Electronic device and method for providing message, and storage medium

Abstract

According to one embodiment of the present disclosure, an electronic device may comprise: a display; a communication circuit; a memory for storing instructions; and at least one processor. According to one embodiment, when executed by the at least one processor, the instructions can instruct the electronic device to: receive a first message from an external electronic device; identify at least one ambiguous part in the first message; determine whether additional information corresponding to the at least one ambiguous part can be provided using an artificial intelligence (AI) model trained on the basis of context information; and, on the basis of the determination that the additional information can be provided, display, on the display, an indication for indicating that the additional information can be provided, together with the first message.

Description

Electronic devices, methods, and storage media for providing messages

[0001] Embodiments disclosed in this document relate to electronic devices, methods, and storage media for providing messages.

[0002] Electronic devices (e.g., smartphones) can use messenger applications to send and receive messages with external electronic devices. Electronic devices can store multimedia information (e.g., images, audio, text). Electronic devices can obtain information from external servers. Electronic devices can access information stored on other electronic devices registered with the same account.

[0003] The above information may be provided as background information to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above is applicable as prior art in connection with the present disclosure.

[0004] According to one embodiment of the present disclosure, an electronic device may include a display, a communication circuit, a memory for storing instructions, and at least one processor. According to one embodiment, when the instructions are executed by the at least one processor, the electronic device may receive a first message from an external electronic device, identify at least one ambiguous part in the first message, determine whether additional information corresponding to the at least one ambiguous part can be provided using an artificial intelligence (AI) model learned based on context information, and, based on the determination that additional information can be provided, display an indication on the display along with the first message that additional information can be provided.

[0005] According to one embodiment of the present disclosure, a method for generating text of an electronic device may include: receiving a first message from an external electronic device; identifying at least one ambiguous part in the first message; determining whether additional information corresponding to the at least one ambiguous part can be provided using an AI model learned based on context information; and displaying an indication that additional information can be provided together with the first message based on the determination that additional information can be provided.

[0006] According to one embodiment of the present disclosure, in a computer-readable storage medium for storing instructions, the instructions may receive a first message from an external electronic device when executed by at least one processor of an electronic device, identify at least one ambiguous part in the first message, determine whether additional information corresponding to the at least one ambiguous part can be provided using an AI model learned based on context information, and, based on the determination that additional information can be provided, display an indication that additional information can be provided together with the first message.

[0007] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0008] FIG. 1 is a block diagram of the configuration of an electronic device according to one embodiment of the present disclosure.

[0009] FIG. 2 is a diagram showing the flow of text generation of an electronic device according to one embodiment of the present disclosure.

[0010] FIG. 3 is a diagram showing the flow of text generation of an electronic device according to one embodiment of the present disclosure.

[0011] FIGS. 4A and 4B are flowcharts of a method for generating text in an electronic device according to one embodiment of the present disclosure.

[0012] FIG. 5 is a flowchart of a method for generating text in an electronic device according to one embodiment of the present disclosure.

[0013] FIGS. 6A and 6B are diagrams illustrating examples of an electronic device generating a message according to one embodiment of the present disclosure.

[0014] FIG. 7 is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0015] FIG. 8 is a diagram illustrating an example of an electronic device generating a message according to an embodiment of the present disclosure.

[0016] FIG. 9 is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0017] FIG. 10 is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0018] FIG. 11 is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0019] FIG. 12 is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0020] FIG. 13A is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0021] FIG. 13b is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0022] FIG. 14A is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0023] FIG. 14b is a drawing illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0024] FIG. 14c is a drawing illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0025] FIG. 15a is a drawing illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0026] FIG. 15b is a drawing illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure.

[0027] FIG. 16 is a block diagram of an exemplary electronic device capable of performing the operations described in this document.

[0028] FIG. 17a is a drawing illustrating an unfolded state of a foldable electronic device according to one embodiment.

[0029] FIG. 17b is a drawing showing the rear of a foldable electronic device in an unfolded state according to one embodiment.

[0030] FIG. 18a is a drawing illustrating a partially infolded state of a foldable electronic device according to one embodiment.

[0031] FIG. 18b is a drawing illustrating a partially in-and-out-folded state of a foldable electronic device according to one embodiment.

[0032] FIG. 19a is a drawing illustrating a foldable electronic device in a completely infolded state according to one embodiment.

[0033] FIG. 19b is a drawing illustrating a foldable electronic device in a completely in-and-out-folded state according to one embodiment.

[0034] FIG. 20 illustrates a generative artificial intelligence system according to one embodiment.

[0035] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0036] Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that various modifications, equivalents, and / or alternatives of the embodiments of the present invention are included.

[0037]

[0038] FIG. 1 is a block diagram of the configuration of an electronic device according to one embodiment of the present disclosure.

[0039] According to various embodiments, the electronic device (110) of FIG. 1 may be at least partially similar to the electronic device (1600) of FIG. 16, or may include other embodiments of the electronic device.

[0040] According to one embodiment, the electronic device (110) may include a communication circuit (111) (e.g., the communication circuit (1660) of FIG. 16), a display (112) (e.g., the display (1640) of FIG. 16), a memory (113) (e.g., the memory (1620) of FIG. 16)) and / or at least one processor (114) (e.g., the processor (1610) of FIG. 16). For example, the electronic device (110) may include any electronic device such as a smartphone, a laptop, a desktop, a TV (television), a smart pad, a tablet PC (personal computer), a connected car, a home appliance, various Internet of Things (IoT) devices based on the Internet of Things (e.g., home IoT devices) and / or a mobile terminal. For example, the electronic device may include any form of wearable device that can be worn by a user, such as a smart watch, a smart band, smart glasses, smart earphones, a smart ring, a smart patch and / or a smart necklace. For example, the electronic device (110) may include at least one of a head-mounted display (HMD), a virtual reality headset (VRH), an augmented reality glasses device in the shape of glasses worn on the face, or an augmented reality helmet that provides content for virtual reality, augmented reality, mixed reality, or extended reality. For example, the electronic device (110) may include a video see-through (VST) device.

[0041] According to one embodiment, the communication circuit (111) can transmit and receive data with another electronic device (not shown) using communication technology. For example, communication technology may include Bluetooth communication, BLE (Bluetooth Low Energy) communication, near field communication (NFC), WLAN (wireless local area network) communication, Zigbee communication, infrared data association (IrDA) communication, WFD (WiFi Direct) communication, UWB (ultra-wideband) communication, ANT (advanced and adaptive network technology) communication, WIFI communication, RFID (radio frequency identification) communication, 3G communication, 4G communication, and 5G communication. However, communication technology is not limited thereto. For example, the communication circuit (111) can transmit and receive data with an external electronic device using any communication protocol.

[0042] According to one embodiment, the display (112) may include a display having a fixed shape and / or a deformable display such as a foldable display or a rollable (or slideable) display. For example, the display (112) may include a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electro mechanical system (MEMS) display, and / or an electronic paper display. According to one embodiment, the display (112) may include a plurality of displays (e.g., a first display, a second display). For example, the display (112) may include a main display (e.g., a relatively large display among the displays of the electronic device (110)) and a sub-display (e.g., a relatively small display among the displays of the electronic device (110).

[0043] According to one embodiment, the memory (113) may include built-in memory (not shown) and / or external memory (not shown). For example, the built-in memory may include at least one of a volatile memory (e.g., dynamic random access memory (DRAM), static random access memory (SRAM), or synchronous DRAM (SDRAM)), a non-volatile memory (e.g., programmable read-only memory (PROM), one time PROM (OTPROM), erasable PROM (EPROM), electrically erasable and PROM (EEPROM), mask ROM, flash ROM, flash memory, a hard drive, or a solid state drive (SSD). The external memory may include at least one of a flash drive (e.g., compact flash), secure digital (SD), micro-SD, mini-SD, extreme digital (xD), multi-media card (MMC), or memory stick.

[0044] According to one embodiment, the memory (113) may store instructions that can be executed by at least one processor (114). The memory (113) may store at least one data related to the operation of the electronic device (110) and / or instructions and / or commands related to the functional operation of components of the electronic device (110). For example, the memory (113) may store at least one application that is preloaded upon manufacturing the electronic device (110) or downloaded from a third party through an online market (e.g., an application store).

[0045] According to one embodiment, at least one processor (114) may be electrically connected to components of an electronic device (110). For example, at least one processor (114) may be connected to a communication circuit (111), a display (112), and / or a memory (113). For example, at least one processor (114) may be wired to components of the electronic device (110). At least one processor (114) may be composed of a single chip or multiple chips. For example, at least one processor (114) may include at least one processing circuitry including a central processing unit (CPU), an application processor (AP), a micro processor unit (MPU), a communication processor (CP), a system on chip (SoC), and / or an integrated circuit (IC).

[0046] According to one embodiment, at least one processor (114) can perform operations necessary for the operation of the electronic device (110). The operations of the electronic device (110) may be performed by at least one processor executing instructions stored in memory (113) individually or collectively. Some of the operations of the electronic device (110) may be performed by a first processor executing instructions, and at least some of the remaining operations may be performed by a second processor different from the first processor executing instructions. At least one processor (114) may control the components of the electronic device (110). For example, the operations of the electronic device (110) described in the disclosure of this document may be referred to as being performed by at least one processor. For example, the operations of the electronic device (110) may be performed by at least one processor executing instructions stored in memory (113).

[0047] According to one embodiment, at least one processor (114) can receive a first message from an external electronic device using a communication circuit (111). For example, at least one processor (114) can receive the first message from an external electronic device through a messenger application.

[0048] In one embodiment, at least one processor (114) may identify at least one ambiguous portion in the first message. For example, upon receiving user input regarding the received first message, the at least one processor (114) may identify at least one ambiguous portion in the first message. For example, the ambiguous portion may include an abstract portion and / or a portion whose reference is unclear. For example, the ambiguous portion may include a pronoun. For example, the ambiguous portion may include an abbreviated word (or sentence). For example, the ambiguous portion may include a portion whose meaning is unclear without other additional information. For example, the ambiguous portion may include at least one word. In one embodiment, the at least one processor (114) may identify at least one ambiguous portion in the first message using an artificial intelligence (AI) model (e.g., a large language model (LLM), a large multimodal model (LMM)).

[0049] According to one embodiment, at least one processor (114) may determine whether additional information corresponding to at least one ambiguous portion can be provided using an AI model learned based on context information. For example, the context information may include at least one of information about messages previously received through an application related to the first message, information related to multimedia stored in the memory (113), information stored on an external server related to another application, or information stored in another electronic device registered with the same account as the electronic device (110).

[0050] For example, information on messages previously received through an application (e.g., a messenger application) associated with the first message may include information on messages previously received from an external electronic device that transmitted the first message and / or information on messages previously received from another external electronic device different from the external electronic device. For example, information on messages previously received through an application associated with the first message may include information on messages transmitted by the electronic device (110) to an external electronic device. For example, information on messages previously received through an application associated with the first message may include text information, audio information, and / or image information. For example, information on messages previously received through an application associated with the first message may include information tagged by a user in relation to specific message content.

[0051] For example, multimedia-related information may include image information, audio information, and / or text information. For example, image information may include image information that can be explored in a gallery application. For example, audio information may include audio information that can be explored in a recording application. For example, image information and / or audio information may include metadata for each image and / or audio. For example, metadata may include information about the date, time, and / or location where each image was acquired. For example, metadata may include information related to the path through which image information and / or audio information were acquired (e.g., identification information of the external electronic device that transmitted the image and / or audio, link information of the external server that acquired the image and / or audio). For example, metadata may include information related to the results of analyzing the image and / or audio. For example, information related to the results of analyzing the image may include information about objects contained in the image (e.g., person information, object information, background information, and / or weather information). For example, information related to the results of audio analysis may include information about the speaker included in the audio (e.g., speech). For example, metadata may include information tagged while acquiring image information and / or audio information. For example, text information may include information related to the user's schedule. For example, information related to the user's schedule may include the user's schedule information (e.g., date information, time information, location information, person information (e.g., who is meeting), and / or behavior information (e.g., what is being done)) that can be explored in a calendar application.

[0052] For example, information stored on an external server related to another application may refer to information stored on a server (e.g., a cloud server) linked to another application (e.g., an application different from the application related to the first message). Information stored on an external server related to another application may include information stored in a database accessible to a user of the electronic device (110) and managed by a third party. For example, the other application may include a messenger application different from the application related to the first message. At least one processor (114) may include text information stored in another application into context information through optical character recognition (OCR) technology.

[0053] For example, information stored in another electronic device registered with the same account as the electronic device (110) (e.g., a user's ID (identification) and password granted to the user when the user subscribes to a service for managing multiple electronic devices) may include information about messages previously received through a messenger application stored in the other electronic device, information related to multimedia, and / or information stored in an external server related to another application. For example, the electronic device (110) may receive information stored in another electronic device registered with the same account through a server that manages the account.

