Electronic device and electronic device file management method

Abstract

An electronic device according to various embodiments of the present document may comprise a display, a memory, and at least one processor operatively connected to the display and the memory. The memory can store instructions that can be executed by the at least one processor and that, when executed, instruct the electronic device to: identify, in an application being executed, an event that triggers file selection; in response to the event, generate a prompt including a request for context information related to data provided on the application; transmit the generated prompt to an AI model; obtain, from the AI model, context information corresponding to the prompt; retrieve one or more files on the basis of the context information; and configure a file selection interface capable of selecting at least one from among the one or more retrieved files, so as to provide the file selection interface through the display. Other various embodiments are possible.

Description

Electronic devices and electronic device file recommendation methods

[0001] This document relates to electronic devices, and, for example, to a method of recommending files on an electronic device.

[0002] Electronic devices can store various files such as documents, images, videos, and music. When a user wishes to select a specific file on an electronic device, they can launch a picker provided by a running application or file manager, and the picker can present a list of multiple files for the user to select. For example, when the picker is launched, the first screen may display recently saved or modified files, files of a specific format, or the storage location where the files are stored (e.g., internal storage, SD card, cloud storage).

[0003] The picker can provide files in a hierarchical form such as a folder structure, and the user can select a file to display or share by its file name or thumbnail.

[0004] Electronic devices can store various files, and with a standard picker, it may take a long time and effort for a user to select the desired file from the stored files.

[0005] An electronic device according to the present disclosure (or specification, invention) may include a display, a memory, and at least one processor operatively connected to the display and the memory.

[0006] According to one embodiment, the memory may be executed by at least one processor, and when executed, the electronic device may store instructions for detecting an event that triggers a file selection in an application being executed, generating a prompt including a request for context information related to data provided on the application in response to the event, transmitting the generated prompt to an AI model, obtaining context information corresponding to the prompt from the AI ​​model, searching for at least one file based on the context information, and configuring a file selection interface capable of selecting at least one of the searched at least one file, and providing the information through the display.

[0007] A file recommendation method for an electronic device according to various embodiments of the present document may include: an operation of identifying an event that triggers a file selection in a running application; an operation of generating a prompt including a request for context information related to data provided on the application in response to the event; an operation of transmitting the generated prompt to an AI model; an operation of obtaining context information corresponding to the prompt from the AI ​​model; an operation of searching for at least one file based on the context information; and an operation of configuring and providing a file selection interface capable of selecting at least one of the searched at least one file.

[0008] A computer-readable non-transient recording medium according to various embodiments of the present document may store instructions for performing operations such as identifying an event that triggers a file selection in a running application, generating a prompt including a request for context information related to data provided on the application in response to the event, transmitting the generated prompt to an AI model, obtaining context information corresponding to the prompt from the AI ​​model, searching for at least one file based on the context information, and configuring and providing a file selection interface capable of selecting at least one of the searched at least one file.

[0009] According to various embodiments of this document, an electronic device and a file recommendation method for the electronic device can be provided, which utilize AI technology to understand the user's situation and, accordingly, enable the user to quickly select the desired file.

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

[0011] FIG. 2 illustrates a file selection interface screen according to one embodiment.

[0012] FIG. 3 is a block diagram of an electronic device according to one embodiment.

[0013] FIG. 4 illustrates software modules for providing a file selection interface based on context information according to one embodiment.

[0014] FIG. 5 illustrates the process of selecting a file through a file selection interface in a message application according to one embodiment.

[0015] FIG. 6 illustrates the process of selecting a file through a file selection interface in an email application according to one embodiment.

[0016] FIG. 7 is a flowchart of a method for selecting data for extracting context information in a message application according to one embodiment.

[0017] FIG. 8 is a block diagram of an electronic device and an AI model according to one embodiment.

[0018] FIG. 9 is a flowchart of a method for an electronic device according to one embodiment to configure a file selection interface.

[0019] FIG. 10 illustrates a file selection interface according to one embodiment.

[0020] FIG. 11 illustrates a file selection interface according to one embodiment.

[0021] FIG. 12 is a flowchart of a file recommendation method for an electronic device according to one embodiment.

[0022] Hereinafter, embodiments of this document are described in detail with reference to the drawings so that those skilled in the art can easily implement them. However, this document may be implemented in various different forms and is not limited to the embodiments described herein. In relation to the description of the drawings, identical or similar reference numerals may be used for identical or similar components. Additionally, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and brevity.

[0023] FIG. 1 is a block diagram of an electronic device (101) in a network environment (100) according to various embodiments.

[0024] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0025] The processor (120) can control at least one other component (e.g., hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., program (140)), for example, and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., sensor module (176) or communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., central processing unit or application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., graphics processing unit, neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0026] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or through a separate server (e.g., server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers.An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0027] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, software (e.g., program (140)) and input data or output data for related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0028] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0029] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0030] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0031] The display module (160) can visually provide information to an external (e.g., user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling said device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of the force generated by said touch.

[0032] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0033] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0034] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0035] The connection terminal (178) may include a connector through which the electronic device (101) can be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0036] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that can be perceived by the user through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0037] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0038] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0039] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0040] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0041] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), full-dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large-scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), external electronic device (e.g., electronic device (104)), or network system (e.g., second network (199)). According to one embodiment, the wireless communication module (192) may support a Peak data rate (e.g., 20 Gbps or more) for eMBB realization, loss coverage (e.g., 164 dB or less) for mMTC realization, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for URLLC realization.

[0042] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0043] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0044] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0045] According to one embodiment, commands or data may be transmitted or received between an electronic device (101) and an external electronic device (104) through a server (108) connected to a second network (199). Each of the external electronic devices (102, or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In one embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within a second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0046] FIG. 2 illustrates a file selection interface screen according to one embodiment.

[0047] According to one embodiment, an electronic device (200) (e.g., the electronic device (101) of FIG. 1) may provide a file selection interface for selecting at least one file among the files stored in the electronic device (200) when an event triggering file selection is detected in a running application. The file selection interface may be referred to as a picker, a file explorer, etc.

[0048] According to one embodiment, the electronic device (200) can install and run various applications, and some applications may provide a file selection interface. For example, applications such as messages, email, calendar, or notes may provide a file selection interface that allows selecting, executing, sending, and / or sharing at least one file.

[0049] According to one embodiment, the application may provide its own interface (or picker) provided by the application, or provide a file selection interface provided by a separate system application (e.g., a file manager application).

[0050] According to one embodiment, the first screen of the file selection interface may list recently modified files or files of a specific format, or provide items of storage where files can be stored (e.g., internal storage, SD card, cloud storage).

[0051] Figures 2a and 2b show examples of the first screen of a file selection interface.

[0052] Referring to FIG. 2a, the file selection interface may provide a recent file item (210) that can call a list of recent files that have been recently saved, selected, and / or changed, category items (220) that can call a list of files belonging to a specific category such as images, videos, audio files, documents, downloads, and installation files, and items (230) corresponding to the storage where the files are stored.

[0053] Referring to FIG. 2b, the file selection interface may display items (240) that can call a list of files belonging to specific categories such as images, audio, and video, items (250) corresponding to other applications that can call a list of files such as Gallery and My Files, and items (260) of recently saved, selected, and / or changed files.

[0054] According to one embodiment, an electronic device (200) can select a specific file based on user input on a file selection interface such as FIG. 2a or FIG. 2b, and can perform functions such as selection, execution, transmission, and / or sharing based on user input for the selected file.

