Electronic device and method for acquiring media content by using model, and non-transitory computer-readable storage medium

The electronic device employs a generative AI model to generate media content that excludes specific portions, addressing the inconvenience of missing important information by maintaining user-selected parts.

WO2026005234A1PCT designated stage Publication Date: 2026-01-02SAMSUNG ELECTRONICS CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2025/005255
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-09-04
Filing Date
2025-04-17
Publication Date
2026-01-02

AI Technical Summary

Technical Problem

Existing electronic devices face challenges in providing media content that omits specific portions, such as appointment times, which can inconvenience users by not including important information.

Method used

An electronic device uses a generative artificial intelligence model to generate media content based on user input and a prompt, ensuring that specific portions, like appointment times, are excluded from the output.

Benefits of technology

The solution effectively generates media content that maintains user-selected portions, alleviating inconvenience by ensuring important information is not omitted.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2025005255_02012026_PF_FP_ABST
    Figure KR2025005255_02012026_PF_FP_ABST
Patent Text Reader

Abstract

This electronic device comprises: a memory, which stores instructions and includes one or more storage media; a communication circuit; a display; and at least one processor including a processing circuit, wherein, when executed individually or collectively by the at least one processor, the instructions can instruct the electronic device to: receive, from an external electronic device and through the communication circuit, first media content and information related to a portion of the first media content; detect an event for generating second media content at least partially linked to the first media content; generate, on the basis of the detection, a prompt for maintaining the portion; acquire the second media content by using a generative artificial intelligence model into which the first media content and the prompt have been input; and display, on the display, the second media content as processing of the event.
Need to check novelty before this filing date? Find Prior Art

Description

Electronic device, method, and non-transitory computer-readable storage medium for obtaining media content using a model

[0001] The present disclosure relates to an electronic device, a method, and a non-transitory computer-readable storage medium for obtaining media content using a model.

[0002] Artificial intelligence is a technology for simulating the neural activity of humans (or living things), such as perception and / or inference, and can be implemented by hardware, software, or a combination of these designed to perform computations for simulating neural activity.

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

[0004] An electronic device is described. The electronic device may include at least one processor, the electronic device including a memory storing instructions and including one or more storage media, a communication circuit, a display, and a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive first media content and information related to at least a portion of the first media content from an external electronic device through the communication circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to detect an event for generating second media content at least partially associated with the first media content. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate a prompt for maintaining the portion indicated by the information based on the detection. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain the second media content using the generative artificial intelligence model input with the first media content and the prompt. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display the second media content on the display as a processing of the event.

[0005] A method is described. The method can be performed within an electronic device including a communication circuit and a display. The method can include receiving first media content and information related to at least a portion of the first media content from an external electronic device through the communication circuit. The method can include detecting an event for generating second media content at least partially linked to the first media content. The method can include generating a prompt for maintaining the portion indicated by the information based on the detection. The method can include obtaining the second media content using a generative artificial intelligence model into which the first media content and the prompt are input. The method can include displaying the second media content on the display as a processing for the event.

[0006] A non-transitory computer-readable storage medium is described. The non-transitory computer-readable storage medium may store one or more programs. The one or more programs may include instructions that, when executed by an electronic device including a communication circuit and a display, cause the electronic device to receive first media content and information related to at least a portion of the first media content from an external electronic device through the communication circuit. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to detect an event for generating second media content at least partially associated with the first media content. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate a prompt for maintaining the portion indicated by the information based on the detection. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to obtain the second media content using the first media content and the generative artificial intelligence model input with the prompt. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to display the second media content on the display as a processing of the event.

[0007] FIG. 1 illustrates an example of obtaining second media content from which a portion specified by a user of an external electronic device is excluded from first media content.

[0008] Figure 2 is a simplified block diagram of an electronic device.

[0009] FIG. 3 is a signal flow diagram between an electronic device and an external electronic device for transmitting first media content and information representing a portion of the first media content.

[0010] FIGS. 4A, 4B, and 4C illustrate examples of inputs for transmitting information representing first media content and data selected within the first media content.

[0011] FIG. 5 is a signal flow diagram between an electronic device and an external electronic device for transmitting first media content and a prompt.

[0012] FIG. 6 illustrates an example of an input for generating first media content to transmit the first media content to an electronic device.

[0013] Figures 7a and 7b illustrate examples of generating first media content using a generative artificial intelligence model.

[0014] Figures 8a and 8b illustrate examples of displaying first media content and receiving additional input.

[0015] FIG. 9 is a flowchart illustrating exemplary operations of an electronic device for acquiring second media content.

[0016] Figure 10a illustrates an example of input for generating second media content.

[0017] Figure 10b illustrates an example of a prompt generator.

[0018] Figures 11a and 11b illustrate examples of generating second media content using a generative artificial intelligence model.

[0019] Figures 12a and 12b illustrate examples of displaying second media content.

[0020] Figure 12c is an example of second media content generated based on relationships between users.

[0021] Figure 13 illustrates an example of an operation for acquiring third media content.

[0022] FIG. 14 is a block diagram of an electronic device within a network environment according to various embodiments.

[0023] FIG. 15 illustrates an example of a generative artificial intelligence system according to one embodiment.

[0024] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0025] FIG. 1 illustrates an example of obtaining second media content from which a portion specified by a user of an external electronic device is excluded from first media content.

[0026] Referring to FIG. 1, an electronic device (100) may be described as a device available for providing media content. For example, the electronic device (100) may be one of various forms of mobile devices, such as smartphones (e.g., bar-type smartphones, foldable-type smartphones, or rollable-type smartphones), tablets, wearable devices, cellular phones, laptops, smartwatches, and / or other similar computing devices, having various form factors that include circuits (or circuitry) for providing operations for media content.

[0027] For example, the electronic device (100) may include a communication circuit (e.g., the communication circuit (230) of FIG. 2). For example, the communication circuit may be used to receive media content from an external electronic device (e.g., the external electronic device (301) of FIG. 3). For example, the electronic device (100) may receive first media content (110) from the external electronic device through the communication circuit.

[0028] For example, the electronic device (100) may include a display (e.g., the display (240) of FIG. 2). For example, the display may be used to display media content. For example, the electronic device (100) may display first media content (110) received from the external electronic device through the display.

[0029] For example, state (105) may be described as a state in which first media content (110) is displayed through the display. For example, within state (105), the first media content (110) may include a first portion (115) and a second portion (120).

[0030] For example, while displaying first media content (110), the electronic device (100) may detect an event for generating second media content (145) using the first media content (110).

[0031] For example, based on the detection, the electronic device (100) may transition from state (105) to state (125). The input may include a user's utterance input and / or a user's text input. For example, the input may be provided by an input means of the electronic device (100) (e.g., a keyboard or a mouse), or by an input means of another external electronic device (e.g., a wireless keyboard, a stylus pen, or a headset) connected to the electronic device (100).

[0032] For example, within state (125), the electronic device (100) may display text (135) extracted from the input through the display based on the input. For example, the text (135) may be displayed on a window (130) displayed through the display. For example, the text (135) may be displayed to notify the input.

[0033] For example, the electronic device (100) may generate a prompt based on the input. As a non-limiting example, at least one processor (210) may generate the prompt for summarizing the first media content (110) by having the text (135) extracted from the input include content such as "summarize." However, the present invention is not limited thereto.

[0034] For example, the electronic device (100) may provide at least a portion of the first media content (110) and the prompt to a generative artificial intelligence model (e.g., the generative artificial intelligence model (710) of FIG. 7A). For example, the electronic device (100) may use the first media content (110) and the prompt as input values ​​of the generative artificial intelligence model, and obtain second media content (145) as an output of the generative artificial intelligence model.

[0035] For example, the electronic device (100) may transition from state (125) to state (140) based on acquiring second media content (145). Within state (140), the electronic device (100) may display second media content (145) via the display. For example, the second media content (145) may be described as a summarized content of the first media content (110).

[0036] In one embodiment, the second media content (145) may include the second portion (120) of the first media content (110) and may not include the first portion (115) of the first media content (110). The user of the external electronic device may have an intention to transmit the first media content to notify the user of the electronic device of the first portion (115). The first portion (115) may include information that the user of the external electronic device intends to convey to the user of the electronic device. The first portion (115) of the first media content (110) may include media content related to an "appointment time" that the user of the external electronic device intends to notify the user of the electronic device (100). Since the second media content (145) does not include the first portion (115) of the first media content (110), the user may not be provided with media content related to the "appointment time." If the first portion (115) of the first media content (110) includes a relatively important portion, the user may feel inconvenienced due to the omission of the important portion. Since the user may feel inconvenienced by not receiving media content related to the "appointment time," a method may be required to alleviate the user's inconvenience caused by the second media content (145) that does not include the first portion (115) of the first media content (110).

