Electronic device and multi-window layout generation method

Abstract

An electronic device according to various embodiments of the present document may comprise: a display (730); a communication module (740); a memory (720); and at least one processor (710) operatively connected to the display, the communication module, and the memory. The memory may store instructions that are executed by the at least one processor and, when executed, cause the electronic device to execute a first application to display an execution screen of the first application on at least a partial area of the display. The memory may store instructions that cause the electronic device to: detect a first event for triggering configuration of a multi-window layout according to the execution of a second application while the first application is being executed; in response to the detection of the first event, generate a prompt including information related to the detected first event and a task request for requesting the configuration of the multi-window layout; and transfer the generated prompt to an AI model.

Description

How to create electronic devices and multi-window layouts

[0001] This article is about electronic devices, and for example, how electronic devices create or change multi-window layouts.

[0002] Generative AI models (GAIs) are AI models that learn from various data and generate new information and sentences. Generative AI models (hereinafter referred to as AI models) are used in natural language processing, enabling them to understand the context of given information and perform various language tasks. For example, a user can generate prompts and input them into the AI ​​to perform a desired task. These prompts can then guide the AI ​​model to perform the desired task.

[0003] Meanwhile, electronic devices such as smartphones, tablet PCs, or XR (extended reality) devices can run multiple applications simultaneously and display the running application screens in a multi-window layout. Here, the multi-window layout can refer to a method of dividing the entire display area and displaying each application screen in a separate window.

[0004] Configuring the screen with a multi-window layout requires multiple input steps, such as selecting the applications the user wishes to run simultaneously. Furthermore, if the user wishes to change the layout after launching multiple applications in multi-window mode, such as adding new applications or changing the position and / or size of each window, multiple input steps may be required.

[0005] An electronic device according to the present disclosure (or specification, invention) may include a display (730), a communication module (740), a memory (720), and at least one processor (710) operatively connected to the display, the communication module, and the memory.

[0006] According to one embodiment, the memory may store instructions that are executed by at least one processor and, when executed, cause the electronic device to execute a first application and display an execution screen of the first application on at least a portion of the display.

[0007] According to one embodiment, the memory may store instructions that cause the electronic device to detect a first event that triggers configuration of a multi-window layout upon execution of a second application while the first application is running, generate a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout in response to detection of the first event, and transmit the generated prompt to an AI model.

[0008] According to one embodiment, the memory may store instructions that cause the electronic device to receive a task response from the AI ​​model, which includes information related to a multi-window layout to be configured in response to the first event, and to configure a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response, and to display the multi-window layout on at least a portion of the display.

[0009] A method performed by an electronic device according to various embodiments of the present document may include: executing a first application to display an execution screen of the first application; detecting a first event that triggers configuration of a multi-window layout according to execution of a second application while the first application is running; generating, in response to detection of the first event, a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout; transmitting the generated prompt to an AI model; receiving, from the AI ​​model, a task response including information related to a multi-window layout to be configured in response to the first event; and configuring and displaying a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response.

[0010] A computer-readable non-transitory recording medium according to various embodiments of the present document may store instructions for performing an operation of executing a first application to display an execution screen of the first application, an operation of detecting a first event that triggers configuration of a multi-window layout according to execution of a second application while the first application is running, an operation of generating a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout in response to detection of the first event, an operation of transmitting the generated prompt to an AI model, an operation of receiving a task response including information related to a multi-window layout to be configured in response to the first event from the AI ​​model, and an operation of configuring and displaying a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response.

[0011] According to various embodiments of the present document, an electronic device and a method for generating a multi-window layout can be provided, which can configure an appropriate multi-window layout that suits a user's intention by requesting an AI model to perform a task for configuring a multi-window layout and configuring the multi-window layout based on a task response of the AI ​​model.

[0012] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0013] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0014] FIG. 2 is a block diagram illustrating an integrated intelligence system according to one embodiment.

[0015] FIG. 3 is a diagram showing a form in which relationship information between concepts and actions is stored in a database according to one embodiment.

[0016] FIG. 4 is a block diagram of a generative artificial intelligence system according to one embodiment.

[0017] FIGS. 5A and 5B illustrate a method for configuring a multi-window layout on an electronic device according to one embodiment.

[0018] FIG. 6 illustrates an electronic device and an AI model according to one embodiment.

[0019] Figure 7 is a block diagram of an electronic device according to one embodiment.

[0020] FIG. 8 is a block diagram of components that perform operations related to setting a multi-window layout according to one embodiment.

[0021] Figure 9 is a flowchart of a method for configuring a multi-window layout according to one embodiment.

[0022] Fig. 10 is a flowchart of a method for configuring a multi-window layout according to one embodiment.

[0023] FIG. 11 illustrates an example of configuring a multi-window layout according to one embodiment.

[0024] Figure 12 illustrates an example of configuring a multi-window layout according to one embodiment.

[0025] FIG. 13 illustrates an example of configuring a multi-window layout according to one embodiment.

[0026] FIG. 14 illustrates an example of configuring a multi-window layout according to one embodiment.

[0027] Below, various embodiments are described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. In the description of the drawings, the same or similar reference numerals may be used to refer to identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0028] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0029] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0030] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0031] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0032] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0033] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0034] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0035] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0036] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0037] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0038] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0039] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0040] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0041] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0042] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0043] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0044] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0045] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0046] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0047] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0048] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0049] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0050] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In one embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0051] FIG. 2 is a block diagram illustrating an integrated intelligence system according to various embodiments.

[0052] Referring to FIG. 2, according to one embodiment, the integrated intelligence system may include an electronic device (210) (e.g., electronic device (101) of FIG. 1), an intelligent server (230) (e.g., server (108) of FIG. 1), and a service server (250) (e.g., server (108) of FIG. 1).

[0053] According to one embodiment, the electronic device (210) may be a terminal device (or electronic device) that can connect to the Internet, for example, a mobile phone, a smart phone, a personal digital assistant (PDA), a laptop computer, a TV, white goods, a wearable device, an HMD, or a smart speaker.

[0054] According to one embodiment, the electronic device (210) may include a communication interface (213) (e.g., the interface (177) of FIG. 1), a microphone (212) (e.g., the input module (150) of FIG. 1), a speaker (216) (e.g., the audio output module (155) of FIG. 1), a display module (211) (e.g., the display module (160) of FIG. 1), a memory (215) (e.g., the memory (130) of FIG. 1), or a processor (214) (e.g., the processor (120) of FIG. 1). The components listed above may be operatively or electrically connected to each other. The electronic device (210) may include at least some of the configurations and / or functions of the electronic device (101) of FIG. 1.

[0055] In one embodiment, the communication interface (213) may be configured to connect to an external device and transmit and receive data. In one embodiment, the microphone (212) may receive sound (e.g., user speech) and convert it into an electrical signal. In one embodiment, the speaker (216) may output the electrical signal as sound (e.g., voice).

[0056] In one embodiment, the display module (211) may be configured to display an image or video. In one embodiment, the display module (211) may also display a graphical user interface (GUI) of a running app (or application program). In one embodiment, the display module (211) may receive a touch input via a touch sensor. For example, the display module (211) may receive a text input via a touch sensor in an on-screen keyboard area displayed within the display module (211).

[0057] According to one embodiment, the memory (215) may store a client module (218), a software development kit (SDK) (217), and / or a plurality of apps (219a, 219b). The client module (218) and the SDK (217) may form a framework (or solution program) for performing general functions. In addition, the client module (218) or the SDK (217) may form a framework for processing user input (e.g., voice input, text input, or touch input).

[0058] According to one embodiment, the plurality of apps (219a, 219b) stored in the memory (215) may be programs for performing a specified function. According to one embodiment, the plurality of apps may include a first app (219a) or a second app (219b). According to one embodiment, the plurality of apps (219a, 219b) may include a plurality of operations for performing a specified function. For example, the apps (219a, 219b) may include an alarm app, a message app, and / or a schedule app. According to one embodiment, the plurality of apps (219a, 219b) may be executed by the processor (214) to perform at least some of the plurality of operations.

[0059] According to one embodiment, the processor (214) can control the overall operation of the electronic device (210). For example, the processor (214) can be electrically connected to a communication interface (213), a microphone (212), a speaker (216), and a display module (211) to perform a specified operation.

[0060] According to one embodiment, the processor (214) may also execute a program stored in the memory (215) to perform a designated function. For example, the processor (214) may execute at least one of the client module (218) or the SDK (217) to perform the following operations for processing user input. The processor (214) may control the operations of a plurality of apps (219a, 219b), for example, through the SDK (217). The following operations described as operations of the client module (218) or the SDK (217) may be operations executed by the processor (214).

[0061] According to one embodiment, the client module (218) can receive user input. For example, the client module (218) can receive a voice signal corresponding to a user utterance detected through the microphone (212). Alternatively, the client module (218) can receive a touch input detected through the display module (211). Alternatively, the client module (218) can receive a text input detected through a keyboard or a visual keyboard. In addition, the client module (218) can receive various forms of user input detected through an input module included in the electronic device (210) or an input module connected to the electronic device (210). The client module (218) can transmit the received user input to the intelligent server (230). The client module (218) can transmit status information of the electronic device (210) together with the received user input to the intelligent server (230). The status information can be, for example, execution status information of an app.

[0062] In one embodiment, the client module (218) may receive a result corresponding to the received user input. For example, the client module (218) may receive a result corresponding to the received user input if the intelligent server (230) can produce a result corresponding to the received user input. The client module (218) may display the received result on the display module (211). Additionally, the client module (218) may output the received result as audio through the speaker (216).

[0063] According to one embodiment, the client module (218) can receive a plan corresponding to the received user input. The client module (218) can display the results of executing multiple operations of the app according to the plan on the display module (211). For example, the client module (218) can display the results of executing multiple operations on the display module (211) and output audio through the speaker (216). The electronic device (210) can, for another example, display only some results of executing multiple operations (e.g., the result of the last operation) on the display module (211) and output audio through the speaker (216).

[0064] In one embodiment, the client module (218) may receive a request from the intelligent server (230) to obtain information necessary to produce a result corresponding to the voice input. In one embodiment, the client module (218) may transmit the necessary information to the intelligent server (230) in response to the request.

[0065] According to one embodiment, the client module (218) may transmit result information of executing multiple operations according to a plan to the intelligent server (230). The intelligent server (230) may use the result information to confirm that the received user input has been processed correctly.

[0066] In one embodiment, the client module (218) may include a voice recognition module. In one embodiment, the client module (218) may recognize voice inputs that perform limited functions through the voice recognition module. For example, the client module (218) may execute an intelligent app that processes voice inputs to perform organic actions based on a specified input (e.g., "Wake up!").

[0067] According to one embodiment, the intelligent server (230) can receive information related to a user voice input from an electronic device (210) via a communication network. According to one embodiment, the intelligent server (230) can convert data related to the received voice input into text data. According to one embodiment, the intelligent server (230) can generate a plan for performing a task corresponding to the user voice input based on the text data.

