Electronic device for providing content using generative artificial intelligence model and operating method thereof

Abstract

According to an embodiment, this first electronic device may comprise a microphone, a communication circuit, a first display, at least one processor, and a memory including instructions. According to an embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to acquire a user's query via the first display or the microphone. According to an embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate at least one prompt on the basis of information about the query, first information related to the first electronic device, and second information related to a second electronic device that is different from the first electronic device. According to an embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to acquire first content based on the first information and second content based on the second information by providing the at least one prompt to a generative AI model. According to an embodiment, the instructions, when executed by the at least one processor, may cause, in response to the query, the electronic device to: display the first content on the first display; and transmit information about the second content to the second electronic device via the communication circuit such that the second electronic device outputs the second content.

Description

Electronic device providing content using a generative artificial intelligence model and its operating method

[0001] The present disclosure relates to an electronic device that provides content using a generative artificial intelligence model and a method of operating the same.

[0002] Thanks to remarkable advancements in information and communication technology and semiconductor technology, the proliferation and use of various electronic devices is rapidly increasing. Electronic devices are being developed to enable users to carry and communicate with one another. An electronic device can refer to any device that performs a specific function based on its embedded software, such as a mobile communication terminal, tablet PC, wearable electronic device, audio / video device, desktop / laptop computer, or in-vehicle navigation system.

[0003] Electronic devices can utilize artificial intelligence (AI) models to provide services for specific purposes. For example, AI models are being utilized in diverse fields such as content streaming, translation, photo editing, finance, new drug development, law, and the military. At least some of the various AI models for specific services can be implemented as generative AI models. Depending on the implementation, the AI ​​models can operate in a form where multiple AI models are linked together.

[0004] According to one embodiment, a first electronic device may include a microphone, a communication circuit, a first display, at least one processor, and a memory including instructions. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to obtain a user's query through the first display or the microphone. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate at least one prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to provide the at least one prompt to a generative AI model to obtain first content based on the first information and second content based on the second information. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to, in response to the query, display the first content on the first display and transmit information about the second content to the second electronic device via the communication circuit so that the second electronic device outputs the second content.

[0005] According to one embodiment, a method of operating a first electronic device may include an operation of obtaining a user's query through a first display included in the first electronic device or a microphone included in the first electronic device. According to one embodiment, the method of operating the first electronic device may include an operation of generating at least one prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device. According to one embodiment, the method of operating the first electronic device may include an operation of providing the at least one prompt to a generative AI model to obtain first content based on the first information and second content based on the second information. According to one embodiment, the method of operating the first electronic device may include an operation of displaying the first content on the first display in response to the query and transmitting information about the second content to the second electronic device through a communication circuit included in the electronic device so that the second electronic device outputs the second content.

[0006] According to one embodiment, a computer-readable, non-transitory recording medium may store instructions that, when executed by at least one processor, cause a first electronic device to perform an operation of obtaining a user's query through a first display included in the first electronic device or a microphone included in the first electronic device, an operation of generating at least one prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device, an operation of providing the at least one prompt to a generative AI model to obtain first content based on the first information and second content based on the second information, and an operation of displaying the first content on the first display and transmitting information about the second content to a second electronic device through a communication circuit included in the electronic device so that the second electronic device outputs the second content in response to the query.

[0007] FIG. 1 is a block diagram of an electronic device within a network environment, according to one embodiment.

[0008] FIG. 2 is a block diagram illustrating a schematic configuration of a first electronic device and a second electronic device according to one embodiment.

[0009] FIG. 3 is a diagram for explaining an operation of obtaining first content and second content using a generative AI model according to one embodiment.

[0010] FIG. 4A is a flowchart illustrating an operation of a first electronic device obtaining first content and second content using a generative AI model according to one embodiment.

[0011] FIG. 4b is a flowchart illustrating an operation of a first electronic device obtaining first content and second content using a generative AI model according to one embodiment.

[0012] FIG. 4c is a flowchart illustrating an operation of a first electronic device obtaining first content based on a first prompt and second content based on a second prompt using a generative AI model according to one embodiment.

[0013] FIG. 4D is a flowchart illustrating an operation in which a first electronic device acquires first content using a generative AI model and transmits a second prompt to a second electronic device to acquire second content, according to one embodiment.

[0014] FIG. 5A is a diagram for explaining an operation of a first electronic device outputting first content and second content based on a query according to one embodiment.

[0015] FIG. 5B is a diagram of a prompt generated by a first electronic device to obtain first content and second content, according to one embodiment.

[0016] FIG. 5c is a diagram illustrating first content modified based on a first user and second content modified based on a second user, according to one embodiment.

[0017] FIG. 6 is a diagram for explaining first content based on a first user and second content based on a second user, according to one embodiment.

[0018] FIG. 7A is a diagram for explaining an operation in which a first electronic device outputs first content based on a first user and second content based on a second user based on a query, according to one embodiment.

[0019] FIG. 7B is a diagram of a prompt generated by a first electronic device to obtain first content and second content, according to one embodiment.

[0020] FIGS. 8A and 8B are diagrams for explaining an operation in which a first electronic device outputs first content based on device information of the first electronic device and second content based on device information of a second electronic device based on a query, according to one embodiment.

[0021] FIG. 8C is a diagram of a prompt generated by a first electronic device to obtain first content and second content, according to one embodiment.

[0022] FIG. 9A is a diagram for explaining an operation of a first electronic device outputting first content based on device information of the first electronic device and second content based on device information of a second electronic device, according to one embodiment.

[0023] FIG. 9B is a diagram of a prompt generated by a first electronic device to obtain first content and second content, according to one embodiment.

[0024] FIG. 10 is a diagram illustrating an operation of synchronizing the order between first content displayed on a first display and second content output from a second electronic device, according to one embodiment.

[0025] Fig. 11 is a diagram for explaining a generative artificial intelligence system according to one embodiment.

[0026] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) or the server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0027] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0028] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, in the electronic device (101) itself where artificial intelligence is performed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0029] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0030] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0031] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0032] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0033] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0034] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0035] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0036] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0037] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0038] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0039] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0040] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0041] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0042] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0043] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0044] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0045] In one embodiment, the antenna module (197) may generate a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band.

[0046] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0047] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0048] FIG. 2 is a block diagram illustrating a schematic configuration of a first electronic device and a second electronic device according to one embodiment.

[0049] Referring to FIG. 2, according to one embodiment, the first electronic device (201) may include a microphone (210), a processor (220), a memory (230), a speaker (240), a display (260), and a communication circuit (290). For example, the first electronic device (201) may be implemented in the same or similar manner as the electronic device (101) of FIG. 1.

[0050] According to one embodiment, the processor (220) (e.g., the processor (120) of FIG. 1) may control the overall operation of the first electronic device (201). The processor (220) according to one embodiment may execute software (e.g., the program (140) of FIG. 1) to control at least one other component (e.g., a hardware or software component) of the electronic device (201) connected to the processor (220), and may perform data processing or calculations based on the instructions. The instructions according to one embodiment may include instructions configured in a machine language that can be processed by the electronic device (201) or the processor (220). For example, the instructions may include instructions corresponding to operation instructions used in the program.

[0051] Meanwhile, although FIG. 2 illustrates the first electronic device (201) as including one processor (220), this is merely exemplary and the technical concept of the present invention may not be limited thereto. For example, the first electronic device (201) may include at least one processor. For example, the processor (220) may be implemented as at least one processor.

[0052] According to one embodiment, the memory (230) (e.g., the memory (130) of FIG. 1) may store at least one command (or instruction) that causes at least one operation of the first electronic device (201). The at least one instruction, when executed by the processor (220), may cause the first electronic device (201) to perform a corresponding operation.

[0053] According to one embodiment, the processor (220) may obtain first content to be displayed on the first electronic device (201) and second content to be displayed on the second electronic device (202) in response to a user's query. For example, the user's query may include content requesting content on a specific topic. For example, the user's query may include content requesting content (e.g., first content and second content) for the first electronic device (201) and the second electronic device (202) on a specific topic. Alternatively, the user's query may include content requesting content (e.g., first content and second content) for the user of the first electronic device (201) and the user of the second electronic device (202) on a specific topic. For example, the first content and the second content may include text, voice, images, and / or videos that are at least partially different on the same topic. For example, the first content may include text, voice, images, and / or video about a specific topic based on a user (e.g., the first user) assigned to the first electronic device (201) or device information of the first electronic device (201). The second content may include text, voice, images, and / or video about a specific topic based on a user (e.g., the second user) assigned to the second electronic device (202) or device information of the second electronic device (202).

[0054] According to one embodiment, the processor (220) may obtain a prompt for generating first content and second content based on a user's query, information about the first electronic device (201) (hereinafter, first information), and information about the second electronic device (202) (hereinafter, second information). For example, the processor (220) may obtain the prompt using a specified algorithm or artificial intelligence model. For example, the artificial intelligence (AI) model may be stored in the memory (230). Alternatively, the AI ​​model may be stored in an external electronic device (e.g., a server). For example, the AI ​​model may be an AI model (e.g., a large language model (LLM)) for generating and outputting a prompt based on the user's query, the first information, and the second information. For example, the AI ​​model may include an AI assistant.