[0037] To resolve this inconvenience, the electronic device (100) may provide second media content including a first portion (115) and a second portion (120) of the first media content (110). For example, the first portion (115) and the second portion (120) of the first media content (110) may be selected by a user of an external electronic device. To provide the second media content including the first portion (115) and the second portion (120) of the first media content (110), information indicating a portion selected by the user of the external electronic device within the first media content (110) may be used. The information indicating the portion selected by the user may be used to maintain the portion selected by the user by specifying the portion selected by the user within the second media content. The electronic device (100) can use the above information to obtain second media content in which the first part (115) and the second part (120) of the first media content (110) are maintained.

[0038] The electronic device (100) may perform operations exemplified in the description of FIGS. 3 to 13 to provide second media content including a first portion (115) and a second portion (120) of the first media content (110). The electronic device (100) and the external electronic device may include components for performing the operations. The components may be exemplified in the description of FIG. 2.

[0039] Figure 2 is a simplified block diagram of an electronic device.

[0040] Referring to FIG. 2, the electronic device (200) may be one of various forms of mobile devices, such as smartphones having various form factors (e.g., bar-type smartphones, foldable-type smartphones, or rollable-type smartphones), tablets, wearable devices, cellular phones, laptops, smartwatches, and / or other similar computing devices. For example, the electronic device (200) may include the electronic device (100) of FIG. 1 or may correspond to the electronic device (100) of FIG. 1. For example, the electronic device (200) may include at least a portion of the electronic device (1401) of FIG. 14 or may correspond to at least a portion of the electronic device (1401) of FIG. 14. For example, the electronic device (200) may include at least one processor (210), a memory (220), a communication circuit (230), and a display (240).

[0041] At least one processor (210) may include processing circuitry. For example, at least one processor (210) may include a central processing unit (CPU) (e.g., including processing circuitry). For example, at least one processor (210) may include a graphics processing unit (GPU) (e.g., including processing circuitry) and / or a neural processing unit (NPU) (e.g., including processing circuitry). For example, at least one processor (210) may be described as an application processor. For example, it may be configured to control at least one memory (220), a communication circuit (230), and a display (240). At least one processor (210) may be configured to individually or collectively execute instructions stored in the memory (220) to cause the electronic device (200) to perform at least some of the operations illustrated in the description of FIG. 1. At least one processor (210) may be configured to execute instructions stored in the memory (220) to cause the electronic device (200) to perform at least some of the operations illustrated in the descriptions of FIGS. 3 through 13.

[0042] The memory (220) may include one or more storage media. For example, the memory (220) may store various data used by at least one component of the electronic device (200) (e.g., at least one processor (210), a communication circuit (230), and / or a display (240)). For example, the data may include input data or output data for software and commands related thereto. The memory (220) may include volatile memory or non-volatile memory.

[0043] The communication circuit (230) may support legacy Bluetooth and / or Bluetooth low energy (BLE). The communication circuit (230) may support wireless communication such as cellular communication. The communication circuit (230) may include at least one of a modem, an antenna, and an optical / electronic (O / E) converter. The communication circuit (230) may support transmission and / or reception of electrical signals based on various types of protocols such as Ethernet, a local area network (LAN), a wide area network (WAN), wireless fidelity (WiFi), Bluetooth, Bluetooth low energy (BLE), zigbee, long term evolution (LTE), or 5G new radio (NR). For example, the communication circuit (230) may be used for communication with an external electronic device (e.g., the external electronic device (301) of FIG. 3). For example, the communication circuit (230) may be configured to receive media content from the external electronic device. For example, the communication circuit (230) may be configured to receive information from the external electronic device.

[0044] The display (240) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the strength of the force generated by the touch. For example, the display (240) may be configured to display media content. For example, the display (240) may be configured to display a visual notification related to the media content. For example, the display (240) may be configured to receive an input for generating media content.

[0045] An external electronic device (e.g., an external electronic device (301) of FIG. 3) may be one of various forms of mobile devices, such as smartphones having various form factors (e.g., a bar-type smartphone, a foldable-type smartphone, or a rollable-type smartphone), tablets, wearable devices, cellular phones, laptops, smartwatches, and / or other similar computing devices. The external electronic device may include at least a portion of the electronic device (1404) of FIG. 14 or may correspond to at least a portion of the electronic device (1404) of FIG. 14. The external electronic device may include components of the electronic device (200) (e.g., at least one processor (210), a memory (220), a communication circuit (230), and a display (240)).

[0046] The electronic device (200) illustrated in the description of FIG. 2 can execute at least some of the operations illustrated in the description of FIGS. 3 to 13. The operations illustrated in the description of FIGS. 3 to 13 can be caused by (or within) the electronic device (200) under the control of at least one processor (210).

[0047] FIG. 3 is a signal flow diagram between an electronic device and an external electronic device for transmitting first media content and information representing a portion of the first media content.

[0048] Referring to FIG. 3, in operation 300, at least one processor of an external electronic device (301) may receive an input for transmitting information representing a first media content (e.g., the first media content (405) of FIG. 4A) and data selected within the first media content (e.g., a portion (410) of FIG. 4A) to the electronic device (200). For example, the information representing data selected by a user of the external electronic device (301) within the first media content may include information representing a portion selected by the user of the external electronic device (301) within the first media content. For example, the selected data may be selected by the user of the external electronic device (301), selected by the external electronic device (301), or selected by a generative artificial intelligence model of the external electronic device (301). For example, a portion of the first media content selected (or specified) by a user of the external electronic device (301) may include a portion of the first media content that cannot be modified and / or a portion of the first media content to be maintained. At least one processor of the external electronic device (301) may display the first media content via a display of the external electronic device (301). For example, the at least one processor of the external electronic device (301) may receive an input while the first media content is not displayed via the display of the external electronic device (301), or may receive an input while the first media content is displayed via the display of the external electronic device (301). An input received while the first media content is displayed is exemplified in the descriptions of FIGS. 4A, 4B, and 4C.

[0049] In operation 310, at least one processor of the external electronic device (301) may transmit, based on the input, information representing the first media content (405) and a portion selected by the user of the external electronic device (301) within the first media content (405) to the electronic device (200) via the communication circuit of the external electronic device (301) (e.g., the portion (410) of FIG. 4A , the other portion (465) of FIG. 4B , or the portion (410) and the other portion (496) of FIG. 4C ). For example, the electronic device (200) may receive, from the external electronic device (301) via the communication circuit (230), the first media content (405) and information representing the portion selected by the user of the external electronic device (301) within the first media content (405).

[0050] Information representing the portion of the first media content (405) may include information highlighting the portion within the first media content (405), text information representing the portion within the first media content (405), and / or visual information surrounding the portion within the first media content (405).

[0051] At least one processor of the external electronic device (301) can generate first media content (405) for transmitting the first media content (405) to the electronic device (200). The first media content (405) generated for transmitting to the electronic device (200) is exemplified within the description of FIG. 5.

[0052] FIGS. 4A, 4B, and 4C illustrate examples of inputs for transmitting information representing first media content and data selected within the first media content.

[0053] Referring to FIG. 4A, a state (400) may be described as a state in which a first media content (405) is displayed through a display of an external electronic device (301). For example, within the state (400), at least one processor of the external electronic device (301) may display an executable object (415) representing a function of sharing the first media content (405) with the electronic device (200).

[0054] For example, the first media content (405) may include data (410) selected within the first media content (405). For example, the data selected by the user of the external electronic device (301) may be selected by the user of the external electronic device (301), or may be selected by the external electronic device (301), or may be selected by the generative artificial intelligence model of the external electronic device (301) (or the generative artificial intelligence of the electronic device (200)). For example, a portion selected by the user of the external electronic device (301) within the first media content (405) may be described as a portion that cannot be changed within the first media content (405). For example, portions of the first media content (405) other than a portion selected by a user of the external electronic device (301) may be described as portions that can be changed in the first media content (405). At least one processor (210) may use the generative artificial intelligence of the electronic device (200) to perform content analysis of the first media content (405) to identify data selected in the first media content (405). For example, at least one processor of the external electronic device (301) may visually emphasize a portion (410) of the first media content (405) to highlight to the user that the portion (410) of the first media content (405) is the selected data. For example, at least a portion of the data (410) of the first media content (405) may be specified through text. For example, a portion (410) of the first media content (405) may be selected based on a line surrounding at least a portion of the data (410) of the first media content (405).