[0068] In one embodiment, the plan may be generated by an artificial intelligence (AI) system. The AI ​​system may be a rule-based system, a neural network-based system (e.g., a feedforward neural network (FNN) or a recurrent neural network (RNN)), or a combination of the foregoing or another AI system. In one embodiment, the plan may be selected from a set of defined plans or may be generated in real time in response to a user request. For example, the AI ​​system may select at least one plan from a plurality of defined plans.

[0069] According to one embodiment, the intelligent server (230) may transmit the results according to the generated plan to the electronic device (210), or transmit the generated plan to the electronic device (210). According to one embodiment, the electronic device (210) may display the results according to the plan on the display module (211). According to one embodiment, the electronic device (210) may display the results of executing an operation according to the plan on the display module (211).

[0070] According to one embodiment, the intelligent server (230) may include a front end (231), a natural language platform (232), a capsule database (238), an execution engine (233), an end user interface (234), a management platform (235), a big data platform (236), or an analytic platform (237).

[0071] According to one embodiment, the front end (231) can receive user input from the electronic device (210). The front end (231) can transmit a response corresponding to the user input.

[0072] According to one embodiment, the natural language platform (232) may include an automatic speech recognition module (ASR module) (232a), a natural language understanding module (NLU module) (232b), a planner module (232c), a natural language generator module (NLG module) (232d), or a text to speech module (TTS module) (232e).

[0073] According to one embodiment, the automatic speech recognition module (232a) can convert voice input received from the electronic device (210) into text data. According to one embodiment, the natural language understanding module (232b) can use the text data of the voice input to determine the user's intent. For example, the natural language understanding module (232b) can perform syntactic analysis or semantic analysis on user input in the form of text data to determine the user's intent. According to one embodiment, the natural language understanding module (232b) can use linguistic features (e.g., grammatical elements) of morphemes or phrases to determine the meaning of words extracted from the voice input, and can match the meaning of the determined words to the intent to determine the user's intent. The natural language understanding module (223b) can obtain intent information corresponding to the user's utterance. The intent information can be information indicating the user's intent determined by interpreting text data. The intent information can include information indicating an action or function that the user intends to execute using the device.

[0074] According to one embodiment, the planner module (232c) can generate a plan using the intent and parameters determined by the natural language understanding module (232b). According to one embodiment, the planner module (232c) can determine a plurality of domains necessary to perform a task based on the determined intent. The planner module (232c) can determine a plurality of operations included in each of the plurality of domains determined based on the intent. According to one embodiment, the planner module (232c) can determine parameters necessary to execute the determined plurality of operations or result values ​​output by the execution of the plurality of operations. The parameters and the result values ​​can be defined as concepts of a specified format (or class). Accordingly, the plan can include a plurality of operations and a plurality of concepts determined by the user's intent. The planner module (232c) can determine the relationships between the plurality of operations and the plurality of concepts in a stepwise (or hierarchical) manner. For example, the planner module (232c) can determine the execution order of a plurality of actions based on the user's intention based on a plurality of concepts. In other words, the planner module (232c) can determine the execution order of a plurality of actions based on parameters required for the execution of the plurality of actions and results output by the execution of the plurality of actions. Accordingly, the planner module (232c) can generate a plan including association information (e.g., ontology) between the plurality of actions and the plurality of concepts. The planner module (232c) can generate the plan using information stored in a capsule database that stores a set of relationships between concepts and actions.

[0075] According to one embodiment, the natural language generation module (232d) can convert specified information into text format. The information converted into text format may be in the form of natural language speech. According to one embodiment, the text-to-speech module (232e) can convert text-to-speech information into speech information.

[0076] According to one embodiment, some or all of the functions of the natural language platform (232) may also be implemented in the electronic device (210).

[0077] The capsule database can store information about the relationships between multiple concepts and actions corresponding to multiple domains. According to one embodiment, the capsule can include multiple action objects (or action information) and concept objects (or concept information) included in the plan. According to one embodiment, the capsule database can store multiple capsules in the form of a concept action network (CAN). According to one embodiment, the multiple capsules can be stored in a function registry included in the capsule database.

[0078] The capsule database may include a strategy registry that stores strategy information necessary for determining a plan corresponding to a user input. The strategy information may include reference information for determining a single plan when there are multiple plans corresponding to the user input. According to one embodiment, the capsule database may include a follow-up registry that stores information on follow-up actions for suggesting follow-up actions to a user in a given situation. The follow-up actions may include, for example, follow-up utterances. According to one embodiment, the capsule database may include a layout registry that stores layout information of information output through the electronic device (210). According to one embodiment, the capsule database may include a vocabulary registry that stores vocabulary information included in the capsule information. According to one embodiment, the capsule database may include a dialog registry that stores information on dialogue (or interaction) with the user. The capsule database may update stored objects through a developer tool. The developer tool may include, for example, a function editor for updating action objects or concept objects. The developer tool may include a vocabulary editor for updating vocabulary. The developer tool may include a strategy editor for creating and registering strategies that determine plans. The developer tool may include a dialog editor for creating conversations with users.The developer tool may include a follow-up editor that activates follow-up goals and allows editing of follow-up utterances that provide hints. The follow-up goals may be determined based on the currently set goals, user preferences, or environmental conditions. In one embodiment, the capsule database may also be implemented within the electronic device (210).

[0079] In one embodiment, the execution engine (233) can use the generated plan to produce a result. The end user interface (234) can transmit the produced result to the electronic device (210). Accordingly, the electronic device (210) can receive the result and provide the received result to the user. In one embodiment, the management platform (235) can manage information used in the intelligent server (230). In one embodiment, the big data platform (236) can collect user data. In one embodiment, the analysis platform (237) can manage the quality of service (QoS) of the intelligent server (230). For example, the analysis platform (237) can manage the components and processing speed (or efficiency) of the intelligent server (230).

[0080] According to one embodiment, the service server (250) may provide a service (e.g., food ordering or hotel reservation) specified to the electronic device (210). According to one embodiment, the service server (250) may be a server operated by a third party. According to one embodiment, the service server (250) may provide information for generating a plan corresponding to the received voice input to the intelligent server (230). The provided information may be stored in a capsule database. In addition, the service server (250) may provide result information according to the plan to the intelligent server (230). The service server (250) may include a plurality of service providers (e.g., CP Service A (251), CP Service B (252), or CP Service C (253)), and each service provider (251, 252, 253) may provide a function for a domain associated with each capsule stored in the capsule database (238) of the intelligent server (230).

[0081] In the integrated intelligence system described above, the electronic device (210) can provide various intelligent services to the user in response to user input. The user input may include, for example, input via a physical button, touch input, or voice input.

[0082] According to one embodiment, the electronic device (210) may provide a voice recognition service through an intelligent app (or voice recognition app) stored within the device. In this case, for example, the electronic device (210) may recognize a user utterance or voice input received through the microphone (212) and provide the user with a service corresponding to the recognized voice input.

[0083] According to one embodiment, the electronic device (210) may perform a designated operation based on the received voice input, either alone or together with the intelligent server (230) and / or the service server (250). For example, the electronic device (210) may execute an app corresponding to the received voice input and perform a designated operation through the executed app.

[0084] According to one embodiment, when an electronic device (210) provides a service together with an intelligent server (230) and / or a service server (250), the electronic device (210) may detect a user's speech using the microphone (212) and generate a signal (or voice data) corresponding to the detected user's speech. The electronic device (210) may transmit the voice data to the intelligent server (230) via a network (240) using a communication interface (213).

[0085] In one embodiment, an intelligent server (230) may generate a plan for performing a task corresponding to a voice input received from an electronic device (210), or a result of performing an operation according to the plan, in response to the voice input. The plan may include, for example, a plurality of operations for performing a task corresponding to a user's voice input, and a plurality of concepts related to the plurality of operations. The concept may define parameters input to the execution of the plurality of operations, or result values ​​output by the execution of the plurality of operations. The plan may include association information between the plurality of operations and the plurality of concepts.

[0086] According to one embodiment, the electronic device (210) can receive the response using the communication interface (213). The electronic device (210) can output a voice signal generated within the electronic device (210) to the outside using the speaker (216), or can output an image generated within the electronic device (210) to the outside using the display module (211).

[0087] Although FIG. 2 illustrates an example in which voice recognition, natural language understanding and generation, and result production using a plan of user input received from an electronic device (210) are performed on an intelligent server (230), the various embodiments of the present document are not limited thereto. For example, at least some components of the intelligent server (230) (e.g., natural language platform (232), execution engine (233), capsule database (238)) may be embedded in the electronic device (210) (or the electronic device (101) of FIG. 1), and the operations may be performed by the electronic device (210).

[0088] FIG. 3 is a diagram showing a form in which relationship information between concepts and actions is stored in a database according to various embodiments.

[0089] According to one embodiment, a capsule database (e.g., capsule database (238) of FIG. 2) of an intelligent server (e.g., intelligent server (230) of FIG. 2) may store capsules in the form of a CAN (concept action network) (300). The capsule database may store operations for processing tasks corresponding to a user's voice input and parameters necessary for the operations in the form of a CAN (concept action network).

[0090] According to one embodiment, the capsule database may store a plurality of capsules (capsule (A) (310), capsule (B) (320)) corresponding to each of a plurality of domains (e.g., applications). According to one embodiment, one capsule (e.g., capsule (A) (310)) may correspond to one domain (e.g., location (geo) or application). In addition, one capsule may correspond to at least one service provider (e.g., CP 1 (331) or CP 2 (332)) for performing a function for a domain related to the capsule. According to one embodiment, one capsule may include at least one operation (350) and at least one concept (360) for performing a specified function.

[0091] In one embodiment, a natural language platform (e.g., the natural language platform (232) of FIG. 2) can generate a plan for performing a task corresponding to a received speech input using capsules stored in a capsule database. For example, a planner module of the natural language platform (e.g., the planner module (232c) of FIG. 2) can generate a plan using capsules stored in a capsule database. For example, a plan can be generated using actions (311, 313) and concepts (312, 314) of capsule A (310) and actions (321) and concepts (322) of capsule B (320).

[0092] FIG. 4 is a block diagram of a generative artificial intelligence system according to one embodiment.

[0093] Referring to FIG. 4, the generative artificial intelligence system (400) may include a generative AI model (450), an AI framework (440), a user query / response interface (410), an applications / service component (430), or a knowledge repository (420). The AI ​​framework (440) may include a prompt design component (442), an API / plugin management component (444), and / or an output modification component (446).

[0094] According to one embodiment, a user query / response interface (410) may receive user input. The user input may be in the form of natural language, images, and / or videos. Additionally, context information may also be transmitted when the user input is transmitted. The context information may include various additional information at the time of the user input. For example, the context information may include information related to the user or the electronic device, such as information about the application the user is currently using or information about the user's location. Additionally, the user input may also be in the form of a mixture of the aforementioned natural language, images, sounds, or context information. Additionally, the user input may also be in a non-natural language form, such as selecting a menu.

[0095] In one embodiment, the user question / response interface (410) may output the results of the generative artificial intelligence system (400) to the user. The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user.

[0096] According to one embodiment, the AI ​​framework (440) can receive user input and coordinate and control each component necessary to perform the user's intention based on the user's query.