[0055] If a file selection interface such as that shown in Fig. 2a or Fig. 2b is provided, the process of finding the file the user wants among various files stored in the electronic device (200) or network is required, but there is a disadvantage that such file search requires a lot of time and effort and is not intuitive.

[0056] Hereinafter, various embodiments for providing a function to recommend files in a file selection interface, which understands the user's situation through context analysis using an AI model and enables the user to quickly select the desired file, will be described through FIGS. 3 to 12.

[0057] FIG. 3 is a block diagram of an electronic device according to one embodiment.

[0058] Referring to FIG. 3, the electronic device (300) may include a communication circuit (340), a display (330), a processor (310), and a memory (320). Various embodiments of this document may be implemented even if some of the illustrated configurations are omitted or replaced with other configurations. In addition to the illustrated configurations, the electronic device (300) may further include at least some of the configurations and / or functions of the electronic device (101) of FIG. 1. At least some of each of the illustrated (or unillustrated) components of the electronic device (300) may be operatively, functionally, and / or electrically connected.

[0059] According to one embodiment, some of the components of the electronic device (300) (e.g., processor (310), memory (320), communication circuit (340)) may be placed inside the housing of the electronic device (300), and some other components (e.g., display (330)) may have at least some of their parts exposed outside the housing.

[0060] According to one embodiment, the electronic device (300) can be implemented as a device of various form factors in which the display area can be expanded, such as a foldable type, a rollable type (or a sliderable type).

[0061] According to one embodiment, the display (330) can display various images provided by the processor (310). For example, the display (330) may be implemented as any one of a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display, a micro electro mechanical systems (MEMS) display, or an electronic paper display, but is not limited thereto. The display (330) may be configured as a touch screen that detects touch and / or proximity touch (or hovering) input using a part of the user's body (e.g., a finger) or an input device (e.g., a stylus pen). The display (330) may include at least some of the configurations and / or functions of the display module (160) of FIG. 1.

[0062] According to one embodiment, the communication circuit (340) may include various configurations to support wireless communication with an external device. For example, the electronic device (300) may perform cellular wireless communication (e.g., 4G LTE (long term evolution), 5G NR (new radio)) and / or short-range wireless communication (e.g., Wi-Fi, Bluetooth) through the communication circuit (340), and there is no fixed type of wireless communication supported by the electronic device (300). The communication circuit (340) may include at least some of the configurations and / or functions of the communication module (190) of FIG. 1.

[0063] According to one embodiment, the memory (320) may include volatile memory and non-volatile memory and may store various data temporarily or permanently. The memory (320) may include at least some of the configuration and / or functions of the memory (130) of FIG. 1 and may store the program (140) of FIG. 1.

[0064] According to one embodiment, the memory (320) can store various instructions that can be executed by the processor (310). Such instructions may include control commands such as arithmetic and logical operations, data movement, and / or input / output that can be recognized by the processor (310).

[0065] According to one embodiment, the processor (310) may be configured to perform operations or data processing regarding the control and / or communication of each component of the electronic device (300), and may be composed of one or more processors. The processor (310) may include at least some of the configuration and / or functions of the processor (120) of FIG. 1.

[0066] According to one embodiment, there are no limitations on the computation and data processing functions that the processor (310) can implement on the electronic device (300); however, this document describes various embodiments for obtaining context information from data on an application, extracting files corresponding to the context information, and providing a file selection interface. The operations of the processor (310) described below can be performed by loading instructions stored in memory (320).

[0067] In this document, the description that a processor (310) can perform a certain operation (or function, task, or operation) may be interpreted substantially as meaning that an instruction (or command, computer program) causing the electronic device (300) (or processor (310)) to perform said operation is stored in memory (320) (e.g., non-volatile memory, storage). Additionally, the description that a processor (310) can perform a certain operation may be interpreted substantially as meaning that at least one processor, without a fixed number, can perform said operation.

[0068] According to one embodiment, the electronic device (300) may install and run various applications, and some applications may provide a file selection interface (or picker) that allows a user to select at least one file. For example, applications such as messages, email, calendar, or notes may provide a file selection interface that allows selecting, executing, sending, and / or sharing at least one file.

[0069] According to one embodiment, the processor (310) can detect an event that triggers a file selection in a running application. For example, the event that triggers a file selection may include user input selecting a file attachment item on the execution screen of an application (e.g., message, email).

[0070] According to one embodiment, the processor (310) can analyze the user's context on the application when an event triggering file selection occurs. For example, the processor (310) can analyze context information through an AI model or the analysis function of the application itself.

[0071] According to one embodiment, the processor (310) can obtain context information related to data provided on an application using an AI model. According to one embodiment, the AI ​​model may be an on-device artificial intelligence model. The on-device AI model may be operated by the processor (310) or / or through a neural processing unit (NPU) independent of the processor (310). According to another embodiment, the AI ​​model may be implemented as a server AI model operating on a server on a network, in which case the electronic device (300) can transmit a generated prompt to the server AI model through a communication circuit (340) and receive a response containing context information from the server AI model.

[0072] According to one embodiment, the processor (310) may acquire context information using either an on-device AI model or a server AI model based on the amount of context to be analyzed or the difficulty of analysis, the load of the electronic device (300), and / or network conditions, or may acquire context information by having the on-device AI model and the server AI model collaborate.

[0073] According to one embodiment, the processor (310) may generate a prompt containing a request for context information related to data provided on the application in response to an event that triggers a file selection. Since the application is aware of data generated on the application (e.g., text, image, and / or video data entered by a user or counterpart in a messaging application), it may put such information into the prompt to transmit such information to the AI ​​model so that the AI ​​model can analyze the context information.

[0074] According to one embodiment, the processor (310) may generate a prompt including information related to categories to which text data and / or image data and / or files belong, based on user input in an application. The processor (310) may generate a prompt including further descriptions related to categories to which files belong. An example of a prompt generated by the processor (310) and transmitted to an AI model will be described in more detail through FIG. 4.

[0075] According to one embodiment, an AI model can analyze context information corresponding to application data (e.g., message data) based on a received prompt. The AI ​​model can generate context information including information about the category of a file associated with the application data.

[0076] According to one embodiment, context information may include file attribute information and file content analysis information.

[0077] According to one embodiment, the file attribute information may include information related to general file attributes. For example, the attribute information may include information such as a filename, file type, file extension, and / or date.

[0078] According to one embodiment, the content analysis information of a file may include information related to the content of the data contained in the file. For example, the context analysis information may include places, people, documents, objects, landscapes, or events in the case of an image or video file, include meta information such as albums or artist names in the case of an audio file, and include text information contained in the document in the case of a document file.

[0079] According to one embodiment, the processor (310) can obtain context information corresponding to a prompt from an AI model.

[0080] According to one embodiment, the processor (310) can search for at least one file based on context information. For example, the processor (310) can search for files stored in the memory (320) of the electronic device (300) or files obtainable through a network based on context information. The processor (310) can search for files corresponding to the context information using various databases (or search functions), such as a media provider, a search engine, and / or a content management hub (CMH).

[0081] According to one embodiment, the processor (310) may determine one of the databases to be used for searching based on the type of context information obtained. For example, the processor (310) may search for files corresponding to file attribute information (e.g., filename, file type, file extension, date) using a media provider (or a first database), and search for files corresponding to file content analysis information (e.g., place, person, document, object, landscape, or event) using a search engine and / or CMH (or a second database).

