Method for executing tasks via communication with peripheral electronic device and electronic device performing same

Abstract

This method executed by an electronic device may comprise the operations of: requesting performance information about a peripheral electronic device, which communicates with the electronic device, from the peripheral electronic device; receiving the performance information about the peripheral electronic device from the peripheral electronic device; when the performance information received from the peripheral electronic device satisfies a condition for executing at least a portion of a task generated by the electronic device, transmitting, to the peripheral electronic device, a request for executing the at least portion of the task; receiving execution information about the at least portion of the task from the peripheral electronic device; and outputting a result of executing the task on the basis of the execution information received from the peripheral electronic device.

Description

Method for performing a task by communicating with a peripheral electronic device and an electronic device performing the same

[0001] Hereinafter, a technology for performing a task through communication with a peripheral electronic device is disclosed.

[0002] Recently, AI models in natural language processing and computer vision, trained on large-scale data, are providing a variety of services, such as real-time translation, image editing, and summarizing web pages, notes, or phone calls. AI-based services on electronic devices have been implemented through cloud computing, where information collected by the device is transmitted to a cloud server and computational results are received from the cloud server.

[0003] Cloud computing methods require time for data collection and transmission and cannot be used in environments without internet access. However, by embedding chips capable of AI computation within electronic devices, AI-based learning and computation can be performed on the device itself, without the need for communication with external servers. Providing AI-based services on electronic devices equipped with on-device AI models reduces latency and, particularly from a security perspective, minimizes data loss, ensuring data security. On-device AI computing can provide data processing results of varying quality and type, depending on the device's hardware performance or the type of AI model embedded.

[0004] According to one embodiment, a method performed by an electronic device may include an operation of requesting performance information of a peripheral electronic device communicating with the electronic device. The method performed by the electronic device may include an operation of receiving performance information of the peripheral electronic device from the peripheral electronic device. The method performed by the electronic device may include an operation of transmitting a request for performing at least a portion of a task generated by the electronic device to the peripheral electronic device when the performance information received from the peripheral electronic device satisfies a condition for performing at least a portion of the task. The method performed by the electronic device may include an operation of receiving performance information of at least a portion of the task from the peripheral electronic device. The method performed by the electronic device may include an operation of outputting a result of performing the task based on the performance information received from the peripheral electronic device.

[0005] According to one embodiment, a non-transitory computer-readable recording medium can store one or more computer programs including commands for executing the method of operating the electronic device described above.

[0006] In one embodiment, a method performed by an electronic device may include an operation of requesting performance information of a peripheral electronic device communicating with the electronic device. The method performed by the electronic device may include an operation of receiving performance information of the peripheral electronic device from the peripheral electronic device. The method performed by the electronic device may include an operation of determining, based on the performance information received from the peripheral electronic device, whether enhanced execution of a task generated in the electronic device is possible by the peripheral electronic device. The method performed by the electronic device may include an operation of transmitting a request for execution of at least a portion of the task to the peripheral electronic device when the peripheral electronic device determines that enhanced execution of the task is possible.

[0007] According to one embodiment, a non-transitory computer-readable recording medium can store one or more computer programs including commands for executing the method of operating the electronic device described above.

[0008] According to an embodiment, an electronic device may include at least one processor including processing circuitry. The electronic device may include a memory including one or more storage media storing instructions. When the instructions are individually or collectively executed by the at least one processor, the electronic device may perform an operation of: requesting performance information of a peripheral electronic device in communication with the electronic device from the peripheral electronic device. When the instructions are individually or collectively executed by the at least one processor, the electronic device may perform an operation of: receiving performance information of the peripheral electronic device from the peripheral electronic device. When the instructions are individually or collectively executed by the at least one processor, the electronic device may perform an operation of: transmitting a request for performing at least a portion of a task generated by the electronic device to the peripheral electronic device if the performance information received from the peripheral electronic device satisfies a condition for performing at least a portion of the task. When the above instructions are individually or collectively executed by the at least one processor, the electronic device may be caused to: perform an operation of receiving performance information of at least a portion of the task from the peripheral electronic device. When the above instructions are individually or collectively executed by the at least one processor, the electronic device may be caused to: perform an operation of outputting a performance result of the task based on the performance information received from the peripheral electronic device.

[0009] According to an embodiment, an electronic device may include at least one processor including processing circuitry. The electronic device may include a memory including one or more storage media storing instructions. When the instructions are individually or collectively executed by the at least one processor, the electronic device may perform an operation of: requesting performance information of a peripheral electronic device in communication with the electronic device from the peripheral electronic device. When the instructions are individually or collectively executed by the at least one processor, the electronic device may perform an operation of: receiving performance information of the peripheral electronic device from the peripheral electronic device. When the instructions are individually or collectively executed by the at least one processor, the electronic device may perform an operation of: determining, based on the performance information received from the peripheral electronic device, whether enhanced execution of a task generated in the electronic device is possible. When the instructions are individually or collectively executed by the at least one processor, the electronic device may perform an action of: transmitting a request for performing at least a portion of the task to the peripheral electronic device, if the electronic device determines that improved performance of the task is possible.

[0010] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment.

[0011] Figure 2 is a diagram illustrating an artificial intelligence system according to one embodiment.

[0012] FIG. 3 is a schematic diagram illustrating a method of performing operations of an on-device artificial intelligence system according to one embodiment.

[0013] Figure 4 is a flowchart of a method for performing a task according to one embodiment.

[0014] FIG. 5 is a flowchart of a method for searching a peripheral electronic device according to one embodiment.

[0015] Figure 6 is a flowchart of a method for performing a task according to one embodiment.

[0016] Figure 7 is a flowchart of a method for performing a task according to one embodiment.

[0017] FIG. 8 is a diagram schematically illustrating a data processing method of an on-device artificial intelligence system according to one embodiment.

[0018] FIG. 9 is a flowchart of a method for providing recommendation information regarding task performance, according to one embodiment.

[0019] Figure 10 is a flowchart of a method for performing a task according to one embodiment.

[0020] Figure 11 is a flowchart of a method for performing a task according to one embodiment.

[0021] Figure 12a is a flowchart of a method for performing a task according to one embodiment.

[0022] Figure 12b is a flowchart of a method for performing a task according to one embodiment.

[0023] FIG. 13 and FIG. 14 are diagrams each illustrating an operation method of an on-device artificial intelligence system according to an example.

[0024] Figure 15 is a drawing illustrating a method of performing a task according to an example.

[0025] FIG. 16 is a diagram illustrating an operation method of an on-device artificial intelligence system according to an example.

[0026] Hereinafter, an embodiment of the present document may be described with reference to the attached drawings.

[0027] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment.

[0028] 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 an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0029] 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).

[0030] According to one embodiment, the processor (120) may be implemented as a circuit (e.g., a processing circuit) such as a system on chip (SoC) or an integrated circuit (IC). The processor (120) may include one or more processors. For example, the processor (120) may include a combination of one or more processors such as a CPU, a GPU, an MPU, an AP, and a CP.

[0031] According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit (CPU) or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit (GPU), 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.

[0032] The auxiliary processor (123) may control at least a part 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, in the electronic device (101) itself where artificial intelligence is performed, 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.

[0033] 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.

[0034] According to one embodiment, the memory (130) may include one or more memories. The instructions stored in the memory (130) may be stored in a single memory. The instructions stored in the memory (130) may be divided and stored in a plurality of memories. The instructions stored in the memory (130) may be individually or collectively executed by the processor (120) to cause the electronic device (101) (e.g., the electronic device (201) of FIG. 2) to perform and / or control the prompting described with reference to FIGS. 2 to 8. The instructions stored in the memory (130) may be individually or collectively executed by a plurality of processors to cause the electronic device (101) (e.g., the electronic device (201) of FIG. 2) to perform and / or control the prompting described with reference to FIGS. 2 to 8. According to one embodiment, the memory (130) may include volatile memory (132) or non-volatile memory (134).

[0035] 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).

[0036] 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).

[0037] 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. According to one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0038] 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.

[0039] 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).

[0040] 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.

[0041] 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.

[0042] 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).

[0043] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0044] 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.

[0045] 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).

[0046] 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.

[0047] 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).

[0048] 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) may 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.

[0049] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). According to 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). According to one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to 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).

[0050] In one embodiment, 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.

[0051] 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)).

[0052] 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 by itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0053] Figure 2 is a diagram illustrating an artificial intelligence system according to one embodiment.

[0054] In an artificial intelligence system (hereinafter, “system”) (200), a user query / response interface (210) can receive user input. The user input can be any type of input, such as natural language, image, audio, and / or video. Additionally, context information can be transmitted together when the user input is transmitted. The context information can include various side information related to the time when the user input is input into the system (200). For example, the various side information can include application information currently being used by the user or location information of the user. Additionally, the user input can be a mixed type of input of the above-described natural language, image, audio, video, and / or context information. Additionally, the user input can include non-natural language input, such as selecting a menu.

[0055] The user query / response interface (210) can provide the user with output from the generative artificial intelligence system. The output may include a natural language-based response and / or specific content. The output may also include an action requested by the user.

[0056] An artificial intelligence framework (220) can receive user input. Based on the user input (e.g., a user's query), the AI ​​framework (220) can coordinate and control one or more components necessary to perform an action corresponding to the user's intent.

[0057] User input received from the user query / response interface (210) can be transmitted to a prompt design component (221). The prompt design component (221) can be used to generate a prompt suitable as input to a generative model (250) based on the user input.

[0058] The prompt design component (221) may be an AI component that uses a machine learning algorithm or a neural network. The prompt design component (221) may generate improved prompts through learning over time. The prompt design component (221) may access a knowledge repository (230) to generate prompts based on user input. The knowledge repository (230) may include user preference data, a prompt library, and / or prompt examples. The prompt design component (223) may provide the generated prompts to a generative model (e.g., an LLM and / or an LMM).

[0059] The APIs / Plugins management component (223) can communicate with external information sources based on requests for additional information when user input is transmitted to the generative model.

[0060] The APIs / Plugins management component (223) can establish a communication channel for communication with the outside of the system (200) via the API. The APIs / Plugins management component (223) can enable access to various data sources via the communication channel. The acquired information can be used to generate prompts by the prompt design component (221) along with user input, or can be used as input to the generative model (250).

[0061] The APIs / Plugins management component (223) can request a final action via an API when the final action in response to user input, rather than an intermediate action, must be performed by an application or service.

[0062] The refiner component (225) can fine-tune the output of the generative model (250). For example, the refiner component (225) can determine the relevance (e.g., score) between the output (e.g., content) of the generative model and the user input. For example, the refiner component (225) can determine whether the output contains biased information (e.g., selective information). For example, the refiner component (225) can determine whether the output contains harmful information (e.g., violent content or profanity).

[0063] The refinement component (225) can determine the degree of matching (e.g., score) between the output of the generative model (250) and the user input (e.g., the intent of the user input). If the refinement component (225) determines that the output of the generative model (250) does not correspond to the user input, the refinement component (225) can modify the output so that it corresponds to the user input.

[0064] The refinement component (225) can provide hints (e.g., hints for prompt generation) to the user so that the user can obtain information that matches the user's intention from the generative model (250).

[0065] In one embodiment, the generative model (250) may form at least a portion of an artificial intelligence neural network. The generative model (250) may include a model that generates images or a model that generates language. The image generation model may include, for example, a generative adversarial network (GAN), a variational autoencoder (VAE), or a diffusion-based model using a VAE and a transformer. The language generation model may include, for example, a large language model (LLM), a large multimodal model (LMM), a large vision model (LVM), a large vision language model (LVLM), or a large action model (LAM). The LAM may automatically generate actions for an environment (e.g., a robot, a car, an electronic device (101), or a program (140)). Additionally, for at least some AI models (e.g. LLM), there may be a LoRA (low-rank adaptation) adapter that is fine-tuned for a specific task or specific situation, for example.

[0066]

[0067] FIG. 3 is a schematic diagram illustrating a method of performing operations of an on-device artificial intelligence system according to one embodiment.

[0068] Referring to FIG. 3, the on-device artificial intelligence system (hereinafter, system) (300) may include an electronic device (301) (e.g., electronic device (101) of FIG. 1) and an external electronic device (302) (e.g., electronic device (102) of FIG. 1). The system (300) is not limited to the illustrated example and may include a plurality of electronic devices.