[0097] In one embodiment, user input received from the user question / response interface (410) may be transmitted to a prompt design component (442). The prompt design component (442) may be used to generate prompts suitable for inputting the user input into a large language model (LLM) or a large multimodal model (LMM). The prompt design component (442) may be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The prompt design component (442) may access a knowledge repository (420) containing user preference data, a prompt library, and prompt examples based on the user input to obtain and generate prompts, and may transmit the generated prompts to the LLM or LMM.

[0098] In one embodiment, the API / plug-in management component (444) may communicate with external information when there is a request for additional information when passing user input as input to the generative model. The API / plug-in management component (444) may establish a channel for communicating with the outside of the AI ​​interface through the API, and may enable access to various data sources through the established channel. In addition, the API / plug-in management component (444) may request an action through the API that ultimately performs the user input, rather than an intermediate result, when the application or service needs to perform the action. Information obtained from the outside may be used to generate a prompt in the prompt design component (442) together with the user input, or may be passed as input to the generative model.

[0099] In one embodiment, the output modification component (446) (or refiner component) can fine-tune the output from the generative model. For example, the output modification component (446) can verify that the content generated through the LLM and / or LMM is not irrelevant, does not contain biased content, or does not contain harmful content. In addition, the output modification component (446) can determine to what extent the content matches the result desired by the user and, if necessary, can perform additional processing. The output modification component (446) can additionally configure and provide the user with hints to avoid undesired output.

[0100] According to one embodiment, a generative AI model (450) may generally refer to an artificial intelligence neural network that creates new types of data based on user input information. The generative AI model (450) may include a model that generates images and / or a model that generates languages. Representative models for generating images include a generative adversarial network (GAN) and a variational auto encoder (VAE), and examples include a Diffusion-based generative model that uses a VAE and a Transformer structure. A model for generating languages ​​is a model trained to statistically output the most appropriate output based on input values, and representative examples include models such as CHAT-GPT 3 or CHAT-GPT 4. In addition, there are also LMMs (large multimodal models) that can recognize various types of data input, such as text, images, and voice, and generate new data corresponding thereto.

[0101] FIGS. 5A and 5B illustrate a method for configuring a multi-window layout on an electronic device according to one embodiment.

[0102] According to one embodiment, an electronic device can simultaneously execute multiple applications, at least in part. In this case, the electronic device can display the execution screens of each running application in a multi-window layout on the display.

[0103] Figure 5a illustrates a process for providing the execution screens of applications A and B in a multi-window layout.

[0104] Referring to (a) of FIG. 5A, the electronic device can execute application A and display its execution screen (510) as a single window on the entire display area. In this case, a recent APP button (512), a home button, a back button, and / or a full menu button may be provided at the bottom of the execution screen of application A.

[0105] When a user selects (591) the recent APP button (512) displayed at the bottom of the display by touch input, a list of recently executed applications may be provided, as in (b) of Fig. 5a. For example, the list of recently executed applications may be arranged in the order in which the applications were most recently executed, with reduced execution screens (522) of the applications being scrollable left and right. Among these, the user may select (592) the icon (524) of Application A.

[0106] When a user selects (592) the icon (524) of application A from the list in (b) of FIG. 5a, executable menus may appear, as in (c) of FIG. 5a. For example, the menus may include menus such as application information, view as pop-up screen, open in recent apps, and / or open in split screen (532).

[0107] When a user selects (593) the Open in Split Screen menu (532) among the menus in (c) of FIG. 5a, the electronic device may display a first window (542) including the execution screen of application A, as in (d) of FIG. 5a, and a second window (%44) for selecting an application to be executed in a multi-window (or split screen) with application A. In this case, the second window (544) may include executable application icons installed on the electronic device.

[0108] When a user selects (594) the icon (546) of application B in the second window (544), as shown in (e) of FIG. 5a, the electronic device can execute application B and display the first window (552) including the execution screen of application A and the second window (554) including the execution screen of application B in a multi-window layout on the display.

[0109] The process of FIG. 5a is only one embodiment for executing the execution screen (552) of application A and the execution screen (554) of application B in a multi-window manner, and is not limited thereto, and the electronic device may implement a user interface for executing a multi-window in a different manner.

[0110] Figure 5b illustrates the process of changing the size and position of each window in a multi-window layout.

[0111] Referring to (f) of FIG. 5b, the electronic device can configure the execution screen (562) of application A, the execution screen (564) of application B, and / or the execution screen (566) of application C as multi-windows and display them on the top, bottom left, and bottom right of the display, respectively. In this case, when a touch and drag input occurs on a portion of the edge area of ​​each window, the electronic device can change the size of each window by adjusting the boundary position of each window.

[0112] An electronic device can move the position of the execution screen of a selected application when a drag operation occurs after a long touch on a specific area (e.g., an edge area) of a specific window. Referring to (g) of FIG. 5b, a user can move the position of the window by long touching and then dragging the top edge (595) of application C.

[0113] When a user drags the execution screen (576) of application C over the execution screen (564) of application B and then releases the touch, the execution screen (586) of application C may be displayed at the moved lower left, and the execution screen (584) of application B may be displayed at the moved lower right, as shown in (h) of Fig. 5c. In this case, the size of each window may change depending on the properties of each application, the user's adjustment of the border area, etc.

[0114] The process of FIG. 5a is only one embodiment for changing the multi-window layout, and is not limited thereto, and the electronic device may implement a user interface that can change the multi-window layout in other ways.

[0115] As described above with reference to FIGS. 5A and 5B , setting or changing the multi-window layout may require multiple user actions. Furthermore, the location and / or size of each application's execution screen may not match the user's actual intent. Furthermore, if a notification (e.g., a received message) occurs while the multi-window is running, the application in question may be launched to confirm the notification, and the process of confirming the notification may result in the multi-window being terminated or an undesirable change to the layout.

[0116] In one embodiment, the electronic device may be implemented as an extended reality (XR) device. In the case of XR devices, the manual manipulation processes for setting and changing multi-window layouts can be difficult and tiring for users. For example, in virtual reality (VR) / augmented reality (AR) / mixed reality (MR) situations where virtual objects must be displayed at various orientations and distances, users may have difficulty manually setting the layout.

[0117] Below, various embodiments are described in which an electronic device can automatically set or change a multi-window layout without separate user operation in response to an event occurrence by requesting a task for an AI model and / or executing a predetermined algorithm.

[0118] FIG. 6 illustrates an electronic device and an AI model according to one embodiment.

[0119] Referring to FIG. 6, the electronic device may be implemented as a portable electronic device (610) such as a smart phone or tablet PC, or as an XR (extended reality) device (620).

[0120] According to one embodiment, when the electronic device is implemented as a portable electronic device (610), the electronic device (610) can execute an application and display the execution screen of the application on the display. When multiple applications are executing, the electronic device (610) can configure a multi-window layout that provides the execution screen of each application through a distinct area on the display and display it through the display. The form of the multi-window layout and the method of configuring and changing the multi-window layout according to user input have been described above with reference to FIGS. 5A and 5B.

[0121] According to one embodiment, when the electronic device is implemented as an XR device (620), the electronic device (620) can output an application execution screen to be recognized by the user through an XR image (e.g., an AR image, a VR image, or an MR image). When multiple applications are running, the electronic device (620) can provide the user with an XR image configured in a multi-window layout. The user can recognize the execution screen of each application in a separate area through the XR image and control each application through a gesture input.

[0122] According to one embodiment, the AI ​​model (650) (artificial intelligence model) may be implemented as a generative AI model, which is an artificial intelligence model that learns various data and generates new information and sentences, and in this document, the generative AI model may also be referred to as an AI model or a large language model (LLM). According to one embodiment, the AI ​​model (650) may include an on-device AI model implemented on an electronic device (e.g., the electronic device (101) of FIG. 1, the electronic device (210) of FIG. 2) and a server AI model implemented by an external server (e.g., the intelligent server (230) of FIG. 2), and the server AI model may be implemented and operated on a server of a manufacturer of the electronic device (610, 620), or may be implemented and operated by a third party.

[0123] According to one embodiment, the electronic device (610, 620) may transmit a task request to the AI ​​model (650) based on a user input to cause the AI ​​model (650) to perform an intended task. For example, when a user of the electronic device (610, 620) inputs a task to be requested to the AI ​​model (650) through a voice input via a microphone or a text input via a keyboard / keypad, the electronic device (610, 620) may generate a prompt including the task request and transmit it to the AI ​​model (650). The prompt is a command for generating a task response in the AI ​​model (650) and may play a role in guiding the AI ​​model (650) to perform a task desired by the user. The AI ​​model (650) can interpret a prompt received from an electronic device (610, 620), execute a task requested by a user, and generate the result of the executed task as text and / or image information and transmit it to the electronic device (610, 620) as a task response.

[0124] According to one embodiment, the AI ​​model (650) can be trained for various types of tasks. There is no specification regarding the training data based on which the AI ​​model (650) is trained and the tasks it can perform.

[0125] According to various embodiments of the present document, the AI ​​model (650) may be trained based on current status information (e.g., application information, device status information, user status / tendency information, stored data, usage pattern and / or preference information) of the electronic device (610, 620) and the form of the multi-window layout. For example, the AI ​​model (650) may be trained based on current status information set by the user in various electronic devices (610, 620) and / or defined by the developer of the electronic device (610, 620) or the application and information of the currently set multi-window layout.

[0126] According to one embodiment, the electronic device (610, 620) may detect an event that triggers the configuration of a multi-window layout when multiple applications are running. For example, the electronic device (610, 620) may detect an event that triggers the configuration of a multi-window layout when a second application is running while the first application's execution screen is displayed by running the first application. In response to detecting the event, the electronic device (610, 620) may generate a prompt including information related to the detected event and a task request for requesting the configuration of a multi-window layout and transmit the prompt to the AI ​​model (650). The AI ​​model (650) may interpret the contents of the received prompt and, based on the information included in the prompt, generate a task response including information related to the multi-layout and transmit the task response to the electronic device (610, 620). The electronic device (610, 620) may configure the multi-window layout based on the task response received from the AI ​​model (650). Accordingly, the electronic device (610, 620) can configure a multi-window layout according to the user's intention without going through multiple user inputs as described through FIGS. 5a and 5b.

[0127] Although this document describes that the electronic device (610, 620) obtains information related to the configuration of a multi-window layout from an AI model (650), various embodiments of this document are not limited thereto. For example, the electronic device (610, 620) may configure a multi-window layout according to a predetermined algorithm based on information related to an event that triggers the creation of a multi-window layout and current status information of the electronic device (610, 620). In this case, the algorithm for reconfiguring the layout may be implemented as a computer program including various instructions, stored in the memory of the electronic device (610, 620), and executed by the processor of the electronic device (610, 620).

[0128] Figure 7 is a block diagram of an electronic device according to one embodiment.

[0129] Referring to FIG. 7, an electronic device (700) may include a communication module (740), a display (730), a processor (710), and a memory (720). In various embodiments of the present document, some of the illustrated components may be omitted or replaced with other components. The electronic device (700) may include at least some of the components and / or functions of the electronic device (101) of FIG. 1 and / or the electronic device (210) of FIG. 2. At least some of the components of the illustrated (or not illustrated) electronic device (700) may be operatively, functionally, and / or electrically connected to each other. The electronic device (700) may also be implemented as a portable electronic device (e.g., a smart phone, a tablet PC) or an XR device (e.g., a head-mounted device, or AR glasses).

