Electronic device for providing information related to call content

Abstract

The present application pertains to an invention relating to an electronic device for providing information related to call content. The electronic device performs the operations of: identifying information about a person to make a call with a user on the basis of the occurrence of a call request event; generating a conversation topic for a conversation between the user and the person on the basis of the information about the person, and displaying, on a display, a first UI screen including the conversation topic; acquiring a portion of conversation content between the user and the person, acquiring keywords from the acquired portion of the conversation content, and displaying, on the display, a second UI screen including the keywords; identifying, by means of the display, a first user input for selecting a first keyword on the second UI screen; acquiring, from the conversation content, first summary information associated with the first keyword on the basis of the identification of the first user input; and displaying the first summary information on the display.

Description

Electronic device for providing information related to call content

[0001] The present disclosure relates to an electronic device for providing information (e.g., main content, summary) related to the content of a call.

[0002] An electronic device can provide useful information to the user by summarizing and displaying call content or by extracting and displaying key content (e.g., keywords) from call content. The electronic device may receive support from artificial intelligence (AI) during the summarization and / or extraction process. For example, the electronic device may record a call between a user and another person (the counterparty), convert the recorded speech into text, and use an AI module to obtain a summary and / or key content from the text (call content). Based on the obtained content, the electronic device may configure a user interface (UI) screen for interaction with the user (e.g., a screen for providing call history) and display the UI screen on a display.

[0003] The information described above is 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.

[0004] Electronic devices may provide the user with information related to the content of a call, such as a summary and / or key points. In addition to useful information, the provided information may include unnecessary information (or information that does not need to be remembered or is of no interest) (e.g., polls, advertisements).

[0005] In an embodiment of the present disclosure, an electronic device may obtain useful information from the content of a call and provide it to a user. The technical problems to be solved by the present disclosure are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below.

[0006] According to one embodiment, the electronic device includes a microphone; a communication circuit for wireless communication with an external electronic device; a touch-sensitive display; at least one processor; and a memory for storing instructions. When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation to verify information of a counterparty to be spoken to by the user of the electronic device based on the occurrence of an event requesting a call by the electronic device. When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation to generate at least one conversation topic for conversation between the user and the counterparty based on the counterparty information, include the at least one conversation topic in a first UI screen, and display the first UI screen on the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of acquiring at least a portion of the conversation content between the user and the counterparty through the microphone and the communication circuit, acquiring at least one keyword from the acquired at least a portion of the conversation content, including the at least one keyword in a second UI screen, and displaying the second UI screen on the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of confirming a first user input selecting a first keyword on the second UI screen through the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of acquiring first summary information associated with the first keyword from the conversation content based on the confirmation of the first user input.When the above instruction is executed individually or collectively by the at least one processor, the electronic device may perform the operation of displaying the first summary information on the display.

[0007] According to one embodiment, a method for operating an electronic device is provided. The method may include an operation of verifying information of a counterparty to be spoken to by a user of the electronic device based on the occurrence of an event requesting a call from the electronic device. The method may include an operation of generating at least one conversation topic for conversation between the user and the counterparty based on the counterparty information, including the at least one conversation topic in a first UI screen, and displaying the first UI screen on a display of the electronic device. The method may include an operation of obtaining at least a portion of the conversation content between the user and the counterparty from a microphone and a communication circuit of the electronic device, obtaining at least one keyword from the obtained at least a portion of the conversation content, including the at least one keyword in a second UI screen, and displaying the second UI screen on the display. The method may include an operation of verifying a first user input selecting a first keyword on the second UI screen through the display. The method may include an operation of obtaining first summary information associated with the first keyword from the conversation content based on the verification of the first user input. The method may include an operation of displaying the first summary information on the display.

[0008] According to one embodiment, a recording medium is provided for storing instructions readable by at least one processor in an electronic device. When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation of verifying information of a counterparty to be spoken to by a user of the electronic device based on the occurrence of an event requesting a call in the electronic device. When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation of generating at least one conversation topic for conversation between the user and the counterparty based on the counterparty information, including the at least one conversation topic in a first UI screen, and displaying the first UI screen on the display. When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation of obtaining at least a portion of the conversation content between the user and the counterparty through the microphone and the communication circuit, obtaining at least one keyword from the at least a portion of the obtained conversation content, including the at least one keyword in a second UI screen, and displaying the second UI screen on the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of confirming a first user input selecting a first keyword on the second UI screen through the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of obtaining first summary information associated with the first keyword from the conversation content based on the confirmation of the first user input.When the above instruction is executed individually or collectively by the at least one processor, the electronic device may perform the operation of displaying the first summary information on the display.

[0009] Various embodiments of the present disclosure may provide an electronic device capable of obtaining useful information from call content and providing it to a user. In addition, various effects that can be understood directly or indirectly through this document may be provided.

[0010] FIG. 1 is a block diagram of an electronic device in a network environment according to various embodiments.

[0011] FIG. 2 is a block diagram of a generative artificial intelligence system according to one embodiment.

[0012] FIG. 3 is a block diagram of an electronic device configured to provide information related to call content to a user, according to one embodiment.

[0013] FIG. 4 is a diagram illustrating an example of a conversation topic generation operation.

[0014] Figure 5 is a diagram illustrating another embodiment of a conversation topic generation operation.

[0015] FIG. 6 is a diagram illustrating an example of a keyword acquisition operation.

[0016] FIGS. 7a, 7b, and 7c illustrate an example of a UI screen for interacting with a user in an electronic device according to one embodiment.

[0017] FIGS. 8a, 8b, 8c, 8d, and 8e illustrate another example of a UI screen for interacting with a user in an electronic device according to one embodiment.

[0018] FIG. 9 is a flowchart illustrating an operation for providing information related to call content to a user in an electronic device according to one embodiment.

[0019] 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.

[0020] 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)).

[0021] The processor (120) can control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., a program (140)), 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., a sensor module (176) or a 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., a central processing unit or an application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a 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 lower 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.

[0022] 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.An 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.

[0023] 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).

[0024] 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).

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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).

[0032] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that can be perceived by the user 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.

[0033] 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.

[0034] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0035] 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.

[0036] 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).

[0037] 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) may support a Peak data rate (e.g., 20 Gbps or more) for eMBB realization, loss coverage (e.g., 164 dB or less) for mMTC realization, 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 URLLC realization.

[0038] 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).

[0039] According to various embodiments, 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.

[0040] 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.

[0041] 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 a 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.

[0042] FIG. 2a is a block diagram illustrating a generative artificial intelligence (AI) system (200) according to one embodiment. Referring to FIG. 2, the generative AI system (200) may include a user interface (210), an AI framework (220), a generative AI model (230), a knowledge repository (240), and an application / service module (250). The above configuration may be operated on one or more of an electronic device (101), an external electronic device (102 or 104), or a server (108). For example, the user interface (210) and the AI ​​framework (220) may be operated on the electronic device (101), and the knowledge repository (240) and the generative AI model (230) may be operated on the server (108).

[0043] According to one embodiment, the user interface (210) may receive user input (e.g., user query). User input may be received in the form of text, images, voice (e.g., natural language), video, menu selection, or a combination thereof. The user interface (210) may include various context information (e.g., running application or user location) related to the generative artificial intelligence system (200) at the time the user input is received, in addition to or instead of the user input. The user interface (210) may provide the user input or the context information to the AI ​​framework (220) and provide the result of processing therefrom to the user, for example, through the AI ​​framework (220). According to one embodiment, in addition to user input, the electronic device may provide context information obtained using information included on the screen to the AI ​​framework (220). The result may be provided in the form of text, images, voice, video, an action requested by the user (e.g., execution of a specified function or app), or a combination thereof.