[0082] According to one embodiment, the processor (310) may determine the database to be used for searching for files based on the recipient of the file transfer on the application (e.g., the recipient of a message or email). For example, if the recipient of a message or email is a person with a high degree of private intimacy, such as family or friends, at least one file may be searched in a database where private data is stored and a database where public data is stored among the storage spaces for storing files, and if the recipient is a person with a public relationship, such as a coworker, at least one file may be searched only in a database where public data is stored.

[0083] According to one embodiment, the processor (310) can obtain context information through the application's own analysis without using an AI model. For example, the processor (310) can call the application's picker by putting context information supported by the application's picker into an intent (e.g., keyword, file type, etc.) in a predefined format. In this case, files can be recommended according to the information transmitted from the application's picker. For example, when a user enters a schedule in a calendar application, keywords such as Jeju Island or travel can be transmitted from the picker based on the entered schedule, and Jeju Island can be transmitted as a place. Among image information, if the schedule is transmitted as a document item, images classified as schedules can be recommended. Additionally, if Jeju Island is transmitted as a file content item among document information, files containing the text "Jeju Island" among document files can be recommended.

[0084] According to one embodiment, the processor (310) may configure a file selection interface capable of selecting at least one of at least one searched file and provide it through a display (330).

[0085] According to one embodiment, the processor (310) can display files found on a file selection interface by classifying them into categories. For example, if the context information includes an image as a file type and a valley as a landscape, the processor (310) can display at least one file belonging to the image category in one area of ​​the file selection interface and at least one file belonging to the valley category in another area.

[0086] According to one embodiment, the processor (310) may display at least one file as a recommended file on a file selection interface. For example, if the context information includes analysis information regarding the file's attribute information and content, the processor (310) may provide at least one file belonging to the category of the file's attribute information and the category of the analysis information regarding content to the recommended file area. Alternatively, the processor (310) may provide at least one file belonging to a plurality of categories as a recommended file, or provide at least one file with high relevance to a specific category as a recommended file.

[0087] The method for configuring the file selection interface will be explained in more detail through Figures 10 and 11.

[0088] According to one embodiment, the processor (310) may configure a file selection interface based on the usage history of files when context information is not obtained. For example, when context information is not obtained, the processor (310) may configure a file selection interface by sorting the files in the order of most recently changed, as shown in FIG. 2.

[0089] According to one embodiment, the processor (310) can attach at least one file selected through a file selection interface on an application. For example, the processor (310) can transmit at least one file selected through a file selection interface on a message application to a counterparty.

[0090] According to one embodiment, the processor (310) may attach a file selected through a file selection interface and then execute the file based on user input regarding the attached file to display it on the display (330). According to one embodiment, the processor (310) may provide context information associated with the file so that the user can check it when the file is executed. For example, if a file mapped to a video or a valley in the context information is provided as a recommended file and executed by the user's selection, the processor (310) may play the video file starting from the point where the valley appears. Additionally, if a file mapped to a document or specific document content in the context information is provided as a recommended file and executed by the user's selection, the processor (310) may highlight and display the part of the document corresponding to the context information.

[0091] Instructions for performing the operation of the electronic device (300) (or processor (310)) described above may be stored in a computer-readable recording medium. The recording medium may be tangible and non-transitory. The recording medium may store one or more computer programs containing the instructions.

[0092] FIG. 4 illustrates software modules for providing a file selection interface based on context information according to one embodiment.

[0093] The context analysis module (410), picker module (420), and search module (430) illustrated in FIG. 4 may each be a software module operated by a processor (e.g., processor (310) of FIG. 3) of an electronic device (e.g., electronic device (300) of FIG. 3). For example, each software module (410, 420, 430) may include independent and reusable codes that perform functions described below, and codes from two or more modules may be used to perform some functions.

[0094] According to one embodiment, the context analysis module (410) can perform an operation of analyzing the context related to data provided on the application. For example, the context analysis module (410) can obtain context information from the conversation content between the user and the counterparty in a message application, or from the content entered in an email application.

[0095] According to one embodiment, when a user wishes to share or attach a file during the use of an application, if the electronic device is an application that supports context analysis, it can execute the picker by obtaining context information supported by the picker through a context analysis module (410). In this case, the context analysis module (410) can analyze the context information through an AI model or the analysis function of the application itself.

[0096] According to one embodiment, context information may include file attribute information and file content analysis information.

[0097] According to one embodiment, the file attribute information may include information related to general file attributes. For example, the attribute information may include information such as a filename, file type, file extension, and / or date. The file attribute information may also be referred to as common information.

[0098] According to one embodiment, the content analysis information of a file may include information related to the content of the data contained in the file. For example, the context analysis information may include places, people, documents, objects, landscapes, or events in the case of an image or video file, include meta information such as albums or artist names in the case of an audio file, and include text information contained in the document in the case of a document file.

[0099] Table 1 shows examples of context information and their descriptions.

[0100] Classification Information Description Attribute Information Filename File Name Keyword The subject or core word of the file File Type Type of file (e.g., image, video, audio, document) File Extension File extension (e.g., jpg, mp4, mp3, pdf) Date Specific date or time Content Analysis Information (Image, Video) Place Specific location or region Name Person Name of a person Document Document Image (e.g., business card, schedule, receipt) Object Word representing a specific object or target (e.g., animal, car, flower, food) Scenery Word describing nature or landscape (e.g., sea, mountain, city, sky) Event Word representing an event or activity (e.g., party, cafe, zoo) Content Analysis Information (Audio) Album Album Name in meta information Artist Artist Name in meta information Content Analysis Information (Document) Document Content Specific text contained within the document

[0101] According to one embodiment, the context analysis module (410) can obtain context information related to data provided on the application using an AI model. For example, the data provided on the application may include text, image, and / or video data entered by a user or counterpart in a message application, text, image, and / or video data entered by a user in an email application, schedule information entered by a user in a calendar application, or data entered by a user in a memo application. According to one embodiment, the context analysis module (410) can generate a prompt to request context information from the AI ​​model. Since the application is aware of the data generated on the application (e.g., text, image, and / or video data entered by a user or counterpart in a message application), it can put the information into the prompt to transmit the information to the AI ​​model so that the AI ​​model can analyze the context information.

[0102] According to one embodiment, the context analysis module (410) can generate a prompt including information related to categories to which text data, image data, and / or files are entered based on user input in the application.

[0103] Table 2 is an example of a prompt containing a request for context information generated by the context analysis module (410).

[0104] / (1) Analysis Request Next (2) Please analyze the sentences of the data obtained from the application and accurately classify them into the designated categories. For keywords, use the main words or file names mentioned in the sentence; if a word falls into another category, please mark it as "None". For file type, use the file type mentioned in the sentence (e.g., images, videos, audios, documents); for file extension, write "None" if not specified in the sentence. For date, write it in yymmdd format if mentioned in the sentence, and exclude future dates. Clearly distinguish between places and scenery. If the file type is images or videos, list the document; if it is audios, list the album and artist; and if it is documents, list the file content. / (2) Sentence of data acquired from the application**Application Data**: XXX / (3) Description of each category - **Keyword**: File name or main word mentioned in the sentence (e.g., Photo) - **File Type**: Type of file mentioned in the sentence (e.g., images, videos, audios, documents) - **File Extension**: File extension mentioned in the sentence (e.g., jpg, mp4, mp3, pdf, ppt) - **Date**: Date mentioned in the sentence (e.g., Yesterday, Today, This Year) - **Place**: Name of region or location mentioned in the sentence (e.g., Busan) - **Person**: Name of person mentioned in the sentence (e.g., Young-cheol) - **Document**: Image of a document mentioned in the sentence (e.g., Business Card, Receipt, Schedule) - **Object**: Object or subject mentioned in the sentence (e.g., Animal, Car, Flower, Food) - **Scenery**: Natural landscape mentioned in the sentence (e.g., Valley) - **Event**: Mentioned in the sentence Event or activity (e.g., 'Party', 'Zoo')- **Album**: Name of the music album mentioned in the sentence (e.g., 'Midnight')- **Artist**: Name of the music artist mentioned in the sentence (e.g., 'Taylor Swift')- **File Content**: Specific text within the file mentioned in the sentence.