[0054] In one embodiment, the context information may include information stored in the external electronic device that transmitted the first message. At least one processor (114) may acquire user authorization from the external electronic device that transmitted the first message. Based on the acquisition of user authorization, at least one processor (114) may utilize information stored in the external electronic device.

[0055] In one embodiment, an AI model learned based on context information may include a model that has learned at least a portion of the context information. For example, an AI model learned based on context information may include a model that has partially learned the context information and is combined with a previously learned model through LoRa (low-rank adaptation) technology. For example, when new information is added to the context information, an AI model learned based on context information may include a model that has learned the added new information. For example, an AI model learned based on context information may include a model that can retrieve and utilize new information added to the context information through RAG (retrieval augmented generation) technology in which the user's context information is logged.

[0056] According to one embodiment, at least one processor (114) may use an AI model trained based on contextual information to identify information related to at least one ambiguous portion. For example, the information related to the at least one ambiguous portion may include information used to provide additional information (e.g., a previously received message, a schedule searched in a calendar application, an image searched in a gallery application). For example, if the contextual information includes information related to the at least one ambiguous portion, the at least one processor (114) may determine that providing additional information corresponding to the at least one ambiguous portion is possible.

[0057] For example, information related to at least one ambiguous part may include, among the context information, information that at least one ambiguous part refers to (or represents), information that clarifies at least one ambiguous part, and / or information that explains (or supplements) at least one ambiguous part.

[0058] For example, additional information corresponding to at least one ambiguous part may include information extracted from information related to at least one ambiguous part. For example, additional information corresponding to at least one ambiguous part may include information referred to (or indicated) by at least one ambiguous part.

[0059] According to one embodiment, at least one processor (114) may display an indication that additional information can be provided on the display (112) along with the first message, based on a judgment that additional information can be provided. For example, if there is information related to at least one ambiguous part in the context information, at least one processor (114) may generate an indication that additional information can be provided and display the indication on the display (112).

[0060] According to one embodiment, at least one processor (114) may provide a second message containing said additional information without displaying an indication that said additional information is possible, based on a judgment that said additional information is possible. For example, if at least one processor (114) identifies at least one ambiguous part in a received first message, it may provide a second message containing said additional information corresponding to at least one ambiguous part.

[0061] According to one embodiment, at least one processor (114) may, based on a determination that the provision of additional information is not possible, provide information indicating that the provision of additional information is not possible. For example, at least one processor (114) may, based on a determination that the provision of additional information is not possible, provide a message, affordance, and / or notification indicating that the provision of additional information is not possible. However, without limitation, at least one processor (114) may provide any form of information indicating that the provision of additional information is not possible.

[0062] In one embodiment, the indication that additional information is available may include at least one of an affordance for transforming the first message into a second message including the additional information, a visual effect for modifying a feature of text included in the at least one ambiguous portion, or a visual effect for modifying a feature of a display area in which the first message is displayed.

[0063] In one embodiment, at least one processor (114) may, if additional information is available, provide an audible notification indicating that additional information is available. For example, at least one processor (114) may display an indication on the display (112) indicating that additional information is available, while providing an audible notification through a speaker (not shown) indicating that additional information is available.

[0064] For example, the affordance may include a user-interactive GUI (graphical user interface) object that can be optionally displayed on the display (112). For example, the affordance may include at least one of an image (e.g., an icon), an emoticon, a button, or text (e.g., a hyperlink).

[0065] For example, a visual effect that modifies the features of text contained in at least one ambiguous part may include an effect that modifies the color, size, thickness, and / or shape of the text (or characters) contained in at least one ambiguous part. For example, a visual effect that modifies the features of text contained in at least one ambiguous part may include an effect that highlights (e.g., highlights, underlines) at least one ambiguous part.

[0066] For example, a visual effect that modifies the characteristics of a display area where a first message is displayed may include an effect that modifies the size, background color, and / or shape of the display area. For example, a visual effect that modifies the characteristics of a display area where a first message is displayed may include an effect that modifies the color and / or thickness of the border of the display area.

[0067] According to one embodiment, at least one processor (114) may generate a second message comprising at least a portion of a first message and the additional information. For example, at least one processor (114) may generate a second message in which at least one ambiguous portion of the first message is replaced with the additional information. For example, at least one processor (114) may generate a second message in which the additional information is added to the first message. For example, at least one processor (114) may generate a second message in which the additional information is added in the form of tagging of at least one ambiguous portion.

[0068] According to one embodiment, at least one processor (114) may generate a second message including image information corresponding to the photograph, if at least one ambiguous portion is related to the photograph. For example, at least one processor (114) may generate a second message that adds image information corresponding to the photograph to the first message, if at least one ambiguous portion is related to the photograph. An example of a second message that adds image information corresponding to the photograph to the first message may be described below in FIG. 12.

[0069] In one embodiment, at least one processor (114) may generate a second message including information used to provide additional information. For example, at least one processor (114) may generate a second message that adds information related to at least one ambiguous portion to the first message. An example of a second message that adds information related to at least one ambiguous portion to the first message may be described below in FIG. 13A or 13B .

[0070] According to one embodiment, at least one processor (114) may, based on receiving a user input (e.g., a gesture input) selecting at least one keyword (e.g., at least one ambiguous part) included in a message (e.g., a first message and / or a second message), provide additional information related to the selected at least one keyword centered around the selected at least one keyword. For example, the at least one processor (114) may display the additional information related to the selected at least one keyword in an area adjacent to the at least one keyword selected based on the user input in the message.

[0071] According to one embodiment, at least one processor (114) may determine the size of the data of additional information based on user input (e.g., pinch in (pinch zoom-out) or pinch out (pinch zoom-in) that adjusts the size of the display area where the first message and / or the second message is displayed. For example, the pinch in input may be a gesture input for zooming out the display area by bringing two touched points closer together, and the pinch out input may be a gesture input for zooming in the display area by moving two touched points further apart. For example, the size of the data of additional information may be determined in correspondence with the size of the display area. For example, at least one processor (114) may increase the size of the data of additional information based on user input that widens the size of the display area where the first message and / or the second message is displayed. For example, if the size of the display area where the first message and / or the second message is displayed is widened, the additional information may contain more text. For example, at least one processor (114) may increase the size of the data of additional information based on user input that narrows the size of the display area where the first message is displayed. Based on input, the size of the data of additional information may be reduced. For example, if the size of the display area where the first message and / or the second message is displayed is narrowed, the additional information may contain less text. According to one embodiment, if at least one processor (114) is unable to provide additional information corresponding to at least one ambiguous part identified in the first message, the size of the display area may not be adjusted even if it receives user input (e.g., pinch out, pinch in) to adjust the size of the display area of ​​the first message (e.g., zoom in, zoom out).

[0072] For example, if the ambiguous part is “there” in “let’s meet there” and the meaning of “there” found based on context information is “Gangnam Station Exit 4”, then depending on the size of the display area, the additional information included in the second message may be “at Gangnam Station” or “at Gangnam Station Exit 4”.

[0073] For example, if the ambiguous part is “then” in “Okay, let’s meet then” and the meaning of “then” found based on context information is “next week x day, x month x day in 2024 at x o’clock in the afternoon,” as the display area expands, the additional information included in the second message can range from “at x o’clock in the afternoon” to “next week x day, at x o’clock in the afternoon”, “x month x day at x o’clock in the afternoon in 2024”, and “next Wednesday, x month x day in 2024 at x o’clock in the afternoon”.

[0074] According to one embodiment, at least one processor (114) may receive user input for an indication that additional information may be provided. For example, at least one processor (114) may receive touch input and / or gesture input for said indication (e.g., touch gestures including tap, double tap, press, flick, swipe, pan, drag, and / or pinch zoom). For example, at least one processor (114) may include gaze input and / or voice input for said indication. For example, gaze input may include input determined based on the direction of the user's gaze or the time at which the user's gaze is located.

[0075] According to one embodiment, at least one processor (114) can display a second message on a display (112) based on user input regarding the indication. For example, at least one processor (114) can convert a first message into a second message based on user input regarding the indication and display the second message. For example, at least one processor (114) can display a second message in a display area where the first message is displayed based on user input regarding the indication.

[0076] According to one embodiment, at least one processor (114) may display an effect indicating that the additional information included in the second message is additional information. For example, at least one processor (114) may display a highlight on the text of the additional information included in the second message. For example, at least one processor (114) may display a change in the color, size, thickness, and / or shape of the text of the additional information included in the second message.

[0077] According to one embodiment, at least one processor (114) may display a first message on a first display and the second message on a second display among a plurality of displays. According to one embodiment, at least one processor (114) may divide an area of ​​a display (112) and display a first message and a second message in each divided area. For example, at least one processor (114) may display a first message in a first area (e.g., a left area or an upper area of ​​the entire area) and display a second message in a second area (e.g., a right area or a lower area of ​​the entire area) among the areas of the display (112).

[0078] According to one embodiment, when a plurality of messages are received, at least one processor (114) may receive a user input for a first message among the plurality of messages. For example, when the plurality of messages are received, the at least one processor (114) may include a touch input and / or a gesture input for a display area where the first message among the plurality of messages is displayed. According to one embodiment, the at least one processor (114) may identify at least one ambiguous part in the first message based on a user input for the first message among the plurality of received messages. The at least one processor (114) may determine whether additional information corresponding to the at least one ambiguous part can be provided. Based on the determination that the provision of the additional information is possible, the at least one processor (114) may provide an indication indicating that the provision of the additional information is possible. Based on the user input for the indication, the at least one processor (114) may generate a second message including at least a portion of the first message and additional information corresponding to the identified at least one ambiguous part. At least one processor (114) may display the generated second message on the display (112). In one embodiment, based on a determination that the provision of the additional information is possible, the at least one processor (114) may generate the second message and display it on the display (112) without providing an indication indicating that the provision of the additional information is possible. In one embodiment, based on a determination that the provision of the additional information is not possible, the at least one processor (114) may provide information indicating that the generation of the second message is impossible.

[0079] According to one embodiment, at least one processor (114) can identify a plurality of ambiguous parts, including a first ambiguous part and a second ambiguous part, in a first message. According to one embodiment, at least one processor (114) can receive user input regarding the first ambiguous part. For example, at least one processor (114) can obtain touch input, gesture input, and / or voice input regarding the first ambiguous part in the first message. According to one embodiment, at least one processor (114) can determine whether additional information corresponding to the first ambiguous part can be provided based on user input regarding the first ambiguous part. Based on the determination that additional information can be provided, at least one processor (114) can provide an indication indicating that additional information can be provided. Based on user input regarding the indication, at least one processor (114) can generate a second message including at least a portion of the first message and additional information corresponding to the first ambiguous part. For example, the second message may include a message in which a first ambiguous part of the first message is replaced with additional information corresponding to said first ambiguous part. For example, the second message may include a message in which additional information corresponding to said first ambiguous part is added in the form of tagging of said first ambiguous part. According to one embodiment, at least one processor (114) may generate a second message and display it on the display (112) without providing an indication that the additional information is available, based on a judgment that the additional information is available. According to one embodiment, at least one processor (114) may provide information that the second message cannot be generated based on a judgment that the additional information is not available.

[0080] According to one embodiment, at least one processor (114) may display on the display (112) a first screen including a first message, a second screen including a second message, and a third screen including information used to generate the second message (or information related to at least one ambiguous portion, information used to provide additional information). For example, at least one processor (114) may display the first screen, the second screen, and the third screen in a divided manner on the display (112). For example, an example of displaying the first screen, the second screen, and the third screen on the display (112) may be described below with reference to FIGS. 15A and 15B.

[0081] In one embodiment, at least one processor (114) may identify at least one ambiguous part in a third message that the user has written and / or is writing. For example, if the user has written and / or is writing a third message that is identical or similar to "Let's meet at the place we talked about last time," the at least one processor (114) may identify an ambiguous part such as "the place we talked about last time." In one embodiment, the at least one processor (114) may determine whether additional information corresponding to the at least one ambiguous part is available for provision using an AI model learned based on context information. If the at least one processor (114) is able to provide additional information corresponding to the at least one ambiguous part, the at least one processor (114) may display an indication indicating that the additional information is available together with the third message. Based on a user input for the indication, the at least one processor (114) may generate a fourth message that includes at least a portion of the third message and the additional information. At least one processor (114) can convert the third message into the fourth message and display it on the display (112).

