Electronic device, method, and computer-readable storage medium for changing style of text

Abstract

An electronic device according to an embodiment may comprise: a display; at least one processor including a processing circuit; and a memory including one or more storage media for storing instructions. The instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to receive, on the basis of a first text input through a software keyboard, a request to generate other texts related to the first text. The instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to, in response to the request, obtain multiple texts related to the first text and corresponding to multiple styles by using a style transfer model.

Description

Electronic device, method, and computer-readable storage medium for changing the style of text

[0001] The various embodiments described below relate to an electronic device, a method, and a computer-readable storage medium for changing the style of text.

[0002] Artificial intelligence is a technology for simulating human (or biological) neural activity, such as perception and / or inference, and can be implemented by hardware, software, or any combination thereof designed to perform computation for simulating neural activity.

[0003] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0004] In one embodiment, an electronic device may include a display, at least one processor including a processing circuit, and a memory including one or more storage media storing instructions. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display a software keyboard provided by an application on the display while the application is running on the electronic device. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive a request for generating other texts related to a first text input via the software keyboard. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, in response to the request, obtain a plurality of texts, using a style conversion model, that are related to the first text, correspond to a plurality of styles, and include at least one text in which one or more emoticon objects are grouped. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display at least a portion of the list including the plurality of texts through the display.

[0005] According to one embodiment, a method of an electronic device may include an operation of displaying a software keyboard provided by an application on a display of the electronic device while the application is running on the electronic device. The method may include an operation of receiving a request for generating other texts related to a first text input through the software keyboard based on the first text. The method may include an operation of obtaining, in response to the request, a plurality of texts using a style conversion model, the plurality of texts being related to the first text, corresponding to a plurality of styles, and including at least one text in which one or more emoticon objects are grouped. The method may include an operation of displaying at least a portion of a list including the plurality of texts through the display.

[0006] In one embodiment, a non-transitory computer readable storage medium storing one or more programs may include instructions that, when executed by at least one processor of an electronic device having a display, cause the electronic device to display a software keyboard provided by the application on the display while the application is running on the electronic device. The one or more programs may include instructions that, when executed by the at least one processor, cause the electronic device to receive a request for generating other texts related to first text, based on first text input via the software keyboard. The one or more programs may include instructions that, when executed by the at least one processor, cause the electronic device to obtain, in response to the request, a plurality of texts, using a style conversion model, that are related to the first text, that correspond to a plurality of styles, and that include at least one text in which one or more emoticon objects are grouped. The one or more programs may include instructions that, when executed by the at least one processor, cause the electronic device to display at least a portion of a list containing a plurality of texts through the display.

[0007] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0008] FIG. 2a illustrates an exemplary electronic device for converting the style of text.

[0009] Figures 2b, 2c, 2d, and 2e illustrate operations for transforming the style of text of an exemplary electronic device.

[0010] Figures 3a, 3b, and 3c illustrate operations for transforming the style of text of an exemplary electronic device.

[0011] Figures 4a, 4b, and 4c illustrate operations of an exemplary electronic device to convert the style and language of text.

[0012] FIGS. 5A, 5B, 5C, 5D, and 5E illustrate operations of an exemplary electronic device to convert the style and language of text.

[0013] Figures 6a, 6b, and 6c illustrate operations for transforming the style of text within an application of an exemplary electronic device.

[0014] FIG. 7 is a signal flow chart for explaining an operation for converting the style of text of an exemplary electronic device.

[0015] Figure 8 illustrates an operation of an exemplary electronic device to transform the style of text.

[0016] FIGS. 9A, 9B, 9C, and 9D illustrate operations of an exemplary electronic device to transform the style of text.

[0017] FIGS. 10A, 10B, 10C, 10D, 10E, and 10F illustrate operations of an exemplary electronic device to transform the style of text.

[0018] Figures 11a, 11b, 11c, and 11d illustrate operations of an exemplary electronic device to correct errors in text.

[0019] Figures 12a, 12b, 12c, and 12d illustrate operations of an exemplary electronic device to convert the style and language of text.

[0020] FIG. 13 is an exemplary block diagram illustrating a generative artificial intelligence system according to one embodiment.

[0021] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0022] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0023] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0024] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0025] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0026] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0027] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0028] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0029] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0030] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0031] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0032] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0033] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0034] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0035] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0036] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0037] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0038] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0039] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0040] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0041] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0042] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0043] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0044] FIG. 2A illustrates an exemplary electronic device for converting the style of text. FIGS. 2B, 2C, 2D, and 2E illustrate operations of the exemplary electronic device for converting the style of text.

[0045] Referring to FIG. 2A, an electronic device (101) may be communicatively connected to an external electronic device (102). The external electronic device (102) may include a server of a service provider (e.g., server (108) of FIG. 1). The server may include a computer designed to provide server functionality, such as a workstation. The embodiment is not limited thereto, and the server may include a combination of a personal computer and a software application installed on the personal computer. The server may include a group (or cluster) of example workstations and / or personal computers. The server may be configured by a service provider to execute a software application for providing a service via a network, such as the Internet.

[0046] According to one embodiment, the electronic device (101) may include a smartphone (101-1), a smartpad, and / or a tablet PC. The electronic device (101) may include a personal computer, such as a desktop (101-2) and a laptop. The embodiment is not limited thereto, and the electronic device (101) may include a smart accessory, such as a smartwatch and / or a head-mounted device (HMD), in which an application provided with a software keyboard (230) is executable within the electronic device (101).

[0047] According to one embodiment, the external electronic device (102) may be configured to receive a request for converting the style of text from the electronic device (101). The style of text may refer to the parlance, literary style, sentence structure, tone, sense, word order, etc. of the text. A plurality of texts with different styles may refer to texts that have substantially the same contextual meaning but different sentence structures, literary styles, tone of text, and speech styles. The external electronic device (102) may perform an operation for converting the style of the text or generating texts different from the text based on a request obtained from the electronic device (101) and / or a text (or text message) input by a community service (e.g., a chat service, SNS, message).

[0048] According to one embodiment, a style conversion model (210) may be provided as a neural network for automatically converting the style of text to an external electronic device (102) in order to execute a function corresponding to a request from an electronic device (101) for converting the style of text. However, the style conversion model (210) is not limited thereto, and may be implemented with various artificial intelligence technologies such as machine learning, deep learning, cognitive computing, generative AI, etc. as well as a neural network. The style conversion model (210) may be configured to generate or output a plurality of texts corresponding to a plurality of styles different from the text, based on an input for converting the text received from the electronic device (101). For example, the style conversion model (210) may be configured to generate or output a plurality of texts having the same contextual meaning as the text but a different tone from the text, based on the text received from the electronic device (101). The electronic device (101) may be configured to display at least some of the plurality of texts output from the style conversion model (210) through the display (220) of the electronic device (101) based on receiving the plurality of texts from an external electronic device (102).

[0049] Although the style conversion model (210) is illustrated and described as being provided through an external electronic device (102) distinct from the electronic device (101), it is not limited thereto. The style conversion model (210) may be provided to the electronic device (101). For example, the style conversion model (210) may be driven based on a plurality of parameters included in the memory of the electronic device (101) (e.g., the memory (130) of FIG. 1).

[0050] Hereinafter, with reference to FIGS. 2b to 2e, an operation of an electronic device (101) converting the style of text input through a software keyboard (230) or displaying converted text using a style conversion model (210) is described. The operations illustrated and described in FIGS. 2b to 2e may be performed under the control of a processor of the electronic device (101) (e.g., processor (120) of FIG. 1).

[0051] Referring to FIG. 2B, the processor (120) of the electronic device (101) may display text messages (e.g., text messages (241, 242, 243)) electronically exchanged between at least two users within the display (220) based on the execution of the message application. The text messages (241, 242, 243) may be displayed within a visual object having a bubble shape within the display (220). However, without being limited thereto, the processor (120) may control to transmit and / or receive messages including text and / or images (e.g., emoticons) based on the execution of the application.

[0052] According to one embodiment, the processor (120) may provide areas (201, 202, 203) for inputting and / or displaying text on the screen of the display (220) while an application is running. Area (201) may be an area for displaying text inputted through a software keyboard (230) or for editing the text inputted through the software keyboard (230). For example, a user may edit text inputted in area (201) by modifying, deleting, and / or adding text inputted in area (201) through a software keyboard (230) displayed in area (202). The user may, for example, add or remove one or more emoticon objects to text in area (201) through the software keyboard (230). The area (202) may be configured to display a software keyboard (230) provided by an application and / or a software keyboard (230) provided by a keyboard application for text input while the application is running, or to receive a user's text input through the software keyboard (230). For example, the processor (120) may be configured to execute a keyboard application of the electronic device (101) for text input based on a user input to the area (201) (e.g., a user's touch input to the area (201). The processor (120) may control the display (220) to display a software keyboard (230) for text input within the area (202) based on the execution of the keyboard application.The area (203) may be an area where text messages (e.g., text messages (241, 242, 243)) exchanged electronically between at least two users and / or visual objects (261, 262) representing at least two users who are senders of each text message (241, 242, 243) are displayed.