[0105] The prompts in Table 2 are examples, and the context analysis module (410) can determine the information included in the prompts based on the AI ​​model used, the characteristics of each application, and / or the presence or absence of supported information. In Table 2 above, the analysis request part (1) may include content regarding how to request the context to be analyzed so that the AI ​​model can understand it. For example, the analysis request part (1) may include content related to examples of context information and explanations described in Table 1 above.

[0106] According to one embodiment, (2) data of a running application (e.g., text, image, and / or video data of a user or counterpart) may be inserted into the data part obtained from the application.

[0107] According to one embodiment, the context analysis module (410) can select recently entered data among the data obtained from the application and insert it into the data part obtained from the application (2). The method for selecting recently entered data will be explained in more detail through FIG. 7.

[0108] Table 3 shows an example of data obtained from a message application and inserted into a prompt for the analysis of context information.

[0109] Hi! How are you? Hi! I'm doing well, even though I've been busy lately. Can you show me some photos from the trip to the valley in Busan yesterday? Oh, right! It was so good, and I did organize the pictures. I'll show them to you. Thanks! Who did you go with? I went with Young-cheol. You'll be surprised when you see the photos.

[0110] Table 4 shows an example of data obtained from an email application and inserted into a prompt for the analysis of context information.

[0111] Subject: 2025 Sales Plan Report To: Team Leader Hello. This is Young-soo, a professional from the Sales Team. We have established the 2025 sales plan and prepared the related report. The report contains detailed information on future sales strategies, goals, and key implementation plans. Please review the attached 2025 Sales Plan PPT file. If you have any questions or any matters requiring further discussion, please feel free to let us know at any time. Thank you.

[0112] According to one embodiment, (3) the description part for each category may include a detailed description of the category of context information that needs to be analyzed. According to one embodiment, the context analysis module (410) may additionally include a detailed description and / or constraints for each category of context information to increase the accuracy of the analysis of the AI ​​model.

[0113] Table 5 shows a detailed description and / or example of constraints for each category of context information.

[0114] Additional Information Explanation Reason Keywords: Request to exclude items because content included in other categories appears as duplicates. Example: The word "image" is analyzed as a keyword and classified as the file type "images." File Type: Classified into commonly used media file types—image, video, audio, and document—and includes file types for which additional information can be provided. File Extension: Request to classify items only when the extension is accurately specified in the context information. Example: There were instances where the response analyzed the file extension "jpg" when the word "photo" was present. Date: Request to convert items mentioned in a sentence into a format recognizable by the picker and exclude future times. Example: Since the word "2025" was present, 2025 was analyzed, but no files created or modified at a future time were found on the device. Place, Scenery: Request to clearly distinguish between place and scenery as they are analyzed interchangeably. Example: When the word "valley" was present, there were instances where it was analyzed as both a place and a landscape. Documents: Information that can be supported when the file type is image or video. Album, Artist: Information that can be supported when the file type is audio. File Content: Information that can be supported when the file type is documents.

[0115] According to one embodiment, the context analysis module (410) can transmit the generated prompt to the AI ​​model. According to one embodiment, the AI ​​model can analyze context information corresponding to the application's data (e.g., message data) based on the received prompt. The AI ​​model can generate context information including information about the category of a file associated with the application's data and transmit it to the context analysis module (410). The context information generated by the AI ​​model based on the prompt will be described in more detail through FIG. 8.

[0116] According to one embodiment, the context analysis module (410) can obtain context information through the application's own analysis without using an AI model. For example, the context analysis module (410) can call the application's picker by putting context information supported by the application's picker into an intent (e.g., keyword, file type, etc.) in a predefined format. In this case, files can be recommended according to the information transmitted from the application's picker. For example, when a user enters a schedule in a calendar application, keywords such as Jeju Island or travel can be transmitted from the picker based on the entered schedule, and Jeju Island can be transmitted as a place. Among image information, if the schedule is transmitted as a document item, images classified as schedules can be recommended. Additionally, if Jeju Island is transmitted as a file content item among document information, files containing the text "Jeju Island" among document files can be recommended.

[0117] According to one embodiment, the context analysis module (410) can transmit context information obtained through self-analysis of the AI ​​model or application to the picker module (420).

[0118] According to one embodiment, the picker module (420) can perform various operations to provide a file selection interface based on context information received from the context analysis module (410). For example, if context information related to an executed application is identified, the picker module (420) may request the search module (430) to search for a file corresponding to the context information. The picker module (420) receives the search results of the files from the search module (430) and can generate a file selection interface based on the received search results and display it through a display (e.g., the display (330) of FIG. 3).

[0119] The file selection interface will be described in more detail through Figures 10 and 11.

[0120] According to one embodiment, the search module (430) can search for files stored in the memory of the electronic device (e.g., the memory (320) of FIG. 3) or files obtainable through a network based on context information received from the picker module (420). For example, the search module (430) can search for files corresponding to the context information using a database such as a media provider, a search engine, and / or a CMH. A media provider can provide information on files stored in the memory of the electronic device. A search engine can provide an integrated search function that enables searching for various files stored in the electronic device through various search methods. A content management hub (CMH) can store and provide image and video-related data used for specialized functions of the electronic device.

[0121] According to one embodiment, the search module (430) may determine one database to use for searching based on the type of acquired context information. For example, the search module (430) may search for files corresponding to attribute information using a media provider for file attribute information such as filename (or keyword), file type, file extension, or date among the context information. The search module (430) may utilize different database information depending on the file type for content analysis information among the context information. For example, in the case of image or video files, it may search through a CMH that stores information analyzing the file, and in the case of audio files or document files that can be searched through meta information, it may search for files containing specific text using a search engine.

[0122] FIG. 5 illustrates the process of selecting a file through a file selection interface in a message application according to one embodiment.

[0123] According to one embodiment, the electronic device (300) can detect an event that triggers a file selection in a running application. For example, the electronic device (300) can detect user input for selecting a file to be delivered or shared with the recipient of a message while a message application is running.

[0124] Referring to FIG. 5a, the electronic device (300) can execute a message application and display it on a display. The message application screen may include a message area (510) containing messages sent by the user of the electronic device (300) and messages received from the other party, and an input area (520) displayed at the bottom of the message area. The electronic device (300) can check user input for additional option items (525) in the input area (520).

[0125] Referring to FIG. 5b, the electronic device (300) can reduce the size of the message area (510) based on user input for additional option items (525) and provide additional option items supported on the message application through the item area (530) provided at the bottom of the input area (522). For example, the item area (530) may include a My File item (532), a Contact item, an Image item, a Scheduled Message item, a Quick Reply Phrase item, a Note item, a Video item, and an Audio item, and each item may provide various data that can be included in a message to be sent to a counterparty according to the user's selection.

[0126] According to one embodiment, the electronic device (300) can detect the occurrence of an event that triggers a file selection based on user input regarding a file item (532). For example, the event that triggers a file selection may include user input selecting a file attachment item on the execution screen of an application (e.g., message, email).

