Method and electronic device for providing personalized text

Abstract

An electronic device is disclosed. The present electronic device may: display an execution screen of an application on a display; when a user input for generating personalized text on the basis of text input to the execution screen of the application is received, acquire style information corresponding to the application from among style information corresponding to each of a plurality of applications stored in a memory; acquire the personalized text by inputting, to an artificial intelligence model, a prompt acquired on the basis of the style information corresponding to the application and the input text; and display the personalized text on the execution screen of the application. The style information corresponding to each of the plurality of applications may be obtained on the basis of text previously input to each of the plurality of applications.

Description

Method and electronic device for providing personalized text

[0001] The present disclosure relates to a method and an electronic device for generating personalized text and providing it to a user.

[0002] Generative AI is a technology that learns the structure and patterns of large-scale data and generates new data based on input data. Generative AI can generate a variety of data, such as text and images.

[0003] According to one embodiment, an electronic device includes a display, a memory storing instructions, and at least one processor including a processing circuit. When the instructions are individually or collectively executed by the at least one processor, the electronic device may display an execution screen of an application on the display, and when a user input for generating personalized text based on text entered on the execution screen of the application is received, acquire style information corresponding to the application from among style information corresponding to each of a plurality of applications stored in the memory, input a prompt obtained based on the style information corresponding to the application and the entered text into an artificial intelligence model to acquire the personalized text, and display the personalized text on the execution screen of the application. The style information corresponding to each of the plurality of applications may be acquired based on text previously entered into each of the plurality of applications.

[0004] A personalized text providing method of an electronic device according to one embodiment may include an operation of displaying an execution screen of an application, an operation of obtaining style information corresponding to an application from among style information corresponding to each of a plurality of applications stored in a memory of the electronic device when a user input for generating personalized text based on text entered on the execution screen of the application is received, an operation of obtaining the personalized text by inputting a prompt obtained based on the style information corresponding to the application and the entered text into an artificial intelligence model, and an operation of displaying the personalized text on the execution screen of the application. The style information corresponding to each of the plurality of applications may be obtained based on text previously entered into each of the plurality of applications.

[0005] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0006] FIG. 2 illustrates an example block diagram of an electronic device according to one embodiment.

[0007] FIG. 3 is a diagram illustrating an operation of an electronic device according to one embodiment of the present invention to map and store text input into an application.

[0008] Figure 4 illustrates an example of text mapped to an application according to one embodiment.

[0009] FIG. 5 is a diagram illustrating an operation of an electronic device according to one embodiment of the present invention to map and store text input into an application.

[0010] FIG. 6 is a diagram illustrating an operation of an electronic device according to one embodiment of the present invention to store text entered into an application based on the number of texts mapped to the application.

[0011] FIG. 7 is a diagram for explaining an operation of an electronic device according to one embodiment of the present invention to obtain style information.

[0012] FIGS. 8A, 8B, and 8C are diagrams illustrating an example of an operation of an electronic device according to one embodiment of the present invention to identify whether the number of texts mapped to identification information of an application is greater than or equal to a preset number.

[0013] FIGS. 9A and 9B illustrate examples of style information generated by an artificial intelligence model according to one embodiment.

[0014] FIG. 10 is a diagram illustrating an example of an operation of an electronic device storing style information according to one embodiment.

[0015] FIG. 11 is a diagram illustrating an example of an operation of an electronic device storing style information according to one embodiment.

[0016] FIG. 12 is a diagram illustrating an operation of an electronic device providing personalized text using style information according to one embodiment.

[0017] FIGS. 13a, 13b, 13c, and 13d are drawings illustrating an example of an electronic device providing personalized text according to one embodiment.

[0018] FIGS. 14A and 14B are diagrams illustrating an operation of an electronic device providing personalized text using style information according to one embodiment.

[0019] FIG. 15 is a diagram illustrating an example of an electronic device providing personalized text according to one embodiment.

[0020] FIG. 16 is a diagram illustrating an example of an operation in which an electronic device provides style information according to one embodiment.

[0021] FIGS. 17A, 17B, and 17C are diagrams illustrating an example of an operation of an electronic device generating personalized text according to one embodiment.

[0022] FIGS. 18a, 18b, 18c, 18d, and 18e are diagrams illustrating an example of an operation of an electronic device generating personalized text according to one embodiment.

[0023] Figure 19 is a diagram for explaining a generative artificial intelligence model according to one embodiment.

[0024] Hereinafter, the present disclosure will be described in detail with reference to the attached drawings.

[0025] 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, wearable devices, or home appliances. Electronic devices according to the embodiments of this disclosure are not limited to the aforementioned devices.

[0026] 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.

[0027] Throughout this specification, singular expressions include plural expressions unless the context clearly dictates otherwise. When a part of this specification refers to "including" a component, this does not exclude other components, but rather implies the inclusion of other components, unless otherwise specifically stated.

[0028] 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).

[0029] The present disclosure relates to a method for generating personalized text by incorporating a user's personalized characteristics when generating text based on a user's request using an artificial intelligence model. According to an embodiment of the present disclosure, text tailored to the user can be obtained by incorporating characteristics acquired from previously written text by the user into the inference (e.g., text generation) of the artificial intelligence model.

[0030] In the present disclosure, the AI ​​model may be a generative model. For example, generative AI may refer to an AI technology capable of generating new text, images, etc. in response to input data (e.g., text, images, etc.). A generative model may refer to an AI model that implements generative AI technology. By learning the patterns and structure of training data, a generative model can generate new data with similar characteristics to the input data or new data corresponding to the input data.

[0031] In this disclosure, the AI ​​model may be a large language model (LLM). An LLM is a type of generative model that can be trained based on large amounts of training data. For example, an LLM can understand the context, structure, and meaning of language and perform various language tasks, such as text generation, translation, summarization, and question answering.

[0032] In the present disclosure, personalized text may refer to text generated using an AI model in response to a user's text generation request. Furthermore, personalized text may refer to text generated by an AI model that reflects the characteristics of text previously written by the user. The personalized text may be generated to include the user's personalized characteristics (e.g., the user's characteristics and the characteristics of sentences written by the user). The personalized text may also be referred to as "custom text."

[0033] In the present disclosure, a prompt may refer to an input for initiating an interaction with an artificial intelligence model. The prompt may be a text input including one or more words and / or one or more sentences. For example, the prompt may include natural language text. The natural language text may include various information that can be utilized by the artificial intelligence model, such as context, intent, task, and constraints. For example, the prompt may include a description of a task to be performed by the artificial intelligence model or a question for requesting information from the artificial intelligence model. The electronic device may process natural language text using a natural language processing (NLP) model.

[0034] In the present disclosure, the term “predetermined” may be replaced with expressions such as “specified” and “predefined,” for example.

[0035] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0036] 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)).

[0037] 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 calculations. According to one embodiment, as at least a part of the data processing or calculations, 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 a secondary 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 therewith. For example, if the electronic device (101) includes a main processor (121) and a secondary processor (123), the secondary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a specified function. The secondary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0038] 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.

[0039] 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).

[0040] 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).

[0041] 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).

[0042] 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.

[0043] 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. In 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.

[0044] 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).

[0045] 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.

[0046] 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.

[0047] 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).

[0048] A 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. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0049] 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.

[0050] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least a part of a power management integrated circuit (PMIC).

[0051] 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.

[0052] 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).

[0053] 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.

[0054] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one 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).

[0055] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent 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.

[0056] 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)).

[0057] 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 technologies may be utilized, for example.

[0058] The electronic device (101) can provide ultra-low latency services, for example, by utilizing distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server 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 a second network (199). The electronic device (101) may be applied to intelligent services (e.g., smart homes, smart cities, smart cars, or healthcare) based on 5G communication technology and IoT-related technology.

[0059] FIG. 2 illustrates an example block diagram of an electronic device according to one embodiment. The electronic device (200) of FIG. 2 may include the electronic device (101) of FIG. 1. The electronic device (200) of FIG. 2 may include at least one component among the components of the electronic device (101) illustrated in FIG. 1. The components, their relationships, and their functions illustrated in FIG. 2 are merely exemplary and do not limit the implementations described or claimed within this document.

[0060] The electronic device (200) may include at least one processor (210) (hereinafter, referred to as processor (210)), at least one memory (220) (hereinafter, referred to as memory (220)), and at least one display (230) (hereinafter, referred to as display (230)). The processor (210), the memory (220), and the display (230) of FIG. 2 may be implemented substantially identically to the processor (120), the memory (130), and the display module (160) of FIG. 1, respectively, and thus may perform the same functions. The components of FIG. 2 are merely exemplary. For example, the electronic device (200) may include other components (e.g., at least one image sensor, at least one communication circuit, at least one sensor, power management integrated circuitry (PMIC), audio processing circuitry, an antenna, a rechargeable battery, and / or an input / output interface). For example, some components may be omitted from the electronic device (200). For example, several components can be combined into one component.

[0061] The processor (210) can control the overall operations of the electronic device (200). For example, the processor (210) can be operatively connected to the memory (220) and the display (230) to control the operations of the electronic device (200). In addition, the processor (210) can control the operations of the electronic device (200) according to the present disclosure by executing one or more instructions stored in the memory (220). The processor (210) can be composed of one or more processors.