[0055] According to one embodiment, the processor (220) may acquire first content and second content based on a prompt using a generative AI model. Thereafter, the first content may be displayed on the display (260), and the second content may be displayed on the display (261). At this time, the first content and the second content may be content related to the same type of information. For example, the first content may be content in a form suitable for the first electronic device (201) (or a user of the first electronic device). The second content may be content in a form suitable for the second electronic device (202) (or a user of the second electronic device).

[0056] According to another embodiment, the processor (220) may obtain content corresponding to a response to a user's query using the first AI model. For example, the processor (220) may analyze the user's query to generate a prompt for obtaining a response to the query, and provide the generated prompt to the first AI model to obtain corresponding content as a response to the query. The processor (220) may display the content through the display (260). In addition, the processor (220) may output the content as a voice through the speaker (240). For example, the content may include text, voice, image, and / or video. For example, the first content may include text, voice, image, and / or video about a specific topic based on a user (e.g., the first user) specified in the first electronic device (201) or device information of the first electronic device (201). According to one embodiment, an artificial intelligence (AI) model may be stored in memory (230). Alternatively, the AI ​​model may be stored in an external electronic device (e.g., a server). For example, the AI ​​model may be an AI model (e.g., a large language model (LLM)) for generating and outputting a response to a user's query. For example, the AI ​​model may include an AI assistant.

[0057] According to one embodiment, the processor (220) may verify a user's query based on user input. For example, the user input may include a touch input on a display (e.g., a touchscreen) (260), an input using an input device (e.g., a keyboard and / or mouse), or a voice input received through a microphone (210). Alternatively, the user input may be obtained through various input devices included in or connected to the first electronic device (201).

[0058] According to one embodiment, the processor (220) may analyze the identified query. For example, the processor (220) may analyze the intent or purpose of the query, the nuance of the query, and the user who made the query. For example, the processor (220) may analyze the user's query using a query analysis module (e.g., the query analysis module (310) of FIG. 3). For example, the query may include content that causes at least some of the information contained in content on a specific topic (e.g., general information on the specific topic) to be output differently from the first electronic device (201) and the second electronic device (202).

[0059] According to one embodiment, the processor (220) may obtain or confirm a prompt based on the result of analyzing the query. For example, the processor (220) may provide the result of analyzing the query to a prompt generation module (e.g., the prompt generation module (320) of FIG. 3). The prompt generation module (320) may generate or output a prompt for generating the first content and the second content based on the result of analyzing the query. According to one embodiment, the processor (220) (e.g., the prompt generation module (320)) may consider first information (e.g., device information and / or user information of the first electronic device (201)) and second information (e.g., device information and / or user information of the second electronic device (202)) when generating the prompt.

[0060] According to one embodiment, the processor (220) may store and manage first information about the first electronic device (202) (e.g., device information of the first electronic device (202) and / or information of a first user designated for the first electronic device (202)) in the memory (230). For example, the first user may represent a user who uses (e.g., currently uses) the first electronic device (201). For example, the first user may be at least one user pre-registered in the first electronic device (201). For example, the information of the first user may include at least one of the first user's role, age, gender, or preference.

[0061] According to one embodiment, the processor (220) may be communicatively connected to the second electronic device (202) via the communication circuit (290). The processor (220) may transmit and receive information (e.g., data) with the second electronic device (202). For example, the processor (220) may obtain second information about the second electronic device (202) from the second electronic device (202) (e.g., device information of the second electronic device (202) and / or user information specified in the second electronic device (202). The processor (220) may store and manage the second information about the second electronic device (202) (e.g., device information of the second electronic device (202) and / or user information specified in the second electronic device (202)) in the memory (230). For example, the second user may represent a user who uses (e.g., currently uses) the second electronic device (202). For example, the second user may be at least one user pre-registered in the second electronic device (202). The second user's information may include at least one of the second user's role, age, gender, or preference.

[0062] According to one embodiment, the processor (220) may obtain personal information (or personalized information) associated with a user (or the user's use) from the first electronic device (201) and / or the second electronic device (202), and may also directly or indirectly receive personal information associated with the user (or the user's use) from at least one external electronic device. For example, the processor (220) may receive personal information by directly establishing a communication connection with the external electronic device. Alternatively, the processor (220) may receive personal information through a server based on the user's account information.

[0063] According to one embodiment, the processor (220) may generate or obtain first content and second content based on a result of analyzing a query (e.g., a prompt), first information (e.g., device information and / or user information of a first electronic device), and second information (e.g., device information and / or user information of a second electronic device) using a generative AI model (e.g., the generative AI model (330) of FIG. 3). For example, the processor (220) may use the generative AI model (330) to modify, edit, or add information included in content (e.g., general content on a specific topic related to a query) so that it is output from the first electronic device (201) and the second electronic device (202) according to the intent of the query. For example, the first content may be content that has been modified, edited, or added to such that information included in the content (e.g., general content on a specific topic related to a query) is output from the first electronic device (201) in accordance with the intent of the query. The second content may be content that has been modified, edited, or added to such that information included in the content (e.g., general content on a specific topic related to a query) is output from the first electronic device (201) in accordance with the intent of the query. For example, at least a portion of the first content may be the same as or different from at least a portion of the second content. For example, the first content may be output or displayed on the first electronic device (201), and the second content may be output or displayed on the second electronic device (202). For example, the second content may be output or displayed on the second electronic device (202) based on the first content being output or displayed on the first electronic device (201).

[0064] In another embodiment, the processor (220) may use the generative AI model (330) to change, edit, or add information contained in content (e.g., general content on a specific topic related to a query) obtained through the AI ​​model based on a user (hereinafter, referred to as the first user) designated for the first electronic device (201). The processor (220) may use the generative AI model (330) to change or edit information contained in content (e.g., content related to a query) based on a user (hereinafter, referred to as the second user) designated for the second electronic device (202). For example, the first user may be the same as or different from the second user. To this end, the processor (220) may generate an additional prompt for editing the content based on information about the first user and information about the second user. For example, when a first user is different from a second user, the first user may have at least one different role, gender, age, or preference from the second user. For example, the first content may be content in which at least a portion of the information contained therein is modified, edited, or created based on the first user. The second content may be content in which at least a portion of the information contained therein is modified, edited, or created based on the second user.

[0065] According to one embodiment, the processor (220) may utilize the history (e.g., usage history) of a user (e.g., the first user and / or the second user) when generating prompts for the first content and the second content. For example, the user's usage history may be stored, classified, analyzed, and stored according to specified conditions, and the processor (220) may use the history to provide personalized services. For example, the user's usage history may be composed of data by specific category or task among the user's conversations. For example, the user's usage history may include data for which the user has asked an AI model questions or requested the AI ​​model to generate questions on topics such as "2024 summer vacation plans" or "preparing a daughter's birthday party." As another example, the user's usage history may include data such as the user's preference information. For example, if the user likes cats, the processor (220) may store the corresponding related data. Thereafter, when a user requests the AI ​​model to “draw a picture with an animal,” the processor (220) may provide the AI ​​model with pre-stored related data to generate or output an image of the user and a cat together. In addition, when the user prefers a specific type of design, the processor (220) may store the preference for the design. Thereafter, when the user requests the AI ​​model to generate a related image, the processor (220) may provide the AI ​​model with the preference for the design to generate an output related to the related design. Such data related to the user’s usage history may be stored for a specific period of time. Depending on the implementation, the data related to the user’s usage history may be automatically deleted after a specific period of time or may be modified or deleted at the user’s request.

[0066] According to one embodiment, the processor (220) may generate first content based on device information (hereinafter, “first device information”) of the first electronic device (201) using the generative AI model (330). For example, the first device information may include information on at least one of the type, performance, remaining battery power, whether activated, or screen size (e.g., the size and ratio of the first display (260)) of the first electronic device (201). The processor (220) may generate second content based on device information (hereinafter, “second device information”) of the second electronic device (202) using the generative AI model (330). For example, the second device information may include information on at least one of the type, performance, remaining battery power, whether activated, or screen size (e.g., the size and ratio of the second display (262)) of the second electronic device (201). For example, the first device information may be the same as or different from the second device information. For example, the first content may be content in which at least a portion of the information included in the content (e.g., general content on a specific topic related to the query) is modified, edited, or added based on the first device information. The second content may be content in which at least a portion of the information included in the content (e.g., general content on a specific topic related to the query) is modified, edited, or added based on the second device information. Depending on the implementation, the first content and the second content may not be limited to being modified, edited, or added from a single content according to each electronic device (201 or 202) (or the user of each electronic device), and the first content and the second content may also be generated based on different content according to the characteristics of each electronic device (201 or 202) and / or the user of each electronic device (201 or 202).

[0067] According to one embodiment, the processor (220) may display the first content on the first display (260) in response to the query. Furthermore, the processor (220) may transmit information about the second content to the second electronic device (202) via the communication circuit (290) in response to the query so that the second electronic device (202) outputs the second content. For example, the information about the second content may include data for outputting (e.g., displaying or voice outputting) the second content and / or a command for outputting the second content. Meanwhile, the content output by the first electronic device (201) or the second electronic device (202) may not be limited to the first content and the second content, and for example, the second content or at least a part of the second content may be displayed on the first electronic device (201).