[0055] At least one processor of the external electronic device (301) can receive an input (420) for an executable object (415) while the first media content (405) is displayed. The input (420) can include a touch input that taps the executable object (415). The input (420) can include a touch input having a contact point on the executable object (415). The at least one processor of the external electronic device (301) can identify the input (420) through a display (e.g., a touchscreen) of the external electronic device (301).

[0056] As a non-limiting example, at least one processor of an external electronic device (301) may perform operation 310 of FIG. 3 based on input (420), but is not limited thereto.

[0057] Based on the input (420), the external electronic device (301) can transition from state (400) to state (425). Within state (425), at least one processor of the external electronic device (301) can display a window (430) on the display of the external electronic device (301) to inquire whether to transmit, based on the input (420), information representing the first media content (405) and data (410) selected by a user of the external electronic device (200) within the first media content (405) to the electronic device (200). The window (430) can include executable objects each corresponding to functions provided in connection with a portion (410) of the first media content (405).

[0058] According to one embodiment, at least one processor of the external electronic device (301) may receive an input (440) selecting an executable object (435) indicating that the executable object retains a portion (410) of the first media content (405) among the executable objects. The input (440) may include a touch input tapping the executable object (435). The input (440) may include a touch input having a contact point on the executable object (435). The at least one processor of the external electronic device (301) may identify the input (440) through a display (e.g., a touchscreen) of the external electronic device (301).

[0059] At least one processor of the external electronic device (301) can perform operation 310 of FIG. 3 based on input (440).

[0060] Referring to FIG. 4B, state (445) can be described as a state in which a window (430) is displayed based on an input (420). At least one processor of the external electronic device (301) can display the window (430) through the display of the external electronic device (301) based on the input (420). The window (430) can correspond to the window (430) of FIG. 4A.

[0061] According to one embodiment, at least one processor of the external electronic device (301) may receive an input (455) selecting an executable object (450) indicating a change to a portion (410) of the first media content (405) among the executable objects. The input (455) may include a touch input tapping the executable object (450). The input (455) may include a touch input having a contact point on the executable object (450). The at least one processor of the external electronic device (301) may identify the input (455) through a display (e.g., a touchscreen) of the external electronic device (301).

[0062] In one embodiment, based on the input (455), the external electronic device (301) can transition from state (445) to state (460). In state (460), guidance (461) is displayed, and at least one processor of the external electronic device (301) can display guidance (461) through a display of the external electronic device (301) to notify the user to re-select data within the first media content (405) based on the input (455).

[0063] According to one embodiment, at least one processor of the external electronic device (301) can receive an input (470) for selecting other data (465) of the first media content (405) while the guidance (461) is displayed. The input (470) can include an input for highlighting another portion (465) of the first media content (405). The input (470) can include an input for dragging to indicate a line surrounding the other portion (465) of the first media content (405). Based on the input (470), the at least one processor of the external electronic device (301) can replace the portion (410) of the first media content (405) with the other portion (465) of the first media content (405). At least one processor of the external electronic device (301) can perform operation 310 of FIG. 3 based on input (470).

[0064] Referring to FIG. 4c, state (400) may correspond to state (400) of FIG. 4a. For example, within state (400), at least one processor of the external electronic device (301) may receive input (420) for an executable object (415).

[0065] In one embodiment, based on the input (420), the external electronic device (301) can transition from state (400) to state (475). For example, within state (475), at least one processor of the external electronic device (301) can display a window (480) requesting input for modifying a portion (410) of the first media content (405) based on the input (420). The window (480) can include an input field (or input portion) (485). The at least one processor of the external electronic device (301) can receive an input (490) for modifying the portion (410) of the first media content (405) via the input field (485). For example, the input (490) can include a user's utterance input and / or a user's text input. The input (490) may be provided by an input means (e.g., a keyboard or mouse) of an external electronic device (301), or by an input means of another external electronic device (e.g., a wireless keyboard, a stylus pen, or a headset) connected to the external electronic device (301).

[0066] Based on the input (490), the external electronic device (301) can transition from state (475) to state (495). Within state (495), a portion (410) of the first media content (405) is changed, and at least one processor of the external electronic device (301) can select the portion (410) of the first media content (405) and another portion (496) of the first media content (405) based on the input (490). The at least one processor of the external electronic device (301) can change the portion selected by the user of the external electronic device (301) within the first media content (405) by adding other data (496) of the first media content (405) to the portion (410) of the first media content (405). At least one processor of the external electronic device (301) can replace a portion (410) of the first media content (405) with a portion (410) of the first media content (405) and another portion (496) of the first media content (405).

[0067] As a non-limiting example, the input (490) may include an input for adding a map image to a portion (410) of the first media content (405). For example, at least one processor of the external electronic device (301) may select, based on the input (490) for adding a map image to a portion (410) of the first media content (405), another portion (496) corresponding to the map image within the first media content (405) and the portion (410) of the first media content (405).

[0068] At least one processor of the external electronic device (301) may modify a portion (410) of the first media content (405) by excluding another portion of the first media content (405) from the portion (410) of the first media content (405), or by replacing another portion of the first media content (405) with another portion of the first media content (405), but is not limited thereto.

[0069] At least one processor of the external electronic device (301) can perform operation 310 of FIG. 3 based on input (490).

[0070] FIG. 5 is a signal flow diagram between an electronic device and an external electronic device for transmitting first media content and a prompt.

[0071] Referring to FIG. 5, at operation 500, at least one processor of the external electronic device (301) may receive an input for generating first media content (405) to transmit the first media content (405). The input is exemplified within the description of FIG. 6.

[0072] In operation 510, at least one processor of the external electronic device (301) may generate a prompt (e.g., prompt (700) of FIG. 7A) for including data selected by a user of the external electronic device (301) within the first media content (405) based on the input. For example, the data selected by the user within the first media content (405) may include at least a portion of the first media content (405) or the entire first media content (405). In another embodiment, at least one processor of the external electronic device (301) may generate a prompt for changing a style of the first media content (405) based on the input. For example, the style of the first media content (405) may include a writing style and / or a literary style.

[0073] The external electronic device (301) may include a prompt generator that supports the function of processing data through an algorithm. The prompt generator may process text extracted from the input. The prompt generator may include the prompt design component (1521) of FIG. 15.

[0074] In operation 520, at least one processor of the external electronic device (301) may obtain first media content (405) using the generative artificial intelligence model for which the prompt has been input. For example, the prompt may request generation of first media content (405) including a portion of the first media content (405) related to the prompt. For example, at least one processor of the external electronic device (301) may, in response to the prompt, obtain first media content (405) including a portion related to the prompt.

[0075] In another embodiment, at least one processor of the external electronic device (301) may further provide (or input) information related to the prompt and stored within the external electronic device (301) to the generative artificial intelligence model. The at least one processor of the external electronic device (301) may further obtain first media content (405) generated using the information from the generative artificial intelligence model. Obtaining the first media content (405) using the generative artificial intelligence model is exemplified in the descriptions of FIGS. 7A and 7B .

[0076] In operation 530, at least one processor of the external electronic device (301) may transmit the first media content (405) and the prompt (700) to the electronic device (200) via the communication circuit. For example, the at least one processor of the external electronic device (301) may transmit only a portion of the first media content (405) and the prompt (700). The electronic device (200) may receive the first media content (405) and the prompt (700) from the external electronic device (301) via the communication circuit (230). Information representing a portion (e.g., a portion (730) of FIG. 7B) selected by a user of the external electronic device (301) within the first media content (405) may include the prompt (700).

[0077] As a non-limiting example, at least one processor of the external electronic device (301) may receive an input for transmitting the first media content (405) to the electronic device (200) while displaying the first media content (405) through a display of the external electronic device (301). Based on the input for transmitting the first media content (405) to the electronic device (200), the at least one processor of the external electronic device (301) may transmit the first media content (405) and the prompt (700) to the electronic device (200). Transmitting the first media content (405) and the prompt (700) to the electronic device (200) based on the input is exemplified within the descriptions of FIGS. 8A and 8B .