[0069] The electronic device (301) and the external electronic device (302) may each be a mobile terminal (e.g., a smartphone, a tablet, or a laptop) or a stationary terminal (e.g., a personal computer (PC)). For example, the electronic device (301) may be implemented in the form of a wearable electronic device (e.g., a smart watch, a smart ring, smart glasses, a head mounted display, or an artificial intelligence pin). For example, the external electronic device (302) may be a smartphone, a laptop, a PC, a WiFi access point (AP), a vehicle, or a home robot.

[0070] The electronic device (301) can acquire data such as images, voices, messages, call records, web page visit records, notes, or sensor information. The electronic device (301) can acquire data based on user input such as taking pictures, recording, typing, drawing, or operating an application. The electronic device (301) can receive data from an external server (e.g., server (108) of FIG. 1) or an external electronic device (e.g., electronic device (102) or electronic device (104) of FIG. 1, or external electronic device (302)).

[0071] The electronic device (301) can generate a task to be performed (or processed, executed, or computed) based on data acquired by the electronic device (301). The task can include functions (or processing, operations, or applications) such as translation, summarization, speech recognition, sentence completion, grammar or spelling check, chatbot, virtual assistant, personalized content recommendation, usage pattern analysis, search pattern analysis, extended reality (e.g., augmented reality, mixed reality, virtual reality) content creation, photo editing, video editing, image creation, object recognition, scene understanding, document recognition, or healthcare (e.g., sleep pattern analysis, activity tracking, stress, pulse, or breathing analysis).

[0072] According to one embodiment, the electronic device (301) can perform a task using an artificial intelligence model.

[0073] According to one embodiment, the artificial intelligence model (or AI neural network) may include various foundation models such as a language model, a code model, an image model, and / or other artificial intelligence neural network models. The artificial intelligence model may include an LLM and / or an LVM. For convenience of explanation, the present disclosure will describe the LLM and / or the LVM as examples.

[0074] The AI ​​model that can be used in this disclosure may include an LLM, an AI neural network-based language model that has learned a large amount of text data through pre-training. The LLM may contain a relatively larger number of parameters (e.g., approximately 10 billion or more) than existing general language models. The LLM may utilize a transformer AI neural network structure based on an attention mechanism.

[0075] In one embodiment, the training of the LLM may include pre-training and / or fine-tuning. Pre-training may involve training the LLM to acquire general language knowledge using a large amount of text data. For example, pre-training may involve self-supervised learning, which predicts the next word in a text string using a previous word string. Fine-tuning may involve training the LLM to be suitable for a specific domain (e.g., chatbot, AI assistant, translation, summary generation, question answering) and / or task. Fine-tuning may involve further training (e.g., supervised learning, adaptive learning) the LLM using a dataset corresponding to the specific domain and / or task based on the pre-trained model. The LLM may perform a task based on text input containing natural language, referred to as a prompt.

[0076] In one embodiment, fine-tuning can be omitted in LLM learning. Users can control the prompts provided to the LLM to improve performance on a desired task. For example, users can control whether the prompts provide additional examples of tasks and / or guidance for performing the task, such as in-context learning, zero-shot learning, and / or few-shot learning. Publicly available LLMs include Bidirectional Encoder Representations from Transformer (BERT) and generative pre-trained transformer (GPT).

[0077] The term "LLM" can refer to the language neural network model itself, but it can also refer to the model of an LLM-based application (e.g., chatbot, AI assistant, translation, summary generation, text classification, sentence generation). For example, an LLM-based chatbot like ChatGPT or an LLM-based translator can also be referred to as "LLM."

[0078] "LLM" may include an inference engine utilizing the LLM neural network model. For example, "inputting an input prompt to the LLM" may mean "inputting the input prompt to an inference engine based on the LLM." For example, "the output of the LLM for the input prompt" may mean the output information of the last neural network layer of the LLM obtained when the input prompt is input to the LLM-based inference engine, and / or the output information modified through additional processing.

[0079] The attention mechanism is a technique that allows an AI model to focus (attention) on important parts of input data. The attention mechanism can be used to predict output data by predicting the extent to which a portion of time-series input data (e.g., time-series input data such as voice or video, or input data of some layers of a neural network) contributes to the output of the intermediate layers and / or the final output of the neural network. While a recurrent neural network (RNN) structure, which sequentially processes each element of a sequence, may exhibit poor prediction performance when there is information dependence between long time-series distances, the attention mechanism can account for information dependence between long time-series distances by controlling the level of weight concentration (attention) within the entire and / or partial context of the input data. A transformer can be configured as an encoder-decoder structure. The encoder can process the input data and output compressed information (e.g., a contextual representation). The decoder can process compressed information and output data in token units. Each encoder and decoder can include an independent attention network, and may further include a cross-attention network connecting the encoder and decoder.

[0080] The electronic device (301) can provide the results of performing a task processed using an artificial intelligence model (e.g., LLM, LVM, and / or LVLM).

[0081] According to one embodiment, the electronic device (301) may include (or store) an artificial intelligence model. The artificial intelligence model may be embedded (or installed or deployed) in the electronic device (301). For example, the electronic device (301) may include a generative artificial intelligence model (e.g., the generative model (250) of FIG. 2). The electronic device (301) may perform a task by on-device artificial intelligence computing using the artificial intelligence model included in the electronic device (301). The electronic device (301) may provide a result of performing a task processed using the artificial intelligence model included in the electronic device (301).

[0082] According to one embodiment, in the system (300), the electronic device (301) and the external electronic device (302) may be connected via direct (e.g., wired) communication or wireless communication (e.g., Bluetooth, WiFi direct, or NFC). The electronic device (301) may offload at least a portion of the work generated by the electronic device (301) to the external electronic device (302). The external electronic device (302) may perform at least a portion of the work generated by the electronic device (301).

[0083] The external electronic device (302) may include (or store) an artificial intelligence model. The artificial intelligence model may be embedded (or installed or distributed) in the external electronic device (302). For example, the external electronic device (302) may include a generative artificial intelligence model (e.g., the generative model (250) of FIG. 2). The external electronic device (302) may perform at least a portion of the tasks generated by the electronic device (301) through on-device artificial intelligence computing using the artificial intelligence model included in the external electronic device (302).

[0084] According to one embodiment, the system (300) may be a system based on the artificial intelligence system (200) of FIG. 2. The system (300) may include at least some components of the artificial intelligence system (200). For example, the electronic device (301) and the external electronic device (302) may be implemented as a user query / response interface (210).

[0085] The electronic device (301) can receive performance information on at least a portion of a task processed using an artificial intelligence model included in the external electronic device (302) from an external electronic device (302). The electronic device (301) can provide a performance result of the task based on the performance information received from the external electronic device (302).

[0086] According to one embodiment, the electronic device (301) and the external electronic device (302) may each include an artificial intelligence model. The external electronic device (302) may perform at least a portion of the tasks generated by the electronic device (301). [Table 1] shows examples of tasks that the electronic device (301) and the external electronic device (302) can perform using the artificial intelligence model, the on-device artificial intelligence model, and the hardware performance.

[0087]

[0088] According to one embodiment, the electronic device (301) may offload tasks (or the performance of tasks) that cannot be performed using an artificial intelligence model on the electronic device (301) to an external electronic device (302). For example, referring to [Table 1], the electronic device (301) may request the external electronic device (302) to perform tasks such as real-time translation or note assist.

[0089] In one embodiment, the electronic device (301) may request an external electronic device (302) with superior performance to the electronic device (301) to perform a task. For example, referring to [Table 1], the electronic device (301) may request an external electronic device (302) with superior hardware performance to perform a task, such as photo editing. Accordingly, the task speed may be improved compared to when the electronic device (301) performs the entire task.

[0090] According to one embodiment, the electronic device (301) may not include an artificial intelligence model, and the external electronic device (302) may include an artificial intelligence model. The external electronic device (302) may perform all tasks generated by the electronic device (301). Even if the electronic device (301) does not include an on-device artificial intelligence model, the electronic device (301) may receive and provide the results of performing tasks processed based on artificial intelligence from the external electronic device (302).

[0091] In operation 310, the electronic device (301) may request performance information of the external electronic device (302) from the external electronic device (302). The performance information of the external electronic device (302) may include hardware performance of the external electronic device (302) and artificial intelligence model information included in the external electronic device (302). The external electronic device (302) may receive a request for performance information from the electronic device (301).

[0092] The hardware performance of the external electronic device (302) may include information about the processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), and / or a neural network processing unit (NPU)), memory, storage, and / or network of the external electronic device (302). For example, the hardware performance of the external electronic device (302) may include at least one of computing performance (e.g., tera floating point operations per second (TFLOPS), tera operations per second (TOPS)), cache size, memory bandwidth, memory capacity, storage speed (e.g., read speed, write speed, input / output operations per second (IOPS)), network performance (e.g., fast Ethernet or Wi-Fi), whether or not in-memory operations are performed, or memory latency.

[0093] The artificial intelligence model information included in the external electronic device (302) may include an on-device artificial intelligence model of the external electronic device (302), such as, for example, a large-scale language model (LLM), a large-scale vision model (LVM), and / or a large-scale vision language model (LVLM).

[0094] In operation 320, the external electronic device (302) can transmit performance information of the external electronic device (302) to the electronic device (301). The electronic device (301) can receive performance information of the external electronic device (302) from the external electronic device (302).

[0095] According to one embodiment, the electronic device (301) may determine whether performance information received from an external electronic device (302) satisfies a condition for performing at least a portion of a task generated by the electronic device (301). For example, the condition may include minimum hardware performance and artificial intelligence model information required to perform the task. For example, the condition may include minimum hardware performance and artificial intelligence model information required for enhanced execution of the task. The condition is described in detail with reference to FIG. 4.

[0096] According to one embodiment, the electronic device (301) may determine, based on performance information received from the external electronic device (302), whether improved performance of a task is possible by the external electronic device (302). Improved performance of a task may include performing the task at a higher speed and / or performing the task to obtain more accurate (or higher quality) results.

[0097] The electronic device (301) may determine that a higher speed task performance is possible by the external electronic device (302) if, for example, the external electronic device (302) can perform more operations per unit time than the electronic device (301) depending on the computational performance of the external electronic device (302), if the external electronic device (302) can process a larger amount of data simultaneously than the electronic device (301) depending on the memory capacity of the external electronic device (302), if the data access or loading time is faster than the electronic device (301) depending on the storage speed of the external electronic device (302), if the external electronic device (302) can transmit data at a higher speed than the electronic device (301) depending on the network performance of the external electronic device (302), and / or if the external electronic device (302) has fewer data input / output bottlenecks than the electronic device (301) depending on the in-memory computation.

[0098] The electronic device (301) may determine that a task can be performed at a higher speed by the external electronic device (302), for example, if the on-device artificial intelligence model of the external electronic device (302) is based on a parallel processing or optimization algorithm relative to the on-device artificial intelligence model of the electronic device (301). The electronic device (301) may determine that a task can be performed to obtain more accurate results by the external electronic device (302), for example, if the external electronic device (302) is equipped with a newer model than the on-device artificial intelligence model of the electronic device (301).

[0099] Enhanced task performance may include offloading tasks that the electronic device (301) does not support for artificial intelligence-based processing to an external electronic device (302). Enhanced task performance may include performing tasks that can save resources (e.g., memory, power consumption, and / or time).

[0100] According to one embodiment, in operation 330, the electronic device (301) may transmit a request to perform a task to the external electronic device (302) if the performance information received from the external electronic device (302) satisfies a condition for performing a task. The external electronic device (302) may receive a request to perform a task from the electronic device (301).

[0101] According to one embodiment, the electronic device (301) may transmit a request to perform a task to the external electronic device (302) if enhanced performance of the task is possible by the external electronic device (302).

[0102] In operation 340, the external electronic device (302) can perform a task based on a task performance request received from the electronic device (301). The external electronic device (302) can perform the task using an artificial intelligence model included in the external electronic device (302).

[0103] In operation 350, the external electronic device (302) can transmit task performance information to the electronic device (301). The electronic device (301) can receive task performance information from the external electronic device (302).

[0104] In operation 360, the electronic device (301) can output a result of performing a task based on the task performance information received from an external electronic device (302).

[0105] Figure 4 is a flowchart of a method for performing a task according to one embodiment.