[0127] According to one embodiment, when an event triggering file selection is detected, the electronic device (300) can identify context information corresponding to a written message using an AI model or its own analysis function. For example, the context information may include attribute information of a file and content analysis information of a file corresponding to a message entered by a user and a counterpart. According to one embodiment, the electronic device (300) can select at least some of the messages in a specific conversation session of a message application and transmit them to an analysis or AI model for determining context information. For example, the electronic device (300) can select a predetermined number of messages recently sent or received in a specific conversation session of a message application, messages sent or received during a recent predetermined period, messages displayed on the current screen, or messages written by running the message application in the foreground. According to one embodiment, the electronic device (300) can search for files corresponding to the context information and provide a file selection interface.

[0128] According to one embodiment, the electronic device (300) can generate a prompt requesting analysis of context information and transmit it to an AI model. For example, the electronic device (300) can generate a prompt by inserting a message selected from a specific conversation session of a message application into the application data part (2) of Table 2.

[0129] Referring to FIG. 5c, the electronic device (300) may provide a file selection interface (505) generated based on context information. For example, the file selection interface (505) may include a recommended file area (540) containing recommended files mapped to the context information. In the recommended file area (540), files (542, 544, 546, 548) belonging to both a category classified according to file attribute information and a category classified according to file content analysis information may be displayed.

[0130] According to one embodiment, the electronic device (300) can determine the placement order of each file based on the priority of the files (542, 544, 546, 548) to be displayed in the recommended file area (540). For example, the electronic device (300) can prioritize each recommended file based on information such as the number of mapped contexts and / or the degree of relevance to a specific context for a plurality of recommended files (542, 544, 546, 548), and display them sequentially from the front in order of highest priority.

[0131] According to one embodiment, the electronic device (300) may display a category area (550) containing categories to which files belong at the bottom of a recommendation area (540). For example, the category area (550) may include image items (551), video items (552), audio file items (553), document items (554), download items (555), and installation file items (556). When any one of the items in the category area (550) is selected according to user input, a list of files belonging to that category may be provided.

[0132] According to one embodiment, the electronic device (300) may display a storage space area (560) that includes storage spaces where files can be stored at the bottom of a category area (550). For example, the storage space area (560) includes an internal storage space item (562) and a drive item (564), and when either item is selected, a list of files stored in the corresponding storage space may be provided.

[0133] According to one embodiment, the electronic device (300) can select at least one file based on user input on the file selection interface (505) of FIG. 5c. Referring to FIG. 5d, the electronic device (300) can provide the selected at least one file (570) through the message area (516). For example, if four recommended files (542, 544, 546, 548) are selected according to user input on the file selection interface (505) of FIG. 5c, the electronic device can transmit the selected four files to a counterpart through a message application as shown in FIG. 5d. Accordingly, at least one file selected by the user can be transmitted or shared with a counterpart.

[0134] The message application screen and file selection interface illustrated in FIGS. 5a to 5d are merely one embodiment, and the various embodiments of this document are not limited thereto.

[0135] FIG. 6 illustrates the process of selecting a file through a file selection interface in an email application according to one embodiment.

[0136] According to one embodiment, the electronic device (300) can detect an event that triggers a file selection in a running application. For example, the electronic device (300) can detect user input for selecting a file to send or share with an email recipient while an email application is running.

[0137] Referring to FIG. 6a, the electronic device (300) can run an email application and display it on a display. The email application screen may include a soft keyboard (620) and text (610) written according to user input using the soft keyboard (620). An attachment item (615) may be provided at the top of the text written on the email application screen.

[0138] Referring to FIG. 6b, the electronic device (300) may display an attachment item area (630) in a popup form, which includes items of an application that supports file attachment, based on user input for an attachment item (615). For example, the attachment item area (630) may include a My Files item (632), a Gallery item, a Camera item, a Contacts item, a Calendar item, a Note item, a Map item, a Voice Recording item, a Sound Selector item, a Drive item, and a Photo item, and each item may provide various data that can be included in an email to be sent to a recipient according to the user's selection.

[0139] According to one embodiment, based on user input for my file item (632), the occurrence of an event that triggers a file selection can be confirmed.

[0140] According to one embodiment, when an event triggering file selection is detected, the electronic device (300) can identify context information corresponding to a written email using an AI model or its own analysis function. For example, the context information may include attribute information of a file and content analysis information of a file corresponding to an email entered by a user and / or a counterparty. According to one embodiment, the electronic device (300) can search for files corresponding to the context information and provide a file selection interface.

[0141] According to one embodiment, the electronic device (300) can generate a prompt requesting analysis of context information and transmit it to an AI model. For example, the electronic device (300) can generate a prompt by inserting email content written in an email application into the application data part (2) of Table 2.

[0142] Referring to FIG. 6c, the electronic device (300) may provide a file selection interface (605) generated based on context information. For example, the file selection interface (605) may include a recommended file area (640) containing recommended files (642, 644) that are mapped to the context information. In the recommended file area (640), files belonging to both categories classified according to file attribute information and categories classified according to file content analysis information may be displayed.

[0143] According to one embodiment, the electronic device (300) may display a category area (650) containing categories to which files belong at the bottom of a recommended file area (640). For example, the category area may include image items (651), video items (652), audio file items (653), document items (654), download items (655), and installation file items (656). When any of the items in the category area (650) is selected according to user input, a list of files belonging to that category may be provided.

[0144] According to one embodiment, the electronic device (300) may display a storage space area (660) that includes storage spaces where files can be stored at the bottom of a category area (650). For example, the storage space area (660) includes an internal storage space item (662) and a drive item (662), and when either item is selected, a list of files stored in the corresponding storage space may be provided.

[0145] According to one embodiment, the electronic device (300) can select at least one file based on user input on the file selection interface (605) of FIG. 6c. Referring to FIG. 6d, the electronic device (300) can insert the selected at least one file (670) into a written email (616). Accordingly, when the email is transmitted, the selected at least one file can be sent to the recipient address.

[0146] The email application screen and file selection interface illustrated in FIGS. 6a to 6d are merely one embodiment, and the various embodiments of this document are not limited thereto.

[0147] FIG. 7 is a flowchart of a method for selecting data for extracting context information in a message application according to one embodiment.

[0148] According to one embodiment, the illustrated method may be performed by an electronic device (e.g., the electronic device (300) of FIG. 3), and the technical features described above may be omitted from the description below.

[0149] According to one embodiment, in operation 710, the electronic device may detect an event that triggers a file selection in a running application. For example, the electronic device may detect user input to select a file to be delivered or shared with a message recipient while a message application is running.

[0150] According to one embodiment, in operation 720, the electronic device can select a specified number of messages based on the input time in a message application. For example, since data of the current conversation content is required for the analysis of context information, if a file selection is triggered in a conversation window with the person currently conversing with, messages entered by the user and the other party during a recent predetermined period of time (e.g., 1 hour, 24 hours) can be selected. Alternatively, the electronic device can select a predetermined number (e.g., 20) of messages based on the order in which they were entered. When requesting context analysis including a large amount of message data, errors may occur in the context analysis of the AI ​​model because the message data contains various topics.

[0151] According to one embodiment, the electronic device may select a predetermined number of messages recently transmitted or received in a message application, a message currently displayed on the screen, or a message created by running a visual application in the foreground.

[0152] According to one embodiment, in operation 730, the electronic device can check whether the number of characters in the selected messages exceeds a specified number of characters. For example, the electronic device can specify a standard number of characters for each input language, such as 1,000 characters for Korean and 250 characters for English, and compare it with the number of characters included in the message.