[0078] At operation 540, at least one processor (210) may use the first media content (405) (or the second media content (850)) and the prompt (700) (or the other prompt) to identify a portion (e.g., a portion (730) of FIG. 7B ) of the first media content (405) (or the second media content (850)) that is associated with the prompt (700) (or the other prompt). For example, a portion of the first media content (405) (or the second media content (850)) may be requested by the prompt (700) to be included within the first media content (405) (or the second media content (850)).

[0079] For example, at least one processor (210) may identify a portion (730) of the first media content (405-1) corresponding to a portion (720) having text such as “including appointment time and appointment place” included in the prompt (700-1) of FIG. 7B . For example, the portion (730) of the first media content (405-1) of FIG. 7B may correspond to the “appointment time” and “appointment place” portion (720) of the prompt (700-1) by including media content for “appointment time” and “appointment place” within the first media content (405-1). For example, at least one processor (210) may identify a portion (730) indicating “appointment time” and “appointment location” within the first media content (405-1) as a portion selected by a user of the external electronic device (301) within the first media content (405-1), based on the prompt (700-1) of FIG. 7b.

[0080] For example, at least one processor (210) may receive an input for generating second media content (e.g., second media content (1105) of FIG. 11A) while displaying a visual notification related to first media content. Operations of the electronic device (200) for obtaining the second media content are exemplified within the description of FIG. 9.

[0081] FIG. 6 illustrates an example of an input for generating first media content to transmit the first media content to an electronic device.

[0082] Referring to FIG. 6, at least one processor of an external electronic device (301) may receive an input for generating a first media content (405) to transmit the first media content (405). The input may include a user's utterance input and / or a user's text input. The input may be provided by an input means (e.g., a keyboard or a mouse) of the external electronic device (301), or may be provided by an input means of another external electronic device (e.g., a wireless keyboard, a stylus pen, or a headset) connected to the external electronic device (301).

[0083] At least one processor of the external electronic device (301) may, based on the input, display text extracted from the input through a display (e.g., a window (600), a pop-up window, a dialog box) of the external electronic device (301) to inform the user of the input content. For example, the text may include text related to the first media content (405) to be generated (e.g., text such as “I have an appointment tonight”), text indicating that the first media content (405) is to be delivered (e.g., text such as “Share this”), and / or text related to a target to which the first media content (405) is to be delivered (e.g., text such as “To Team Ocean members”). For example, by providing the text to the user, the user may recognize whether the input corresponds to an input intended by the user. The at least one processor of the external electronic device (301) may perform operation 510 of FIG. 5 based on the input.

[0084] Figures 7a and 7b illustrate examples of generating first media content using a generative artificial intelligence model.

[0085] Referring to FIG. 7A, the external electronic device (205) may include a generative artificial intelligence model (710). The generative artificial intelligence model (710) may be trained to generate media content. The generative artificial intelligence model (710) may include the generative AI model (1530) of FIG. 15.

[0086] The generative artificial intelligence model (710) may include a large language model (LLM), a natural language processing model (NLP model), and / or a large vision model (LVM). For example, the generative artificial intelligence model (710) may include an encoder-decoder structure. For example, the encoder may process input data to output compressed information (e.g., an attention mechanism), and the decoder may process the compressed information to output output data in token units. For example, the encoder and decoder may include independent attention networks, and may include a cross-attention network connecting the encoder and decoder.

[0087] At least one processor of the external electronic device (301) can input (or provide) a prompt (700) to the generative artificial intelligence model (710). For example, the prompt (700) can include the prompt generated in operation 510 of FIG. 5. At least one processor of the external electronic device (301) can execute the generative artificial intelligence model (710) using the prompt (700).

[0088] At least one processor of the external electronic device (301) can obtain first media content (405) using a generative artificial intelligence model (710) into which a prompt (700) is input (or provided). The first media content (405) can be derived from the prompt (700). The first media content (405) can include a portion selected by a user of the external electronic device (301) within the first media content (405).

[0089] As a non-limiting example, the generative artificial intelligence model (710) may be included in a server. At least one processor of an external electronic device (301) may transmit a prompt (700) to the server via a communication circuit. The server may input the prompt (700) to the generative artificial intelligence model (710) by receiving the prompt (700) from the external electronic device (301). As a non-limiting example, the server may obtain first media content (405) using the generative artificial intelligence model (710) into which the prompt (700) has been input. The server may transmit the first media content (405) to the external electronic device (301). The external electronic device (301) may obtain the first media content (405) by receiving the first media content (405) from the server via a communication circuit. However, the present invention is not limited thereto.

[0090] Referring to FIG. 7B, the prompt (700-1) may include a portion (720) having text such as "including the appointment time and appointment location." For example, at least one processor of the external electronic device (301) may obtain the first media content (405-1) using the generative artificial intelligence model (710) into which the prompt (700-1) is input.

[0091] The first media content (405-1) may include a portion (730) related to a prompt (700-1) of an external electronic device (301) within the first media content (405-1). The portion (730) of the first media content (405-1) may be selected based on the portion (720) of the prompt (700-1). For example, the portion (730) of the first media content (405-1) corresponding to “appointment time” and “appointment location” within the portion (720) of the prompt (700-1) may be selected. For example, a portion (730) of the first media content (405-1) may include media content for “appointment time” and “appointment place” within the first media content (405-1) that corresponds to “appointment time” and “appointment place” within the portion (720) of the prompt (700-1).

[0092] At least one processor of the external electronic device (301) can perform operation 530 of FIG. 5 based on acquiring the first media content (405, 405-1).

[0093] Figures 8a and 8b illustrate examples of displaying first media content and receiving additional input.

[0094] Referring to FIG. 8A, within a state (800), at least one processor of the external electronic device (301) may display the first media content (405) through a display of the external electronic device (301) based on acquiring the first media content (405). While the first media content (405) is being displayed, the at least one processor of the external electronic device (301) may display a window (805) through the display of the external electronic device (301) for inquiring whether to transmit the first media content (405).

[0095] A window (805) may be displayed together with the first media content (405). The window (805) may include executable objects corresponding to whether to transmit the first media content (405). At least one processor of the external electronic device (301) may receive an input for an executable object indicating to refrain from transmitting the first media content (405) among the executable objects. Based on the input for the executable object indicating to refrain from transmitting the first media content (405), the at least one processor of the external electronic device (301) may refrain from transmitting (or stop, omit, or not perform transmission) the first media content (405) and the prompt (700) to the electronic device (200).

[0096] At least one processor of the external electronic device (301) can receive an input (815) for an executable object (810) indicating that the executable object transmits the first media content (405) among the executable objects. The input (815) can include a touch input that taps the executable object (810). The input (815) can include a touch input having a contact point on the executable object (810). For example, the at least one processor of the external electronic device (301) can identify the input (815) through a display (e.g., a touchscreen) of the external electronic device (301).

[0097] In another embodiment, at least one processor of the external electronic device (301) may receive a speech input indicating to transmit the first media content (405) without displaying the window (805) while the first media content (405) is being displayed. The speech input may correspond to the input (815).

[0098] At least one processor of the external electronic device (301) can transmit first media content (405) and a prompt (700) to the electronic device (200) via the communication circuit based on the input (815).

[0099] Referring to FIG. 8B, a state (820) can be described as a state in which a window (825) for requesting a change in a prompt (700) is displayed. Within the state (820), at least one processor of the external electronic device (301) can display the first media content (405) through the display of the external electronic device (301) based on obtaining the first media content (405). While the first media content (405) is being displayed, the at least one processor of the external electronic device (301) can display a window (825) for requesting a change in a prompt (700) through the display of the external electronic device (301). The window (825) can be displayed overlapping the first media content (405). The window (825) can include an input field (or input portion) (835).

[0100] According to one embodiment, at least one processor of the external electronic device (301) can receive an input (840) for changing the prompt (700) via an input field (835). The input (840) can include a user's utterance input and / or a user's text input. For example, the input (840) can be provided by an input means (e.g., a keyboard or a mouse) of the external electronic device (301), or by an input means of another external electronic device (e.g., a wireless keyboard, a stylus pen, or a headset) connected to the external electronic device (301). According to another embodiment, at least one processor of the external electronic device (301) can receive a user's utterance input without displaying the input field (835).

[0101] According to one embodiment, at least one processor of the external electronic device (301) may generate a prompt different from the prompt (700) based on the input (840). The different prompt may be generated based on text extracted from the input (840).