[0106] According to one embodiment, the operations 410 to 460 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0107] In operation 410, the electronic device may request performance information of a peripheral electronic device (e.g., the electronic device (102) of FIG. 1 or the external electronic device (302) of FIG. 3) that communicates with the electronic device.

[0108] The external electronic device (302) of FIG. 3 may include a peripheral electronic device. In one embodiment, the peripheral electronic device may refer to an external electronic device within a communicable distance (or area) of the electronic device. In one embodiment, the peripheral electronic device may refer to an external electronic device that has communicated with the electronic device (e.g., an external electronic device paired with the electronic device) or an external electronic device that is connected to the same account as the electronic device.

[0109] According to one embodiment, the performance information of the peripheral electronic device may include hardware performance of the peripheral electronic device and artificial intelligence model information included in the peripheral electronic device.

[0110] The hardware performance of the peripheral electronic device may include information about the processor (e.g., central processing unit (CPU), graphics processing unit (GPU), and / or neural processing unit (NPU)), memory, storage, and / or network of the peripheral electronic device. For example, the hardware performance of the peripheral electronic device may include at least one of compute performance (e.g., TFLOPS, TOPS), cache size, memory bandwidth, memory capacity, storage speed (e.g., read speed, write speed, and / or IOPS), network performance (e.g., fast Ethernet or Wi-Fi), in-memory computing, or memory latency.

[0111] The artificial intelligence model information contained in the peripheral electronic device may include an on-device artificial intelligence model of the peripheral electronic device, such as, for example, a large-scale language model (LLM), a large-scale vision model (LVM), and / or a large-scale vision language model (LVLM).

[0112] In operation 420, the electronic device may receive performance information of the peripheral electronic device from the peripheral electronic device.

[0113] In operation 430, the electronic device can determine whether performance information received from a peripheral electronic device satisfies a condition for performing at least a portion of a task generated by the electronic device.

[0114] In one embodiment, the conditions may include minimum hardware performance required to perform at least a portion of the task (e.g., 2.5 TLFOPS or higher, or 17 TOS or higher) and artificial intelligence model information (e.g., LLM, LVM, LVLM, or a specific type of model).

[0115] In one embodiment, the conditions may include minimum hardware performance and artificial intelligence model information required for improved task performance. The conditions may include minimum hardware performance and artificial intelligence model information that enable faster task performance and / or more accurate (or higher quality) results than when the task is performed on an electronic device. For example, the conditions may include improved hardware performance and artificial intelligence model information compared to an electronic device.

[0116] In operation 440, the electronic device may transmit a request to perform at least a portion of the task to the peripheral electronic device if the performance information received from the peripheral electronic device satisfies a condition for performing at least a portion of the task generated by the electronic device.

[0117] In one embodiment, an electronic device can determine whether a peripheral electronic device supports a specified encryption protocol. The electronic device can perform a security authentication procedure prior to transmitting or receiving data associated with a task. The electronic device and the peripheral electronic device can verify support for the specified encryption protocol by exchanging encrypted test messages, public keys, or digital certificates, or by performing a protocol handshake. For example, operations (410, 420) for requesting and receiving performance information may include operations for verifying support for the specified encryption protocol described above.

[0118] In one embodiment, an electronic device may encrypt data associated with a task if the peripheral electronic device supports a specified encryption protocol. The electronic device may transmit a request to the peripheral electronic device to perform the task, including the encrypted data associated with the task. For example, the electronic device may encrypt the data associated with the task using an end-to-end encryption (E2EE) protocol.

[0119] In operation 450, the electronic device may receive information regarding the performance of at least a portion of a task from a peripheral electronic device. The information regarding the performance of at least a portion of the task may include encrypted data regarding the results of performing at least a portion of the task. For example, the peripheral electronic device may encrypt data regarding the results of performing at least a portion of the task using an end-to-end encryption protocol. The electronic device may decrypt the encrypted data included in the information regarding the performance of at least a portion of the task received from the peripheral electronic device.

[0120] In operation 460, the electronic device may output a result of performing the task based on at least a portion of the task performance information received from a peripheral electronic device. The electronic device may output the result of performing the task based on decrypted data.

[0121] The electronic device can output a result of performing a task based on the performance information of the task received from the peripheral electronic device when the task is fully performed in the peripheral electronic device.

[0122] The electronic device may output a result of performing a task based on performance information of a portion of the task received from the peripheral electronic device and performance information of another portion of the task performed by the electronic device, when the task is partially performed by the peripheral electronic device.

[0123] The electronic device may perform a task and output a result of the performed task if performance information received from a peripheral electronic device does not satisfy a condition for performing at least a part of the task generated by the electronic device.

[0124] FIG. 5 is a flowchart of a method for searching a peripheral electronic device according to one embodiment.

[0125] According to one embodiment, the operations 510 to 530 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0126] According to one embodiment, operations 510 and 520 may be performed prior to operation 430 of determining whether performance information received from a peripheral electronic device of FIG. 4 satisfies a condition for performing at least a portion of a task generated by the electronic device.

[0127] In operation 510, the electronic device may generate a task. The task may include functions such as translation, summarization, speech recognition, sentence completion, grammar or spelling check, chatbot, virtual assistant, personalized content recommendation, usage pattern analysis, search pattern analysis, augmented reality content creation, photo editing, video editing, image creation, object recognition, scene understanding, document recognition, or healthcare, which may be performed using an artificial intelligence model.

[0128] In operation 520, the electronic device may generate a condition to perform at least a portion of the task generated by the electronic device.

[0129] In one embodiment, the conditions may include minimum hardware performance and artificial intelligence model information required to perform at least a portion of the task.

[0130] In one embodiment, the conditions may include minimum hardware performance and artificial intelligence model information required for enhanced task performance. The conditions may include minimum hardware performance and artificial intelligence model information that enable task performance at a higher speed and / or yielding more accurate (or higher quality) results than when the task is performed on an electronic device.

[0131] In operation 530, the electronic device may search for a peripheral electronic device (e.g., the electronic device (102) of FIG. 1 or the external electronic device (302) of FIG. 3) that satisfies a condition.

[0132] According to one embodiment, an electronic device can determine whether there is a nearby electronic device capable of communicating with the electronic device. The electronic device can request performance information of the nearby electronic device from a nearby electronic device within a communicable distance (or area) of the electronic device. The electronic device can receive the performance information of the nearby electronic device from the nearby electronic device. The electronic device can determine whether the performance information of the nearby electronic device received from the nearby electronic device satisfies a condition.

[0133] According to one embodiment, an electronic device may determine a peripheral electronic device that satisfies a condition based on communication history information of the electronic device. The communication history information may include at least one of at least one external electronic device that has communicated with the electronic device (e.g., an external electronic device paired with the electronic device or an external electronic device registered under the same account as the electronic device), time information of communication between the electronic device and the at least one external electronic device, or performance information of the at least one external electronic device. For example, the communication history information may include identification information about an external electronic device to which the electronic device has offloaded a task in the past and performance information of the external electronic device. The electronic device may determine a peripheral electronic device that satisfies a condition among at least one external electronic device to which the electronic device has offloaded a task in the past based on the communication history information.

[0134] According to one embodiment, an electronic device may determine a nearby electronic device that satisfies a condition based on the account information of a user of the electronic device. For example, multiple electronic devices (e.g., smartphones, PCs, laptops, and vehicles) including the electronic device may be logged in with the same user's account information. The account information of the user of the electronic device may include performance information for each of the multiple electronic devices owned by the user. For example, the account information of the user of the electronic device may include identification information for at least one electronic device of the user to which the electronic device has previously offloaded a task, and performance information of at least one electronic device of the user. The electronic device may determine a nearby electronic device that satisfies a condition among other electronic devices of the user based on the account information of the user of the electronic device.

[0135] According to one embodiment, operation 430 of determining whether performance information received from a peripheral electronic device of FIG. 4 satisfies a condition for performing at least a portion of a task generated by the electronic device may include operation 530.

[0136] Figure 6 is a flowchart of a method for performing a task according to one embodiment.

[0137] According to one embodiment, the operations 610 to 650 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0138] In operation 610, the electronic device may generate a task. The task may include functions such as translation, summarization, speech recognition, sentence completion, grammar or spelling check, chatbot, virtual assistant, personalized content recommendation, usage pattern analysis, search pattern analysis, augmented reality content creation, photo editing, video editing, image creation, object recognition, scene understanding, document recognition, or healthcare, which may be performed using an artificial intelligence model.

[0139] In operation 620, the electronic device may determine whether a task corresponds to an urgent task. Urgent tasks may include one or more designated tasks that must be performed without substantial delay. For example, urgent tasks may include designated tasks that require real-time results, such as real-time translation, real-time sentence editing, or real-time chat generation.

[0140] In operation 630, the electronic device may perform a task if the task corresponds to an emergency task. The electronic device may perform the task directly using an artificial intelligence model included in the electronic device.

[0141] In operation 640, the electronic device may generate a condition for performing at least a portion of the task if the task does not correspond to an urgent task. If the task is one of one or more designated tasks that do not need to be performed immediately (e.g., analysis requiring large-scale data processing, user-tailored recommendations, or image generation), the electronic device may generate a condition for performing at least a portion of the task. The task corresponding to or not corresponding to an urgent task is not limited to the present disclosure. For example, the electronic device may determine whether a task corresponds to an urgent task differently based on factors such as the scale of data to be processed or user settings, even for tasks of the same type.

[0142] According to one embodiment, operation 640 may be performed prior to operation 430 of determining whether performance information received from a peripheral electronic device of FIG. 4 satisfies a condition for performing at least a portion of a task generated by the electronic device.

[0143] In operation 650, the electronic device may transmit a request to perform at least a portion of the task to a peripheral electronic device (e.g., the electronic device (102) of FIG. 1 or the external electronic device (302) of FIG. 3) if the task does not correspond to an emergency task.

[0144] According to one embodiment, when the performance information received from the peripheral electronic device of FIG. 4 satisfies a condition for performing at least a part of a task generated by the electronic device, operation 440 of transmitting a request to perform at least a part of the task to the peripheral electronic device may include operation 650. That is, the electronic device may transmit a request to perform at least a part of the task to the peripheral electronic device when the performance information received from the peripheral electronic device satisfies a condition for performing at least a part of the task generated by the electronic device and the task does not correspond to an emergency task.

[0145] Figure 7 is a flowchart of a method for performing a task according to one embodiment.

[0146] According to one embodiment, the operations 710 to 770 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0147] In operation 710, the electronic device can generate a task. The electronic device can generate a condition for performing at least a portion of the task generated by the electronic device.

[0148] In operation 720, the electronic device may determine whether there is a peripheral electronic device (e.g., the electronic device (102) of FIG. 1 or the external electronic device (302) of FIG. 3) that is capable of communicating with the electronic device.

[0149] The external electronic device (302) of FIG. 3 may include a peripheral electronic device. In one embodiment, the peripheral electronic device may represent an external electronic device within a communicable distance (or area) of the electronic device. In one embodiment, the peripheral electronic device may represent an external electronic device that has communicated with the electronic device (e.g., an external electronic device paired with the electronic device).

[0150] In operation 730-1, the electronic device can search for a peripheral electronic device that satisfies a condition among at least one peripheral electronic device that is capable of communicating with the electronic device.

[0151] An electronic device may request performance information about a peripheral electronic device from at least one peripheral electronic device within a communication distance (or area) of the electronic device. The electronic device may receive performance information about the peripheral electronic device from the peripheral electronic device. The electronic device may determine whether the performance information about the peripheral electronic device received from the peripheral electronic device satisfies a condition.

[0152] In operation 740, the electronic device is capable of communicating with the electronic device and can immediately transmit a request to perform at least a portion of the task to a peripheral electronic device that satisfies the condition.

[0153] According to one embodiment, if the task of FIG. 6 does not correspond to an emergency task, operation 650 of transmitting a request to perform at least a portion of the task to a peripheral electronic device may include operation 740. That is, if the performance information received from the peripheral electronic device satisfies a condition for performing at least a portion of the task generated by the electronic device, the task does not correspond to an emergency task, and the electronic device is in a state where communication with the peripheral electronic device is possible, the electronic device may immediately transmit a request to perform at least a portion of the task to the peripheral electronic device.