[0082] According to one embodiment, at least one processor (114) may identify at least one ambiguous portion in voice information received from an external electronic device. For example, when the at least one processor (114) is in voice communication with the external electronic device (e.g., when the user is on a phone call with a third party), the at least one processor (114) may identify at least one ambiguous portion in the voice information received from the external electronic device. The at least one processor (114) may determine whether additional information corresponding to the at least one ambiguous portion can be provided using an AI model learned based on context information. Based on the determination that the provision of additional information is possible, the at least one processor (114) may display an indication on the display (112) indicating that the provision of additional information is possible. The at least one processor (114) may receive a user input for the indication indicating that the provision of additional information is possible. At least one processor (114) may provide the additional information through the display (112) and / or a speaker (not shown) based on a user input for the indication. For example, when a user is making a call while wearing a wearable device (e.g., a VST device, smart earphones), if the at least one processor (114) identifies at least one ambiguous part in the voice call with the other party, the at least one processor (114) may display an indication through the display (112) indicating that there is additional information corresponding to the at least one ambiguous part. The at least one processor (114) may provide the additional information through the display (112) and / or the speaker based on a user input for the indication (e.g., a gaze input, a touch input, a voice input, and / or a gesture input).

[0083] According to one embodiment, at least one processor (114) can identify at least one ambiguous part in voice information containing the voices of a plurality of speakers. At least one processor (114) can provide additional information corresponding to at least one ambiguous part. For example, the additional information may include information about who spoke the at least one ambiguous part and / or who spoke the additional information.

[0084] According to one embodiment, at least one processor (114) can identify at least one ambiguous part in text information provided by an external server. At least one processor (114) can provide additional information corresponding to at least one ambiguous part. For example, at least one processor (114) can provide said additional information based on other text information provided by an external server.

[0085] According to one embodiment, at least one processor (114) may receive a first image from an external electronic device. According to one embodiment, at least one processor (114) may identify at least one ambiguous part in the received first image. For example, at least one processor (114) may identify a part in the first image that is difficult to recognize because it is blurred or has low illumination. According to one embodiment, at least one processor (114) may search for additional information corresponding to the at least one ambiguous part using an AI model learned based on context information. At least one processor (114) may generate a second image that complements at least one ambiguous part in the first message using the additional information. At least one processor (114) may display the second image through a display (112).

[0086] Each of the components of the electronic device (110) described above may include a singular or multiple entities. For example, some of the multiple entities may be separated and placed in other components. According to one embodiment, one or more of the components of the electronic device (110) described above may be omitted, or one or more other components may be added. According to one embodiment, the components of the electronic device (110) may omit at least some of the operations of the components of the electronic device (110) described above (e.g., operations of the processor (114)), or additionally perform one or more other operations.

[0087]

[0088] FIG. 2 is a diagram illustrating the flow of text generation in an electronic device according to one embodiment of the present disclosure. In the following, any description that overlaps with the description in FIG. 1 will be omitted or briefly described.

[0089] According to one embodiment, the electronic device (110) can obtain user input through a user input unit (210). For example, the user input unit (210) can include a display (112) and / or a microphone (not shown).

[0090] In one embodiment, the electronic device (110) may execute a messenger application (220) based on user input. For example, the electronic device (110) may execute a messenger application (220) capable of browsing messages exchanged with an external electronic device.

[0091] According to one embodiment, the electronic device (110) can identify at least one ambiguous part in the messenger application (220). For example, the electronic device (110) can identify at least one ambiguous part in a first message included in a screen displayed through the messenger application (220). For example, the ambiguous part may include an abstract part or a part whose reference is unclear. For example, the ambiguous part may include a pronoun. For example, the ambiguous part may include an abbreviated word (or sentence). For example, the ambiguous part may include a part whose meaning is unclear without other additional information. For example, the ambiguous part may include at least one word.

[0092] According to one embodiment, the electronic device (110) may determine whether additional information corresponding to the identified ambiguous portion can be provided using an AI model (240) learned based on context information (230). For example, the context information may include at least one of information about messages previously received through a messenger application (220), information related to multimedia stored in the electronic device (110), information stored in an external server related to another application, or information stored in another electronic device registered with the same account as the electronic device (110).

[0093] According to one embodiment, the electronic device (110) may provide an indication indicating that additional information can be provided based on a judgment that additional information can be provided. For example, if the electronic device (110) has information related to at least one ambiguous part in the context information, it may display an indication indicating that additional information can be provided on the display (112) together with the first message. For example, the indication indicating that additional information can be provided may include at least one of an affordance that converts the first message into a second message containing additional information, a visual effect that modifies the features of the text included in at least one ambiguous part, or a visual effect that modifies the features of the display area where the first message is displayed.

[0094] For example, the affordance may include a user-interactive GUI (graphical user interface) object that can be optionally displayed on the display (112). For example, the affordance may include at least one of an image (e.g., an icon), an emoticon, a button, or text (e.g., a hyperlink).

[0095] For example, a visual effect that modifies the features of text contained in at least one ambiguous part may include an effect that modifies the color, size, thickness, and / or shape of the text (or characters) contained in at least one ambiguous part. For example, a visual effect that modifies the features of text contained in at least one ambiguous part may include an effect that highlights (e.g., highlights, underlines) at least one ambiguous part.

[0096] For example, a visual effect that modifies the characteristics of a display area where a first message is displayed may include an effect that modifies the size, background color, and / or shape of the display area. For example, a visual effect that modifies the characteristics of a display area where a first message is displayed may include an effect that modifies the color and / or thickness of the border of the display area.

[0097] According to one embodiment, the electronic device (110) may receive user input regarding an indication that additional information may be provided. For example, the electronic device (110) may include touch input and / or gesture input regarding the indication (e.g., touch gestures including tap, double tap, press, flick, swipe, pan, drag, and / or pinch zoom). For example, the electronic device (110) may include gaze input and / or voice input regarding the indication. For example, the gaze input may include input determined based on the direction of the user's gaze or the time at which the user's gaze is located.

[0098] According to one embodiment, the electronic device (110) may generate a second message including at least a portion of a first message and the additional information based on user input regarding the indication. For example, the electronic device (110) may generate a second message in which at least one ambiguous part of the first message is replaced with the additional information based on user input regarding the indication. For example, the electronic device (110) may generate a second message in which the additional information is added to the first message based on user input regarding the indication. For example, the electronic device (110) may generate a second message in which the additional information is added in the form of tagging of at least one ambiguous part based on user input regarding the indication.

[0099] According to one embodiment, the electronic device (110) can display a second message on a display (112). For example, the electronic device (110) can convert a first message into a second message and display the second message. For example, the electronic device (110) can display the second message in a display area where the first message is displayed.

[0100]

[0101] FIG. 3 is a diagram illustrating the flow of text generation of an electronic device according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0102] According to one embodiment, the electronic device (110) can receive a first message. The electronic device (110) can display (310) the received first message through a display (112). For example, the electronic device (110) can display (310) the first message on the screen of a messenger application through the display (112).

[0103] According to one embodiment, the electronic device (110) can extract ambiguous parts (330) from a first message using a message management unit (301). For example, when the electronic device (110) receives user input for a received first message, it can extract ambiguous parts (330) from the first message using the message management unit (301). For example, the electronic device (110) can extract ambiguous parts (330) from the first message, including abstract parts and / or parts whose referring content is unclear. For example, the electronic device (110) can extract ambiguous parts (330) from the first message, including pronouns. For example, the electronic device (110) can extract ambiguous parts (330) from the first message, including abbreviated words (or sentences).

[0104] According to one embodiment, the electronic device (110) can summarize the received messages (320). For example, the electronic device (110) can summarize (320) the first message and at least one message previously received through a messenger application. According to one embodiment, the electronic device (110) can store the received messages in a database. For example, the electronic device (110) can store at least one message received prior to the reception of the first message and / or the first message in a database.

[0105] According to one embodiment, the electronic device (110) can search for additional information (340) corresponding to the ambiguous part using an additional information search unit (303). For example, the additional information search unit (303) can search for additional information (340) corresponding to the ambiguous part using an AI model learned based on context information. For example, the context information may include information about a summarized message received from a message management unit (301). For example, the context information may include a database in which received messages are stored. For example, the context information may include at least one of information about messages previously received through a messenger application, information related to multimedia stored in the electronic device (110), information stored on an external server related to another application, or information stored on another electronic device registered with the same account as the electronic device (110). According to one embodiment, the additional information search unit (303) can search for additional information (340) corresponding to the ambiguous part in a database in which received messages are stored using a retrieval augmented generation (RAG) method.

[0106] According to one embodiment, the electronic device (110) can generate a second message (350). For example, the electronic device (110) can generate a second message (350) including additional information corresponding to at least a part and an ambiguous part of the first message. For example, the electronic device (110) can generate a second message (350) in which an ambiguous part of the first message is replaced with additional information. For example, the electronic device (110) can generate a second message (350) in which additional information is added to the first message. For example, the electronic device (110) can generate a second message (350) in which additional information is added in the form of tagging of at least one ambiguous part.

[0107] According to one embodiment, the electronic device (110) can display (360) the generated second message through the display (112). For example, the electronic device (110) can convert the first message into a second message and display (360) the second message through the display (112). For example, the electronic device (110) can display (360) the second message through the display (112) in a display area where the first message is displayed.

[0108]

[0109] FIGS. 4a and 4b are flowcharts of a method for generating text of an electronic device according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0110] According to one embodiment, in FIG. 4a, operations 410a to 440a can be understood as being performed in a processor (e.g., processor (114) of FIG. 1) of an electronic device (e.g., electronic device (110) of FIG. 1).

[0111] In operation 410a, according to one embodiment, the electronic device may receive a first message from an external electronic device. For example, the electronic device may receive the first message from the external electronic device through a messenger application. According to one embodiment, the electronic device may display the received first message on a display (e.g., the display (112) of FIG. 1).

[0112] In operation 420a, according to one embodiment, the electronic device may identify at least one ambiguous part, a missing part, a missing context or content, and / or a skipped context or content in the first message. For example, the ambiguous part may include an abstract part or a part whose meaning is unclear. For example, the ambiguous part may include a pronoun. For example, the ambiguous part may include an abbreviated word (or sentence). For example, the ambiguous part may include a part whose meaning is unclear without other additional information. For example, the ambiguous part may include at least one word.

[0113] In operation 430a, according to one embodiment, the electronic device may determine whether additional information corresponding to at least one ambiguous part can be provided. For example, the electronic device may search for additional information corresponding to at least one ambiguous part using an AI model learned based on context information. For example, the context information may include at least one of information on messages previously received through an application related to the first message, information related to multimedia stored in the electronic device, information stored on an external server related to another application, or information stored on another electronic device registered with the same account as the electronic device.

[0114] For example, an AI model learned based on context information may include a model that has learned at least a portion of the context information. For example, an AI model learned based on context information may include a model that has partially learned the context information and is combined with a previously learned model using LoRa (low-rank adaptation) technology. For example, if new information is added to the context information, an AI model learned based on context information may include a model that has learned the added new information. For example, an electronic device may use an AI model learned based on context information to determine whether the context information contains information related to at least one ambiguous part.

[0115] In operation 440a, according to one embodiment, the electronic device may display an indication indicating that provision of additional information is possible on a display (e.g., display 112 of FIG. 1) together with the first message, if the context information includes information related to at least one ambiguous portion, the electronic device may generate an indication indicating that provision of additional information is possible and display the indication on the display. For example, the indication indicating that provision of additional information is possible may include at least one of an affordance for converting the first message into a second message including the additional information, a visual effect for modifying a feature of text included in the at least one ambiguous portion, or a visual effect for modifying a feature of a display area on which the first message is displayed.

[0116] According to one embodiment, in FIG. 4b, operations 410b to 450b may be understood to be performed in a processor (e.g., processor (114) of FIG. 1) of an electronic device (e.g., electronic device (110) of FIG. 1).

[0117] In operation 410b, according to one embodiment, the electronic device may receive a first message from an external electronic device. For example, the electronic device may receive the first message from the external electronic device through a messenger application. According to one embodiment, the electronic device may display the received first message on a display (e.g., the display (112) of FIG. 1).

[0118] In operation 410b, according to one embodiment, the electronic device may receive user input for the first message. For example, the electronic device may receive touch input and / or gesture input (e.g., touch gestures including tap, double tap, press, flick, swipe, pan, drag, and / or pinch zoom) for the received first message.

[0119] In operation 430b, according to one embodiment, the electronic device may identify at least one ambiguous part, a missing part, a missing context or content, and / or a skipped context or content in the first message. For example, the ambiguous part may include an abstract part or a part whose meaning is unclear. For example, the ambiguous part may include a pronoun. For example, the ambiguous part may include an abbreviated word (or sentence). For example, the ambiguous part may include a part whose meaning is unclear without other additional information. For example, the ambiguous part may include at least one word.

[0120] In operation 440b, according to one embodiment, the electronic device may generate a second message containing additional information corresponding to at least one ambiguous part. For example, when the electronic device identifies at least one ambiguous part in a first message, it may search for additional information corresponding to said at least one ambiguous part using an AI model learned based on context information. The electronic device may generate a second message containing the searched additional information and at least a portion of the first message. The electronic device may generate a second message in which said at least one ambiguous part is changed to said additional information.

