Electronic device for generating response message based on conversation context by using artificial intelligence model, control method therefor, and storage medium

Abstract

Disclosed is an electronic device. The electronic device of the present disclosure comprises: a display; at least one processor including a processing circuit; and a memory for storing instructions, wherein the instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to: on the basis of receiving a first user input for summarizing a plurality of unread messages in a state in which the plurality of unread messages are included in a chat window, acquire a plurality of pieces of summary information related to the plurality of unread messages by using an artificial intelligence model; display the plurality of pieces of summary information; receive a second user input for selecting at least one piece of summary information from among the plurality of pieces of summary information; generate at least one recommended answer by using the artificial intelligence model on the basis of the at least one piece of summary information; and display the at least one recommended answer.

Description

Electronic device for generating response messages based on conversational context using an artificial intelligence model, a method for controlling the same, and a storage medium

[0001] Embodiments of the present disclosure relate to an electronic device that generates a response message based on conversational context using an artificial intelligence model, a method for controlling the same, and a storage medium.

[0002] Various services and additional functions provided through electronic devices, such as portable electronic devices like smartphones, are gradually increasing. To enhance the utility value of these devices and satisfy the needs of diverse users, telecommunications service providers or electronic device manufacturers are competitively developing devices to offer various functions and differentiate themselves from competitors. Consequently, the various functions provided through electronic devices are also becoming increasingly sophisticated.

[0003] To provide services for specific purposes, multiple artificial intelligence (AI) models may operate in a connected form. For example, AI models are utilized in various fields such as content streaming, translation, photo editing, finance, new drug development, law, and the military. At least some of the multiple AI models for a single service may be implemented as generative AI models. For example, a service that provides the content of relatively high-capacity PDF files may include an embedding AI model for vectorizing PDF files and a generative AI language model for processing vector search results.

[0004] Generative AI models generate data or content corresponding to inputs and can provide the generated content. As the development of deep learning models used as generative AI models advances, the quality of the data or content provided by generative AI models is also improving. The types of generation tasks provided by generative AI models (e.g., LMM (large multimodal model), LLM (large language model), LVM (large vision model)) may include, for example, text generation, image generation, code generation, speech generation, and / or video generation.

[0005] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0006] According to one embodiment, the electronic device may include a display, at least one processor including a processing circuit, and a memory for storing instructions.

[0007] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may obtain multiple summary information related to multiple unread messages using an artificial intelligence model based on the reception of a first user input for summarizing multiple unread messages, while multiple unread messages are included in a dialog box.

[0008] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may display the plurality of summary information.

[0009] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may receive a second user input selecting at least one summary information among the plurality of summary information.

[0010] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may generate at least one recommended answer based on the at least one summary information using the artificial intelligence model.

[0011] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be able to display the at least one recommended answer.

[0012] According to one embodiment, a control method for an electronic device may include an operation of obtaining a plurality of summary information related to a plurality of unread messages using an artificial intelligence model based on receiving a first user input for summarizing a plurality of unread messages while a plurality of unread messages are included in a dialog box.

[0013] According to one embodiment, a control method for an electronic device may include an operation of displaying the plurality of summary information.

[0014] According to one embodiment, a control method for an electronic device may include receiving a second user input that selects at least one summary information among the plurality of summary information.

[0015] According to one embodiment, a control method for an electronic device may include an operation of generating at least one recommended answer based on at least one summary information using the artificial intelligence model.

[0016] According to one embodiment, a control method for an electronic device may include an operation of displaying the at least one recommended answer on a display of the electronic device.

[0017] According to one embodiment, in a non-transient computer-readable storage medium storing one or more programs, the one or more programs may include instructions for an electronic device to obtain a plurality of summary information related to the plurality of unread messages using an artificial intelligence model based on receiving a first user input for summarizing the plurality of unread messages, while the plurality of unread messages are included in a dialog box.

[0018] According to one embodiment, the one or more programs may include instructions that cause the electronic device to display the plurality of summary information.

[0019] According to one embodiment, the one or more programs may include instructions that cause the electronic device to receive a second user input selecting at least one summary information among the plurality of summary information.

[0020] According to one embodiment, the one or more programs may include instructions that cause the electronic device to generate at least one recommended answer based on at least one summary information using the artificial intelligence model.

[0021] According to one embodiment, the one or more programs may include instructions that cause the electronic device to display the at least one recommended answer.

[0022] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0023] FIG. 1 is a block diagram of an electronic device in a network environment according to various embodiments.

[0024] FIG. 2 is a diagram illustrating a generative artificial intelligence system according to one embodiment.

[0025] FIG. 3 is a flowchart illustrating the operation of generating a recommended answer using an artificial intelligence model of an electronic device according to one embodiment.

[0026] FIG. 4 is a diagram illustrating the operation of summarizing unread conversations and generating recommended answers using an artificial intelligence model of an electronic device according to one embodiment.

[0027] FIG. 5 is a diagram illustrating an operation to generate a recommended answer when two or more summary information are selected from a plurality of summary information of an electronic device according to one embodiment.

[0028] FIG. 6 is a diagram illustrating the operation of generating a recommended answer by further considering text entered by a user in an electronic device according to one embodiment.

[0029] FIG. 7 is a diagram illustrating the recommended answer regeneration operation of an electronic device according to one embodiment.

[0030] FIG. 8a is a diagram illustrating the operation of highlighting a message corresponding to selected summary information of an electronic device according to one embodiment.

[0031] FIG. 8b is a diagram illustrating the operation of an electronic device according to one embodiment, which generates new summary information based on user input and highlights a message corresponding to the newly generated summary information.

[0032] FIG. 9a is a diagram illustrating the operation of changing summary information selected according to user input and highlighting a message corresponding to the changed summary information of an electronic device according to one embodiment.

[0033] FIG. 9b is a diagram illustrating the operation of an electronic device according to one embodiment, which generates new summary information based on user input and highlights a message corresponding to the newly generated summary information.

[0034] FIG. 10 is a flowchart illustrating the operation of generating a recommended answer based on external information of an electronic device according to one embodiment.

[0035] FIG. 11 is a diagram illustrating the operation of generating a recommended answer based on external information of an electronic device according to one embodiment.

[0036] FIG. 12 is a diagram illustrating the operation of generating a recommended answer based on external information of an electronic device according to one embodiment.

[0037] FIGS. 13a and FIGS. 13b are drawings for explaining a recommended answer regeneration operation based on external information of an electronic device according to one embodiment.

[0038] FIG. 14 is a flowchart illustrating the operation of displaying a generated recommended answer of an electronic device according to one embodiment as an answer to a specific conversationalist's message.

[0039] FIG. 15 is a diagram illustrating the operation of displaying a generated recommended answer of an electronic device according to one embodiment as an answer to a specific conversationalist's message.

[0040] FIG. 16 is a diagram illustrating an operation to provide summary information according to a set schedule when there are many summary topics for unread messages of an electronic device according to one embodiment.

[0041] FIG. 17 is a drawing for explaining the form of a summary information card displayed on the execution screen of a message application of an electronic device according to one embodiment.

[0042] FIG. 18 is a drawing for explaining the form of a summary information card displayed on the execution screen of a message application of an electronic device according to one embodiment.

[0043] FIG. 19 is a diagram illustrating the operation of graphically displaying summary information of unread messages of an electronic device according to one embodiment.

[0044] Hereinafter, embodiments of the present disclosure are described in detail with reference to the drawings so that those skilled in the art can easily practice them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and brevity.

[0045] FIG. 1 is a block diagram of an electronic device (101) in a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or may communicate with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0046] The processor (120) can control at least one other component (e.g., hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., program (140)), for example, and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., sensor module (176) or communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., central processing unit or application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., graphics processing unit, neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, if the electronic device (101) includes a main processor (121) and an 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 designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0047] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) 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. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or through a separate server (e.g., server (108)). The learning algorithm may 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 may include a plurality of artificial neural network layers.The artificial neural network may be 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 the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially. The number of processors (120) may be one or more. For example, the processor (120) may have the structure of a multi-core processor, such as a dual core, a quad core, or a hexa core.

[0048] The processor (120) can control the operations of the electronic device (101) by executing instructions stored in memory (130). For example, the processor (120) may correspond to a plurality of processors that divide and collectively perform a plurality of operations among the processors.

[0049] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0050] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0051] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0052] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0053] The display module (160) can visually provide information to an external (e.g., 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 said 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 the force generated by said touch.

[0054] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0055] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0056] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to 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.

[0057] The connection terminal (178) may include a connector through which the electronic device (101) can 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).

[0058] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0059] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0060] The power management module (188) can manage the power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0061] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0062] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an 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 include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and 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., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., 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 may 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 identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0063] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), 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), external electronic device (e.g., electronic device (104)), or network system (e.g., 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 realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mMTC, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for realizing URLLC.

[0064] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to 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 a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0065] According to one embodiment, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0066] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0067] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) through a server (108) connected to a second network (199). Each of the external electronic devices (102, or 104) may be the same or different type of device as the electronic device (101). According to one embodiment, all or part of the operations performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or 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 provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within a 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.

[0068] FIG. 2 is a diagram illustrating a generative artificial intelligence system according to one embodiment.

[0069] Referring to FIG. 2, the user query / response interface (210) can receive user input. The user input may be in the form of natural language, images, and / or videos, but there are no limitations. Additionally, context information may be transmitted along with the user input. The context information may include various additional information at the time of user input. For example, the additional information may include information about the application currently being used by the user or the user's location information. Furthermore, the user input may be in a mixed form of the aforementioned natural language, images, sounds, and context information. Additionally, the user input may be in a non-natural language form, such as selecting a menu. The user query / response interface (210) can output results from 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 (210) can output results from a generative artificial intelligence system to the user. The output can be in the form of natural language or specific content, and it can also be provided in a form such as the action requested by the user.