[0068] According to one embodiment, the processor (220) may generate a prompt for the generative AI model (330) to generate first content and second content. For example, the processor (220) may obtain a prompt for generating the first content and the second content based on information about a query (e.g., information about a result of analyzing the query), first information related to a first electronic device (e.g., information about the first device and / or information about the first user), and second information related to a second electronic device (e.g., information about the second device and / or information about the second user). Depending on the implementation, the first information and / or the second information may be generated based on profile information determined by an existing user or a policy. For example, the profile information may include policy information (e.g., a security policy, a protection policy, and / or an age policy). For example, the second information may be configured to set a profile so that content modified for minors can be displayed on all electronic devices connected to the first electronic device (201). In this case, the second information may include information that can generate content for minors.

[0069] According to one embodiment, the processor (220) may generate a prompt using a prompt generation model (e.g., the prompt generation model (320) of FIG. 3). For example, the prompt may include a command (e.g., text) for modifying, editing, or generating first content and second content based on the results of analyzing the user's query, first information, and second information. For example, the prompt may include a command for modifying, editing, adding, or generating content included in the content (e.g., text, images, and / or videos) to suit the electronic device or the user.

[0070] In one embodiment, the prompt may include a plurality of texts. For example, the plurality of texts may include a first text for transforming information contained in content related to the query based on first device information and / or a first user. For example, the plurality of texts may include a second text for transforming information contained in content related to the query based on second device information and / or a second user.

[0071] According to one embodiment, the processor (220) may obtain first content and second content by providing prompts and content to the generative AI model (330). For example, the generative AI model (330) may be stored in the memory (230) or stored in an external device (e.g., a server).

[0072] According to one embodiment, the second electronic device (202) may include a processor (222), a memory (232), a speaker (242), a display (262), and a communication circuit (292). For example, the second electronic device (202) may be an electronic device of the same or different type as the first electronic device (201). For example, the second electronic device (202) may be implemented in the same or similar manner as the electronic device (101) of FIG. 1.

[0073] According to one embodiment, the processor (222) may control the overall operation of the second electronic device (202). For example, the processor (222) may be implemented identically or similarly to the processor (120) of FIG. 1.

[0074] According to one embodiment, the processor (222) may receive information about second content from the first electronic device (201) via the communication circuit (292). The processor (222) may store the information about the second content in the memory (232).

[0075] According to one embodiment, the processor (222) may output second content via the speaker (242) and / or the display (262) based on receiving information about the second content. For example, the second content may include text, voice, images, and / or video about a specific topic based on device information of the second user or the second electronic device.

[0076] According to one embodiment, the processor (222) may transmit status information regarding the output of the second content to the first electronic device (201) while outputting the second content. In addition, the processor (220) may adjust the output order of the second content based on a synchronization signal received from the first electronic device (201) while outputting the second content.

[0077] FIG. 3 is a diagram for explaining an operation of obtaining first content and second content using a generative AI model according to one embodiment.

[0078] Referring to FIG. 3, according to one embodiment, the first electronic device (201) may include or store a query analysis module (310), a prompt generation module (320), and a generative AI model (330).

[0079] According to one embodiment, the query analysis module (310) and the prompt generation module (320) may be implemented as software. For example, at least a portion of the query analysis module (310) and the prompt generation module (320) may be implemented as an artificial intelligence (AI) model. For example, the AI ​​model may include an AI model based on machine learning (ML). In addition, the generative AI model (330) may also include an AI model based on machine learning (ML).

[0080] According to one embodiment, the query analysis module (310) may analyze a user's query and provide or output information about the analysis results to the prompt generation module (320). For example, the query analysis module (310) may analyze the intent or purpose of the query, the nuance of the query, and the user who made the query. Information about the query analysis results may include information about the analyzed results as described above.

[0081] According to one embodiment, the prompt generation module (320) may generate a prompt based on information about the analysis result, device information (e.g., first device information and / or second device information), and user information (e.g., information about the first user and / or information about the second user). Depending on the implementation, a single prompt or multiple prompts may be generated. For example, the prompt may include a command (e.g., text) for modifying, editing, or generating content related to the query based on a specific electronic device or a specific user using a generative AI model. For example, the prompt may include a command (e.g., text) for the generative AI model to generate first content and second content related to the query. The prompt generation module (320) may provide or output the generated prompt to the generative AI model (330).

[0082] According to one embodiment, user information (e.g., information about a first user and / or information about a second user) may include personal information (or personalized information) and information about a user's history. Depending on the implementation, the user information may further include device information (e.g., device information of the corresponding user). The first electronic device (201) may perform operations for managing, storing, deleting, and / or updating each piece of information. For example, the first electronic device (201) may preserve, delete, or update each piece of information when a specified period of time has elapsed. In addition, the first electronic device (201) may update the usage history of each piece of information to the user information when generating a prompt through the prompt generation module (320).

[0083] According to one embodiment, the generative AI model (330) may generate first content and second content based on a prompt using at least one artificial intelligence (AI) model (e.g., a large language model (LLM)). For example, the generative AI model (330) may be stored in memory (230) or an external device (e.g., a server).

[0084] According to one embodiment, the generative AI model (330) can newly generate (or obtain, output) similar content (e.g., first content and second content) to content such as text, audio, images, and / or video (e.g., content including general information) about a specific topic related to a user's query. For example, the generative AI model (330) can learn patterns of content and generate (or obtain, output) new content as an inference result. For example, the generative AI model (330) can generate new content (e.g., first content and second content) by including at least some of the information included in the content (e.g., general information about a specific topic) or newly generating at least some of the information. For example, the generative AI model (330) can generate (or obtain, output) new text based on text included in content about a specific topic. Depending on the implementation, the generative AI model (330) may generate (or acquire, output) new audio, images, and / or videos based on audio, images, and / or videos included in content on a specific topic. Alternatively, the generative AI model (330) may extract (or select) some information from existing content in a form suitable for the corresponding electronic device (or user), and place the extracted information based on the corresponding electronic device (or user).

[0085] According to one embodiment, the generative AI model (330) may generate or obtain first content corresponding to a first electronic device (201) (or a first user) and second content corresponding to a second electronic device (202) (or a second user) based on being provided (or input) with a prompt. Thereafter, the first content may be output (e.g., displayed) by the first electronic device (201). The second content may be provided to the second electronic device (202) to be output (e.g., displayed) by the second electronic device (202).

[0086] Through the above-described method, the first electronic device (201) can obtain first content and second content, in which general content on a specific topic is transformed, edited, or added to a form suitable for output by each of the specific electronic devices, using the generative AI model (330). In addition, the first electronic device (201) can obtain second content, in which general content on a specific topic is transformed, edited, or added to a form suitable for providing to each of the specific users, using the generative AI model (330). The first electronic device (201) can display the first content, and transmit or provide the second content to another electronic device (e.g., the second electronic device (202)). For example, when at least one user uses multiple electronic devices in the same space to check information on the same topic (e.g., a topic related to the user's query), the first electronic device (201) can provide content in a form suitable for the device's properties (e.g., device information) or the user of the device. Through this, the usability of the first electronic device (201) can be increased when at least one user uses multiple electronic devices in the same space to check information on the same topic (e.g., the topic of the user's inquiry).

[0087] At least some of the operations of the first electronic device (201) described below may be performed by the processor (220) and / or the generative AI model (330). However, for convenience of explanation, the operations below will be described as being performed by the first electronic device (201).

[0088] FIG. 4A is a flowchart illustrating an operation of a first electronic device obtaining first content and second content using a generative AI model according to one embodiment.

[0089] Referring to FIG. 4A, according to an embodiment, in operation 401, a first electronic device (e.g., the first electronic device (201) of FIG. 2) may connect to a second electronic device (e.g., the second electronic device (202) of FIG. 2) via a communication circuit (e.g., the communication circuit (290) of FIG. 2) using a wireless communication technology (or a wired communication technology). The first electronic device (201) may obtain information about the second electronic device (202) (hereinafter, second information) (e.g., second device information and / or information about a second user). In addition, the first electronic device (201) may confirm information about the first electronic device (201) (hereinafter, first information) (e.g., first device information and / or information about a first user).

[0090] According to one embodiment, in operation 402, the first electronic device (201) may obtain or confirm a user's query through a first display (e.g., display (260) of FIG. 2) or a microphone (e.g., microphone (210) of FIG. 2). Depending on the implementation, the first electronic device (201) may also obtain or confirm the user's query through at least one input device (e.g., keyboard, microphone, mouse, controller, and / or sensing device) connected to the first electronic device (201). For example, the first electronic device (201) may obtain a query based on text input by the user. Alternatively, the first electronic device (201) may obtain a query based on the user's voice.

[0091] According to one embodiment, in operation 403, the first electronic device (201) may generate a prompt based on the query, the first information, and the second information. For example, the first electronic device (201) may generate the prompt using a specified algorithm or artificial intelligence model. For example, the prompt may be a prompt for generating first content and second content, and may include a command (e.g., a text prompt) for generating the first content and the second content.

[0092] According to one embodiment, in operation 404, the first electronic device (201) may obtain first content and second content based on the prompt using a generative AI model.

[0093] According to one embodiment, in operation 405, the first electronic device (201) may display the first content on the first display (260) and transmit information about the second content to the second electronic device (202). The second electronic device (202) may display the second content based on the information about the second content.

[0094] According to the above-described method, the first electronic device (201) may obtain a prompt for generating a plurality of contents (e.g., first content and second content) to be displayed on a plurality of different electronic devices (e.g., 201, 202) based on a user's query, and may generate or obtain the first content and the second content having a form suitable for providing to a specific electronic device or a specific user using the generative AI model (330). In addition, the first electronic device (201) may enable the second electronic device (202) to display or output the second content having a form suitable for providing to the second electronic device (202) or the user of the second electronic device (202).