[0121] In operation 450b, according to one embodiment, the electronic device may change the first message into a second message and display it. For example, the electronic device may display the content of the second message in the display area of ​​the first message. However, not limited thereto, the electronic device may also display the second message together with the first message.

[0122] The order of operations described above in relation to FIGS. 4a and 4b is merely an example, and embodiments of the present disclosure are not limited thereto. For example, at least some of the operations may be performed differently from the order of FIG. 4 or may be performed substantially simultaneously with other operations of FIG. 4. At least some of the operations described above in relation to FIG. 4 may be omitted.

[0123]

[0124] FIG. 5 is a flowchart of a method for generating text of an electronic device according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0125] According to one embodiment, operations 510 to 590 may be understood to be performed in a processor (e.g., processor (114) of FIG. 1) of an electronic device (e.g., electronic device (110) of FIG. 1).

[0126] In operation 510, according to one embodiment, an electronic device (e.g., the electronic device (110) of FIG. 1) can execute a messenger application. For example, the electronic device can execute the messenger application based on user input that executes the messenger application. For example, the electronic device can execute the messenger application based on receiving a first message from an external electronic device.

[0127] In operation 520, according to one embodiment, the electronic device may display a first screen including a plurality of messages exchanged with an external electronic device. For example, the electronic device may display a first screen including a first message received from a first external electronic device and at least one message exchanged with the external electronic device prior to the first message.

[0128] In operation 530, according to one embodiment, the electronic device can recognize the contents of a plurality of messages. For example, the electronic device can recognize the contents of messages included in the first screen (e.g., the first message and messages transmitted or received prior to the first message).

[0129] In operation 540, according to one embodiment, the electronic device may recognize a received message received from an external electronic device among a plurality of messages. For example, the received message may include a first message and at least one message received from an external electronic device prior to the first message. For example, the electronic device may recognize a first message and at least one message received from an external electronic device prior to the first message.

[0130] In operation 550, according to one embodiment, the electronic device may determine whether there is an ambiguity in the received message based on the contents of the plurality of messages. For example, the electronic device may determine whether there is an ambiguity in the first message and at least one message received prior to the first message based on the contents of the messages included in the first screen. For example, if an ambiguity is identified in the received message and there is no content related to the ambiguity in the messages included in the first screen, the electronic device may determine that there is an ambiguity in the received message (e.g., operation 550 - Yes). For example, even if an ambiguity is identified in the received message, if the messages included in the first screen contain content related to the ambiguity (e.g., even if there is an ambiguity in the received message, if the ambiguity is clarified from the contents included in the first screen), the electronic device may determine that there is no ambiguity in the received message (e.g., operation 550 - No). According to one embodiment, the electronic device may determine whether there is an ambiguity in a specific message based on a user input for a specific message among the plurality of messages. The electronic device may determine that there are no ambiguous parts in a specific message if there is content related to a specific message among the messages included in the first screen. The electronic device may determine that there are ambiguous parts in a specific message if there is no content related to a specific message among the messages included in the first screen.

[0131] For example, an ambiguous part may contain abstract parts and / or parts whose meaning is unclear. For example, an ambiguous part may contain pronouns. For example, an ambiguous part may contain abbreviated words (or sentences). For example, an ambiguous part may contain parts whose meaning is unclear without additional information. For example, an ambiguous part may contain at least one word.

[0132] In operation 560, according to one embodiment, if the electronic device determines that there is an ambiguous part in the received message (e.g., operation 550-Yes), it may extract the ambiguous part (e.g., the ambiguous part extraction (330) of FIG. 3). For example, the electronic device may extract an ambiguous part in the received message that includes an abstract part and / or a part whose reference is unclear. For example, the electronic device may extract an ambiguous part in the received message that includes a pronoun. For example, the electronic device may extract an ambiguous part in the received message that includes an abbreviated word (or sentence).

[0133] In operation 570, according to one embodiment, the electronic device may search for additional information corresponding to the ambiguous part. For example, the electronic device may search for additional information corresponding to the ambiguous part by using an AI model trained based on context information. For example, the context information may include at least one of information on messages previously received through a messenger application, information related to multimedia stored on the electronic device, information stored on an external server related to another application, or information stored on another electronic device registered with the same account as the electronic device.

[0134] In operation 580, according to one embodiment, the electronic device may generate a second message including additional information. For example, the electronic device may generate a second message including additional information corresponding to at least a portion of the received message and the ambiguous portion. For example, the electronic device may generate a second message by replacing the ambiguous portion of the received message with the additional information. For example, the electronic device may generate a second message by adding additional information to the received message. For example, the electronic device may generate a second message by adding the additional information in the form of tagging the ambiguous portion. According to one embodiment, after generating the second message, the electronic device may display a notification indicating that the second message has been generated. For example, the electronic device may display an affordance indicating the presence of the second message in association with the ambiguous portion (e.g., next to the ambiguous portion, next to the message including the ambiguous portion).

[0135] In operation 590, according to one embodiment, the electronic device may display a second message. For example, the electronic device may convert a received message containing an ambiguous portion into a second message and display the second message on the first screen. For example, the electronic device may display the second message in a display area where the received message containing an ambiguous portion is displayed. For example, the electronic device may display the second message generated based on a user input regarding the ambiguous portion. For example, the electronic device may display the second message based on a user input regarding the display area where the message containing the ambiguous portion is displayed. For example, the electronic device may display the second message based on a user input regarding a notification indicating that a second message has been generated.

[0136] The order of the operations described above with respect to FIG. 5 is merely an example and embodiments of the present disclosure are not limited thereto. For example, at least some of the operations may be executed differently from the order of FIG. 5 or may be executed substantially simultaneously with other operations of FIG. 5. At least some of the operations described above with respect to FIG. 5 may be omitted.

[0137]

[0138] FIGS. 6a and 6b are drawings illustrating examples of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0139] According to one embodiment, an electronic device (e.g., electronic device 110 of FIG. 1) may receive a first message (611). For example, the electronic device may receive the first message (611) from an external electronic device through a messenger application. The first screen (610) may include the first message (611) and messages exchanged with the external electronic device prior to the first message. According to one embodiment, the electronic device may identify at least one ambiguous part in the first message (611). For example, the ambiguous part may include an abstract part or a part whose reference is unclear. For example, the ambiguous part may include a pronoun. For example, the ambiguous part may include an abbreviated word (or sentence). For example, the ambiguous part may include a part whose meaning is unclear without other additional information. For example, the ambiguous part may include at least one word.

[0140] For example, the electronic device may receive a first message (611) such as “Let’s meet then at the place we mentioned last time!”. In the first message (611), the electronic device may identify multiple ambiguous parts such as “the place we mentioned last time” and / or “then”.

[0141] According to one embodiment, the electronic device can determine whether it is possible to provide additional information corresponding to at least one ambiguous part. For example, the electronic device can search for additional information corresponding to at least one ambiguous part by using an AI model learned based on context information. For example, the context information may include at least one of information on messages previously received through an application related to the first message (611), information related to multimedia stored in the electronic device, information stored on an external server related to another application, or information stored on another electronic device registered with the same account as the electronic device.

[0142] According to one embodiment, the electronic device may display an indication (621) that additional information may be provided together with the first message (611). For example, the electronic device may display an indication (621) that converts the first message (611) into a second message (631) containing the additional information. For example, the electronic device may display a second screen (620) including the first message (611) and the indication (621).

[0143] In one embodiment, the electronic device may generate a second message (631) that includes at least a portion of the first message (611) and the additional information. For example, the electronic device may generate the second message (631) by replacing at least one ambiguous portion of the first message (611) with the additional information.

[0144] According to one embodiment, the electronic device may display a second message (631) based on user input (e.g., touch input) for an indication (621). For example, the electronic device may display the second message (631) by converting a first message (611) into a second message (631) based on user input for the indication (621).

[0145] For example, if the additional information corresponding to “at the place we talked about last time” is “at Gangnam Station” and the additional information corresponding to “at that time” is “at 6 PM next Wednesday,” the electronic device can convert “let’s meet at the place we talked about last time” to “let’s meet at 6 PM next Wednesday at Gangnam Station” and display the converted second message (631). For example, the electronic device can display a third screen (630) including the second message (631).

[0146] According to one embodiment, the electronic device may receive a user input (e.g., pinch out (pinch to zoom in) or pinch in (pinch to zoom out)) that changes the size of the display area in which the first message (611) is displayed. For example, the electronic device may receive a user input (e.g., pinch out (zoom in)) for enlarging the size of the display area on which the first message (611) is displayed on the second screen (620). For example, the electronic device may enlarge the size of the display area on which the first message (611) is displayed from the first size (622) to the second size (642) based on the user input. According to one embodiment, the electronic device may increase the size of data of additional information corresponding to at least one ambiguous portion based on the user input for enlarging the size of the display area of ​​the first message (611). For example, when the size of the display area of ​​the first message (611) is changed to the second size (642), the electronic device may determine the size of data of additional information corresponding to the second size (642).

[0147] According to one embodiment, when the electronic device determines the size of data of additional information corresponding to the second size (642), it can generate a second message (651) including additional information corresponding to the display area of ​​the second size (642). The electronic device can provide information (641) indicating that it is generating the second message (651) corresponding to the size of the transformed display area. For example, the electronic device can provide a notification message, a visual effect, and / or an affordance indicating that it is generating the second message (651) including additional information corresponding to the display area of ​​the second size (642). For example, when the electronic device is generating the second message (651) including additional information corresponding to the display area of ​​the second size (642), it can display a notification message such as “Generating message...” on the display area enlarged to the second size (642). For example, the fourth screen (640) can be a screen provided while the electronic device is generating the second message (651) including additional information corresponding to the display area of ​​the second size (642). According to one embodiment, the electronic device may display a second message (651) including at least a portion of the first message (611) and additional information corresponding to a display area of ​​the second size (642). For example, if the electronic device completes the second message (651) while providing information (641) indicating that the second message (651) is being generated, the electronic device may display the generated second message (651) in the display area of ​​the second size (642). For example, the additional information corresponding to the display area of ​​the second size (642) of “the place I mentioned last time” may be “at Exit 12 of Gangnam Station,” and the additional information corresponding to the display area of ​​the second size (642) of “at that time” may be “at 6:00 PM on April 22, 2024.” For example, the electronic device may display a fifth screen (650) including the second message (651).

[0148]

[0149] FIG. 7 is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0150] FIG. 7 differs from FIG. 6 in that it displays a second message (721) in which at least one ambiguous portion selected by a user from among the ambiguous portions identified in the first message (711) is replaced with additional information. In one embodiment, an electronic device may receive the first message (711) (e.g., "Let's meet then at the place we talked about last time!"). The electronic device may identify a plurality of ambiguous portions (e.g., "at the place we talked about last time," "then") in the first message (711). The electronic device may receive a user input selecting a first ambiguous portion (712) (e.g., "at the place we talked about last time") from among the plurality of ambiguous portions. For example, the electronic device may receive a touch input and / or a gesture input (e.g., a touch gesture including a tap, a double tap, a press, a flick, a swipe, a pan, a drag, and / or a pinch zoom) to select a first ambiguous portion (712) from among the first message (711). In one embodiment, the electronic device may search for additional information (722) corresponding to the selected first ambiguous portion (712) (e.g., “at Gangnam Station Exit 12”). In one embodiment, the electronic device may display a user interface (713) indicating that the search is in progress while searching for additional information corresponding to the ambiguous portion. The electronic device may generate a second message (721) that includes the additional information (722) corresponding to the first ambiguous portion (712). For example, the electronic device may generate the second message (721) by replacing the first ambiguous portion (712) from among the first message (711) with the additional information (722).

[0151]

[0152] FIG. 8 is a diagram illustrating an example of an electronic device generating a message according to an embodiment of the present disclosure. Below, any description overlapping with that of FIG. 1 will be omitted or briefly described.

[0153] FIG. 8 differs from FIG. 6 in that the electronic device (110) displays the first message (811) in the form of a pop-up. According to one embodiment, the electronic device (110) can receive the first message (811). The electronic device (110) can display the received first message (811) in the form of a pop-up in a part area of ​​the display (e.g., the display (112) of FIG. 1). The electronic device (110) can identify at least one ambiguous part in the received first message (811). The electronic device (110) can display an indication (812) indicating that additional information corresponding to at least one ambiguous part may be provided.

[0154] According to one embodiment, the electronic device (110) can obtain user inputs (821, 831) related to the indication (812) based on the indication of the indication (812). For example, the electronic device (110) can obtain touch input (821) for the indication (812). For example, the electronic device (110) can obtain swipe input (831) for swiping a display area of ​​the first message (811) based on the indication of the indication (812).