[0070] The AI ​​framework (240) can receive input from the user and coordinate and control each component necessary to perform the user's intent based on the user's query.

[0071] User input received from the user query / response interface (210) can be transmitted to a prompt design component (241). The prompt design component (241) 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 (241) may be an AI component that uses machine learning algorithms or neural networks to develop better prompts over time. The prompt design component (241) can generate prompts by accessing a knowledge component containing user preference data, a prompt library, and prompt examples based on user input, and can transmit the generated prompts to the LLM or LMM.

[0072] The API (application programming interface) / plug-in management component (242) can perform the role of communicating with external information when there is a request for additional information when user input is passed as input to a generative model. The API / plug-in management component (242) establishes a channel to communicate with the outside of the AI ​​Interface via the API, and can enable access to various data sources (e.g., knowledge repository (220)) through the established channel. Additionally, the API / plug-in management component (242) can request the application / service component (230) via the API to perform an action that ultimately executes the user input, rather than an intermediate result, in the case where the application or service needs to perform such action. The information obtained from the outside may be used to generate a prompt in the prompt design component (241) along with the user input, or it may be passed as input to the generative model.

[0073] The output modification component (or refiner component) (243) can fine-tune the output of the generative model. For example, the output modification component (243) can verify whether the content generated through the LLM and / or LMM is irrelevant, contains biased content, or contains harmful content. Additionally, the output modification component (243) can determine the extent to which the output matches the desired result and, if additional processing is required, proceed with that process. Furthermore, the output modification component (243) can configure and provide hints to the user to avoid unwanted output.

[0074] A generative AI model (260) generally refers to an artificial intelligence neural network that generates new forms of data based on user input information. A generative AI model (260) may include a model that generates images and / or a model that generates language. Models that generate images include, but are not limited to, GANs (generative adversarial networks) and VAEs (variational autoencoders), and examples include Diffusion-based generative models that use VAEs and Transformer structures. Models that generate language are models trained to output the most statistically appropriate output value based on input values, and examples include models such as CHAT-GPT 3 and CHAT-GPT 4. There are also LMMs (large multimodal models) that can recognize various forms of data input, such as text, images, and voice, and generate new data corresponding to them.

[0075] FIG. 3 is a flowchart illustrating the operation of generating a recommended answer using an artificial intelligence model of an electronic device according to one embodiment.

[0076] In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0077] According to one embodiment, operations 310 to 350 may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1).

[0078] Referring to FIG. 3, in operation 310, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) can obtain multiple summary information related to multiple unread messages by using an artificial intelligence model (e.g., an artificial intelligence model stored in memory (e.g., the memory (130) of FIG. 1)) based on receiving a first user input for summarizing multiple unread messages while multiple unread messages are included in a dialog box.

[0079] In operation 310, multiple unread messages are exemplified, but are not limited thereto. According to one embodiment, operations related to multiple unread messages may be applied identically or similarly to a range of messages (e.g., messages corresponding to a range specified by a user and / or messages sent / received within a specified period). For example, an electronic device may obtain multiple summary information related to a range of messages using an artificial intelligence model based on the reception of a first user input for summarizing a range of messages while the range of messages is included in a dialog box. Additionally, the operations related to multiple unread messages described below may be performed identically or similarly to the range of messages.

[0080] According to one embodiment, the chat window may include an execution screen of a message application (or conversation application).

[0081] According to one embodiment, the artificial intelligence model may acquire conversation information from a message application and transmit the processed result to the message application. According to one embodiment, the artificial intelligence model may be a configuration independent of the message application or a configuration included in the message application.

[0082] According to one embodiment, the artificial intelligence model may be stored in the memory of an electronic device or stored on a server.

[0083] According to one embodiment, the artificial intelligence model may include a large language model (LM).

[0084] An LLM can be a language model based on an artificial neural network that has been trained on a large amount of text data through prior training. An LLM can contain far more parameters (e.g., over 10 billion) than existing general language models. An LLM can use a transformer artificial neural network structure based on an attention mechanism.

[0085] The attention mechanism is a technique that helps artificial intelligence models focus on important parts within input data. The attention mechanism predicts the extent to which certain parts of time-series input data (e.g., input data such as voice or video, or input data for specific layers of a neural network) contribute to the network's intermediate or final output, and can be utilized for output data prediction. While the recurrent neural network (RNN) structure, which processes each element of a sequence sequentially, suffers from degraded prediction performance when there is information dependency over long time-series distances, the attention mechanism can account for information dependency over long time-series distances by controlling the degree of weighted attention within the context of the input data as a whole (or part thereof).

[0086] A Transformer can be composed of an encoder-decoder structure. The encoder processes input data to output compressed information (e.g., contextual representation), and the decoder processes the compressed information to output data in token units. Each of the encoder and decoder may include an independent attention network and a cross-attention network connecting the encoder and decoder.

[0087] For example, LLM learning may include pre-training and / or fine-tuning. Pre-training is the process of enabling the LLM to acquire general linguistic knowledge using large amounts of text data, and may include, for example, self-supervised learning that predicts the next word based on the previous word sequence in a text sequence. Fine-tuning is the process of training the LLM to be suitable for a specific domain (e.g., chatbot, translation, summarization, Q&A) or task; based on the pre-trained model, the LLM may undergo additional supervised learning (or adaptive learning) using a dataset tailored to the domain purpose.

[0088] LLMs can perform tasks using text inputs containing natural language called prompts. For example, fine-tuning can be omitted during LLM training. Users can control the prompts input to the LLM to improve the performance of desired tasks. Similar to in-context learning or zero-shot / few-shot learning, examples of the task and / or guides for performing the task can be added to the prompts. Publicly available LLMs include BERT (Bidirectional Encoder Representations from Transformer) and GPT (Generative Pre-trained Transformer).

[0089] The LLM can receive additional input of image information (including video) in addition to text. The LLM can convert the image information into text through a separate operation (e.g., image recognition operation, scene recognition operation) and generate a response by including the converted text in the prompt. As another example, a separately trained model (e.g., a large multimodal model) can convert the input image into image embeddings aligned with text through an image encoder and generate a response using the text embeddings corresponding to the input text.

[0090] The term 'LLM' can refer to the language neural network model itself, but it can also refer to models for LLM-based applications (e.g., chatbots, translation, summarization, text classification, sentence generation). For instance, an LLM-based chatbot or translator such as ChatGPT can also be referred to as 'LLM'.

[0091] 'LLM' may include an inference engine using an LLM neural network model. For example, "inputting an input prompt into the LLM" may mean "inputting an input prompt into an inference engine based on the LLM." For example, "the output of the LLM for the input prompt" may refer to the output information of the last neural network layer of the LLM (or output information modified through additional processing) obtained when the input prompt is input into an inference engine based on the LLM.

[0092] According to one embodiment, when an electronic device performs functions such as conversation summarization and user response generation through an LLM, it may generate an LLM input (or prompt) for performing each function. According to one embodiment, the prompt template to be used by the electronic device may be changed when performing each function. For example, the electronic device may use a summary prompt template when summarizing a conversation and a response generation prompt template when generating a user response.

[0093] According to one embodiment, when an artificial intelligence model is independent of applications installed on an electronic device, the electronic device can obtain information included in the execution screen of an application (e.g., conversation information, application operation information) through screen analysis. For example, the electronic device can obtain text information corresponding to a displayed image through optical character recognition (OCR), image recognition / classification, or scene recognition / classification. According to one embodiment, the electronic device may also obtain relevant information using screen composition information (e.g., Android accessibility framework).

[0094] According to one embodiment, the electronic device may process a query (e.g., a search term, a prompt, information required for generating a prompt) to search for or generate necessary information and provide the search or generation results. According to one embodiment, the electronic device may utilize automatic speech recognition (ASR), LLM, natural language processing (NLP), and / or internal / external databases for information retrieval and / or generation.

[0095] When a query includes text, NLP can process the text to facilitate the subsequent generation of responses using LLM or internal / external databases.

[0096] An LLM can generate a response by receiving a prompt consisting of text or images. An LLM may also be implemented using other large models capable of text input and output (e.g., LVM, LMM). The output of an LLM may include actions to be performed. These actions may include additional searches using internal or external databases. An LLM can utilize retrieval augmented generation (RAG) to process more information.

[0097] According to one embodiment, the electronic device can perform information retrieval using an internal or external database based on a query. The database can be stored and retrieved in various forms, such as SQL (structured query language) and NoSQL (not only SQL).

[0098] According to one embodiment, although it has been described above that ASR, LLM, and NLP stored in an electronic device are used for information retrieval and / or generation and internal and external databases are used by the electronic device, this is not limited thereto, and ASR, LLM, and NLP stored in a server may be used and internal and external databases may be used by the server.

[0099] According to one embodiment, an electronic device may summarize conversation information of a currently viewed dialog window in response to a user's request or a system request. For example, the electronic device may receive a request for summarizing conversation information when unread messages of the currently viewed dialog window are included. According to one embodiment, the electronic device may receive a request for summarizing conversation information through user-specified input. For example, the electronic device may confirm that a request for summarizing conversation information has been received when the user scrolls up the dialog window two or more times.