[0130] According to one embodiment, the display (730) can display various images provided from the processor (710). For example, the display (730) can 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 (730) can be configured as a touch screen that detects touch and / or proximity touch (or hovering) input using a part of a user's body (e.g., a finger) or an input device (e.g., a stylus pen). The display (730) may be implemented as a flexible display including at least a portion of a flexible material, and the electronic device (700) may be formed into various form factors, such as a foldable device or a slidable device, which may have a variable display area by utilizing the characteristics of the flexible display (730). The display (730) may include at least a portion of the configuration and / or functions of the display module (160) of FIG. 1. Hereinafter, the expression that some image information (e.g., at least one application execution screen) is displayed on the display (730) may be interpreted to mean that it is displayed on at least a portion of the display (730) (e.g., a portion of the display or the entire display).

[0131] According to one embodiment, the communication module (740) may support wireless communication with an external device using cellular wireless communication (e.g., 4G long term evolution (LTE), 5G new radio (NR)) and / or short-range wireless communication (e.g., Wi-Fi). For example, the electronic device (700) may use the communication module (740) to communicate with an external server (e.g., the intelligent server (230) of FIG. 2) that provides a voice assistant service through a network. The communication module (740) may include at least some of the configurations and / or functions of the communication module (190) of FIG. 1 and / or the communication interface (213) of FIG. 2.

[0132] According to one embodiment, the memory (720) can temporarily or permanently store various data, including volatile memory and non-volatile memory. The memory (720) includes at least a portion of the configuration and / or function of the memory (130) of FIG. 1 and / or the memory (215) of FIG. 2, and can store the program (140) of FIG. 1. The memory (720) can store various applications (e.g., the first app (219a) or the second app (219b) of FIG. 2) and program modules supporting intelligent services (e.g., the client module (218) of FIG. 2).

[0133] According to one embodiment, the memory (720) may store various instructions that may be performed by the processor (710). Such instructions may include control commands such as arithmetic and logical operations, data movement, and / or input / output that may be recognized by the processor (710).

[0134] According to one embodiment, the processor (710) is a configuration capable of performing calculations or data processing related to control and / or communication of each component of the electronic device (700), and may include one or more processors. The processor (710) may include at least some of the configurations and / or functions of the processor (120) of FIG. 1 and / or the processor (214) of FIG. 2.

[0135] According to one embodiment, there is no limitation to the computational and data processing functions that the processor (710) can implement on the electronic device (700). However, this document will describe various embodiments for configuring a multi-window layout using an AI model and / or a predetermined algorithm according to an event. The operations of the processor (710) described below can be performed by loading instructions stored in the memory (720).

[0136] In this document, the description that the processor (710) can perform a certain operation (or function, work, task) may be interpreted to mean substantially the same as that an instruction (or command, computer program) that causes the electronic device (700) (or the processor (710)) to perform the corresponding operation is stored in the memory (720) (e.g., non-volatile memory, storage). In addition, the description that the processor (710) can perform a certain operation may be interpreted to mean substantially the same as that at least one processor, without specifying the operation, can perform the corresponding operation.

[0137] According to one embodiment, the memory (720) may store various data required for setting up a multi-window layout. For example, the memory (720) may store application information including information related to various applications installed and / or running on the electronic device (700), device status information related to the status of the electronic device (700), user status / tendency information including information such as the user's personal information or behavioral patterns, and / or various content data. Examples of data stored in the memory (720) will be described in more detail with reference to FIG. 8.

[0138] According to one embodiment, the processor (710) can execute at least one application stored in the memory (720). For example, the processor (710) can execute a first application when a user inputs an application icon or a specified condition is satisfied. The processor (710) can display an execution screen of the executed first application on the display (730). If the first application is the only application currently running in the foreground, the processor (710) can display the execution screen of the first application in a substantially entire area of ​​the display (730) in a single window layout.

[0139] According to one embodiment, the processor (710) may detect an event that triggers the configuration of a multi-window layout while the first application is running. For example, the event that triggers the configuration of the multi-window layout is an event that triggers the second application, and may include, but is not limited to, events such as the occurrence of an input for selecting an application to be executed with the multi-window layout described through FIGS. 5A and 5B , satisfaction of a specified execution condition, receipt of a message, or occurrence of a notification.

[0140] According to one embodiment, the processor (710) may generate a prompt including a task request for requesting an AI model (e.g., a generative AI model) to configure a multi-window layout. For example, the AI ​​model may be trained based on operational status information (e.g., application information, device status information, user status / tendency information, content data, usage pattern and / or preference information) of the electronic device (700) and the form of the multi-window layout. For example, the AI ​​model may be trained based on current status information and currently configured multi-window layout information set by a user in various electronic devices (700) and / or defined by a developer of the electronic device (700) or an application. Accordingly, the AI ​​model may configure a multi-window layout according to the task request included in the prompt of the electronic device (700) and transmit a task response including information related thereto to the electronic device (700).

[0141] According to one embodiment, the AI ​​model may include an on-device AI model implemented on the electronic device (700) and a server AI model implemented by an external server (e.g., the intelligent server (230) of FIG. 2), and the server AI model may be implemented and operated on a server of a manufacturer of the electronic device (700) or may be implemented and operated by a third party.

[0142] According to one embodiment, the processor (710) may generate a prompt including information related to a detected event, information related to a current operating state of the electronic device (700), and a task request for requesting configuration of a multi-window layout.

[0143] According to one embodiment, the processor (710) may analyze at least some of the information (e.g., application information, device status information, user status / tendency information, or content data) stored in the memory (720) to analyze a user's usage pattern for a plurality of applications to be displayed in a multi-window layout. When the configuration of the multi-window layout is triggered by the execution of a second application while a first application is running, the processor (710) may analyze the user's usage pattern and preference for the first application and the second application based on application information such as the type of the first application and the second application (e.g., media player, messenger, document, calendar, calculator, or game), execution history, conversation content, registered schedule, and notification content), and device status information such as the detachment / attachment or folding / unfolding state of the stylus pen. For example, the processor (710) may analyze changes in the content provided by a running application, user input actions (e.g., interaction target, click, long-click, swipe, or pinch & zoom), device status changes (e.g., connection / disconnection with an external device, network connection status change, change in location information based on GPS, or incoming message / call), and analyze user input using an input device (e.g., keypad, stylus pen, mouse, or finger touch).

[0144] Examples of prompts generated based on the analysis results of the current operating status information of the electronic device (700) and / or the user's usage pattern are as shown in Table 1 below.

[0145] Application 1 is located in the upper left corner with sizes A*B, Application 2 is located in the upper right corner with sizes C*D, and Application 3 is located in the lower left corner with sizes E*F. Application 1 provides a soccer match broadcast screen, is currently playing an advertisement, and is the currently active screen. Application 2 is an internet application screen that searches for the soccer player mentioned in Application 1 30 minutes ago, and there is currently no user interaction. Application 3 is a gallery application that has been displaying cat photos for 7 minutes. Application 4 generates a notification for an incoming message asking, "Did you buy Dad a birthday present?" For Application 1, Application 2, Application 3, and Application 4, the task determines whether to run them in multi-window mode, partially in pop-up windows, minimize them to widget form, or terminate them. The task determines whether to resize and reposition each window, and requests the transmission of numerical data regarding the position, size, and window type of each application.

[0146] According to one embodiment, the processor (710) may check the content provided by the running application and determine the current operating state information of the electronic device (700) based on the content of the content. For example, if the running application is providing a soccer game broadcast screen, the processor (710) may analyze the content of the content, such as the situation, score, player name mentioned in the broadcast screen of the application, or product information provided in an advertisement screen, and may include the content of the analyzed content in the current operating state information of the electronic device (700) to generate a prompt. According to one embodiment, the processor (710) may analyze the location information or surrounding information of the electronic device (700) to determine the current operating state information of the electronic device (700). For example, the processor (710) may monitor the current location of the electronic device (700) in real time using GPS, cellular wireless communication (e.g., 4G LTE or 5G NR), and / or short-range wireless communication (e.g., Wi-Fi, Bluetooth, or BLE (Bluetooth low energy)). For example, when an electronic device (700) moves near a coffee shop and is located, it can detect that it is moving near the coffee shop through cell information of GPS or cellular wireless communication, and / or recognize this by receiving a broadcast signal of a Wi-Fi AP placed in the coffee shop, and / or a BLE beacon signal. If the usage pattern of the user of the electronic device (700) tends to place an order through an ordering application near a coffee shop, the processor (710) can include the information in the current operating state information of the electronic device (700) to generate a prompt.

[0147] According to one embodiment, the processor (710) can recognize an adjacent external device through short-range wireless communication (e.g., Wi-Fi or Bluetooth), determine an adjacent location through external device recognition, and generate a prompt by including the information in the current operating state information of the electronic device (700).

[0148] According to one embodiment, the processor (710) may determine the current operating state of the electronic device (700) based on an external device connected via the communication module (740) and information transmitted from the external device. For example, when a user is moving in a vehicle, the electronic device (700) may be connected to an in-vehicle device via short-range wireless communication (e.g., Bluetooth), receive current driving information, traffic information, location information, surrounding information, and / or passenger information transmitted from the in-vehicle device, and include the information in the current operating state information of the electronic device (700) to generate a prompt.

[0149] In one embodiment, the processor (710) may transmit a prompt to the AI ​​model via the communication module (740). For example, when transmitting a task request for configuring a multi-window layout to an on-device AI model, the processor (710) may transmit the prompt to an AI processor configured independently of the processor (710) or to an AI module including a program that can be executed via the processor (710). Alternatively, the processor (710) may transmit the generated prompt to the server AI model via a network using the communication module (740).

[0150] According to one embodiment, the AI ​​model can configure a multi-window layout based on the content of a prompt received from the electronic device (700). The AI ​​model can be trained to understand the content of the text included in the received prompt. The AI ​​model can execute a task for a task request included in the prompt and generate information related to the multi-window layout as a result of the execution. For example, the information related to the multi-window layout can include information necessary for configuring the multi-window layout in the electronic device (700), such as the location and size of a window including an execution screen of each application, the shape of the window, whether it is a pop-up window, and whether it is switched to the background. The AI ​​model can transmit information related to the generated multi-window layout to the electronic device (700).

[0151] According to one embodiment, the processor (710) may configure a multi-window layout based on a task response received from an AI model and display the same on the display (730). For example, the processor (710) may determine the location, size, shape of a window including execution screens of running applications, whether to use a pop-up window, and whether to switch to the background based on multi-window layout-related information included in the task response received from the AI ​​model.

[0152] According to one embodiment, when an event related to a change in the multi-window layout occurs while the processor (710) is displaying execution screens of multiple applications in a multi-window layout, the processor may request the AI ​​model to reconfigure the multi-window layout.