[0155] According to one embodiment, the electronic device (110) may display a second message (841) based on user input (e.g., touch input (821) and / or swipe input (831)) associated with the indication (812). For example, the electronic device (110) may generate a second message (841) in which at least one ambiguous part of the first message (811) is replaced with additional information corresponding to at least one ambiguous part. The electronic device (110) may display the second message (841) in a display area where the first message (811) is displayed.

[0156]

[0157] FIG. 9 is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0158] FIG. 9 differs from FIG. 8 in that it displays a second message (921) in which a user-selected ambiguous part among at least one ambiguous part identified in the first message (911) is replaced with additional information. According to one embodiment, an electronic device may receive a first message (911) (e.g., "Let's meet then at the place we mentioned last time!"). The electronic device may display the received first message (911) in the form of a popup. The electronic device may identify a plurality of ambiguous parts (e.g., "at the place we mentioned last time," "then") in the first message (911). The electronic device may receive user input selecting a first ambiguous part (912) (e.g., "at the place we mentioned last time") among the plurality of ambiguous parts. For example, the electronic device may receive a gesture input (e.g., a touch gesture) selecting the first ambiguous part (912) in the first message (911). According to one embodiment, the electronic device may search for additional information (922) (e.g., "at Gangnam Station Exit 12") corresponding to a selected first ambiguous part (912). According to one embodiment, the electronic device may display a user interface (913) indicating that it is searching while searching for additional information corresponding to the ambiguous part. The electronic device may generate a second message (921) containing additional information (922) corresponding to the first ambiguous part (912). For example, the electronic device may generate a second message (921) in which the first ambiguous part (912) in the first message (911) is replaced with additional information (922).

[0159]

[0160] FIG. 10 is a diagram illustrating an example of a message generated by an electronic device according to an embodiment of the present disclosure. In the following, any description that overlaps with the description of FIG. 1 will be omitted or briefly described.

[0161] According to one embodiment, an electronic device (e.g., the electronic device (110) of FIG. 1) may receive a first message (1011) (e.g., "Did you buy what Mom told you to buy when you came home?") from a first external electronic device (e.g., a younger sibling's user terminal). The electronic device may identify an ambiguous part (e.g., "thing") in the first message (1011).

[0162] According to one embodiment, the electronic device can determine whether additional information corresponding to the ambiguous part can be provided by using an AI model learned based on context information. For example, the context information may include information about a message received prior to receiving the first message (1011). For example, the context information may include the first message (1011) as a message received from a second external electronic device (e.g., a mother's user terminal). According to one embodiment, the electronic device can determine that additional information can be provided if there is information related to the ambiguous part in the context information. For example, the electronic device can determine that additional information can be provided if there is information related to the ambiguous part in messages exchanged with the second external electronic device (e.g., the second message (1021), the third message (1022)). For example, the electronic device may determine from the second message (1021) (e.g., "Buy green onions and eggs at the supermarket when you come home") and the third message (1022) (e.g., "Yes, I understand~") that additional information (e.g., "green onions and eggs") corresponding to the ambiguous part (e.g., "thing") can be provided.

[0163] According to one embodiment, the electronic device may display an indication (1031) indicating that additional information can be provided, based on a judgment that additional information corresponding to an ambiguous part can be provided. Based on user input regarding the indication (1031), the electronic device may display a fourth message (1041) including a part of the first message (1011) and additional information. For example, the electronic device may display a fourth message (1041) in which an ambiguous part (e.g., "thing") in the first message (1011) is replaced with additional information (e.g., "green onion and egg").

[0164]

[0165] FIG. 11 is a diagram illustrating an example of a message generated by an electronic device according to an embodiment of the present disclosure. In the following, any description that overlaps with the description of FIG. 1 will be omitted or briefly described.

[0166] In one embodiment, an electronic device (e.g., electronic device (110) of FIG. 1) may receive a first message (1111) (e.g., "You didn't forget our anniversary, did you? Come out soon!"). The electronic device may identify an ambiguous portion (e.g., "Our anniversary") in the first message (1111).

[0167] According to one embodiment, the electronic device can determine whether additional information corresponding to the ambiguous part can be provided by using an AI model learned based on context information. For example, the context information may include information related to a user's schedule stored in the electronic device. According to one embodiment, the electronic device may determine that additional information can be provided if there is information related to the ambiguous part in the context information. For example, the electronic device may determine that additional information can be provided if there is information related to the ambiguous part in the information related to the user's schedule. For example, the electronic device may determine that additional information (e.g., "June 16 at 2 PM in Itaewon") corresponding to the ambiguous part (e.g., "Our Anniversary") can be provided based on context information including the user's schedule information (1121) recorded in a calendar application.

[0168] According to one embodiment, the electronic device may display an indication (1131) indicating that additional information can be provided based on a judgment that additional information corresponding to an ambiguous part can be provided. Based on user input regarding the indication (1131), the electronic device may display a second message (1141) including a part of the first message (1111) and additional information. For example, the electronic device may display a second message (1141) in which an ambiguous part (e.g., "our anniversary") of the first message (1111) is replaced with additional information (e.g., "June 16 at 2 PM in Itaewon").

[0169]

[0170] FIG. 12 is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0171] According to one embodiment, an electronic device (e.g., the electronic device (110) of FIG. 1) may receive a first message (1211) (e.g., "The clothes you wore when we took our group photo last time were so pretty, please wear them to the next meeting too!"). The electronic device may identify an ambiguous part (e.g., "the clothes you wore when we took our group photo last time") in the first message (1211). Based on context information, the electronic device may determine whether additional information corresponding to the ambiguous part can be provided. For example, the electronic device may determine if there is information related to the ambiguous part in the context information. For example, the context information may include image information stored in the electronic device. For example, if the first message (1211) is related to a photo, the electronic device may determine if there is information related to the ambiguous part (e.g., "the clothes you wore when we took our group photo last time") in the image information stored in the electronic device.

[0172] According to one embodiment, if the electronic device contains image information (1222) related to the ambiguous part in the image information stored in the electronic device, the electronic device may display an indication (1212) indicating that additional information corresponding to the ambiguous part can be provided. For example, if the ambiguous part is "the clothes I wore when we took our group photo last time," the image information (1222) may include the group photo taken last time.

[0173] According to one embodiment, the electronic device may display a second message (1221) containing additional information based on user input for an indication (1212). For example, the electronic device may display a second message (1221) that is added as additional information (e.g., image information (1222)) to the first message (1211).

[0174]

[0175] FIG. 13a is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0176] According to one embodiment, an electronic device (1300) (e.g., the electronic device (110) of FIG. 1) may receive a first message (1311) (e.g., "Let's meet at the place we talked about last time then!"). The electronic device (1300) may identify a plurality of ambiguous parts (e.g., "the place we talked about last time", "then") in the first message (1311).

[0177] According to one embodiment, the electronic device (1300) can display a fourth message (1321) containing additional information corresponding to a plurality of ambiguous parts based on context information. For example, the electronic device (1300) may display a fourth message (1321) comprising a second message (1322) containing some of the first message (1311) and additional information, and a third message (1323) containing information used to provide additional information. For example, the electronic device (1300) may generate a second message (1322) in which a plurality of ambiguous parts of the first message (1311) (e.g., "the place mentioned last time," "then") are replaced with additional information (e.g., "at Gangnam Station," "next Wednesday at 6 p.m."). For example, the electronic device (1300) may generate a third message (1323) containing information used to provide additional information (e.g., "at Gangnam Station," "next Wednesday at 6 p.m.") (e.g., information from a message received prior to receiving the first message (1311)). For example, the electronic device (1300) may second A fourth message (1321) including message (1322) and third message (1323) can be displayed in the display area where the first message (1311) is displayed.

[0178] According to one embodiment, the electronic device (1300) may display a first screen including a first message (1311) in a first area (1301) (e.g., a left area) of a display (e.g., a display (112) of FIG. 1) and may display a second screen including a fourth message (1321) in a second area (1302) (e.g., a right area). For example, the first screen may correspond to an execution screen of a messenger application related to the first message (1311). For example, the second screen may include a second message (1322) in which ambiguous parts of the first message (1311) are replaced with additional information, and a third message (1323) including information used to provide the additional information.

[0179]

[0180] FIG. 13b is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 13b are omitted or briefly described.

[0181] According to one embodiment, an electronic device (1305) (e.g., the electronic device (110) of FIG. 1) may receive a first message (1331) (e.g., "Let's meet at the place we talked about last time then!"). The electronic device (1305) may identify a plurality of ambiguous parts (e.g., "the place we talked about last time", "then") in the first message (1331).

[0182] In one embodiment, the electronic device (1305) may display a fourth message (1341) that includes additional information corresponding to a plurality of ambiguous portions based on context information. For example, the electronic device (1305) may display a fourth message (1341) that includes a portion of the first message (1331) and a second message (1342) that includes additional information, and a third message (1343) that includes information used to provide the additional information.

[0183] According to one embodiment, the electronic device (1305) may display a first screen containing a first message (1311) in a first area (1306) (e.g., top area) of an area of ​​a display (e.g., display (112) of FIG. 1), and display a second screen containing a fourth message (1341) in a second area (1307) (e.g., bottom area).

[0184]

[0185] FIG. 14a is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0186] According to one embodiment, an electronic device (1400) (e.g., the electronic device (110) of FIG. 1) may receive a first message (1411). The electronic device (1400) may display the received first message (1411) through an auxiliary display (1401) (e.g., the display (112) of FIG. 1). The electronic device (1400) may identify at least one ambiguous part in the first message (1411). For example, the electronic device (1400) may identify at least one ambiguous part in the first message (1411) based on user input regarding the first message (1411). The electronic device (1400) may determine, based on context information, whether additional information corresponding to at least one ambiguous part can be provided. The electronic device (1400) may display an indication (1412) on an auxiliary display (1401) indicating that additional information can be provided, based on a judgment that additional information corresponding to at least one ambiguous part can be provided. The electronic device (1400) may convert a first message (1411) into a second message (1421) containing additional information based on user input regarding the indication (1412), and display the second message (1421).

[0187]

[0188] FIG. 14b is a diagram illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0189] According to one embodiment, an electronic device (1405) (e.g., the electronic device (110) of FIG. 1) may receive a first message (1431). For example, the electronic device (1405) may include a wearable device. The electronic device (1405) may display the received first message (1431) through a display (1406) (e.g., the display (112) of FIG. 1). The electronic device (1405) may identify at least one ambiguous part in the first message (1431). For example, the electronic device (1405) may identify at least one ambiguous part based on user input regarding the first message (1431). The electronic device (1405) may determine whether additional information corresponding to at least one ambiguous part can be provided based on context information. The electronic device (1405) may display an indication (1432) on the display (1406) indicating that provision of additional information is possible based on a determination that provision of additional information corresponding to at least one ambiguous portion is possible.

[0190] According to one embodiment, the electronic device (1405) can obtain a user input based on the display of the indication (1432). For example, the electronic device (1405) can obtain a touch input and / or a gesture input for the indication (1422). For example, the electronic device (1405) can receive a physical input for the first part (1407) of the housing of the electronic device (1405). According to one embodiment, the electronic device (1405) can convert the first message (1431) into a second message (1441) including additional information based on the user input and display the second message (1441).

[0191]

[0192] FIG. 14c is a drawing illustrating an example of an electronic device generating a message according to one embodiment of the present disclosure. In the following, descriptions that overlap with the description of FIG. 1 are omitted or briefly described.

[0193] FIG. 14c differs from FIG. 14b in that the electronic device (1405) displays the first message (1451) in the form of a pop-up. According to one embodiment, the electronic device (1405) may receive the first message (1451). The electronic device (1405) may display the received first message (1451) in the form of a pop-up in a portion of the display (1406) (e.g., the display (112) of FIG. 1). The electronic device (1405) may identify at least one ambiguous part in the received first message (1451). The electronic device (1405) may display an indication (1452) indicating that additional information corresponding to at least one ambiguous part may be provided.

[0194] According to one embodiment, the electronic device (1405) may obtain user input related to the indication (1452) based on the display of the indication (1452). For example, the electronic device (1405) may obtain touch input and / or gesture input for the indication (1452). For example, the electronic device (1405) may receive physical input for a first part (1407) of the housing of the electronic device (1405). According to one embodiment, the electronic device (1405) may display the second message (1461) by converting the first message (1451) into a second message (1461) containing additional information based on the user input.

[0195]

[0196] According to this embodiment, the electronic device provides additional information corresponding to ambiguous portions of the message, eliminating the need for the user to perform separate actions to retrieve the additional information. Therefore, while searching for additional information can be difficult when the display size of the electronic device is small, the user can obtain the additional information without performing separate actions to retrieve the additional information.

[0197]

[0198] FIG. 15A is a diagram illustrating an example of an electronic device generating a message according to an embodiment of the present disclosure. FIG. 15B is a diagram illustrating an example of an electronic device generating a message according to an embodiment of the present disclosure. In the following, any description that overlaps with the description of FIG. 1 will be omitted or briefly described.