[0100] According to one embodiment, an electronic device may generate summary information based on conversation information received through a conversation window of a message application. The conversation information may include multiple contexts (or conversation topics). Each context may be divided into a continuous conversation session, or a single continuous conversation session may include unit messages of multiple different contexts (e.g., a unit of text entered by one person at a time, a unit displayed as a single speech bubble). According to one embodiment, the electronic device may generate multiple summary information for each of the multiple conversation contexts using an LLM. According to one embodiment, the electronic device may use a summary prompt template such as [Table 1] below to summarize the conversation content.

[0101] Summarize the [Conversation] below. - [Conversation] can include one or more topics. - If there are two or more topics, summarize each topic separately. - Please keep the summary for each topic within 8 characters. Separate the [Conversation] by the topics above. [Conversation]# Enter Conversation #

[0102] According to one embodiment, in operation 320, the electronic device may display a plurality of summary information. According to one embodiment, the plurality of summary information may include topic-specific summary information and a plurality of conversationalist information of a conversation window.

[0103] According to one embodiment, the topic-specific summary information may include each summary information obtained as message content corresponding to each topic, based on the identification of multiple topics according to conversation context among multiple unread messages.

[0104] According to one embodiment, the plurality of conversational information may include information for each conversational person included in the conversation window. According to one embodiment, the plurality of conversational information included in the summary information may be included in the conversation window, but information about conversational people who did not converse may not be included.

[0105] According to one embodiment, the electronic device can check multiple messages of at least one conversationalist based on receiving user input selecting at least one conversationalist among multiple conversationalists. According to one embodiment, the electronic device can display summary information on the subject of at least some of the multiple messages of at least one conversationalist.

[0106] According to one embodiment, in operation 330, the electronic device may receive a second user input selecting at least one summary information among a plurality of summary information.

[0107] According to one embodiment, the electronic device may receive user input selecting one summary information or two or more summary information among a plurality of summary information with different subjects.

[0108] According to one embodiment, the electronic device may display at least one selected summary information as a pop-up screen in a portion of a message application (e.g., top) where a dialog box is displayed. According to one embodiment, the electronic device may highlight a message related to at least one selected summary information among a plurality of unread messages included in the dialog box. According to one embodiment, at least one summary information may be extracted from a message related to at least one summary information.

[0109] According to one embodiment, the electronic device may display summary information of a different subject based on receiving user input to change selected summary information to summary information of a different subject. For example, when the electronic device displays selected summary information as a popup screen in a dialog box, if user input to swipe the popup screen is received, it may confirm that user input to display summary information of a different subject has been received. According to one embodiment, when the electronic device confirms that user input to display summary information of a different subject has been received, it may display summary information of a different subject on the popup screen.

[0110] According to one embodiment, the electronic device can highlight at least some of the multiple messages related to different topics among the multiple unread messages. For example, the electronic device can highlight messages displayed on a display among the multiple messages related to different topics.

[0111] According to one embodiment, the electronic device may receive user input selecting at least one of a plurality of conversational information included in a conversation window.

[0112] According to one embodiment, the electronic device can highlight at least some of the multiple messages of at least one selected conversationalist among the multiple messages. For example, the electronic device can highlight a displayed message among the multiple messages of at least one selected conversationalist.

[0113] According to one embodiment, the electronic device may display summary information regarding a message from at least one selected conversational partner as a pop-up screen in a portion of a message application where a conversation window is displayed (e.g., top). According to one embodiment, the electronic device may highlight a message from a selected conversational partner among a plurality of unread messages included in the conversation window.

[0114] According to one embodiment, the electronic device may display information about another conversational partner and summary information about the other conversational partner’s message based on receiving user input to change at least one selected conversational partner to another conversational partner. For example, if the electronic device displays summary information about the selected conversational partner’s message as a pop-up screen in a conversation window, when user input to swipe the pop-up screen is received, it may confirm that user input to display summary information about the other conversational partner’s message has been received. According to one embodiment, when the electronic device confirms that user input to display summary information about the other conversational partner’s message has been received, it may display summary information about the other conversational partner’s message on the pop-up screen.

[0115] According to one embodiment, the electronic device can highlight at least some of the multiple messages of another interlocutor among the multiple unread messages. For example, the electronic device can highlight the message displayed on the display among the multiple messages of another interlocutor.

[0116] According to one embodiment, the operation of highlighting a message related to summary information of a selected topic or summary information of a selected conversationalist's message, and changing it to summary information of another topic or summary information of another conversationalist's message based on user input, will be explained below with reference to FIGS. 8a and 9a.

[0117] According to one embodiment, when a message displayed among a plurality of messages related to a topic selected by scroll input changes, the electronic device can highlight the changed message.

[0118] According to one embodiment, when a displayed message among a plurality of messages of at least one conversational partner selected by scroll input changes, the electronic device can highlight the changed message.

[0119] According to one embodiment, the operation of changing the highlighted message as the message displayed based on scroll input changes will be explained below with reference to FIGS. 8b and FIGS. 9b.

[0120] According to one embodiment, in operation 340, the electronic device can generate at least one recommended answer based on at least one summary information using an artificial intelligence model. For example, the electronic device can generate at least one recommended answer based on at least one summary information using an LLM.

[0121] According to one embodiment, an electronic device can generate at least one recommended answer using an artificial intelligence model based on one selected summary information. For example, the electronic device can generate at least one recommended answer as output data by using one selected summary information as input data for an artificial intelligence model.

[0122] According to one embodiment, an electronic device may generate a plurality of recommended answers based on at least one of the first summary information or the second summary information by using an artificial intelligence model, based on receiving a user input selecting a plurality of summary information including a first summary information and a second summary information among a plurality of summary information. For example, the electronic device may generate a plurality of recommended answers as output data by using the selected plurality of summary information as input data for the artificial intelligence model.

[0123] According to one embodiment, a plurality of recommended answers may include recommended answers generated based on first summary information and second summary information.

[0124] According to one embodiment, the electronic device can identify a plurality of messages corresponding to at least one selected summary information among a plurality of unread messages.

[0125] According to one embodiment, the electronic device may generate at least one recommended answer (or input guide) by further utilizing a plurality of messages corresponding to at least one selected summary information. For example, the electronic device may obtain at least one recommended answer as output data by using at least one selected summary information and a plurality of messages corresponding to at least one summary information as input data for an artificial intelligence model.

[0126] According to one embodiment, the electronic device may receive user input that inputs text related to at least one summary information. For example, the electronic device may receive text through a text window for inputting text that is to be included in a recommended answer.

[0127] According to one embodiment, the electronic device may generate at least one recommended answer by further utilizing text received through user input. For example, the electronic device may obtain at least one recommended answer as output data by using at least one selected summary information, a plurality of messages corresponding to at least one summary information, and the input text as input data for an artificial intelligence model.

[0128] According to one embodiment, the electronic device may obtain at least one recommended answer by further utilizing external information. According to one embodiment, the electronic device may generate at least one recommended answer based on at least one of summary information related to a plurality of unread messages included in another dialog box or information of an application related to at least one summary information. For example, the application related to at least one summary information may be an application different from the message application.

[0129] According to one embodiment, the electronic device may display at least one of summary information related to multiple unread messages included in another dialog box or information of an application as multiple summary information. For example, the electronic device may display at least one of summary information related to multiple unread messages included in another dialog box or information of an application, along with multiple summary information related to multiple unread messages included in the current dialog box.

[0130] According to one embodiment, the electronic device may display a user interface (UI) for checking summary information of another dialog box and a UI for checking information of another application, along with multiple summary information related to multiple unread messages included in the current dialog box. According to one embodiment, when the UI for checking summary information of another dialog box or the UI for checking information of another application is selected, the electronic device may display at least one of the summary information related to multiple unread messages included in the other dialog box or the information of the application.

[0131] According to one embodiment, the electronic device may generate at least one recommended answer based on at least one summary information selected from among a plurality of summary information related to the current dialog box and at least one summary information selected from among a plurality of summary information related to another dialog box or another application, based on receiving a user input selecting at least one summary information related to a plurality of unread messages included in another dialog box or information of another application.

[0132] According to one embodiment, the operation of generating at least one recommended answer using external information will be explained below with reference to FIGS. 10, 11, and 12.

[0133] According to one embodiment, in 350 operation, the electronic device can display at least one recommended answer.

[0134] According to one embodiment, the electronic device may display at least one list of recommended answers. According to one embodiment, when user input is received to select one of the at least one recommended answer displayed in the list, the electronic device may display the selected recommended answer in a text input window of a dialog box or input it as a user's dialogue in the dialog box.

[0135] According to one embodiment, the electronic device may display a UI for regenerating a recommended answer. According to one embodiment, after displaying at least one recommended answer, the electronic device may regenerate at least one recommended answer based on receiving user input for regenerating a recommended answer, by further utilizing at least one of summary information related to a plurality of unread messages included in another dialog box or information of an application. For example, user input for regenerating a recommended answer may include user input for selecting a UI for regenerating a recommended answer.

[0136] According to one embodiment, the operation of regenerating a recommended answer using external information based on user input after generating a recommended answer will be explained below with reference to FIGS. 13a and 13b.

[0137] According to one embodiment, the electronic device may input a recommended answer as a user message as a response to the message most relevant to the selected recommended answer. According to one embodiment, the operation of inputting a selected recommended answer as a response to a specific message will be explained below with reference to FIG. 15.

[0138] According to one embodiment, if the number of subjects of summary information of unread messages exceeds a set number, the electronic device may provide the summary information as a schedule for the relevant time. According to one embodiment, the operation of providing the summary information in sections will be described below with reference to FIG. 16.