[0153] According to one embodiment, the processor (710) may detect an event that triggers a change in the layout while the multi-window layout is being displayed on the display (730). For example, the event may include, but is not limited to, when a new application is launched, when there is a change or an important event in the content provided by the application, when a message / phone notification occurs, when there is a change in application information and / or device status information, when there is a connection or disconnection with an external device, when a short-range wireless communication function is activated or deactivated, when there is an insertion / removal of a stylus pen, etc.

[0154] According to one embodiment, the processor (710) may, in response to detecting the event, generate a prompt including information related to the detected event and a task request for requesting reconfiguration of the multi-window layout. Here, the method for generating the prompt or the information included in the prompt may be substantially the same as the prompt generated when requesting configuration of the multi-window layout. The processor (710) may include information related to the configuration of the current multi-window layout, such as the type of application currently running in multi-window, the content of the provided content, and the size and position of each window, in the prompt.

[0155] According to one embodiment, the generated prompt may be transmitted to an AI model, a task response may be received from the AI ​​model, and a multi-window layout may be reconfigured based on the received task response and displayed on the display (730). For example, the processor (710) may determine the position, size, or shape of a window including execution screens of running applications based on multi-window layout-related information included in the task response received from the AI ​​model, and may switch some applications to pop-up windows or to the background.

[0156] In the embodiments described above, the electronic device (700) is described as obtaining information related to the configuration of a multi-window layout from an AI model. However, the various embodiments of this document are not limited thereto. For example, the electronic device (700) may configure a multi-window layout according to a predetermined algorithm based on information related to an event that triggers the creation of a multi-window layout and current status information of the electronic device (700). In this case, the algorithm for reconfiguring the layout may be implemented as a computer program including various instructions, stored in the memory (720) of the electronic device (700), and executed by the processor (710) of the electronic device (700).

[0157] Instructions for performing the operations of the electronic device (700) (or processor (710)) described above may be stored on a computer-readable recording medium. The recording medium may be tangible and non-transitory. The recording medium may store one or more computer programs including the instructions.

[0158] FIG. 8 is a block diagram of components that perform operations related to setting a multi-window layout according to one embodiment.

[0159] According to one embodiment, an electronic device (e.g., electronic device (700) of FIG. 7) may store various data (810) necessary to configure a multi-window layout on a memory (e.g., memory (720) of FIG. 7).

[0160] According to one embodiment, the application information (812) may include information related to various applications installed and / or running on the electronic device. For example, the application information (812) may include at least some of the following: application-specific information, such as the type of each application (e.g., media player, messenger, document, calendar, calculator, or game), resolution, execution history, usage frequency, user preference, association with other applications, simultaneous execution frequency, execution screen size, aspect ratio, and resolution; application-related information, such as whether multi-window is supported, display position, size, and resolution when multi-window is run, and other frequently run applications in multi-window mode; and / or application content information, such as content (e.g., video, audio), messages, or notifications provided by the running application. The application information (812) described in this document is not limited to the examples described above.

[0161] According to one embodiment, the device status information (814) may include information related to the status of the electronic device. For example, the device status information (814) may include at least some of the device current status information such as model information of the electronic device, information on each hardware (e.g., processor, memory, or communication module), display information (e.g., size, aspect ratio, resolution, landscape / portrait mode), firmware information, operating system information, basic device information such as current battery status, activation / connection / quality status of wireless communication (e.g., cellular wireless communication, Bluetooth, Wi-Fi), external devices connected via wireless communication (e.g., Wi-Fi access points, other electronic devices), location information based on GPS and / or wireless communication, movement path, relative position between the user or other electronic devices and the electronic device, attachment / detachment of a stylus pen, folding / unfolding status and / or folding angle in the case of a foldable device, slider-in / slide-out status and / or display expansion distance in the case of a slider-in device, VR / MR / AR operation mode, field of view (FoV), or rotation / movement information in the case of an XR device. The device status information (814) described in this document is not limited to the examples described above.

[0162] According to one embodiment, the user status / tendency information (816) may include user personal information such as the age, gender, or occupation of the user of the electronic device, the user's current behavior information (e.g., starting to drive, while driving, watching a lecture, exercising, playing a game, or sleeping), the application execution history, usage frequency, preferences, application search history, internet search history, frequently executed applications (or relevance of applications) at the same time, or user tendency information such as a preferred form of multi-window layout, and a behavioral pattern when a notification (e.g., receiving a message) occurs. The user status / tendency information (816) described in this document is not limited to the examples described above.

[0163] According to one embodiment, content data (818) may include at least a portion of media data (e.g., captured images, videos, music, or documents), object or background information included in the media data, capture time information and / or download information, message information sent and received via a social network service (SNS), message, or email application, visited location information, schedule, anniversary, or payment history. The content data (818) described in this document is not limited to the examples described above.

[0164] According to one embodiment, the analysis module (820) can analyze the current operating state of the electronic device based on data (810) stored in the memory when an event triggering a multi-window layout change occurs.

[0165] According to one embodiment, the application analysis module (822) can analyze information such as the type of at least one application currently running or displayed on the display, the type and content of the provided content, etc. For example, the application analysis module (822) can analyze the types of running applications (e.g., music, messenger, document, calendar, calculator, or game) and monitor screen changes to determine the status (e.g., content playback, text output, or real-time conversation) of the content currently displayed on the screen. In addition, the application analysis module (822) can analyze execution history, usage frequency, or user preferences to determine whether the content provided through each window is important content to the user. The application analysis module (822) can, during the analysis, further base its analysis on at least some of the device status information (814), user status / tendency information (816), and / or content data (818) in addition to the application information (812).

[0166] In one embodiment, the application analysis module (822) can analyze application properties, relationships, execution patterns, and multi-window related information to determine the relationship between each concurrently running application. For example, based on at least some of the above information, the application analysis module (822) can determine that a navigation application and a music player application have a higher relationship than a navigation application and a banking application.

[0167] Table 2 below is an example of the analysis results of the application analysis module (822).

[0168] The first application is a soccer match broadcast screen, currently playing an ad, and is the active screen. The second application is an internet application that searched for the soccer player mentioned in the first application 30 minutes ago, and no user interaction has occurred. The third application is a messenger application, and a conversation about a birthday present for a father has been ongoing for five minutes.

[0169] According to one embodiment, the device analysis module (824) can analyze information related to the properties and status of the electronic device. For example, the device analysis module (824) can analyze the screen size, ratio, resolution, landscape / portrait mode information, folding status and / or folding angle of the electronic device, external devices connected to wireless communication, location information, battery status, or attachment / detachment of a stylus pen, etc. based on the stored device status information (814). The device analysis module (824) can, during the analysis, further base not only on the device status information (814), but also on at least some of the application information (812), user status / tendency information (816), and / or content data (818). According to one embodiment, the user analysis module (826) can analyze the current behavioral status of the user. For example, the user analysis module (826) can determine what behavior the user is currently engaged in, such as starting to drive, driving, watching a lecture, exercising, playing a game, or sleeping, based on the stored user status / tendency information (816). The user analysis module (826) may, during the analysis, be based on at least some of the user status / tendency information (816), as well as application information (812), device status information (814), and / or content data (818).

[0170] According to one embodiment, the data analysis module (828) may analyze content data (818) and / or received alarms in memory. For example, the data analysis module (828) may analyze stored images, objects and backgrounds included in videos, shooting time information, user conversations, registered schedule information, visited area information, etc. When analyzing, the data analysis module (828) may further be based on at least some of application information (812), device status information (814), and / or user status / tendency information (816) in addition to the content data (818).

[0171] According to one embodiment, the usage pattern / taste analysis module (829) can analyze the user's usage pattern or behavior pattern for the electronic device in various situations based on the analysis results of at least some of the application analysis module (822), the device analysis module (824), the user analysis module (826), and the data analysis module (828). The usage pattern / taste analysis module (829) can classify whether the user's behavior (e.g., rejection, agreement, touch, long click, termination) was intended. The usage pattern / taste analysis module (829) can patternize the user's behavior in various situations, detect the user's habits, and learn the objects (e.g., applications, contents, other people) that the user prefers or does not prefer.

[0172] According to one embodiment, the usage pattern / taste analysis module (829) can analyze the pattern of what actions a user takes on an electronic device when an event (e.g., receiving a message, changing location, using a stylus pen, connecting to Bluetooth, starting to drive, reaching a calendar schedule, detecting a keyword) occurs in a specific situation (e.g., location, time, application in use).

[0173] According to one embodiment, the analysis results of the usage pattern / taste analysis module (829) may be stored in a usage pattern / taste information database (840). For example, the usage pattern / taste information database (940) may be stored in the memory of the electronic device, or may be stored on an external server, and the external server may obtain usage pattern / taste information of various electronic devices to construct the database.

[0174] According to one embodiment, the electronic device may generate a prompt (830) based on the analysis results of the analysis module (820). For example, the electronic device may generate the prompt (830) including a task request for configuring a multi-window layout, information on the current operating status of the electronic device generated based on the analysis results of the analysis module, and / or information necessary for configuring the multi-window layout, such as usage pattern and preference information.

[0175] According to one embodiment, the electronic device may generate a prompt (834) containing the content of an event that occurred without going through the analysis module (820) when a separate analysis action is not required, such as connecting or disconnecting with an external device via short-range wireless communication (e.g., Bluetooth), or folding or unfolding the electronic device.

[0176] In one embodiment, the electronic device may transmit a prompt (830, 834) containing a generated task request to the AI ​​model (860).

[0177] According to one embodiment, the AI ​​model (860) can analyze the contents of the received prompts (830, 834) to configure and / or reconfigure the multi-window layout. The AI ​​model (860) can be trained based on current status information and information of the currently configured multi-window layout, which are set by the user in various electronic devices and / or defined by the developer of the electronic device or application. For example, the AI ​​model (860) can determine the user's usage patterns and tendencies based on the contents of the prompts received from the electronic device and the trained data, and determine the importance and interrelationship of each application, thereby determining the configuration form of the multi-window layout.

[0178] According to one embodiment, the AI ​​model (860) can configure a multi-window layout in a way that does not obscure information provided by the application as much as possible. For example, if an electronic device is running a first application, a second application, and a third application and a fourth application is configured as a pop-up window, the AI ​​model (860) can place the pop-up window of the fourth application in a location where the pop-up window of the fourth application does not obscure the area providing important information in the windows of the first, second, and third applications. According to one embodiment, if the electronic device is implemented as an XR device, the multi-window layout can be configured to place the windows of each application in an area without a major object based on information acquired from the front camera of the electronic device, and / or to place the windows of applications with high preference in the direction of the user's gaze. For example, if the gaze of a user wearing an XR device is directed toward a fish tank containing fish, this can be captured through the front camera, and information on the location and size of each object, such as fish, can be included in a prompt and transmitted to the AI ​​model. Based on the information it receives, the AI ​​model can position each application's window so that objects (e.g., fish) are not obscured.

[0179] According to one embodiment, the AI ​​model (860) can transmit information related to the generated multi-window layout to the electronic device.

[0180] According to one embodiment, the electronic device may configure a multi-window layout through the UI module (880) based on a task response received from the AI ​​model (860) and display the same on the display. For example, the electronic device may determine the position, size, and shape of windows including execution screens of running applications based on multi-window layout-related information included in the task response received from the AI ​​model (860), and may switch some applications to pop-up windows or to the background.