[0199] According to one embodiment, an electronic device (1500) (e.g., electronic device (110) of FIG. 1) may receive a first message (1511). For example, the electronic device (1500) may include at least one of a head-mounted display, a virtual reality headset, an augmented reality glasses device in the form of glasses worn on the face, or an augmented reality helmet that provides content for virtual reality, augmented reality, mixed reality, or extended reality. According to one embodiment, the electronic device (1500) may display a first screen (1510) including the received first message through a display (1501). The electronic device (1500) may identify at least one ambiguous part in the first message (1511). For example, the electronic device (1500) may identify at least the ambiguous part based on a user input (e.g., a touch input, a gesture input, a gaze input) for the first message (1511) displayed on the display (1501). The electronic device (1500) may determine, based on context information, whether or not additional information corresponding to at least one ambiguous portion can be provided. Based on the determination that the provision of additional information corresponding to at least one ambiguous portion is possible, the electronic device (1500) may display an indication (1512) indicating that the provision of additional information is possible on the first screen (1510) together with the first message (1511). Based on a user input for the indication (1512), the electronic device (1500) may generate a second message (1521) including additional information (e.g., image information). The electronic device (1500) may display the second screen (1520) including the second message (1521) through the display (1501).

[0200] According to one embodiment, the electronic device (1500) may display a screen containing information related to the source of additional information. For example, if the additional information is image information stored in the electronic device (1500), the electronic device (1500) may display a third screen (1530) that executes a gallery application containing said image information. For example, the third screen (1530) may include a plurality of image information containing additional information. The electronic device (1500) may extract additional information (e.g., image information) corresponding to an ambiguous part among the plurality of images included in the third screen (1530).

[0201] According to one embodiment, the electronic device (1500) may display a first screen (1510) and, upon receiving user input for an indication (1512), display a second screen and / or a third screen. However, it is not limited thereto. For example, user input for an indication (1512) may include a user gesture input detected using at least one sensor included in the electronic device (1500) (e.g., a camera (e.g., an image sensor, an RGB sensor, an IR sensor, but not limited thereto) (e.g., the sensor (1670) of FIG. 16), a user key (button) input, touch input, gesture input, swipe input, scroll input, and / or pinch-to-zoom (zoom in / zoom out) input received through an input device (e.g., a controller) included in or connected to the electronic device (1500), and is not limited to the types of inputs listed above. For example, the electronic device (1500) may list the first screen (1510), the second screen (1520), and the third screen (1530) and display them simultaneously through the display (1501). For example, the electronic device (1500) may omit any one of the first screen (1510), the second screen (1520), and the third screen (1530), or list the order of each screen differently.

[0202]

[0203] According to one embodiment of the present disclosure, an electronic device (110, 1600, 1700) may include a display (112, 1640, 1701), a communication circuit (111, 1660), a memory (113, 1620) for storing instructions, and at least one processor (114, 1610).

[0204] According to one embodiment of the present disclosure, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive a first message from an external electronic device.

[0205] According to one embodiment of the present disclosure, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify at least one ambiguous portion in the first message.

[0206] According to one embodiment of the present disclosure, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to determine whether additional information corresponding to the at least one ambiguous portion can be provided using an artificial intelligence (AI) model learned based on context information.

[0207] According to one embodiment of the present disclosure, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display an indication on the display together with the first message, indicating that provision of the additional information is possible, based on a determination that provision of the additional information is possible.

[0208] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive user input for an indication that provision of the additional information is possible.

[0209] According to one embodiment of the present disclosure, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate, based on the user input, a second message including at least a portion of the first message and the additional information.

[0210] According to one embodiment of the present disclosure, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display the generated second message on the display.

[0211] According to one embodiment of the present disclosure, the second message may include information used to provide the additional information among the context information.

[0212] According to one embodiment of the present disclosure, the identified at least one ambiguous part may include a first ambiguous part and a second ambiguous part.

[0213] According to one embodiment of the present disclosure, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive a user input selecting the first ambiguous portion.

[0214] According to one embodiment of the present disclosure, when the instructions are executed individually or collectively by the at least one processor, the electronic device may generate a second message including at least a portion of the first message and first additional information corresponding to the first ambiguous portion of the additional information, based on the user input.

[0215] According to one embodiment of the present disclosure, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display the generated second message on the display.

[0216] According to one embodiment of the present disclosure, the user input may include an input that adjusts the size of the display area where the second message is displayed.

[0217] According to one embodiment of the present disclosure, the size of the data of the additional information may be determined based on the size of the display area.

[0218] According to one embodiment of the present disclosure, the second message may be a message in which the at least one ambiguous part is replaced with the additional information.

[0219] According to one embodiment of the present disclosure, the second message may include at least one ambiguous part.

[0220] According to one embodiment of the present disclosure, if the at least one ambiguous part is related to a photograph, the additional information may include image information.

[0221] According to one embodiment of the present disclosure, the second message may include the image information.

[0222] According to one embodiment of the present disclosure, the context information may include at least one of information on messages previously received through an application associated with the first message, information related to multimedia stored in the memory, information stored on an external server associated with another application, or information stored on another electronic device registered with the same account as the electronic device.

[0223] According to one embodiment of the present disclosure, an indication indicating that the additional information can be provided may include at least one of an affordance that converts the first message into a second message containing the additional information, a visual effect that modifies the features of the text included in the at least one ambiguous part, or a visual effect that modifies the features of the display area where the first message is displayed.

[0224] According to one embodiment of the present disclosure, the display may include a first display and a second display.

[0225] According to one embodiment of the present disclosure, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be able to display the first message on the first display.

[0226] According to one embodiment of the present disclosure, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be able to display the second message on the second display.

[0227] According to one embodiment of the present disclosure, a method of generating text in an electronic device may include receiving a first message from an external electronic device.

[0228] A method for generating text of an electronic device according to one embodiment of the present disclosure may include an operation of identifying at least one ambiguous part in the first message.

[0229] A method for generating text of an electronic device according to one embodiment of the present disclosure may include an operation of determining whether additional information corresponding to at least one ambiguous part can be provided using an AI model learned based on context information.

[0230] A method for generating text of an electronic device according to one embodiment of the present disclosure may include an operation of displaying an indication that the additional information can be provided together with the first message, based on a determination that the additional information can be provided.

[0231] A method for generating text of an electronic device according to one embodiment of the present disclosure may include receiving user input for an indication that the additional information may be provided.

[0232] A method for generating text of an electronic device according to one embodiment of the present disclosure may include generating a second message comprising at least a portion of the first message and the additional information based on the user input.

[0233] A method for generating text of an electronic device according to one embodiment of the present disclosure may include an operation of displaying the generated second message.

[0234] In a method for generating text of an electronic device according to one embodiment of the present disclosure, the second message may include information used to provide additional information among the context information.

[0235] In a method for generating text of an electronic device according to one embodiment of the present disclosure, the identified at least one ambiguous part may include a first ambiguous part and a second ambiguous part.

[0236] A method for generating text of an electronic device according to one embodiment of the present disclosure may include receiving user input selecting the first ambiguous part.

[0237] A method for generating text of an electronic device according to one embodiment of the present disclosure may include, based on the user input, generating a second message comprising at least a portion of the first message and first additional information corresponding to the first ambiguous portion of the additional information.

[0238] A method for generating text of an electronic device according to one embodiment of the present disclosure may include an operation of displaying the generated second message.

[0239] In a method for generating text of an electronic device according to one embodiment of the present disclosure, the user input may include an input that adjusts the size of a display area in which the second message is displayed.

[0240] In a method for generating text of an electronic device according to one embodiment of the present disclosure, the size of the data of the additional information may be determined based on the size of the display area.

[0241] In a method for generating text of an electronic device according to one embodiment of the present disclosure, the second message may be a message in which the at least one ambiguous part is replaced with the additional information.

[0242] In a method for generating text of an electronic device according to one embodiment of the present disclosure, the second message may include the at least one ambiguous part.

[0243] In a method for generating text of an electronic device according to one embodiment of the present disclosure, if the at least one ambiguous part is related to a photograph, the additional information may include image information.

[0244] In a method for generating text of an electronic device according to one embodiment of the present disclosure, the second message may include the image information.

[0245] According to one embodiment of the present disclosure, in a computer-readable storage medium for storing instructions, the instructions may enable the electronic device to receive a first message from an external electronic device when executed by at least one processor of the electronic device.

[0246] According to one embodiment of the present disclosure, in a computer-readable storage medium for storing instructions, the instructions can be executed by at least one processor of an electronic device, so that the electronic device can identify at least one ambiguous part in the first message.

[0247] In a computer-readable storage medium for storing instructions according to one embodiment of the present disclosure, when the instructions are executed by at least one processor of an electronic device, the electronic device may determine whether additional information corresponding to the at least one ambiguous part can be provided using an AI model learned based on context information.

[0248] In a computer-readable storage medium for storing instructions according to one embodiment of the present disclosure, the instructions may be executed by at least one processor of an electronic device, and the electronic device may display an indication indicating that the additional information can be provided together with the first message based on a judgment that the additional information can be provided.

[0249]

[0250] According to one embodiment of the present disclosure, when there is an abstract or difficult-to-understand context in a message received through an electronic device, the user may not need to go through a separate search process to find out what that abstract or difficult-to-understand context is. For example, the user does not need to go through a process of searching through previously conversed content or searching through separate personal data, such as a notepad or gallery, to find out what the ambiguous part of the received message represents.

[0251] According to one embodiment of the present disclosure, an electronic device can provide a user with an effective user experience in which the user's personal data interacts in a user-friendly manner by naturally synthesizing generated text into a message sentence with an interaction such as dragging.

[0252] According to one embodiment of the present disclosure, the user can check specific and personalized data regarding conversation information with a minimal interface, thereby enabling efficient and convenient operation. In addition, by activating the function of the present invention using a separate physical button on an electronic device (e.g., a smart watch), the user can conveniently use the function of the present invention even during active moments.

[0253]

[0254] FIG. 16 is a block diagram of an exemplary electronic device capable of performing the operations described in this document.

[0255] Referring to FIG. 16, the electronic device (1600) may be one of various forms of electronic devices, such as a notebook (1690), smartphones (1691) having various form factors (e.g., a bar-type smartphone (1691-1), a foldable-type smartphone (1691-2), or a sliderable (or rollable) type smartphone (1691-3)), a tablet (1692), a cellular phone (not shown), and other similar computing devices (not shown). The components, their relationships, and their functions illustrated in FIG. 16 are exemplary only and do not limit the implementations described or claimed in this document. The electronic device (1600) may be referred to as a mobile device, a user device, a multi-function device, a portable device, or a server.

[0256] The electronic device (1600) may include components including at least one processor (1610) (hereinafter referred to as processor (1610)), at least one memory (1620) (hereinafter referred to as memory (1620)), at least one display (1640) (hereinafter referred to as display (1640)), at least one image sensor (1650) (hereinafter referred to as image sensor (1650)), at least one communication circuit (1660) (hereinafter referred to as communication circuit (1660)), and / or at least one sensor (1670) (hereinafter referred to as sensor (1670)). The above components are merely exemplary. For example, the electronic device (1600) may include other components (e.g., power management integrated circuitry (PMIC), audio processing circuitry, an antenna, a rechargeable battery, or an input / output interface). For example, some components may be omitted from the electronic device (1600). For example, some components can be integrated into a single component.

[0257] The processor (1610) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing operations. The processor (1610) may include at least one electrical circuit and may process instructions (or programs, data) stored in memory (1620) individually or collectively in a distributed manner. The processor (1610) may include a processor assembly comprising one or more processing circuits. The processor (1610) may include any processing circuit that is operative to control the performance and operations of one or more components of the electronic device (1600) (e.g., memory (1620), display (1640), image sensor (1650), communication circuit (1660), and / or sensor (1670)). For example, a processor (1610) (e.g., an application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or a chipset). For example, the processor (1610) may be implemented as a plurality of cores (or at least one core circuit), a plurality of chips, or a plurality of chipsets. For example, the processor (1610) may include one or more processing circuits. For example, the processor (1610) may include one or more processing circuits configured to perform the various functions of the present disclosure individually and / or collectively. As an example without limitation, at least a portion of the processor (1610) may be included in a first chip of the electronic device (1600), and at least another portion of the processor (1610) may be included in a second chip of the electronic device (1600) different from the first chip of the electronic device (1600).