[0139] According to one embodiment, the electronic device may display selected summary information in various forms. For example, the electronic device may display at least one of a banner-type popup screen that includes summary information and is displayed at the top of the screen, a popup screen that includes summary information and has a size of more than half of the screen, an indicator indicating that summary information is present, or a bar-type popup screen that displays only the number of summary information. According to one embodiment, various forms of summary information will be described below with reference to FIGS. 17 and 18.

[0140] According to one embodiment, the electronic device may provide summary information of unread messages as well as as graphics. For example, the electronic device may display summary information graphically based on the number of words or sentences included in the unread messages and the number of messages for each of the multiple interlocutors. According to one embodiment, the operation of displaying summary information graphically will be described below with reference to FIG. 19.

[0141] When there are many unread messages, it takes a long time for the user to understand the content of the unread messages, and because various topics are mixed, it is difficult to check content related to the topic the user wants, and if information from another application is needed during a conversation, the user must leave the chat window. However, according to the present disclosure, summary information regarding unread messages is provided, summary information of related other chat windows or other applications is provided together, and a recommended answer reflecting the user's intent can be provided by generating a recommended answer using various summary information and / or text entered by the user.

[0142] FIG. 4 is a diagram illustrating the operation of summarizing unread conversations and generating recommended answers using an artificial intelligence model of an electronic device according to one embodiment.

[0143] Referring to FIG. 4, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) can display a list of dialog boxes containing a dialog box (410) containing an unread message through the execution screen of a message application.

[0144] According to one embodiment, when the electronic device receives a user input (411) selecting a dialog box (410) containing unread messages, it may display a plurality of summary information (420) obtained based on the unread messages. The plurality of summary information (420) may be obtained by analyzing the conversation content of the plurality of unread messages using an artificial intelligence model.

[0145] According to one embodiment, a plurality of summary information (420) may include topic-specific summary information (421), conversational information (422), and a UI (423) for receiving input guides.

[0146] According to one embodiment, the electronic device may receive user input selecting at least one summary information among a plurality of summary information (420). For example, when the electronic device receives user input selecting summary information (430) of one topic among the topic-specific summary information (420), it may display a recommended answer (441) corresponding to the summary information (430) of the selected topic through an input guide window (440). According to one embodiment, the recommended answer (441) may be generated using an artificial intelligence model based on the summary information (430) of the selected topic, a plurality of message contents related to the summary information (430) of the selected topic, or text entered by the user.

[0147] According to one embodiment, when the electronic device receives user input selecting a UI (423) for receiving an input guide after selecting summary information (430) of a topic, it may display a recommended answer (441) corresponding to the summary information (430) of the selected topic through an input guide window (440).

[0148] According to one embodiment, when the electronic device receives user input selecting a recommended answer (441), it may display the recommended answer (441) in the text input window (450) of the dialog box. According to one embodiment, when a set time has elapsed after the recommended answer (441) is displayed, the electronic device may display the recommended answer (441) in the text input window (450) of the dialog box. According to one embodiment, when user input for sending a message is received while the recommended answer (441) is displayed in the text input window (450), the electronic device may send the recommended answer (441) as a message to the user.

[0149] According to one embodiment, the electronic device may receive user input selecting a recommended answer (441) or, after a set time has elapsed since the recommended answer (441) was displayed, send the user's message directly to the chat window without displaying it in the text input window (450).

[0150] FIG. 5 is a diagram illustrating an operation to generate a recommended answer when two or more summary information are selected from a plurality of summary information of an electronic device according to one embodiment.

[0151] Referring to FIG. 5, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) can combine the two or more selected summary information (511, 512) to generate at least one recommended answer (520) when a user selects two or more summary information (511, 512) from a plurality of summary information (510).

[0152] According to one embodiment, the electronic device may change the recommended answer in real time based on the selection of summary information. For example, when the electronic device receives a user input selecting the first summary information (511), it may display a first recommended answer generated based on the first summary information (511). According to one embodiment, after displaying the first recommended answer generated based on the first summary information (511), when the electronic device receives a user input selecting the second summary information (512), it may add and display a second recommended answer generated based on at least one of the first summary information (511) or the second summary information (512) to the first recommended answer. According to one embodiment, after displaying the first recommended answer generated based on the first summary information (511), when the electronic device receives a user input selecting the second summary information (512), it may delete the first recommended answer and display a second recommended answer generated based on at least one of the first summary information (511) or the second summary information (512).

[0153] FIG. 6 is a diagram illustrating the operation of generating a recommended answer by further considering text entered by a user in an electronic device according to one embodiment.

[0154] Referring to FIG. 6, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display at least one recommended answer (610) generated based on selected summary information, and then, when user input selecting a text input window (611) is received, display a UI (620) for text input. According to one embodiment, the UI (620) for text input may include a text input window and a keyboard UI for text input.

[0155] According to one embodiment, when text (630) is entered into a text input window via a keyboard UI, the electronic device may generate at least one recommended answer (640) by further utilizing the entered text (630) as well as selected summary information and multiple messages related to the selected summary information. According to one embodiment, the text (630) may include one or more words or a sentence containing one or more words. For example, the electronic device may use the selected summary information, multiple messages related to the selected summary information, and the entered text (630) as input data for an artificial intelligence model (e.g., LLM) to obtain at least one recommended answer (640) as output data. According to one embodiment, at least one recommended answer (640) may include the entered text (630).

[0156] According to one embodiment, the prompt template input to the artificial intelligence model may be as shown in [Table 2] below.

[0157] User # selected Summary #1, "Decided to eat sashimi," from the [Topic Summary] that summarizes the [Conversation Content] below. Additionally, the user wants to create their desired response message using the [Simple Text] below. Considering the intent conveyed in the [Simple Text] below from User #'s perspective, please generate three response messages that can be used in the conversation regarding the selected summary. - Create appropriate response messages by referring to the [Conversation Content] below. - Maintain a sentence style similar to User #'s tone in the [Conversation Content] below. - Keep each response message within 10 words. - If necessary, use the [User Info] below to generate responses tailored to the user's situation. [Simple Text]# Simple Text #[Conversation Content]# Input conversation content #[Topic Summary]# Topic summary information generated via previous LLM #[User Info]# Search history ## Other message history ## User preferences #...

[0158] According to one embodiment, a prompt input to an artificial intelligence model may include multiple response generation criteria for generating a response. For example, the prompt may include criteria for generating a recommendation message that is similar to the user's tone of voice (e.g., a recommendation message with a sentence style similar to the user's tone of voice) by utilizing the user conversation content. For example, the prompt may include criteria for the length of each recommendation message (e.g., within 10 words). In this way, by further utilizing the text input by the user, a recommendation response containing the user's intent or will can be generated.

[0159] FIG. 7 is a diagram illustrating the recommended answer regeneration operation of an electronic device according to one embodiment.

[0160] Referring to FIG. 7, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display a list of dialog boxes containing a dialog box (711) containing an unread message through the execution screen (710) of a message application.

[0161] According to one embodiment, when the electronic device receives user input selecting a dialog box (711) containing unread messages, it may display a plurality of summary information (720) obtained based on unread messages. The plurality of summary information (720) may be obtained by analyzing the conversation content of a plurality of unread messages using an artificial intelligence model.

[0162] According to one embodiment, when a user input is received in which the electronic device selects a UI (721) for receiving an input guide (or recommended answer) and selects one summary information (730) among a plurality of summary information, the electronic device may display a recommended answer (731) corresponding to the selected summary information (730). According to one embodiment, when a user input is received in which the electronic device selects one summary information (730) among a plurality of summary information and selects a UI (721) for receiving an input guide, the electronic device may display a recommended answer (731) corresponding to the selected summary information (730).

[0163] According to one embodiment, when a user input is received selecting two or more summary information (730, 740) among a plurality of summary information, the electronic device can generate a recommended answer based on the selected two or more summary information (730, 740).

[0164] According to one embodiment, when the electronic device receives user input selecting a UI (741) for regenerating recommended answers, it may display a list of recommended answers (750) that includes newly generated recommended answers in addition to the displayed recommended answers. According to one embodiment, when the electronic device receives user input selecting a UI (741) for regenerating recommended answers, it may delete the displayed recommended answers and display new recommended answers.

[0165] FIG. 8a is a diagram illustrating the operation of highlighting a message corresponding to selected summary information of an electronic device according to one embodiment.

[0166] Referring to FIG. 8a, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display a list of dialog boxes containing a dialog box (811) containing an unread message through the execution screen (810) of a message application.

[0167] According to one embodiment, when the electronic device receives user input selecting a conversation window (811) containing unread messages, it may display a plurality of summary information (820) obtained based on unread messages. The plurality of summary information (820) may be obtained by analyzing the conversation content of the plurality of unread messages using an artificial intelligence model. According to one embodiment, the plurality of summary information (820) may include topic-based summary information and conversationalist information.

[0168] According to one embodiment, the electronic device may receive user input selecting at least one summary information among a plurality of summary information (820). For example, when the electronic device receives user input selecting one of a plurality of conversational partners (821), it may display summary information (830) generated based on the message of the selected conversational partner (821). For example, the electronic device may display the summary information (830) as a banner-type pop-up screen in a part area (e.g., top) of the execution screen of the message application. According to one embodiment, the summary information (830) may include topic-specific summary information generated based on the message of the selected conversational partner (821).

[0169] According to one embodiment, the electronic device can highlight a message (831) of a selected conversationalist (821) among a plurality of messages currently displayed.