[0095] FIG. 4b is a flowchart illustrating an operation of a first electronic device obtaining first content and second content using a generative AI model according to one embodiment.

[0096] Referring to FIG. 4b, according to one embodiment, operations 411 and 412 may be implemented identically to operations 401 and 402 of FIG. 4a.

[0097] According to one embodiment, in operation 413, the first electronic device (201) may obtain content on a specific topic related to the query using a first AI model (e.g., an AI model for obtaining general content on a specific topic related to the user's query). In this case, the content may represent general content on the specific topic related to the query. For example, the content may include at least one of text, voice, image, or video related to the query (or a topic related to a response to the query).

[0098] According to one embodiment, in operation 414, the first electronic device (201) may generate at least one prompt for transforming content (e.g., general content on a specific topic related to the query) based on information about the query, first information related to the first electronic device (201), and second information related to the second electronic device (202). For example, if the user's query is about "spaghetti recipes," the content may include text, images, and / or videos related to "spaghetti recipes" in general. In this case, the at least one prompt may include a command (e.g., a text prompt) for transforming the content to fit the first information and the second information.

[0099] According to one embodiment, in operation 415, the first electronic device (201) may obtain first content and second content by providing at least one prompt and content to a generative AI model (e.g., the generative AI model (330) of FIG. 3). For example, if the generative AI model (330) is stored in the memory (230), the first electronic device (201) may input at least one prompt and / or content into the generative AI model (330) to obtain the first content and / or second content. Alternatively, if the generative AI model (330) is stored in an external device (e.g., a server), the first electronic device (201) may transmit at least one prompt and / or content to the external device (or the generative AI model (330) stored in the external device) and obtain the first content and the second content from the external device. Depending on the implementation, the first electronic device (201) may transmit a specific prompt and / or content among at least one prompt to the second electronic device (202). The second electronic device (202) may obtain second content based on the received specific prompt and content. Alternatively, the first electronic device (201) may transmit a specific prompt and / or content among at least one prompt to an external device (e.g., a server). The external device (e.g., the server) may obtain second content based on the received specific prompt and content. Thereafter, the second electronic device (202) may obtain the second content from the external device (e.g., the server).

[0100] According to one embodiment, in operation 416, the first electronic device (201) may, in response to the query, display the first content on the first display (260) and transmit information about the second content to the second electronic device (202) via the communication circuit (290). At this time, the second electronic device (202) may display the second content on the display (262) in response to receiving the information about the second content. According to an implementation, if the first content includes voice, the first electronic device (201) may output the first content through a speaker (e.g., the speaker (240) of FIG. 2). Additionally, if the second content includes voice, the second electronic device (202) may output the second content through a speaker (e.g., the speaker (242) of FIG. 2). For example, when the second electronic device (202) is a wireless earphone (e.g., a TWS device), the second electronic device (202) can output voice included in the second content. Or, when the second electronic device (202) is an HMD device or smart glasses, the second electronic device (202) can output text, images, and / or videos included in the second content.

[0101] According to the above-described method, the first electronic device (201) can obtain content corresponding to a response to a user query using the first AI model, and can transform, edit, or generate the obtained content into a form suitable for providing to a specific user using the generative AI model (330). The first electronic device (201) can display the transformed, edited, or generated first content, and transmit or provide the transformed, edited, or generated second content to another electronic device (e.g., the second electronic device (202)). For example, when at least one user uses multiple electronic devices in the same space to check information on the same topic (e.g., a topic related to the user's query), the first electronic device (201) can provide content transformed into a form suitable for the device's properties (e.g., device information) or the user of the device. Through this, the usability of the first electronic device (201) and the second electronic device (202) can be increased when at least one user uses multiple electronic devices in the same space to check information on the same topic (e.g., the topic of the user's inquiry).

[0102] FIG. 4c is a flowchart illustrating an operation of a first electronic device obtaining first content based on a first prompt and second content based on a second prompt using a generative AI model according to one embodiment.

[0103] Referring to FIG. 4c, according to one embodiment, operations 421 and 423 may be implemented identically to operations 401 and 402 of FIG. 4a.

[0104] According to one embodiment, in operation 425, the first electronic device (201) may generate a first prompt and a second prompt based on the query, the first information, and the second information. For example, the first electronic device (201) may generate the first prompt and the second prompt using a specified algorithm or artificial intelligence model. For example, the first prompt may be a prompt for generating a first content and may include a command (e.g., a text prompt) for generating the first content. For example, the second prompt may be a prompt for generating a second content and may include a command (e.g., a text prompt) for generating the second content.

[0105] According to one embodiment, in operation 427, the first electronic device (201) may obtain first content based on the first prompt and obtain second content based on the second prompt using the generative AI model.

[0106] According to one embodiment, in operation 429, the first electronic device (201) may display the first content on the first display (260) and transmit information about the second content to the second electronic device (202). The second electronic device (202) may display the second content based on the information about the second content.

[0107] According to the above-described method, the first electronic device (201) can obtain the first prompt and the second prompt based on the user's query, and can generate or obtain the first content and the second content in a form suitable for providing to a specific electronic device or a specific user using the generative AI model (330). In addition, the first electronic device (201) can enable the second electronic device (202) to display or output the second content in a form suitable for providing to the second electronic device (202) or the user of the second electronic device (202).

[0108] FIG. 4D is a flowchart illustrating an operation in which a first electronic device acquires first content using a generative AI model and transmits a second prompt to a second electronic device to acquire second content, according to one embodiment.

[0109] Referring to FIG. 4d, according to one embodiment, operations 451 and 453 may be implemented identically to operations 401 and 402 of FIG. 4a.

[0110] According to one embodiment, in operation 455, the first electronic device (201) may generate a first prompt and a second prompt based on the query, the first information, and the second information. For example, the first electronic device (201) may generate the first prompt and the second prompt using a specified algorithm or artificial intelligence model. For example, the first prompt may be a prompt for generating a first content and may include a command (e.g., a text prompt) for generating the first content. For example, the second prompt may be a prompt for generating a second content and may include a command (e.g., a text prompt) for generating the second content.

[0111] According to one embodiment, in operation 457, the first electronic device (201) may obtain first content based on the first prompt using a generative AI model.

[0112] According to one embodiment, in operation 459, the first electronic device (201) may transmit a second prompt to the second electronic device (202) so that the second electronic device (202) generates second content. The second electronic device (202) may generate or obtain the second content based on the second prompt. At this time, the second electronic device (202) may utilize a generative AI model.

[0113] According to one embodiment, in operation 461, the first electronic device (201) may display first content on the first display (260). The second content may be displayed by the second electronic device (202).

[0114] According to the method described above, the first electronic device (201) can obtain the first prompt and the second prompt based on the user's query, and transmit the second prompt to the second electronic device (202) so that the second electronic device (202) can obtain the second content. Through this, the first electronic device (201) can enable the second electronic device (202) to display or output the second content in a form suitable for providing to the second electronic device (202) or the user of the second electronic device (202).

[0115] Meanwhile, although examples of two electronic devices (201 and 202) are described in FIGS. 4A to 4D , the technical concept of the present invention may not be limited thereto. For example, the number of electronic devices is not limited to the first electronic device (201) and the second electronic device (202), and may be expanded to multiple electronic devices depending on the user. For example, the first electronic device (201) may be further connected to a third electronic device and / or a fourth electronic device, and third content and / or fourth content may be further generated.

[0116] Meanwhile, for convenience of explanation, the following description will focus on the embodiment of FIG. 4a to explain how each electronic device displays the first content and the second content. However, the embodiments of FIGS. 4b, 4c, and 4d can also display the first content and the second content by each electronic device in the same or similar manner.

[0117] FIG. 5A is a diagram for explaining an operation of a first electronic device outputting first content and second content based on a query according to one embodiment.

[0118] Referring to FIG. 5A, according to one embodiment, a first electronic device (520) (e.g., the first electronic device (201) of FIG. 2) may confirm a user's inquiry (510) through a microphone (e.g., the microphone (210) of FIG. 2). However, this is an example, and the first electronic device (520) may also confirm the user's inquiry (510) through a touchscreen (e.g., the display (260) of FIG. 2) or another input device.

[0119] According to one embodiment, the first electronic device (520) may generate or obtain a prompt based on information about a query (e.g., a query analysis result), first information related to the first electronic device (520) (e.g., first device information and / or information about the first user), and second information related to the second electronic device (530) (e.g., second device information and / or information about the second user). For example, the first electronic device (520) may identify at least one external electronic device in close proximity and receive information about the external electronic device and user information (e.g., personal information) of the external electronic device. For example, if the user's query includes information about the electronic device of the other party or user information of the other party, the corresponding operation may be omitted.

[0120] Additionally, depending on the implementation, the first electronic device (520) may obtain general content (e.g., a spaghetti recipe) corresponding to a response to a query. At this time, the first electronic device (520) may analyze the query and generate a prompt for obtaining content corresponding to the response. However, according to various embodiments, the operation of obtaining the general content may be omitted. At this time, the prompt may include a command (e.g., a text prompt) for generating first content to be displayed (or suitable) on the first electronic device (520) and second content to be displayed (or suitable) on the second electronic device (530) using a generative AI model. For example, the first electronic device (520) may analyze the query to generate a prompt for obtaining a response, and provide the generated prompt to the AI ​​model to obtain corresponding content (e.g., the first content and the second content) as a response to the query.