[0062] The processor (210) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing. The processor (210) may include at least one electrical circuit and may individually or collectively perform distributed processing of instructions (or programs, data, etc.) stored in the memory (220). The processor (210) may include a processor assembly including one or more processing circuits. The processor (210) may include any processing circuit operative to control the performance and operations of one or more components (e.g., the memory (220), the display (230)) of the electronic device (200). For example, the processor (210) (e.g., an application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or chipset). For example, the processor (210) may be implemented as multiple cores (or at least one core circuit), multiple chips, or multiple chipsets. For example, the processor (210) may include one or more processing circuits. For example, the processor (210) may include one or more processing circuits configured to individually and / or collectively perform various functions of the present disclosure. As a non-limiting example, at least a portion of the processor (210) may be included in a first chip of the electronic device (200), and at least another portion of the processor (210) may be included in a second chip of the electronic device (200) that is different from the first chip of the electronic device (200).

[0063] For example, the processor (210) may include a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), an image signal processor (ISP), a display controller, a memory controller, a storage controller, a communication processor (CP), and / or a sensor interface. These components of the processor (210) are merely exemplary. For example, the processor (210) may further include other components. For example, some components of the processor (210) may be omitted from the processor (210). For example, some components of the processor (210) may be included as separate components of the electronic device (200) outside the processor (210). For example, some components of the processor (210) (e.g., a memory controller) may be included within other components (e.g., at least a portion of the memory (220), an interface (e.g., available for connecting to at least one component of the electronic device (200), the display (230)).

[0064] The processor (210) may cause other components of the electronic device (200) to perform various operations by executing instructions stored in the memory (220). The CPU (or central processing circuit) may be configured to control components of the processor (210) based on the execution of instructions stored in the memory (220) (e.g., volatile memory and / or non-volatile memory). The GPU (or graphics processing circuit) may be configured to perform parallel operations (e.g., rendering). The NPU (or neural processing circuit, or AI (artificial intelligence) chip) may be configured to perform operations for an artificial intelligence model (e.g., convolution computation). The ISP (or image signal processing circuit) may be configured to process a raw image acquired through an image sensor into a format suitable for components within the electronic device (200) or components of the processor (210). A display controller (or display control circuit, or display processing unit (DPU)) may be configured to process an image acquired from a CPU, GPU, ISP, or memory (220) (e.g., volatile memory) into a format suitable for the display (230). A memory controller (or memory control circuit) may be configured to control reading data from volatile memory and writing data to volatile memory. A storage controller (or storage control circuit) may be configured to control reading data from non-volatile memory and writing data to non-volatile memory. A communication processing circuit (CP) may be configured to process data acquired from a component of the processor (210) into a format suitable for transmitting to another electronic device via a communication circuit, or to process data acquired from another electronic device via a communication circuit into a format suitable for processing by a component of the processor (210).For example, the communication circuit may include one or more communication circuits. The sensor interface (or sensing data processing circuit, sensor hub) may be configured to process data about the state of the electronic device (200) and / or the state of the surroundings of the electronic device (200), obtained through the sensor, into a format suitable for components of the processor (210).

[0065] For example, the processor (210) may perform a method according to an embodiment of the present disclosure by executing one or more instructions stored in the memory (220).

[0066] When a method according to an embodiment of the present disclosure includes multiple operations, the multiple operations may be performed by one processor or by multiple processors. For example, when a first operation, a second operation, and a third operation are performed by a method according to an embodiment, the first operation, the second operation, and the third operation may all be performed by the first processor, or the first operation and the second operation may be performed by the first processor (e.g., a general-purpose processor) and the third operation may be performed by the second processor (e.g., an artificial intelligence-specific processor).

[0067] The processor (210) may be implemented as a single core processor including one core, or may be implemented as one or more multicore processors including multiple cores (e.g., homogeneous multicores or heterogeneous multicores). When the processor (210) is implemented as a multicore processor, each of the multiple cores included in the multicore processor may include an internal processor memory, such as a cache memory or an on-chip memory, and a common cache shared by the multiple cores may be included in the multicore processor. In addition, each of the multiple cores (or some of the multiple cores) included in the multicore processor may independently read and execute a program instruction for implementing a method according to an embodiment of the present disclosure, or all (or some) of the multiple cores may be linked to read and execute a program instruction for implementing a method according to an embodiment of the present disclosure.

[0068] When a method according to an embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one core among the plurality of cores included in a multi-core processor, or may be performed by the plurality of cores. For example, when a first operation, a second operation, and a third operation are performed by a method according to an embodiment, the first operation, the second operation, and the third operation may all be performed by a first core included in the multi-core processor, or the first operation and the second operation may be performed by a first core included in the multi-core processor, and the third operation may be performed by a second core included in the multi-core processor.

[0069] In embodiments of the present disclosure, a processor may mean a system on a chip (SoC) in which one or more processors and other electronic components are integrated, a single-core processor, a multi-core processor, or a core included in a single-core processor or a multi-core processor, wherein the core may be implemented as a CPU, a GPU, an APU, a MIC, a DSP, an NPU, a hardware accelerator, or a machine learning accelerator, but embodiments of the present disclosure are not limited thereto.

[0070] The memory (220) may include one or more storage media (or one or more storage devices). For example, the memory (220) may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory (e.g., non-volatile memory) such as a hard drive, flash memory, read-only memory (ROM), semi-permanent memory (e.g., volatile memory) such as random access memory (RAM), any other suitable type of storage (or storage assembly), or any combination thereof. The memory (220) may include cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (200). As a non-limiting example, the cache memory may be included within the processor (210). The memory (220) may be fixedly embedded within the electronic device (200) or incorporated into one or more suitable types of components (e.g., a subscriber identity module (SIM) card and / or a secure digital (SD) card) that can be repeatedly inserted into and removed from the electronic device (200).

[0071] For example, the memory (220) may store one or more software applications, such as an operating system (or system) software application, a firmware software application, a driver software application, a plug-in (e.g., add-in, add-on, and / or applet) software application, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (210). For example, the memory (220) may store instructions callable by an application programming interface (API). For example, the memory (220) may store instructions within a library.

[0072] The display (230) is controlled by the processor (210) and can output visual information to the user. The visual information may include visual objects displayed on the display (230). For example, the visual objects may include screens, images, icons, GUIs, UI elements, etc. For example, the display (230) may be implemented as a flat panel display (FPD), a curved display, a flexible display, etc. For example, the display (230) may be implemented as various types of displays such as a Liquid Crystal Display (LCD) display, an Active Matrix Organic Light Emitting Diodes (AMOLED) display, a Light Emitting Diodes (LED), a micro LED, a Mini LED, etc.

[0073] The display (230) may include a touch sensing circuit configured to detect a touch. The touch sensing circuit may acquire a user input to the display (230). For example, the touch sensing circuit may detect an input (e.g., a touch input or a hovering input) at a specific location of the display (230) by measuring a change in a signal (e.g., voltage, light intensity, resistance, or charge) at the specific location, and provide information about the detected input to the processor (210).

[0074] FIG. 3 is a diagram illustrating an operation of an electronic device according to one embodiment of the present invention to map and store text input into an application. The processor (210) may perform at least one of the operations of FIG. 3. Instructions stored in the memory (220) of the electronic device (200), when individually or collectively executed by the processor (210) of the electronic device (200), may cause the electronic device (200) to perform the operations of FIG. 3.

[0075] In operation 310, the electronic device (200) can display the execution screen of the application on the display (230).

[0076] According to one embodiment, the electronic device (200) may display a plurality of icons corresponding to a plurality of applications on the display (230). For example, the electronic device (200) may display a home screen including a plurality of icons corresponding to a plurality of applications. The applications may include applications installed on the electronic device (200). In response to a user input for selecting an icon from among the plurality of icons, the electronic device (200) may execute an application corresponding to the selected icon and display an execution screen of the application on the display (230). The user input may include a touch input to an icon. The execution screen of the application may be a screen including visual information provided by the application by executing the application.

[0077] In operations 320-Y, 330, the electronic device (200) may display the keyboard interface on the display (230) when a user input for displaying the keyboard interface is received while the application is running.

[0078] A keyboard interface may be an interface that allows a user to input text. For example, the keyboard interface may be implemented in the form of a soft keyboard displayed on a display (230) and may include various keys (e.g., character keys, emoji input keys, a space bar, etc.).

[0079] According to one embodiment, when a touch input is received for a text input field (e.g., a message input window, a search window, or an input window of a login screen) for entering text on the execution screen of an application, the electronic device (200) may display a keyboard interface on the execution screen of the application. For example, the keyboard interface may be called by an application that provides the execution screen. The system of the electronic device (200) (e.g., the operating system (142) of FIG. 1) may display the keyboard interface on the display (230) in response to a request to display the keyboard interface. For example, the electronic device (200) may display the keyboard interface in the form of an overlay on the execution screen of the application. When the keyboard interface is displayed, the layout of the execution screen of the application may be adjusted so that the text input field is not covered by the keyboard interface.

[0080] However, the present disclosure is not limited thereto. For example, when a touch input is received for an icon (e.g., a keyboard-shaped icon) located around a text input field, the electronic device (200) may display a keyboard interface. As another example, when an application execution screen is displayed on the display (230), the electronic device (200) may display a keyboard interface together with the application execution screen.

[0081] In operation 340, the electronic device (200) can display text entered through the keyboard interface on the execution screen of the application.

[0082] According to one embodiment, when a touch input is received for a key of a keyboard interface, the electronic device (200) may display letters, numbers, punctuation marks, symbols, etc. corresponding to the key in a text input field of an application's execution screen. The text may include at least one sentence composed of letters, numbers, punctuation marks, symbols, etc.