[0170] According to one embodiment, when the electronic device receives user input to change the summary information included in the popup screen containing the summary information (830), the summary information included in the popup screen may change the summary information included in the popup screen. For example, when the electronic device receives input (832) of selecting the popup screen containing the summary information (830) and swiping left or right, the summary information (830) generated based on the message of the selected conversationalist (821) may be changed to summary information (840) generated based on the message of another conversationalist. For example, the electronic device may change the summary information to summary information (840) generated based on the message of another conversationalist among a plurality of messages currently displayed.

[0171] According to one embodiment, the electronic device can highlight the changed conversationalist's message (841) among a plurality of messages currently displayed.

[0172] FIG. 8b is a diagram illustrating the operation of an electronic device according to one embodiment, which generates new summary information based on user input and highlights a message corresponding to the newly generated summary information.

[0173] Referring to FIG. 8b, when the electronic device receives user input selecting a UI (850) to check details of summary information on a popup screen containing summary information, the device may further display details (860) related to the summary information on the popup screen. According to one embodiment, the electronic device may increase the size of the popup screen and further display details (860) related to the summary information within the increased popup screen. For example, details (860) related to the summary information may include details regarding the relationship with other conversational partners within the conversation window in relation to the topic of the summary information.

[0174] According to one embodiment, the electronic device may move a plurality of currently displayed messages out of the screen and, upon receiving user input to display a new message, additionally display summary information (871) generated based on the new message on the popup screen. For example, the electronic device may move at least some of the displayed plurality of messages out of the screen and display a new message based on receiving input (861) to scroll the displayed plurality of messages. According to one embodiment, the electronic device may generate summary information (871) based on a conversational message (870) that has a history of being displayed on the screen via scrolling and display it on the popup screen. For example, the electronic device may add summary information generated by a newly displayed message via scrolling input to the existing summary information and display it on the popup screen.

[0175] FIG. 9a is a diagram illustrating the operation of changing summary information selected according to user input and highlighting a message corresponding to the changed summary information of an electronic device according to one embodiment.

[0176] Referring to FIG. 9a, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display a list of dialog boxes containing a dialog box (911) containing an unread message through the execution screen (910) of a message application.

[0177] According to one embodiment, when the electronic device receives user input selecting a conversation window (911) containing unread messages, it may display a plurality of summary information obtained based on unread messages. The plurality of summary information may be obtained by analyzing the conversation content of the plurality of unread messages using an artificial intelligence model. According to one embodiment, the plurality of summary information may include topic-based summary information and conversationalist information.

[0178] According to one embodiment, the electronic device may receive user input selecting at least one summary information among a plurality of summary information. For example, when the electronic device receives user input selecting summary information (920) of one topic among the topic-specific summary information, it may display summary information (930) generated based on the message of the selected summary information (920). For example, the electronic device may display the summary information (930) as a banner-type pop-up screen in a part area (e.g., top) of the execution screen of a message application. According to one embodiment, the summary information (930) may be generated based on a message corresponding to the summary information (920) of the selected topic.

[0179] According to one embodiment, the electronic device can highlight the corresponding messages (931, 932, 933) of the summary information (920) of a selected topic among a plurality of currently displayed messages.

[0180] According to one embodiment, when the electronic device receives user input to change the summary information included in the popup screen containing the summary information (930), the electronic device can change the summary information included in the popup screen. For example, when the electronic device receives input (934) of selecting the popup screen containing the summary information (930) and swiping left or right, the summary information (920) of the selected topic can be changed to the summary information (940) of another topic. For example, the electronic device can change the summary information to the summary information (940) generated based on a message related to another topic among a plurality of messages currently displayed.

[0181] According to one embodiment, the electronic device can highlight a message (941) related to a changed topic among a plurality of messages currently displayed.

[0182] According to one embodiment, when the electronic device receives an input (942) that selects a popup screen containing changed summary information (940) and swipes left or right, it can change the changed summary information (940) to summary information of another topic.

[0183] FIG. 9b is a diagram illustrating the operation of an electronic device according to one embodiment, which generates new summary information based on user input and highlights a message corresponding to the newly generated summary information.

[0184] Referring to FIG. 9b, when the electronic device selects a popup screen containing changed summary information (e.g., changed summary information (940) of FIG. 9a) as shown in FIG. 9a and receives an input to swipe left or right (e.g., swipe input (942) of FIG. 9a), the changed summary information can be changed to summary information (950) of another topic.

[0185] According to one embodiment, the electronic device can highlight a message (951) related to a changed topic among a plurality of messages currently displayed.

[0186] When the electronic device receives user input selecting a UI (952) to check details of summary information on a popup screen containing summary information, it may further display details (960) related to the summary information on the popup screen. According to one embodiment, the electronic device may increase the size of the popup screen and further display details (960) related to the summary information within the increased popup screen. For example, details (960) related to the summary information may include details based on messages from other conversationalists within the conversation window regarding the subject of the summary information.

[0187] According to one embodiment, the electronic device may move a plurality of currently displayed messages out of the screen and, upon receiving user input to display more new messages, additionally display summary information (974) generated based on new messages (971, 972, 973) on the popup screen. For example, the electronic device may move at least some of the displayed plurality of messages out of the screen and display new messages (971, 972, 973) based on receiving input (961) for scrolling the plurality of displayed messages. According to one embodiment, the electronic device may generate summary information (974) based on a conversational message (970) that has a history of being displayed on the screen via scrolling and display it on the popup screen. For example, the electronic device may add summary information generated by a newly displayed message via scrolling input to existing summary information and display it on the popup screen.

[0188] FIG. 10 is a flowchart illustrating the operation of generating a recommended answer based on external information of an electronic device according to one embodiment.

[0189] In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0190] According to one embodiment, operations 1010 to 1060 may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1).

[0191] Referring to FIG. 10, in operation 1010, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) can perform a summary using an LLM (or artificial intelligence model) and display multiple contexts (or summary information).

[0192] According to one embodiment, an electronic device may use multiple unread messages of a conversation window as input data for an LLM to obtain multiple contexts as output data. According to one embodiment, the context relates to the context of a conversation through messages and may include summary information by topic of the message or summary information by conversational partner.

[0193] According to one embodiment, in operation 1020, the electronic device can select a context based on user input.

[0194] According to one embodiment, the electronic device may display a plurality of contexts in a list form and receive user input selecting at least one of the plurality of contexts.

[0195] According to one embodiment, in operation 1030, the electronic device may acquire a plurality of external information. According to one embodiment, the plurality of external information may include conversation content of another dialog window of a message application and / or information of an application other than the message application (e.g., another message application, a calendar application, a memo application). According to one embodiment, the plurality of external information may include information related to a plurality of contexts and / or information related to at least one context selected among the plurality of contexts.

[0196] According to one embodiment, in operation 1040, the electronic device can measure similarity with a context selected from a plurality of external information.

[0197] According to one embodiment, an electronic device may convert each piece of information into a vector through a language model (LM) (e.g., BERT (bidirectional encoder representation from transformer)) to determine the similarity between acquired external information and a selected context, and calculate the cosine similarity between the vectors of each piece of information. However, the method of measuring (e.g., calculating) the similarity is not limited to the cosine similarity described above. For example, to measure the similarity, a Jaccard similarity technique or a TF-IDF (term frequency inverse document frequency) technique may be used. In one embodiment, the similarity may include semantic similarity.

[0198] According to one embodiment, in operation 1050, the electronic device may determine related external information based on similarity. For example, the electronic device may determine that among a plurality of external information, information with a cosine similarity higher than a set value is external information related to the selected context.

[0199] According to one embodiment, in operation 1060, the electronic device can generate a recommendation message based on external information and context.

[0200] According to one embodiment, the electronic device may use an artificial intelligence model (e.g., LLM) to generate at least one recommendation message (or recommendation answer) based on selected context and determined external information.

[0201] FIG. 11 is a diagram illustrating the operation of generating a recommended answer based on external information of an electronic device according to one embodiment.

[0202] Referring to FIG. 11, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display a list of dialog boxes containing a dialog box (1111) containing an unread message through the execution screen (1110) of a message application.

[0203] According to one embodiment, when the electronic device receives user input selecting a dialog box (1111) containing unread messages, it may display a plurality of summary information (1120) obtained based on unread messages. The plurality of summary information (1120) may be obtained by analyzing the conversation content of the plurality of unread messages using an artificial intelligence model. According to one embodiment, the plurality of summary information (1120) may include a UI (1121, 1122) for obtaining external information. For example, the UI (1121, 1122) for obtaining external information may include at least one of a UI (1121) for obtaining summary information from another dialog box or a UI (1122) for obtaining information from another application.

[0204] According to one embodiment, when the electronic device receives user input selecting a UI (1121) for obtaining summary information from another chat window, it may additionally display summary information (1130, 1131) for unread messages from another chat window in addition to the summary information in the current chat window. According to one embodiment, the electronic device may highlight (e.g., bold) the content related to the summary information in the current chat window among the summary information (1130, 1131) for unread messages from another chat window.

[0205] According to one embodiment, when the electronic device receives user input selecting a UI (1122) for obtaining information of another application, it may further display information of another application (1140, 1141) related to the summary information in the current dialog box.

[0206] According to one embodiment, the electronic device can determine an external application to retrieve information based on the type of information included in the summary information in the current dialog box. For example, if the information included in the summary information is location information, information from a map application can be obtained; if it is a person, search results from an internet application or a contact application can be obtained; and if it is a date, information from a calendar application can be obtained.

[0207] For example, the electronic device may display search results (1140) of an internet application for 'A developer' included in the summary information in the current dialog box. According to one embodiment, the electronic device may display search results (1141) of a map application for a place (e.g., region, restaurant) included in the summary information in the current dialog box.

[0208] According to one embodiment, when the electronic device receives user input selecting information (1140, 1141) of another application, it can display an execution screen of the application corresponding to the selected information.