[0121] According to one embodiment, the first electronic device (520) may obtain first content (525) and second content (535) by providing a prompt to a generative AI model (e.g., the generative AI model (330) of FIG. 3). In this case, the first content (525) and the second content (535) may be responses to a user's query. According to another embodiment, the first electronic device (520) may obtain first content (525) and second content (535) by providing a prompt and content to a generative AI model (e.g., the generative AI model (330) of FIG. 3). For example, the first content may be content in which information included in the content is modified, edited, or generated based on the first user (e.g., the first user's role, age, gender, and / or preferences). The second content may be content that is modified, edited, or generated based on information included in the content about a second user (e.g., the role, age, gender, and / or preferences of the first user). In response to a query, the first electronic device (520) may display the first content on a first display (e.g., the display (260) of FIG. 2) and transmit information about the second content to the second electronic device (530) via a communication circuit (e.g., the communication circuit (290) of FIG. 2). Depending on the implementation, the first electronic device (520) may display the second content on the first display (260) before transmitting the second content. Thereafter, when an input corresponding to the user's confirmation is confirmed, the first electronic device (520) may transmit the second content to the second electronic device (530).

[0122] According to one embodiment, the first electronic device (520) may display first content (525) on the first display (260). The second electronic device (530) may display second content (535) on the second display (e.g., display (262) of FIG. 2). For example, the first content (525) may include text that has been modified, edited, or added based on the first user (e.g., adult or mother) compared to general content related to the query (e.g., spaghetti recipe). The second content (535) may include text and images that have been modified, edited, or added based on the second user (e.g., child or child) compared to general content (e.g., spaghetti recipe). For example, the first content (525) may include information corresponding to the role or age of the first user (e.g., parent or adult). The second content (535) may include information corresponding to the role or age (e.g., child or young child) of the second user. For example, the first content (525) may include texts corresponding to the role or age (e.g., parent or adult) of the first user (e.g., spaghetti recipe that a mother can make), and the second content (535) may include texts corresponding to the role or age (e.g., child or young child) of the second user (e.g., spaghetti recipe that a child can make). For example, if the first user is an adult and the second user is a young child, the second content (535) may include more images (or videos) than the first content (525). Depending on the implementation, the first content (525) may include content corresponding to the preferences of the first user (e.g., text preference, image preference, or video preference), and the second content (535) may include content corresponding to the preferences of the second user (e.g., text preference, image preference, or video preference).Additionally, based on the preference, content corresponding to the preference may be included more in the first content or second content for the user.

[0123] FIG. 5B is a diagram of a prompt generated by a first electronic device to obtain first content and second content, according to one embodiment.

[0124] Referring to FIG. 5B, according to one embodiment, a first electronic device (e.g., first electronic device (520) of FIG. 5A) may generate a prompt (560) to obtain first content (e.g., first content (525) of FIG. 5A) and second content (e.g., second content (535) of FIG. 5A). For example, the first electronic device (520) may generate a prompt based on a user's query (e.g., information about the query (510) of FIG. 5A), first information related to the first electronic device (520) (e.g., first device information and / or information about the first user), and second information related to the second electronic device (530) (e.g., second device information and / or information about the second user). For example, when the user's query includes device information and / or user information, the first electronic device (520) may generate a prompt based on the corresponding information. Alternatively, when the user's query does not include some of the device information or user information, the first electronic device (520) may obtain the remaining information using the given information. For example, when the user's query includes content about "smartphone" and "tablet," the first electronic device (520) may check the user information of the "smartphone" and the "tablet" and determine the user of the "smartphone." The user of the “tablet” can be identified as “child”. Alternatively, for example, if the user’s query includes “mother” and “child”, the first electronic device (520) can identify the device information of the “mother” and the “child”, identify the electronic device of the “mother” as a “smartphone”, and identify the electronic device of the “child” as a “tablet”. For example, if the device of the corresponding user is pre-registered, the first electronic device (201) can identify the device information thereof. Alternatively, if the device of the corresponding user is not pre-registered, the first electronic device (201) can search for (in-use) external electronic devices around the first electronic device (201) to identify the device information.

[0125] Based on the above-described method, the first electronic device (201) can generate or obtain a prompt.

[0126] In one embodiment, the first electronic device (201) may generate a prompt to cause the second content to include more images than the first content based on determining that the first user is an adult and the second user is a child. The first electronic device (201) may generate a prompt to cause the second content to include more images than the first content based on determining that the first user prefers text and the second user prefers images. The first electronic device (201) may generate a prompt to cause the first content to include information corresponding to the first role and the second content to include information corresponding to the second role based on determining that the first user has a first role (e.g., parent) and the second user has a second role (e.g., child). The first electronic device (201) may generate a prompt such that the first content includes information corresponding to the age of the first user and the second content includes information corresponding to the age of the second user based on verifying the age of the first user (e.g., adult) and the age of the second user (e.g., child). The first electronic device (201) may generate a prompt such that the first content includes information corresponding to the gender of the first user and the second content includes information corresponding to the gender of the second user based on verifying the gender of the first user (e.g., male) and the gender of the second user (e.g., female). In addition, the first electronic device (201) may generate the prompt by considering at least one of the attributes of the first user described above (role, age, gender, and preference).

[0127] In one embodiment, the prompt (560) may include a plurality of texts. For example, the plurality of texts may include text related to the query (565 and 567), text for the first information (561), and text for the second information (563).

[0128] According to one embodiment, the plurality of texts may include a first text (568) for generating (or modifying) information included in the general content (e.g., a spaghetti recipe) based on a first user, and a second text (569) for generating (or modifying) information included in the general content based on a second user. Alternatively, the plurality of texts may include a first text for generating (or modifying) information included in the general content (e.g., a spaghetti recipe) based on first device information, and a second text for modifying information included in the general content based on second device information.

[0129] FIG. 5c is a diagram illustrating first content modified based on a first user and second content modified based on a second user, according to one embodiment.

[0130] Referring to FIG. 5c, at least some of the descriptions below may be operations performed internally by the electronic device (201) when generating the first content (525) and the second content (535). For example, the content (515) may not be generated by the electronic device (201) and may not be displayed to the user. However, depending on the implementation, the content (515) may also be generated internally by the electronic device (201).

[0131] According to one embodiment, the electronic device (201) may generate first content (525) and second content (535) corresponding to content and form (or layout) suitable for the first electronic device (520) and the second electronic device (530), which are different from content (515) including general information (e.g., a general spaghetti recipe). The first content (525) and the second content (535) may be obtained based on a prompt corresponding to a result of analyzing a user's query. For example, the content (515) may include a plurality of texts (571, 572, 573, 574, 576, 577, 578, 579) and at least one image (575). In another embodiment, a first electronic device (e.g., electronic device 201 or 501 of FIG. 2 or FIG. 5A ) may obtain content (515) corresponding to a response to a query (e.g., a spaghetti recipe) using an AI model (e.g., an LLM). For example, the content (515) may be obtained based on a prompt corresponding to a result of analyzing the query. For example, the content (515) may be content corresponding to a general response to a user's query (e.g., a general spaghetti recipe).

[0132] According to one embodiment, the first electronic device (201) may generate or obtain the first content (525) and the second content (535) based on a prompt for generating content in a form suitable for each electronic device. According to another embodiment, the first electronic device (201) may also generate or obtain the first content (525) and the second content (535) based on a prompt for regenerating the content (515) to suit each electronic device. For example, the first content (525) may be content specialized for the first electronic device (201) and / or a user of the first electronic device (201), such as a specialized spaghetti recipe. Additionally, the second content (535) may be content specialized for the second electronic device (202) and / or a user of the second electronic device (202), such as a specialized spaghetti recipe. For example, the first electronic device (201) can use the generative AI model (330) to generate or acquire the first content (525) and the second content (535). For example, the first electronic device (201) can generate or acquire the first content (525) by using some of the information (571, 572, 573, and 574) included in the content (515). The first electronic device (201) can generate or acquire the first content (525) by using some of the information (576, 577, 578, and 579) included in the content (515).

[0133] According to one embodiment, the first content (525) and the second content (535) may be generated or acquired based on device information of the corresponding electronic device. For example, the first content (525) (or information included in the first content) may be arranged based on a first layout corresponding to the size and ratio of the display of the first electronic device (201) (e.g., the display (260) of FIG. 2). The second content (535) (or information included in the second content) may be arranged based on a second layout corresponding to the size and ratio of the display of the second electronic device (202) (e.g., the display (262) of FIG. 2).

[0134] Meanwhile, although FIGS. 5A to 5C illustrate that the first electronic device (520) obtains or generates the prompt (560), the first content (525), and the second content (535), the present invention may not be limited thereto. For example, instead of the first electronic device (520), the second electronic device (530) may obtain or generate at least one of the prompt (560), the first content (525), and the second content (535). Alternatively, instead of the first electronic device (520), an external electronic device (e.g., a server) may obtain or generate at least one of the prompt (560), the first content (525), and the second content (535). In this case, the second electronic device (202) may obtain at least one of the prompt (560) and the second content (535) from the external electronic device (e.g., a server).

[0135] FIG. 6 is a diagram for explaining first content based on a first user and second content based on a second user, according to one embodiment.