[0153] According to one embodiment, if the number of characters of the selected messages does not exceed the specified number of characters, in operation 740, the electronic device may select the selected number of messages as the input message of the prompt. According to one embodiment, if there is no limit on the number of characters that can be inserted into the prompt, the electronic device may not perform the character count check operation of operation 730 and may determine the message selected in operation 720 as the input message of the prompt.

[0154] According to one embodiment, if the number of characters of the selected messages exceeds a specified number of characters, in operation 750, the electronic device may exclude from the prompt input messages the oldest messages in chronological order from the selected number of messages. For example, the electronic device may exclude past messages, excluding recent messages corresponding to a specified number of characters based on an updated time, which is the time when the message was updated as read or delivered.

[0155] According to one embodiment, in operation 760, the electronic device may generate a prompt to request context information from an AI model. According to one embodiment, the electronic device may generate a prompt including information related to categories to which text data, image data, and / or files are entered based on user input in an application. When a file selection is triggered while a message application is running, the electronic device may generate a prompt including an input message selected in operation 740 or operation 750. The electronic device may transmit the generated prompt to an AI model and receive context information from the AI ​​model as a response to the prompt.

[0156] According to one embodiment, instructions for performing each operation constituting the method may be stored on a tangible and non-transitory computer-readable recording medium.

[0157] FIG. 8 is a block diagram of an electronic device and an AI model according to one embodiment.

[0158] According to one embodiment, the electronic device (300) can obtain context information related to data provided on an application using an AI model (800).

[0159] According to one embodiment, the AI ​​model (800) may be an on-device artificial intelligence model. To implement the on-device AI model, the electronic device (300) may include a neural processing unit (NPU) that processes the machine learning operations of the AI ​​model (800). According to another embodiment, the AI ​​model (800) may be implemented as a server AI model that operates on a server over a network.

[0160] According to one embodiment, the AI ​​model (800) may include a machine learning model trained to extract context information from input data of an application. For example, the machine learning model may be trained or learned through sufficiently large training data to associate attribute information of a file and / or content analysis information of a file corresponding to data (e.g., text, image, video) input by a user on an application such as a message or email. The operation of the AI ​​model (800) may include a learning and inference process of finding patterns in the data, storing them as a generalized regular model, and obtaining results by inputting new data into the learned model.

[0161] According to one embodiment, the AI ​​model (800) may include a large language model (LLM) and / or a generative AI model.

[0162] According to one embodiment, the electronic device (300) can obtain user input data (820) on an application. Here, the user input data (820) is data associated with a context related to file selection, and may include, for example, text, image, and / or video data entered by a user or a counterpart in a message application, text, image, and / or video data entered by a user in an email application, schedule information entered by a user in a calendar application, or data entered by a user in a memo application.

[0163] According to one embodiment, the electronic device (300) can generate a prompt for requesting context information from the AI ​​model (800). The electronic device (300) can generate a prompt including information related to categories to which text data, image data, and / or files are entered based on user input in an application. An example of a prompt including a request for context information generated in the context module of the electronic device (300) has been described above through Table 2.

[0164] According to one embodiment, the electronic device (300) can transmit a generated prompt to the AI ​​model (800). According to one embodiment, the AI ​​model (800) can analyze context information corresponding to the application's data (e.g., message data) based on the received prompt. The AI ​​model (800) can generate context information including information about the category of a file associated with the application's data and transmit it to the electronic device (300).

[0165] Table 6 shows a response containing context information received from the AI ​​model (800) when data obtained from the message application of Table 3 described above is inserted into the prompt of Table 2 and transmitted to the AI ​​model (800).

[0166] Keywords: Photo File Type: images File Extension: None Date: 240826 Location: Busan Person: Yeongcheol Document: None Object: None Landscape: Valley Event: None Album: None Artist: None File Content: None

[0167] Referring to Table 6 above, the AI ​​model (800) can extract information such as keywords, file type and date corresponding to file attribute information as context information, and information such as place, person, and landscape as content analysis information based on data from a message application. According to one embodiment, when an electronic device (300) receives a response such as Table 6 from the AI ​​model (800), it can search for at least one file corresponding to keyword: photo, file type: images, date: 240826, place: Busan, person: Yeongcheol, landscape: valley based on the received context information. The electronic device (300) can provide a file selection interface through the message application that allows the user to select at least some of the searched files.

[0168] Table 7 shows a response containing context information received from the AI ​​model (800) when data obtained from the email application of Table 4 described above is inserted into the prompt of Table 2 and transmitted to the AI ​​model (800).

[0169] Keywords: 2025 Sales Plan, PPT File File Type: documents File Extension: PPT Date: None Location: None Person: Young-soo Pro, Team Leader Document: Sales Plan Report Object: None Scenery: None Event: None Album: None Artist: None File Content: Future sales strategy, goals, and key action plans

[0170] Referring to Table 7 above, the AI ​​model (800) can extract keywords, file type, and file extension corresponding to file attribute information as context information based on data from a message application, and people, documents, and file content as content analysis information. According to one embodiment, when an electronic device (300) receives a response such as Table 7 from the AI ​​model (800), it can search for at least one file corresponding to: keyword: 2025 sales plan, ppt file, file type: documents, file extension: ppt, person: Young-soo Pro, Team Leader, document: sales plan report, file content: future sales strategy, goal, and major execution plan based on the received context information. The electronic device (300) can provide a file selection interface through an email application that allows the user to select at least some of the searched files.

[0171] FIG. 9 is a flowchart of a method for an electronic device according to one embodiment to configure a file selection interface.

[0172] According to one embodiment, the illustrated method may be performed by an electronic device (e.g., the electronic device (300) of FIG. 3), and the technical features described above may be omitted from the description below.

[0173] According to one embodiment, in operation 910, the electronic device may obtain context information from an AI model. The electronic device may generate and transmit a prompt to the AI ​​model to request context information in response to an event that triggers file selection. The context information received from the AI ​​model may include file attribute information and / or content analysis information. Here, the file attribute information may include information related to general file attributes. For example, the attribute information may include information such as filename, file type, file extension, and / or date. The file content analysis information may include information related to the content of the data contained in the file. For example, the content analysis information may include places, people, documents, objects, landscapes, or events in the case of an image or video file, include meta-information such as albums and artist names in the case of an audio file, and include text information contained in the document in the case of a document file. For example, the context analysis information may include information analyzed by an AI engine. For example, the electronic device may use an AI engine to generate and store summary information for images, video files, audio files, and document files.

[0174] According to one embodiment, in operation 920, the electronic device can determine whether both file attribute information and content analysis information are obtained from context information received from an AI model. According to one embodiment, if both file attribute information and content analysis information are obtained, in operation 940, the electronic device can provide recommended files and files separated by category through a file selection interface. For example, the electronic device can display files belonging to a specific category of file attribute information (e.g., filename, file type, file extension, date) and files belonging to a specific category of content analysis information (e.g., place, person, document, object, landscape, or event in the case of an image or video file; album, artist name in the case of an audio file; text information contained in a document in the case of a document file) separated by category, and at least one file belonging to both the category of file attribute information and the specific category of content analysis information can be displayed as a recommended file.

[0175] According to another embodiment, the electronic device may provide at least one file belonging to a plurality of categories among the categories of file attribute information and the categories of content analysis information as a recommended file, and / or display at least one file highly relevant to at least one category as a recommended file.