[0258] For example, the processor (1610) may include a central processing unit (CPU) (1611), a graphics processing unit (GPU) (1612), a neural processing unit (NPU) (1613), an image signal processor (ISP) (1614), a display controller (1615), a memory controller (1616), a storage controller (1617), a communication processor (CP) (1618), and / or a sensor interface (1619). These components of the processor (1610) are merely exemplary. For example, the processor (1610) may further include other components. For example, some components of the processor (1610) may be omitted from the processor (1610). For example, some components of the processor (1610) may be included as separate components of the electronic device (1600) outside the processor (1610). For example, some components of the processor (1610) (e.g., memory controller (1616)) may be included in other components (e.g., at least part of memory (1620), an interface (e.g. available for connection to at least one component of the electronic device (100)), a display (1640) and / or an image sensor (1650)).

[0259] The processor (1610) may cause other components of the electronic device (1600) to perform various operations by executing instructions stored in the memory (1620). The CPU (1611) (or central processing circuit) may be configured to control components of the processor (1610) based on the execution of instructions stored in the memory (1620) (e.g., volatile memory (1621) and / or non-volatile memory (1622)). The GPU (1612) (or graphics processing circuit) may be configured to execute parallel operations (e.g., rendering). The NPU (1613) (or neural processing circuit, or artificial intelligence (AI) chip) may be configured to execute operations for an artificial intelligence model (e.g., convolution computation). The ISP (1614) (or image signal processing circuit) may be configured to process a raw image acquired through the image sensor (1650) into a format suitable for a component within the electronic device (1600) or a component of the processor (1610). The display controller (1615) (or display control circuit, or display processing unit (DPU)) may be configured to process an image acquired from the CPU (1611), the GPU (1612), the ISP (1614), or the memory (1620) (e.g., the volatile memory (1621)) into a format suitable for the display (1640). The memory controller (1616) (or memory control circuit) may be configured to control reading data from the volatile memory (1621) and writing data to the volatile memory (1621). The storage controller (1617) (or storage control circuit) may be configured to control reading data from non-volatile memory (1622) and writing data to non-volatile memory (1622).The CP (1618) (communication processing circuit) may be configured to process data obtained from a component of the processor (1610) into a format suitable for transmission to another electronic device via the communication circuit (1660), or to process data obtained from another electronic device via the communication circuit (1660) into a format suitable for processing by the component of the processor (1610). For example, the communication circuit (1660) may include one or more communication circuits. The sensor interface (1619) (or sensing data processing circuit, sensor hub) may be configured to process data on the state of the electronic device (1600) and / or the state of the surroundings of the electronic device (1600), obtained via the sensor (1670), into a format suitable for the component of the processor (1610).

[0260] Memory (1620) may include one or more storage media (or one or more storage devices). For example, memory (1620) may include a memory assembly comprising one or more storage media. For example, the one or more storage media may include a hard drive, a flash memory, a permanent memory such as ROM (read-only memory) (e.g., non-volatile memory (1622)), a semi-permanent memory such as RAM (random access memory) (e.g., volatile memory (1621)), any other suitable type of storage (or storage assembly), or any combination thereof. Memory (1620) may include a cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (1600). As an example not limited to, the cache memory may be included within the processor (1610). The memory (1620) may be fixedly embedded within the electronic device (1600) or incorporated into one or more suitable types of components (e.g., a SIM (subscriber identity module) card and / or an SD (secure digital) card) that can be repeatedly inserted into and removed from the electronic device (1600).

[0261] For example, the memory (1620) may store one or more software applications, such as an operating system (or system) software application, a firmware software application, a driver software application, a plug-in (e.g., add-in, add-on, and / or applet) software application, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (1610). For example, the memory (1620) may store instructions callable by an application programming interface (API). For example, the memory (1620) may store instructions within a library.

[0262]

[0263] FIG. 17a is a drawing illustrating an unfolded state of a foldable electronic device according to one embodiment.

[0264] FIG. 17b is a drawing showing the rear of a foldable electronic device in an unfolded state according to one embodiment.

[0265] Referring to FIGS. 17a and 17b, according to one embodiment, a foldable electronic device (1700) (e.g., the electronic device (110) of FIG. 1) may include a first housing (1710), a second housing (1720), and a third housing (1730). For example, the first housing (1710) and the second housing (1720) may be coupled through a first hinge portion (1740), and the second housing (1720) and the third housing (1730) may be coupled through a second hinge portion (1750). A plurality of housings including a first housing (1710), a second housing (1720), and a third housing (1730) are not bent when the foldable electronic device (1700) is folded, and a plurality of hinge portions including a first hinge portion (1740) and a second hinge portion (1750) can be bent when the foldable electronic device (1700) is folded. The plurality of hinge portions may include separate hinge structures (not shown) for bending inside. For example, the hinge structure may include a bending axis extending long in the y-axis direction inside and a connecting member extending from the bending axis to connect the first housing (1710) and the second housing (1720). Through this, the plurality of housings can be folded and unfolded.

[0266] According to one embodiment, the unfolded state can be defined as a state in which the plurality of housings and the plurality of hinge portions of the foldable electronic device (1700) form substantially the same plane.

[0267] A foldable electronic device (1700) may include a flexible display (1701). The flexible display (1701) may be formed as a curved or flat surface so that at least some area can be bent. For example, the bendable portion of the flexible display (1701) may be bent in the same direction as the bending direction of a plurality of hinge portions when the foldable electronic device (1700) is folded. Thus, the flexible display (1701) can maintain a continuous shape regardless of whether the foldable electronic device (1700) is folded. According to one embodiment, the flexible display (1701) may be visible through the front surfaces (1711, 1811, 1911) of a plurality of housings including a first housing (1710), a second housing (1720), and a third housing (1730).

[0268] The above front surface (1711, 1811, 1911) may be positioned above the area where the flexible display (1701) is visible (e.g., above the +z-axis direction) and may constitute part of the exterior of the foldable electronic device (1700). According to one embodiment, the above front surface (1711, 1811, 1911) may be a plate in which at least a portion is substantially transparent (e.g., a glass plate including various coating layers, or a polymer plate).

[0269] According to one embodiment, the rear surface (1712, 1812, 1912) of the plurality of housings may be defined as the opposite side facing the front surface (1711, 1811, 1911) of the plurality of housings. For example, the rear surface (1712, 1812, 1912) may face in a direction opposite to the direction in which the flexible display (1701) is viewed. The rear surface (1712, 1812, 1912) may be a substantially opaque plate. For example, the opaque plate may be formed of coated or colored glass, ceramic, polymer metal (e.g., aluminum, stainless steel (STS), or magnesium), fabric, leather, or a combination of at least two of the materials.

[0270] According to one embodiment, the sides (1713, 1813, 1913) of a plurality of housings may surround at least a portion of the space between the front (1711, 1811, 1911) and the rear (1712, 1812, 1912). For example, the sides (1713, 1813, 1913) may be a side bezel structure connecting the front (1711, 1811, 1911) and the rear (1712, 1812, 1912). The side bezel structure may comprise a metal and / or a polymer.

[0271] For example, a plurality of housings may be formed from a plurality of materials. For example, the front (1711, 1811, 1911), the rear (1712, 1812, 1912), and the side (1713, 1813, 1913) may be formed from different materials. Alternatively, the rear (1712, 1812, 1912) and the side (1713, 1813, 1913) may be formed integrally and may include the same material. For example, the rear (1712, 1812, 1912) and the side (1713, 1813, 1913) may include a metallic material (e.g., aluminum).

[0272] According to one embodiment, the first housing (1710) may include a first front surface (1711), a first rear surface (1712), and a first side surface (1713). The first side surface (1713) may include a first upper side surface (1713a), a first lower side surface (1713b), and a first outer side surface (1713c).

[0273] The first upper side surface (1713a) can be defined as the surface located at the uppermost part of the first housing (1710) with respect to the y-axis. For example, the first upper side surface (1713a) can extend from the upper end of the first front surface (1711) (e.g., the uppermost end with respect to the y-axis) along one axis (e.g., the -z-axis direction) to the upper end of the first rear surface (1712) (e.g., the uppermost end with respect to the y-axis).

[0274] The first lower side (1713b) may be opposite to the first upper side (1713a). For example, the first lower side (1713b) may extend from the lower end of the first front side (1711) (e.g., the other end located at the lowest position relative to the y-axis) along an axis (e.g., the -z-axis direction) to the lower end of the first rear side (1712) (e.g., the other end located at the lowest position relative to the y-axis).

[0275] The first outer side surface (1713c) may extend from one end of the first upper side surface (1713a) to one end of the first lower side surface (1713b). For example, it may extend from one end of the first upper side surface (1713a) that is least adjacent to the first hinge portion (1740) to one end of the first lower side surface (1713b) that is least adjacent to the first hinge portion (1740) in a direction substantially perpendicular to the first upper side surface (1713a) (e.g., in the -y-axis direction).

[0276] In various embodiments, the first side surface (1713) may be formed as a flat surface or a curved surface. For example, the points where the first upper side surface (1713a) and the first outer side surface (1713c) contact each other and the points where the first lower side surface (1713b) and the first outer side surface (1713c) contact each other may be formed as curved surfaces. That is, the points may include portions where the direction of a normal line perpendicular to the corresponding surfaces continuously changes. Accordingly, the points may smoothly connect the first upper side surface (1713a) and the first lower side surface (1713b) to the first outer side surface (1713c) so that the first side surface (1713) has a continuous shape. The points may be corners or edges of the first housing (1710).

[0277] According to one embodiment, the second housing (1720) may include a second front surface (1811), a second back surface (1812), and a second side surface (1813). The second side surface (1813) may include a second upper surface (1813a) and a second lower surface (1813b).

[0278] The second upper side surface (1813a) may be defined as the uppermost surface of the second housing (1720) with respect to the y-axis. For example, the second upper side surface (1813a) may extend from the upper end of the second front surface (1811) (e.g., the uppermost end with respect to the y-axis) along one axis (e.g., the -z-axis direction) to the upper end of the second rear surface (1812) (e.g., the uppermost end with respect to the y-axis).

[0279] The second lower side (1813b) may be opposite to the second upper side (1813a). For example, the second lower side (1813b) may extend along one axis (e.g., in the -z axis direction) from the lower end of the second front (1811) (e.g., the other end located lowest with respect to the y-axis) to the lower end of the second rear (1812) (e.g., the other end located lowest with respect to the y-axis).

[0280] According to one embodiment, the third housing (1730) may include a third front surface (1911), a third rear surface (1912), and a third side surface (1913). The third side surface (1913) may include a third upper side surface (1913a), a third lower side surface (1913b), and a third outer side surface (1913c).

[0281] The third upper side surface (1913a) may be defined as the surface located at the uppermost part of the third housing (1910) with respect to the y-axis. For example, the third upper side surface (1913a) may extend from the upper end of the third front surface (1911) (e.g., the uppermost end with respect to the y-axis) along one axis (e.g., the -z-axis direction) to the upper end of the third rear surface (1912) (e.g., the uppermost end with respect to the y-axis).

[0282] The third lower side (1913b) may be opposite to the third upper side (1913a). For example, the third lower side (1913b) may extend along one axis (e.g., in the direction of the -z axis) from the lower end of the first front side (1911) (e.g., the other end located lowest with respect to the y-axis) to the lower end of the third rear side (1912) (e.g., the other end located lowest with respect to the y-axis).

[0283] The third outer surface (1913c) may extend from one end of the third upper surface (1913a) to one end of the third lower surface (1913b). For example, it may extend in a direction substantially perpendicular to the third upper surface (1913a) (e.g., -y-axis direction) from one end of the third upper surface (1913a) that is not closest to the second hinge portion (1750) to one end of the third lower surface (1913b) that is not closest to the second hinge portion (1750).

[0284] According to one embodiment, the portion drawn by a dotted line between the first housing (1710) and the second housing (1720) and the portion drawn by a dotted line between the second housing (1720) and the third housing (1730) may represent a bending area of ​​the foldable electronic device (1700). For example, the first hinge portion (1740) and the second hinge portion (1750) may include at least a portion of the bending area. Additionally, the bending area of ​​the flexible display (1701) may be an area corresponding to the portions drawn by the dotted lines.

[0285] In various embodiments, a separate display (not shown) may be arranged on a portion of the rear surface (1712, 1812, 1912). For example, in a folded state of the foldable electronic device (1700), a separate display (not shown) distinct from the flexible display (101) may be displayed on one side of the rear surface (1712, 1812, 1912) of the foldable electronic device (1700) facing the outside of the foldable electronic device (1700). For example, in the infolded state of the foldable electronic device (1700), when the first housing (1710) is folded first toward the second housing (1720), a separate display (not shown) may be externally visible in at least one part of the third rear surface (1912) of the third housing (1730) and the second rear surface (1812) of the second housing (1720) (e.g., an area that does not touch an external object).

[0286]

[0287] FIG. 18a is a drawing illustrating a partially infolded state of a foldable electronic device according to one embodiment.