[0136] Referring to FIG. 6, according to an embodiment, a first electronic device (201) may display first content (620) regarding a specific topic (e.g., a spaghetti recipe) related to a user's query. A second electronic device (202) may display second content (630) regarding a specific topic (e.g., a spaghetti recipe) related to the user's query. For example, the first content (620) and the second content (630) may include different content regarding the same specific topic by taking into account at least one of the user's role, age, gender, or preference. Additionally, the first content (620) and the second content (630) may include different content regarding the same specific topic by taking into account a task.

[0137] In one embodiment, the first content (620) may include information corresponding to the role or age of the first user (e.g., parent or adult). The second content (630) may include information corresponding to the role or age of the second user (e.g., child or young child). For example, the information included in the first content (620) may be different from the information included in the second content (630). For example, some content included in the second content (630) (e.g., content about cutting sausages with a knife or scissors) may be different from the first content (620). Depending on the implementation, some content (e.g., content about cutting sausages with a knife or scissors) may be excluded from the second content (630).

[0138] In one embodiment, the first content (620) may include texts corresponding to a role or age of the first user (e.g., parent or adult) (e.g., a spaghetti recipe that a mom can make), and the second content (630) may include texts corresponding to a role or age of the second user (e.g., child or young child) (e.g., a spaghetti recipe that a child can make). For example, the first content (620) may include text (e.g., cut with a knife) for a spaghetti recipe that the first user (e.g., parent or young adult) can make. The text (e.g., cut with a knife) may not be included in the second content (630). On the other hand, the second content (630) may include text (e.g., cut with scissors or ask a parent for help) for a spaghetti recipe that the second user (e.g., child or young child) can make. The text (e.g., cut with scissors or ask your parents for help) may not be included in the first content (620).

[0139] Meanwhile, while FIG. 6 illustrates that information contained in the first content may differ from information contained in the second content based on the user's role or age, the present invention may not be limited thereto. For example, information contained in the first content may differ from information contained in the second content based on the user's gender or preferences.

[0140] FIG. 7A is a diagram illustrating an operation of a first electronic device outputting first content based on a first user and second content based on a second user based on a query, according to one embodiment. FIG. 7B is a diagram illustrating a prompt generated by the first electronic device to obtain first content and second content, according to one embodiment.

[0141] Referring to FIG. 7A, according to one embodiment, a first electronic device (201) (e.g., the first electronic device (201) of FIG. 2 ) may acquire or confirm a user's query (710) through a display (e.g., the display (260) of FIG. 2 , a touchscreen). For example, the query may be about "math problems" for "4th grade elementary school students." For example, first content (720) and second content (730) may include different content considering their roles for the same specific topic (e.g., 4th grade elementary school math problems).

[0142] According to one embodiment, the first electronic device (201) may obtain or generate first content (720) and second content (730) in response to a query using a generative AI model (e.g., the generative AI model (330) of FIG. 3).

[0143] In one embodiment, the first electronic device (201) may, in response to the query, display the first content (720) on the display (260) and transmit information about the second content (730) to the second electronic device (202) so that the second electronic device (202) displays the second content (730).

[0144] In one embodiment, the first content (720) may be generated based on a first user (e.g., the role of the first user), and the second content (730) may be generated based on a second user (e.g., the role of the second user). For example, the first user may be a parent or a teacher, and the second user may be a child or a student. The first content (720) may include information (e.g., text) about a math problem and its answer. The second content (730) may only include information (e.g., text) about the math problem.

[0145] Referring to FIG. 7B, according to one embodiment, the first electronic device (201) may obtain or generate a prompt (760) such that the first content (720) includes a math problem and an answer, and the second content (730) includes only a math problem, based on determining that the first user is a parent or teacher and the second user is a child or student.

[0146] In one embodiment, the prompt (760) may include a plurality of texts. The plurality of texts may include a first text (761) for the generative AI model (330) to obtain the first content (720) and a second text (765) for obtaining the second content (730). For example, the first text (761) may include a command (e.g., text) that causes the first content (720) to include a math problem and its solution. For example, the second text (765) may include a command (e.g., text) that causes the second content (730) to include only math problems.

[0147] Meanwhile, the mathematical problems described in FIGS. 7A and 7B are merely examples, and embodiments of the present invention may not be limited thereto. For example, more than one prompt may be generated, and depending on the implementation, multiple prompts may be generated. For example, the first electronic device (201) may generate first content and / or second content using multiple prompts.

[0148] FIGS. 8A and 8B are diagrams illustrating an operation of a first electronic device outputting first content based on device information of the first electronic device and second content based on device information of a second electronic device based on a query according to one embodiment. FIG. 8C is a diagram illustrating a prompt generated by the first electronic device to obtain first content and second content according to one embodiment.

[0149] Referring to FIGS. 8A and 8B , according to one embodiment, a first electronic device (201) (e.g., the first electronic device (201) of FIG. 2 ) may obtain or confirm a user's query (810) through a display (e.g., the display (260) of FIG. 2 , a touchscreen). For example, the query may be about "duck stew recipe."

[0150] According to one embodiment, the first electronic device (201) may obtain or generate first content (820) and second content (830) in response to a query using a generative AI model (e.g., the generative AI model (330) of FIG. 3).

[0151] According to one embodiment, the first electronic device (201) may, in response to at least one query, display the first content (820) on the display (260) and transmit information about the second content (830) to the second electronic device (202) so that the second electronic device (202) displays the second content (830). For example, the first electronic device (201) may cause the second electronic device (202) to display the second content (830) via an external electronic device (e.g., a server). For example, when the first electronic device (201) transmits the second content (830) to the external electronic device (e.g., a server), the second electronic device (202) may obtain the second content from the external electronic device (e.g., the server).

[0152] According to one embodiment, the first content (820) may be generated based on first device information of the first electronic device (201) (e.g., type, performance, display size and ratio, activation state, and / or battery state of the first electronic device (201), and the second content (830) may be generated based on second device information of the second electronic device (202) (e.g., type, performance, display size and ratio, activation state, and / or battery state of the second electronic device (201).

[0153] Referring to FIG. 8A, according to one embodiment, the first electronic device (201) may be a smartphone, and the second electronic device (202) may be a tablet PC. The first content (820) may include text regarding a duck stew recipe. The second content (830) may include a video regarding the duck stew recipe.

[0154] Referring to FIG. 8B, according to an embodiment, the first electronic device (201) may be a smartphone, and the second electronic device may be a smartphone. The first content (820) may include text regarding a duck stew recipe. The second content (840) may include an image regarding a duck stew recipe. For example, the performance of the second electronic device (202) may be better than the performance of the first electronic device (201). Alternatively, the display of the second electronic device (202) may be larger than the display of the first electronic device (201). Alternatively, the battery status (e.g., battery charge status) of the second electronic device (202) may be better than the battery status of the first electronic device (201). Depending on the implementation, the content displayed on the corresponding electronic device may be determined based on the user's preference. For example, if a user of the first electronic device (201) prefers text, the first electronic device (201) may display first content (820). Alternatively, if a user of the first electronic device (201) prefers images, the first electronic device (201) may display second content (840).

[0155] Referring to FIG. 8c, according to one embodiment, the first electronic device (201) may obtain or generate a prompt (860) to cause the first content (820) to include information about a duck stew recipe centered on text and the second content (830 or 840) to include information about a duck stew recipe centered on a video or image, based on determining that the first electronic device (201) is a smartphone and the second electronic device (202) is a tablet PC or smartphone.

[0156] According to one embodiment, the prompt (860) may include a plurality of texts. The plurality of texts may include a first text (861) for the generative AI model (e.g., the generative AI model (330) of FIG. 3) to obtain the first content (820) and a second text (863) for obtaining the second content (830 or 840). For example, the first text (861) may include a command (e.g., text) that causes the first content (820) to include information about the duck stew recipe centered on the text. For example, the second text (863) may include a command (e.g., text) that causes the second content (730) to include information about the duck stew recipe centered on a video or image.

[0157] In one embodiment, the generation of prompts may be configured separately to request actions to be performed on each electronic device (e.g., 201 or 202). For example, the first electronic device (201) may generate two prompts, based on a user's query: "Tell me on my phone how to cook spaghetti, but only the parts that my child can do." and "Tell me on my phone the parts of how to cook spaghetti, except the parts that my child can do." Alternatively, the generation of prompts may be configured to generate a single prompt.

[0158] Meanwhile, the duck stew recipes described in FIGS. 8A, 8B, and 8C are merely examples, and embodiments of the present invention may not be limited thereto. Furthermore, embodiments of the present invention may generate corresponding prompts and corresponding content by considering not only device information of the electronic device but also information about the user.

[0159] FIG. 9A is a diagram illustrating an operation of a first electronic device outputting first content based on device information of the first electronic device and second content based on device information of a second electronic device, according to an embodiment. FIG. 9B is a diagram illustrating a prompt generated by the first electronic device to obtain first content and second content, according to an embodiment.

[0160] Referring to FIG. 9A, according to one embodiment, a first electronic device (901) (e.g., the first electronic device (201) of FIG. 2) may obtain or confirm a user's query (910) through a display (e.g., the display (260) of FIG. 2, a touchscreen). For example, the query may be about "duck stew recipe."

[0161] According to one embodiment, the first electronic device (901) may obtain or generate first content (920) and second content (930) in response to a query using a generative AI model (e.g., the generative AI model (330) of FIG. 3).