[0053] According to one embodiment, the processor (120) of the electronic device (101) may be configured to display a software keyboard (230) provided by the application on the display (220) while the application is running. For example, the application running on the electronic device (101) may provide a software keyboard (230) for inputting text messages (241, 242, 243). For example, while the application is running in the electronic device (101), the processor (120) may be configured to display, through the display (220), an area (201) for inputting text, and an area (202) for a software keyboard (230) provided by the application below the area (201). The processor (120) may be configured to display the software keyboard (230) within the area (202) based on a user input for text input (e.g., a touch input in the area (201)) and / or a user input for displaying the software keyboard (230). For example, the processor (120) may be configured to execute a keyboard application of the electronic device (101) for text input based on a user input for text input (e.g., a touch input in the area (201)) and / or a user input for displaying the software keyboard (230) while the application is running. The processor (120) may control the display (220) to display the software keyboard (230) within the area (202) based on the running of the keyboard application.

[0054] Although the processor (120) of the electronic device (101) has been described as displaying a software keyboard (230) within the area (202) via the display (220), the present invention is not limited thereto. Although not illustrated, an input device capable of being connected wirelessly and / or wiredly to the electronic device (101) may be provided. The input device may include, for example, at least one of a wireless keyboard and a wired keyboard. For example, the processor (120) may be configured to display text input via the display (220) based on receiving the text.

[0055] According to one embodiment, the processor (120) of the electronic device (101) may be configured to display text (251) in the area (201) in response to text (251) input through the software keyboard (230). For example, the processor (120) may be configured to display text (251) corresponding to a user's touch input through the software keyboard (230) displayed in the area (202) in the area (201). The text (251) may be transmitted to a user terminal corresponding to the visual object (262) or displayed in the area (203) based on a user input to a visual object (265) for determining transmission of a text message including the text (251). Within this document, a visual object may be referred to as, but is not limited to, an affordance for inducing an action of the electronic device (101) to cause a function of the electronic device (101) and / or an application running within the electronic device (101). For example, the processor (120) may control the display (220) to display a visual object (265) (or affordance) for determining the transmission of a text message based on the execution of a messaging application.

[0056] Referring to FIG. 2C, the processor (120) of the electronic device (101) may be configured to receive a request to generate other texts related to the text (251) based on text (251) input through the software keyboard (230). For example, the processor (120) may receive a request to generate other texts related to the text (251) based on a user input through the software keyboard (230) not being identified for a specified period of time after the text (251) is input into the area (201). For example, the processor (120) may receive a request to generate other texts related to the text (251) based on a user input to a visual object (not shown) for generating other texts related to the text (251) after the text (251) is input into the area (201). For example, the processor (120) may be configured to identify, while the application is running, whether the application is included in a preset application group. Based on identifying that the application is included in the application group, the processor (120) may receive a request to generate other text related to the text (251) through user input to a visual object (265) for determining transmission of the text (251) entered in the area (201). However, the above-described embodiments are exemplary and not limited thereto.

[0057] For example, the processor (120) may identify text (251) entered into the area (201) through a software keyboard (230). The processor (120) may receive, based on the text (251) entered into the area (201), a request to generate texts related to the text (251) and different from the text (251). For example, the processor (120) may receive, based on the text (251) displayed in the area (201), a request to generate a plurality of texts each corresponding to a plurality of preset styles of the text (251).

[0058] Referring to FIG. 2C, the processor (120) of the electronic device (101) may be configured to execute a function for inputting data related to an application and the text (251) into a style conversion model (210) based on receiving a request for generating other texts related to the text (251). The data related to the application may refer to, for example, information related to a service provided by the application (e.g., SNS service, game service, health care service, online video service) or information related to the characteristics of the application, but is not limited thereto. The processor (120) may be configured to store data related to the application within the electronic device (101) in the memory (130). For example, the processor (120) may be configured to execute a function to input (or transmit) data related to text (251) entered through a software keyboard (230) in an area (201) and / or text messages (241, 242, 243) displayed in an area (203) to a style conversion model (210). The style conversion model (210) may be configured to use the data related to the text messages (241, 242, 243) to generate the text (251) into text having a style corresponding to a conversation style between at least two users corresponding to visual objects (261, 262). Data related to the above text messages (241, 242, 243) may include, but is not limited to, personal information such as a conversation list between two users who are conversation subjects including the text messages (241, 242, 243) and a phone number of a conversation partner corresponding to a visual object (262).The processor (120) may be configured to store data related to the text messages (241, 242, 243) in the memory (130) of the electronic device (101). For example, referring to FIG. 2E together, the style conversion model (210) may be configured to generate text (251) input in the area (201) based on text messages (241, 243) transmitted from the electronic device (101), into polite text (252) corresponding to the conversation style between two users, taking into account the conversation style. The processor (120) may be configured to display the polite text (252) output from the style conversion model (210) through the display (220). However, the present invention is not limited thereto.

[0059] The processor (120) can control the display (220) to display a plurality of texts having a different shape from the text (251) by using the style conversion model (210) for generating text. For example, the processor (120) can be configured to display one or more texts with an underline or highlight added to the text (251) by using the style conversion model (210), or to display one or more texts including a formatted shape or a bold shape of the text (251) by using the style conversion model (210). However, the above-described embodiments are exemplary and are not limited thereto. The electronic device (101) can provide a variety of user experiences to the user by using the style conversion model (210) to provide texts having various styles that vary depending on the recipient of the text.

[0060] According to one embodiment, the processor (120) of the electronic device (101) may display a visual object (271) in the area (202) for the software keyboard (230) to indicate that other texts related to the text (251) are being generated based on the text (251) entered in the area (201) of the screen provided through the display (220). For example, the processor (120) may be configured to transmit the text (251) and data related to the application to the style conversion model (210) based on the text (251) entered in the area (201). The processor (120) may be configured to display the visual object (271) in the area (202) instead of the software keyboard (230) while receiving a plurality of texts corresponding to a plurality of styles output (or converted) from the style conversion model (210) based on the text (251). For example, the processor (120) may be configured to display a visual object (272) for canceling generation of the plurality of texts in an area (202) provided through the display (220) while receiving a plurality of texts from the style conversion model (210) based on text (251) entered in an area (201). The processor (120) may be configured to display a software keyboard (230) for text input in the area (202) as illustrated in FIG. 2B based on receiving a user input through the visual object (272).

[0061] Referring to FIG. 2D , the processor (120) of the electronic device (101) may be configured to, in response to a request for generating other texts related to the text (251), obtain a plurality of texts, using the style conversion model (210), that are related to the text (251), correspond to a plurality of styles, and include at least one text in which one or more emoticon objects are grouped. The processor (120) may be configured to display, through the display (220), at least a portion of a list (280) including the plurality of texts. The text in which one or more emoticon objects are grouped may mean a text that is displayed together with the one or more emoticon objects or in which the one or more emoticon objects are displayed between one or more words included in the text and / or at both ends of a sentence. For example, the visual object (284) may display a text in which an emoticon object (255a) is placed between one or more words. For example, a visual object (287) may display text in which an emoticon object (256a) is placed at the end of a sentence.

[0062] For example, the processor (120) may be configured to display, through the display (220), visual objects (281, 282, 283, 284, 285, 286, 287), each of which includes a plurality of texts output from the style conversion model (210) based on the text (251). For example, the visual objects (281, 282, 283, 284, 285, 286, 287) may include a plurality of texts that are substantially the same in contextual meaning as the text (251), but different in sentence structure, literary style, tone of text, parlance, etc. from the text (251). For example, the style conversion model (210) may include a plurality of prompts corresponding to each of the plurality of styles in order to output a plurality of texts having a plurality of styles using the text input to the style conversion model (210).

[0063] For example, the visual object (281) can provide text in the original style of the text (251) output from the style conversion model (210) based on the text (251) input in the area (201). For example, the visual object (282) can provide text in the professional style of the text (251) output from the style conversion model (210) based on the text (251) input in the area (201). For example, the visual object (283) can provide text in the casual style of the text (251) output from the style conversion model (210) based on the text (251) input in the area (201). For example, the visual object (284) may provide a text (255) in a social post style, based on the text (251) input into the area (201), of the text (251) output from the style conversion model (210), including an emoticon object (255a) and / or one or more tag words (255b, 255c). For example, the visual object (285) may provide a text (252) in a polite style, based on the text (251) input into the area (201), of the text (251) output from the style conversion model (210). For example, the visual object (286) may provide a text in a witty style, based on the text (251) input into the area (201). For example, a visual object (287) may provide text (256) of a style including an emoticon object (256a) output from a style conversion model (210) based on text (251) entered within an area (201). However, the present invention is not limited thereto.