[0102] According to one embodiment, at least one processor of the external electronic device (301) can obtain second media content (850) different from the first media content (405) using the generative artificial intelligence model (710) into which the other prompt is input. The second media content (850) can include a portion (855) that has been modified from (or added to) the first media content (405).

[0103] In one embodiment, based on the input (840), the external electronic device (301) can transition from state (820) to state (845). State (845) can be described as a state in which second media content (405) is displayed. For example, within state (845), at least one processor of the external electronic device (301) can display the second media content (405) through the display of the external electronic device (301) based on the input (840).

[0104] In one embodiment, at least one processor of the external electronic device (301) may select a portion within the second media content (850) based on another prompt. The at least one processor of the external electronic device (301) may transmit the second media content (850) and the other prompt to the electronic device (200) via the communication circuitry based on the input (840). The electronic device (200) may receive the second media content (850) and the other prompt from the external electronic device (301) via the communication circuitry (230).

[0105] FIG. 9 is a flowchart illustrating exemplary operations of an electronic device for acquiring second media content.

[0106] Referring to FIG. 9, at operation 910, at least one processor (210) may detect an event for generating second media content (e.g., second media content (1105) of FIG. 11A). For example, the second media content may be at least partially linked with the first media content (405). The event for generating the second media content may include receiving an input for generating the second media content. For example, the at least one processor (210) may predetermine, based on receiving the first media content (405), to generate the second media content using the first media content (405). The event for generating the second media content may include receiving the first media content (405) within a predetermined state for generating the second media content. The input for generating the above second media content is exemplified within the description of FIG. 10a.

[0107] In operation 920, at least one processor (210) may generate a prompt (e.g., prompt (1100) of FIG. 11A) based on detection of an event for generating the second media content. The at least one processor (210) may generate the prompt using the prompt generator. The prompt may include text for maintaining a portion of the first media content (405) based on information representing the portion of the first media content (405) (e.g., portion (410) of FIG. 4A or portion (730) of FIG. 7B).

[0108] In operation 930, at least one processor (210) may obtain second media content (e.g., second media content (1105) of FIG. 11a) using the first media content (405) and the generative artificial intelligence model (e.g., the generative artificial intelligence model (710) of FIG. 7a) into which the prompt has been input. Obtaining the second media content using the generative artificial intelligence model is exemplified within the descriptions of FIGS. 11a and 11b.

[0109] In another embodiment, at least one processor (210) may input (or provide) to the generative artificial intelligence model a first media content (405) and a prompt received from an external electronic device (301) (e.g., prompt (700) of FIG. 7A). The at least one processor (210) may obtain from the generative artificial intelligence model a second media content comprising a portion of the first media content (405) related to the prompt received from the external electronic device (301).

[0110] At operation 940, at least one processor (210) may display second media content (1105) on the display (240). The at least one processor (210) may display the second media content (1105) as a result of processing the event for generating the second media content (1105). Displaying the second media content (1105) is exemplified in the descriptions of FIGS. 12A and 12B.

[0111] Figure 10a illustrates an example of input for generating second media content.

[0112] Referring to FIG. 10A, within state (1000), at least one processor (210) may display a visual notification related to first media content (405) via a display (240). Displaying the visual notification related to first media content (405) may include displaying the first media content (405).

[0113] For example, at least one processor (210) may display, via the display (240), information representing a portion (410) specified by a user of the external electronic device (205) within the first media content (405). The information representing the portion (410) of the first media content (405) may include information highlighting the portion (410) of the first media content (405), text information representing the portion (410) of the first media content (405), and / or visual information surrounding the portion (410) of the first media content (405).

[0114] At least one processor (210) may receive an input for generating a second media content (e.g., the second media content (1105) of FIG. 11A) while displaying a visual notification related to the first media content (405). The second media content may be at least partially linked with the first media content (405). For example, the input may include a user's utterance input and / or a user's text input. The input may be provided by an input means of the electronic device (200) (e.g., a keyboard or a mouse), or by an input means of another external electronic device (e.g., a wireless keyboard, a stylus pen, or a headset) connected to the electronic device (200).

[0115] Based on the input, the electronic device (200) can transition from state (1000) to state (1005). Within state (1005), at least one processor (210) can display text (1015) extracted from the input through the display (240) based on the input. The text (1015) can be displayed on the window (1010) and can include content regarding the input. For example, the text (1015) can include text related to the second media content to be generated (e.g., text such as “summary”). For example, the at least one processor (210) can display the text (1015) to notify the user of the input. By the at least one processor (210) providing the text (1015) to the user, the user can recognize whether the input corresponds to an input intended by the user. At least one processor (210) may perform operation 920 of FIG. 9 based on the input.

[0116] Figure 10b illustrates an example of a prompt generator.

[0117] Referring to FIG. 10b, the electronic device (200) may include a prompt generator (1020). The prompt generator (1020) may correspond to the prompt design component (1521) of FIG. 15. At least one processor (210) may use the prompt generator (1020) to generate a prompt.

[0118] The prompt generator (1020) may include an artificial intelligence module (1030). The artificial intelligence module (1030) may generate data for changing or modifying a portion of the first media content based on information about the type of the electronic device (200). For example, when the size of the display (240) of the electronic device (200) is relatively small, the artificial intelligence module (1030) may generate data for changing the first media content while maintaining a portion of the first media content.

[0119] The prompt generator (1020) can, at operation 1040, identify a portion within the first media content based on data for changing or modifying the portion of the first media content, based on information representing the portion of the first media content received from the external electronic device (301) and information about the type of the electronic device (200).

[0120] The prompt generator (1020) may generate a prompt based on identifying a portion within the first media content at operation 1060. The prompt generator (1020) may further generate the prompt based on an event (1045) for generating the second media content, user preference information (1050) stored within the memory (220), and / or user relationship information (1055). The prompt generator (1020) may provide the prompt generated at operation 1060 to the generative artificial intelligence model. Providing the prompt to the generative artificial intelligence model is exemplified in the descriptions of FIGS. 11A and 11B .

[0121] Figures 11a and 11b illustrate examples of generating second media content using a generative artificial intelligence model.

[0122] Referring to FIG. 11A, at least one processor (210) may generate a prompt (1100) based on an event for generating second media content (1105). The at least one processor (210) may generate the prompt (1100) using the prompt generator. The at least one processor (210) may use information representing a portion of the first media content (405) (the portion (410) of FIG. 10A) to generate a prompt (1100) for maintaining the portion (410) represented by the information. For example, the portion within the first media content (405) may be selected by a user of the external electronic device (301), selected by the external electronic device (301), or selected by a generative artificial intelligence model of the external electronic device (301). A portion within the first media content may include a portion within the first media content that cannot be modified and / or a portion within the first media content that is to be maintained. The prompt (1100) may include text for maintaining a portion (410) indicated by the information within the first media content (405).

[0123] At least one processor (210) may generate a prompt (1100) corresponding to an event for generating second media content (1105) using the prompt generator (or based on input to the prompt generator). The event for generating the second media content may include receiving an input for generating the second media content. For example, the at least one processor (210) may predetermine, based on receiving the first media content (405), to generate the second media content using the first media content (405). The event for generating the second media content may include receiving the first media content (405) within a predetermined state for generating the second media content. The input for generating the second media content (1105) may include an input for summarizing the first media content (405), an input for translating the first media content (405), and / or an input for requesting additional description of the first media content (405). The prompt (1100) may further include text for summarizing the first media content (405), text for translating the first media content (405), and / or text for requesting additional description of the first media content (405).

[0124] At least one processor (210) can identify information about a usage pattern of the media content, information about a relationship between a user of the external electronic device (301) and a user of the electronic device (200), and / or information about a size of the display (240) based on an event for generating the second media content (1105). At least one processor (210) can generate a prompt (1100) further based on the information about the usage pattern of the media content, information about a relationship between a user of the external electronic device (301) and a user of the electronic device (200), and / or information about a size of the display (240). The prompt (1100) may further include text for requesting additional media content according to a usage pattern of the media content, text for requesting a style of writing according to a relationship between a user of the external electronic device (301) and a user of the electronic device (200), and / or text for requesting media content having a size corresponding to the size of the display (240).