[0154] In operation 750, the electronic device can perform a task if there is no peripheral electronic device that satisfies a condition among at least one peripheral electronic device in communication with the electronic device. The electronic device can directly perform the task using an artificial intelligence model included in the electronic device.

[0155] In operation 730-2, the electronic device can search for a peripheral electronic device that satisfies a condition among peripheral electronic devices that are in a state where communication with the electronic device is impossible.

[0156] According to one embodiment, an electronic device may determine a peripheral electronic device that satisfies a condition based on communication history information of the electronic device. The electronic device may determine a peripheral electronic device that satisfies the condition among at least one external electronic device to which it has previously offloaded any task based on the communication history information.

[0157] According to one embodiment, the electronic device may determine a nearby electronic device that satisfies a condition based on the account information of the user of the electronic device. The electronic device may determine a nearby electronic device that satisfies the condition among other electronic devices of the user based on the account information of the user of the electronic device.

[0158] In operation 760, the electronic device may transmit a request to perform at least a portion of the task to a peripheral electronic device when the electronic device is currently in a state of not being able to communicate with the electronic device and is able to communicate with a peripheral electronic device that satisfies a condition. The electronic device may transmit the request to perform at least a portion of the task to the peripheral electronic device when the peripheral electronic device is within a distance (or area) where the electronic device can communicate with the electronic device.

[0159] According to one embodiment, when the task of FIG. 6 does not correspond to an emergency task, operation 650 of transmitting a request to perform at least a part of the task to a peripheral electronic device may include operation 760. That is, when the performance information received from the peripheral electronic device satisfies a condition for performing at least a part of the task generated by the electronic device, and the task does not correspond to an emergency task and is in a state where communication with the peripheral electronic device is impossible, the electronic device may transmit a request to perform at least a part of the task to the peripheral electronic device when communication with the peripheral electronic device is possible.

[0160] In operation 770, the electronic device can generate recommendation information for performing a task on a peripheral electronic device that is currently in a state of communication incompatibility with the electronic device and that satisfies a condition, based on communication history information of the electronic device.

[0161] According to one embodiment, the communication history information may include at least one of at least one external electronic device that has communicated with the electronic device, time information of communication between the electronic device and the at least one external electronic device, or performance information of the at least one external electronic device. If the communication history information indicates that the electronic device is repeatedly or periodically connected to the external electronic device, the electronic device may determine routine information of the user of the electronic device based on the communication history information. For example, the electronic device may be repeatedly connected to an external electronic device (e.g., a vehicle) around 7:00 AM when the user goes to work. For example, the electronic device may be repeatedly connected to an external electronic device (e.g., a PC, a home appliance) around 9:00 PM when the user returns home. The routine information may indicate a repetitive behavior within a specified error rate regarding the time or time range during which the electronic device and the external electronic device communicate.

[0162] According to one embodiment, the recommendation information may include at least one of a task generated by the electronic device, an external electronic device to perform at least part of the task, or a time to request the external electronic device to perform the task.

[0163] An electronic device may generate recommendation information suggesting that at least part of a task be performed at a time when communication with a nearby electronic device that satisfies a condition is currently unavailable for communication based on the electronic device's communication history information. The electronic device may generate recommendation information suggesting that at least part of a task be performed at a time when communication with a nearby electronic device is possible (or a time when communication is expected to be possible) based on the routine information of the user of the electronic device.

[0164] In operation 780, the electronic device may display recommended information on its display. For example, the electronic device may display a notification such as, "Would you like to perform [task] when connecting to the user's PC after work?" based on the recommended information.

[0165] In operation 790, the electronic device may transmit a request to perform at least a portion of a task to a peripheral electronic device based on user input received regarding the recommendation information.

[0166] The electronic device may receive a user's consent input regarding recommended information. If the electronic device receives a user's consent input regarding recommended information, the electronic device may determine the conditions for performing a task based on the recommended information. The electronic device may schedule a request to perform at least part of the task to a nearby electronic device.

[0167] According to one embodiment, when the task of FIG. 6 does not correspond to an urgent task, operation 650 of transmitting a request to perform at least a part of the task to a peripheral electronic device may include operations 770 to 790. That is, when performance information received from the peripheral electronic device satisfies a condition for performing at least a part of the task generated by the electronic device, the task does not correspond to an urgent task, and communication with the peripheral electronic device is impossible, the electronic device may generate recommendation information based on communication history information, display the recommendation information, and transmit a request to perform at least a part of the task to the peripheral electronic device based on user input received with respect to the recommendation information.

[0168] In operation 750, the electronic device can perform a task if there is no surrounding electronic device that satisfies the condition. The electronic device can directly perform the task using an artificial intelligence model included in the electronic device.

[0169] FIG. 8 is a diagram schematically illustrating a data processing method of an on-device artificial intelligence system according to one embodiment.

[0170] Referring to FIG. 8, the on-device artificial intelligence system (hereinafter, “system”) (300) may include an electronic device (301) (e.g., the electronic device (101) of FIG. 1) and an external electronic device (302) (e.g., the electronic device (102) of FIG. 1). The system (300) is not limited to the illustrated example and may include a plurality of electronic devices. Any description overlapping with that described above with reference to FIG. 3 regarding the system (300) will be omitted.

[0171] According to one embodiment, the electronic device (301) can determine whether the external electronic device (302) supports a specified encryption protocol. The electronic device (301) and the external electronic device (302) can perform an authentication procedure regarding security before transmitting and receiving data associated with a task. The electronic device (301) and the external electronic device (302) can confirm whether each other supports the specified encryption protocol by exchanging encrypted test messages, public keys, or digital certificates, or by performing a protocol handshake.

[0172] In operation 810, the electronic device (301) may encrypt data associated with the task if the external electronic device (302) supports a specified encryption protocol. For example, the specified encryption protocol may be an end-to-end encryption protocol. The electronic device (301) may encrypt data associated with the task using the end-to-end encryption protocol.

[0173] For example, the electronic device (301) can encrypt data about photo files associated with a photo editing task and user input for editing the photo.

[0174] For example, the electronic device (301) may encrypt the user's application execution, web page visit log, usage time, and / or transmitted / received data associated with the user's usage pattern analysis task.

[0175] In operation 820, the electronic device (301) may transmit a request to perform a task, including encrypted data associated with the task, to an external electronic device (302). The external electronic device (302) may receive the request to perform the task from the electronic device (301).

[0176] In operation 830, the external electronic device (302) can decrypt encrypted data included in a request for performing a task received from the electronic device (301).

[0177] In operation 840, the external electronic device (302) can perform a task based on the decrypted data. The external electronic device (302) can perform the task using an artificial intelligence model included in the external electronic device (302).

[0178] According to one embodiment, operation 340 of performing a task based on a request for performing a task received from the electronic device (301) of FIG. 3 may include operations 830 and 840.

[0179] In operation 850, the external electronic device (302) may encrypt data regarding the result of performing the task. For example, the external electronic device (302) may encrypt data regarding the result of performing the task using an end-to-end encryption protocol.

[0180] In operation 860, the external electronic device (302) can transmit task performance information including encrypted data on the result of performing the task to the electronic device (301). The electronic device (301) can receive task performance information from the external electronic device (302).

[0181] In operation 870, the electronic device (301) can decrypt encrypted data included in the task performance information received from the external electronic device (302).

[0182] In operation 880, the electronic device (301) can output the result of performing the task based on the decrypted data.

[0183] According to one embodiment, operation 360 of outputting a result of performing a task based on the performance information of the task received from the external electronic device (302) of FIG. 3 may include operations 870 and 880.

[0184] FIG. 9 is a flowchart of a method for providing recommendation information regarding task performance, according to one embodiment.

[0185] According to one embodiment, the operations 910 to 950 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0186] In operation 910, the electronic device may request performance information of a peripheral electronic device (e.g., the electronic device (102) of FIG. 1 or the external electronic device (302) of FIG. 3) that communicates with the electronic device.

[0187] According to one embodiment, the performance information of the peripheral electronic device may include hardware performance of the peripheral electronic device and artificial intelligence model information included in the peripheral electronic device.

[0188] In operation 920, the electronic device may receive performance information of the peripheral electronic device from the peripheral electronic device.

[0189] At operation 930, the electronic device can determine whether performance information received from a peripheral electronic device satisfies a condition for performing at least a portion of a task generated by the electronic device.

[0190] In one embodiment, the conditions may include minimum hardware performance and artificial intelligence model information required to perform at least a portion of the task.

[0191] In one embodiment, the conditions may include minimum hardware performance and artificial intelligence model information required for enhanced task performance. The conditions may include minimum hardware performance and artificial intelligence model information that enable task performance at a higher speed and / or yielding more accurate (or higher quality) results than when the task is performed on an electronic device.

[0192] In operation 940, the electronic device may generate recommendation information for performing a task on the peripheral electronic device based on communication history information of the electronic device, if performance information received from the peripheral electronic device satisfies a condition for performing at least a part of a task generated by the electronic device.

[0193] According to one embodiment, the communication history information may include at least one of at least one external electronic device that has communicated with the electronic device, time information of communication between the electronic device and the at least one external electronic device, or performance information of the at least one external electronic device.

[0194] According to one embodiment, the recommendation information may include at least one of a task generated by the electronic device, an external electronic device to perform at least part of the task, or a time to request the external electronic device to perform the task.

[0195] According to one embodiment, the electronic device may generate recommendation information based on communication history information when performance information of a peripheral electronic device satisfies a condition for performing at least a portion of a specified task.

[0196] Even if a specific task has not been created, an electronic device can generate recommendations regarding peripheral electronic devices capable of enhanced performance of a specified task (or type of specified task), i.e., enhanced AI-based processing of the task. For example, based on communication history information, an electronic device can generate recommendations regarding peripheral electronic devices capable of enhanced AI-based processing of a photo editing task among external electronic devices that have communicated with the electronic device (e.g., external electronic devices paired with the electronic device).

[0197] According to one embodiment, an electronic device may generate recommendation information regarding the performance of a task for one or more external electronic devices that satisfy a condition for performing at least a portion of a task for which corresponding performance information is generated by the electronic device. The electronic device may generate recommendation information regarding a plurality of external electronic devices when performance information received from the plurality of external electronic devices satisfies the condition.

[0198] For example, the electronic device may generate recommendation information about each of a plurality of external electronic devices that satisfy conditions for performing a specified task.

[0199] For example, the electronic device can generate recommendation information regarding at least one external electronic device that satisfies conditions including minimum hardware performance and artificial intelligence model information required to perform a specified task, and at least one external electronic device capable of enhanced performance of the specified task.

[0200] For example, the electronic device may generate, for each of a plurality of designated tasks, recommendation information about at least one external electronic device that satisfies a condition for performing each task.

[0201] In operation 950, the electronic device may display recommendation information through the display of the electronic device. For example, the electronic device may display a message such as, "Would you like to activate the enhanced AI function of [the peripheral electronic device]?" based on the recommendation information.

[0202] According to one embodiment, the electronic device may display recommendation information regarding a plurality of external electronic devices through a display of the electronic device.

[0203] For example, an electronic device may display a list of multiple external electronic devices that satisfy conditions for performing a specified task. The electronic device may calculate the time required to perform the specified task based on performance information of the multiple external electronic devices. The electronic device may display the time required for the multiple external electronic devices to perform the specified task.

[0204] For example, an electronic device may distinguish and display at least one external electronic device that satisfies conditions including minimum hardware performance and artificial intelligence model information required to perform a specified task, and at least one external electronic device capable of enhanced performance of the specified task. For example, the electronic device may prioritize at least one external electronic device capable of enhanced performance of the specified task among a plurality of external electronic devices. The electronic device may preferentially display (or recommend) at least one external electronic device capable of enhanced performance of the specified task.

[0205] For example, the electronic device may display, for each of a plurality of designated tasks, at least one external electronic device capable of performing each task.

[0206] Figure 10 is a flowchart of a method for performing a task according to one embodiment.

[0207] According to one embodiment, the operations 1010 to 1050 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0208] In operation 1010, the electronic device may generate a task. The task may include functions such as translation, summarization, speech recognition, sentence completion, grammar or spelling check, chatbot, virtual assistant, personalized content recommendation, usage pattern analysis, search pattern analysis, augmented reality content creation, photo editing, video editing, image creation, object recognition, scene understanding, document recognition, or healthcare, which may be performed using an artificial intelligence model.