[0083] In operation 350, the electronic device (200) can obtain identification information of the application.

[0084]

[0085] *For example, the application may be an application that invokes a keyboard interface. The application may be an application that provides an execution screen displayed on the display (230).

[0086] Application identification information may include a unique identifier that identifies (or distinguishes) the application. For example, application identification information may include the application's name, the application's package name, or the application ID.

[0087] In operation 360, the electronic device (200) can map the input text to the application's identification information and store it in the memory (220).

[0088] According to one embodiment, when the electronic device (200) receives a user input to transmit the entered text to an external electronic device (e.g., a server (108)), the electronic device (200) may map the entered text to identification information of the application and store it in the memory (220).

[0089] For example, the electronic device (200) may receive a user input for transmitting text entered in a text input field to an external electronic device. The user input may include a touch input to an interface element included in an execution screen of an application. The interface element may be a button for transmitting text to an external electronic device. When a user input is entered, the electronic device (200) may transmit the text entered in the text input field at the time the user input is entered to the external electronic device and store the text by mapping it to the application's identification information. The external electronic device may be a server that supports the functions of the application and stores and manages data so that the application can provide services smoothly to the user.

[0090] For example, the application may be a social media application. When the electronic device (200) receives a touch input on an interface element (e.g., a button displayed on the display (230)) for uploading text on the execution screen of the social media application, the electronic device (200) may transmit the text entered in the text input field to a server, thereby uploading a post to the user's account. Based on the touch input received on the interface element, the electronic device (200) may map the text to identification information of the social media application and store the mapped text.

[0091] For example, the application may be a messaging application. When a touch input is received on an interface element (e.g., a button displayed on the display (230)) for sending a message on the execution screen of the messaging application, the electronic device (200) may transmit the message entered in the text input field to a server, thereby transmitting the message to the other party's device via the server. Based on the touch input received on the interface element, the electronic device (200) may map the text to the identification information of the messaging application and store it.

[0092] For example, the application may be a web browser application. When a touch input is received on an interface element (e.g., a button displayed on the display (230)) for uploading text on the execution screen of the web browser application, the electronic device (200) may transmit the text entered in the text input field to a server, thereby uploading a post to a web page. Based on the touch input received on the interface element, the electronic device (200) may map the text to identification information of the web browser application and store it.

[0093] According to one embodiment, when text input is completed, the electronic device (200) can map the input text to the application's identification information and store it in the memory (220).

[0094] Completion of text entry may include receiving user input to save text entered on the application's execution screen, or when the application is terminated or switched to another application while text is entered on the application's execution screen.

[0095] For example, a user may exit the memo application while writing a text using the memo application, or may touch the save button of the memo application to save the text. The electronic device (200) may obtain the text entered on the running screen of the memo application and store the text by mapping it to the application's identification information.

[0096] According to one embodiment, when a call to the keyboard interface is terminated, the electronic device (200) can map the entered text to the application's identification information and store it in the memory (220).

[0097] For example, when text entered into a text input field is transmitted to an external electronic device (e.g., server (108)) based on user input, or when text entry is completed as described above, the call to the keyboard interface may be terminated and the keyboard interface may visually disappear from the display (230). When the keyboard interface is visually removed from the display (230), the electronic device (200) may store the text displayed in the text input field by mapping it to the application's identification information.

[0098] According to one embodiment, the electronic device (200) may store text in a database by associating (or linking) it with application identification information. For example, the database may use a key-value data structure to map and store text and application identification information. However, the present disclosure is not limited thereto, and the electronic device (200) may use various data structures to map and store text and application identification information. Hereinafter, the text database may be a database that includes data in which text and application are mapped and stored.

[0099] For example, a user may input text into a social media application (or social network service application) installed on an electronic device (200) to create a post on his or her account. The electronic device (200) may map the text entered into the social media application to identification information of the social media application and store the same. For example, referring to FIG. 4, a database (401) may include a name (410) of a social media application (e.g., AAA) and an input text (420). FIG. 4 illustrates an example where a user uploads his or her own text to a social media server five times. Accordingly, five texts (421, 422, 423, 424, 425) may each be mapped to the name of the social media application. In some embodiments, the database may further include a sequence ID (SequenceID) corresponding to the text. For example, a sequence ID may be a unique identifier assigned to each request when a social media application sends a request to a server, such as uploading text.

[0100] Although the application is described as a social media application in FIG. 4, the present disclosure is not limited thereto. For example, a user may input text into a message application installed on the electronic device (200) to send a message to a counterpart. The electronic device (200) may map the text input into the message application to identification information of the message application and store it. For example, the database may include the name of the message application and the input text.

[0101] In this way, the electronic device (200) can store text entered into an application by mapping it to the application's identification information for each of multiple applications.

[0102] FIG. 5 is a diagram illustrating an operation of an electronic device according to one embodiment of the present invention to map and store text input into an application. The processor (210) may perform at least one of the operations of FIG. 5. Instructions stored in the memory (220) of the electronic device (200), when individually or collectively executed by the processor (210) of the electronic device (200), may cause the electronic device (200) to perform the operations of FIG. 5.

[0103] According to one embodiment, the electronic device (200) may, in addition to the application's identification information, map text entered into the application to additional information related to the application and store the mapped text in the memory (220). Since the other contents are the same as those of FIG. 3 except that additional information related to the application may be mapped to the entered text, any duplicate content described in FIG. 3 will be omitted when describing FIG. 5.

[0104] In operation 510, the electronic device (200) can obtain identification information of the application and additional information related to the application.

[0105] In one embodiment, additional information related to the application may include identification information of the web page where the text was entered. The identification information of the web page may include the Uniform Resource Locator (URL) of the web page. For example, a user may use a web browser application to launch a web browser, access the web page, and enter text. The electronic device (200) may obtain identification information of the web page where the text was entered.

[0106] In one embodiment, additional information related to the application may include identification information of the recipient to whom the text is being sent. The identification information may include the recipient's name, nickname, or hash ID. For example, a user may send a message to a recipient using a messaging application. The user may select a recipient from among multiple recipients and enter text on the messaging application's launch screen to send the message to the recipient. The electronic device (200) may obtain identification information of the recipient to whom the text is being sent.

[0107] In operation 520, the electronic device (200) can map the input text to the application's identification information and additional information related to the application and store the mapped text in the memory (220).

[0108] For example, the electronic device (200) may acquire text entered for each of a plurality of web pages and store the text by mapping it to identification information of the web browser application and identification information of the web pages. The text entered for each of the plurality of web pages may be mapped to identification information of the web browser application and identification information of each of the plurality of web pages. The database may include text entered for the web pages, identification information of the web browser application, and identification information of the web pages.

[0109] For example, the electronic device (200) may acquire text entered into a messaging application for transmission to multiple counterparts, map the text to identification information of the messaging application and the counterparts, and store the text. The text entered for each of the multiple counterparts may be mapped to the identification information of the messaging application and the identification information of each of the multiple counterparts. The database may include the name of the messaging application, the names of the counterparts, and the text entered for transmission to the counterparts.

[0110] In this way, the electronic device (200) can store text entered into the application by mapping it to the application's identification information and additional information related to the application.

[0111] Meanwhile, while the above-described example described text being input via a keyboard interface displayed on the electronic device (200), the present disclosure is not limited thereto. For example, the text may be input via a physical keyboard connected to the electronic device (200) via a wire or wireless connection. Furthermore, the text may be text converted from a voice signal. For example, the electronic device (200) may receive a voice signal via a microphone, convert the voice signal into text using STT (speech-to-text), and obtain the text.

[0112] FIG. 6 is a diagram illustrating an operation of an electronic device according to one embodiment of the present invention to store text input into an application. The processor (210) may perform at least one of the operations of FIG. 6. Instructions stored in the memory (220) of the electronic device (200), when individually or collectively executed by the processor (210) of the electronic device (200), may cause the electronic device (200) to perform the operations of FIG. 6.

[0113] According to one embodiment, the electronic device (200) can identify the identification information of the application to which the input text is to be mapped, and identify the number of texts already mapped to the same identification information. Based on the number, the electronic device (200) can store the input text by mapping it to the identification information of the application, or delete some of the pre-stored texts and store the input text by mapping it to the identification information of the application.

[0114] In operations 610-Y, 620, if the electronic device (200) determines that the number of texts mapped to the application's identification information exceeds a preset number, the electronic device may delete the oldest text among the texts mapped to the application's identification information from the memory (220).

[0115] For example, the preset number may be set during the manufacturing or initial use of the electronic device (200), or may be set and changed by user input. For example, the preset number may be 10. However, the present invention is not limited thereto, and the preset number may have various values.

[0116] For example, the oldest text may be the text that is stored earliest in time among the texts mapped to the application's identification information. When storing text, the electronic device (200) may record the time information at which the text was stored using the system time (e.g., date and time) managed by the operating system (e.g., 142 of FIG. 1). Using the recorded time information, the electronic device (200) may identify the text that is stored earliest in time among the texts mapped to the application's identification information and delete the text.

[0117] In operation 630, the electronic device (200) can map the input text to the application's identification information and store it in the memory (220).

[0118] In operations 610-N, 630, if the electronic device (200) determines that the number of texts mapped to the application's identification information does not exceed a preset number, the electronic device may map the input text to the application's identification information and store it in the memory (220).