[0176] According to one embodiment, in operation 930, the electronic device can determine whether only one of file attribute information or content analysis information is obtained from context information received from an AI model. According to one embodiment, if only one of file attribute information or content analysis information is obtained, in operation 950, the electronic device can provide files separated by category through a file selection interface. For example, the electronic device can display files belonging to a specific category of file attribute information or files belonging to a specific category of content analysis information separated by category. In operation 950, the electronic device may not display separate recommended files. According to another embodiment, if multiple categories are obtained from file attribute information or multiple categories are obtained from content analysis information through context information, the electronic device can display at least one file belonging to multiple categories among the searched files as a recommended file. According to one embodiment, if neither file attribute information nor content analysis information is obtained, in operation 960, the electronic device can configure a file selection interface based on previous usage history. This is a case where the context information generated by the AI ​​model does not include both file attribute information and content analysis information, or where the AI ​​model sends a response indicating that the context information is not extracted, and the file selection interface (e.g., the file selection interface of (a) or (b) in FIG. 2) can be configured in the order of recent saved, selected, and / or changed without separate recommendations.

[0177] According to one embodiment, instructions for performing each operation constituting the method may be stored on a tangible and non-transitory computer-readable recording medium.

[0178] FIGS. 10 and 11 illustrate a file selection interface according to one embodiment.

[0179] According to one embodiment, the electronic device (300) may obtain context information from an AI model, search for at least one file using the context information, and configure a file selection interface using at least one searched file.

[0180] According to one embodiment, the electronic device (300) may display files searched in a file selection interface by category and display at least one file as a recommended file. In this case, the electronic device (300) may provide at least one file belonging to a plurality of categories as a recommended file, or provide at least one file with high relevance to a specific category as a recommended file.

[0181] According to one embodiment, the electronic device (300) can identify the place Seoul and the landscape cafe that belong to the content analysis information of an image or video file, based on context information received from an AI model. The electronic device (300) can search for files corresponding to Seoul and the cafe among the image and video files stored in memory or a network.

[0182] Referring to FIG. 10a, the electronic device (300) can display files corresponding to Seoul (1061, 1062, 1063) among the searched files on the Seoul category area (1020) and files corresponding to Cafe (1064, 1065, 1066) on the Cafe category area (1030).

[0183] According to one embodiment, the electronic device (300) can display files (1063, 1066) belonging to both the Seoul category and the Cafe category on the recommended file area (1010).

[0184] Referring to FIG. 10b, the electronic device (300) may display files corresponding to Seoul (1071, 1072, 1073) among the searched files on the Seoul category area (1025) and files corresponding to Cafe (1074, 1075, 1076) on the Cafe category area (1035). The electronic device (300) may display an attribute category area (1040) containing items corresponding to the file attribute categories of image, video, audio file, document, download, and installation file, respectively, at the bottom of the Seoul category area (1025) and the Cafe category area (1035). When a user selects an image item among the attribute categories, images included in context information (e.g., Seoul, Cafe) among the images stored in the electronic device (300) may be provided, or all stored images may be provided based on history.

[0185] According to one embodiment, if only one of file attribute information or content analysis information is obtained from context information received from an AI model, the electronic device (300) may provide files classified by category through a file selection interface. In this case, the electronic device (300) may not display recommended files separately.

[0186] According to one embodiment, the electronic device (300) can determine from context information received from an AI model that only file extensions of pdf belonging to file attribute information are included. In this case, the electronic device (300) can search for files with a file extension of pdf among files stored in memory or a network.

[0187] Referring to FIG. 11a, the electronic device (300) can display files with a file extension of pdf in the pdf category area (1110). The electronic device (300) can display an attribute category area (1120) containing items corresponding to the file attribute categories of images, videos, audio files, documents, downloads, and installation files, respectively, and a storage area (1130) containing items of a storage (e.g., internal storage, drive) where files can be stored, at the bottom of the pdf category area (1110).

[0188] According to one embodiment, the electronic device (300) can confirm from context information received from an AI model that only the place Seoul belonging to the file content analysis information is included. In this case, the electronic device (300) can search for files related to the place Seoul among the files stored in memory or a network.

[0189] Referring to FIG. 11b, the electronic device (300) can display files corresponding to the place Seoul in the Seoul category area (1150). The electronic device (300) can display an attribute category area (1120) and a storage space area (1130) at the bottom of the Seoul category area (1110).

[0190] FIG. 12 is a flowchart of a file recommendation method for an electronic device according to one embodiment.

[0191] According to one embodiment, the illustrated method may be performed by an electronic device (e.g., the electronic device (300) of FIG. 3), and the technical features described above may be omitted from the description below.

[0192] According to one embodiment, in operation 1210, the electronic device can detect an event that triggers a file selection. For example, the event that triggers a file selection may include user input selecting a file attachment item on the execution screen of an application (e.g., message, email).

[0193] According to one embodiment, in operation 1220, the electronic device may generate a prompt including a request for context information related to data provided on an application and transmit it to an AI model. For example, the electronic device may generate a prompt including information related to categories to which text data and / or image data and / or files belong, which are entered based on user input in the application. The electronic device may generate a prompt including further descriptions related to categories to which files belong.

[0194] According to one embodiment, in operation 1230, the electronic device may obtain context information from an AI model. For example, the AI ​​model may generate context information including information about the category of a file associated with the application's data. According to one embodiment, the context information may include file attribute information and file content analysis information. The file attribute information may include information related to general file attributes. The file content analysis information may include information related to the content of the data contained in the file.

[0195] According to one embodiment, in operation 1240, the electronic device can search for at least one file based on context information obtained from an AI model. For example, the electronic device can search for files stored in the memory of the electronic device (e.g., the memory of FIG. 3) or files obtainable through a network based on the context information. The electronic device can search for files corresponding to the context information using a database such as a media provider, a search engine, and / or a CMH. According to one embodiment, the electronic device can determine which database to use for the search based on the type of the obtained context information.

[0196] According to one embodiment, in operation 1250, the electronic device may configure a file selection interface that can select at least one of at least one retrieved file. According to one embodiment, the electronic device may display the retrieved files on the file selection interface by classifying them by category. For example, if the context information includes an image as a file type and a valley as a landscape, the processor may display at least one file belonging to the image category in one area of ​​the file selection interface and at least one file belonging to the valley category in another area.

[0197] According to one embodiment, an electronic device may display at least one file as a recommended file on a file selection interface. For example, if the context information includes file attribute information and analysis information regarding the content, the electronic device may provide at least one file belonging to a category of file attribute information and a category of analysis information regarding the content in the recommended file area. Alternatively, the electronic device may provide at least one file belonging to a plurality of categories as a recommended file, or provide at least one file with high relevance to a specific category as a recommended file.

[0198] According to one embodiment, instructions for performing each operation constituting the method may be stored on a tangible and non-transitory computer-readable recording medium.

[0199] An electronic device according to various embodiments of the present document may include a display, a memory, and at least one processor operatively connected to the display and the memory.

[0200] According to one embodiment, the memory may be executed by at least one processor, and when executed, the electronic device may store instructions for detecting an event that triggers a file selection in an application being executed, generating a prompt including a request for context information related to data provided on the application in response to the event, transmitting the generated prompt to an AI model, obtaining context information corresponding to the prompt from the AI ​​model, searching for at least one file based on the context information, and configuring a file selection interface capable of selecting at least one of the searched at least one file, and providing the information through the display.

[0201] According to one embodiment, the memory may store instructions that cause the electronic device to check text data and / or image data entered based on user input in the application, and to generate the prompt including the entered text data and / or image data.

[0202] According to one embodiment, the memory may store instructions that cause the electronic device to generate the prompt, including descriptions related to the categories to which the file belongs.

[0203] According to one embodiment, the context information may include attribute information of a file and analysis information regarding the content of the file.