[0064] For example, the processor (120) may be configured to generate a prompt for correcting a grammatical error in text (251) based on text (251) entered in an area (201). The processor (120) may be configured to input the text (251) and the prompt to a style conversion model (210). The processor (120) may be configured to receive another text output from the style conversion model (210) that is related to the text (251) and has grammatical errors corrected. For example, the processor (120) may be configured to generate a prompt for changing the language of the text (251) based on text (251) entered in an area (201). The processor (120) may be configured to input the text (251) and the prompt to a style conversion model (210). The processor (120) may be configured to receive another text output from the style conversion model (210) that is related to the text (251) and has a different language than the text (251).

[0065] For example, the processor (120) may be configured to generate a plurality of prompts for changing the style of the text (251) based on the text (251) input into the region (201). For example, the processor (120) may be configured to maintain the original meaning and length of the text (251) input into the region (201) and generate prompts corresponding to a plurality of texts having a different style from the text (251). The processor (120) may be configured to input the text (251) and the prompts into a style conversion model (210). The processor (120) may be configured to receive a plurality of texts output from the style conversion model (210) that are related to the text (251) and have a different style from the text (251).

[0066] For example, the list (280) may provide visual objects that include one or more texts that include one or more punctuation marks, including one or more emoticon objects. For example, the visual object (282) may display text that provides punctuation marks (282a) that are not included in the text (251) based on a professional style provided by the style conversion model (210). For example, the visual object (283) may display text that provides punctuation marks (283a) that are not included in the text (251) based on a casual style provided by the style conversion model (210). For example, the visual object (286) may display text that provides punctuation marks (286a) that are not included in the text (251) based on a witty style provided by the style conversion model (210). However, the above-described embodiments are exemplary and not limiting.

[0067] For example, the processor (120) of the electronic device (101) may provide visual objects (281, 282, 283, 284, 285, 286, 287) each including a plurality of texts corresponding to a plurality of styles through a list (280). At least a portion of the list (280) may be displayed in an area (203) for a software keyboard (230). For example, the processor (120) may be configured to scrollably display at least a portion of the list (280) including a plurality of texts related to text (251) and corresponding to a plurality of styles within an area (202). By providing a scrollable display of the list (280) within the area (202), the electronic device (101) can be configured to change the text (251) within the area (201) to text having a style specified by the user through visual objects (281, 282, 283, 284, 285, 286, 287) within the area (202).

[0068] A plurality of texts corresponding to a plurality of styles provided from a style conversion model (210) are described through a list (280) including visual objects (281, 282, 283, 284, 285, 286, 287), but are not limited thereto. Including the above-described styles, the processor (120) of the electronic device (101) can be configured to display a text input through a software keyboard (230) as a plurality of texts corresponding to various styles by using the style conversion model (210).

[0069] According to one embodiment, the processor (120) of the electronic device (101) may be configured to display a visual object (273) for changing the style of text (251) input through a software keyboard (230) through the display (220). The processor (120) may be configured to display a visual object (274) for changing the language of the text (251) through the display (220) based on the input text (251). Changing the style of the text (251) through the visual object (273) and changing the language of the text (251) through the visual object (274) will be described later with reference to FIGS. 4A and 4B.

[0070] An operation of an electronic device (101) in response to receiving an input for determining a visual object (285) containing polite style text (252) among visual objects (281, 282, 283, 284, 285, 286, 287) containing multiple texts is illustrated with reference to FIG. 2e.

[0071] Referring to FIGS. 2d and 2e, the processor (120) of the electronic device (101) may be configured to, in response to receiving an input for determining text (252) from a list (280) provided from a style conversion model (210), display the text (252) in the area (201) instead of the text (251) previously displayed in the area (201). For example, the processor (120) may be configured to, based on a touch input to a visual object (285) among the list (280) scrollably displayed in the area (202) in FIG. 2d, display the text (252) included in the visual object (285) in the area (201). The processor (120) may be configured to delete text (251) within an area (201) and display text (252) included in the visual object (285) based on an input to the visual object (285), as shown in FIG. 2e.

[0072] The operation of the processor (120) of the electronic device (101) after transmitting the text (252) displayed in the area (201) to the user terminal of the other party corresponding to the visual object (262) through the visual object (265) is described with reference to FIGS. 3a to 3c.

[0073] Figures 3a, 3b, and 3c illustrate operations for transforming the style of text of an exemplary electronic device.

[0074] Referring to FIGS. 3A, 3B, and 3C, the processor (120) of the electronic device (101) may be configured to display a text message (244) including the text (252) in the area (203) based on an input (e.g., a touch input to a visual object (265)) for transmitting the text (252) entered in the area (201) to a user terminal of the other party corresponding to the visual object (262).

[0075] According to one embodiment, the processor (120) of the electronic device (101) may be configured to display, within the area (201), text (254) related to the text (253) and having the same style as the text (252), based on text (253) input through a software keyboard (230) after the text (252) is displayed in the area (201).

[0076] For example, referring to FIGS. 3A and 3B, the processor (120) may be configured to transmit text (252) displayed in an area (201) through a visual object (265), and then display an area (310) for displaying text input through a software keyboard (230) through the display (220). The area (310) may be displayed within the area (202) for the software keyboard (230). The text (253) input through the software keyboard (230) may be displayed within the area (310).

[0077] For example, referring to FIGS. 3b and 3c, the processor (120) may be configured to, based on text (253) input into an area (310), display text (254) in an area (201) that is related to the text (253) and has the same style as the style of the text (252) (e.g., a polite style corresponding to the visual object (285) of FIG. 2d). For example, the processor (120) may be configured to, based on receiving an input for determining text (252) in FIG. 2d, display text input into an area (310) after the text (252) is displayed in the area (201) as text having the same style as the text (252) using the style conversion model (210). For example, the processor (120) may be configured to automatically display text (254) in the area (201) based on text (253) entered in the area (310) and having the same style as the text (252) and related to the text (253) using the style conversion model (210).

[0078] For example, the processor (120) may provide, while the application is running, a menu (e.g., the visual object (273) of FIG. 2d or the list (430) of FIG. 4b) for generating text that is related to the text (253) entered in the area (201) and has a different style from the text (253) for a counterpart corresponding to a visual object (262) preset within the application. For example, the processor (120) may be configured to display, while the application is running, text corresponding to a specified style (e.g., a polite style) using a style conversion model (210) for a counterpart corresponding to a visual object (262).

[0079] For example, the processor (120) may be configured to analyze a conversation style between a user and the counterpart based on information related to the counterpart corresponding to the visual object (262) while the application is running, using the style conversion model (210). For example, the processor (120) may be configured to provide text having a style specified for the user based on a list of conversations between the user and the counterpart (e.g., text messages (241, 242, 243, 244)) within the application. For example, the processor (120) may be configured to provide text having a style specified for the user based on information related to the counterpart (e.g., phone number, ID, address, etc.) within the application. However, the present invention is not limited thereto. For example, the processor (120) may be configured to analyze a conversation style between the user and the counterpart within a plurality of applications. With regard to analyzing the conversation style between the user and the counterpart within multiple applications, this is described below in FIG. 8.

[0080] The processor (120) is configured to display text (e.g., text (254)) to which the style set is applied to text input after the style of the text is set according to the application and / or the counterpart of the text, thereby providing a variety of user experiences to the user.

[0081] Figures 4a, 4b, and 4c illustrate operations of an exemplary electronic device to convert the style and language of text.

[0082] Referring to FIGS. 4A, 4B, and 4C, the processor (120) of the electronic device (101) may be configured to display a visual object (273) for changing the style of text (251) input through a software keyboard (e.g., the software keyboard (230) of FIG. 2A) through the display (220). The processor (120) may be configured to display a visual object (274) for changing the language of the text (251) through the display (220) based on the input text (251).

[0083] According to one embodiment, the processor (120) of the electronic device (101) may be configured to receive a request to generate texts in a second language (e.g., English) different from the first language related to the text (251) in a first language (e.g., Korean) input through a software keyboard (230). For example, the processor (120) may be configured to execute a function to input the text (251) in the first language into a style conversion model (210) to generate texts in a second language different from the first language based on the text (251) in the first language input within the region (201).