[0209] FIG. 12 is a diagram illustrating the operation of generating a recommended answer based on external information of an electronic device according to one embodiment.

[0210] Referring to FIG. 12, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) can display at least one recommended answer (1210) generated based on at least one selected summary information.

[0211] According to one embodiment, when a user input selecting a UI (1211) for obtaining external information is received, the electronic device may include a UI (1220, 1221) for obtaining external information. For example, the UI (1220, 1221) for obtaining external information may include at least one of a UI (1220) for obtaining summary information from another dialog box or a UI (1221) for obtaining information from another application.

[0212] According to one embodiment, when the electronic device receives user input selecting a UI (1222) to return to a previous screen, it can delete a UI (1220, 1221) for obtaining external information and display at least one recommended answer (1210).

[0213] According to one embodiment, when the electronic device receives user input selecting a UI (1220) for obtaining summary information from another chat window, it may additionally display summary information (1230) for unread messages from another chat window in addition to the summary information in the current chat window. According to one embodiment, when the electronic device receives user input selecting at least one of the summary information (1230) for unread messages from another chat window, it may display a recommended answer generated based on at least one summary information selected from the summary information of the current chat window and at least one summary information selected from the summary information of another chat window.

[0214] According to one embodiment, when user input is received to select a UI (1231) for displaying a previous screen while summary information (1230) for unread messages in another dialog box is displayed, a screen displaying a UI (1220, 1221) for obtaining external information may be displayed.

[0215] According to one embodiment, when the electronic device receives user input selecting a UI (1221) for obtaining information of another application, it may further display information of another application (1240, 1241) related to the summary information in the current dialog box.

[0216] According to one embodiment, when the electronic device receives user input selecting at least one (1240) of information (1240, 1241) of another application, it may display a recommended answer (1250) generated based on at least one summary information selected from the summary information of the current dialog box and the selected information (1240) of another application.

[0217] According to one embodiment, when user input is received selecting one of a plurality of recommended answers, the electronic device may display the selected recommended answer in the text input window of the dialog box or input it as a user's dialogue in the dialog box.

[0218] FIGS. 13a and FIGS. 13b are drawings for explaining a recommended answer regeneration operation based on external information of an electronic device according to one embodiment.

[0219] Referring to FIGS. 13a and 13b, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may additionally display a newly generated recommended answer (1320) when a user input (1311) is received to select a UI for regenerating a recommended answer, while at least one recommended answer (1310) generated based on at least one summary information selected from a plurality of summary information generated based on a plurality of unread messages in a dialog box is displayed.

[0220] According to one embodiment, when a user input (1321) is received to select a UI for regenerating a recommended answer while a newly generated recommended answer (1320) is displayed, a newly generated recommended answer (1330) may be additionally displayed.

[0221] According to one embodiment, when the electronic device receives user input selecting a UI for regenerating a recommended answer n times (e.g., 3 times) or more, it may display a UI (1331) for generating a recommended answer using external information.

[0222] According to one embodiment, when user input is received for selecting a UI (1331) to generate a recommended answer using external information, the electronic device may display at least one recommended answer (1332, 1333) generated by further using summary information of another dialog box or information of another application related to at least one selected summary information.

[0223] According to one embodiment, when user input is received selecting one (1333) of at least one recommended answer (1332, 1333), the electronic device may display the selected recommended answer (1333) in the text input window (1340) of the dialog box or input it as a user's conversation in the dialog box.

[0224] According to one embodiment, when a user input is received to select a UI (1341) for displaying a previous screen while a selected recommended answer (1333) is displayed in the text input window (1340) of a dialog box, the electronic device may display at least one recommended answer (1332, 1333).

[0225] FIG. 14 is a flowchart illustrating the operation of displaying a generated recommended answer of an electronic device according to one embodiment as an answer to a specific conversationalist's message.

[0226] In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0227] According to one embodiment, operations 1410 to 1440 may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1).

[0228] FIG. 15 is a diagram illustrating the operation of displaying a generated recommended answer of an electronic device according to one embodiment as an answer to a specific conversationalist's message.

[0229] Referring to Fig. 14, in operation 1410, the electronic device can generate a recommended answer message based on the selected context and brief text.

[0230] According to one embodiment, an electronic device can use multiple unread messages from a dialog box as input data for an artificial intelligence model (e.g., LLM) to obtain multiple contexts (or summary information) as output data.

[0231] According to one embodiment, the electronic device can generate at least one recommended answer message (or recommended answer) based on at least one context selected by user input among a plurality of contexts. According to one embodiment, the electronic device can generate at least one recommended answer message based on at least one selected context, a plurality of messages corresponding to the selected at least one context, and brief text (or text) entered by the user using an artificial intelligence model.

[0232] For example, as illustrated in FIG. 15, the electronic device can display at least one recommended answer (1510) generated based on at least one selected context.

[0233] According to one embodiment, in the operation of 1420, the electronic device can determine a plurality of dialogue units corresponding to the selected context.

[0234] According to one embodiment, an electronic device may identify two or more messages corresponding to a selected context among a plurality of messages, and determine each of the identified two or more messages as a conversation unit. Each conversation unit may include different detailed contexts based on the content of the message.

[0235] According to one embodiment, in operation 1430, the electronic device can determine a relevant conversation unit among a plurality of conversation units based on similarity with a recommended answer message.

[0236] According to one embodiment, the electronic device may select the conversation unit most closely related to a recommended answer message (or recommended answer) among a plurality of conversation units through similarity measurement. According to one embodiment, the electronic device may convert each conversation unit and the recommended answer into vectors through a language model (e.g., BERT) for similarity measurement and calculate the cosine similarity between the vectors of each conversation unit and the recommended answer. However, the method of measuring (e.g., calculating) the similarity is not limited to the cosine similarity described above.

[0237] According to one embodiment, the electronic device can determine the conversation unit with the highest cosine similarity to the recommended answer among a plurality of conversation units.

[0238] According to one embodiment, in operation 1440, the electronic device can create and display a reply UI object based on a relevant conversation unit and a recommended answer.

[0239] According to one embodiment, the electronic device may display a recommended answer in the form of a response from a conversation unit determined to have the highest similarity to the recommended answer.

[0240] According to one embodiment, as illustrated in FIG. 15, when a user input selecting a recommended answer (1510) is selected, the electronic device can display the selected recommended answer in the text input window (1520) of the dialog box.

[0241] According to one embodiment, when the electronic device receives user input to send a recommended answer displayed in a text input window (1520) as a message, it may display the recommended answer in the form of a response (1530) of a conversation unit determined to have the highest similarity to the recommended answer.

[0242] FIG. 16 is a diagram illustrating an operation to provide summary information according to a set schedule when there are many summary topics for unread messages of an electronic device according to one embodiment.

[0243] Referring to FIG. 16, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display at least one selected summary information (1610) (e.g., topic-specific summary information and / or conversational information) among a plurality of summary information obtained based on unread messages as a banner-type pop-up screen.

[0244] According to one embodiment, the electronic device can highlight a message (1611) corresponding to summary information included in a pop-up screen among a plurality of messages currently displayed.

[0245] According to one embodiment, the electronic device may move a plurality of currently displayed messages out of the screen and, upon receiving user input to display a new message, additionally display summary information (1620) generated based on the new message on the popup screen. For example, the electronic device may move at least some of the displayed plurality of messages out of the screen and display a new message based on receiving input (1612) to scroll the displayed plurality of messages. According to one embodiment, the electronic device may generate summary information (1620) based on the conversational messages (1621, 1622) that have a history of being displayed on the screen via scrolling and display them on the popup screen. For example, the electronic device may add summary information generated by the newly displayed message via the scroll input to the existing summary information and display it on the popup screen.

[0246] According to one embodiment, the electronic device can add (1630) newly generated summary information to the popup screen in real time at the point where the summary information of the displayed multiple messages changes, depending on the speed or number of times the input (1612) scrolls the displayed multiple messages.

[0247] According to one embodiment, if a scrolling input (1612) is detected more than a set number of times, and different summary information is generated with the same text, the electronic device may determine that the summary information is difficult to identify. According to one embodiment, the electronic device may display a pop-up screen so that the summary information can be received according to the schedule associated with each summary information. For example, the electronic device may display the execution screen (1640) of a calendar application as a pop-up screen to display each summary information as a schedule for the associated date.

[0248] FIG. 17 is a drawing for explaining the form of a summary information card displayed on the execution screen of a message application of an electronic device according to one embodiment.

[0249] Referring to FIG. 17, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display a pop-up screen (1710) containing summary information as the top layer of the execution screen of a message application. According to one embodiment, the pop-up screen (1710) containing summary information may have a size of more than half the size of the execution screen of the message application.

[0250] According to one embodiment, when the electronic device receives user input (1711) selecting an area other than the popup screen (1710) containing summary information, the size of the popup screen (1710) containing summary information can be changed to a minimum size indicator (1720) (e.g., in the form of a chip). According to one embodiment, by displaying the popup screen (1710) containing summary information as an indicator (1720), the electronic device can display multiple messages of a dialog box.

[0251] According to one embodiment, when an input (1721) of swiping an indicator (1720) is received, the electronic device may display a banner-shaped pop-up screen (1730) at the top of the execution screen of a message application. According to one embodiment, the electronic device may display summary information in a condensed form through the banner-shaped pop-up screen (1730) and display multiple messages of a conversation window.