[0119] As described below, text mapped to an application can be used to generate style information. According to the present disclosure, based on the number of texts mapped to an application, the oldest text stored among the texts mapped to the application can be deleted and new text mapped to the application and stored. Accordingly, style information reflecting the user's recent text writing patterns can be acquired.

[0120] FIG. 7 is a diagram illustrating an operation of an electronic device acquiring style information according to one embodiment. The processor (210) may perform at least one of the operations of FIG. 7. Instructions stored in the memory (220) of the electronic device (200), when individually or collectively executed by the processor (210) of the electronic device (200), may cause the electronic device (200) to perform the operations of FIG. 7.

[0121] In operation 710, the electronic device (200) can identify whether the number of texts mapped to the identification information of the application is greater than or equal to a preset number.

[0122] For example, the preset number may be set during the manufacturing or initial use of the electronic device (200), or may be set and changed by user input. For example, the preset number may be multiple. For example, the preset number may be three. However, the present invention is not limited thereto, and the preset number may have various values. In this way, the electronic device (200) can identify whether the text mapped to the application's identification information is a preset multiple.

[0123] FIGS. 8A, 8B, and 8C are diagrams illustrating an example of an operation of an electronic device according to one embodiment of the present invention to identify whether the number of texts mapped to identification information of an application is greater than or equal to a preset number.

[0124] Referring to FIG. 8A, in operations 811-Y and 820, when a user input for obtaining style information corresponding to an application is received, the electronic device (200) can identify whether the number of texts mapped to the application's identification information is greater than or equal to a preset number. For example, the user input may include a touch input for an interface element included in the application's execution screen. The interface element may be a button for obtaining style information.

[0125] Referring to FIG. 8B, in operations 812-Y and 820, the electronic device (200) can identify whether the number of texts mapped to the application's identification information is greater than or equal to a preset number when the input text is mapped to the application's identification information and stored. As described above, the electronic device (200) can map the text entered in the text input field to the application's identification information and store it. When the electronic device (200) performs the operation of mapping the input text to the application's identification information and storing it, it can identify whether the number of texts mapped to the application's identification information is greater than or equal to a preset number.

[0126] Referring to FIG. 8C, in operations 813-Y and 820, if the mode of the electronic device (200) is a low-power mode, the electronic device (200) may identify whether the number of texts mapped to the identification information of the application is greater than or equal to a preset number. The low-power mode may include a mode in which the performance and functions of the electronic device (200) are partially limited to reduce battery consumption. For example, the electronic device (200) may lower the performance of the CPU, lower the brightness or resolution of the screen, or limit the operation of applications running in the background in the low-power mode. When a user input for activating the low-power mode is received, the electronic device (200) may change the mode of the electronic device (200) to the low-power mode and identify whether the number of texts mapped to the identification information of the application is greater than or equal to a preset number. As another example, if the load of the system is below a preset condition, the electronic device (200) may identify whether the number of texts mapped to the identification information of the application is greater than or equal to a preset number.

[0127] In this way, the electronic device (200) can identify whether the number of texts mapped to the application's identification information is greater than or equal to a preset number at various points in time. However, the present disclosure is not limited thereto. For example, the electronic device (200) can also identify whether the number of texts mapped to the application's identification information and stored is greater than or equal to a preset number, periodically or in real time.

[0128] Returning to FIG. 7, in operations 710-Y, 720, and 730, if the electronic device (200) determines that the number of texts mapped to the identification information of the application is greater than or equal to a preset number, the electronic device (200) obtains a prompt for requesting style analysis of the text based on the text mapped to the identification information of the application, and inputs the prompt to the artificial intelligence model to obtain style information from the artificial intelligence model.

[0129] According to one embodiment, if the electronic device (200) identifies that the number of texts mapped to the identification information of the application is a preset number or more, the electronic device can identify a text to be referenced in the process of generating style information among the plurality of texts mapped to the identification information of the application.

[0130] For example, the electronic device (200) can identify a plurality of texts mapped to the application's identification information as texts to be used for style analysis.

[0131] For example, the electronic device (200) may determine that some of the texts among the plurality of texts mapped to the identification information of the application are texts to be used for style analysis.

[0132] For example, the electronic device (200) may identify texts among a plurality of texts mapped to the application's identification information, wherein the text has a sentence length greater than a preset length, as text to be used for style analysis. The sentence length may be determined based on the number of characters, the number of letters, or the number of clauses.

[0133] Style information may include features of the text that can be inferred from sentences contained in the text and features of the user who wrote the text.

[0134] For example, the style information may include at least one of the following: a character analysis of the user who wrote the text, linguistic characteristics, personality characteristics of the user, sentence tone, sentence length, the way the user refers to people or pets, punctuation usage patterns, symbol usage patterns, emoji usage patterns, phrases used at the beginning or end of sentences, sentence division methods, emotional expression methods, and frequently used words before and after certain symbols (e.g., hashtags (#), quotation marks, etc.). The linguistic characteristics may include a list of frequently used verbs, adverbs, conjunctions, exclamations, and adjectives. Frequent use may include use of two or more times. The sentence division methods may include information such as “periods separate sentences” or “new lines separate sentences.” The emotional expression methods may include a list of expressions used to express laughter, tears, or other emotions.

[0135] According to one embodiment, the electronic device (200) may generate a prompt to request style analysis of text based on text mapped to identification information of the application.

[0136] For example, the electronic device (200) may generate prompts such as “Analyze the following sentences and tell me [style information]” and “[sentences]”. Here, [style information] may include the aforementioned style information, and [sentences] may include text mapped to the application’s identification information. However, the present disclosure is not limited thereto, and the prompt may include various formats of text for requesting analysis of style information for text mapped to the application’s identification information.

[0137] According to one embodiment, the electronic device (200) may input a prompt to an AI model and obtain style information generated by the AI ​​model from the AI ​​model. For example, the AI ​​model may analyze text based on the prompt and output style information inferred from the text. The style information may include text.

[0138] For example, the artificial intelligence model may be implemented in the form of an on-device included in the electronic device (200). The electronic device (200) may input a prompt into the artificial intelligence model stored in the memory (220) to obtain style information from the artificial intelligence model. As another example, the artificial intelligence model may be stored in a server (e.g., 108 of FIG. 1) connected to the electronic device (200). When the artificial intelligence model is stored in the server, the electronic device (200) may transmit text mapped to the identification information of the application or a prompt generated based on the text to the server, and receive style information from the server.

[0139] FIGS. 9A and 9B illustrate examples of style information generated by an artificial intelligence model according to one embodiment.

[0140] Referring to FIGS. 9A and 9B , the electronic device (200) may obtain a prompt for requesting style analysis of a text (420) using a text (e.g., 420 of FIG. 4 ) mapped to a name of a social media application (e.g., 410 of FIG. 4 ), input the prompt into an artificial intelligence model, and obtain style information (901) from the artificial intelligence model. The style information (901) may include text, and may include characteristic information of a user who wrote a sentence included in the text (420) and characteristic information of the sentence.

[0141] Returning to FIG. 7, at operation 740, the electronic device (200) can map style information obtained from the artificial intelligence model to the application's identification information and store it in the memory (220).

[0142] According to one embodiment, the electronic device (200) may store style information acquired from an artificial intelligence model in a database by associating it with the application's identification information. The identification information to which the style information is mapped may be identical to the application's identification information to which the text input into the artificial intelligence model for acquiring the style information is mapped. For example, the database may use a key-value data structure to map and store the style information and the application's identification information. However, this is merely an example, and the electronic device (200) may use various data structures to map and store the style information and the application's identification information. Hereinafter, the style information database may be a database that includes data in which style information and an application are mapped and stored.

[0143] FIG. 10 is a diagram illustrating an example of an operation of an electronic device storing style information according to one embodiment.

[0144] Referring to FIG. 10, a text database (1010) may include text (1011) mapped to identification information of a first application and text (1012) mapped to identification information of a second application.

[0145] The electronic device (200) can generate a prompt (1021) for obtaining style information of the text (1011) using text (1011) mapped to the identification information of the first application, and input the prompt (1021) into the artificial intelligence model (1001). The artificial intelligence model (1001) can generate style information (1031) for the prompt (1021). The electronic device (200) can store the style information (1031) by mapping it to the identification information of the first application. The electronic device (200) can generate a prompt (1022) for obtaining style information of the text (1012) using text (1012) mapped to the identification information of the second application, and input the prompt (1022) into the artificial intelligence model (1001). The artificial intelligence model (1001) can generate style information (1032) for the prompt (1022). The electronic device (200) can store style information (1032) by mapping it to identification information of the second application.

[0146] The style information database (1040) may include style information (1041) mapped to identification information of a first application and style information (1042) mapped to identification information of a second application.

[0147] In the above example, the style information (1041, 1042) may be changed or updated as the text (1011, 1012) included in the prompt (1021, 1022) is updated. For example, the text mapped to the application's identification information may be updated as new text is mapped to the application's identification information or the text mapped to the identification information is deleted. Accordingly, when the style information (1031, 1032) is generated using the updated text (1011, 1012), the style information (1041, 1042) of the style information database (1040) may be changed or updated.

[0148] In this way, the electronic device (200) can obtain style information corresponding to each application for each of multiple applications and store the style information by mapping it to the application's identification information.

[0149] The above-described example describes an operation in which an electronic device (200) acquires style information using text mapped to an application's identification information, and stores the style information by mapping it to the application's identification information. This description can be equally applied to an operation in which an electronic device (200) stores text by mapping it to an application's identification information and to the application's additional information.