[0181] Figure 9 is a flowchart of a method for configuring a multi-window layout according to one embodiment.

[0182] The illustrated method can be performed by an electronic device (e.g., an electronic device (700) of FIG. 7), and the technical features described above may be omitted from the description below.

[0183] According to one embodiment, in operation 910, the electronic device may receive a multi-window execution request. For example, the electronic device may detect that when a second application is executed while the first application's execution screen is displayed while the first application is being executed, this may be an event that triggers the configuration of a multi-window layout.

[0184] According to one embodiment, in operation 920, the electronic device may analyze at least some of the text, images, and videos provided by the running application. For example, if the running application provides a soccer match broadcast screen, the electronic device may analyze the content, such as situations mentioned in the broadcast screen, scores, player names, and product information provided in an advertisement screen, based on at least some of the text, images, and videos displayed on the broadcast screen.

[0185] According to one embodiment, in operation 930, the electronic device may analyze the correlation between running applications. For example, the electronic device may determine the correlation between each application installed on the electronic device based on the application type, properties, the user's manual arrangement record when configuring a multi-window layout, keywords (or context) provided by the application obtained through content analysis, and / or application execution history. For example, if a navigation application and a music player application frequently run simultaneously, the correlation may be determined to be higher than that between a navigation application and a banking application. According to one embodiment, the electronic device may determine the correlation between each application based on the similarity of keywords that can be extracted from each application execution screen of the multi-window. For example, if a specific application is live-streaming a soccer match and a user is searching for a soccer player's profile via a web browser, the electronic device may determine that the two applications have a high correlation. For example, if a compass application and a shopping mall application providing a screen for purchasing baby products are running simultaneously, the two applications may be judged to have low relevance due to low keyword similarity. According to one embodiment, an electronic device can determine relevance between applications based on the positions of application windows arranged in a multi-window layout. For example, if a user frequently arranges a messenger application and a shopping mall application, or a gallery application and a file application, adjacent to each other when directly configuring a multi-window layout, the two applications may be determined to have high relevance.

[0186] According to one embodiment, in operation 940, the electronic device may analyze the device status and properties. For example, the electronic device may analyze the screen size, aspect ratio, resolution, landscape / portrait mode information, folding status and / or folding angle, external devices connected to wireless communication, location information, battery status, attachment / detachment of a stylus pen, etc. of the electronic device based on the stored device status information.

[0187] According to one embodiment, at operation 950, the electronic device may generate a prompt requesting the creation of a multi-window layout. For example, the electronic device may generate the prompt including a task request for configuring the multi-window layout, information on the current operating state of the electronic device generated based on the analysis results of operation 920 and / or operation 930, and / or information necessary for configuring the multi-window layout, such as usage pattern and preference information.

[0188] In one embodiment, the electronic device can pass the generated prompt to the AI ​​model.

[0189] In one embodiment, the AI ​​model can analyze the content of the generated prompt to configure and / or reconfigure the multi-window layout. The AI ​​model can be trained based on current status information and information about the currently configured multi-window layout, which are set by the user on various electronic devices and / or defined by the developer of the electronic device or application. For example, the AI ​​model can determine the user's usage patterns and tendencies based on the content of the prompt received from the electronic device and the trained data, and determine the importance and interrelationship of each application to determine the configuration form of the multi-window layout.

[0190] According to one embodiment, at operation 960, the electronic device may receive a task response from the AI ​​model that includes information related to the configuration of the multi-window layout.

[0191] According to one embodiment, at operation 970, the electronic device may configure a multi-window layout based on a task response received from the AI ​​model and display it through the display.

[0192] Fig. 10 is a flowchart of a method for configuring a multi-window layout according to one embodiment.

[0193] The illustrated method can be performed by an electronic device (e.g., an electronic device (700) of FIG. 7), and the technical features described above may be omitted from the description below.

[0194] According to one embodiment, in operation 1010, the electronic device can monitor application and device status in real time. For example, the electronic device can store application information, device status information, user status / tendency information, and content data, monitor for changes in the stored information, and update the changed data in real time.

[0195] According to one embodiment, in operation 1022, the electronic device may analyze the type of the running application and the real-time screen. For example, the application type may include media players, messengers, documents, calendars, calculators, and games. According to one embodiment, the electronic device may analyze the text, images, and videos of the content provided by the running application to determine the content currently being provided.

[0196] According to one embodiment, in operation 1024, the electronic device may analyze the status of the electronic device and the user. For example, the electronic device may analyze information such as current location information, surrounding information, movement path, attachment / detachment of a stylus pen, folding / unfolding state and / or folding angle in the case of a foldable device, slider-in / slide-out state and / or display expansion distance in the case of a slider-able device, VR / MR / AR operation mode, field of view (FoV), rotation / movement information, and device current status information.

[0197] According to one embodiment, in operation 1026, the electronic device may analyze conversations, schedules, and notifications. For example, the electronic device may analyze conversations registered through messages or SNS applications, and schedules registered through a calendar application and / or notifications generated in response to message receipt.

[0198] According to one embodiment, in operation 1028, the electronic device may analyze stored data. For example, the electronic device may analyze images captured by a camera, video data, generated document data, and / or various data generated by various applications.

[0199] According to one embodiment, in operation 1030, the electronic device may analyze usage patterns and preferences based on the analysis results of operations 1022 to 1028. For example, the electronic device may classify what the user's actions (e.g., rejection, agreement, touch, long click, termination) were intended to do. The electronic device may pattern the user's actions in various situations, detect the user's habits, and learn objects (e.g., applications, content, other people) that the user prefers or dislikes. According to one embodiment, the electronic device may analyze the history related to the user's multi-window layout configuration, and analyze which applications are configured in which layouts based on the user's usage patterns.

[0200] According to one embodiment, at operation 1040, the electronic device may determine the correlation between running applications and the importance of each application. For example, the electronic device may determine that applications that frequently run simultaneously have a high correlation. Additionally, applications that frequently run in the background may be determined to have a low importance.

[0201] According to one embodiment, at operation 1050, the electronic device may determine a multi-window layout. For example, the electronic device may configure the multi-window layout based on analyzed usage patterns and preferences, and the correlation and importance between running applications.

[0202] According to one embodiment, at least some of the analysis operations of operations 1022 to 1040 and the multi-window layout configuration operation of operation 1050 may be performed by the electronic device or the AI ​​model. For example, when the operations are performed by the AI ​​model, the electronic device may generate a prompt including at least some of the stored data and analysis results and a task request related to configuration of the multi-window layout and transmit the prompt to the AI ​​model in order to cause the AI ​​model to perform some of the operations. The AI ​​model may analyze the prompt to configure the multi-window layout and transmit a task response including information related to the multi-window layout to the electronic device. For example, when the operations are performed by the electronic device, the electronic device (e.g., a processor) may analyze the given data according to a predetermined algorithm to configure the multi-window layout.

[0203] According to one embodiment, at operation 1060, the electronic device may configure an updated multi-window layout to display the execution screen of each application.

[0204] FIG. 11 illustrates an example of reconfiguring a multi-window layout according to one embodiment.

[0205] According to one embodiment, the electronic device may perform an analysis on stored data (e.g., data (810) of FIG. 8) (e.g., analysis module (820) of FIG. 8), extract keywords based on the analysis results to determine the user's intention or purpose, and generate a prompt (e.g., prompt (830) of FIG. 8) to request configuration of a multi-window layout.

[0206] In one embodiment, if the user is currently driving, the electronic device may, based on the analysis results, determine that the user's driving usage pattern / taste is listening to music while looking at navigation. In this case, the electronic device may generate a prompt containing a task request, as shown in Table 3 below, and transmit it to the AI ​​model.

[0207] I'm driving, and my usage pattern is to run navigation and music simultaneously. Increase the importance of navigation while driving, configure the layout for simultaneous navigation and music playback, and run it in multi-window mode.

[0208] According to one embodiment, the electronic device may generate and transmit the prompt to the AI ​​model when a touch input or voice input for the user to execute multi-windows occurs. Alternatively, the electronic device may automatically generate and transmit the prompt to the AI ​​model when the user is recognized as driving based on speed / acceleration information, distance measurement via UWB communication (e.g., direction of approach to a vehicle or location within a vehicle), and / or information transmitted from sensors disposed within the vehicle (e.g., seat confirmation from a sensor disposed within the driver's seat), or when the vehicle is connected via short-range wireless communication (e.g., Bluetooth). According to one embodiment, the AI ​​model may execute a task according to the prompt request, and generate and provide to the electronic device a task response including information related to a layout in which a navigation application is placed in a left window closer to the user, a music application is placed in a right window, and a size ratio of 8:2. For example, an electronic device may run a navigation application and a music application, and may configure a multi-window by displaying the navigation application on the left and the music application on the right according to a layout determined from a task response received from an AI model, as illustrated in (a) of FIG. 11, with a size ratio of 8 to 2.

[0209] According to one embodiment, when an event triggering a layout change is detected while the electronic device is configured in a multi-window layout as shown in (a) of FIG. 11, the electronic device may generate a prompt including the event and current status information and transmit it to an AI model for layout reconfiguration. Here, the event triggering the layout change may include events such as a change in device status, a change in user status, or receipt of a notification.

[0210] According to one embodiment, when a navigation application (1112) and a music application (1122) are configured in a multi-window layout and displayed on a display as shown in (a) of FIG. 11, and the vehicle is determined to be stopped based on information transmitted from a sensor (e.g., an acceleration sensor) of the electronic device or from the vehicle, the electronic device may determine that an event triggering a layout change has occurred. Since a user's touch input to the display is easy when the vehicle is stopped, making a touch input related to music playback control may be consistent with the user's usage pattern.

[0211] In one embodiment, the electronic device may generate a prompt, such as Table 4 below, and transmit it to the AI ​​model when the vehicle stops.

[0212] The vehicle is stopped. Reconfigure the multi-window layout to expand the music application's area while the vehicle is stopped.

[0213] According to one embodiment, the AI ​​model may execute a task according to the prompt request, and generate a task response including information related to a layout in which the window sizes of the navigation application and the music application are 1:1, and provide the task response to the electronic device. Referring to FIG. 11(b), the electronic device may reduce the size of the navigation application (1112) and expand the size of the music application (1122), and reconfigure the layout so that the window sizes of the navigation application (1112) and the music application (1122) are substantially 1:1, and display the reconfigured layout on the display. According to one embodiment, the AI ​​model may provide the electronic device with information related to additional layout changes as a task response based on usage pattern and preference information. For example, when the vehicle is moving again, the AI ​​model may generate a task response and provide the electronic device with information related to a layout in which the area of ​​the music application is gradually reduced by 20% based on the moving speed. The electronic device may reconfigure the layout by gradually reducing the area of ​​the music application from 50% to 20% based on the vehicle's starting speed, based on the task response received from the AI ​​model, without requesting additional prompts.