[0252] According to one embodiment, a banner-shaped popup screen (1730) may include a UI for displaying additional details. When user input is received to select the UI for displaying additional details, the size of the banner-shaped popup screen (1730) is increased to display additional details, and the UI for displaying additional details may be changed to a UI for displaying only summarized information. According to one embodiment, when the UI for displaying only summarized information is selected while the size of the banner-shaped popup screen (1730) is increased, the size of the popup screen (1730) may be reduced again.

[0253] FIG. 18 is a drawing for explaining the form of a summary information card displayed on the execution screen of a message application of an electronic device according to one embodiment.

[0254] Referring to FIG. 18, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display a pop-up screen (1810) containing summary information as the top layer of the execution screen of a message application. According to one embodiment, the pop-up screen (1810) containing summary information may have a size of more than half the size of the execution screen of the message application.

[0255] According to one embodiment, when a user input (1811) is received to change a popup screen (1810) containing summary information into a bar shape, a portion of the execution screen of the message application can be changed into a vertical bar-shaped popup screen (1820). According to one embodiment, the vertical bar-shaped popup screen (1820) may include a number (e.g., a number or a character) representing each summary information. According to one embodiment, as the electronic device displays the vertical bar-shaped popup screen (1820), the electronic device can display a plurality of messages of a conversation window.

[0256] According to one embodiment, when user input is received for selecting a UI (1821) to check overall summary information among the numbers included in a vertical bar-shaped popup screen (1820), the electronic device can display a popup screen (1810) containing summary information.

[0257] According to one embodiment, when the electronic device receives user input selecting a number (1822) (e.g., number 1) corresponding to specific summary information among the numbers included in a vertical bar-shaped pop-up screen (1820), the electronic device may display summary information (1830) corresponding to the selected number (1822). According to one embodiment, after displaying the summary information (1830) corresponding to the selected number (1822) and after a set time has elapsed, the electronic device may disable the display of the summary information (1830) corresponding to the selected number (1822) and highlight a plurality of messages (1831, 1832) corresponding to the summary information (1830).

[0258] According to one embodiment, when the electronic device receives user input selecting a number (1823) (e.g., the letter C) corresponding to specific summary information among the numbers included in a vertical bar-shaped pop-up screen (1820), the electronic device may display conversational information (1840) corresponding to the selected number (1823). According to one embodiment, the electronic device may highlight at least one message corresponding to the conversational information (1840) among a plurality of displayed messages.

[0259] FIG. 19 is a diagram illustrating the operation of graphically displaying summary information of unread messages of an electronic device according to one embodiment.

[0260] Referring to FIG. 19, an electronic device (e.g., the electronic device (101) of FIG. 1 or the processor (120) of FIG. 1) may display a list of dialog boxes containing a dialog box (1911) containing an unread message through the execution screen (1910) of a message application.

[0261] According to one embodiment, when the electronic device receives user input selecting a dialog box (1911) containing unread messages, it can display a plurality of summary information obtained based on unread messages in the form of a list (1920).

[0262] According to one embodiment, the electronic device may display a plurality of summary information in a graphic form (1930). For example, the electronic device may display different sizes of UIs corresponding to a conversationalist based on the number of messages per conversationalist among the unread messages. For example, if the number of messages for conversationalist A is the highest, the size of the UI corresponding to A may be displayed as the largest.

[0263] According to one embodiment, the electronic device can display words or sentences frequently mentioned by each conversationalist on a UI corresponding to the conversationalist.

[0264] According to one embodiment, when displaying topic-specific summary information in a graphical form, the electronic device may display the size of the UI corresponding to the topic-specific summary information differently based on the number of messages related to the topic-specific summary information among the unread messages. For example, if the number of messages related to the summary information of the first topic is the largest, the size of the UI corresponding to the summary information of the first topic may be displayed as the largest.

[0265] According to one embodiment, the electronic device can display frequently mentioned words or sentences by topic in a UI corresponding to topic-specific summary information.

[0266] According to one embodiment, the electronic device may include a display, at least one processor including a processing circuit, and a memory for storing instructions.

[0267] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may obtain multiple summary information related to multiple unread messages using an artificial intelligence model based on the reception of a first user input for summarizing multiple unread messages, while multiple unread messages are included in a dialog box.

[0268] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may display the plurality of summary information.

[0269] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may receive a second user input selecting at least one summary information among the plurality of summary information.

[0270] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may generate at least one recommended answer based on the at least one summary information using the artificial intelligence model.

[0271] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be able to display the at least one recommended answer.

[0272] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may generate a plurality of recommended answers based on at least one of the first summary information or the second summary information using the artificial intelligence model, based on the reception of the second user input selecting a plurality of summary information including a first summary information and a second summary information among the plurality of summary information.

[0273] According to one embodiment, the plurality of recommended answers may include recommended answers generated based on the first summary information and the second summary information.

[0274] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be able to identify a first plurality of messages corresponding to the selected at least one summary information among the unread plurality of messages.

[0275] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may generate the at least one recommended answer by further using the first plurality of messages.

[0276] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may receive a third user input that inputs at least one text related to the at least one summary information.

[0277] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may generate the at least one recommended answer using the at least one text further.

[0278] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may generate the at least one recommended answer based on at least one of summary information related to a plurality of unread messages included in the dialog box and another dialog box, or information of an application related to the at least one summary information.

[0279] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may display at least one of the summary information related to the plurality of unread messages included in the other dialog box or the information of the application as the plurality of summary information.

[0280] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may generate the at least one recommended answer based on the at least one summary information selected by the second user input and the at least one summary information selected by the fourth user input, based on receiving a fourth user input selecting at least one of the summary information related to the plurality of unread messages included in the other dialog box or the information of the application.

[0281] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may regenerate at least one recommended answer by further using at least one of summary information related to the plurality of unread messages included in the other dialog box or information of the application, based on the reception of a fifth user input for regenerating the recommended answer after the at least one recommended answer is displayed.

[0282] According to one embodiment, the plurality of summary information may include topic-specific summary information and a plurality of conversationalist information of the conversation window.

[0283] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be able to confirm a second plurality of messages of the at least one interlocutor based on the reception of the second user input selecting at least one interlocutor among the plurality of interlocutors.

[0284] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may display summary information of the subject of at least some of the second plurality of messages.

[0285] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be able to highlight at least some of the second plurality of messages among the unread plurality of messages.

[0286] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may display summary information of a subject different from the subject based on the reception of a sixth user input for changing the summary information of the subject.

[0287] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be able to highlight at least some of the third plurality of messages related to the other subject among the unread plurality of messages.

[0288] According to one embodiment, a control method for an electronic device may include an operation of obtaining a plurality of summary information related to a plurality of unread messages using an artificial intelligence model based on receiving a first user input for summarizing a plurality of unread messages while a plurality of unread messages are included in a dialog box.

[0289] According to one embodiment, a control method for an electronic device may include an operation of displaying the plurality of summary information.

[0290] According to one embodiment, a control method for an electronic device may include receiving a second user input that selects at least one summary information among the plurality of summary information.

[0291] According to one embodiment, a control method for an electronic device may include an operation of generating at least one recommended answer based on at least one summary information using the artificial intelligence model.

[0292] According to one embodiment, a control method for an electronic device may include an operation of displaying the at least one recommended answer on a display of the electronic device.

[0293] According to one embodiment, the operation of generating at least one recommended answer may generate a plurality of recommended answers based on at least one of the first summary information or the second summary information by using the artificial intelligence model, based on the reception of the second user input selecting a plurality of summary information including a first summary information and a second summary information among the plurality of summary information.

[0294] According to one embodiment, the plurality of recommended answers may include recommended answers generated based on the first summary information and the second summary information.

[0295] According to one embodiment, the control method of an electronic device may further include an operation of checking a first plurality of messages corresponding to at least one selected summary information among the unread plurality of messages.

[0296] According to one embodiment, the operation of generating the at least one recommended answer may generate the at least one recommended answer by further utilizing the first plurality of messages.

[0297] According to one embodiment, the control method of an electronic device may further include the operation of receiving a third user input that inputs at least one text related to the at least one summary information.

[0298] According to one embodiment, the operation of generating the at least one recommended answer may generate the at least one recommended answer by further using the at least one text.

[0299] According to one embodiment, the operation of generating at least one recommended answer may generate the at least one recommended answer based on at least one of summary information related to a plurality of unread messages included in another dialog box or information of an application related to the at least one summary information.

[0300] According to one embodiment, the control method of an electronic device may further include an operation of displaying at least one of the summary information related to the plurality of unread messages included in the other dialog box or the information of the application as the plurality of summary information.

[0301] According to one embodiment, the operation of generating the at least one recommended answer may generate the at least one recommended answer based on the at least one summary information selected by the second user input and the at least one summary information selected by the fourth user input, based on the reception of a fourth user input selecting at least one of the summary information related to the plurality of unread messages included in the other dialog box or the information of the application.

[0302] According to one embodiment, the operation of generating at least one recommended answer may, based on receiving a fifth user input for regenerating the recommended answer after displaying the at least one recommended answer, further utilize at least one of summary information related to the plurality of unread messages included in the other dialog box or information of the application to regenerate at least one recommended answer.

[0303] According to one embodiment, the plurality of summary information may include topic-specific summary information and a plurality of conversationalist information of the conversation window.

[0304] According to one embodiment, the control method of an electronic device may further include an operation of checking a second plurality of messages of at least one conversational partner based on receiving a second user input selecting at least one conversational partner among the plurality of conversational partners.

[0305] According to one embodiment, the control method of an electronic device may further include an operation of displaying summary information of at least some of the topics of the second plurality of messages.

[0306] According to one embodiment, the control method of an electronic device may further include the operation of highlighting at least some of the second plurality of messages among the unread plurality of messages.