[0150] The electronic device (200) can obtain style information using text mapped to the application's identification information and the application's additional information, and store the style information by mapping it to the application's identification information and the application's additional information.

[0151] For example, the application may be a web browser application. The electronic device (200) may obtain text mapped to a web page for each of a plurality of web pages, obtain style information using the text, and map and store the style information to the identification information of the web browser application and the identification information of the web pages. The style information corresponding to each of the plurality of web pages may be mapped to the identification information of the web browser application and the identification information of each of the plurality of web pages.

[0152] For example, the application may be a messaging application. The electronic device (200) may obtain text mapped to each of multiple counterparts, use the text to obtain style information, and map and store the style information to the identification information of the messaging application and the counterparts. The style information corresponding to each of the multiple counterparts may be mapped to the identification information of the messaging application and the identification information of each of the multiple counterparts.

[0153] FIG. 11 is a diagram illustrating an example of an operation of an electronic device storing style information according to one embodiment.

[0154] Referring to FIG. 11, the text database (1110) may include text (1111) mapped to the identification information of the first application and the first additional information, text (1112) mapped to the identification information of the first application and the second additional information, and text (1113) mapped to the identification information of the second application.

[0155] The first additional information and the second additional information may be different information. For example, the first additional information may include identification information for the first web page, and the second additional information may include identification information for a second web page that is different from the first web page. For example, the first additional information may include identification information for the first counterpart, and the second additional information may include identification information for a second counterpart that is different from the first counterpart.

[0156] The electronic device (200) can generate a prompt (1121) for obtaining style information of the text (1111) using the text (1111) mapped to the identification information of the first application and the first additional information, and input the prompt (1121) into the artificial intelligence model (1101). The artificial intelligence model (1101) can generate style information (1131) for the prompt (1121). The electronic device (200) can store the style information (1131) by mapping it to the identification information of the first application and the first additional information.

[0157] The electronic device (200) can generate a prompt (1122) for obtaining style information of the text (1112) using the text (1112) mapped to the identification information of the first application and the second additional information, and input the prompt (1122) into the artificial intelligence model (1101). The artificial intelligence model (1101) can generate style information (1132) for the prompt (1122). The electronic device (200) can store the style information (1132) by mapping it to the identification information of the first application and the second additional information.

[0158] The electronic device (200) can generate a prompt (1123) to obtain style information of the text (1113) using the text (1113) mapped to the identification information of the second application, and input the prompt (1123) into the artificial intelligence model (1101). The artificial intelligence model (1101) can generate style information (1133) for the prompt (1123). The electronic device (200) can store the style information (1133) by mapping it to the identification information of the second application.

[0159] The style information database (1140) may include style information (1141) mapped to the identification information of the first application and the first additional information, style information (1142) mapped to the identification information of the first application and the second additional information, and style information (1143) mapped to the identification information of the second application.

[0160] In this way, the electronic device (200) can obtain style information based on text mapped to the application's identification information and additional information, and store the style information by mapping it to the application's identification information and additional information.

[0161] In one embodiment, the electronic device (200) can share style information stored in the memory (220) with another device. For example, the electronic device (200) can access a server (e.g., 108 of FIG. 1) through a communication module (e.g., 190 of FIG. 1) and log in to the server using a user account. The electronic device (200) can communicate with the server based on the logged-in user account and transmit the style information stored in the memory (220) to the server. The server can associate the style information received from the electronic device (200) with the user account and store it. When an external electronic device (e.g., 104 of FIG. 1) accesses the server using the same user account as the electronic device (200), the server can transmit the style information stored in the server to the external electronic device. The external electronic device can map the style information received from the server to the application's identification information and store it. Although the above-described example describes an electronic device (200) transmitting style information to an external electronic device via a server using a long-range wireless communication network, the present disclosure is not limited thereto. For example, the electronic device (200) may use a communication module (e.g., 190 of FIG. 1 ) to communicate with an external electronic device via a short-range communication network (e.g., Bluetooth, WiFi), thereby transmitting style information to the external electronic device.

[0162] FIG. 12 is a diagram illustrating an operation of an electronic device providing personalized text using style information according to one embodiment. The processor (210) may perform at least one of the operations of FIG. 12. Instructions stored in the memory (220) of the electronic device (200), when individually or collectively executed by the processor (210) of the electronic device (200), may cause the electronic device (200) to perform the operations of FIG. 12.

[0163] In FIG. 12, the description of operation 310 can be applied to operation 1210, the description of operation 320 can be applied to operation 1220, the description of operation 330 can be applied to operation 1230, and the description of operation 340 can be applied to operation 1240, so repeated descriptions are omitted.

[0164] At operation 1250, the electronic device (200) may receive user input to generate personalized text.

[0165] In one embodiment, user input for generating personalized text may be input through the application's execution screen. For example, the application's execution screen may include interface elements (e.g., buttons) for receiving user input. The electronic device (200) may receive touch input for the visual elements.

[0166] Referring to FIG. 13A, an electronic device (200) may display a running screen (1301) of a social media application. A user may input a simple sentence or word containing the subject of a text to be uploaded to his or her account through a keyboard interface (1311). For example, the user may input text (1312) such as "Thinking about what to give my boyfriend for his birthday." The electronic device (200) may display the text (1312) entered through the keyboard interface (1311) in a text input field (1313). The running screen (1301) may include a button (1314) for generating personalized text. The electronic device (200) may receive a touch input to the button (1314).

[0167] Returning to FIG. 12, at operations 1250-Y, 1260, the electronic device (200) may obtain style information corresponding to the application when user input for generating personalized text is received.

[0168] According to one embodiment, the electronic device (200) can obtain style information corresponding to an application from among style information corresponding to each of a plurality of applications stored in the memory (220).

[0169] For example, the application may be an application that invokes a keyboard interface. The application may be an application that provides an execution screen displayed on the display (230).

[0170] According to one embodiment, the electronic device (200) can obtain style information corresponding to an application by obtaining style information mapped to the application's identification information among style information mapped to each of a plurality of applications.

[0171] For example, the memory (220) can store style information mapped to application identification information for each of multiple applications. The electronic device (200) can obtain style information mapped to application identification information from among the style information stored in the memory (220).

[0172] For example, the memory (220) may store style information mapped to application identification information and additional information for each of multiple applications. The electronic device (200) may obtain style information mapped to application identification information and additional information from among the style information stored in the memory (220).

[0173] For example, the application may be a web browser application. When receiving user input for generating personalized text based on text entered on a web page, the electronic device (200) may identify the identification information of the web page where the text was entered. Using the identification information, the electronic device (200) may acquire style information mapped to the identification information of the web page where the text was entered, from among the style information mapped to the identification information of each of the plurality of web pages.

[0174] For example, the application may be a messaging application. When the electronic device (200) receives a user input for generating personalized text based on text entered on the execution screen of the messaging application, the electronic device (200) may identify the identification information of the other party based on the entered text. Using the identification information, the electronic device (200) may acquire style information mapped to the identification information of the other party from among the style information mapped to the identification information of each of the plurality of other parties.

[0175] In operations 1270 and 1280, the electronic device (200) may obtain a prompt based on style information corresponding to the application and the input text, and input the prompt into an artificial intelligence model to obtain personalized text.

[0176] According to one embodiment, the electronic device (200) may obtain text entered into a text input field and generate a prompt to request generation of text with style information mapped to the application based on the text.

[0177] According to one embodiment, the electronic device (200) can input a prompt to the artificial intelligence model to obtain personalized text generated by the artificial intelligence model from the artificial intelligence model.

[0178] For example, an AI model may generate text based on at least one piece of information related to the subject matter of the input text and included in the style information. The AI ​​model may generate personalized text that reflects the characteristics of text previously written by the user in the application. The personalized text may be text tailored to the user for each application. For example, in the case of a social media application, personalized text may be generated that reflects the length of hashtags frequently used by the user in posts, the length of sentences, etc. In another example, in the case of an email application, personalized text may be generated that reflects the user's frequently used headings, greetings, and conclusions in emails. Accordingly, according to the present disclosure, a user may obtain personalized text that reflects the user's text patterns for each application, thereby increasing the efficiency of text writing.

[0179] For example, the artificial intelligence model may be implemented in the form of a device included in the electronic device (200). The electronic device (200) may input a prompt into the artificial intelligence model stored in the memory (220) to obtain style information from the artificial intelligence model. As another example, the artificial intelligence model may be stored in a server (e.g., 108 of FIG. 1) connected to the electronic device (200). When the artificial intelligence model is stored in the server, the electronic device (200) may transmit style information mapped to the input text and the application to the server, or transmit a prompt generated based on the text and the style information to the server and receive text from the server.

[0180] Referring to the example illustrated in FIG. 13A above, a user may input text (1312) such as "Thinking about what to give my boyfriend for his birthday" into the launch screen (1301) of a social media application. The text (1312) may be displayed in a text input field (1313) of the launch screen (1301).

[0181] Referring to FIG. 13b, the electronic device (200) can obtain the input text, i.e., "Thinking about a birthday present for my boyfriend" (1312). The electronic device (200) can obtain style information (1322) mapped to the identification information of the social media application from among the style information stored in the style information database (1321).