[0162] In one embodiment, in response to a query, the first electronic device (901) may display the first content (920) on the display (260) and transmit information about the second content (930) to the second electronic device (902) (e.g., the second electronic device (202) of FIG. 2) so that the second electronic device (902) displays the second content (930).

[0163] According to one embodiment, the first content (920) may be generated based on first device information of the first electronic device (901) (e.g., type, performance, display size and ratio, activation state, and / or battery state of the first electronic device (901), and the second content (930) may be generated based on second device information of the second electronic device (902) (e.g., type, performance, display size and ratio, activation state, and / or battery state of the second electronic device (902). For example, the first electronic device (901) may be a smartphone, and the second electronic device (902) may be a notebook PC. The first content (920) may include text about a duck stew recipe. The second content (930) may include a video about a duck stew recipe.

[0164] Referring to FIG. 9B, according to one embodiment, the first electronic device (901) may obtain or generate a prompt (960) such that the first content (920) includes information about a duck stew recipe centered on text and the second content (930) includes information about a duck stew recipe centered on video (or image), based on determining that the first electronic device (901) is a smartphone and the second electronic device (902) is a laptop PC.

[0165] According to one embodiment, the prompt (960) may include a plurality of texts. The plurality of texts may include a first text (961) for the generative AI model (e.g., the generative AI model (330) of FIG. 3) to obtain the first content (920) and a second text (963) for obtaining the second content (930). For example, the first text (961) may include a command (e.g., text) that causes the first content (920) to include information about the duck stew recipe centered on the text. For example, the second text (963) may include a command (e.g., text) that causes the second content (930) for the second electronic device (902) (e.g., a notebook PC) to include information about the duck stew recipe centered on the video (or image).

[0166] Meanwhile, the duck stew recipes described in FIGS. 8A, 8B, 8C, 9A, and 9B are examples, and embodiments of the present invention may not be limited thereto. Furthermore, embodiments of the present invention may take into account information about the user as well as device information of the electronic device.

[0167] FIG. 10 is a diagram illustrating an operation of synchronizing the order between first content displayed on a first display and second content output from a second electronic device, according to one embodiment.

[0168] In one embodiment, in operation 1001, a first electronic device (e.g., the first electronic device (201) of FIG. 2) may display first content on a first display (e.g., the display (260) of FIG. 2) and transmit information about second content to a second electronic device (e.g., the second electronic device (202) of FIG. 2).

[0169] According to one embodiment, in operation 1003, the first electronic device (201) may receive, via a communication circuit (e.g., the communication circuit (290) of FIG. 2), status information indicating a state in which the second electronic device (202) outputs the second content. For example, the status information may include information indicating which position of the second content is currently being displayed.

[0170] According to one embodiment, in operation 1005, the first electronic device (201) may synchronize the order between the second content output from the second electronic device (202) and the first content displayed on the first display (260) based on the status information. For example, the first electronic device (201) may match the order of the contents of the first content currently displayed on the first display (260) with the order of the contents of the second content displayed on the second display (262). For example, the first electronic device (201) may check the order of the second content currently displayed on the second display (262) based on the status information, and display the contents of the first content that matches the checked order of the second content on the first display (260).

[0171] In one embodiment, the first electronic device (201) may transmit a command to the second electronic device (202) to cause the second electronic device (202) to adjust the order of the second content based on the order of the first content currently displayed on the first display (260).

[0172] According to the method described above, the first electronic device (201) can align the order of information displayed on the multiple electronic devices when at least one user uses multiple electronic devices in the same space to check information on the same topic (e.g., a topic related to the user's query). This can increase usability when at least one user uses multiple electronic devices (e.g., the first electronic device (201) and the second electronic device (202)) in the same space to check information on a topic related to the user's query.

[0173] The artificial intelligence system described below can be applied identically or similarly to the generative AI model described above (e.g., the generative AI model of FIG. 3).

[0174] Fig. 11 is a diagram for explaining a generative artificial intelligence system according to one embodiment.

[0175] According to one embodiment, a user query / response interface (1110) may receive a user's input. The user's input may be in the form of natural language, images, and / or videos, but is not limited thereto. Furthermore, context information may also be transmitted when the user's input is transmitted. The context information may include various additional information at the time of the user's input. For example, the additional information may include information about the application currently being used by the user or information about the user's location. Furthermore, the user's input may be in a form that combines the aforementioned natural language, images, sounds, and context information. Furthermore, the user's input may also be in a non-natural language form, such as selecting a menu. The user query / response interface (1110) may output the results of a generative artificial intelligence system to the user. The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user. The user query / response interface (1110) may output the results of a generative artificial intelligence system to the user. The output can be in natural language form, in the form of specific content, or in the form of actions requested by the user.

[0176] The AI ​​framework (1140) can receive user input and coordinate and control each component necessary to perform the user's intention based on the user's query.

[0177] User input received from the user query / response interface (1110) can be transmitted to a prompt design component (1141). The prompt design component (1141) can be used to generate prompts suitable for inputting user input into a large language model (LLM) or a large multimodal model (LMM). The prompt design component (1141) can be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The prompt design component (1141) can access a knowledge component including user preference data, a prompt library, and prompt examples based on the user input to generate prompts, and transmit the generated prompts to the LLM or LMM.

[0178] The API / Plug-in management component (1142) can communicate with external information when there is a request for additional information when passing user input as input to the generative model. The API / Plug-in management component (1142) can establish a channel for communicating with the outside of the AI ​​Interface through the API, and can enable access to various data sources (e.g., knowledge storage (1120)) through the established channel. In addition, the API / Plug-in management component (1142) can request the application / service component (1130) through the API for an action that ultimately performs the user input, rather than an intermediate result, when the action needs to be performed in the application or service. Information obtained from the outside can be used to generate a prompt in the prompt design component (1141) together with the user input, or can be passed as an input to the generative model.

[0179] The output modification component (also called a refiner component) (1143) can fine-tune the output from the generative model. For example, the output modification component (1143) can verify that the content generated through the LLM and / or LMM is not irrelevant, does not contain biased content, or does not contain harmful content. In addition, the output modification component (1143) can determine to what extent it matches the result desired by the user and, if necessary, can perform additional processes. The output modification component (1143) can additionally configure hints to avoid unwanted output and provide them to the user.

[0180] A generative AI model (1160) may generally refer to an artificial intelligence neural network that creates new types of data based on user input information. The generative AI model (1160) may include an image-generating model and / or a language-generating model. Representative models for generating images include a generative adversarial network (GAN) and a variational auto encoder (VAE), and examples include a VAE and a Diffusion-based generative model that uses a Transformer structure. A language-generating model is a model trained to statistically output the most appropriate output based on input values, and representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, there are also LMMs (large multimodal models) that can recognize various types of data input, such as text, images, and voice, and generate new data corresponding to them.

[0181] According to one embodiment, a first electronic device (201) may include a microphone (210), a communication circuit (290), a first display (260), at least one processor (220), and a memory (230) including instructions. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to obtain a user's query through the first display or the microphone. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate at least one prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device. In one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to provide the at least one prompt to a generative AI model to obtain first content based on first information and second content based on the second information. In one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to, in response to the query, display the first content on the first display and transmit information about the second content to the second electronic device via the communication circuit such that the second electronic device outputs the second content.

[0182] According to one embodiment, the first information may include at least one of first device information of the first electronic device or information about a first user specified for the first electronic device. According to one embodiment, the second information may include at least one of second device information of the second electronic device or information about a second user specified for the second electronic device.

[0183] According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate the at least one prompt comprising a plurality of texts. According to one embodiment, the plurality of texts may include a first text for generating the first content related to the query based on first device information of the first electronic device, and a second text for generating the second content related to the query based on second device information of the second electronic device.

[0184] According to one embodiment, the information included in the first content may be arranged based on a first layout corresponding to the size and ratio of the first display included in the first device information. According to one embodiment, the information included in the second content may be arranged based on a second layout corresponding to the size and ratio of the second display of the second electronic device included in the second device information. According to one embodiment, at least a portion of the first content may be different from at least a portion of the second content.

[0185] According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate the at least one prompt to cause the second content to include more images than the first content based on determining that the second display is larger than the first display.

[0186] According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to receive, through the communication circuit, state information indicating a state in which the second electronic device outputs the second content. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to synchronize an order between the second content output by the second electronic device and the first content displayed on the first display based on the state information.

[0187] In one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate the at least one prompt comprising a plurality of texts. In one embodiment, the plurality of texts may include a first text for generating the first content related to the query based on the first user, and a second text for generating the second content related to the query based on the second user.

[0188] According to one embodiment, the information included in the first content may be determined based on at least one of the role, age, gender, or preference of the first user included in the information about the first user. According to one embodiment, the information included in the second content may be determined based on at least one of the role, age, gender, or preference of the second user included in the information about the second user. According to one embodiment, at least a portion of the first content may be different from at least a portion of the second content.

[0189] In one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate the at least one prompt to cause the second content to include more images than the first content based on determining that the first user is an adult and the second user is a child.

[0190] In one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate the at least one prompt to cause the second content to include more images than the first content, based on determining that the first user prefers text and the second user prefers images.

[0191] According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to generate the at least one prompt, based on identifying a first role of the first user and a second role of the second user, such that the first content includes information corresponding to the first role and the second content includes information corresponding to the second role.