[0044] According to one embodiment, the AI ​​framework (220) can identify (e.g., estimate) a user intent based on at least some user input or context information received from a user interface (210), control each of the relevant modules (e.g., 221, 223, or 225) to perform a function or action corresponding to the identified user intent, and coordinate collaboration between two or more modules. The AI ​​framework (220) may include a prompt design module (221), an API / plugin management module (223), and an output modification module (225), as illustrated in FIG. 2.

[0045] According to one embodiment, the prompt design module (221) can generate a prompt to be input to a generative AI model (230) based at least partially on user input or context information received from a user interface (210). For example, the prompt design module (221) can generate a prompt using user preferences, a prompt library, or prompt examples stored in a Knowledge Repository (240) based at least partially on user input or context information.

[0046] According to one embodiment, the API / Plug-in Management Module (223) may communicate, for example, via an API, with various resources (e.g., Knowledge Repository (240)) that provide said additional information when there is a request for said additional information in relation to user input. Additionally or alternatively, when a specified action (e.g., function, app, or service) is performed in response to said user input, the API / Plug-in Management Module (223) may request the application / service module (250) to perform said specified action via a corresponding API. The API / Plug-in Management Module (223) may provide information obtained from the knowledge repository (240), the application / service module (250), or another external resource to the prompt design module (221). The obtained information may be used by the prompt design module (221) to generate a prompt together with the user input, or provided to a generative AI model (230).

[0047] According to one embodiment, the output modification module (225) can fine-tune the result obtained through the generative AI model (230) as at least part of the response to user input (e.g., user query). For example, the output modification module (225) can determine whether the content of the response obtained through the generative AI model (230) is appropriate as a response to a request made by the user input. For example, the output modification module (225) can determine the degree of relevance, degree of bias (e.g., political or social bias), or degree of harmfulness (e.g., sexual or profanity) of the difference between the response obtained through the generative AI model (230) and the user input. Additionally or generally, the output modification module (225) can request that additional AI processing be performed on the obtained response, or provide the user with a hint to avoid unwanted output. For example, the response can be obtained again through the generative AI model (230) by generating additional prompts through the prompt design module.

[0048] According to one embodiment, the generative AI model (230) may form at least part of an artificial intelligence neural network and may include a model that generates images or a model that generates language. The image generation model may include, for example, a generative adversarial network (GAN), a variational autoencoder (VAE), or a Diffusion-based model using a VAE and a Transformer. The language generation model may include, for example, a large language model (LLM), a large multimodal model (LMM), a large vision model (LVM), or a large action model (LAM). The LAM may automatically generate actions for an environment (e.g., a robot, a car, an electronic device (101), or a program (140)). Additionally, for at least some AI models (e.g., LLM), there may be a low-rank adaptation (LoRA) adaptor fine-tuned for, for example, a specific task or a specific situation.

[0049] FIG. 2b illustrates an AI framework (220) having on-device AI processing capabilities according to one embodiment. In this case, the AI ​​framework (220) may generate and learn a response to user input using resources within the device, instead of sending user input received through a user interface (210) operating on the same device (e.g., electronic device (101)) to a generative AI model (230) operating on an external device (e.g., server (108)), or additionally. Referring to FIG. 3, the AI ​​framework (220) may include a Cross-Application Action Module (280), a Personal Data Managing Module (290), an On-device AI Model (260), and an Orchestration Module (270).

[0050] According to one embodiment, the cross-application operation module (280) determines one or more additional applications required for the operation of an executed application (e.g., an assistant app) and may connect or propose operations between the app and at least one additional application, or between a plurality of additional applications. For example, the cross-application operation module (280) may execute one or more additional applications to be used to respond to a user request through the assistant app sequentially or at least partially and simultaneously. Additionally, the cross-application operation module (280) may communicate with the additional applications so that the result of the execution of one additional application (e.g., content) can be shared with other additional applications.

[0051] According to one embodiment, the personal data management module (290) may provide personal information (e.g., schedule, contact, or message information) about a user of the application (e.g., assistant app) or the additional application running on the device (e.g., electronic device 101) or other related individuals (e.g., family or friends) to another module of the AI ​​framework (220) or a related module (e.g., generative AI model 230) operating on another device.

[0052] According to one embodiment, the on-device AI model (260) may include at least one model among one or more AI models (e.g., GAN, VAE, LLM, LMM, LVM, or LAM) operated on an external device (e.g., server (108)) or a corresponding lightweight AI model. Additionally, for said model or said lightweight model, there may be, for example, a LoRA adaptor.

[0053] According to one embodiment, the orchestration module (270) may select one or more AI models to be used to obtain a response to user input (e.g., user query). For example, the orchestration module (270) may select one or more AI models among an on-device AI model (260), an AI model operating on an external device (e.g., server (108)) (e.g., generative AI model (230)), or a third AI model (not shown) operating on another external device. When multiple AI models are selected, the orchestration module (270) may communicate with the selected models or devices so that the operation between the selected AI models and the processing of the results thereof can be coordinated between the relevant models or devices.

[0054] According to one embodiment, two or more modules of a generative AI system (200) (e.g., a cross-application task module (280) and an orchestration module (270)) may be implemented as a single module to maintain the same functionality. Various variations are possible.

[0055] For convenience of explanation, the side of the display (e.g., flexible display or main display) that is visually exposed to the user may be referred to as the front of the electronic device (101). The side opposite the front may be referred to as the rear of the electronic device (101). Additionally, the side surrounding the space between the front and the rear may be referred to as the side of the electronic device (101). In this document, the term “state” may refer to the structural form, posture, shape, or form of the electronic device (101) (or the display, slider, or housing constituting the electronic device (101)).

[0056] In the electronic device, the display mode may be determined as portrait mode (or portrait mode) or landscape mode (or landscape mode) based on the state of the electronic device. For example, in FIG. 1, the sensor module (176) may include a sensor (e.g., accelerometer, gyroscope) that generates data used to determine the relative position between sides in the housing structure of the electronic device (101) and to determine the movement and direction of movement of the electronic device (101). The processor (120) may recognize the orientation in which the electronic device is positioned based on the data received from the sensor, and may determine the display mode as landscape mode or portrait mode based on the recognized orientation. The processor (120) may display visual information on the display based on the determined display mode.

[0057] A bar-type housing structure may be applied to an electronic device (e.g., smartphone, tablet PC) (101). For example, the bar-type housing structure may include a plate (or cover) forming the front of the electronic device (101), a plate forming the rear of the electronic device (101), and a bezel structure forming sides surrounding the front and rear. A display may be placed on the front.

[0058] A foldable housing structure can be applied to an electronic device (e.g., smartphone, tablet PC, laptop PC) (101). For example, the electronic device (101) may have a foldable housing structure that is divided into two housings around a folding axis. A first display area of ​​a display (e.g., a flexible display) may be placed in the first housing, and a second display area of ​​the display may be placed in the second housing. The foldable housing structure may be implemented in an in-folding manner where the first display area and the second display area face each other when the electronic device (101) is folded. Alternatively, the foldable housing structure may be implemented in an out-folding manner where the first display area and the second display area face each other when the electronic device (101) is folded. The electronic device may further include a sub-display. For example, a flexible display, which is the main display, may be placed on the front of the electronic device, and a sub-display may be placed on the rear of the electronic device.