[0214] In one embodiment, if the electronic device detects that the user's fatigue or concentration is increasing based on biometric information obtained through a wearable device (e.g., a smartwatch) worn by the user, the electronic device may generate a prompt containing a task request including the corresponding information and transmit it to the AI ​​model. For example, the AI ​​model may execute a task and transmit information related to the layout that increases the size of a navigation application to the electronic device as a task response. In this case, the AI ​​model may include information related to a music track in the music application that improves the user's concentration in the task response, and the electronic device may change playback to the corresponding music track in the music application.

[0215] FIG. 12 illustrates an example of reconfiguring a multi-window layout according to one embodiment.

[0216] According to one embodiment, an electronic device (e.g., electronic device (700) of FIG. 7) may configure a multi-window layout including an execution screen of an additionally executed application based on current location information and / or surrounding information.

[0217] According to one embodiment, an electronic device may obtain current location information of the electronic device based on a global positioning system (GPS) or wireless communication (e.g., cellular wireless communication, near-field wireless communication). Furthermore, the electronic device may scan wireless signals transmitted from nearby external devices via near-field wireless communication (e.g., Wi-Fi, Bluetooth, BLE) to obtain surrounding information related to nearby locations, such as stores and hospitals. The electronic device may store and update the obtained location information and / or surrounding information on a device stored in memory.

[0218] In one embodiment, when a user is driving, a navigation application and a music application may be launched based on the user's selection, or based on a layout configuration determined by an AI model. In this case, the electronic device may configure a multi-window layout, such as shown in (a) of FIG. 12, with the navigation application (1212) positioned at the top and the music application (1222) positioned at the bottom.

[0219] In one embodiment, when a user moves near a drive-through coffee shop, the electronic device can determine that the user is moving near the store based on location information and surrounding information. For example, the electronic device can determine that the user is moving near the store based on information such as movement path, past movement patterns, payment history, message content, and application execution history. Alternatively, the electronic device can determine that the user is moving near the store if the user requests an order from the store through an ordering application.

[0220] In one embodiment, when the electronic device determines that the user is moving near a particular store, it may generate a prompt, such as Table 5 below, and transmit it to the AI ​​model to reconfigure the layout.

[0221] When a vehicle is stopped at a traffic light within 500m of a coffee shop, configure the layout to include an ordering application so that the driver can place an order.

[0222] For example, a user's past behavior pattern is to order coffee by executing an ordering application when stopping within 500m of a coffee shop, and the electronic device can recognize this from stored data and generate a prompt as described above. According to one embodiment, the electronic device can reconfigure the multi-window layout based on a task response received from the AI ​​model. According to one embodiment, the electronic device can execute an ordering application (1232) as in (b) or (c) of FIG. 12, and add the ordering application (1232) to the navigation application (1212) and music application (1222) that are currently running, thereby reconfiguring the layout to include three windows.

[0223] According to one embodiment, if the AI ​​model confirms through a prompt that only a driver is currently in the vehicle, the AI ​​model may configure a layout in which an order application (1232) expected to have a user input is displayed at a left position adjacent to the user, and a music application (1222) expected to have a low input frequency is displayed at a right position, as shown in (b) of FIG. 12, and transmit a task response including layout-related information to the electronic device.

[0224] In one embodiment, if the AI ​​model determines through a prompt that a passenger other than the driver is currently in the vehicle, the AI ​​model may configure a layout in which the ordering application (1232) is displayed on the right side adjacent to the passenger located to the right of the driver, as shown in (c) of FIG. 12, and transmit a task response containing layout-related information to the electronic device. For example, the electronic device may recognize that the user's behavioral pattern is that the passenger places an order if there is a passenger in the vehicle, and include this information in the prompt to be transmitted to the AI ​​model.

[0225] FIG. 13 illustrates an example of reconfiguring a multi-window layout according to one embodiment.

[0226] According to one embodiment, the electronic device may perform an operation to configure or reconfigure a multi-window layout when a change in the device state is detected. For example, the device state information may include at least some of, but is not limited to, a current battery state, an activation / connection / quality state of wireless communication (e.g., cellular wireless communication, Bluetooth, Wi-Fi), an external device connected via wireless communication (e.g., a Wi-Fi access point, another electronic device), location information based on GPS and / or wireless communication, a movement path, a relative position between the electronic device and a user or another electronic device, attachment / detachment of a stylus pen, a folding / unfolding state and / or a folding angle in the case of a foldable device, a slider-in / slide-out state and / or a display expansion distance in the case of a slider-in device, a VR / MR / AR operation mode, a field of view (FoV), and rotation / movement information. The electronic device may store the above-described device state information in a memory and / or monitor it in real time to detect a change therein.

[0227] Referring to (a) of FIG. 13, an electronic device can execute a lecture application (1310) and provide the contents of the lecture application (1310) in a single window layout. The lecture application (1310) can include video and text contents.

[0228] According to one embodiment, in a state such as (a) of FIG. 13, the electronic device can detect an action of detaching the stylus pen. The electronic device recognizes that the user's usage pattern is to execute a note application when the stylus pen is detached, and can execute the note application (1320) as in (b) of FIG. 13, thereby configuring and displaying the lecture application (1310) and the note application (1320) in a multi-window layout.

[0229] According to one embodiment, the electronic device may analyze the content of the content provided in the lecture application (1310) in real time and determine that execution of the textbook application is necessary.

[0230] According to one embodiment, when the electronic device is executing a textbook application (1330) and the current user is inputting handwriting for a note application (1320), the electronic device may configure and display the lecture application (1310), the note application (1320), and the textbook application (1330) as a multi-window, as shown in (c) of FIG. 13. Alternatively, when the user is not inputting handwriting for the note application (1320), the electronic device may terminate the execution of the note application (1320) and configure and display the lecture application (1310) and the textbook application (1330) as a multi-window, as shown in (d) of FIG.

[0231] In one embodiment, the operation of configuring the aforementioned multi-window layout can be performed by an AI model. The electronic device generates a prompt containing content detected in the running lecture application and a stylus pen detachment event, and transmits the prompt to the AI ​​model. The AI ​​model can configure the multi-layout based on the transmitted prompt and the analysis results of the user's usage pattern.

[0232] FIG. 14 illustrates an example of configuring a multi-window layout according to one embodiment.

[0233] Referring to (a) of FIG. 14, an electronic device may execute a video application (1410) and display it in full screen, and the content provided by the video application may include a soccer broadcast. For example, the electronic device may store soccer-related photos, videos, schedules, and / or conversations, and the electronic device may analyze the stored data to recognize that the user is interested in soccer.

[0234] In one embodiment, an electronic device can analyze the content provided through a running application and data stored on the electronic device to determine whether the user has a high level of interest in the application. For example, the electronic device can analyze the title provided through a video application, the commentary from the commentator, whether the broadcast is live, the schedule stored in the calendar application, and / or information regarding recently saved images to determine that a soccer broadcast currently provided through the video application is of high priority to the user.

[0235] In one embodiment, the electronic device may analyze the content provided by a running application to trigger the configuration of a multi-window layout. For example, the electronic device may analyze the video, text, and sound output from a video application (1410) to recognize the name of a specific player related to a soccer broadcast and determine a user's usage pattern of searching for the player's name on the Internet. In this case, the user's usage pattern may be that the Internet application was executed at a size and location that did not interfere with the soccer broadcast video. Based on the analysis results, the electronic device may generate a prompt including a task request related to the configuration of a multi-window layout, as shown in Table 6 below.

[0236] A video application is displayed in full screen, the video is playing, the connected Bluetooth devices are earbuds and a Bluetooth keyboard, and language such as "Player A is making his first appearance" is detected in the video content. Other applications that users frequently use when watching a soccer match with a video application are Internet applications, calendar applications, and calculator applications. If a screen update is required, it is decided whether to run it as a multi-window or pop-up window, shrink it to a widget form, or terminate the application, whether to resize the window, and whether to change the window layout, and the location, size, window type, and numerical data of each application are transmitted.

[0237] According to one embodiment, the electronic device can transmit the generated prompt to the AI ​​model and configure a multi-window layout based on the task response received from the AI ​​model. For example, the AI ​​model can configure a multi-window layout in which the video application (1410) is placed at the top and the internet application (1420) is placed at the bottom, with the video application (1410) having a larger area, and transmit information related to the position and size of each window to the electronic device as a task response. The electronic device can configure a multi-window layout including the execution screens of the video application (1410) and the internet application (1420) and display it on the display, as shown in (b) of FIG. 14. According to one embodiment, while the multi-window layout is being configured and output, as shown in (b) of FIG. 14, the electronic device can check the received message of the message application. The electronic device can determine that, unlike the execution of the aforementioned internet application, the user's usage pattern is one in which messages are not checked while watching a video. In response to the receipt of a message, the electronic device can generate a prompt as shown in Table 7 below and transmit it to the AI ​​model.

[0238] My sister received a message saying, "Did you order the jacket you said you wanted for your father's birthday? You have to order it within an hour to get a special discount." Currently, a video application and an Internet application are running in multiple windows, the video is playing, the connected Bluetooth devices are earbuds and a Bluetooth keyboard, and language such as "The first half has ended" has been detected in the video content. When the user watches the soccer broadcast in the video application, other applications that are frequently used are an Internet application, a calendar application, and a calculator application. If a screen refresh is required, make a final decision on whether to run in multiple windows or a pop-up window, shrink it to a widget form, or close the application. Also, determine whether to resize the window or change the window layout. Then, pass the location, size, window type, and numerical data for each application.

[0239] According to one embodiment, the AI ​​model can analyze the content of the received prompt and the user's usage pattern to configure a multi-window layout that adds a message application as a pop-up window (1430). As shown in (c) of FIG. 14, the electronic device can display the message application's pop-up window (1430) by overlaying it on the Internet application (1420). According to one embodiment, the electronic device can detect a user's touch input to the message application's pop-up window (1430). In this case, the electronic device can generate a prompt as shown in Table 8 below and transmit it to the AI ​​model.

[0240] The video is playing, the connected Bluetooth devices are earbuds and a Bluetooth keyboard, the video volume is turned down to 0, and other applications that the user mainly uses when watching a soccer match with a video application are an Internet application, a calendar application, and a calculator application. If a screen update is required, it is decided whether to run it as a multi-window or pop-up window, shrink it to a widget form, or terminate the application, whether to resize the window, and whether to change the window layout, and the location, size, window type, and numerical data of each application are transmitted.

[0241] In one embodiment, the AI ​​model may decide to terminate (or run in the background) the Internet application (1420) and additionally run the shopping application (1440) by considering the user's actions of touching the pop-up window (1430), the user's input into the message application, and the user's preference lowered due to the volume adjustment of the video application (1410). In addition, the AI ​​model recognizes that the priority of the message application (1450) is high and that the priority of the video application (1410) is low, and thus, as shown in (d) of FIG. 14, a multi-window layout is configured to display the message application (1450) on the right, the video application (1410) in a small size on the upper left, and the shopping application (1440) in a large size on the lower left, and transmit the same to the electronic device. According to one embodiment, the electronic device may detect that the user has completed an order in the shopping application (1440), that the conversation with the other party in the message application (1450) has ended, and that the second half of the soccer broadcast has started in the video application (1410) while displaying the multi-window layout as shown in (d) of FIG. 14, in this case, the electronic device may generate a prompt as shown in Table 9 below and transmit the same to the AI ​​model.