[0125] At least one processor (210) can input (or provide) first media content (405) and a prompt (1100) to a generative artificial intelligence model (710). At least one processor (210) can execute the generative artificial intelligence model (710) by inputting (or providing) the first media content (405) and the prompt (1100) to the generative artificial intelligence model (710). At least one processor (210) can obtain second media content (1105) using the generative artificial intelligence model (710) to which the first media content (405) and the prompt (1100) are inputted (or provided). A portion (410) of the first media content (405) represented by the information can be maintained within the second media content (1105).

[0126] For example, if the prompt (1100) includes text to summarize the first media content (405), at least one processor (210) can summarize the first media content (405) and obtain second media content (1105) that retains a portion (410) of the first media content (405).

[0127] For example, if the prompt (1100) includes text for translating the first media content (405), at least one processor (210) can translate the first media content (405) and obtain second media content (1105) in which a portion (410) of the first media content (405) is maintained.

[0128] For example, if the prompt (1100) includes text requesting additional description of the first media content (405), at least one processor (210) can provide the additional description of the first media content (405) and obtain second media content (1105) that retains a portion (410) of the first media content (405).

[0129] For example, if the prompt (1100) includes text for requesting additional media content according to a usage pattern of the media content, at least one processor (210) may provide additional media content according to the usage pattern of the media content and obtain second media content (1105) in which a portion (410) of the first media content (405) is maintained. The additional media content may include a type of media content that is relatively frequently requested by the user while the user uses the media content.

[0130] For example, if the prompt (1100) includes text requesting a style of writing according to a relationship between a user of the external electronic device (301) and a user of the electronic device (200), at least one processor (210) can obtain a second media content (1105) having the style and retaining a portion (410) of the first media content (405).

[0131] For example, if the prompt (1100) includes text for requesting media content corresponding to the size of the display (240), at least one processor (210) can obtain second media content (1105) having a size corresponding to the size of the display (240) and retaining a portion (410) of the first media content (405).

[0132] As a non-limiting example, the generative artificial intelligence model (710) may be included in a server. As a non-limiting example, at least one processor (210) may transmit a prompt (700) to the server via a communication circuit (230). The server may input the prompt (1100) to the generative artificial intelligence model (710) by receiving the prompt (1100) from the electronic device (200). The server may obtain second media content (1105) using the generative artificial intelligence model (710) into which the prompt (1100) has been input. The server may transmit the second media content (1105) to the electronic device (200). As a non-limiting example, the electronic device (200) may obtain the second media content (1105) by receiving the second media content (1105) from the server via the communication circuit (230). But it is not limited to this.

[0133] Referring to FIG. 11B, the first media content (405-1) may include a portion (410-1) within the first media content (405-1). For example, the portion within the first media content (405-1) may be selected by a user of the external electronic device (301), selected by the external electronic device (301), or selected by a generative artificial intelligence model of the external electronic device (301). The portion within the first media content may include a portion within the first media content that cannot be modified and / or a portion within the first media content that is to be maintained. For example, a portion (410-1) of the first media content (405-1) may include media content related to “appointment time” and “appointment place.” For example, a portion (410-1) of the first media content (405-1) may be described as a portion including the purpose (or intention) of transmitting the first media content (405-1) by a user (e.g., a sender) of the external electronic device (301).

[0134] At least one processor (210) may generate a prompt (1100-1) including text such as “including appointment time and appointment place” based on information representing a portion (410-1) of first media content (405-1) including media content related to “appointment time” and “appointment place.”

[0135] At least one processor (210) may detect an event to generate second media content (1105) by summarizing the first media content (405). For example, based on the event, the at least one processor (210) may generate a prompt (1100-1) further including text such as "summarize."

[0136] At least one processor (210) can input (or provide) first media content (405-1) and a prompt (1100-1) to a generative artificial intelligence model (710). For example, at least one processor (210) can obtain second media content (1105-1) using the generative artificial intelligence model (710) to which the first media content (405-1) and the prompt (1100-1) are input (or provided).

[0137] For example, if the prompt (1100-1) includes text such as “summarize,” at least one processor (210) can obtain the second media content (1105-1) by omitting, deleting, or modifying some media content within the first media content (405-1).

[0138] For example, since the prompt (1100-1) includes text such as “including the appointment time and appointment place,” the text “including the appointment time and appointment place” is a portion that includes the purpose (or intention) of transmitting the first media content (405-1) by the user (e.g., the sender) of the external electronic device (301) (or a portion that is specified to be maintained within the first media content (405-1) by the user (e.g., the receiver) of the electronic device (300), so that the media content related to “appointment time” and “appointment place” included within the portion (410-1) of the first media content (405-1) can be maintained within the second media content (1105-1). For example, the second media content (1105-1) can include a portion (1110) corresponding to the portion (410-1) of the first media content (405-1).

[0139] Figures 12a and 12b illustrate examples of displaying second media content.

[0140] Referring to FIG. 12A, a state (1200) may be described as a state in which second media content (1105) is displayed. For example, within the state (1200), at least one processor (210) may display the second media content (1105) through the display (240) as processing for an event for generating the second media content (1105).

[0141] The second media content (1105) may include only a portion (1110) corresponding to a portion selected by the user of the external electronic device (301) within the first media content (405) (e.g., a portion (410) of FIG. 10A). At least one processor (210) may display the second media content (1105) to provide information included within the portion selected by the user of the external electronic device (301) within the first media content (405).

[0142] At least one processor (210) can provide the second media content (1105) without omitting the portion selected by the user of the external electronic device (301) within the first media content (405) by displaying the second media content (1105) including only a portion (1110).

[0143] Referring to FIG. 12B, the electronic device (200) may be described as a smartwatch. The electronic device (200) may include a relatively small-sized display (240). For example, at least one processor (210) may identify the size of the display (240) based on an event that generates second media content (1210).

[0144] At least one processor (210) may generate a prompt (e.g., prompt (1100) of FIG. 11A) for generating second media content (1105) that includes only a portion (1110) based on the size of the display (240). At least one processor (210) may obtain second media content (1210) having a size corresponding to the size of the display (240) by using the first media content (405) and the generative artificial intelligence model (710) into which the prompt is input. Since the display (240) of the electronic device (200) has a relatively small size, the second media content (1210) may have a relatively small size. At least one processor (210) may display the second media content (1210) according to the resolution of the display (240) (or the state of the electronic device (200)). At least one processor (210) can modify the second media content (1210) to display the second media content (1210). Since the display (240) of the electronic device (200) has a relatively small size, the at least one processor (210) can display only relatively essential contents of the first media content (405).

[0145] Within the state (1205), at least one processor (210) can display second media content (1210) via the display (240). For example, the second media content (1210) may include a portion (1215) corresponding to a portion selected by a user of the external electronic device (301) within the first media content (405), even if the second media content (1210) has a relatively small size. For example, since the prompt includes text for maintaining the portion of the first media content (405), the second media content (1210) may include a portion (1215) corresponding to the portion of the first media content (405).

[0146] At least one processor (210) can further display an executable object (1219) together with the second media content (1210). The at least one processor (210) can receive an input (1220) for displaying the first media content (405) using another external electronic device (1230) via the executable object (1219). The input (1220) can include a touch input for the executable object (1219). The photographing input can include a touch input of tapping the executable object. The input (1220) can include a touch input having a contact point on the executable object (1219). The at least one processor (210) can identify the input (1220) via the display (240) (e.g., a touchscreen).

[0147] At least one processor (210) can transmit the first media content (405) to another external electronic device (1230) through the communication circuit (230) based on the input (1220). For example, the other external electronic device (1230) can be described as a smartphone (e.g., a bar-type smartphone, a foldable type smartphone, or a rollable type smartphone), a tablet, a wearable device, a cellular phone, a laptop, and / or other similar computing devices. The electronic device (200) can be wirelessly connected to or interoperate with the other external electronic device (1230). While a connection is established with the other external electronic device (1230), the electronic device (200) can transmit the first media content (405) to the other external electronic device (1230) based on the input (1220). Another external electronic device (1230) can receive first media content (405) from the electronic device (200) while a connection is established with the electronic device (200).

[0148] Within the state (1225), the other external electronic device (1230) may display the first media content (405) through a display (e.g., the display (240) of FIG. 2) based on receiving the first media content (405). The size of the display of the other external electronic device (1230) may be larger than the size of the display (240) of the electronic device (200). Since the size of the display of the other external electronic device (1230) is larger than the size of the display (240), the display of the other external electronic device (1230) may have a wider display area. Since the display of the other external electronic device (1230) has a relatively wide display area, the display of the other external electronic device (1230) may provide the first media content (405) including more media content than the second media content (1210). Another external electronic device (1230) may display information about a portion (410) of the first media content (405) within the first media content (405).