[0059] A sliderable (or rollable) housing structure may be applied to an electronic device (e.g., smartphone, tablet PC, laptop PC) (101). The electronic device (101) may include a sliderable housing comprising a housing (or a first housing) and a slider (or a second housing), a rail structure (e.g., a rail structure formed by a gear coupling between a rack gear and a pinion gear) that allows the slider to be retracted into the housing and the slider to be withdrawn from the housing, and a rollable display (e.g., a flexible display). The slider may be divided into a portion that can be retracted into the housing (hereinafter referred to as the retracted portion) and a portion that remains exposed to the outside. When the retracted portion of the slider is in a slide-out state (in other words, first state, open state, extended state, roll-out state) in which it is fully withdrawn from the housing, the entire display (or most of the display area) may be exposed to the outside through the front. As the inlet portion of the slider is retracted into the housing, the display can also be retracted into the housing. The display can be divided into a portion that remains exposed to the outside (e.g., first display area, first section) and a portion that can enter the housing (e.g., second display area, second section, bendable section). When the entire inlet portion of the slider is retracted into the housing in a slide-in state (or, alternatively, second state, closed state, reduced state, roll-in state), the entire second display area of ​​the display can be retracted into the housing. In one embodiment, when transitioning from a slide-out state to a slide-in state, a portion of the display (e.g., second display area) may not be retracted into the housing but may be moved and positioned toward the rear via the side.As exemplified above, the electronic device (101) may have a sliding structure in which a portion of the display is retracted into the housing, or a sliding structure in which a portion of the display is moved from the front to the rear. In the display, only the portion exposed through the front may be determined as an active display area (hereinafter, active area) to display visual information. The portion retracted into the housing or moved to the rear may be determined as an inactive area where visual information is not displayed. The electronic device having a slideable housing structure may include a separate button for switching the state from slide-in to slide-out or vice versa.

[0060] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may analyze raw data (e.g., application data, usage data, or system data) stored in the electronic device. Application data may include information regarding the execution history of applications installed on the electronic device (e.g., call history, text messages). Usage data may include information regarding the usage history of the electronic device (e.g., information regarding online and / or offline places visited). System data may include information regarding the usage history of the system (e.g., processor, camera, display). Based on the analyzed results, the electronic device may perform an operation to obtain (or extract) personal data regarding the person with whom the user is speaking from the raw data. For example, personal data may include at least one of a profile (e.g., information indicating the relationship with the user), preference information (e.g., intimacy, events, preferred places), context information (e.g., places, behaviors, regularities), and activity information (e.g., travel, exercise).

[0061] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may perform an operation of generating information regarding a conversation topic predicted to be discussed with a counterpart. The electronic device may perform an operation of obtaining (or extracting) at least one keyword from the content of a conversation shared between a user and a counterpart. The electronic device may perform an operation of obtaining additional information (or update information) related to the keyword selected by the user. The electronic device may perform an operation of summarizing the content of the conversation related to the keyword selected by the user.

[0062] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may display a conversation topic, keywords, additional information, and a summary on a display. For example, during a call, the electronic device may display a first UI screen containing a conversation topic and a second UI screen containing at least one keyword on the display. The electronic device may obtain a summary associated with a keyword selected by the user from the conversation content on the second UI screen. The electronic device may display the summary during the call or after the call ends. The electronic device may obtain additional information associated with the selected keyword from an external device (e.g., a database (265)) and / or raw data within the electronic device. During a call, the electronic device may display additional information and / or a summary on the first UI screen. For example, the electronic device may include and display additional information and / or a summary on the first UI screen so that the user can identify the conversation topic associated with the additional information or summary among a number of conversation topics and identify that it is associated with that conversation topic.

[0063] According to one embodiment, when an electronic device (e.g., the electronic device (101) of FIG. 1) performs at least one of the personal data acquisition operation, conversation topic generation operation, keyword acquisition operation, additional information acquisition operation and summary operation described above, it may receive support from an artificial intelligence model (e.g., an AI framework (280) and / or a generative AI model (290)).

[0064] FIG. 3 is a block diagram of an electronic device (800) configured to provide information related to call content to a user according to one embodiment. Referring to FIG. 3, the electronic device (300) (e.g., the electronic device (101) of FIG. 1) may include a communication circuit (310), a touch-sensitive display (320), an audio processing circuit (330), a microphone (333), a memory (388), and a processor (399).

[0065] According to one embodiment, the communication circuit (310), display (320), audio processing circuit (330), memory (388), and processor (399) can each perform the same function by being implemented substantially identically to the communication module (190), display module (160), audio module (170), memory (130), and processor (120). The microphone (333) may be configured to receive external sound and convert the sound into an analog electrical signal (audio signal). The audio processing circuit (330) may receive the analog electrical signal from the microphone (333) and convert it into a digital electrical signal (audio data). The audio processing circuit (330) may output the audio data to other components of the electronic device (300) (e.g., processor (399) and / or communication circuit (310)).

[0066] According to one embodiment, the memory (388) may include a data storage (340). The data storage (340) may include application data (341), usage data (343), and system data (345). The processor (399) may include at least one processor (e.g., a main processor (121) and / or an auxiliary processor (123)). Instructions may be stored in the memory (388). When the instructions are executed collectively or individually by the processor (399), they may cause the electronic device (300) to perform a given operation using the data stored in the data storage (340). According to one embodiment, at least one module among a personal information verification module (351), a conversation topic generation module (353), a keyword acquisition module (355), an additional information acquisition module (357), and a summary generation module (359) may be composed of instructions and stored in the memory (388). According to one embodiment, a portion of the instruction may be stored in memory (388) and another portion may be stored in the internal memory of the processor (399).

[0067] According to one embodiment, the electronic device (300) may further include an AI module (360). The AI ​​module (360) may include an AI framework (361) and / or a generative AI model (363) corresponding to the AI ​​framework (220) and the generative AI model (230) described above, respectively. At least one of the modules described above (351, 353, 355, 357, 359) may be supported by the AI ​​module (360). As another example, at least one of the modules described above (351, 353, 355, 357, 359) may be included in the AI ​​module (360). As another example, at least one of the modules described above (351, 353, 355, 357, 359) may not be included in memory (388) but may be included in the electronic device (300) as a separate component (e.g., hardware structure and / or software structure). At least some of the functions of the AI ​​module (360) may be executed on a server (e.g., server (108) of FIG. 1).

[0068] According to one embodiment, at least one of the modules described above (351, 353, 355, 357, 359) can perform a given operation based on the occurrence of an event requesting a call (e.g., incoming call event, outgoing call event, missed call notification) in the electronic device (300).

[0069] The personal information verification module (351) can verify information about the other party (or personal data) (e.g., call history, relationship with the user (e.g., company colleagues, family, or friends), text message / email transmission history) related to the other party to be spoken to by the user of the electronic device (300) from the data storage (340). According to one embodiment, the personal information verification module (351) can transmit a message requesting information about the other party to an external device (e.g., server (108)) through a communication circuit (310). The request message may include information (e.g., name, phone number) to identify who the other party is. The personal information verification module (351) can receive a response (information about the other party) from the external device through the communication circuit (310).

[0070] According to one embodiment, the personal information verification module (351) can verify the other party's information using an AI module (360) (e.g., a generative AI model (363)). For example, the personal information verification module (351) can complete a prompt to be input to the generative AI model (363) by adding the other party's identification information (e.g., name, phone number) and information indicating the time when the call request event occurred to a prompt template prepared in advance to obtain the result (other party's information). The prompt template may include instructions indicating the task that the generative AI model (363) must perform. For example, natural language to the effect of “Check the other party's information in the data storage (340) and / or external device” may be included in the instructions. The personal information verification module (351) can input the prompt to the generative AI model (363). The generative AI model (363) can process the prompt and return the result obtained to the personal information verification module (351).