[0182] The electronic device (200) can generate a prompt (1331) based on the input text (1312) and style information (1322). For example, the electronic device (200) can generate a prompt (1331) such as “Generate text with the topic “Thinking about a birthday present for my boyfriend” by reflecting the following information” and “[Style information]”. Here, [Style information] can include style information (1322) (e.g., 901 of FIGS. 9A and 9B ). However, the present disclosure is not limited thereto, and the prompt can include various formats of text for requesting the generation of text to which style information mapped to an application is applied based on the text.

[0183] The electronic device (200) can input a prompt (1331) into an artificial intelligence model (1341) to obtain text (1351) from the artificial intelligence model (1341). The text (1351) generated by the artificial intelligence model (1341) may be personalized text that reflects the characteristics of text previously written by the user through a social media application.

[0184] Returning to FIG. 12, at operation 1290, the electronic device (200) may display personalized text on the execution screen of the application.

[0185] According to one embodiment, the electronic device (200) displays personalized text on the execution screen of an application, and when a user input is received to select the personalized text, the electronic device may change the text entered in a text input field of the execution screen to the personalized text. For example, the user input may include a touch input to an interface element included in the execution screen of the application. The interface element may be a button for inserting the personalized text into the text input field.

[0186] For example, referring to FIG. 13C, the electronic device (200) may display personalized text (1351) on the execution screen (1301) of the social media application, and when a touch input is received for the confirmation button (1315), the electronic device (200) may remove the text (e.g., “Thinking about what to get for my boyfriend’s birthday”) displayed in the text input field (1313) of the execution screen (1301) and display the personalized text (1351) in the text input field (1313). Thereafter, when a touch input is received for the transmit button (1316) for uploading a post, the electronic device (200) may transmit the image (1317) and the personalized text (1351) to the server for uploading the post.

[0187] According to one embodiment, when a user input for regenerating personalized text is received, the electronic device (200) can input a prompt back to the artificial intelligence model to obtain personalized text from the artificial intelligence model and display the personalized text on the execution screen of the application.

[0188] For example, user input may include a touch input to an interface element included in the application's running screen, such as a button for regenerating personalized text.

[0189] Referring to FIG. 13D , when a touch input for the regenerate button (1317) is received, the electronic device (200) can re-input a prompt to the artificial intelligence model to obtain personalized text from the artificial intelligence model. The electronic device (200) can remove the personalized text (1351) displayed on the execution screen (1301) and display the personalized text (1352) re-obtained from the artificial intelligence model on the execution screen (1301). When a touch input for the confirmation button (1315) is received, the electronic device (200) can display the personalized text (1352) in the text input field (1313). According to an embodiment of the present disclosure, user satisfaction can be improved by providing various personalized texts to the user.

[0190] In one embodiment, a user can modify (or edit) personalized text generated by an AI model. For example, when personalized text is displayed in a text input field, the user can modify the personalized text by deleting some text or adding new text using a keyboard interface. The electronic device (200) can store the modified personalized text by mapping it to the application's identification information and obtain style information using the text mapped to the application's identification information, thereby updating the existing style information. When a touch input is received on a button for regenerating personalized text, the electronic device (200) can regenerate the personalized text using the updated style information.

[0191] The aforementioned FIGS. 13a, 13b, 13c, and 13d illustrate an operation in which an electronic device (200) provides a user with personalized text using style information mapped to an application's identification information (e.g., social media application's identification information). This description can be equally applied to an operation in which an electronic device (200) provides a user with personalized text using style information mapped to an application's identification information and additional information of the application.

[0192] For example, a user can input a simple sentence or word containing the subject of a message to be sent to a first counterpart through a keyboard interface using a messaging application, and touch a button to generate personalized text. Referring to FIG. 14A, the electronic device (200) can obtain the input text, i.e., “Christmas greetings” (1411). The electronic device (200) can obtain style information (1422-1) mapped to the identification information of the messaging application and the identification information of the first counterpart from among the style information stored in the style information database (1421). The electronic device (200) can generate a prompt (1431-1) based on the input text (1411) and the style information (1422-1). For example, the electronic device (200) can generate a prompt (1431-1) such as “Generate a text having the subject of “Christmas greetings” by reflecting the following information” and "[Style information]". Here, [style information] may include style information (1422-1). The electronic device (200) may input a prompt (1431-1) into an artificial intelligence model (1441) to obtain text (1451-1) from the artificial intelligence model (1441). The text (1451-1) generated by the artificial intelligence model (1441) may be a personalized text that reflects the characteristics of a message previously sent by the user to the first counterpart.

[0193] For example, a user can input a simple sentence or word containing the subject of a message to be sent to a second party through a keyboard interface using a messaging application, and touch a button to generate a personalized text. Referring to FIG. 14B, the electronic device (200) can obtain the input text, i.e., “Christmas greetings” (1411). The electronic device (200) can obtain style information (1422-2) mapped to the identification information of the messaging application and the identification information of the second party from among the style information stored in the style information database (1421). The electronic device (200) can generate a prompt (1431-2) based on the input text (1411) and the style information (1422-2). For example, the electronic device (200) can generate a prompt (1431-2) such as “Generate a text having the subject of “Christmas greetings” by reflecting the following information” and "[Style information]". Here, [style information] may include style information (1422-2). The electronic device (200) may input a prompt (1431-2) into an artificial intelligence model (1441) to obtain text (1451-2) from the artificial intelligence model (1441). The text (1451-2) generated by the artificial intelligence model (1441) may be a personalized text that reflects the characteristics of a message previously sent by the user to a second party.

[0194] In this way, the electronic device (200) can input a prompt obtained based on the style information corresponding to the other party and the input text into an artificial intelligence model to obtain personalized text, and display the personalized text on the execution screen of the message application. The operation of the electronic device (200) displaying the personalized text can be applied as described in operation 1290.

[0195] While the above example illustrates a messaging application, the above description can also be applied to a web browser application. For example, the electronic device (200) can input a prompt obtained based on style information corresponding to a web page and input text into an artificial intelligence model to obtain personalized text, and display the personalized text on the execution screen of the web browser application.

[0196] In one embodiment, the electronic device (200) can generate personalized text for text entered into another application using style information mapped to the application's identification information and additional information.

[0197] For example, the memory (220) may include style information mapped to the identification information of the first application and the identification information of the other party. In order to send a message to the same other party using a second application different from the first application, the user may input text into the second application and input user input to generate a personalized text. When the user input is received, the electronic device (200) may identify the other party to whom the message is to be sent through the second application and obtain style information mapped to the identification information of the other party from the style information stored in the memory (220). For example, the electronic device (200) may obtain style information mapped to the identification information of the first application and the identification information of the other party. In addition, the electronic device (200) may obtain personalized text based on the obtained style information and the text input into the second application. The electronic device (200) may further add the second application to the identification information of the first application and the identification information of the other party, and store the style information by mapping it to the identification information of the first and second applications and the identification information of the other party.

[0198] FIG. 15 is a diagram illustrating an example of an electronic device providing personalized text according to one embodiment.

[0199] Referring to 1501 of FIG. 15, the electronic device (200) may display an execution screen (1510) of a social media application. The execution screen (1510) may include interface elements (1511, 1512, 1513, 1514) for receiving settings related to the generation of personalized text. For example, the electronic device (200) may display interface elements (1511, 1512, 1513, 1514) when a touch input for a specific button is received.

[0200] Interface element (1511) may be an interface element for setting the format style of personalized text. For example, if a user selects “Social,” the format of the personalized text may be set to the same format as a social media post. Interface element (1512) may be an interface element for setting style information. For example, if a user selects “My Style,” personalized text may be generated using the style information. Interface element (1513) may be an interface element for setting the length of the personalized text. For example, if a user selects “Normal,” the length of the personalized text may be set to the normal length. Interface element (1514) may be an interface element for setting the language of the personalized text. For example, if a user selects “Korean,” the language of the personalized text may be set to Korean.

[0201] A user can input a simple sentence or word containing the subject of the text they wish to upload to their account via the keyboard interface (1521). For example, the user can input text such as "Thinking about what to get for my boyfriend's birthday." Referring to 1502 of FIG. 15 , the electronic device (200) can display the text (1531) input via the keyboard interface (1521) in a text input field (1532). The execution screen (1510) can include a button (1533) for generating personalized text. When a touch input is received on the button (1533), the electronic device (200) can obtain the personalized text.

[0202] For example, the electronic device (200) can obtain style information mapped to the identification information of a social media application from among the style information stored in the style information database. The electronic device (200) can generate a prompt based on the input text and style information. For example, the electronic device (200) can generate a prompt such as “Generate a Korean text of normal length with the topic “Thinking about a birthday present for my boyfriend” and in the format of a social media post, reflecting the following information” and “[Style information].” In other words, the electronic device (200) can generate a prompt to request the generation of personalized text corresponding to settings based on user input. The electronic device (200) can input the prompt to an artificial intelligence model and obtain personalized text from the artificial intelligence model.

[0203] FIG. 16 is a diagram illustrating an example of an operation in which an electronic device provides style information according to one embodiment.

[0204] Referring to FIG. 16, the execution screen (1610) of the application may include an interface element (1611). When the user selects “My Style” through the interface element (1611), the electronic device (200) may provide style information mapped to the application’s identification information. For example, the electronic device (200) may display information on character analysis (e.g., a mukbang YouTuber who likes to communicate with fans) (1612) among the style information mapped to the application’s identification information (e.g., 901 of FIGS. 9A and 9B ) in the text input field (1613). In this way, the present disclosure may display style information in the form of a preview to guide the user on what characteristics personalized text will be generated. When text is input through the keyboard interface, the display of information displayed in the text input field (1613) may be stopped, and the input text may be displayed in the text input field (1613).