[0084] According to one embodiment, the processor (120) of the electronic device (101) may be configured to, in response to a request to generate texts of a second language associated with a text (251) of a first language, obtain a plurality of texts of the second language associated with the text (251) and corresponding to a plurality of styles, using a style conversion model (210). The processor (120) may be configured to display, through a display (220), at least a portion of a list (420) including the plurality of texts of the second language.

[0085] For example, referring to FIG. 4A, the processor (120) may be configured to display a visual object (413) for selecting a translation language of text (251) entered in the region (201), a visual object (412) for indicating a current translation language of text (251) entered in the region (201), and a visual object (411) for disabling a translation function, based on receiving a user input via the visual object (274) (e.g., a touch input to the visual object (274)). For example, the processor (120) may be configured to display, via the visual object (413), a plurality of texts of a second language (e.g., English) corresponding to a plurality of styles associated with the text (251) output from the style conversion model (210) based on text (251) of a first language (e.g., Korean) entered in the region (201), within the region (202). The processor (120) may be configured to scrollably display a list (420) containing the plurality of texts of the second language within the area (202).

[0086] For example, referring to FIG. 4B, the processor (120) may be configured to display, in the area (203), a list (430) of styles for style conversion of text (251) in a first language entered in the area (201) based on receiving a user input via the visual object (273) (e.g., a touch input to the visual object (273). Based on a user input for determining one style in the list (430) (e.g., a touch input for a polite style in the list (430), the processor (120) may be configured to display, in the area (202), a visual object (421) including text (451) in a second language corresponding to the one style. The processor (120) may be configured to display the text (451) of the second language in place of the text (251) of the first language within the region (201) based on a user input (e.g., a touch input to a visual object (421)) for determining the text (451) of the second language.

[0087] According to one embodiment, the processor (120) of the electronic device (101) may be configured to detect grammatical errors in text (251) input through a software keyboard (230). The processor (120) may be configured to, in response to a request to generate another text related to the text (251), obtain a plurality of texts corresponding to a plurality of styles and having the errors corrected through a plurality of prompts stored in the style conversion model (210). For example, the processor (120) may be configured to execute a function for inputting the text (251) having the grammatical errors corrected into the style conversion model (210) based on identifying that a text (251) including a grammatical error is input into an area (201). The processor (120) may be configured to display, through a display (220), a plurality of texts corresponding to a plurality of styles, which are output from the style conversion model (210), and have the grammatical errors corrected.

[0088] The operation of the processor (120) that provides a plurality of texts having different languages ​​and styles from the text input through the software keyboard (230) using the style conversion model (210) is described below in FIGS. 5a to 5e.

[0089] FIGS. 5A, 5B, 5C, 5D, and 5E illustrate operations of an exemplary electronic device to convert the style and language of text.

[0090] Referring to FIG. 5A, a processor (120) of an electronic device (101) may be configured to receive a request to generate texts in a second language (e.g., Korean) that are related to a text (551) in a first language (e.g., English) input through a software keyboard (230) and that are different from the first language. The processor (120) may be configured, for example, in response to the request, to obtain a plurality of texts in the second language that are related to the text (551) and that correspond to a plurality of styles, using a style conversion model (e.g., the style conversion model (210) of FIG. 2A). For example, the processor (120) may be configured to scrollably display at least a portion of a list (510) including the plurality of texts within an area (202).

[0091] For example, the processor (120) may be configured to display, in the region (202), a plurality of texts of a second language different from the first language and related to the text (551) output from the style conversion model (210), based on a text (551) of a first language input into the region (201). The processor (120) may be configured to display, in the region (202), a visual object (273) for changing the style of the text (551) based on the text (551) of the first language input into the region (201), and a visual object (274) for selecting a translation language of the text (551). The visual object (273) may be configured to display a style of the plurality of texts displayed in the region (202). The visual object (274) may be configured to display a language of the plurality of texts displayed in the region (202).

[0092] Referring to FIGS. 5A and 5B , the processor (120) may be configured to display text (552) of a second language instead of text (551) of a first language (e.g., English) within the region (201) based on a user input (e.g., a touch input to a visual object (511) of FIG. 5A) for determining text (552) of a second language (e.g., Korean) among a plurality of texts of a second language provided from a style conversion model (210) and corresponding to a plurality of styles. For example, the processor (120) may be configured to delete text (551) of the first language within the region (201) and display text (552) of the second language based on the user input for determining text (552) of the second language.

[0093] Referring to FIGS. 5C and 5D , the processor (120) may be configured to display, in the region (530), text (553) of a first language inputted through a software keyboard (230) in the region (201) after text (552) of a second language is displayed, text (541) of a second language related to the text (553) of the first language and having the same style (e.g., polite style) as the text (552). The region (530) may be a preview region in which text having the same language and style as the text (552) is displayed, automatically output from the style conversion model (210) based on texts inputted after the text (552) is displayed in the region (201). The processor (120) is configured to display text input into an area (201) as text having a language and style specified through a style conversion model (210), thereby providing a variety of user experiences to the user.

[0094] Referring to FIGS. 5d and 5e, the processor (120) of the electronic device (101) may be configured to display the text (554) in the second language within the region (201) based on a user input (e.g., a touch input to the region (530)) for converting text (553) in the first language into text (554) in the second language having a designated style. For example, the processor (120) may be configured to display, but is not limited to, a visual object (561) for canceling the conversion of the text (554) in the second language within the region (203) and / or a visual object (562) for disabling the automatic conversion function into text in the designated language (e.g., Korean) or in the designated style (e.g., polite style) based on identifying the text (554) in the second language automatically converted from the text (553) in the first language through the style conversion model (210).

[0095] According to the above-described embodiment, the processor (120) of the electronic device (101) may provide a plurality of texts of a second language corresponding to a plurality of styles and related to the text of a first language (e.g., English) input through a software keyboard (230) using a style conversion model (210), thereby providing a variety of user experiences to the user. The processor (120) may be configured to automatically convert and display the text input through the software keyboard (230) in a preset style and / or language, thereby enhancing the convenience of the user.

[0096] Figures 6a, 6b, and 6c illustrate operations for transforming the style of text within an application of an exemplary electronic device.

[0097] Referring to FIGS. 6A, 6B, and 6C, the processor (120) of the electronic device (101) may be configured to display a software keyboard (230) through the display (220) while an application is running. The application may be referred to as a social application for multiple users to share media content.

[0098] Referring to FIGS. 6A and 6B, the processor (120) of the electronic device (101) may be configured to display text (651) input through a software keyboard (230) provided from a social application within an area (601) while the social application is running. The area (601) may be an area for creating or composing media content to be shared through the social application.

[0099] In one embodiment, the processor (120) may be configured to receive a request to generate text (651) related to the text (651) entered in the region (601) and having a style associated with a social application. For example, the processor (120) may be configured to display a visual object (211) in the region (602) indicating that it is generating text related to the text (651) and having a style associated with a social application while receiving the request.

[0100] For example, the processor (120) may be configured to identify whether the social application is included in a preset application group while the social application is running. Based on identifying that the social application is included in the application group, the processor (120) may provide a menu (e.g., a visual object (273)) for generating text that is related to the text (651) entered in the area (201) and has a different style from the text (651). For example, the processor (120) may be configured to display text (652) corresponding to a specified style (e.g., a social post style) using a style conversion model (210) based on identifying that the social application is included in a preset application group while the application is running.

[0101] According to one embodiment, the processor (120) may be configured to, in response to a request to generate text (651) associated with input text (651) in an area (201) and having a style associated with a social application, obtain text (652) having a style associated with the social application using the style conversion model (210). For example, the processor (120) may be configured such that, while the social application is running, texts input through the software keyboard (230) are converted and displayed as texts having a style associated with the social application. For example, the processor (120) may be configured such that, using the style conversion model (210), text (652) having a style associated with the social application (e.g., a social post style corresponding to the visual object (284) of FIG. 2D) is displayed in the area (602) based on text (651) input in the area (601). The text (652) displayed within the above region (602) may be displayed in place of the text (651) within the above region (601) based on a user input (e.g., a touch input to a visual object (620)) for determining the text (652).

[0102] For example, the processor (120) may be configured to display, through the display (220), a visual object (273) for selecting a style of the text (651) and / or a visual object (274) for translating the text (651) based on the text (651) entered in the area (601). For example, the processor (120) may be configured to display, through the display (220), a visual object (521) representing the automatic conversion while the text entered in the area (601) is set to be automatically converted into a specified style and a specified language.

[0103] According to the above-described embodiment, the processor (120) of the electronic device (101) is configured to provide text having a specified style and / or a specified language using the style conversion model (210), depending on the type and / or settings of the application running on the electronic device (101), thereby improving user convenience.