[0071] The conversation topic generation module (353) can generate at least one topic for conversation between the user and the other party based on the other party information.

[0072] According to one embodiment, the conversation topic generation module (353) can verify the other party's information using an AI module (360) (e.g., a generative AI model (363)). The conversation topic generation module (353) can complete a prompt to be input to the generative AI model (363) by adding the other party's information to a pre-prepared prompt template to obtain a result (conversation topic). The instructions in the prompt template may include, for example, natural language to the effect of “Generate a conversation topic expected to be discussed with the other party based on the other party's information.” The conversation topic generation module (353) can input the prompt to the generative AI model (363). The generative AI model (363) can process the prompt and return the result obtained to the conversation topic generation module (353).

[0073] FIG. 4 is a diagram illustrating an embodiment of a conversation topic generation operation. Referring to FIG. 4, if the caller is a person related to company business (e.g., a team leader), the personal information verification module (351) can verify personal data (481) necessary for generating a business-related conversation topic from a data storage (401) (e.g., a data storage (340) and / or an external device (e.g., a server (108))). For example, the personal information verification module (351) can obtain the caller's personal data (481) from raw data related to business, such as schedules, emails, memos, and call history. The conversation topic generation module (353) can generate a conversation topic (490) using the personal data (481). According to one embodiment, the conversation topic generation module (353) may be included in an AI module (360). For example, an AI framework (361) (e.g., the prompt design module (221) of FIG. 2a) can generate a prompt containing natural language with the intent of “write and display information expected to be discussed with the team leader, focusing on work-related materials” based on personal data (481). A generative AI model (363) (e.g., the generative AI model (290) of FIG. 2a and / or the on-device AI model (260) of FIG. 2b)) can process the prompt input from the AI ​​framework (361) and generate a conversation topic (490) as a result. For example, the conversation topic (490) may include a first topic (491) related to a meeting schedule, a second topic (492) related to an email received from the other party (team leader), and a third topic (493) related to a vacation schedule.

[0074] FIG. 5 is a diagram illustrating another embodiment of a conversation topic generation operation. Referring to FIG. 5, if the call partner is a person personally related to the user (e.g., family, friend), the personal information verification module (351) can verify personal data (581) necessary for generating a privately related conversation topic from a data store (501) (e.g., a data store (340) and / or an external device (e.g., a server (108))). For example, the personal information verification module (351) can obtain the call partner's personal data (581) from privately related raw data such as finance, shopping, schedules, and messages. The conversation topic generation module (353) can generate a conversation topic (590) using the personal data (581). According to one embodiment, the conversation topic generation module (353) can generate a conversation topic (590) through an AI module (360) (e.g., a generative AI model (363)). The conversation topic generation module (353) can output personal data (581) to an AI framework (361) (e.g., the prompt design module (221) of FIG. 2a). The conversation topic generation module (353) can receive a prompt from the AI ​​framework (361). For example, the provided prompt may include natural language to the effect of “Please write and display information expected to be discussed with my wife, focusing on family-related materials.” The conversation topic generation module (353) can output the prompt to a generative AI model (363) (e.g., the generative AI model (290) of FIG. 2a and / or the on-device AI model (260) of FIG. 2b). The generative AI model (363) can reply to the conversation topic generation module (353) with a conversation topic (590) as a result. For example, conversation topics (590) may include a first topic (591) related to travel, a second topic (592) related to delivery, and a third topic (593) related to cards.

[0075] The keyword acquisition module (355) can acquire conversation content between the user and the other party from the microphone (333) and / or the communication circuit (310) and acquire at least one keyword from the conversation content.

[0076] According to one embodiment, a keyword acquisition module (355) can acquire keywords from conversation content by using an AI module (360) (e.g., a generative AI model (363)). For example, the keyword acquisition module (355) can output a prompt generated using a pre-prepared prompt or a prompt generation module (e.g., an AI framework (361)) to the generative AI model (363) to acquire results (keywords). The instructions in the prompt may include, for example, natural language to the effect of “acquire conversation content and extract keywords from conversation content.” The keyword acquisition module (355) can input the prompt into the generative AI model (363). The generative AI model (363) can process the conversation content according to the instructions in the prompt and return the obtained results (keywords) to the keyword acquisition module (355).

[0077] FIG. 6 is a diagram illustrating an embodiment of a keyword acquisition operation. Referring to FIG. 6, a first keyword (610) obtained from a first conversation content (601), a second keyword (620) obtained from a second conversation content (602), and a third keyword (630) obtained from a third conversation content (603) can be returned to a keyword acquisition module (355). For example, the other party may be a person related to work, and the first conversation content (601) and the second conversation content (602) with the other party may be work-related content, while the third conversation content (603) may be conversation content unrelated to work. For instance, the natural language “inquiry regarding progress of Thursday report” can be acquired as a first keyword (610) related to work. The natural language “request for tomorrow’s meeting regarding Thursday report” can be acquired as a second keyword (620) related to work. The natural language “stories related to take-out (or to go) in the company” can be obtained as a third keyword (630) unrelated to work.

[0078] The additional information acquisition module (357) can identify a keyword selected by the user among a plurality of keywords acquired by the keyword acquisition module (355). The additional information acquisition module (357) can check whether there is a conversation topic related to the keyword selected by the user among a plurality of conversation topics generated by the conversation topic generation module (353). If there is a conversation topic related to the selected keyword, the additional information acquisition module (357) can acquire additional information (or update information) associated with the selected keyword from a data store (e.g., a data store (340) and / or an external device (e.g., a knowledge store (240) of FIG. 2a)). According to one embodiment, the additional information acquisition module (357) can perform an operation for acquiring additional information during a call.

[0079] According to one embodiment, the additional information acquisition module (357) can acquire additional information by using an AI module (360) (e.g., a generative AI model (363)). For example, the additional information acquisition module (357) can complete a prompt to be input to the generative AI model (363) by adding a keyword (a keyword selected by the user) to a pre-prepared prompt template to acquire a result (additional information). The instructions in the prompt template may include, for example, natural language to the effect of “acquire additional information related to the keyword.” The additional information acquisition module (357) can input the prompt to the generative AI model (363). The generative AI model (363) can search a data repository according to the instructions in the prompt and return the result (additional information) obtained to the additional information acquisition module (357).

[0080] The summary generation module (359) can identify the conversation parts associated with keywords selected by the user among the conversation content between the user and the other party, and summarize the identified conversation parts. The summarization can be performed during the call or after the call has ended.

[0081] According to one embodiment, the summary generation module (359) can summarize conversation content using an AI module (360) (e.g., a generative AI model (363)). For example, the summary generation module (359) can complete a prompt to be input to the generative AI model (363) by adding a keyword (a keyword selected by the user) to a pre-prepared prompt template to obtain a result (summary). The instructions in the prompt template may include, for example, natural language to the effect of “summarize the part of the conversation related to the keyword within the conversation content.” The summary generation module (359) can input the prompt to the generative AI model (363). The generative AI model (363) can process the conversation content according to the instructions in the prompt and return the result (summary) obtained to the additional information acquisition module (357).