[0205] FIGS. 17A, 17B, and 17C are diagrams illustrating an example of an operation of an electronic device generating personalized text according to one embodiment.

[0206] FIG. 17A illustrates an example of text (1711) mapped to a social media application. The text (1711) may include a post made by a user using the social media application.

[0207] The electronic device (200) can generate prompts such as “Analyze the following sentences and tell me [style information]” and “[sentences].” Here, [sentences] can include text (1711). The electronic device (200) can input the prompts into an artificial intelligence model to obtain style information from the artificial intelligence model. FIG. 17B illustrates an example of style information (1721) obtained by an artificial intelligence model analyzing the text (1711) of FIG. 17A. The style information (1721) can include characteristics of the user who wrote the text (1711) and characteristics of the text (1711).

[0208] A user may input text such as “I brought a precious plant home again today” into a social media application. The electronic device (200) may generate personalized text related to the input text “I brought a precious plant home again today” using style information (1721) mapped to the social media application. For example, the electronic device (200) may generate prompts such as “Write a text with the topic “I brought a precious plant home again today” based on the following characteristics” and “[Style information].” Here, [Style information] may include style information (1721). The electronic device (200) may input the prompt into an artificial intelligence model and obtain text (1731) as shown in FIG. 17C from the artificial intelligence model. The text (1731) may have the topic “I brought a precious plant home again today” and may be personalized text that reflects the characteristics of text previously written by the user through the social media application.

[0209] FIGS. 18a, 18b, 18c, 18d, and 18e are diagrams illustrating an example of an operation of an electronic device generating personalized text according to one embodiment.

[0210] FIG. 18A illustrates an example of text (1811) mapped to a social media application. The text (1811) may include a post made by a user using the social media application.

[0211] The electronic device (200) can generate prompts such as “Analyze the following sentences to tell me [my relationship with my pet or animal, my thoughts about my pet or animal, and style information]” and “[sentences].” Here, [sentences] can include text (1811). For example, the electronic device (200) can analyze sentences of text mapped to a social media application using a pre-trained language model, and identify whether the text contains words related to animals or pets by understanding the meaning, context, etc. of words within the sentences. If the electronic device (200) identifies the presence of the words, it can generate a prompt to obtain style information that further includes information about the relationship with my pet or animal, and my thoughts about my pet or animal. FIGS. 18B and 18C illustrate examples of style information (1821) obtained by an artificial intelligence model analyzing the text (1811) of FIG. 18A. Style information (1821) may include characteristics of the user who wrote the text (1811), characteristics of the text (1811), and the user's thoughts about the pet or animal.

[0212] Referring to FIG. 18d, a user may input text (1831) such as “cat in picture” into a social media application. The electronic device (200) may generate personalized text related to the input text “cat in picture” using style information (1821) mapped to the social media application. For example, the electronic device (200) may generate prompts such as “Write a text with the topic “cat in picture” based on the following features” and “[style information].” Here, [style information] may include style information (1821). The electronic device (200) may input the prompt into an artificial intelligence model and obtain text (1841) such as FIG. 18e from the artificial intelligence model. The text (1841) may have the topic “cat in picture” and may be personalized text that reflects the features of a text previously written by the user through the social media application.

[0213] According to various embodiments of the present disclosure, users can quickly obtain personalized text tailored to their personal style, thereby improving productivity related to text writing. Furthermore, personalized text can be generated that reflects the user's frequently used text writing patterns (e.g., frequently used words, sentence length, etc.) and the user's intentions for using specific words. This reduces the time it takes for the user to write and edit sentences, thereby improving the user experience and productivity.

[0214] Figure 19 is a diagram for explaining a generative artificial intelligence model according to one embodiment.

[0215] FIG. 19 illustrates a generative artificial intelligence model that is an example of an artificial intelligence model (e.g., 1001 of FIG. 10, 1101 of FIG. 11, 1341 of FIG. 13, 1441 of FIGS. 14a and 14b) according to various embodiments of the present disclosure.

[0216] The User Query / Response Interface can receive user input. User input can be in the form of natural language, images, and / or videos. Context information can also be transmitted when the user input is transmitted. Context information can include various additional information at the time of user input. For example, it can include information about the application the user is currently using or the user's location. Furthermore, user input can also be a mixture of natural language, images, sounds, and context information as described above. Furthermore, user input can also be in the form of non-natural language, such as selecting a menu.

[0217] The User Query / Response Interface can output the results of a generative AI system to the user. The output can be in natural language or in a specific content format, and can also be provided in the form of actions requested by the user. The User Query / Response Interface can output the results of a generative AI system to the user. The output can be in natural language or in a specific content format, and can also be provided in the form of actions requested by the user. For example, the User Query / Response Interface can output personalized text generated by an AI model.

[0218] The AI ​​framework can receive user input and coordinate and control each component necessary to carry out the user's intention based on the user's query.

[0219] User input received from the User Query / Response Interface can be transmitted to the Prompt design component. The Prompt design component can be used to generate prompts suitable for inputting the user input into an LLM or LMM. The Prompt design component 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 can access a knowledge component containing user preference data, a prompt library, and prompt examples based on the user input to generate prompts and pass the generated prompts to the LLM or LMM. For example, the Prompt design component can obtain prompts for requesting a style analysis of text and / or for generating personalized text, and input the prompts into an AI model.

[0220] The API / Plug-in management component can communicate with external information when additional information is requested when user input is passed as input to a generative model. The API / Plug-in management component establishes a channel for communication with external entities within the AI ​​Interface via APIs, enabling access to various data sources. Furthermore, if an application or service needs to perform an action that ultimately implements user input, rather than an intermediate result, the API / Plug-in management component can request such action via APIs. Information obtained from external sources can be used to generate prompts in the Prompt design component alongside user input, or can be passed as input to the generative model.

[0221] The Refiner component can fine-tune the output from generative models. For example, the Refiner component can verify that the content generated by LLMs and / or LMMs is not irrelevant, biased, or harmful. Furthermore, the Refiner component can determine the degree to which the output matches the user's desired outcome and, if necessary, initiate additional processing. Additionally, the Refiner component can configure and provide users with hints to avoid undesirable output.

[0222] Generative AI models generally refer to artificial intelligence neural networks that generate new forms of data based on user input. Generative AI models may include image-generating models and / or language-generating models. Representative image-generating models include generative adversarial networks (GANs) and variational autoencoders (VAEs), with examples including VAEs and diffusion-based generative models using Transformer architectures. Language-generating models are trained to statistically optimize output based on input values, and examples include models such as CHAT-GPT 3 and CHAT-GPT 4 (e.g., including CHAT-GPT 4o). Additionally, large multimodal models (LMMs) can recognize various forms of data input, such as text, images, and speech, and generate corresponding new data. In some embodiments, when a prompt is input from the prompt design component, the Generative AI Model can generate style information and / or personalized text corresponding to the prompt.

[0223] As described above, according to one embodiment, an electronic device (e.g., 200 of FIG. 2) may include a display (e.g., 230 of FIG. 2), a memory (e.g., 220 of FIG. 2) for storing instructions, and at least one processor (e.g., 210 of FIG. 2) including a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display an execution screen of an application on the display, and, when a user input for generating personalized text based on text entered on the execution screen of the application is received, acquire style information corresponding to the application from among style information corresponding to each of a plurality of applications stored in the memory, input a prompt acquired based on the style information corresponding to the application and the entered text into an artificial intelligence model to acquire the personalized text, and display the personalized text on the execution screen of the application. The style information corresponding to each of the plurality of applications may be acquired based on text previously entered into each of the plurality of applications.

[0224] For example, the memory may store style information mapped to identification information of each of the plurality of applications. When the instructions are individually or collectively executed by the at least one processor, the electronic device may obtain style information mapped to the identification information of the application from among the style information mapped to the identification information of each of the plurality of applications, thereby obtaining style information corresponding to the application.

[0225] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to: map the input text to identification information of the application and store the input text in the memory based on text input into the application; obtain a prompt for requesting analysis of a style of the text based on text mapped to the identification information of the application based on a number of texts mapped to the identification information of the application being greater than or equal to a preset number; input the prompt into the artificial intelligence model to obtain style information from the artificial intelligence model; and map the style information to the identification information of the application and store the style information in the memory.

[0226] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain text input into the message application for transmission to a plurality of counterparts based on the application being a message application, obtain style information corresponding to each of the plurality of counterparts based on the obtained text, and map the obtained style information to identification information of each of the plurality of counterparts and store the mapped style information in the memory.

[0227] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, when a user input is received for generating a personalized text based on text entered on an execution screen of the message application to be transmitted to a counterpart among a plurality of counterparts, obtain style information corresponding to the counterpart among style information corresponding to each of the plurality of counterparts, input a prompt obtained based on the style information corresponding to the counterpart and the entered text into the artificial intelligence model to obtain the personalized text, and display the personalized text on the execution screen of the message application.

[0228] For example, the style information may include information about at least one of the following: a character analysis of the user who wrote the text, linguistic characteristics, personality characteristics of the user, tone of sentences, length of sentences, the way the user refers to people or pets, usage patterns of punctuation marks, usage patterns of symbols, usage patterns of emojis, phrases used at the beginning or end of sentences, sentence division methods, emotional expression methods, and words frequently used before and after specific symbols.