[0192] According to one embodiment, the operating method of the first electronic device (201) may include an operation of obtaining a user's query through a first display (260) included in the first electronic device or a microphone (210) included in the first electronic device. According to one embodiment, the operating method of the first electronic device may include an operation of generating at least one prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device. According to one embodiment, the operating method of the first electronic device may include an operation of providing the at least one prompt to a generative AI model to obtain first content based on the first information and second content based on the second information. According to one embodiment, the method of operating the first electronic device may include, in response to the query, displaying the first content on the first display and transmitting information about the second content to the second electronic device through a communication circuit (290) included in the electronic device so that the second electronic device outputs the second content.

[0193] According to one embodiment, the first information may include at least one of first device information of the first electronic device or information about a first user specified for the first electronic device. According to one embodiment, the second information may include at least one of second device information of the second electronic device or information about a second user specified for the second electronic device.

[0194] In one embodiment, the act of generating the at least one prompt may include an act of generating the at least one prompt including a plurality of texts. In one embodiment, the plurality of texts may include a first text for generating the first content related to the query based on first device information of the first electronic device, and a second text for generating the second content related to the query based on second device information of the second electronic device.

[0195] According to one embodiment, the information included in the first content may be arranged based on a first layout corresponding to the size and ratio of the first display included in the first device information. According to one embodiment, the information included in the second content may be arranged based on a second layout corresponding to the size and ratio of the second display of the second electronic device included in the second device information. According to one embodiment, at least a portion of the first content may be different from at least a portion of the second content.

[0196] In one embodiment, the act of generating the at least one prompt may include the act of generating the at least one prompt to cause the second content to include more images than the first content, based on determining that the second display is larger than the first display.

[0197] In one embodiment, the act of generating the at least one prompt may include the act of generating the at least one prompt comprising a plurality of texts. In one embodiment, the plurality of texts may include a first text for generating the first content related to the query based on the first user, and a second text for generating the second content related to the query based on the second user.

[0198] According to one embodiment, the information included in the first content may be determined based on at least one of the role, age, gender, or preference of the first user included in the information about the first user. According to one embodiment, the information included in the second content may be determined based on at least one of the role, age, gender, or preference of the second user included in the information about the second user. According to one embodiment, at least a portion of the first content may be different from at least a portion of the second content.

[0199] In one embodiment, the act of generating the at least one prompt may include an act of generating the at least one prompt to cause the second content to include more images than the first content, based on determining that the first user is an adult and the second user is a child.

[0200] According to one embodiment, a first electronic device (201) may include a microphone (210), a communication circuit (290), a first display (260), at least one processor (220), and a memory (230) including instructions. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to obtain a user's query through the first display or the microphone. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to obtain the first prompt and the second prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to provide the first prompt and the second prompt to a generative AI model (330), thereby obtaining first content based on the first prompt and second content based on the second prompt as a response corresponding to the query. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to display the first content on the first display and transmit information about the second content to the second electronic device via the communication circuit so that the second electronic device outputs the second content.

[0201] According to one embodiment, a first electronic device (201) may include a microphone (210), a communication circuit (290), a first display (260), at least one processor (220), and a memory (230) including instructions. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to obtain a user's query through the first display or the microphone. According to one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to obtain the first prompt and the second prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device. In one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to provide the first prompt to the generative AI model (330) to obtain first content based on the first prompt as a response corresponding to the query. In one embodiment, the instructions, when executed by the at least one processor, may cause the electronic device to display the first content on the first display and transmit information about the second prompt to the second electronic device via the communication circuit so that the second electronic device outputs the second content.

[0202] According to one embodiment, a computer-readable non-transitory recording medium (130, 230) is configured to, when executed by at least one processor (220), cause a first electronic device (201) to perform an operation of obtaining a user's query through a first display (260) included in the first electronic device or a microphone (210) included in the first electronic device, an operation of generating at least one prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device, an operation of providing the at least one prompt to a generative AI model to obtain first content based on the first information and second content based on the second information, and an operation of displaying the first content on the first display and transmitting information about the second content to a second electronic device through a communication circuit (290) included in the electronic device so that the second electronic device outputs the second content in response to the query. Instructions can be stored.

[0203] The embodiments of this document and the terminology used herein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "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" can 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 merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0204] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0205] Various embodiments of the present document may be implemented as software (e.g., a program) including one or more instructions stored in a storage medium (e.g., built-in memory or external memory) readable by a machine (e.g., an electronic device). For example, a processor (e.g., a processor) of the machine (e.g., an electronic device) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0206] According to one embodiment, the method according to various embodiments of the present disclosure may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0207] According to embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In the first electronic device (201), Mike (210); Communication circuit (290); First display (260); At least one processor (220); and A memory (230) including instructions, wherein the instructions, when executed by the at least one processor, cause the electronic device to: Obtaining the user's query through the first display or the microphone, Obtaining at least one prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device different from the first electronic device; Providing at least one prompt to the generative AI model (330) to obtain first content based on the first information and second content based on the second information, An electronic device that, in response to the above inquiry, displays the first content on the first display and transmits information about the second content to the second electronic device through the communication circuit so that the second electronic device outputs the second content.

2. In paragraph 1, The first information includes at least one of first device information of the first electronic device or information about a first user specified in the first electronic device, An electronic device wherein the second information includes at least one of second device information of the second electronic device or information about a second user specified in the second electronic device.

3. In any one of paragraphs 1 to 2, the instructions, when executed by the at least one processor, cause the electronic device to: Generate at least one prompt containing multiple texts, An electronic device wherein the plurality of texts includes a first text for generating the first content related to the query based on first device information of the first electronic device and a second text for generating the second content related to the query based on second device information of the second electronic device.

4. In any one of paragraphs 1 to 3, The information included in the first content is arranged based on a first layout corresponding to the size and ratio of the first display included in the first device information, The information included in the second content is arranged based on a second layout corresponding to the size and ratio of the second display of the second electronic device included in the second device information, An electronic device, characterized in that at least a portion of the first content is different from at least a portion of the second content.

5. In any one of paragraphs 1 to 4, the instructions, when executed by the at least one processor, cause the electronic device to: An electronic device that generates at least one prompt to cause the second content to include more images than the first content based on determining that the second display is larger than the first display.

6. In any one of paragraphs 1 to 5, the instructions, when executed by the at least one processor, cause the electronic device to: Through the above communication circuit, the second electronic device receives status information indicating a status of outputting the second content, An electronic device that synchronizes the order between the second content output from the second electronic device and the first content displayed on the first display based on the above status information.

7. In any one of paragraphs 1 to 6, the instructions, when executed by the at least one processor, cause the electronic device to: Generate at least one prompt containing multiple texts, An electronic device wherein the plurality of texts include a first text for generating the first content based on the first user and a second text for generating the second content based on the second user.

8. In any one of paragraphs 1 to 7, The information included in the first content is determined based on at least one of the role, age, gender, or preference of the first user included in the information about the first user, The information included in the second content is determined based on at least one of the role, age, gender, or preference of the second user included in the information about the second user, An electronic device, characterized in that at least a portion of the first content is different from at least a portion of the second content.

9. In any one of paragraphs 1 to 8, the instructions, when executed by the at least one processor, cause the electronic device to: An electronic device that generates at least one prompt to cause the second content to include more images than the first content, based on determining that the first user is an adult and the second user is a child.

10. In any one of paragraphs 1 to 9, the instructions, when executed by the at least one processor, cause the electronic device to: An electronic device that generates at least one prompt to cause the second content to include more images than the first content, based on determining that the first user prefers text and the second user prefers images.

11. In any one of paragraphs 1 to 10, the instructions, when executed by the at least one processor, cause the electronic device to: An electronic device that generates at least one prompt based on identifying a first role of the first user and a second role of the second user, such that the first content includes information corresponding to the first role and the second content includes information corresponding to the second role.

12. In the operating method of the first electronic device (201), An operation of obtaining a user's inquiry through a first display (260) included in the first electronic device or a microphone (210) included in the first electronic device; An operation of generating at least one prompt based on information about the query, first information related to the first electronic device, and second information related to a second electronic device (202) different from the first electronic device; An operation of providing at least one prompt to a generative AI model (330) to obtain first content based on first information and second content based on second information; and A method of operating an electronic device, comprising, in response to the above inquiry, displaying the first content on the first display and transmitting information about the second content to the second electronic device through a communication circuit (290) included in the electronic device so that the second electronic device outputs the second content.

13. In paragraph 12, The first information includes at least one of first device information of the first electronic device or information about a first user specified in the first electronic device, A method of operating an electronic device, wherein the second information includes at least one of second device information of the second electronic device or information about a second user specified in the second electronic device.

14. In any one of paragraphs 12 to 13, the operation of generating at least one prompt comprises: comprising an action to generate at least one prompt comprising a plurality of texts; A method of operating an electronic device, wherein the plurality of texts include a first text for generating the first content related to the query based on first device information of the first electronic device and a second text for generating the second content related to the query based on second device information of the second electronic device.

15. In any one of paragraphs 12 to 14, The information included in the first content is arranged based on a first layout corresponding to the size and ratio of the first display included in the first device information, A method of operating an electronic device in which information included in the second content is arranged based on a second layout corresponding to the size and ratio of the second display of the second electronic device included in the second device information.

Images