[0209] In operation 1020, the electronic device may determine whether a task corresponds to an urgent task. An urgent task may include one or more designated tasks that must be performed without substantial delay.

[0210] In operation 1030, the electronic device may perform a task if the task corresponds to an emergency task. The electronic device may perform the task directly using an artificial intelligence model included in the electronic device.

[0211] In operation 1040, if the task does not correspond to an urgent task, the electronic device may generate recommendation information regarding the performance of a task regarding a peripheral electronic device based on the communication history information of the electronic device. If the task is one of one or more designated tasks that do not need to be performed immediately (e.g., analysis requiring large-scale data processing, user-tailored recommendations, image generation), the electronic device may generate recommendation information regarding the performance of a task regarding a peripheral electronic device based on the communication history information of the electronic device. The tasks corresponding to or not corresponding to an urgent task are not limited to the present disclosure. For example, the electronic device may determine whether a task is an urgent task differently based on factors such as the scale of data to be processed or user settings, even for tasks of the same type.

[0212] According to one embodiment, when the performance information received from the peripheral electronic device of FIG. 9 satisfies a condition for performing at least a part of a task generated by the electronic device, operation 940 of generating recommendation information for performing the task related to the peripheral electronic device based on the communication history information of the electronic device may include operation 1040. That is, when the performance information received from the peripheral electronic device satisfies a condition for performing at least a part of a task generated by the electronic device and the task does not correspond to an emergency task, the electronic device may generate recommendation information for performing the task related to the peripheral electronic device based on the communication history information of the electronic device.

[0213] In one embodiment, the electronic device may display recommendation information through a display of the electronic device.

[0214] In operation 1050, the electronic device may transmit a request to perform at least a portion of a task to a nearby electronic device based on user input received regarding the recommendation information. If the electronic device receives a user's consent input regarding the recommendation information, the electronic device may determine the conditions for performing the task based on the recommendation information. The electronic device may schedule the request to perform at least a portion of the task to the nearby electronic device.

[0215] Figure 11 is a flowchart of a method for performing a task according to one embodiment.

[0216] According to one embodiment, the operations 1110 to 1120 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0217] According to one embodiment, the electronic device may generate recommendation information as described with reference to FIGS. 9 and 10. The electronic device may display the recommendation information through a display of the electronic device.

[0218] According to one embodiment, operation 1050 of transmitting a request to perform at least a portion of a task to a peripheral electronic device based on user input received with respect to the recommendation information of FIG. 10 may include operations 1110 and 1120.

[0219] In operation 1110, the electronic device may determine a condition for performing a task with respect to a peripheral electronic device (e.g., the electronic device (102) of FIG. 1 or the external electronic device (302) of FIG. 3) based on a user input. The condition for performing the task may include at least one of an external electronic device from which to request the performance of the task, a time at which to request the performance of the task, a type of task, or data required for the task.

[0220] An electronic device may receive a user's consent input regarding recommended information. When the electronic device receives a user's consent input regarding recommended information, the electronic device may determine the conditions for performing a task based on the recommended information.

[0221] For example, the electronic device may determine to request a nearby electronic device included in the recommendation information to perform a task. For example, the electronic device may determine to request the performance of a task included in the recommendation information. For example, the electronic device may determine to request the performance of a task included in the recommendation information to a nearby electronic device at the time the task is requested. For example, the electronic device may be configured to request the performance of a specified task when it can communicate with a nearby electronic device included in the recommendation information.

[0222] An electronic device may receive user input modifying recommendation information. Upon receiving user input modifying recommendation information, the electronic device may determine conditions for performing an adjusted task based on the user input. For example, the electronic device may receive user input modifying a task (or type of task), a peripheral electronic device to perform at least part of the task, or a time at which the peripheral electronic device is requested to perform the task. Upon receiving user input modifying recommendation information, the electronic device may determine to request performance of the task at the changed time, and / or with the changed peripheral electronic device, based on the user input.

[0223] According to one embodiment, an electronic device may receive user input regarding recommended information regarding a plurality of external electronic devices (or, a plurality of peripheral electronic devices). For example, the electronic device may receive user input for selecting an external electronic device from among a plurality of external electronic devices that satisfy conditions for performing a specified task, from which to request performance of the task. For example, the electronic device may receive user input for selecting an external electronic device capable of enhanced performance of the specified task from among a plurality of external electronic devices. For example, the electronic device may receive user input for selecting an external electronic device from which to request performance of each of the plurality of specified tasks.

[0224] The electronic device may determine to request performance of a task (or enhanced performance of a task) by each of the at least one external electronic device when the electronic device receives user input selecting at least one external electronic device in relation to recommended information about a plurality of external electronic devices.

[0225] In operation 1120, the electronic device may transmit a request to perform at least a portion of the task to the peripheral electronic device based on a condition for performing the task with respect to the peripheral electronic device.

[0226] The electronic device can transmit a request to perform at least a part of the task to a peripheral electronic device at a predetermined time based on the conditions for performing the task.

[0227] The electronic device may transmit a request to perform at least a portion of the task to a peripheral electronic device based on the conditions for performing the task.

[0228] An electronic device may transmit a request to perform at least a part of a task (or type of task) determined according to the conditions for performing the task, along with data required for the task, to a peripheral electronic device.

[0229] The electronic device may transmit a request to perform at least a portion of the task to each of at least one external electronic device (or at least one peripheral electronic device) determined according to the conditions for performing the task.

[0230] According to one embodiment, an electronic device may receive information about the performance of at least a portion of a task from a peripheral electronic device. The electronic device may output a result of the task performance based on the performance information received from the peripheral electronic device.

[0231] Figure 12a is a flowchart of a method for performing a task according to one embodiment.

[0232] According to one embodiment, the operations 1210-1 to 1240-1 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0233] In operation 1210-1, the electronic device may request performance information of the peripheral electronic device from a peripheral electronic device that communicates with the electronic device.

[0234] In one embodiment, an electronic device may request performance information from one or more peripheral electronic devices that communicate with the electronic device.

[0235] In operation 1220-1, the electronic device can receive performance information about the peripheral electronic device from the peripheral electronic device. Any description of the performance information that overlaps with the description provided above with reference to FIGS. 3 to 11 will be omitted.

[0236] According to one embodiment, the electronic device can receive performance information from one or more peripheral electronic devices that communicate with the electronic device.

[0237] In operation 1230-1, the electronic device may determine, based on performance information received from the peripheral electronic device, whether enhanced performance of a task generated by the electronic device is possible by the peripheral electronic device. Enhanced performance of the task may include performing the task at a higher speed and / or performing the task with more accurate (or higher quality) results.

[0238] The electronic device may determine that a higher speed of operation is possible by the peripheral electronic device if, for example, the peripheral electronic device has a computing performance that allows more operations per unit time than the electronic device, if the peripheral electronic device has a memory capacity that allows simultaneous processing of a larger amount of data than the electronic device, if the peripheral electronic device has a storage speed that allows faster data access or loading times than the electronic device, if the peripheral electronic device has a network performance that allows faster data transfer than the electronic device, and / or if the peripheral electronic device has fewer data input / output bottlenecks than the electronic device due to in-memory operations.

[0239] An electronic device may determine that a task can be performed at a higher speed by the peripheral electronic device, for example, if the peripheral electronic device's on-device AI model is based on parallel processing or optimization algorithms compared to the electronic device's on-device AI model. An electronic device may determine that a task can be performed with more accurate results by the peripheral electronic device, for example, if the peripheral electronic device is equipped with a more recent model than the electronic device's on-device AI model.

[0240] In operation 1240-1, the electronic device may transmit a request to perform at least a portion of the task to the peripheral electronic device if the electronic device determines that improved performance of the task is possible by the peripheral electronic device.

[0241] According to one embodiment, the electronic device may transmit a request to perform at least a portion of a task to a peripheral electronic device capable of enhanced performance of the task, if the electronic device determines that at least one peripheral electronic device satisfies conditions including minimum hardware performance and artificial intelligence model information required to perform a specified task and that enhanced performance of the task is possible by at least one other peripheral electronic device.

[0242] In one embodiment, when the electronic device determines that improved performance of the task is possible by a plurality of peripheral electronic devices, the electronic device may transmit a request to perform at least a portion of the task to a peripheral electronic device selected by the user based on user input.

[0243] In one embodiment, when the electronic device determines that improved performance of a task is possible by multiple peripheral electronic devices, the electronic device may transmit a request to perform at least a portion of the task to the peripheral electronic device that requires the shortest time to perform the task.

[0244] Figure 12b is a flowchart of a method for performing a task according to one embodiment.

[0245] According to one embodiment, the operations 1210-2 to 1230-2 below may be performed by an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0246] In operation 1210-2, the electronic device may display a first user interface (UI) regarding a task generated by the electronic device through a display of the electronic device.

[0247] For example, the first UI may represent a screen displayed in response to the execution of an application (e.g., a photo editing application, a translation application, a gallery application, or a note application). For example, the first UI may represent a screen displayed during the process of receiving user input regarding a task.

[0248] An electronic device may request performance information of a peripheral electronic device from a peripheral electronic device that communicates with the electronic device (operation 1210-1). The electronic device may receive performance information of the peripheral electronic device from the peripheral electronic device (operation 1220-1).

[0249] Operations 1210-1 and 1220-1 of FIG. 12A and operation 1210-2 of FIG. 12B may be performed in parallel, sequentially, or at significant time intervals. For example, the electronic device may request performance information from a peripheral electronic device in response to the execution of an application. For example, the electronic device may request performance information from the peripheral electronic device in response to establishing a communication connection with the peripheral electronic device. The electronic device may also establish a communication connection with the peripheral electronic device while the application is running. For example, the electronic device may receive performance information from the peripheral electronic device at a past point in time and store it as communication history information.

[0250] In operation 1220-2, the electronic device may determine whether improved performance of a task generated by the electronic device is possible by the peripheral electronic device based on performance information received from the peripheral electronic device.

[0251] According to one embodiment, an electronic device may generate conditions for performing at least a portion of a task generated by the electronic device. The conditions may include minimum hardware performance and artificial intelligence model information required for enhanced performance of the task. The conditions may include minimum hardware performance and artificial intelligence model information that enable the task to be performed at a higher speed and / or produce more accurate (or higher quality) results than when the task is performed on the electronic device.

[0252] The electronic device may determine that improved performance of a task is possible by the peripheral electronic device if the performance information of the peripheral electronic device satisfies the conditions required for improved performance of the task.

[0253] In operation 1230-2, if the electronic device determines that enhanced performance of the task is possible by the peripheral electronic device, the electronic device may display a second UI indicating that enhanced performance of the task is possible through the display of the electronic device.

[0254] For example, the second UI may represent a screen that includes designated UI elements (e.g., buttons, icons, and / or images) that indicate that enhanced task performance is possible. For example, the second UI may represent a screen that includes designated UI elements that indicate that enhanced task performance is possible in the first UI.

[0255] If the electronic device determines that improved performance of a task is possible with a peripheral electronic device, the electronic device may generate recommendation information regarding the performance of the task with respect to the peripheral electronic device. The recommendation information may include at least one of the task generated by the electronic device, the peripheral electronic device that will perform at least a portion of the task, or a time at which the peripheral electronic device is requested to perform the task. The electronic device may display the recommendation information through the display of the electronic device. Based on user input received regarding the recommendation information, the electronic device may display a second UI indicating that improved performance of the task is possible.

[0256] In one embodiment, the electronic device may transmit a request to perform at least a portion of a task to a peripheral electronic device based on user input received with respect to the second UI.

[0257] The electronic device may determine conditions for performing a task on a peripheral electronic device based on user input received for the second UI. The electronic device may transmit a request for performing at least a portion of the task to the peripheral electronic device based on the conditions for performing the task.

[0258] FIG. 13 and FIG. 14 are diagrams each illustrating an operation method of an on-device artificial intelligence system according to an example.

[0259] The screens (1310, 1410, 1420, 1430, 1440, 1450) are examples of information displayed through a display of an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0260] As described with reference to FIGS. 7, 9, 11, and 12B, an electronic device may generate recommendation information. The recommendation information may include at least one of a task generated by the electronic device, an external electronic device to perform at least part of the task, or a time at which the external electronic device is requested to perform the task. Any description of the recommendation information that overlaps with the above description will be omitted.