[0229] For example, the personalized text generated by the artificial intelligence model may include at least one sentence related to the subject of the text entered on the execution screen of the application and generated based on at least one piece of information included in the style information.

[0230] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to change the text entered in a text input field of the execution screen to the personalized text based on a user input selecting the personalized text displayed on the execution screen.

[0231] For example, the above artificial intelligence model may be LLM.

[0232] According to one embodiment of the present invention, a personalized text providing method of an electronic device as described above may include an operation of displaying an execution screen of an application, an operation of obtaining style information corresponding to an application from among style information corresponding to each of a plurality of applications stored in a memory of the electronic device when a user input for generating personalized text based on text entered on the execution screen of the application is received, an operation of inputting a prompt obtained based on the style information corresponding to the application and the entered text into an artificial intelligence model to obtain the personalized text, and an operation of displaying the personalized text on the execution screen of the application. The style information corresponding to each of the plurality of applications may be obtained based on text previously entered into each of the plurality of applications.

[0233] For example, the memory may store style information mapped to the identification information of each of the plurality of applications. The operation of obtaining the style information may include an operation of obtaining style information corresponding to the application by obtaining style information mapped to the identification information of the application among the style information mapped to the identification information of each of the plurality of applications.

[0234] For example, a personalized text provision method may further include an operation of mapping the input text to identification information of the application and storing the input text in the memory based on text input into the application, an operation of obtaining a prompt for requesting analysis of the style of the text based on text mapped to the identification information of the application based on the number of texts mapped to the identification information of the application being greater than or equal to a preset number, an operation of inputting the prompt into the artificial intelligence model and obtaining style information from the artificial intelligence model, and an operation of mapping the style information to the identification information of the application and storing the style information in the memory.

[0235] For example, a personalized text provision method may further include an operation of obtaining text input into the message application for transmission to a plurality of counterparts based on the application being a message application, an operation of obtaining style information corresponding to each of the plurality of counterparts based on the obtained text, and an operation of mapping the obtained style information to identification information of each of the plurality of counterparts and storing the mapped information in the memory.

[0236] For example, a personalized text providing method may further include, when a user input is received for generating a personalized text based on text input on an execution screen of the message application to be sent to a counterpart among a plurality of counterparts, an operation of obtaining style information corresponding to the counterpart among style information corresponding to each of the plurality of counterparts, an operation of inputting a prompt obtained based on the style information corresponding to the counterpart and the input text into the artificial intelligence model to obtain the personalized text, and an operation of displaying the personalized text on the execution screen of the message application.

[0237] For example, the style information may include information about at least one of the following: a character analysis of the user who wrote the text, linguistic characteristics, personality characteristics of the user, tone of sentences, length of sentences, the way the user refers to people or pets, usage patterns of punctuation marks, usage patterns of symbols, usage patterns of emojis, phrases used at the beginning or end of sentences, sentence division methods, emotional expression methods, and words frequently used before and after specific symbols.

[0238] For example, the personalized text generated by the artificial intelligence model may include at least one sentence related to the subject of the text entered on the execution screen of the application and generated based on at least one piece of information included in the style information.

[0239] For example, the displayed action may include an action of changing the text entered in a text input field of the execution screen to the personalized text based on a user input selecting the personalized text displayed on the execution screen.

[0240] For example, the above artificial intelligence model may be LLM.

[0241] Various embodiments of the present document may be implemented as software including one or more instructions stored in a storage medium (e.g., memory (220)) readable by a machine (e.g., electronic device (200)). For example, a processor (e.g., processor (210)) of the machine (e.g., electronic device (200)) 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.

[0242] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). ™) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0243] 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 an electronic device (200), display (230); Memory (220) for storing instructions; and At least one processor (210) comprising processing circuitry; The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Display the application's execution screen on the above display, When a user input for generating personalized text based on text entered on the execution screen of the above application is received, style information corresponding to the application is acquired from among style information corresponding to each of a plurality of applications stored in the memory, The personalized text is obtained by inputting the style information corresponding to the application and the prompt obtained based on the input text into an artificial intelligence model, To display the personalized text on the execution screen of the application, Style information corresponding to each of the above multiple applications is: An electronic device, wherein the plurality of applications are obtained based on text previously entered into the application.

2. In paragraph 1, The above memory stores style information mapped to the identification information of each of the plurality of applications, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that obtains style information mapped to the identification information of the application among the style information mapped to the identification information of each of the plurality of applications, thereby obtaining style information corresponding to the application.

3. In paragraph 2, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Based on the text entered into the application, the entered text is mapped to the identification information of the application and stored in the memory, Obtain a prompt for requesting analysis of the style of the text based on the text mapped to the identification information of the application, based on the number of texts mapped to the identification information of the application being greater than or equal to a preset number; By inputting the above prompt into the above artificial intelligence model, style information is obtained from the above artificial intelligence model, An electronic device that stores the style information in the memory by mapping it to the identification information of the application.

4. In any one of paragraphs 1 to 3, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Based on the above application being a message application, obtaining the text entered into the message application for transmission to the other party for each of the plurality of other parties, Based on the acquired text, style information corresponding to each of the plurality of counterparts is acquired, An electronic device that maps the acquired style information to the identification information of each of the plurality of counterparties and stores the mapped information in the memory.

5. In paragraph 4, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: When a user input is received to generate a personalized text based on the text entered on the execution screen of the message application to be sent to a counterpart among a plurality of counterparts, style information corresponding to the counterpart is acquired from among the style information corresponding to each of the plurality of counterparts, By inputting the style information corresponding to the counterpart and the prompt obtained based on the input text into the artificial intelligence model, the personalized text is obtained, An electronic device that displays the personalized text on the execution screen of the message application.

6. In any one of paragraphs 1 to 5, The above style information is, An electronic device comprising information about at least one of the following: a character analysis of the user who wrote the text, linguistic characteristics, personality characteristics of the user, tone of sentences, length of sentences, the way the user refers to people or pets, punctuation usage patterns, symbol usage patterns, emoji usage patterns, phrases used at the beginning or end of sentences, sentence division methods, emotional expression methods, and words frequently used before and after specific symbols.

7. In paragraph 6, The personalized text generated by the above artificial intelligence model is: An electronic device comprising at least one sentence associated with the subject of text entered on the execution screen of the application and generated based on at least one piece of information included in the style information.

8. In any one of paragraphs 1 to 7, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: An electronic device that changes the text entered in a text input field of the execution screen to the personalized text based on a user input selecting the personalized text displayed on the execution screen.

9. In any one of paragraphs 1 to 8, The above artificial intelligence model is an electronic device that is a large language model (LLM).

10. In a method for providing personalized text on an electronic device, Action to display the application's execution screen (1210); When a user input for generating personalized text based on text entered on the execution screen of the application is received, an operation (1250, 1260) of acquiring style information corresponding to the application from among style information corresponding to each of a plurality of applications stored in the memory of the electronic device; An operation (1270, 1280) of obtaining the personalized text by inputting the style information corresponding to the application and the prompt obtained based on the input text into an artificial intelligence model; and An action (1290) of displaying the personalized text on the execution screen of the application; Style information corresponding to each of the above multiple applications is: A method for providing personalized text, obtained based on text previously entered into an application for each of the above multiple applications.

11. In paragraph 10, The above memory stores style information mapped to the identification information of each of the plurality of applications, The action of obtaining the above style information is: A personalized text provision method, comprising: an operation of obtaining style information mapped to the identification information of the application from among the style information mapped to the identification information of each of the plurality of applications, thereby obtaining style information corresponding to the application.

12. In paragraph 11, An operation of storing the entered text in the memory based on the text entered in the application and mapping the entered text to the identification information of the application; An action of obtaining a prompt for requesting analysis of the style of the text based on the text mapped to the identification information of the application, based on the number of texts mapped to the identification information of the application being greater than or equal to a preset number; An operation of inputting the above prompt into the artificial intelligence model to obtain style information from the artificial intelligence model; and A personalized text providing method, further comprising: an operation of mapping the style information to the identification information of the application and storing the same in the memory.

13. In any one of paragraphs 10 to 12, An operation of obtaining text entered into the message application for transmission to a plurality of counterparts based on the application being a message application; An operation of obtaining style information corresponding to each of the plurality of counterparts based on the obtained text; and A personalized text provision method further comprising: an operation of mapping the acquired style information to the identification information of each of the plurality of counterparties and storing the same in the memory.

14. In paragraph 13, When a user input is received for generating a personalized text based on a text entered on the execution screen of the message application to be sent to a counterpart among a plurality of counterparts, an operation of acquiring style information corresponding to the counterpart among style information corresponding to each of the plurality of counterparts; An operation of obtaining the personalized text by inputting a prompt obtained based on the style information corresponding to the counterpart and the input text into the artificial intelligence model; and A personalized text providing method, further comprising: an action of displaying the personalized text on the execution screen of the message application.

15. In any one of paragraphs 10 to 14, The above style information is, A method for providing personalized text, comprising information about at least one of the following: a character analysis of the user who wrote the text, linguistic characteristics, personality characteristics of the user, tone of sentences, length of sentences, the way the user refers to people or pets, punctuation usage patterns, symbol usage patterns, emoji usage patterns, phrases used at the beginning or end of sentences, sentence division methods, emotional expression methods, and words frequently used before and after specific symbols.

Images