[0082] FIGS. 7a, 7b, and 7c illustrate an example of a UI screen for interacting with a user in an electronic device (e.g., the electronic device (300) of FIG. 3) according to one embodiment. According to one embodiment, at least one processor in the electronic device (e.g., the processor (399) of FIG. 3) may be configured to perform an operation for providing a UI screen. According to one embodiment, instructions (e.g., the modules (351, 353, 355, 357, 359, 360)) stored in memory (e.g., memory (388) and / or internal memory of the processor (399)) in the electronic device may cause the electronic device to perform an operation for providing a UI screen when executed individually or collectively by at least one processor. In describing such an operation with reference to FIGS. 7a, 7b, and 7c, details that overlap with those described above may be omitted or briefly described.

[0083] Referring to FIG. 7a, a call request event (e.g., incoming call event, outgoing call event, missed call notification) may occur in an electronic device. For example, the electronic device may receive user input for making a call from an input device (e.g., display (320)) and, in response, generate an outgoing call request event. The electronic device may receive an incoming call request event through a communication circuit (e.g., communication circuit (310) of FIG. 3). Based on the occurrence of a call request event or during a call, the electronic device may display a first UI screen (or conversation topic screen) (701), a second UI screen (or keyword screen) (702), and a third UI screen (or call event screen) (703) on a display (720) (e.g., display (320) of FIG. 3). For example, UI screens (701, 702, 703) may be displayed when an electronic device having a bar-type housing structure is in landscape mode, when an electronic device having a foldable housing structure is in an unfolded state, or when an electronic device having a sliderable housing structure is in a slide-out state. As another example, the electronic device may display an icon for calling the first UI screen (701) to the display and / or an icon for calling the second UI screen (702) to the display along with the third UI screen (703). The electronic device may display the corresponding UI screen on the display when the icon is selected by the user. The electronic device may check the information of the call partner from a data store, generate a conversation topic based on the partner information, and display the generated conversation topic on the first UI screen (701). For example, the call partner is the user's wife, and the topics predicted to be discussed with the wife may include a first topic related to travel (711), a second topic related to tomorrow's schedule (712), a third topic related to lunch (713), and a fourth topic related to Christmas (714).The electronic device may obtain keywords from the conversation content between the other party and the user and display the obtained keywords on the second UI screen (702). For example, the keywords obtained from the conversation content may include a first keyword (721) related to tomorrow's schedule. The electronic device may display a first UI element (721a) on the second UI screen (702) along with the first keyword (721), which allows the user to select whether to summarize the conversation content regarding the first keyword (721) and / or whether to obtain additional information regarding the first keyword (721). For example, the UI element for selecting whether to obtain the summary and / or additional information may include a “+” shaped icon and a “-” shaped icon, as illustrated.

[0084] Referring to FIG. 7b, a call can continue between the other party and the user. Accordingly, the electronic device can obtain a second keyword (722) from the content of the conversation. The electronic device can display the second keyword (722) and the related second UI element (722a) on the second UI screen (702).

[0085] Referring again to FIG. 7b, the user can select the first keyword (721) through the first UI element (721a). For example, a “+” shaped icon on the first UI element (721a) may be touched. In response to the touch input, the electronic device may perform an action of identifying a conversation part associated with the first keyword (721) and summarizing the identified conversation part. The summarization action may be performed during a call or after the call has ended. Additionally, the electronic device may identify a conversation topic associated with the first keyword (721) among the conversation topics (711, 712, 713, 714). For example, by identifying that the first keyword (721) and the second topic (712) are related to tomorrow's schedule, the electronic device may perform an action of obtaining additional information associated with the first keyword (721) from a data storage (e.g., a data storage (340) and / or an external device (e.g., a knowledge storage (240) in FIG. 2a)). The electronic device may display summary information and / or additional information obtained through the operation described above on the display (720). According to one embodiment, the electronic device may display summary information and / or additional information on the display (720) so that the user can identify that it is associated with the corresponding conversation topic. For example, the electronic device may display summary information and / or additional information as sub-items of the corresponding conversation topic on the first UI screen (701). For example, additional information (712a, 712b) obtained in relation to the first keyword (721) may be displayed as sub-items of the second topic (712). The first additional information (712a) is information indicating that the user needs to check with his wife regarding the time to leave for the hospital tomorrow, and the second additional information (712b) indicates that the user needs to check with his wife regarding whether to pick up his son from school. Meanwhile, as the first keyword (721) is selected, the electronic device can leave the first keyword (721) on the second UI screen (702) and remove the first UI element (721a) from the second UI screen (702).

[0086] Referring again to FIG. 7b, the user may decide that the conversation content corresponding to the second keyword (722) is not useful and may not select the second keyword (722) through the second UI element (722a). For example, a “-” shaped icon may be touched on the second UI element (722a). In response to the touch input, the electronic device may remove the second keyword (722) and the second UI element (722a) from the second UI screen (702). Since the second keyword (722) is not selected, the task associated with the second keyword (722) (obtaining a summary and / or additional information) may be omitted.

[0087] Referring to FIG. 7c, the electronic device may display a summary (741) obtained in relation to a selected first keyword (721; see FIG. 7b) on a fourth UI screen (or, call summary screen) (704). According to one embodiment, the electronic device may display the fourth UI screen (704) based on the termination of a call with the other party. When the fourth UI screen (704) is displayed, the electronic device may exclude at least one of the UI screens (701, 702, 703) from the display target. According to one embodiment, the electronic device may display the fourth UI screen (704) in response to a user's call. For example, an execution screen provided by a call application may include an icon for calling the fourth UI screen (704) to the display. The electronic device may display the fourth UI screen (704) in response to the icon being touched. According to one embodiment, the electronic device may record the contents of the call and store them in memory (e.g., memory (388)). The electronic device can acquire audio data corresponding to a summary (741) from the recorded content based on the user's selection of playback of the recorded content. The electronic device can play the acquired audio data through a speaker.

[0088] FIGS. 8a, 8b, 8c, 8d, and 8e illustrate another example of a UI screen for interacting with a user in an electronic device according to one embodiment. According to one embodiment, at least one processor in the electronic device (e.g., processor (399) of FIG. 3) may be configured to perform an operation for providing a UI screen. According to one embodiment, instructions (e.g., the modules (351, 353, 355, 357, 359, 360)) stored in memory (e.g., memory (388) and / or internal memory of the processor (399)) in the electronic device may cause the electronic device to perform an operation for providing a UI screen when executed individually or collectively by at least one processor. In describing such an operation with reference to FIGS. 8a, 8b, 8c, 8d, and 8e, details that overlap with those described above may be omitted or briefly described.

[0089] Referring to FIG. 8a, the electronic device may display a first UI screen (or conversation topic screen) (801), a second UI screen (or keyword screen) (802), and a third UI screen (or call event screen) (803) on a display (820) (e.g., the display (320) of FIG. 3) based on the occurrence of a call request event or during a call. For example, the call partner is the user's boss, a team leader, and the topics predicted to be discussed with the team leader may include a first topic (811) related to a reporting schedule, a second topic (812) related to emails exchanged with the team leader, and a third topic (813) related to vacation. The electronic device may display the predicted conversation topics (811, 812, 813) on the first UI screen (801). For example, keywords obtained from the conversation between the user and the other party (team leader) may include a first keyword (821) and a second keyword (822) related to a reporting schedule. The electronic device can display the first keyword (821) and the first UI element (821a) and the second keyword (822) and the second UI element (822a) on the UI screen (802).