[0104] FIG. 7 is a signal flow chart for explaining an operation for converting the style of text of an exemplary electronic device.

[0105] The style conversion system of text illustrated in FIG. 7 may include an electronic device (101) and a style conversion model (210). The operations illustrated in FIG. 7 may be performed by the electronic device (101), a processor included in the electronic device (101) (e.g., the processor (120) of FIG. 1), the style conversion model (210), and / or an electronic device including the style conversion model (210) (e.g., the external electronic device (102) of FIG. 2A).

[0106] In operation (701), the processor (120) of the electronic device (101) may be configured to identify input of a first text (e.g., text (251) of FIG. 2B) via a software keyboard (230) while an application is running on the electronic device (101). For example, the processor (120) may be configured to identify text (251) input into an area for writing text within the application (e.g., area (201) of FIG. 2B) via a software keyboard (230) provided by the application.

[0107] In operation (703), the processor (120) of the electronic device (101) may be configured to input the input first text (251) and style information into the style conversion model (210) in response to a request to convert the style of the input first text (251). For example, the processor (120) may be configured to transmit, based on the text (251) input within the region (201), information for determining the text (251) and the style of the text (251) (e.g., text messages (241, 243) of FIG. 2B) to the style conversion model (210).

[0108] In operation (705), the style conversion model (210) may be configured to convert the style of text through a prompt corresponding to the style information based on the first text (251) and style information received from the electronic device (101). For example, the style conversion model (210) may be configured to generate a plurality of texts having substantially the same contextual meaning as the first text (251) and having a plurality of styles, using the first text (251) and the style information. For example, the style conversion model (210) may be configured to analyze a conversation style between a user and the counterpart based on a conversation list between the user and the counterpart within an application or personal information (e.g., phone number, ID, address, etc.) of the counterpart within the application. The style conversion model (210) may be configured to provide the user with a text having a designated style for the counterpart based on the analyzed conversation style. For example, the style conversion model (210) may be configured to provide a user with text in a specified style while the application is running on the electronic device (101) and is included in a preset application group on the electronic device (101).

[0109] In operation (707), the style conversion model (210) may be configured to transmit the second text (252) to the electronic device (101) based on the outputted second text (e.g., text (252) of FIG. 2d). For example, the style conversion model (210) may be configured to transmit a list (e.g., list (280) of FIG. 2d) including a plurality of texts including the second text (252) outputted using the first text (251) to the electronic device (101).

[0110] In operation (709), the processor (120) of the electronic device (101) may be configured to display the second text (252) on a screen provided through a display (e.g., the display (220) of FIG. 2B) based on receiving the second text (252). For example, the processor (120) may be configured to scrollably display a list (280) including a plurality of texts corresponding to a plurality of styles, including the second text (252), in an area for a software keyboard (230) (e.g., the area (202) of FIG. 2B).

[0111] In operation (711), the processor (120) of the electronic device (101) may be configured to execute a function for inputting third text (e.g., text (253) of FIG. 3b) and style information into the style conversion model (210) in response to input of third text (e.g., text (253) of FIG. 3b) through a software keyboard (230) provided by an application after second text (252) is provided through the screen of the display (220). For example, the processor (120) may be configured to transmit, based on text (253) input within an area (310) of FIG. 3a, information for determining the text (253) and the style of the text (253) (e.g., information related to the style of the previously input second text (252)) to the style conversion model (210).

[0112] In operation (713), the style conversion model (210) may be configured to convert the style of text through a prompt corresponding to the style information based on the third text (253) and style information received from the electronic device (101). For example, the style conversion model (210) may be configured to generate text having substantially the same contextual meaning as the third text (253) and the same style as the second text (252) using the third text (253) and the style information.

[0113] In operation (715), the style conversion model (210) may be configured to transmit the fourth text (254) to the electronic device (101) based on the outputted fourth text (e.g., the text (254) of FIG. 3c). For example, the style conversion model (210) may be configured to transmit the fourth text (254) having the same style as the second text (252), which is output using the third text (253), to the electronic device (101).

[0114] In operation (717), the processor (120) of the electronic device (101) may be configured to display the fourth text (254) on a screen provided through the display (220) based on receiving the fourth text (254). For example, the processor (120) may be configured to display the fourth text (254) having the same style as the second text (252) in the area (201) for text input of the application instead of the third text (253).

[0115] Figure 8 illustrates an operation of an exemplary electronic device to transform the style of text.

[0116] Referring to FIG. 8, the processor (120) of the electronic device (101) may be configured to display a software keyboard (230) through the display (220) while an application is running. The application may be referred to as a social network service application (SNS application) for conversation between multiple users.

[0117] According to one embodiment, while the application is running, a plurality of visual objects (861, 862, 863) corresponding to each of a plurality of users, and a plurality of text messages (841, 842, 843) transmitted from the plurality of users may be displayed within the area (203).

[0118] According to one embodiment, the processor (120) of the electronic device (101) may provide text having a style specified to the user by using information related to an application running within the electronic device (101) in FIG. 8 and another application (e.g., an application running within the electronic device (101) in FIG. 2B).

[0119] For example, among the visual objects (861, 862, 863), the counterpart corresponding to the visual object (862) may be the counterpart corresponding to the visual object (262) of FIG. 2B. The processor (120) may be configured to provide text in a designated style (e.g., polite style) using the style conversion model (210) through a conversation list with the counterpart corresponding to the visual object (262) and / or personal information of the counterpart in the message application of FIG. 2B while the SNS application of FIG. 8 is running. For example, the processor (120) may be configured to provide text (852) in a style related to the counterpart corresponding to the visual object (862) through the area (201) using the style conversion model (210) based on text (851) entered in the area (310). For example, the processor (120) may be configured to display a visual object (871) to distinguish a counterparty from another party providing text of a specified style within a conversation window including multiple users.

[0120] According to the above-described embodiment, the electronic device (101) is configured to provide text having a designated style for one of the plurality of users within an application for communication among the plurality of users, thereby providing the user with a variety of user experiences. The electronic device (101) can enhance user convenience by providing text having the designated style using information acquired through another application.

[0121] FIGS. 9A, 9B, 9C, and 9D illustrate operations of an exemplary electronic device to transform the style of text.

[0122] Referring to FIGS. 9A, 9B, 9C, and 9D, the processor (120) of the electronic device (101) may be configured to display a software keyboard (230) through the display (220) while an application is running. The application may be an application for sending an e-mail to a counterpart.

[0123] According to one embodiment, the processor (120) may display, through the display (220), an area (900a) for adding and displaying recipients, an area (900b) for adding and removing attachment files, and an area (900c) for writing the content of an email while the application is running. The area (900a) may include a visual object (961) for providing a list of email addresses of recipients. The area (900b) may include a visual object (962) for adding attachment files.

[0124] Referring to FIGS. 9A and 9B , text (951) can be entered within an area (900c) via a software keyboard (230). The text (951) can include sentences (951a, 951b, 951c). For example, referring to FIG. 9B , the processor (120) can be configured to, based on identifying that an email address (950) is input via the area (900a), provide text (952) having a specified style and associated with a counterpart corresponding to the email address (950). For example, the counterpart corresponding to the email address (950) of FIG. 9B can be the counterpart corresponding to the visual object (262) of FIG. 2B . The processor (120) may be configured to display text (952) having a designated style (e.g., polite style) related to the counterpart provided from the message application of FIG. 2b based on text (951) entered in the area (900c) and using the style conversion model (210). For example, the processor (120) may be configured to display a visual object (273) for changing the text style for the counterpart corresponding to the email address (950) and / or a visual object (274) for changing the language of the text in the area (202). For example, the processor (120) may be configured to display, through the area (202), text (952) that includes sentences (952a, 952b, 952c) that are related to each of the sentences (951a, 951b, 951c) entered in the area (201) and have a different style from each of the sentences (951a, 951b, 951c).For example, the processor (120) may control the display (220) to display a sentence (952a) having a different style (e.g., polite style) from the sentence (951a) in the area (202) using the style conversion model (210). For example, the processor (120) may control the display (220) to display a sentence (952b) having a different style from the sentence (951b) in the area (202) using the style conversion model (210). For example, the processor (120) may control the display (220) to display a sentence (952c) having a different style from the sentence (951c) in the area (202) using the style conversion model (210). However, the above-described embodiments are exemplary and are not limited thereto.