[0288] Referring to FIG. 18A, in the example of FIG. 18A, the display of the foldable electronic device (1700) (e.g., the display (112) of FIG. 1) is omitted for convenience of explanation, but a person skilled in the art will understand that the display may be included on the front of the foldable electronic device (1700).

[0289] Referring to FIG. 17a, FIG. 17b, and FIG. 18a, according to one embodiment, the foldable electronic device (1700) can be folded in an infold manner. For example, with respect to the second housing (1720), the first front (1711) of the first housing (1710) and the third front (1911) of the third housing (1730) can be folded toward the second front (1811) of the second housing (1720) through bending of the first hinge portion (1740) and the second hinge portion (1750), respectively. Referring to FIG. 18a, the first housing (1710) and the third housing (1730) may be movable in the direction of the illustrated arrow.

[0290] According to one embodiment, the remaining housings of a plurality of housings of a foldable electronic device (1700) may be folded over one of the housings. The remaining housings may be folded sequentially, and the surfaces of the plurality of housings that come into contact with each other may differ depending on the folding order. For example, when the second housing (1720) is placed at the bottom, the first housing (1710) may be folded first (e.g., before the third housing (1730)) so that the second front surface (1811) of the second housing (1720) and the first front surface (1711) of the first housing (1710) come into substantial contact, and then the third housing (1730) may be folded so that the third front surface (1911) of the third housing (1730) and the first rear surface (1712) of the first housing (1710) come into substantial contact. In the case where the second housing (1720) is placed at the bottom and the third housing (1730) is folded first (e.g., before the first housing (1710)), the third housing (1730) may be folded first so that the second front (1811) of the second housing (1720) and the third front (1911) of the third housing (1730) are substantially in contact, and then the first housing (1710) may be folded so that the first front (1711) of the first housing (1710) and the third rear (1912) of the third housing (1730) are substantially in contact. The above description may apply in the same or similar way to the case where the first housing (1710) is placed at the bottom and the case where the third housing (1730) is placed at the bottom.

[0291] In various embodiments, the foldable electronic device (1700) may be folded in an outfold manner (not shown). For example, the front surfaces (1711, 1811, 1911) of a plurality of housings in which a flexible display is visible may be folded so that they do not face each other but are separated. In this case, the rear surfaces (1712, 1812, 1912) of the plurality of housings may be folded so that they come into contact with each other.

[0292]

[0293] FIG. 18b is a drawing illustrating a partially in-and-out-folded state of a foldable electronic device according to one embodiment.

[0294] Referring to FIG. 18b, in the example of FIG. 18b, the display of the foldable electronic device (1700) (e.g., the display (112) of FIG. 1) is omitted for convenience of explanation, but a person skilled in the art will understand that the display may be included on the front of the foldable electronic device (1700).

[0295] Referring to FIGS. 17A, 17B, and 18B, according to one embodiment, the foldable electronic device (1700) can be folded in an in-and-out manner. For example, with respect to the second housing (1720), the first rear surface (1712) of the first housing (1710) can be folded (e.g., outfolded) toward the second rear surface (812) of the second housing (1720), and the third front surface (1911) of the third housing (1730) can be folded (e.g., infolded) toward the second front surface (1811) of the second housing (1720). The first housing (1710) and the third housing (1730) can be moved in the directions of the arrows shown. The movement of the first housing (1710) and the third housing (1730) can be achieved through the bending of the first hinge portion (1740) and the second hinge portion (1750), which can involve the bending of the flexible display (1701). The bending area can include a portion shown by a dotted line. In this case, the bending area of ​​the flexible display (1701) can be positioned to correspond to the bending area. The first hinge portion (1740) and the second hinge portion (1750) can each include a portion shown by a dotted line. For example, the first hinge portion (1740) can include a dotted line area shown between the first housing (1710) and the second housing (1720), and the second hinge portion (1750) can include a dotted line area shown between the second housing (1720) and the third housing (1730).

[0296]

[0297] FIG. 19a is a drawing illustrating a foldable electronic device in a completely infolded state according to one embodiment.

[0298] Referring to FIGS. 17a, 17b, and 19a, according to one embodiment, a plurality of housings of a foldable electronic device (1700) may be folded such that their front surfaces (1711, 1811, 1911) overlap each other. For example, when the first housing (1710) is folded before the third housing (1730) with respect to the second housing (1720), the first front surface (1711) of the first housing (1710) may face the second front surface (1811) of the second housing (1720). For example, the first housing (1710) may be positioned on top of the second housing (1720) in the z-axis direction, and the third housing (1730) may be positioned on top of the first housing (1710). In this case, the first hinge part (1740) and the second hinge part (1750) may be bent in opposite directions, and the second hinge part (1750) may be formed to be relatively longer than the first hinge part (1740) (e.g., longer in the x-axis direction based on the unfolded state). However, when the third housing (1730) is folded before the first housing (1710) with respect to the second housing (1720), the first front side (1711) of the first housing (1710) may face the third rear side (1912) of the third housing (1730). For example, the third housing (1730) may be positioned above the second housing (1720) in the z-axis direction, and the first housing (1710) may be positioned above the third housing (1730). In this case, the first hinge portion (1740) may be formed to be relatively longer than the second hinge portion (1750) (e.g., longer in the x-axis direction based on the unfolded state).

[0299] FIG. 19b is a drawing illustrating a foldable electronic device in a completely in-and-out-folded state according to one embodiment.

[0300] Referring to FIGS. 17A, 17B, and 19B, according to one embodiment, a plurality of housings of a foldable electronic device (1700) may be folded such that one surface thereof overlaps with another. For example, with respect to a second housing (1720), a first rear surface (1712) of a first housing (1710) may be folded (e.g., outfolded) toward a second rear surface (1812) of a second housing (1720), and a third front surface (1911) of a third housing (1730) may be folded (e.g., infolded) toward a second front surface (1811) of a second housing (1720). For example, the second housing (1720) may be positioned above the third housing (1730) in the z-axis direction, and the first housing (1710) may be positioned above the second housing (1720). In this case, the first hinge portion (1740) and the second hinge portion (1750) may have substantially the same length (e.g., length in the x-axis direction relative to the unfolded state).

[0301]

[0302] FIG. 20 illustrates a generative artificial intelligence system according to one embodiment.

[0303] Referring to FIG. 20, in a generative artificial intelligence system (2000), a user question / response interface (2010) can receive user input. The user input may be in the form of natural language, images, and / or videos. Additionally, contextual information may also be transmitted when the user input is transmitted. The contextual information may include various additional information at the time of the user input. For example, the contextual information may include information about the application currently being used by the user and / or information about the user's location. Furthermore, the user input may also be in a form that combines the aforementioned natural language, images, sounds, and contextual information. Furthermore, the user input may also be in a form other than natural language, such as selecting a menu.

[0304] According to one embodiment, the user question / response interface (2010) can output results of a generative artificial intelligence system to the user. The output may be in the form of natural language or specific content, and may also be provided in a form such as an action requested by the user. The user question / response interface (2010) can output results of a generative artificial intelligence system (2000) to the user. The output may be in the form of natural language or specific content, and may also be provided in a form such as an action requested by the user.

[0305] According to one embodiment, the artificial intelligence framework (2020) can receive user input and coordinate and control each component or module necessary to perform the user's intention based on the user's query.

[0306] According to one embodiment, user input received from a user question / response interface (2010) may be transmitted to a prompt design module (2021). The prompt design module (2021) may be used to generate prompts suitable for inputting user input into a large language model (LMM) or a large multi-modal model (LMM). The prompt design module (2021) may be an artificial intelligence component that uses machine learning algorithms or neural networks to develop better prompts over time. The prompt design module (2021) may generate prompts by accessing a database (2030) containing user preference data, a prompt library, and prompt examples based on user input, and transmit the generated prompts to the LLM or LMM.

[0307] According to one embodiment, the API / plugin management module (2022) can perform the role of communicating with external information when there is a request for additional information when transmitting user input as input to the generative artificial intelligence model (2050). The API / plugin management module (2022) establishes a channel to communicate with the outside of the artificial intelligence interface through an application programming interface (API), and can enable access to various data sources through the established channel. Additionally, the API / plugin management module (2022) can request the action through the API if the application / service module (2040) needs to perform an action that executes the user input as a final step, rather than an intermediate result. The information obtained from the outside may be used to generate a prompt in the prompt design module (2021) along with the user input, or it may be transmitted as input to the generative artificial intelligence model (2050).

[0308] According to one embodiment, the transformation module (2023) can fine-tune the output from the generative artificial intelligence model (2050). For example, the transformation module (2023) can verify whether the content generated through the LLM and / or LMM is irrelevant, contains biased content, or contains harmful content. Additionally, the transformation module (2023) can determine the extent to which the output matches what the user wants and, if additional processing is required, proceed with that process. Furthermore, the transformation module (2023) can configure and provide hints to the user to avoid unwanted output.

[0309] According to one embodiment, a generative artificial intelligence model (2050) may generally refer to an artificial intelligence neural network that creates new types of data based on user input information. The generative artificial intelligence model (2050) may include a model that generates images and / or a model that generates language. Representative models that generate images include a generative adversarial network (GAN) and a variational autoencoder (VAE), and examples include a diffusion-based generative model that uses a VAE and a transformer structure. A model that generates language is a model that is trained to statistically output the most appropriate output based on input values, and representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, there is also an LMM that can recognize various types of data input, such as text, images, and voice, and generate new data corresponding to them.

Claims

1. In electronic devices, display; Communication circuit; Memory that stores instructions; and comprising at least one processor; When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Receive a first message from an external electronic device, Identify at least one ambiguous part in the first message, Using an artificial intelligence (AI) model trained based on context information, determining whether additional information corresponding to at least one ambiguous part can be provided, and An electronic device that displays an indication indicating that the additional information can be provided on the display along with the first message, based on a judgment that the additional information can be provided.

2. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Receiving user input for an indication that the provision of the above additional information is possible; Based on the user input, generate a second message including at least a portion of the first message and the additional information; An electronic device that causes the generated second message to be displayed on the display.

3. In claim 2, An electronic device wherein the second message includes information used to provide the additional information among the context information.

4. In claim 1, The above-identified at least one ambiguous portion includes a first ambiguous portion and a second ambiguous portion, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Receiving a user input selecting the first ambiguous part, Based on the above user input, a second message is generated including at least a portion of the first message and first additional information corresponding to the first ambiguous portion of the additional information, and An electronic device that causes the generated second message to be displayed on the display.

5. In claim 2, The above user input includes an input that adjusts the size of the display area where the second message is displayed, and An electronic device in which the size of the data of the above additional information is determined based on the size of the above display area.

6. In Claim 2, The above second message is an electronic device, which is a message in which at least one ambiguous part is replaced with the additional information.

7. In Claim 2, The above second message is an electronic device comprising the above at least one ambiguous part.

8. In Claim 2, If at least one of the above ambiguous parts relates to a photograph, the above additional information includes image information, and The above second message is an electronic device including the above image information.

9. In claim 1, An electronic device comprising at least one of the above context information, which includes information on messages previously received through an application related to the first message, information related to multimedia stored in the memory, information stored on an external server related to another application, or information stored on another electronic device registered with the same account as the electronic device.

10. In claim 1, An electronic device comprising at least one of an indication indicating that the above additional information can be provided, the indication comprising an affordance that converts the first message into a second message containing the above additional information, a visual effect that modifies the features of text included in the at least one ambiguous part, or a visual effect that modifies the features of a display area where the first message is displayed.

11. In Claim 2, The above display includes a first display and a second display, and The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Display the first message on the first display, and An electronic device that displays the second message on the second display.

12. In a method for generating text on an electronic device, The operation of receiving a first message from an external electronic device; An action of identifying at least one ambiguous part in the first message above; An operation to determine whether additional information corresponding to at least one ambiguous part can be provided using an AI model trained based on context information; and A method comprising the action of displaying an indication that the additional information can be provided together with the first message, based on the judgment that the additional information can be provided.

13. In claim 12, An action of receiving user input for an indication that the above additional information can be provided; An operation to generate a second message including at least some of the first message and the additional information based on the above user input; and A method comprising an action of displaying the second message generated above.

14. In claim 12, The above-identified at least one ambiguous portion includes a first ambiguous portion and a second ambiguous portion, The operation of receiving user input to select the first ambiguous part above; An operation to generate a second message based on the above user input, comprising at least a portion of the first message and first additional information corresponding to the first ambiguous portion of the additional information; and A method comprising an action of displaying the second message generated above.

15. In a computer-readable storage medium for storing instructions, When the above instructions are executed by at least one processor of the electronic device, the electronic device: Receive a first message from an external electronic device, Identify at least one ambiguous part in the first message above, and Using an AI model trained based on context information, determine whether additional information corresponding to at least one ambiguous part can be provided, and A computer-readable storage medium that displays, together with the first message, an indication indicating that the additional information can be provided, based on the judgment that the additional information can be provided.

Images