messages into a language different from the detected language; The number of second lexical units is counted, which is the number of lexical units in the translated chat message; and In response to the fact that the number of second lexical units is less than the number of first lexical units, the translated chat message is used as the abbreviated message.

5. The display device according to claim 1, wherein, At least one processor is configured individually or in combination as follows: Language in chat messages detected and identified based on language models; The number of the first word element is counted, which is the number of words in the identified chat message; Determine the number of second lexical units that is less than the number of first lexical units; Based on the determined number of second lexical units, the identified chat messages are translated into a language different from the detected language; and The translated chat message is used as the abbreviated message.

6. The display device according to claim 1, wherein, At least one processor is configured individually or in combination as follows: Recognize emojis included in the identified chat messages; The name of the emoji is obtained based on the language model; Based on the obtained name, the meaning of the emoji is identified, and a first text indicating the identified meaning is generated; The second text is generated by abbreviating the first text based on the context information, and the second text has fewer lexical units than the first text. and The message including the second text is used as the abbreviated message.

7. The display device according to claim 1, wherein, The context information is generated based on metadata, and The metadata includes at least one of the following: broadcast time information, broadcast channel information, broadcast program title, broadcast program description, broadcast program type, broadcast program cast information, broadcast program staff information, or broadcast program video information obtained based on the Electronic Program Guide (EPG).

8. The display device according to claim 1, wherein, The context information is generated based on metadata, and Meta-information includes at least one of the following: information about people or objects appearing in the content or background information about the content obtained through screen analysis of the display device; speech or sound information obtained through audio analysis of the display device; text information obtained from the screen of the content through text detection operations; information about one or more chat participants including the user; or conversation history information about one or more chat participants.

9. The display device according to claim 7 or 8, wherein, At least one processor is configured individually or in combination as follows: The metadata is changed into abbreviations with similar meanings, and the transceiver is controlled to send the abbreviations to the server. The abbreviation information includes a smaller number of lexical units than the number of lexical units in the meta-information.

10. The display device according to claim 1, wherein, At least one processor is configured individually or in combination as follows: Receive a response message for the abbreviated message from the server via the transceiver; and Control the display to show the received response messages as the chatbot's response.

11. A method for providing a chat service via a display device, the method comprising: Display content; When the content is displayed, identify chat messages entered by the user; Based on contextual information associated with the content being displayed, the identified chat message is transformed into a shortened message with the same or similar meaning as the identified chat message. and The abbreviated message is sent to a server that can provide a chatbot response.

12. The method according to claim 11, wherein, The abbreviated message includes a number of lexical units that are less than the number of lexical units in the identified chat message.

13. The method according to claim 11, wherein, The change to the abbreviated message includes: based on a language model, changing the first text included in the identified chat message to a second text, the second text including a number of lexical units less than the number of lexical units in the first text, and using the message including the second text as the abbreviated message.

14. The method according to claim 11, wherein, The change to the abbreviated message includes: Language in chat messages detected and identified based on language models; The number of the first word element is counted, which is the number of words in the identified chat message; Translate the identified chat messages into a language different from the detected language; Count the number of second lexical units, which is the number of lexical units in the translated chat message; and In response to the fact that the number of second lexical units is less than the number of first lexical units, the translated chat message is used as the abbreviated message.

15. The method according to claim 11, wherein, The change to the abbreviated message includes: Language in chat messages detected and identified based on language models; The number of the first word element is counted, which is the number of words in the identified chat message; Determine the number of second lexical units that is less than the number of first lexical units; Based on a determined number of second-order lexical units, the identified chat messages are translated into a language different from the detected language; and The translated chat message is used as the abbreviated message.

Images