[0125] Referring to FIGS. 9b and 9c, the processor (120) may display a visual object (970) including visual objects (972, 973) for determining whether to provide and / or generate text in a specified style to a counterpart based on a user input to a visual object (965) for determining whether to transmit a file attached to an area (900b) and / or text written in an area (900c) to the counterpart corresponding to the email address (950), through the display (220). For example, the visual object (970) may include text (971) for indicating a counterpart corresponding to the email address (950) and for displaying the specified text, a visual object (972) for determining maintenance of the determined text style, and a visual object (973) for changing the determined text style.

[0126] Referring to FIGS. 9c and 9d, the processor (120) may be configured to display text (952) instead of text (951) within the area (900c) based on a user input for selection of any one of the visual objects (972, 973). The processor (120) may be configured to send an email including the text (952) to an email address (950) based on a user input to a visual object (965).

[0127] FIGS. 10A, 10B, 10C, 10D, 10E, and 10F illustrate operations of an exemplary electronic device to transform the style of text.

[0128] Referring to FIGS. 10A, 10B, 10C, 10D, 10E, and 10F, the processor (120) of the electronic device (101) may be configured to display a software keyboard (230) through the display (220) while an application is running. The application may be an application for sending a text message to a counterpart or receiving a text message from the counterpart.

[0129] Referring sequentially to FIGS. 10A and 10B , the processor (120) may be configured to display text (1051) entered through a software keyboard (230) (or area (202)) within an area (201) while an application is running. The processor (120) may be configured to display visual objects (1021, 1022) to provide a menu for converting the style of the text (1051) entered within the area (201) or correcting grammatical errors in the text (1051), based on a user input via a visual object (1015). For example, the processor (120) may be configured to display a visual object (1021) for transforming the style of text (1051) displayed within the area (201), and a visual object (1022) for correcting grammatical errors in the text (1051), based on user input to the visual object (1015), instead of the software keyboard (230).

[0130] Referring sequentially to FIGS. 10b and 10c, the processor (120) may be configured to receive, based on a user input to a visual object (1021) for converting the style of text (1051) entered in an area (201), a request to generate other texts related to the text (1051) and having a different style than the text (1051). The processor (120) may be configured to execute a function for inputting information related to the text (1051) and a running application (e.g., information related to the other party of a text message) into a style conversion model (e.g., the style conversion model (210) of FIG. 2a), based on receiving, through the visual object (1021), a request to generate other texts related to the text (1051) and having a different style than the text (1051).

[0131] According to one embodiment, the processor (120) may be configured to display a visual object (1016) and text (e.g., text (1033)) within the region (202) while generating other texts related to the text (1051) displayed within the region (201) and having a different style than the text (1051) using the style conversion model (210) to indicate that the other texts are being generated. The text displayed to indicate that the other texts are being generated within the region (202) may vary depending on a style determined through a user input. For example, based on a user input corresponding to all styles provided from the style conversion model (e.g., a touch input to the All tone menu), the processor (120) may be configured to display one of the texts (1031, 1032, 1033) within the region (202). For example, based on a user input corresponding to a professional style (e.g., a touch input to a professional menu) provided from the style conversion model (210), the processor (120) may be configured to display text (1034) within the region (202). For example, based on a user input corresponding to a casual style (e.g., a touch input to a casual menu) provided from the style conversion model (210), the processor (120) may be configured to display text (1035) within the region (202). For example, based on a user input corresponding to a social post style (e.g., a touch input to a social post menu) provided from the style conversion model (210), the processor (120) may be configured to display text (1036) within the region (202).For example, based on a user input corresponding to a polite style and / or an original style (e.g., a touch input to a polite menu and / or an original menu) provided from the style conversion model (210), the processor (120) may be configured to display text (1037) within the region (202). For example, based on a user input corresponding to a witty style (e.g., a touch input to a witty menu) provided from the style conversion model (210), the processor (120) may be configured to display text (1038) within the region (202). However, the above-described embodiments are exemplary and not limited thereto, and the text indicating that text related to the text (1051) input within the region (201) with the style determined by the user input is being generated may have various embodiments other than the texts included in the list (1030).

[0132] Referring to FIGS. 10d and 10e, the processor (120) may be configured to scrollably display a list (1040) within an area (202) that includes visual objects (1041, 1042, 1043, 1044) that are related to text (1051) and each include other texts having a different style than the text (1051). For example, the visual objects (1041, 1042, 1043, 1044) may include a visual object (1061) for copying texts displayed within each of the visual objects (1041, 1042, 1043, 1044) to temporarily store them within a memory (e.g., volatile memory (132) of FIG. 1), and / or a visual object (1062) for inserting texts displayed within each of the visual objects (1041, 1042, 1043, 1044) into an area (201) instead of text (1051).

[0133] Referring sequentially to FIGS. 10E and 10F, the processor (120) may be configured to receive user input to a visual object (1062) for determining text (1052) including an emoticon object (1052a) within a visual object (1044). The processor (120) may be configured to delete the text (1051) within the region (201) and display the text (1052) based on receiving the user input to the visual object (1062) for determining the text (1052). The processor (120) may be configured to display a software keyboard (230) instead of a list (1040) within the region (202). Although not shown, the processor (120) may be configured to transmit the text (1052) (or a text message including the text (1052)) to the other party's terminal or display the text (1052) within the area (203) based on a user input to a visual object (265) for determining transmission of the text (1052) displayed within the area (201).

[0134] Figures 11a, 11b, 11c, and 11d illustrate operations of an exemplary electronic device to correct errors in text.

[0135] Referring to FIGS. 11A, 11B, 11C, and 11D, the processor (120) of the electronic device (101) may be configured to display a software keyboard (230) through the display (220) while an application is running. The application may be an application for sending a text message to a counterpart or receiving a text message from the counterpart.

[0136] Referring sequentially to FIGS. 11A and 11B , the processor (120) may control the display (220) to display, in the area (202), a visual object (1121) for translating the text (1051) into another language, a visual object (1122) for converting the style of the text (1051), and a visual object (1023) for correcting grammatical errors in the text (1051), based on text (1051) entered into the area (201) through the software keyboard (230), instead of the software keyboard (230). The processor (120) may further control the display (220) to display an area (1101) for displaying text entered through the software keyboard (230). The area (1101) may be, for example, an area for translating text entered into the area (1101) into another language. The processor (120) may control the display (220) to display a visual object (1105) for indicating a translation language of text entered in the region (1011). For example, the processor (120) may be configured to perform a function for generating other texts related to the text (1051) and having a different style from the text (1051) based on text (1051) entered in the region (201) and user input to the visual object (1122). For example, the processor (120) may be configured to perform a function for correcting grammatical errors in the text (1051) based on text (1051) entered in the region (201) and user input to the visual object (1123). For example, the processor (120) may be configured to perform a function for translating the text entered in the area (1101) into another language based on user input entered in the area (1101). However, the above-mentioned embodiments are exemplary and are not limited thereto.

[0137] According to one embodiment, the processor (120) may be configured to perform a function for correcting grammatical errors in text (1051) entered in the region (201) based on user input to a visual object (1123). The processor (120) may control the display (220) to display a visual object (1131) and / or text (1132) within the region (202) indicating that the grammatical error is being corrected while correcting the grammatical error in the text (1051) or generating another text with the grammatical error corrected.

[0138] Referring sequentially to FIGS. 11B and 11C , the processor (120) may be configured to display text (1052) in which grammatical errors are corrected from text (1051) within an area (202). The processor (120) may control the display (220) to display a visual object (1131) for copying the text (1052) in which grammatical errors are corrected within the area (202) for temporary storage in a memory (e.g., the volatile memory (132) of FIG. 1), and / or a visual object (1132) for inputting the text (1052) in which grammatical errors are corrected instead of the text (1051) containing grammatical errors into the area (201).

[0139] Referring sequentially to FIGS. 11C and 11D , the processor (120) may control the display (220) to display text (1052) with a corrected grammatical error within a region (1102) distinct from the region (201) and the region (1101), based on receiving a user input to the visual object (1132). The region (1102) may be a region for pre-displaying text (1052) copied from the region (202) based on the user input. The processor (120) may control the display (220) to display text (1052) with a corrected grammatical error instead of text (1051) including a grammatical error within the region (201), based on the user input to the visual object (1132).

[0140] Figures 12a, 12b, 12c, and 12d illustrate operations of an exemplary electronic device to convert the style and language of text.

[0141] Referring to FIGS. 12a, 12b, 12c, and 12d, the processor (120) of the electronic device (101) may be configured to display a software keyboard (230) through the display (220) while an application is running. The application may be an application for sending a text message to a counterpart or receiving a text message from the counterpart.