[0090] Referring to FIG. 8b, the user can select a first keyword (821) by touching a “+” shaped icon in a first UI element (821a). Additionally, the user can select a second keyword (822) by touching a “+” shaped icon in a second UI element (822a). The electronic device may also select the keyword based on receiving direct user input for the keyword from the display instead of a “+” shaped icon (e.g., a gesture of double-tapping the keyword using a finger or pen). Based on the selection of the keyword (821, 822), the electronic device may perform an action of checking the corresponding conversation part and summarizing the confirmed conversation part. Additionally, as it is confirmed that the keywords (821, 822) and the first topic (811) are related to the reporting schedule, the electronic device may perform an action of obtaining additional information related to the keywords (821, 822) from a data repository (e.g., a data repository (340) and / or an external device (e.g., a knowledge repository (240) of FIG. 2a)). The electronic device may display the summary information and / or additional information obtained through the above action on the display (720). For example, the electronic device may display additional information (811a) indicating that a developer meeting and a meeting room reservation need to be checked in relation to the reporting schedule on the first UI screen (801) as a sub-item of the first topic (811). Based on the additional information selected through user input, the electronic device may execute a related application (e.g., an application for booking a meeting room) and display the execution screen on the display, thereby allowing the user to change the schedule for a meeting with a developer or book a meeting room.

[0091] Referring to FIG. 8c, as the first keyword (821) and the second keyword (822) are selected, the electronic device can leave the keywords (821, 822) on the second UI screen (802) and remove the corresponding UI elements (821a, 822a) from the second UI screen (802).

[0092] Referring again to FIG. 8c, a conversation between the other party and the user may continue. Accordingly, the electronic device may obtain a third keyword (823) from the content of the conversation. The electronic device may display the third keyword (823) and the associated third UI element (823a) on the second UI screen (802). The user may decide that the conversation content corresponding to the third keyword (823) is not useful and may not select the third keyword (823) by touching a “-” shaped icon on the third UI element (823a). The electronic device may not select the keyword based on receiving direct user input for the keyword from the display instead of the “-” shaped icon (e.g., a gesture of swiping the keyword with a finger or pen, a gesture of removing the keyword with a pen while the erase function provided by the electronic device is activated, or a gesture of drawing a line through the keyword with a pen). Referring to FIG. 8d, the electronic device can remove the third keyword (823) and the third UI element (823a) from the second UI screen (802) in response to a touch input. Since the third keyword (823) is not selected, the operation associated with the third keyword (823) (obtaining a summary and / or additional information) can be omitted.

[0093] Referring to FIG. 8e, the electronic device may summarize the conversation parts (851, 852) associated with keywords (821, 822) (selected keywords) among the conversation contents (851, 852, 853) and display the summary (841) on a fourth UI screen (or call summary screen) (804). According to one embodiment, the electronic device may display the fourth UI screen (804) based on the termination of a call with the other party. When the fourth UI screen (704) is displayed, the electronic device may exclude at least one of the UI screens (801, 802, 803) from the display targets. According to one embodiment, the electronic device may display the fourth UI screen (804) in response to a user calling for a summary. According to one embodiment, the electronic device may summarize the conversation contents (851, 852, 853) respectively and extract keywords from each summary.

[0094] FIG. 9 is a flowchart illustrating an operation for providing information related to call content to a user in an electronic device (e.g., the electronic device (300) of FIG. 3) according to one embodiment. According to one embodiment, at least one processor in the electronic device (e.g., the processor (399) of FIG. 3) may be configured to perform the operation of FIG. 9. According to one embodiment, instructions stored in memory (e.g., memory (388) and / or internal memory of the processor (399)) in the electronic device (e.g., the modules (351, 353, 355, 357, 359, 360) described above) may cause the electronic device to perform the operation of FIG. 9 when executed individually or collectively by at least one processor. According to one embodiment, the operation of FIG. 9 may be performed based on a call request event (e.g., an incoming call request event or an outgoing call request event) occurring in the electronic device. In describing the operation of FIG. 9, details that overlap with those described above may be omitted or briefly described.

[0095] In operation 910, the electronic device can check the information of the call partner (personal data) in a data storage. For example, the electronic device can check in a data storage within the electronic device (e.g., the data storage (340) of FIG. 3). Alternatively or additionally (e.g., if the information of the call partner is not found in the internal storage of the electronic device or if the caller number is included in a spam call list), the electronic device can request the partner information from an external device (e.g., a server (108)) via a communication circuit and receive a response (partner information).

[0096] In operation 920, the electronic device can generate a conversation topic predicted to be discussed between the user and the other party based on the other party's information (personal data) and include it in a first UI screen (e.g., first UI screen (701) or first UI screen (801)) and display it on a display (e.g., display (320) of FIG. 3).

[0097] According to one embodiment, the electronic device may receive support from an external device (e.g., AI system (200)) through a component inside the electronic device (e.g., AI module (360)) and / or a communication circuit (e.g., communication circuit (310)) for generating a conversation topic (e.g., conversation topic (701) in FIG. 7a or conversation topic (801) in FIG. 8a) that is predicted to be conversed between the user and the other party.

[0098] According to one embodiment, the electronic device may display a first UI screen during a call or after the call ends. For example, the electronic device may display the first UI screen together with a call event screen during a call. As another example, the electronic device may display the first UI screen in response to the end of a call. As yet another example, the electronic device may display the first UI screen in response to a user's call after the call ends. For example, an execution screen provided by a call application may include an icon for calling the first UI screen to the display. The electronic device may display the first UI screen in response to the icon being touched.

[0099] In operation 930, the electronic device may acquire the actual conversation content exchanged between the user and the other party during a call through a microphone and / or communication circuit, acquire keywords from the acquired conversation content, and include the keywords in a second UI screen (e.g., a second UI screen (702) or a second UI screen (802)) and display them on a display. According to one embodiment, the electronic device may acquire at least a portion of the conversation content. For example, the electronic device may acquire the user's conversation content or the other party's conversation content. As another example, the electronic device may acquire at least a portion of the user's conversation content or at least a portion of the other party's conversation content. As yet another example, the electronic device may acquire at least a portion of the user's conversation content and at least a portion of the other party's conversation content.

[0100] According to one embodiment, the electronic device may receive support from an external device (e.g., AI system (200)) through a component inside the electronic device (e.g., AI module (360)) and / or a communication circuit for acquiring keywords.

[0101] According to one embodiment, the electronic device may display a second UI screen during a call or after the call ends. For example, the electronic device may display the second UI screen together with a call event screen during a call. As another example, the electronic device may display the second UI screen in response to the end of a call. As yet another example, the electronic device may display the second UI screen in response to a user's call after the call ends. For example, an execution screen provided by a call application may include an icon for calling the second UI screen to the display. The electronic device may display the second UI screen in response to the icon being touched.

[0102] According to one embodiment, the electronic device may display a second UI screen together with a first UI screen.

[0103] In operation 940, the electronic device can receive a first user input from a display or microphone selecting a first keyword from among the keywords included in the second UI screen. For example, the electronic device can receive a first user input from the display touching an icon (e.g., an icon in the shape of “+”) for selecting the first keyword. As another example, the electronic device can convert speech received from the microphone into text and receive the first user input (e.g., the natural language “Please select the first keyword”) in the text through natural language understanding (NLU) on the text. To receive the first user input from the microphone, the electronic device may receive support from an artificial intelligence model trained for automatic speech recognition (ASR) and NLU. For example, the electronic device may receive support from an artificial intelligence model of an external device through the corresponding artificial intelligence model installed on the electronic device and / or communication circuits.