[0204] According to one embodiment, the memory may store instructions that cause the electronic device to search for at least one file corresponding to attribute information of the file and at least one file corresponding to analysis information for the content among the files stored in the memory.

[0205] According to one embodiment, the memory may store instructions that cause the electronic device to display at least one retrieved file by classifying it by category.

[0206] According to one embodiment, the memory may store instructions that cause the electronic device to provide at least one of the searched at least one file to an area of ​​recommended files.

[0207] According to one embodiment, the memory may store instructions that cause the electronic device to provide at least one file belonging to the category of the file's attribute information and the category of the content's analysis information to the area of ​​the recommended file, when the context information includes the file's attribute information and the content's analysis information.

[0208] According to one embodiment, the memory may store instructions that cause the electronic device to search for at least one file corresponding to attribute information of the file on a first database and to search for at least one file corresponding to analysis information of the content on a second database.

[0209] According to one embodiment, the memory may store instructions that cause the electronic device to configure the file selection interface based on the usage history of files when the context information is not obtained.

[0210] A file recommendation method for an electronic device according to various embodiments of the present document may include: an operation of identifying an event that triggers a file selection in a running application; an operation of generating a prompt including a request for context information related to data provided on the application in response to the event; an operation of transmitting the generated prompt to an AI model; an operation of obtaining context information corresponding to the prompt from the AI ​​model; an operation of searching for at least one file based on the context information; and an operation of configuring and providing a file selection interface capable of selecting at least one of the searched at least one file.

[0211] According to one embodiment, the operation of generating the prompt may include the operation of verifying text data and / or image data entered based on user input in the application, and the operation of generating the prompt including the entered text data and / or image data.

[0212] According to one embodiment, the operation of generating the prompt may include an operation of generating the prompt including a description related to the categories to which the file belongs.

[0213] According to one embodiment, the context information may include attribute information of a file and analysis information regarding the content of the file.

[0214] According to one embodiment, the operation of searching for at least one file may include searching for at least one file corresponding to attribute information of the file and at least one file corresponding to analysis information for the content among the files stored in the memory.

[0215] According to one embodiment, the operation constituting the file selection interface may include the operation of displaying at least one searched file by category.

[0216] According to one embodiment, the operation constituting the file selection interface may include the operation of providing at least one of the searched at least one file to the recommended file area.

[0217] According to one embodiment, an operation constituting a file selection interface may include, when the context information includes attribute information of the file and analysis information regarding the content, an operation of providing at least one file belonging to a category of attribute information of the file and a category of analysis information regarding the content to an area of ​​recommended files.

[0218] According to one embodiment, the operation of searching for at least one file may include searching for at least one file corresponding to attribute information of the file on a first database and searching for at least one file corresponding to analysis information for the content on a second database.

[0219] A computer-readable non-transient recording medium according to various embodiments of the present document may store instructions for performing operations such as identifying an event that triggers a file selection in a running application, generating a prompt including a request for context information related to data provided on the application in response to the event, transmitting the generated prompt to an AI model, obtaining context information corresponding to the prompt from the AI ​​model, searching for at least one file based on the context information, and configuring and providing a file selection interface capable of selecting at least one of the searched at least one file.

[0220] The electronic device according to the various embodiments disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the devices described above.

[0221] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as “coupled” or “connected” to another (e.g., 2nd) component, with or without the terms “functionally” or “communicationly,” it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0222] The term “module” as used in the various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0223] Various embodiments of the present document may be implemented as software (e.g., program (140)) comprising one or more instructions stored in a storage medium (e.g., internal memory (136) or external memory (138)) readable by a machine (e.g., electronic device (101)). For example, a processor (e.g., processor (120)) of the machine (e.g., electronic device (101)) may call at least one of the one or more instructions stored in the storage medium and execute it. This enables the machine to be operated to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0224] According to one embodiment, the method according to the various embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or an application store (e.g., Play Store). TM It can be distributed online (e.g., downloaded or uploaded) through ) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0225] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device, display; Memory; and The above display, and at least one processor operatively connected to the memory, The above memory can be executed by at least one processor, and at the time of execution, the electronic device, Check for events that trigger file selection in a running application, and In response to the above event, a prompt is generated that includes a request for context information related to data provided on the application, and Pass the above-generated prompt to the AI ​​model, and Obtain context information corresponding to the prompt from the above AI model, and Based on the above context information, search for at least one file, and An electronic device that stores instructions configured to provide at least one of the above-mentioned searched files through a display, configured to select at least one of the above-mentioned searched files.

2. In Paragraph 1, The above memory is, the electronic device, In the above application, text data and / or image data entered based on user input are checked, and An electronic device that stores instructions for generating the prompt, including the input text data and / or image data.

3. In Paragraph 2, The above memory is, the electronic device, An electronic device that stores instructions for generating the above prompt, including descriptions related to the categories to which the file belongs.

4. In any one of paragraphs 1 to 3, The above context information is an electronic device including file attribute information and analysis information about the content of the file.

5. In Paragraph 4, The above memory is, the electronic device, An electronic device storing instructions for searching among the files stored in the memory, at least one file corresponding to attribute information of the file, and at least one file corresponding to analysis information for the content.

6. In Paragraph 4 or 5, The above memory is, the electronic device, An electronic device that stores instructions for displaying at least one file found above by classifying it into categories.

7. In any one of paragraphs 4 through 6, The above memory is, the electronic device, An electronic device storing instructions that provide at least one of the above-mentioned searched files to an area of ​​recommended files.

8. In Paragraph 7, The above memory is, the electronic device, An electronic device storing instructions for providing at least one file belonging to a category of the file's attribute information and a category of the content's analysis information to an area of ​​the recommended file, wherein the context information includes attribute information of the file and analysis information of the content.

9. In Paragraph 4, The above memory is, the electronic device, An electronic device storing instructions for searching at least one file corresponding to attribute information of the above file in a first database and searching at least one file corresponding to analysis information for the above content in a second database.

10. In any one of paragraphs 1 through 9, The above memory is, the electronic device, An electronic device that stores instructions for configuring the file selection interface based on the usage history of files when the above context information is not obtained.

11. Regarding the file recommendation method of an electronic device, Action to check for an event that triggers file selection in a running application; An operation to generate a prompt including a request for context information related to data provided on the application in response to the above event; The action of transmitting the above-mentioned generated prompt to the AI ​​model; An operation to obtain context information corresponding to the prompt from the above AI model; An operation to search for at least one file based on the above context information; and A method comprising the operation of configuring and providing a file selection interface capable of selecting at least one of the at least one of the above-mentioned searched files.

12. In Paragraph 11, The operation of generating the above prompt is, An operation to verify text data and / or image data entered based on user input in the above application; and A method comprising the operation of generating the prompt including the input text data and / or image data.

13. In Paragraph 12, The operation of generating the above prompt is, A method including the operation of generating the above prompt, including a description related to the categories to which the file belongs.

14. In any one of Paragraphs 11 through 13, A method in which the above context information includes attribute information of a file and analysis information about the content of a file.

15. In a computer-readable non-transient recording medium, Action to check for an event that triggers file selection in a running application; An operation to generate a prompt including a request for context information related to data provided on the application in response to the above event; The action of transmitting the above-mentioned generated prompt to the AI ​​model; An operation to obtain context information corresponding to the prompt from the above AI model; An operation to search for at least one file based on the above context information; and A recording medium storing instructions for performing an operation to configure and provide a file selection interface capable of selecting at least one of the at least one of the above-mentioned searched files.

Images