[0242] The shopping app displays keywords such as "order completed," "thank you," and "jacket." The video app detects the message "the second half is about to begin." The messaging app then responds with "yes." Based on previously reported user patterns, preferences, and analyzable information, the app makes a final decision on whether to run the screen as a multi-window or pop-up window, shrink it to a widget, or terminate the application. The app then resizes the window, and whether the window layout needs to be changed. The app then delivers the location, size, window type, and numerical data for each application.

[0243] In one embodiment, the AI ​​model may recognize that the messaging application (1410) and the shopping application (1440) have lower priorities based on the content of the prompt and the user's usage pattern. Furthermore, the AI ​​model may recognize that the messaging application (1450) and the shopping application (1440) have high correlations, while the messaging application (1450) and the video application (1410) have low correlations based on application information, and may decide to terminate (or run in the background) the shopping application (1440) and the messaging application (1450). Accordingly, the AI ​​model may configure a single-window layout that displays the video application (1410) in full screen, thereby transmitting relevant information to the electronic device. The electronic device may display a video application (1410) in full screen as in (e) of FIG. 14 based on the received task response. The electronic device according to various embodiments of the present document may include a display (730), a communication module (740), a memory (720), and at least one processor (710) operatively connected to the display, the communication module, and the memory.

[0244] According to one embodiment, the memory may store instructions that are executed by at least one processor and, when executed, cause the electronic device to execute a first application and display an execution screen of the first application on at least a portion of the display.

[0245] According to one embodiment, the memory may store instructions that cause the electronic device to detect a first event that triggers configuration of a multi-window layout upon execution of a second application while the first application is running, generate a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout in response to detection of the first event, and transmit the generated prompt to an AI model.

[0246] According to one embodiment, the memory may store instructions that cause the electronic device to receive a task response from the AI ​​model, which includes information related to a multi-window layout to be configured in response to the first event, and to configure a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response, and to display the multi-window layout on at least a portion of the display.

[0247] According to one embodiment, the memory may store instructions that cause the electronic device to analyze information stored in the memory, analyze a usage pattern related to the first application and the second application, and generate the prompt including the analyzed usage pattern.

[0248] According to one embodiment, the memory may store at least one of application information (812) related to applications stored in the memory, device status information (814) related to a status of the electronic device, user status / tendency information (816), or content data (818).

[0249] According to one embodiment, the memory may store instructions that cause the electronic device to determine current operating state information of the electronic device by analyzing at least some of application information, device state information, user state / tendency information, or content data stored in the memory.

[0250] According to one embodiment, the memory may store instructions that cause the electronic device to check content being provided by the first application or the second application and determine current operating state information of the electronic device based on the content of the content.

[0251] According to one embodiment, the memory may store instructions that cause the electronic device to analyze location information or surrounding information of the electronic device to determine current operating state information of the electronic device.

[0252] According to one embodiment, the memory may store instructions that cause the electronic device to determine current operating state information of the electronic device based on information transmitted from an external device connected through the communication module.

[0253] According to one embodiment, the task response may include information related to the size and position of a first window including an execution screen of the first application and a second window including an execution screen of the second application.

[0254] According to one embodiment, the memory may include instructions for detecting a second event that triggers a change of the layout while the electronic device is displaying the multi-window layout on at least a portion of the display, generating a prompt including information related to the detected first event and a task request for requesting reconfiguration of the multi-window layout in response to detection of the second event, transmitting the generated prompt to the AI ​​model, receiving a task response from the AI ​​model including information related to the multi-window layout to be reconfigured in response to the second event, and reconfiguring the multi-window layout based on the received task response and displaying it on at least a portion of the display.

[0255] According to one embodiment, the memory may store instructions that cause the electronic device to determine that a change in the layout is necessary based on content being provided by the first application or the second application.

[0256] A method performed by an electronic device according to various embodiments of the present document may include: executing a first application to display an execution screen of the first application; detecting a first event that triggers configuration of a multi-window layout according to execution of a second application while the first application is running; generating, in response to detection of the first event, a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout; transmitting the generated prompt to an AI model; receiving, from the AI ​​model, a task response including information related to a multi-window layout to be configured in response to the first event; and configuring and displaying a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response.

[0257] According to one embodiment, the method may include an operation of analyzing information stored in the electronic device to analyze a usage pattern related to the first application and the second application, and an operation of generating the prompt including the analyzed usage pattern.

[0258] According to one embodiment, the electronic device may store at least one of application information related to applications, device status information related to a status of the electronic device, user status / tendency information, or content data.

[0259] According to one embodiment, the method may include an operation of determining current operating state information of the electronic device by analyzing at least some of the stored application information, device state information, user state / tendency information, or content data.

[0260] According to one embodiment, the operation of determining the current operating state information of the electronic device may include an operation of checking content being provided by the first application or the second application, and an operation of determining the current operating state information of the electronic device based on the content of the content.

[0261] According to one embodiment, the operation of determining current operating state information of the electronic device may include an operation of analyzing location information or surrounding information of the electronic device to determine current operating state information of the electronic device.

[0262] According to one embodiment, the operation of determining current operating state information of the electronic device may include an operation of determining current operating state information of the electronic device based on information transmitted from an external device connected via wireless communication.

[0263] According to one embodiment, the task response may include information related to the size and position of a first window including an execution screen of the first application and a second window including an execution screen of the second application.

[0264] According to one embodiment, the method may include an operation of detecting, while the multi-window layout is being displayed, a second event that triggers a change of the layout; an operation of generating, in response to detection of the second event, a prompt including information related to the detected first event and a task request for requesting reconfiguration of the multi-window layout; an operation of transmitting the generated prompt to the AI ​​model; an operation of receiving, from the AI ​​model, a task response including information related to a multi-window layout to be reconfigured in response to the second event; and an operation of reconfiguring and displaying the multi-window layout based on the received task response.

[0265] A computer-readable non-transitory recording medium according to various embodiments of the present document may store instructions for performing an operation of executing a first application to display an execution screen of the first application, an operation of detecting a first event that triggers configuration of a multi-window layout according to execution of a second application while the first application is running, an operation of generating a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout in response to detection of the first event, an operation of transmitting the generated prompt to an AI model, an operation of receiving a task response including information related to a multi-window layout to be configured in response to the first event from the AI ​​model, and an operation of configuring and displaying a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response.

[0266] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0267] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0268] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0269] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0270] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0271] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In electronic devices, Display (730); Communication module (740); Memory (720); and At least one processor (710) operatively connected to the display, the communication module and the memory, The above memory is, executed by at least one processor, and when executed, said electronic device: Executing a first application and displaying the execution screen of the first application on at least a portion of the display, While the first application is running, a first event that triggers the configuration of a multi-window layout is detected according to the execution of the second application, In response to detecting the first event, generate a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout; Pass the generated prompt to the AI model, Receive a task response from the AI model including information related to a multi-window layout to be configured in response to the first event, and An electronic device storing instructions for configuring a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response and displaying the multi-window layout on at least a portion of the display.

2. In paragraph 1, The above memory, the electronic device, By analyzing the information stored in the above memory, the usage patterns related to the first application and the second application are analyzed, An electronic device storing instructions for generating the prompt including the analyzed usage pattern.

3. In paragraph 1 or 2, The above memory is, An electronic device storing at least one of application information (812) related to applications stored in the memory, device status information (814) related to the status of the electronic device, user status / tendency information (816), or content data (818).

4. In paragraph 3, The above memory, the electronic device, An electronic device storing instructions for determining current operating status information of the electronic device by analyzing at least some of the application information, device status information, user status / tendency information, or content data stored in the memory.

5. In paragraph 4, The above memory, the electronic device, Check the content provided by the first application or the second application, An electronic device storing instructions for determining current operating state information of the electronic device based on the contents of the above content.

6. In paragraph 4, The above memory, the electronic device, By analyzing the location information or surrounding information of the electronic device, the current operating status information of the electronic device is determined, and / or An electronic device storing instructions for determining current operating status information of the electronic device based on information transmitted from an external device connected through the communication module.

7. In any one of paragraphs 1 to 6, The above task response is, An electronic device including information related to the size and position of a first window including an execution screen of the first application and a second window including an execution screen of the second application.

8. In any one of paragraphs 1 to 7, The above memory, the electronic device, detecting a second event that triggers a change of the layout while the multi-window layout is being displayed on at least a portion of the display; In response to detection of the second event, generate a prompt including information related to the detected first event and a task request for requesting reconfiguration of the multi-window layout; The generated prompt is passed to the AI model, Receive a task response from the AI model including information related to a multi-window layout to be reconstructed in response to the second event, and An electronic device comprising instructions for reconfiguring the multi-window layout based on the received task response and displaying it on at least a portion of the display.

9. In paragraph 8, The above memory, the electronic device, An electronic device storing instructions that determine that a change in the layout is necessary based on content provided by the first application or the second application.

10. In a method performed by an electronic device, An action of executing a first application and displaying the execution screen of the first application; An action of detecting a first event that triggers the configuration of a multi-window layout according to the execution of a second application while the first application is running; In response to detecting the first event, generating a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout; An action of passing the generated prompt to the AI model; An operation of receiving a task response including information related to a multi-window layout to be configured in response to the first event from the AI model; and A method including an action of configuring and displaying a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response.

11. In paragraph 10, An operation of analyzing information stored in the electronic device to analyze usage patterns related to the first application and the second application; and A method comprising an action of generating said prompt including said analyzed usage pattern.

12. In paragraph 10, The operation of determining the current operating status information of the above electronic device is: An operation of checking the content provided by the first application or the second application and determining the current operating status information of the electronic device based on the content of the content; An operation of analyzing the location information or surrounding information of the electronic device to determine the current operating status information of the electronic device, or A method comprising at least one of the operations of determining current operating state information of the electronic device based on information transmitted from an external device connected via wireless communication.

13. In any one of paragraphs 10 to 12, The above task response is, A method including information related to the size and position of a first window including an execution screen of the first application and a second window including an execution screen of the second application.

14. In any one of paragraphs 10 to 13, An action of detecting a second event that triggers a change of the layout while the above multi-window layout is being displayed; In response to detection of said second event, generating a prompt including information related to said detected first event and a task request for requesting reconfiguration of the multi-window layout; An action of transmitting the generated prompt to the AI model; An operation of receiving a task response including information related to a multi-window layout to be reconstructed in response to the second event from the AI model; and A method including an action of reconfiguring and displaying the multi-window layout based on the received task response.

15. In a non-transitory computer-readable recording medium, An action of executing a first application and displaying the execution screen of the first application; An action of detecting a first event that triggers the configuration of a multi-window layout according to the execution of a second application while the first application is running; In response to detecting the first event, generating a prompt including information related to the detected first event and a task request for requesting configuration of a multi-window layout; An action of passing the generated prompt to the AI model; An operation of receiving a task response including information related to a multi-window layout to be configured in response to the first event from the AI model; and A recording medium storing instructions for performing an operation of displaying a multi-window layout including an execution screen of the first application and an execution screen of the second application based on the received task response.

Images