[0104] In operation 950, the electronic device can extract first summary information associated with a first keyword from the conversation content based on the confirmation of the first user input and display the first summary information on the display.

[0105] According to one embodiment, the electronic device may display the first summary information on the display after the call ends. For example, the electronic device may display the first summary information on the display by including it in a call summary screen (e.g., the fourth UI screen (704) or the fourth UI screen (804)) in response to the end of the call. As another example, the electronic device may display the call summary screen in response to a user's call after the call ends. For example, an execution screen provided by a call application may include an icon for calling the call summary screen to the display. The electronic device may display the call summary screen in response to the icon being touched.

[0106] According to one embodiment, the electronic device may display first summary information on a display during a call. For example, the electronic device may identify a first conversation topic associated with a first keyword among conversation topics. The electronic device may display the first summary information as a sub-item of the first conversation topic on a first UI screen.

[0107] According to one embodiment, the electronic device may obtain additional information associated with the first keyword from a data store (e.g., data store (340) and / or an external device (e.g., knowledge store (240) of FIG. 2a)) based on the identification of a first conversation topic associated with the first keyword. The electronic device may display the additional information (e.g., additional information (712a, 712b) or additional information (811a)) as a sub-item of the first conversation topic on the first UI screen.

[0108] According to one embodiment, the electronic device can detect a second user input from a display or microphone in which the second keyword is not selected among the keywords included in the second UI screen. For example, the electronic device can receive a second user input from the display in which the user touches an icon (e.g., an icon in the shape of “-”) to not select the second keyword. As another example, the electronic device can convert voice received from the microphone into text and detect the second user input (e.g., the natural language “exclude the second keyword”) in the text through natural language understanding (NLU) of the text. The electronic device may receive support from an artificial intelligence model trained for ASR and NLU to detect the second user input from the microphone. Based on the detection of the second user input, the electronic device may exclude the conversational portion corresponding to the second keyword from the target for summarization. Additionally, the electronic device may remove the second keyword from the second UI screen.

[0109] According to one embodiment, an electronic device can display a UI screen based on a display mode and / or a housing structure. When an electronic device having a bar-type housing structure is in landscape mode, when an electronic device having a foldable housing structure is in an unfolded state, or when an electronic device having a sliderable housing structure is in a slide-out state, the electronic device can display a first UI screen and a second UI screen.

[0110] According to one embodiment, when the electronic device has a foldable housing structure, it may include a sensor that generates data used to determine whether the first housing and the second housing are in an unfolded state. For example, the sensor may include a Hall sensor attached to an axis connecting the first housing and the second housing in the foldable housing structure. The electronic device (e.g., processor (399)) may receive data corresponding to the strength of the magnetic field from the Hall sensor and calculate an angle using the received data. The electronic device (e.g., processor (399)) may determine whether the first housing and the second housing are in an unfolded state based on the calculated angle value. As another example, the sensor may further include a first inertial sensor located in the first housing and a second inertial sensor located in the second housing. The electronic device (e.g., processor (399)) may receive data indicating the movement of the first housing from the first inertial sensor and data indicating the movement of the second housing from the second inertial sensor. An electronic device (e.g., processor (399)) may calculate an angle using data received from two inertial sensors and determine whether the electronic device is in an unfolded state based on the calculated angle value. As another example, an electronic device (e.g., processor (399)) may calculate an angle using data received from two inertial sensors and a Hall sensor and determine whether the electronic device is in an unfolded state based on the calculated angle value.

[0111] According to one embodiment, when the electronic device has a slideable housing structure, it may include a state sensing sensor that generates data used to determine whether the first housing and the second housing are in a slide-out state. For example, the sensor may include a sensor (e.g., an encoder, a Hall sensor) that is attached to a gear (e.g., a pinion gear) that allows the slider (e.g., the second housing) to move, and generates and outputs data corresponding to the angle of rotation when the gear is rotated by a force transmitted from a slide motor or a force transmitted from a user through the slider. As another example, the sensor may include a sensor (e.g., a pressure sensor) that is placed in a curved part of a display and generates data corresponding to the curvature of that part.

[0112] According to one embodiment, the electronic device may display an icon for calling a first UI screen to a display and / or an icon for calling a second UI screen to a display. The electronic device may display the corresponding UI screen on a display when the icon is selected by a user.

[0113] According to one embodiment, an electronic device (e.g., the electronic device (300) of FIG. 3) includes a microphone; a communication circuit for wireless communication with an external electronic device; a touch-sensitive display; at least one processor; and a memory for storing instructions. When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation to identify information of a person to call with the user of the electronic device based on the occurrence of an event requesting a call from the electronic device. When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation to generate at least one conversation topic for conversation between the user and the person based on the person information, include the at least one conversation topic in a first UI screen, and display the first UI screen on the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of acquiring at least a portion of the conversation content between the user and the counterparty through the microphone and the communication circuit, acquiring at least one keyword from the acquired at least a portion of the conversation content, including the at least one keyword in a second UI screen, and displaying the second UI screen on the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of confirming a first user input selecting a first keyword on the second UI screen through the display.When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of obtaining first summary information associated with the first keyword from the conversation content based on the confirmation of the first user input. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of displaying the first summary information on the display.

[0114] When the above command is executed individually or collectively by the at least one processor, the electronic device may perform the operation of confirming through the display a second user input in which a second keyword is not selected on the second UI screen; and the operation of excluding second summary information associated with the second keyword from the extraction target based on the confirmation of the second user input.

[0115] When the above command is executed individually or collectively by the at least one processor, the electronic device may perform the operation of removing the second keyword from the second UI screen.

[0116] When the above command is executed individually or collectively by the at least one processor, the electronic device may perform the operation of identifying a first conversation topic associated with the first keyword among conversation topics included in the first UI screen while a call is being made between the user and the counterparty; and the operation of displaying additional information associated with the first keyword on the display based on the identification of the first conversation topic.

[0117] When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of displaying the additional information on the display so that the user can identify that the additional information is associated with the first conversation topic.

[0118] When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of displaying the first summary information on the display so that the user can identify that the first summary information is associated with the first conversation topic.

[0119] When the above command is executed individually or collectively by the at least one processor, the electronic device may perform the operation of displaying the first summary information on the display based on the termination of a call between the user and the counterparty.

[0120] When the above command is executed individually or collectively by the at least one processor, the electronic device may perform the operation of displaying the first UI screen and the second UI screen together on the display.

[0121] The electronic device may further include a foldable housing structure comprising a first housing and a second housing foldably coupled to one side of the first housing; and a sensor that generates data used to determine whether the first housing and the second housing are in an unfolded state. When the instruction is executed individually or collectively by the at least one processor, the electronic device may perform an operation of simultaneously displaying the first UI screen and the second UI screen on the display based on the determination that the first housing and the second housing are in the unfolded state.

[0122] The electronic device may further include a slideable housing structure comprising a first housing and a second housing coupled to the first housing to be slidably driven relative to the first housing; and a sensor that generates data used to determine whether the first housing and the second housing are in a slide-out state. When the instruction is executed individually or collectively by the at least one processor, the electronic device may perform an operation of simultaneously displaying the first UI screen and the second UI screen on the display based on the determination that the first housing and the second housing are in the slide-out state.

[0123] When the above instruction is executed individually or collectively by the at least one processor, the electronic device may perform the operation of generating the at least one conversation topic using a generative artificial intelligence model.

[0124] When the above instruction is executed individually or collectively by the at least one processor, the electronic device may perform the operation of acquiring the at least one keyword using a generative artificial intelligence model.