[0142] Referring sequentially to FIGS. 12A and 12B , the processor (120) may control the display (220) to display a visual object (1215) for translation of text (1251) input through a software keyboard (230) within an area (201) together with the software keyboard (230) within an area (202). The processor (120) may be configured to perform a function for translating the text (1251) in a first language (e.g., Korean) into text (1252) in a second language (e.g., English) that has substantially the same contextual meaning as the text (1251) and is different from the first language, based on a user input to the visual object (1215). For example, the processor (120) may control the display (220) to display, based on user input to the visual object (1215), text (1252) related to the text (1251) and having a second language within the region (201), instead of the text (1251) in the first language. The processor (120) may control the display (220) to display the region (1201) for displaying the text (1251) and a visual object (1105) for indicating the second language. The processor (120) may control the display (220) to display a visual object (1211) for determining an automatic translation of the text entered within the region (201) into the second language and / or a visual object (1212) for determining a translation language of the text entered within the region (201).

[0143] Referring sequentially to FIGS. 12b and 12c, the processor (120) may control the display (220) to display, in the area (202), instead of the software keyboard (230), a visual object (1221) for generating other texts related to the text (1252), having the second language, and having a different style than the text (1252), based on a user input to a visual object (1015) for style conversion of the text (1252) of the second language entered in the area (201). The visual object (1221) for generating other texts having a different style than the text (1252) and / or a visual object (1222) for correcting grammatical errors in the text (1252).

[0144] Referring sequentially to FIGS. 12C and 12D , the processor (120) may be configured to perform a function for generating texts (1252) in a second language within an area (201) that are related to the text (1252) within the area (201), that have the second language, and that have a different style than the text (1252), based on a user input to a visual object (1221), using a style conversion model (e.g., the style conversion model (210) of FIG. 2A ). The processor (120), based on the performance of the function, may control the display (220) to scrollably display, in the area (202), visual objects (1241, 1242) (or a list (1240) including visual objects (1241, 1242)), each including texts (1252) in the area (202), that are related to the text (1252), that have the second language, and that have a different style than the text (1252).

[0145] FIG. 13 is an exemplary block diagram illustrating a generative artificial intelligence system according to an embodiment. In FIG. 13, an exemplary artificial intelligence system is illustrated, including a user question response interface (1310), an AI framework (1320), a generative AI model (1330) (e.g., the style conversion model (210) of FIG. 2A), a knowledge repository (1340), and an application / service component (1350). According to an embodiment, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) may execute one or more programs defined by the blocks of FIG. 13 to execute functions related to generative artificial intelligence.

[0146] In one embodiment, a User Query / Response Interface (1310) can receive user input. The user input may be in the form of natural language, images, and / or videos. Context information may also be transmitted when the user input is transmitted. Context information may include various additional information at the time of user input. For example, information about the application currently being used by the user or information about the user's location. Furthermore, the user input may be in a mixed form of the aforementioned natural language, images, sounds, and context information. Furthermore, the user input may be in a non-natural language form, such as selecting a menu. The User Query / Response Interface (1310) can output the results of a generative artificial intelligence system to the user. The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user. The User Query / Response Interface (1310) can output the results of a generative artificial intelligence system to the user. The output can be in natural language form, in the form of specific content, or in the form of actions requested by the user.

[0147] The AI ​​framework (1320) can receive user input and coordinate and control each component necessary to perform the user's intent based on the user's query. The AI ​​framework (1320) can include a prompt design component (1321), an API / plug-in management component (1322), and a refinery component (1323).

[0148] User input received from the user question response interface (1310) can be transmitted to the prompt design component (1321). The prompt design component (1321) can be used to generate prompts suitable for inputting the user input into an LLM or LMM (Large Multimodal Model). The prompt design component (1321) can be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The prompt design component (1321) can access knowledge repositories (1340) containing user preference data, a prompt library, and prompt examples based on the user input to generate prompts and transmit the generated prompts to the LLM or LMM.

[0149] The API / plugin management component (1322) can communicate with external information when there is a request for additional information when passing user input as input to the generative model. The API / plugin management component (1322) can establish a channel for communicating with the outside of the AI ​​framework (1320) through an application programming interface (API) and can enable access to various data sources through the established channel. In addition, the API / plugin management component (1322) can request an action through the API that ultimately performs the user input, rather than an intermediate result, when the action needs to be performed by the application / service component (1350) (e.g., the program (140) or application (146) of FIG. 1). Information obtained from the outside can be used to generate a prompt in the prompt design component (1321) together with the user input or can be passed as input to the generative model.

[0150] The refinement component (1323) (or output modification component) can fine-tune the output from the generative AI model (1330). For example, the refinement component (1323) can verify whether the content generated through the LLM and / or LMM is irrelevant, biased, or harmful. In addition, the refinement component (1323) can determine to what extent the content matches the user's desired result and, if necessary, perform additional processing. The refinement component (1323) can additionally configure and provide hints to the user to avoid undesired output.

[0151] A generative AI model (1330) may generally refer to an artificial intelligence neural network that creates new types of data based on user input information. The generative AI model (1330) 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 auto encoder (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 are also large multimodal models (LMMs) that can recognize various types of data input, such as text, images, and voice, and generate new data corresponding to them.

[0152] According to the above-described embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may include a display (e.g., display (220) of FIG. 2b), at least one processor including a processing circuit (e.g., processor (120) of FIG. 1), and a memory (e.g., memory (130) of FIG. 1) including one or more storage media for storing instructions. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, on the display, a software keyboard (e.g., software keyboard (230) of FIG. 2b) provided by an application while the application is running on the electronic device. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive a request for generating other texts related to first text (e.g., text (251) of FIG. 2b) entered via the software keyboard. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device, in response to the request, to obtain a plurality of texts, using a style conversion model (e.g., style conversion model (210) of FIG. 2a), that are associated with the first text, correspond to a plurality of styles, and include at least one text grouped with one or more emoticon objects (e.g., emoticon objects (255a, 256a) of FIG. 2d). The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, through the display, at least a portion of a list (e.g., list (280) of FIG. 2d) including the plurality of texts.

[0153] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, in a second area (e.g., area (202) of FIG. 2b) for the software keyboard, a visual object (e.g., visual object (271) of FIG. 2c) indicating that other texts related to the first text are being generated based on the first text entered in a first area (e.g., area (201) of FIG. 2b) of a screen provided through the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to scrollably display, in the second area, at least a portion of the list including the plurality of texts, based on obtaining the plurality of texts.

[0154] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, through the display, a visual object (e.g., the visual object (273) of FIG. 2D) for style conversion of the first text based on the first text input through the software keyboard. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, through the display, a list including the plurality of styles based on the input for style conversion of the first text through the visual object.

[0155] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive a request for generating texts in a second language, different from the first language, related to the first text in the first language, based on the first text in the first language input via the software keyboard. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, in response to the request for generating the texts in the second language, obtain, using a style conversion model, the plurality of texts in the second language, the plurality of texts being related to the first text, corresponding to the plurality of styles, and including at least one text grouped with one or more emoticon objects. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, through the display, at least a portion of a list including the plurality of texts in the second language.

[0156] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, through the display, a visual object (e.g., the visual object (274) of FIG. 2D) for converting a language and style of the first text based on the first text input through the software keyboard. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display, through the display, a list including a plurality of languages ​​in which the plurality of styles are provided, based on the input for converting the language and style of the first text through the visual object.

[0157] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, in response to first text entered via the software keyboard, display the first text in a first area within a screen for text input provided from the application. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, in response to receiving an input for determining a second text having a first style from among the plurality of texts, display the second text in the first area in place of the first text.

[0158] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive a request to generate another text related to the third text (e.g., text (253) of FIG. 3b) entered via the software keyboard after the second text is displayed in the first area. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, in response to the request to generate the another text related to the third text, display, in the first area, a fourth text related to the third text and having the first style (e.g., text (254) of FIG. 3c), using a style conversion model.

[0159] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, based on receiving the input for determining the second text having the first style, display a third area (e.g., area (310) of FIG. 2A) on the display for displaying text entered via the software keyboard after the first text has been entered. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, based on third text entered within the third area, use the style conversion model to display a fourth text within the first area that is related to the third text and has the first style.

[0160] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to execute a function for inputting data related to the application and the first text into the style conversion model based on receiving a request to generate the other texts related to the first text.

[0161] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to detect grammatical errors in the first text based on the first text entered via the software keyboard. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, in response to a request to generate other texts related to the first text, obtain, through a plurality of prompts stored in the style conversion model, the plurality of texts corresponding to the plurality of styles and having the errors corrected.