[0261] Referring to screen (1310), the electronic device may display a UI for activating enhanced task (or AI task) performance. For example, the electronic device may display a toggle (1301) as a UI element for activating enhanced AI-based processing of the task. The UI for activating enhanced task performance is not limited to the examples described and illustrated herein, and may display a button, icon, checkbox, drop-down menu, or notification.

[0262] The electronic device may offload at least a portion of its work to an external electronic device when enhanced task performance is enabled.

[0263] For example, an electronic device may request an external electronic device to perform a task at a higher speed, perform a task that produces more accurate results, offload a type of task that the electronic device does not support AI-based processing, and / or perform a task that saves resources when enhanced task performance is enabled.

[0264] According to one embodiment, the electronic device may display a peripheral electronic device included in the recommended information that satisfies a specified task and a condition for performing the specified task. The electronic device may display a connection status (e.g., connected or disconnected) between the peripheral electronic device and the electronic device.

[0265] In one embodiment, the electronic device may display a designated task and peripheral electronic device(s) capable of performing an enhanced version of the designated task.

[0266] An electronic device may receive user input regarding recommended information. The electronic device may receive user input regarding enhanced task performance for a peripheral electronic device. Based on the user input received regarding the recommended information, the electronic device may set conditions for performing a task for the peripheral electronic device. The conditions for performing a task may include at least one of the following: an external electronic device from which to request the task, a time at which to request the task, a type of task, or data required for the task.

[0267] For example, the electronic device may receive user input selecting a peripheral electronic device that is capable of communicating with the electronic device, or an external electronic device included in the communication history information, to activate enhanced artificial intelligence-based processing.

[0268] Referring to screen (1410), the electronic device may display a first UI related to a task generated by the electronic device. For example, the electronic device may display a first UI related to a photo editing task in response to the execution of a photo editing application.

[0269] Referring to screen (1420), the electronic device may display a UI for activating enhanced task (or AI task) performance. For example, the electronic device may display a toggle as a UI element for activating enhanced AI-based processing of the task.

[0270] If the electronic device determines that improved performance of a task is possible with a peripheral electronic device, the electronic device may generate recommendation information regarding the performance of the task with respect to the peripheral electronic device. The electronic device may display the recommendation information on its display. The electronic device may display peripheral electronic devices that satisfy the conditions for performing the photo editing task included in the recommendation information. For example, the electronic device may display a peripheral electronic device (1401) that is capable of improved performance of a specified task included in the recommendation information.

[0271] Referring to screens (1430, 1440), for example, the electronic device may display a message such as "Would you like to activate the enhanced AI function (of the [peripheral electronic device]?" based on the recommendation information. The electronic device may receive a user's consent input regarding the recommendation information. Based on the user input received regarding the recommendation information, the electronic device may display a second UI indicating that enhanced performance of the task is possible.

[0272] Referring to screen (1450), the electronic device may display a second UI indicating that enhanced task performance is possible. For example, the electronic device may display a second UI including UI elements (1402) (e.g., buttons, icons, and / or images) indicating that enhanced task performance is possible.

[0273] The electronic device may determine the conditions for performing a task related to a peripheral electronic device (1401) based on user input received for the second UI. For example, the electronic device may receive various inputs related to a photo editing task (e.g., starting photo editing, selecting a photo, or editing an object) for the second UI. The electronic device may determine the conditions for performing the task, including information such as data required for the photo editing task, the peripheral electronic device (1401) to request the task to be performed, and the time at which the task is to be requested to be performed, based on the user input received for the second UI.

[0274] Figure 15 is a drawing illustrating a method of performing a task according to an example.

[0275] The screens (1510, 1520, 1530, 1540, 1550) are examples of information displayed through a display of an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0276] In one embodiment, the electronic device can generate a task. The task may include functions such as translation, summarization, speech recognition, sentence completion, grammar or spelling check, chatbot, virtual assistant, personalized content recommendation, usage pattern analysis, search pattern analysis, augmented reality content creation, photo editing, video editing, image creation, object recognition, scene understanding, document recognition, or healthcare, which can be performed using an artificial intelligence model.

[0277] According to one embodiment, an electronic device may generate a condition for performing at least a portion of a task generated by the electronic device. The electronic device may search for a peripheral electronic device (e.g., the electronic device (102) of FIG. 1 or the external electronic device (302) of FIG. 3) that satisfies the condition. The electronic device may receive performance information about the peripheral electronic device from the peripheral electronic device.

[0278] According to one embodiment, the electronic device may determine a nearby electronic device that satisfies a condition based on communication history information of the electronic device. According to one embodiment, the electronic device may determine a nearby electronic device that satisfies a condition based on account information of a user of the electronic device. If performance information of the nearby electronic device satisfies a condition for performing at least a portion of a task, the electronic device may generate recommendation information based on the communication history information. The recommendation information may include at least one of a task generated by the electronic device, an external electronic device that will perform at least a portion of the task, or a time at which the external electronic device is requested to perform the task.

[0279] According to one embodiment, an electronic device may determine whether improved performance of a task generated by the electronic device is possible based on performance information received from a peripheral electronic device. Any descriptions that overlap with the above-described performance information, communication history information, recommendation information, and improved task performance are omitted.

[0280] According to one embodiment, the electronic device may generate recommendation information regarding peripheral electronic devices capable of enhanced performance of a specified task (or a specified type of task), i.e., enhanced AI-based processing of the task, even when no task has been generated. For example, the electronic device may generate recommendation information regarding peripheral electronic devices capable of enhanced AI-based processing of a photo editing task among external electronic devices paired with the electronic device based on communication history information. For example, the electronic device may generate recommendation information regarding peripheral electronic devices capable of enhanced AI-based processing among external electronic devices currently communicating with the electronic device.

[0281] In one embodiment, the electronic device can identify a task.

[0282] An electronic device can identify a task corresponding to the running application in response to the execution of an application. For example, an electronic device can identify a translation task in response to the execution of a translation application. The electronic device can identify a translation task even if the user has not entered text to be translated, i.e., no specific task has been created.

[0283] An electronic device can identify actions corresponding to application settings. For example, an electronic device can identify a translation action in response to the launch of a messaging application with an automatic translation feature enabled.

[0284] Electronic devices can identify tasks that are performed periodically or repeatedly. For example, electronic devices can identify designated tasks, such as analyzing user usage patterns and health care tasks, that are performed at specified intervals.

[0285] In one embodiment, an electronic device can generate conditions for performing an identified task. The electronic device can search for nearby electronic devices that satisfy the conditions. The electronic device can generate recommendation information regarding nearby electronic devices capable of enhanced AI-based processing of the identified task that satisfies the conditions.

[0286] Referring to screen (1510), the electronic device may display a first UI regarding a task generated on the electronic device.

[0287] An electronic device may identify a photo editing task in response to the execution of a photo editing application. In response to the execution of the photo editing application, the electronic device may display a first UI related to the photo editing task. The electronic device may display the first UI, which is a screen displayed during the process of receiving user input related to the photo editing task.

[0288] An electronic device can request performance information from a peripheral electronic device that communicates with the electronic device. The electronic device can receive performance information from the peripheral electronic device.

[0289] The electronic device can determine, based on performance information received from the peripheral electronic device, whether improved performance of a task generated by the electronic device is possible by the peripheral electronic device.

[0290] Referring to screen (1520), if the electronic device determines that enhanced performance of a task is possible by a peripheral electronic device, the electronic device may display a second UI indicating that enhanced performance of the task is possible. For example, the electronic device may display a second UI including UI elements (1501) (e.g., buttons, icons, and / or images) indicating that enhanced performance of the task is possible. The second UI may represent a screen with UI elements (1501) indicating that enhanced performance of the task is possible added to the first UI.

[0291] The electronic device may receive user input for the second UI. For example, on screen (1520), the electronic device may receive user input selecting a UI element (1501). In response to receiving user input selecting the UI element (1501), the electronic device may activate enhanced operation performance (or enhanced artificial intelligence-based processing) for a photo editing task.

[0292] On screen (1530), in response to activation of enhanced task performance, the electronic device may display a modified UI indicating the enhanced task performance. For example, the electronic device may display a modified UI including a UI element indicating the enhanced task performance (a 'generate' button) (1502).

[0293] Referring to screens (1530, 1540), the electronic device may receive user input regarding a task. For example, the electronic device may receive user input regarding a photo editing task (e.g., selecting an object, moving an object, or rotating a photo).

[0294] The electronic device may receive user input for creating a task. For example, the electronic device may receive user input for editing a photo (e.g., a touch input to a UI element (1502)) based on user input related to a photo editing task. The electronic device may then create a new task based on the user input for creating the task.

[0295] The electronic device may determine conditions for performing a task on a peripheral electronic device based on user input received for the changed UI. The electronic device may transmit a request for performing at least a portion of the task to the peripheral electronic device based on the conditions for performing the task.

[0296] An electronic device can encrypt data related to photo files and user input for editing photos associated with a photo editing task. The electronic device can transmit a request to perform the task to a peripheral electronic device. The request may include encrypted data. The electronic device can receive information about the task's performance from the peripheral electronic device.

[0297] Referring to screen (1550), the electronic device can output a task execution result based on performance information received from a peripheral electronic device. The electronic device can output an edited photo using an artificial intelligence model included in the peripheral electronic device.

[0298] FIG. 16 is a diagram illustrating an operation method of an on-device artificial intelligence system according to an example.

[0299] The screens (1610, 1620, 1630) are examples of information displayed through a display of an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (301) of FIG. 3). The electronic device may include at least some of the components of the electronic device (101) described in FIG. 1. For example, the electronic device may include at least one processor including a processing circuit (e.g., the processor (120) of FIG. 1), a memory including one or more storage media for storing instructions (e.g., the memory (130) of FIG. 1), and a communication unit (e.g., the communication module (190) of FIG. 1).

[0300] If the electronic device determines that improved performance of a task is possible with a peripheral electronic device, the electronic device may generate a recommendation regarding the performance of the task with respect to the peripheral electronic device. The recommendation may include at least one of the following: a task generated by the electronic device, a peripheral electronic device to perform at least a portion of the task, or a time at which the peripheral electronic device is requested to perform the task.

[0301] On screen (1610), the electronic device may display recommended information via its display. For example, the electronic device may display a notification based on the recommended information, such as, "Would you like to perform [enhanced AI tasks] when connected to 'your car' after work?"

[0302] The electronic device may receive a user's consent input regarding recommended information. If the electronic device receives a user's consent input regarding recommended information, the electronic device may determine the conditions for performing a task based on the recommended information.

[0303] The electronic device may receive user input to modify the recommended information. When the electronic device receives user input to modify the recommended information, the electronic device may determine conditions for performing an action adjusted based on the user input.

[0304] On screen (1620), the electronic device may display a UI indicating that improved performance of a task is possible based on receiving a user's consent input regarding recommended information. The electronic device may display a UI indicating information regarding the performance of the task (e.g., a reservation time, and / or identification information of a nearby electronic device).

[0305] An electronic device may transmit a request to perform at least a portion of a task to a peripheral electronic device based on the performance conditions of the task. For example, the electronic device may transmit a request to perform at least a portion of the task to a peripheral electronic device at a predetermined time based on the performance conditions of the task. For example, the electronic device may transmit a request to perform at least a portion of the task to a predetermined peripheral electronic device based on the performance conditions of the task. For example, the electronic device may transmit a request to perform at least a portion of the task (or type of task) based on the performance conditions of the task, along with data required for the task, to a peripheral electronic device.

[0306] On the screen (1630), the electronic device may display a UI indicating the progress or status of a task. For example, the electronic device may display a notification containing information such as the degree of task completion and / or the expected time.

[0307] According to one embodiment, if the electronic device cannot perform a task (or enhance the performance of the task) due to a peripheral electronic device (e.g., if there is no peripheral electronic device that satisfies the conditions required to perform the task, if communication with a peripheral electronic device that satisfies the conditions is impossible, or if communication with a peripheral electronic device is impossible at a scheduled time), the electronic device may display a UI indicating that the task cannot be performed. For example, the electronic device may suggest moving closer to a peripheral electronic device that satisfies the conditions, or display a notification or message suggesting resetting the conditions for performing the task.