[0149] Figure 12c is an example of second media content generated based on relationships between users.

[0150] Referring to FIG. 12C, at least one processor (210) can receive a first media content (1235) including a first portion (1240) and a second portion (1245) from an external electronic device (301). Based on a relationship between a user of the electronic device (200) and a user of the external electronic device (301), at least one processor (210) can select the first portion (1240) within the first media content (1235) as a portion for maintenance within the first media content (1235). As a non-limiting example, since the user of the electronic device (200) and the user of the external electronic device (301) are not very familiar with each other, the second portion (1245) including the face of the user of the external electronic device (301) may be avoided as a part to be maintained within the first media content (1235), and the first portion (1240) may be selected as a part to be maintained within the first media content (1235). However, the present invention is not limited thereto.

[0151] At least one processor (210) can generate a prompt for maintenance within the first media content (1235) using a prompt generator based on selecting a first portion (1240) within the first media content (1235) as a portion for maintenance within the first media content (1235). At least one processor (210) can obtain second media content (1250) by inputting the prompt and the first media content (1235) into a generative artificial intelligence model. The second media content (1250) can be output from the generative artificial intelligence model.

[0152] The second media content (1250) may be derived from a prompt and may include a first portion (1240) of the first media content (1235) and may not include a second portion (1245) of the first media content (1235). The second media content (1250) may include the first portion (1240) of the first media content (1235), thereby providing the user with information contained within the first portion (1240).

[0153] At least one processor (210) can obtain third media content (e.g., third media content (1320) of FIG. 13) using second media content (1250). Obtaining the third media content is exemplified in the description of FIG. 13.

[0154] Figure 13 illustrates an example of an operation for acquiring third media content.

[0155] Referring to FIG. 13, state (1300) may be described as a state in which second media content (1105) is displayed. For example, within state (1300), at least one processor (210) may receive an input for generating third media content (1320) while the second media content (1105) is displayed. For example, the input for generating the third media content (1320) may correspond to the input for generating the second media content (1105) in operation 910 of FIG. 9.

[0156] The third media content (1320) may be at least partially linked to the second media content (1105). In one embodiment, the third media content (1320) may include at least a portion of the content of the second media content (1105), or may include additional content generated by at least a portion of the content. The input may include a user's utterance input and / or a user's text input. For example, the input may be provided by an input means of the electronic device (200) (e.g., a keyboard or a mouse), or may be provided by an input means of another external electronic device (e.g., a wireless keyboard, a stylus pen, or a headset) connected to the electronic device (200).

[0157] At least one processor (210) may display text (1310) extracted from the input through the display (240) based on the input. For example, the text (1310) may be displayed on a window (1305). The text (1310) may correspond to the input. For example, the text (1310) may include text related to the third media content (1320) to be generated (e.g., text such as "Add a recommended menu"). For example, the at least one processor (210) may display the text (1310) to notify the user of the input. For example, by the at least one processor (210) providing the text (1310) to the user, the user may recognize whether the input corresponds to an input intended by the user.

[0158] At least one processor (210) may generate another prompt based on the input. For example, at least one processor (210) may generate the another prompt using the prompt generator. For example, at least one processor (210) may use information representing a portion selected by a user of the external electronic device (301) within the first media content (405) to generate the another prompt for maintaining the portion indicated by the information. For example, the another prompt may include text for maintaining the portion indicated by the information within the first media content (405).

[0159] At least one processor (210) may generate another prompt corresponding to the input for generating the third media content (1320). For example, the input for generating the third media content (1320) may include an input for requesting additional description of the second media content (1105). For example, the other prompt may further include text such as "Add a recommendation menu" in response to the input for requesting additional description of the second media content (1105).

[0160] At least one processor (210) can input (or provide) the second media content (1105) and the other prompt to a generative artificial intelligence model (e.g., the generative artificial intelligence model (710) of FIG. 7A). For example, the at least one processor (210) can obtain third media content (1320) using the generative artificial intelligence model (710) to which the second media content (1105) and the other prompt have been input (or provided). For example, the third media content (1320) can include a portion (1110) corresponding to a portion (410) of the first media content (405), such that the other prompt includes text for maintaining a portion indicated by the information within the first media content (405). For example, a portion (1110) of the third media content (1320) may correspond to a portion (1110) of the second media content (1105).

[0161] Based on the above input, the electronic device (200) may transition from state (1300) to state (1315). For example, state (1315) may be described as a state in which third media content (1320) is displayed. For example, within state (1315), at least one processor (210) may display third media content (1320) via the display (240). For example, the third media content (1320) may further include a portion (1325) that provides media content related to "recommended menu" by including text such as "Add recommended menu" corresponding to the input, whereby the other prompt may be provided. For example, at least one processor (210) may provide a result for the input by displaying the third media content (1320).

[0162] FIG. 14 is a block diagram of an electronic device within a network environment according to various embodiments.

[0163] Referring to FIG. 14, in a network environment (1400), an electronic device (1401) may communicate with an electronic device (1402) via a first network (1498) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (1404) or a server (1408) via a second network (1499) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (1401) may communicate with the electronic device (1404) via the server (1408). According to one embodiment, the electronic device (1401) may include a processor (1420), a memory (1430), an input module (1450), an audio output module (1455), a display module (1460), an audio module (1470), a sensor module (1476), an interface (1477), a connection terminal (1478), a haptic module (1479), a camera module (1480), a power management module (1488), a battery (1489), a communication module (1490), a subscriber identification module (1496), or an antenna module (1497). In some embodiments, the electronic device (1401) may omit at least one of these components (e.g., the connection terminal (1478)), or may have one or more other components added. In some embodiments, some of these components (e.g., sensor module (1476), camera module (1480), or antenna module (1497)) may be integrated into a single component (e.g., display module (1460)).

[0164] The processor (1420) may, for example, execute software (e.g., a program (1440)) to control at least one other component (e.g., a hardware or software component) of the electronic device (1401) connected to the processor (1420) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (1420) may store commands or data received from other components (e.g., a sensor module (1476) or a communication module (1490)) in a volatile memory (1432), process the commands or data stored in the volatile memory (1432), and store result data in a non-volatile memory (1434). According to one embodiment, the processor (1420) may include a main processor (1421) (e.g., a central processing unit or an application processor) or an auxiliary processor (1423) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (1421). For example, when the electronic device (1401) includes the main processor (1421) and the auxiliary processor (1423), the auxiliary processor (1423) may be configured to use less power than the main processor (1421) or to be specialized for a given function. The auxiliary processor (1423) may be implemented separately from the main processor (1421) or as a part thereof.

[0165] The auxiliary processor (1423) may control at least a portion of functions or states associated with at least one component (e.g., the display module (1460), the sensor module (1476), or the communication module (1490)) of the electronic device (1401), for example, on behalf of the main processor (1421) while the main processor (1421) is in an inactive (e.g., sleep) state, or together with the main processor (1421) while the main processor (1421) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (1423) (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 (1480) or a communication module (1490)). In one embodiment, the auxiliary processor (1423) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (1401) where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (1408)). 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.

[0166] The memory (1430) can store various data used by at least one component (e.g., the processor (1420) or the sensor module (1476)) of the electronic device (1401). The data can include, for example, software (e.g., the program (1440)) and input data or output data for commands related thereto. The memory (1430) can include volatile memory (1432) or non-volatile memory (1434).

[0167] The program (1440) may be stored as software in memory (1430) and may include, for example, an operating system (1442), middleware (1444), or an application (1446).

[0168] The input module (1450) can receive commands or data to be used in a component of the electronic device (1401) (e.g., a processor (1420)) from an external source (e.g., a user) of the electronic device (1401). The input module (1450) 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).

[0169] The audio output module (1455) can output audio signals to the outside of the electronic device (1401). The audio output module (1455) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0170] The display module (1460) can visually provide information to an external party (e.g., a user) of the electronic device (1401). The display module (1460) may include, for example, a display, a holographic device, or a projector, and a control circuit for controlling the device. In one embodiment, the display module (1460) 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.

[0171] The audio module (1470) can convert sound into an electrical signal, or vice versa. According to one embodiment, the audio module (1470) can acquire sound through the input module (1450), output sound through the sound output module (1455), or an external electronic device (e.g., electronic device (1402)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (1401).