[0125] When the above instruction is executed individually or collectively by the at least one processor, the electronic device may perform the operation of acquiring the first summary information using a generative artificial intelligence model.

[0126] According to one embodiment, a method for operating an electronic device (e.g., the electronic device (300) of FIG. 3) is provided. The method may include an operation of confirming information of a counterparty to whom a user of the electronic device will speak based on the occurrence of an event requesting a call from the electronic device. The method may include an operation of generating at least one conversation topic to be conversed between the user and the counterparty based on the counterparty information, including the at least one conversation topic in a first UI screen, and displaying the first UI screen on the display of the electronic device. The method may include an operation of obtaining at least a portion of the conversation content between the user and the counterparty from the microphone and communication circuit of the electronic device, obtaining at least one keyword from the obtained at least a portion of the conversation content, including the at least one keyword in a second UI screen, and displaying the second UI screen on the display. The method may include an operation of confirming a first user input selecting a first keyword on the second UI screen through the display. The method may include an operation of obtaining first summary information associated with the first keyword from the conversation content based on the confirmation of the first user input. The above method may include the operation of displaying the first summary information on the display.

[0127] The above method may further include: an operation of confirming through the display a second user input in which a second keyword is not selected on the second UI screen; and an operation of excluding second summary information associated with the second keyword from the extraction target based on the confirmation of the second user input.

[0128] The above method may further include the operation of removing the second keyword from the second UI screen.

[0129] According to one embodiment, a recording medium is provided for storing instructions readable by at least one processor in an electronic device (e.g., the electronic device (300) of FIG. 3). When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation of verifying information of a counterpart to whom a call is to be made between the user of the electronic device and the other party based on the occurrence of an event requesting a call in the electronic device. When the instructions are executed individually or collectively by the at least one processor, the electronic device may perform an operation of generating at least one conversation topic for conversation between the user and the counterpart based on the counterpart information, including the at least one conversation topic in a first UI screen, and displaying the first UI screen on the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of acquiring at least a portion of the conversation content between the user and the counterparty through the microphone and the communication circuit, acquiring at least one keyword from the acquired at least a portion of the conversation content, including the at least one keyword in a second UI screen, and displaying the second UI screen on the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of confirming a first user input selecting a first keyword on the second UI screen through the display. When the above command is executed individually or collectively by the at least one processor, the electronic device may perform an operation of acquiring first summary information associated with the first keyword from the conversation content based on the confirmation of the first user input.When the above instruction is executed individually or collectively by the at least one processor, the electronic device may perform the operation of displaying the first summary information on the display.

[0130] In the above explanation, prefixes such as “first,” “second,” and “third” are intended merely to distinguish components of the same name and are not assigned any special meaning in themselves, such as importance or order.

[0131] In the present disclosure, the expression 'connection' means not only a direct connection between components, but also an electrical connection where other components (e.g., resistors, inductors, etc.) are present between components.

[0132] In the present disclosure, an element constituting a 'keyword' may include at least one word, or the keyword may have the form of a sentence or the form of a list of multiple words.

[0133] The electronic device according to the various 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.

[0134] The various 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" may each 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.

[0135] The term “module” as used in the various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, 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. According to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0136] Various embodiments 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.

[0137] According to one embodiment, the method according to the various embodiments disclosed herein may be provided as 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.

[0138] According to various embodiments, 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 various embodiments, 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 multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, 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, mike; Communication circuit for wireless communication with external electronic devices; Touch-sensitive display; At least one processor; and It includes memory for storing instructions, When the above instruction is executed individually or collectively by the at least one processor, the electronic device, Based on the occurrence of a call request event in the electronic device, the information of the counterparty to be spoken to by the user of the electronic device is verified, and Based on the above counterpart information, at least one conversation topic to be conversed between the user and the counterpart is generated, the at least one conversation topic is included in the first UI screen, and the first UI screen is displayed on the display. Acquiring at least a portion of the conversation content between the user and the counterparty through the microphone and the communication circuit, acquiring at least one keyword from the acquired at least portion of the conversation content, including the at least one keyword in a second UI screen, and displaying the second UI screen on the display. A first user input selecting a first keyword on the second UI screen is confirmed through the display, and Based on the confirmation of the first user input, first summary information associated with the first keyword is obtained from the conversation content, and An electronic device that displays the above first summary information on the display.

2. In claim 1, when the instruction is executed individually or collectively by the at least one processor, the electronic device, Checking the second user input that has not selected the second keyword on the second UI screen through the display, and An electronic device that excludes second summary information associated with the second keyword from the extraction target based on the confirmation of the second user input.

3. In claim 2, when the instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that removes the above second keyword from the above second UI screen.

4. In claim 1, when the instruction is executed individually or collectively by the at least one processor, the electronic device, While a call is taking place between the above user and the above counterparty, a first conversation topic associated with the above first keyword is identified among the conversation topics included in the above first UI screen, and An electronic device that displays additional information associated with the first keyword on the display based on the identification of the first conversation topic.

5. In claim 4, when the instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that displays the additional information on the display so that the user can identify that the additional information is associated with the first conversation topic.

6. In claim 4, when the instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that displays the first summary information on the display so that the user can identify that the first summary information is associated with the first conversation topic.

7. In claim 1, when the instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that displays the first summary information on the display based on the termination of a call between the user and the counterparty.

8. In claim 1, when the instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that displays the first UI screen and the second UI screen together on the display.

9. The foldable housing structure of claim 8, comprising a first housing and a second housing foldably coupled to one side of the first housing; and further comprising a sensor that generates data used to determine whether the first housing and the second housing are in an unfolded state. When the above instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that displays the first UI screen and the second UI screen simultaneously on the display based on the first housing and the second housing being determined to be in the unfolded state.

10. The slideable housing structure of claim 8, comprising a first housing and a second housing coupled to the first housing to be slidably driven relative to the first housing; and further comprising a sensor that generates data used to determine whether the first housing and the second housing are in a slide-out state, When the above instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that displays the first UI screen and the second UI screen simultaneously on the display based on the first housing and the second housing being determined to be in the slide-out state.

11. In claim 1, when the instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that generates at least one conversation topic using a generative artificial intelligence model.

12. In claim 1, when the instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that obtains at least one keyword using a generative artificial intelligence model.

13. In claim 1, when the instruction is executed individually or collectively by the at least one processor, the electronic device, An electronic device that obtains the first summary information using a generative artificial intelligence model.

14. In a method of operating an electronic device, An operation to verify information of the counterparty to be spoken to by the user of the electronic device based on the occurrence of an event requesting a call in the electronic device; Based on the above counterpart information, the operation of generating at least one conversation topic for conversation between the user and the counterpart, including the at least one conversation topic in a first UI screen, and displaying the first UI screen on the display of the electronic device; The operation of obtaining at least a portion of the conversation content between the user and the counterparty from the microphone and communication circuit of the electronic device, obtaining at least one keyword from the obtained at least portion of the conversation content, including the at least one keyword in a second UI screen, and displaying the second UI screen on the display; An operation of confirming a first user input selecting a first keyword on the second UI screen through the display; and Based on the confirmation of the first user input, the operation of obtaining first summary information associated with the first keyword from the conversation content; and A method including the operation of displaying the above first summary information on the above display.

15. In Paragraph 14, An operation to confirm through the display a second user input in which a second keyword is not selected on the second UI screen; and A method further comprising the operation of excluding second summary information associated with the second keyword from the extraction target based on the confirmation of the second user input.

Images