[0308] In one embodiment, a method performed by an electronic device (101; 301) may include an operation of requesting performance information of a peripheral electronic device (102; 302) communicating with the electronic device (101; 301), an operation of receiving performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302), an operation of transmitting a request for performing at least a part of a task generated in the electronic device (101; 301) to the peripheral electronic device (102; 302) if the performance information received from the peripheral electronic device (102; 302) satisfies a condition for performing at least a part of the task, an operation of receiving performance information of at least a part of the task from the peripheral electronic device (102; 302), and an operation of outputting a result of performing the task based on the performance information received from the peripheral electronic device (102; 302).

[0309] According to one embodiment, the performance information may include artificial intelligence model information included in the peripheral electronic device (102; 302) and hardware performance of the peripheral electronic device (102; 302).

[0310] According to one embodiment, a method performed by an electronic device (101; 301) may further include an operation of generating a condition for performing at least a part of a task generated in the electronic device (101; 301), the condition including minimum hardware performance and artificial intelligence model information required to perform at least a part of the task, and an operation of determining whether performance information received from a peripheral electronic device (102; 302) satisfies the condition for performing at least a part of the task.

[0311] According to one embodiment, the method performed by the electronic device (101; 301) further includes an operation of determining whether the task corresponds to an urgent task, and if the performance information satisfies a condition for performing at least a part of the task generated by the electronic device (101; 301), the operation of transmitting a request for performing at least a part of the task to a peripheral electronic device (102; 302) may include an operation of transmitting a request for performing at least a part of the task to the peripheral electronic device (102; 302) if the performance information satisfies the condition and the task does not correspond to an urgent task.

[0312] According to one embodiment, when the performance information satisfies the condition and the task does not correspond to an emergency task, the operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) may include an operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) when the electronic device (101; 301) is in a state where it cannot communicate with the peripheral electronic device (102; 302) when it can communicate with the peripheral electronic device (102; 302).

[0313] According to one embodiment, when the performance information satisfies the condition and the task does not correspond to an emergency task, the operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) may include, when the electronic device (101; 301) is in a state where communication with the peripheral electronic device (102; 302) is impossible, the operation of generating recommendation information for performing the task for the peripheral electronic device (102; 302) based on communication history information of the electronic device (101; 301), the operation of displaying the recommendation information through a display of the electronic device (101; 301), and the operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) based on a user input received with respect to the recommendation information.

[0314] According to one embodiment, the communication history information may include at least one of at least one external electronic device (102; 302) that has communicated with the electronic device (101; 301), time information of communication between the electronic device (101; 301) and the at least one external electronic device (102; 302), or performance information of the at least one external electronic device (102; 302).

[0315] In one embodiment, the recommendation information may include at least one of a task generated by the electronic device (101; 301), an external electronic device (102; 302) to perform at least part of the task, or a time to request the external electronic device (102; 302) to perform the task.

[0316] According to one embodiment, the act of transmitting a request to perform at least a portion of a task to a peripheral electronic device (102; 302) may include, if the peripheral electronic device (102; 302) supports a specified encryption protocol, encrypting data associated with the task and transmitting a request to perform at least a portion of the task including the encrypted data to the peripheral electronic device (102; 302).

[0317] According to one embodiment, the operation of outputting the performance result of a task based on the performance information received from the peripheral electronic device (102; 302) may include the operation of decrypting encrypted data included in the performance information received from the peripheral electronic device (102; 302) and the operation of outputting the performance result of the task based on the decrypted data.

[0318] According to one embodiment, a method performed by an electronic device (101; 301) may include an operation of requesting performance information of a peripheral electronic device (102; 302) communicating with the electronic device (101; 301), an operation of receiving performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302), an operation of generating recommendation information for performing a task related to the peripheral electronic device (102; 302) based on communication history information of the electronic device (101; 301) when the performance information received from the peripheral electronic device (102; 302) satisfies a condition for performing at least a part of a task generated in the electronic device (101; 301), and an operation of displaying the recommendation information through a display of the electronic device (101; 301).

[0319] According to one embodiment, the performance information may include hardware performance of the peripheral electronic device (102; 302) and artificial intelligence model information included in the peripheral electronic device (102; 302).

[0320] According to one embodiment, a method performed by an electronic device (101; 301) may further include an operation of generating a condition for performing at least a part of a task generated in the electronic device (101; 301), the condition including minimum hardware performance and artificial intelligence model information required to perform at least a part of the task, and an operation of determining whether performance information received from a peripheral electronic device (102; 302) satisfies the condition for performing at least a part of the task.

[0321] According to one embodiment, a method performed by an electronic device (101; 301) may further include an operation of transmitting a request for performing at least a part of a task to a peripheral electronic device (102; 302) based on a user input received regarding recommendation information, an operation of receiving performance information of at least a part of the task from the peripheral electronic device (102; 302), and an operation of outputting a performance result of the task based on the performance information received from the peripheral electronic device (102; 302).

[0322] According to one embodiment, the method performed by the electronic device (101; 301) further includes an operation of determining whether the task corresponds to an emergency task, and if the performance information satisfies a condition for performing at least a part of the task generated by the electronic device (101; 301), the operation of generating recommendation information for performing the task on a peripheral electronic device (102; 302) based on communication history information of the electronic device (101; 301) may include an operation of generating recommendation information for performing the task on a peripheral electronic device (102; 302) based on communication history information of the electronic device (101; 301) if the performance information satisfies the condition and the task does not correspond to an emergency task.

[0323] According to one embodiment, the communication history information may include at least one of at least one external electronic device (102; 302) that has communicated with the electronic device (101; 301), time information of communication between the electronic device (101; 301) and the at least one external electronic device (102; 302), or performance information of the at least one external electronic device (102; 302).

[0324] In one embodiment, the recommendation information may include at least one of a task generated by the electronic device (101; 301), an external electronic device (102; 302) to perform at least a portion of the task, or a time at which to request the external electronic device (102; 302) to perform at least a portion of the task.

[0325] According to one embodiment, the operation of transmitting a request to perform at least a portion of a task to a peripheral electronic device (102; 302) based on user input received regarding recommendation information may include: determining, based on the user input, a time at which to request the peripheral electronic device (102; 302) to perform at least a portion of the task; and transmitting, at the determined time, the request to perform at least a portion of the task to the peripheral electronic device (102; 302).

[0326] In one embodiment, a method performed by an electronic device (101; 301) may include an operation of requesting performance information of a peripheral electronic device (102; 302) communicating with the electronic device (101; 301), an operation of receiving performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302), an operation of determining whether enhanced execution of a task generated in the electronic device (101; 301) is possible by the peripheral electronic device (102; 302) based on the performance information received from the peripheral electronic device (102; 302), and an operation of transmitting a request for execution of at least a part of the task to the peripheral electronic device (102; 302) when it is determined that enhanced execution of the task is possible by the peripheral electronic device (102; 302).

[0327] According to one embodiment, the performance information may include hardware performance of the peripheral electronic device (102; 302) and artificial intelligence model information included in the peripheral electronic device (102; 302).

[0328] According to one embodiment, a method performed by an electronic device (101; 301) may further include an operation of displaying a first UI (user interface) regarding a task generated in the electronic device (101; 301) through a display of the electronic device (101; 301) and an operation of displaying a second UI indicating that enhanced performance of the task is possible through the display when it is determined that enhanced performance of the task is possible by a peripheral electronic device (102; 302).

[0329] According to one embodiment, when it is determined that improved performance of a task is possible by the peripheral electronic device (102; 302), the operation of displaying a second UI indicating that improved performance of the task is possible may include, when it is determined that improved performance of the task is possible by the peripheral electronic device (102; 302), the operation of generating recommendation information for performance of the task with respect to the peripheral electronic device (102; 302), the operation of displaying the recommendation information through a display of the electronic device (101; 301), and the operation of displaying a second UI indicating that improved performance of the task is possible based on a user input received with respect to the recommendation information.

[0330] According to one embodiment, the act of transmitting a request to perform at least a portion of a task to a peripheral electronic device (102; 302) may include transmitting a request to perform at least a portion of a task to the peripheral electronic device (102; 302) based on a user input received with respect to the second UI.

[0331] In one embodiment, the recommendation information may include at least one of a task generated by the electronic device (101; 301), an external electronic device (102; 302) to perform at least a portion of the task, or a time at which to request the external electronic device (102; 302) to perform at least a portion of the task.

[0332] According to one embodiment, the operation of transmitting a request to perform at least a part of a task to a peripheral electronic device (102; 302) based on a user input received for the second UI may include an operation of determining, based on the user input, a condition for performing the task with respect to the peripheral electronic device (102; 302) and an operation of transmitting, based on the condition for performing the task, a request to perform at least a part of the task to the peripheral electronic device (102; 302).

[0333] According to one embodiment, a non-transitory computer-readable recording medium can store a program for executing a method performed by an electronic device (101; 301) in combination with hardware.

[0334] According to one embodiment, a non-transitory computer-readable recording medium stores one or more programs including instructions, which, when individually or collectively executed by at least one processor of an electronic device, cause the electronic device to: request performance information of a peripheral electronic device (102; 302) from a peripheral electronic device (102; 302) in communication with the electronic device (101; 301); receive performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302); transmit a request for performing at least a part of a task generated in the electronic device (101; 301) to the peripheral electronic device (102; 302) if the performance information received from the peripheral electronic device (102; 302) satisfies a condition for performing at least a part of the task; receive performance information of at least a part of the task from the peripheral electronic device (102; 302); And an operation of outputting the result of performing a task based on the performance information received from the peripheral electronic device (102; 302) can be performed.

[0335] According to one embodiment, a non-transitory computer-readable recording medium stores one or more programs including instructions, which when individually or collectively executed by at least one processor of an electronic device, cause the electronic device (101; 301) to: request performance information of a peripheral electronic device (102; 302) in communication with the electronic device (101; 301); receive performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302); and determine, based on the performance information received from the peripheral electronic device (102; 302), whether enhanced execution of a task generated in the electronic device (101; 301) is possible by the peripheral electronic device (102; 302). If it is determined that improved performance of the task is possible by the peripheral electronic device (102; 302), an operation may be performed to transmit a request for performance of at least a portion of the task to the peripheral electronic device (102; 302).

[0336] According to one embodiment, an electronic device (101; 301) includes at least one processor (120) including processing circuitry and a memory (130) including one or more storage media storing instructions, wherein when the instructions are individually or collectively executed by the at least one processor (120), the electronic device (101; 301) performs: an operation (410) of requesting performance information of a peripheral electronic device (102; 302) from a peripheral electronic device (102; 302) in communication with the electronic device (101; 301); an operation (420) of receiving performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302); When the performance information received from the peripheral electronic device (102; 302) satisfies a condition for performing at least a part of a task generated in the electronic device (101; 301), the operation (440) of transmitting a request for performing at least a part of the task to the peripheral electronic device (102; 302); the operation (450) of receiving performance information for at least a part of the task from the peripheral electronic device (102; 302); and the operation (460) of outputting a performance result of the task based on the performance information received from the peripheral electronic device (102; 302) can be performed.

[0337] According to one embodiment, when the instructions are individually or collectively executed by at least one processor (120), the electronic device (101; 301) may further perform the following operations: generating a condition for performing at least a part of a task generated in the electronic device (101; 301), the condition including minimum hardware performance and artificial intelligence model information required to perform at least a part of the task; and determining whether performance information received from a peripheral electronic device (102; 302) satisfies the condition for performing at least a part of the task.

[0338] According to one embodiment, when the instructions are individually or collectively executed by at least one processor (120), the electronic device (101; 301) further performs: an operation (620) of determining whether a task corresponds to an urgent task, and if the performance information satisfies a condition for performing at least a portion of the task generated by the electronic device (101; 301), an operation (440) of transmitting a request for performing at least a portion of the task to a peripheral electronic device (102; 302) may include an operation of transmitting a request for performing at least a portion of the task to the peripheral electronic device (102; 302) if the performance information satisfies the condition and the task does not correspond to an urgent task.

[0339] According to one embodiment, when the performance information satisfies the condition and the task does not correspond to an emergency task, the operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) may include an operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) when the electronic device (101; 301) is in a state where it cannot communicate with the peripheral electronic device (102; 302) when it can communicate with the peripheral electronic device (102; 302).