[0162] According to one embodiment, a method of an electronic device may include an operation of displaying a software keyboard provided by an application on a display of the electronic device while the application is running on the electronic device. The method may include an operation of receiving a request for generating other texts related to a first text input through the software keyboard based on the first text. The method may include an operation of obtaining, in response to the request, a plurality of texts using a style conversion model, the plurality of texts being related to the first text, corresponding to a plurality of styles, and including at least one text in which one or more emoticon objects are grouped. The method may include an operation of displaying at least a portion of a list including the plurality of texts through the display.

[0163] For example, the method may further include an action of displaying a visual object indicating that other texts related to the first text are being generated in a second area for the software keyboard based on the first text entered in a first area of ​​a screen provided through the display. The action of displaying at least a portion of the list through the display may include an action of scrollably displaying at least a portion of the list including the plurality of texts in the second area based on obtaining the plurality of texts.

[0164] For example, the method may include an operation of displaying a visual object for style conversion of the first text through the display based on the first text input through the software keyboard. The method may further include an operation of displaying a list including the plurality of styles through the display based on the input for style conversion of the first text through the visual object.

[0165] For example, the method may further include receiving a request for generating texts in a second language, different from the first language, related to the first text based on the first text in the first language input through the software keyboard. The method may further include, in response to the request, obtaining, using a style conversion model, a plurality of texts in the second language, the plurality of texts being related to the first text, corresponding to the plurality of styles, and including at least one text in which one or more emoticon objects are grouped. The method may further include displaying, through the display, at least a portion of a list including the plurality of texts in the second language.

[0166] For example, the method may further include an operation of displaying a visual object for converting a language and style of the first text through the display based on the first text input through the software keyboard. The operation of displaying at least a portion of a list including the plurality of texts in the second language through the display may include an operation of displaying a list including a plurality of languages ​​in which the plurality of styles are provided through the display based on an input for converting the language and style of the first text through the visual object.

[0167] For example, the method may further include an action of displaying, in response to a first text input via the software keyboard, the first text in a first area within a screen for text input provided from the application. The method may further include an action of displaying, in response to receiving an input for determining a second text having a first style from among the plurality of texts, the second text in place of the first text in the first area.

[0168] For example, the method may further include receiving a request for generating another text related to the third text based on the third text input via the software keyboard after the second text is displayed in the first area. The method may further include, in response to the request for generating the another text, displaying a fourth text related to the third text and having the first style within the first area using a style conversion model.

[0169] For example, the method may further include an operation of displaying, through the display, a third area for displaying text input through the software keyboard after the first text is input, based on receiving the input for determining the second text having the first style. The method may further include an operation of displaying, through the display, a fourth text related to the third text and having the first style, using the style conversion model, based on the third text input within the third area.

[0170] For example, the method may further include an action of executing a function for inputting data related to the application and the first text into the style conversion model based on receiving a request to generate other texts related to the first text.

[0171] In one embodiment, a non-transitory computer readable storage medium storing one or more programs may include instructions that, when executed by at least one processor of an electronic device having a display, cause the electronic device to display a software keyboard provided by the application on the display while the application is running on the electronic device. The one or more programs may include instructions that, when executed by the at least one processor, cause the electronic device to receive a request for generating other texts related to first text, based on first text input via the software keyboard. The one or more programs may include instructions that, when executed by the at least one processor, cause the electronic device to obtain, in response to the request, a plurality of texts, using a style conversion model, that are related to the first text, that correspond to a plurality of styles, and that include at least one text in which one or more emoticon objects are grouped. The one or more programs may include instructions that, when executed by the at least one processor, cause the electronic device to display at least a portion of a list containing a plurality of texts through the display.

[0172] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, electronic devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0173] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0174] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0175] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0176] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0177] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In electronic devices, display; At least one processor comprising a processing circuit; and A memory comprising one or more storage media storing instructions, said instructions, when individually or collectively executed by said processor, causing said electronic device to: While the application is running on the electronic device, display a software keyboard on the display; Receive a request to generate other texts related to the first text based on the first text entered via the software keyboard; In response to the request, a style conversion model for generating text is used to obtain a plurality of texts, which are related to the first text, correspond to a plurality of styles, and include at least one text in which one or more emoticon objects are grouped; Causing at least a portion of a list containing said plurality of texts to be displayed through said display; Electronic devices.

2. In paragraph 1, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Displaying a visual object indicating that other texts related to the first text are being generated in a second area for the software keyboard based on the first text entered in the first area of ​​the screen provided through the display; Based on obtaining the plurality of texts, causing at least a part of the list including the plurality of texts to be scrollably displayed in the second area. Electronic devices.

3. In paragraph 1 or 2, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Based on the first text entered through the software keyboard, a visual object for style conversion of the first text is displayed through the display; Causing a list including the plurality of styles to be displayed through the display based on the input for the style transformation of the first text through the visual object. Electronic devices.

4. In any one of paragraphs 1 to 3, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Receiving a request to generate texts in a second language different from the first language related to the first text based on the first text in the first language input through the software keyboard; In response to the request to generate the texts in the second language, using a style conversion model, obtaining the plurality of texts in the second language, wherein the plurality of texts are related to the first text, correspond to the plurality of styles, and include at least one text in which one or more emoticon objects are grouped; causing at least a portion of a list containing said plurality of texts in said second language to be displayed through said display; Electronic devices.

5. In paragraph 4, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Based on the first text entered through the software keyboard, a visual object for converting the language and style of the first text is displayed through the display; Causing to display a list including a plurality of languages ​​in which the plurality of styles are provided, through the display, based on an input for conversion of the language and the style of the first text through the visual object; Electronic devices.

6. In any one of paragraphs 1 to 5, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: In response to a first text entered via the software keyboard, displaying the first text in a first area within a screen for text input provided from the application; In response to receiving an input for determining a second text having a first style among the plurality of texts, causing the second text to be displayed in the first area instead of the first text, Electronic devices.

7. In paragraph 6, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: After the second text is displayed in the first area, a request is received to generate another text related to the third text based on the third text input through the software keyboard; In response to the request to generate the other text related to the third text, using a style transformation model, causing a fourth text related to the third text and having the first style to be displayed within the first region. Electronic devices.

8. In paragraph 6, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Based on receiving the input for determining the second text having the first style, a third area for displaying text input via the software keyboard after the first text is input is displayed via the display; Based on the third text entered in the third area, using the style conversion model, a fourth text related to the third text and having the first style is displayed in the first area. Electronic devices.

9. In any one of paragraphs 1 to 8, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Based on receiving a request to generate said other texts related to said first text, causing a function to be executed for inputting data related to said application and said first text into said style conversion model. Electronic devices.

10. In any one of paragraphs 1 to 9, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Based on the first text entered through the software keyboard, detecting grammatical errors in the first text; In response to a request to generate said other texts related to said first text, causing a plurality of texts corresponding to said plurality of styles and having said errors corrected to be obtained through a plurality of prompts stored in said style conversion model. Electronic devices.

11. In the method of an electronic device, An action of displaying a software keyboard on the display of said electronic device while an application is running on said electronic device; An action of receiving a request to generate other texts related to a first text, based on a first text entered via the software keyboard; In response to the request, an operation of obtaining a plurality of texts, wherein the plurality of texts are related to the first text, correspond to a plurality of styles, and include at least one text in which one or more emoticon objects are grouped, using a style transformation model for generating text; and Comprising an action of displaying at least a portion of a list containing the plurality of texts through the display; method.

12. In paragraph 11, Further comprising an action of displaying a visual object indicating that other texts related to the first text are being generated in a second area for the software keyboard based on the first text entered in the first area of ​​the screen provided through the display; The action of displaying at least a portion of the above list through the above display is: Based on obtaining the plurality of texts, the method comprises an action of scrollably displaying at least a portion of the list including the plurality of texts in the second area. method.

13. In paragraph 11 or 12, An action of displaying a visual object for style conversion of the first text through the display based on the first text input through the software keyboard; and Further comprising an action of displaying a list including the plurality of styles through the display based on an input for style transformation of the first text through the visual object. method.

14. In any one of paragraphs 11 to 13, An action of receiving a request to generate texts in a second language different from the first language related to the first text based on the first text in the first language input through the software keyboard; In response to the request, an operation of obtaining a plurality of texts in the second language, the plurality of texts being related to the first text, corresponding to the plurality of styles, and including at least one text in which one or more emoticon objects are grouped, using a style conversion model; and Further comprising an action of displaying at least a portion of a list containing said plurality of texts in said second language through said display; method.

15. In paragraph 14, Further comprising an action of displaying a visual object for converting the language and style of the first text through the display based on the first text input through the software keyboard; An action of displaying at least a portion of a list containing said plurality of texts in said second language through said display, An operation of displaying a list including a plurality of languages ​​in which the plurality of styles are provided, through the display, based on an input for conversion of the language and the style of the first text through the visual object. method.

Images