[0307] According to one embodiment, in a non-transient computer-readable storage medium storing one or more programs, the one or more programs may include instructions for an electronic device to obtain a plurality of summary information related to the plurality of unread messages using an artificial intelligence model based on receiving a first user input for summarizing the plurality of unread messages, while the plurality of unread messages are included in a dialog box.

[0308] According to one embodiment, the one or more programs may include instructions that cause the electronic device to display the plurality of summary information.

[0309] According to one embodiment, the one or more programs may include instructions that cause the electronic device to receive a second user input selecting at least one summary information among the plurality of summary information.

[0310] According to one embodiment, the one or more programs may include instructions that cause the electronic device to generate at least one recommended answer based on at least one summary information using the artificial intelligence model.

[0311] According to one embodiment, the one or more programs may include instructions that cause the electronic device to display the at least one recommended answer.

[0312] According to one embodiment, the one or more programs may include instructions that cause the electronic device to generate a plurality of recommended answers based on at least one of the first summary information or the second summary information by using the artificial intelligence model, based on the reception of the second user input in which the electronic device selects a plurality of summary information including a first summary information and a second summary information among the plurality of summary information.

[0313] According to one embodiment, the plurality of recommended answers may include recommended answers generated based on the first summary information and the second summary information.

[0314] According to one embodiment, the one or more programs may include instructions that cause the electronic device to check a first plurality of messages corresponding to at least one selected summary information among the unread plurality of messages.

[0315] According to one embodiment, the one or more programs may include instructions that cause the electronic device to generate the at least one recommended answer by further using the first plurality of messages.

[0316] According to one embodiment, the one or more programs may include instructions that cause the electronic device to receive a third user input that inputs at least one text related to the at least one summary information.

[0317] According to one embodiment, the one or more programs may include instructions that cause the electronic device to generate the at least one recommended answer by further using the at least one text.

[0318] According to one embodiment, the one or more programs may include instructions that cause the electronic device to generate the at least one recommended answer based on at least one of summary information related to a plurality of unread messages included in the dialog box and another dialog box, or information of an application related to the at least one summary information.

[0319] According to one embodiment, the one or more programs may include instructions that cause the electronic device to display at least one of summary information related to the plurality of unread messages included in the other dialog box or information of the application as the plurality of summary information.

[0320] According to one embodiment, the one or more programs may include instructions that cause the electronic device to generate the at least one recommended answer based on the at least one summary information selected by the second user input and the at least one summary information selected by the fourth user input, based on the reception of a fourth user input selecting at least one of the summary information related to the plurality of unread messages included in the other dialog box or the information of the application.

[0321] According to one embodiment, the one or more programs may include instructions that cause the electronic device to regenerate at least one recommended answer by further utilizing at least one of summary information related to the plurality of unread messages included in the other dialog box or information of the application, based on the reception of a fifth user input for regenerating the recommended answer after the display of at least one recommended answer.

[0322] According to one embodiment, the plurality of summary information may include topic-specific summary information and a plurality of conversationalist information of the conversation window.

[0323] According to one embodiment, the one or more programs may include instructions that cause the electronic device to check a second plurality of messages of the at least one interlocutor based on the reception of a second user input selecting at least one interlocutor among the plurality of interlocutors.

[0324] According to one embodiment, the one or more programs may include instructions that cause the electronic device to display summary information of at least some of the topics of the second plurality of messages.

[0325] According to one embodiment, the one or more programs may include instructions that cause the electronic device to highlight at least some of the second plurality of messages among the unread plurality of messages.

[0326] According to one embodiment, the one or more programs may cause the electronic device to display summary information of a subject different from the subject based on the reception of a sixth user input for changing the summary information of the subject.

[0327] According to one embodiment, the one or more programs may include instructions that cause the electronic device to highlight at least some of the third plurality of messages related to the other subject among the unread plurality of messages.

[0328] The electronic device according to the embodiments disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the devices described above.

[0329] The embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said 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 said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" each may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as “coupled” or “connected” to another (e.g., 2nd) component, with or without the terms “functionally” or “communicationly,” it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0330] The term “module” as used in the 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, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof 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).

[0331] One embodiment of the present document may be implemented as software (e.g., program (140)) comprising one or more instructions stored in a storage medium (e.g., internal memory (136) or external memory (138)) readable by a machine (e.g., electronic device (101)). For example, a processor (e.g., processor (120)) of the machine (e.g., electronic device (101)) may call at least one of the one or more instructions stored in the storage medium and execute it. This enables the machine to be operated to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0332] According to one embodiment, the method according to the embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through 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 created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0333] According to one embodiment, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to one embodiment, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the components of the multiple components in the same or similar manner as those performed by the corresponding components among the multiple components prior to integration. According to one embodiment, operations performed by the module, program, or other components 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 an electronic device, display; At least one processor including a processing circuit; and It includes memory for storing instructions, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Based on the reception of a first user input for summarizing the multiple unread messages while the chat window contains multiple unread messages, multiple summary information related to the multiple unread messages is obtained using an artificial intelligence model, and Displaying the above multiple summary information, and Receiving a second user input that selects at least one summary information among the plurality of summary information above, Using the above artificial intelligence model, at least one recommended answer is generated based on the above at least one summary information, and An electronic device that enables the display of at least one recommended answer.

2. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Based on the reception of the second user input selecting a plurality of summary information including a first summary information and a second summary information among the plurality of summary information, the artificial intelligence model is used to generate a plurality of recommended answers based on at least one of the first summary information or the second summary information. The above multiple recommended answers are, An electronic device comprising recommended answers generated based on the above-mentioned first summary information and the above-mentioned second summary information.

3. In Paragraph 1 or 2, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Among the above unread multiple messages, identify the first multiple messages corresponding to the selected at least one summary information, and An electronic device that generates at least one recommended answer by further utilizing the above first plurality of messages.

4. In any one of paragraphs 1 through 3, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Receiving a third user input that inputs at least one keyword related to the above at least one summary information, and An electronic device that generates at least one recommended answer by further using at least one keyword.

5. In any one of paragraphs 1 through 4, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that generates at least one recommended answer based on at least one of summary information related to multiple unread messages included in the above-mentioned conversation window and another conversation window, or information of an application related to the at least one summary information.

6. In Paragraph 5, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, At least one of the summary information related to the plurality of unread messages included in the aforementioned other dialog box or the information of the aforementioned application is displayed as the plurality of summary information, and An electronic device that generates at least one recommended answer based on at least one summary information selected by the second user input and at least one summary information selected by the fourth user input, based on receiving at least one summary information related to the plurality of unread messages included in the other dialog box or information of the application.

7. In Paragraph 5, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that, based on receiving a fifth user input for regenerating a recommended answer after displaying at least one recommended answer, further utilizes at least one of summary information related to a plurality of unread messages included in the other dialog box or information of the application to regenerate at least one recommended answer.

8. In any one of paragraphs 1 through 7, The above multiple summary information is, It includes summary information by topic and information on multiple conversation participants of the above conversation window, and When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Based on the reception of the second user input selecting at least one of the plurality of conversational participants, the second plurality of messages of the at least one conversational participant are verified, and An electronic device that displays summary information of at least some of the topics of the second plurality of messages.

9. In Paragraph 8, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that highlights at least some of the second plurality of messages among the above unread plurality of messages.

10. In Paragraph 8, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Based on the reception of a sixth user input for changing the summary information of the above topic, the summary information of a topic different from the above topic is displayed, and An electronic device that highlights at least some of the third plurality of messages related to the other subject among the aforementioned unread plurality of messages.

11. In a method for controlling an electronic device, An operation of obtaining multiple summary information related to multiple unread messages using an artificial intelligence model based on receiving a first user input for summarizing multiple unread messages while the chat window contains multiple unread messages; Operation of displaying the above plurality of summary information; The operation of receiving a second user input that selects at least one summary information among the plurality of summary information above; The operation of generating at least one recommended answer based on at least one summary information using the above artificial intelligence model; and A method for controlling an electronic device, comprising the operation of displaying at least one recommended answer on a display of the electronic device.

12. In Paragraph 11, The operation of generating at least one recommended answer above is, Based on the reception of the second user input selecting a plurality of summary information including a first summary information and a second summary information among the plurality of summary information, the artificial intelligence model is used to generate a plurality of recommended answers based on at least one of the first summary information or the second summary information, and The above multiple recommended answers are, A method for controlling an electronic device, comprising recommended answers generated based on the first summary information and the second summary information.

13. In Paragraph 11 or 12, The operation of identifying a first plurality of messages corresponding to at least one selected summary information among the above unread plurality of messages; further comprising The operation of generating at least one recommended answer above is, A method for controlling an electronic device, which generates at least one recommended answer by further utilizing the above first plurality of messages.

14. In any one of paragraphs 11 through 13, The method further includes the operation of receiving a third user input that inputs at least one keyword related to the above at least one summary information; The operation of generating at least one recommended answer above is, A method for controlling an electronic device, which generates at least one recommended answer by further using at least one keyword.

15. In a non-transient computer-readable storage medium storing one or more programs, said one or more programs are: an electronic device: Based on the reception of a first user input for summarizing the multiple unread messages while the chat window contains multiple unread messages, multiple summary information related to the multiple unread messages is obtained using an artificial intelligence model, and Displaying the above multiple summary information, and Receiving a second user input that selects at least one summary information among the plurality of summary information above, Using the above artificial intelligence model, at least one recommended answer is generated based on the above at least one summary information, and A storage medium comprising instructions that cause at least one recommended answer to be displayed.

Images