[0340] According to one embodiment, when the performance information satisfies the condition and the task does not correspond to an emergency task, the operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) may include: when the electronic device (101; 301) is in a state where communication with the peripheral electronic device (102; 302) is impossible, the operation of generating recommendation information for performing the task for the peripheral electronic device (102; 302) based on communication history information of the electronic device (101; 301); the operation of displaying the recommendation information through a display of the electronic device (101; 301); and the operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) based on a user input received with respect to the recommendation information.

[0341] According to one embodiment, the operation of transmitting a request to perform at least a portion of a task to a peripheral electronic device (102; 302) based on user input received regarding the recommendation information may include: determining, based on user input received regarding the recommendation information, a condition for performing the task with respect to the peripheral electronic device (102; 302); and transmitting, based on the condition for performing the task, a request to perform at least a portion of the task to the peripheral electronic device (102; 302).

[0342] According to one embodiment, the communication history information may include at least one of at least one external electronic device (102; 302) that has communicated with the electronic device (101; 301), time information of communication between the electronic device (101; 301) and the at least one external electronic device (102; 302), or performance information of the at least one external electronic device (102; 302).

[0343] In one embodiment, the recommendation information may include at least one of a task generated by the electronic device (101; 301), an external electronic device (102; 302) to perform at least a portion of the task, or a time at which to request the external electronic device (102; 302) to perform at least a portion of the task.

[0344] According to one embodiment, the operation of transmitting a request to perform at least a portion of a task to a peripheral electronic device (102; 302) may include: encrypting data associated with the task if the peripheral electronic device (102; 302) supports a specified encryption protocol; and transmitting a request to perform at least a portion of the task including encrypted data to the peripheral electronic device (102; 302).

[0345] According to one embodiment, the operation of outputting the performance result of a task based on the performance information received from the peripheral electronic device (102; 302) may include the operation of decrypting encrypted data included in the performance information received from the peripheral electronic device (102; 302); and the operation of outputting the performance result of the task based on the decrypted data.

[0346] According to one embodiment, an electronic device (101; 301) includes at least one processor (120) including processing circuitry and a memory (130) including one or more storage media storing instructions, wherein when the instructions are individually or collectively executed by the at least one processor (120), the electronic device (101; 301) performs: an operation (1210-1) of requesting performance information of a peripheral electronic device (102; 302) from a peripheral electronic device (102; 302) communicating with the electronic device (101; 301); an operation (1220-1) of receiving performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302); An operation (1230-1) of determining whether enhanced execution of a task generated in an electronic device (101; 301) is possible by the peripheral electronic device (102; 302) based on performance information received from the peripheral electronic device (102; 302); and an operation (1240-1) of transmitting a request for execution of at least a part of the task to the peripheral electronic device (102; 302) when it is determined that enhanced execution of the task is possible by the peripheral electronic device (102; 302).

[0347] According to one embodiment, the performance information may include hardware performance of the peripheral electronic device (102; 302) and artificial intelligence model information included in the peripheral electronic device (102; 302).

[0348] According to one embodiment, when the instructions are individually or collectively executed by at least one processor (120), the electronic device (101; 301) may further perform: an operation (1210-2) of displaying a first UI (user interface) regarding a task generated in the electronic device (101; 301) through a display of the electronic device (101; 301); and an operation (1230-2) of displaying a second UI indicating that the enhanced performance of the task is possible through the display when it is determined that the enhanced performance of the task is possible by the peripheral electronic device (102; 302).

[0349] According to one embodiment, when it is determined that improved performance of a task is possible by the peripheral electronic device (102; 302), the operation (1230-2) of displaying a second UI indicating that improved performance of the task is possible may include: when it is determined that improved performance of the task is possible by the peripheral electronic device (102; 302), the operation of generating recommendation information for performance of the task with respect to the peripheral electronic device (102; 302); the operation of displaying the recommendation information through a display of the electronic device (101; 301); and the operation of displaying a second UI indicating that improved performance of the task is possible based on a user input received regarding the recommendation information.

[0350] According to one embodiment, the operation (1240-1) of transmitting a request to perform at least a portion of a task to a peripheral electronic device (102; 302) may include an operation of transmitting a request to perform at least a portion of a task to the peripheral electronic device (102; 302) based on a user input received for the second UI.

[0351] According to one embodiment, the operation of transmitting a request to perform at least a part of a task to a peripheral electronic device (102; 302) based on a user input received for the second UI may include an operation (1110) of determining a condition for performing the task with respect to the peripheral electronic device (102; 302) based on the user input; and an operation (1120) of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) based on the condition for performing the task.

[0352] In one embodiment, the recommendation information may include at least one of a task generated by the electronic device (101; 301), an external electronic device (102; 302) to perform at least a portion of the task, or a time at which to request the external electronic device (102; 302) to perform at least a portion of the task.

[0353] The embodiments described above may be implemented using hardware components, software components, and / or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and software applications running on the operating system. Furthermore, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0354] Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may, independently or collectively, command the processing device. The software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave, for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on a computer-readable recording medium.

[0355] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination, and the program commands recorded on the medium may be those specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc.

[0356] The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0357] Although the embodiments have been described with limited drawings, those skilled in the art will appreciate that various technical modifications and variations can be applied based on the described embodiments. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0358] Therefore, other implementations, embodiments and equivalents to the claims also fall within the scope of the claims described below.

Claims

1. In an electronic device (101; 301), At least one processor (120) comprising processing circuitry; and A memory (130) comprising one or more storage media for storing instructions, When the above instructions are individually or collectively executed by the at least one processor (120), the electronic device (101; 301) causes: An operation (410) of requesting performance information of a peripheral electronic device (102; 302) communicating with the electronic device (101; 301); An operation (420) of receiving performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302); An operation (440) of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) when the performance information received from the peripheral electronic device (102; 302) satisfies a condition for performing at least a part of the task generated in the electronic device (101; 301); An operation (450) of receiving performance information of at least a part of the task from the peripheral electronic device (102; 302); and An operation (460) of outputting the performance result of the task based on the performance information received from the peripheral electronic device (102; 302) to perform, Electronic devices (101; 301).

2. In paragraph 1, The above performance information includes artificial intelligence model information included in the peripheral electronic device (102; 302) and hardware performance of the peripheral electronic device (102; 302). Electronic devices (101; 301).

3. In either of paragraphs 1 and 2, When the above instructions are individually or collectively executed by the at least one processor (120), the electronic device (101; 301) causes: An operation of generating a condition for performing at least a part of the work generated in the electronic device (101; 301), wherein the condition includes minimum hardware performance and artificial intelligence model information required to perform at least a part of the work; and An operation of determining whether the performance information received from the peripheral electronic device (102; 302) satisfies the condition for performing at least a part of the task. to do more, Electronic devices (101; 301).

4. In any one of paragraphs 1 to 3, When the above instructions are individually or collectively executed by the at least one processor (120), the electronic device (101; 301) causes: Action (620) to determine whether the above task corresponds to an emergency task. To do more, If the performance information satisfies the condition for performing at least a part of the task generated in the electronic device (101; 301), the operation (440) of transmitting a request for performing at least a part of the task to the peripheral electronic device (102; 302) is An operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) when the performance information satisfies the condition and the task does not correspond to the emergency task. including, Electronic devices (101; 301).

5. In any one of paragraphs 1 to 4, If the above performance information satisfies the above conditions and the task does not correspond to an emergency task, the operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) is When the electronic device (101; 301) is in a state where it cannot communicate with the peripheral electronic device (102; 302), an operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) when it can communicate with the peripheral electronic device (102; 302) including, Electronic devices (101; 301).

6. In any one of paragraphs 1 to 5, If the above performance information satisfies the above conditions and the task does not correspond to an emergency task, the operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) is An operation of generating recommendation information for performing the task on the peripheral electronic device (102; 302) based on the communication history information of the electronic device (101; 301) when the electronic device (101; 301) is in a state where communication with the peripheral electronic device (102; 302) is impossible; An operation of displaying the above recommended information through the display of the electronic device (101; 301); and An operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) based on user input received regarding the above recommendation information. including, Electronic devices (101; 301).

7. In any one of paragraphs 1 to 6, An operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) based on user input received regarding recommendation information for performing the task, An operation of determining a condition for performing the task regarding the peripheral electronic device (102; 302) based on the user input received regarding the recommendation information; and An operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) based on the performance conditions of the task. including, Electronic devices (101; 301).

8. In any one of paragraphs 1 to 7, The operation of transmitting a request to perform at least a part of the above task to the above peripheral electronic device (102; 302) comprises: An operation of encrypting data associated with the task, if the peripheral electronic device (102; 302) supports a specified encryption protocol; and An operation of transmitting a request to perform at least a part of the task including the encrypted data to the peripheral electronic device (102; 302). Includes, The operation of outputting the performance result of the task based on the performance information received from the peripheral electronic device (102; 302) is as follows: An operation of decrypting encrypted data included in the performance information received from the peripheral electronic device (102; 302); and An operation of outputting the result of the above-described operation based on the above-described decrypted data. including, Electronic devices (101; 301).

9. In the electronic device (101; 301), At least one processor (120) comprising processing circuitry; and A memory (130) comprising one or more storage media for storing instructions, When the above instructions are individually or collectively executed by the at least one processor (120), the electronic device (101; 301) causes: An operation (1210-1) of requesting performance information of a peripheral electronic device (102; 302) communicating with the electronic device (101; 301); An operation (1220-1) of receiving performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302); An operation (1230-1) of determining whether enhanced execution of a task generated in an electronic device (101; 301) is possible by the peripheral electronic device (102; 302) based on the performance information received from the peripheral electronic device (102; 302); and When it is determined that improved performance of the task is possible by the peripheral electronic device (102; 302), an operation (1240-1) of transmitting a request for performance of at least a part of the task to the peripheral electronic device (102; 302) to perform, Electronic devices (101; 301).

10. In paragraph 9, The above performance information includes hardware performance of the peripheral electronic device (102; 302) and artificial intelligence model information included in the peripheral electronic device (102; 302). Electronic devices (101; 301).

11. In any one of paragraphs 9 and 10, When the above instructions are individually or collectively executed by the at least one processor (120), the electronic device (101; 301) causes: An operation (1210-2) of displaying a first UI (user interface) regarding a task generated in the electronic device (101; 301) through the display of the electronic device (101; 301); and When it is determined that improved performance of the task is possible by the peripheral electronic device (102; 302), an operation (1230-2) of displaying a second UI indicating that improved performance of the task is possible through the display to do more, Electronic devices (101; 301).

12. In any one of paragraphs 9 to 11, When it is determined that the improved performance of the task is possible by the peripheral electronic device (102; 302), the operation (1230-2) of displaying a second UI indicating that the improved performance of the task is possible is An action of generating recommendation information for performance of the task with respect to the peripheral electronic device (102; 302), when it is determined that improved performance of the task is possible by the peripheral electronic device (102; 302); An operation of displaying the above recommended information through the display of the electronic device (101; 301); and An action of displaying the second UI indicating that improved performance of the task is possible based on user input received regarding the above recommendation information. including, Electronic devices (101; 301).

13. In any one of paragraphs 9 to 12, The operation (1240-1) of transmitting a request to perform at least a part of the above task to the peripheral electronic device (102; 302) is An operation of transmitting a request for performing at least a part of the task to the peripheral electronic device (102; 302) based on a user input received for the second UI indicating that enhanced performance of the task is possible. Includes, An operation of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) based on the user input received for the second UI, An operation (1110) of determining a condition for performing the task on the peripheral electronic device (102; 302) based on the user input; and An operation (1120) of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) based on the performance conditions of the task. including, Electronic devices (101; 301).

14. In a method performed by an electronic device (101; 301), An operation (410) of requesting performance information of a peripheral electronic device (102; 302) communicating with the electronic device (101; 301); An operation (420) of receiving performance information of the peripheral electronic device (102; 302) from the peripheral electronic device (102; 302); An operation (440) of transmitting a request to perform at least a part of the task to the peripheral electronic device (102; 302) when the performance information received from the peripheral electronic device (102; 302) satisfies a condition for performing at least a part of the task generated in the electronic device (101; 301); An operation (450) of receiving performance information of at least a part of the task from the peripheral electronic device (102; 302); and An operation (460) of outputting the performance result of the task based on the performance information received from the peripheral electronic device (102; 302) including, method.

15. A non-transitory computer-readable recording medium storing a program for executing the method of claim 14 in combination with hardware.

Images