[0172] The sensor module (1476) can detect the operating status (e.g., power or temperature) of the electronic device (1401) 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 (1476) 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.

[0173] The interface (1477) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (1401) with an external electronic device (e.g., the electronic device (1402)). In one embodiment, the interface (1477) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0174] The connection terminal (1478) may include a connector through which the electronic device (1401) may be physically connected to an external electronic device (e.g., the electronic device (1402)). In one embodiment, the connection terminal (1478) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0175] The haptic module (1479) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (1479) may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0176] The camera module (1480) can capture still images and videos. In one embodiment, the camera module (1480) may include one or more lenses, image sensors, image signal processors, or flashes.

[0177] The power management module (1488) can manage the power supplied to the electronic device (1401). According to one embodiment, the power management module (1488) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0178] A battery (1489) may power at least one component of the electronic device (1401). In one embodiment, the battery (1489) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0179] The communication module (1490) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (1401) and an external electronic device (e.g., electronic device (1402), electronic device (1404), or server (1408)), and the performance of communication through the established communication channel. The communication module (1490) may operate independently from the processor (1420) (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 (1490) may include a wireless communication module (1492) (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 (1494) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, a corresponding communication module can communicate with an external electronic device (1404) via a first network (1498) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (1499) (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 local area network or a wide area network)). 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 (1492) can verify or authenticate the electronic device (1401) within a communication network such as the first network (1498) or the second network (1499) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (1496).

[0180] The wireless communication module (1492) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimizing terminal power and connecting multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency communications (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (1492) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (1492) may support various technologies for securing performance in high-frequency bands, 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 (1492) may support various requirements specified in the electronic device (1401), an external electronic device (e.g., the electronic device (1404)), or a network system (e.g., the second network (1499)). According to one embodiment, the wireless communication module (1492) may support a peak data rate (e.g., 20 Gbps or more) for eMBB implementation, a loss coverage (e.g., 164 dB or less) for mMTC implementation, 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 implementation.

[0181] The antenna module (1497) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (1497) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (1497) 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 (1498) or the second network (1499), may be selected from the plurality of antennas by, for example, the communication module (1490). A signal or power may be transmitted or received between the communication module (1490) and the external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (1497).

[0182] According to various embodiments, the antenna module (1497) 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.

[0183] 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)).

[0184] According to one embodiment, commands or data may be transmitted or received between the electronic device (1401) and an external electronic device (1404) via a server (1408) connected to a second network (1499). Each of the external electronic devices (1402 or 1404) may be the same or a different type of device as the electronic device (1401). According to one embodiment, all or part of the operations executed in the electronic device (1401) may be executed in one or more of the external electronic devices (1402, 1404, or 1408). For example, when the electronic device (1401) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (1401) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (1401). The electronic device (1401) 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 (1401) may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (1404) may include an Internet of Things (IoT) device. The server (1408) may be an intelligent server utilizing machine learning and / or a neural network.According to one embodiment, an external electronic device (1404) or server (1408) may be included within the second network (1499). The electronic device (1401) may be applied to intelligent services (e.g., smart homes, smart cities, smart cars, or healthcare) based on 5G communication technology and IoT-related technology.

[0185] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0186] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0187] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0188] Various embodiments of the present document may be implemented as software (e.g., a program (1440)) including one or more instructions stored in a storage medium (e.g., an internal memory (1436) or an external memory (1438)) readable by a machine (e.g., an electronic device (1401)). For example, a processor (e.g., a processor (1420)) of the machine (e.g., an electronic device (1401)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0189] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as included in a computer program product. The computer program product may be traded as a commodity between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0190] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0191] FIG. 15 illustrates an example of a generative artificial intelligence system according to one embodiment.

[0192] Referring to FIG. 15, a generative artificial intelligence system (1500) illustrates an example of a system including a generative AI model (1530). For example, the generative artificial intelligence system (1500) may be included in an electronic device (200) or an external electronic device (301). For example, the generative artificial intelligence system (1500) may be included in a server. For example, the generative AI model (1530) may include the generative artificial intelligence model (710) of FIG. 7A or the generative artificial intelligence model (710) of FIG. 11A.

[0193] A user query / response interface (1510) can receive user input. The user input may be in the form of natural language, images, and / or videos. Furthermore, context information may also be transmitted when the user input is transmitted. The context information may include various additional information at the time of user input. For example, the various additional information may include information about the application currently being used by the user or information about the user's location. Furthermore, the user input may be in a mixed form of natural language, images, sounds, and context information. Furthermore, the user input may also be in a non-natural language form, such as selecting a menu. The user query / response interface (1510) can output the results of the generative artificial intelligence system (1500) to the user. The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user. The user query / response interface (1510) can output the results of the generative artificial intelligence system (1500) to the user. The output can be in natural language form, in the form of specific content, or in the form of actions requested by the user.

[0194] The AI ​​framework (1520) can receive user input and coordinate and control each component necessary to perform the user's intention based on the user's query.

[0195] User input received from the user question response interface (1510) can be transmitted to a prompt design component (1521). The prompt design component (1521) can be used to generate a prompt suitable for inputting the user input into an LLM or LMM. The prompt design component (1521) can be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The prompt design component (1521) can access knowledge repositories (1540) containing user preference data, a prompt library, and prompt examples based on the user input to generate a prompt, and transmit the generated prompt to the LLM or LMM.

[0196] The API / plug-in management component (1522) can communicate with external information when there is a request for additional information when passing user input as input to the generative model. The API / plug-in management component (1522) can establish a channel for communicating with the outside of the AI ​​Interface through the API, and can enable access to various data sources through the established channel. In addition, the API / plug-in management component (1522) can request an action through the API when the application / service component (1550) needs to perform an action that performs the user input as a final result rather than an intermediate result. Information obtained from the outside can be used to generate a prompt in the prompt design component (1521) together with the user input, or can be passed as an input to the generative AI model (1530).

[0197] The refiner component (1523) can fine-tune the output from the generative model. For example, the refiner component (1523) can verify that the content generated through the LLM and / or LMM is not irrelevant, biased, or harmful. Furthermore, the refiner component (1523) can determine the degree to which the content matches the user's desired result and, if necessary, perform additional processing. The refiner component (1523) can additionally configure and provide hints to the user to avoid undesirable output.

[0198] A generative AI model (1530) may generally refer to an artificial intelligence neural network that creates new types of data based on user input information. The generative AI model (1530) may include an image-generating model and / or a language-generating model. Representative models for generating images include a generative adversarial network (GAN) and a variational auto encoder (VAE), and examples include a Diffusion-based generative model that uses a VAE and a Transformer structure. A language-generating model is a model trained to output the most statistically appropriate output value based on input values, and representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4.

[0199] For example, a language-generating model can refer to a language model that can perform inference without fine-tuning using methods such as few-shot learning, and can have more than 10 times more parameters (e.g., about 100 billion parameters) than existing general language models. For example, large-scale language models such as GPT-3 (generative pre-trained transformer 3) and GPT-4 (generative pre-trained transformer 4) are excellent few-shot learners that can be controlled through natural text prompts. They can solve NLP (natural language processing) problems by understanding patterns with only a small amount of data through prompts, which is possible with in-context learning. For example, a language-generating model can also be an LMM (large multimodal model) that can recognize various types of data input such as text, images, and speech and generate new data corresponding to them.

[0200] As described above, the electronic device (e.g., the electronic device (200) of FIG. 2) may include a memory (e.g., the memory (220) of FIG. 2) that stores instructions and includes one or more storage media, a communication circuit (e.g., the communication circuit (230) of FIG. 2), a display (e.g., the display (240) of FIG. 2), and at least one processor (e.g., the at least one processor (210) of FIG. 2) that includes a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive, from an external electronic device (e.g., the external electronic device (301) of FIG. 3) through the communication circuit, first media content (e.g., the first media content (405) of FIG. 10A) and information related to at least a portion of the first media content (e.g., the portion (410) of FIG. 10A). The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to detect an event for generating second media content at least partially linked to the first media content. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate, based on the detection, a prompt for maintaining the portion indicated by the information (e.g., prompt (1100) of FIG. 11A). The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain the second media content (e.g., second media content (1105) of FIG. 11A) using a generative artificial intelligence model (e.g., generative artificial intelligence model (710) of FIG. 11A) input with the first media content and the prompt.The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display the second media content on the display in response to the event.

[0201] For example, the information may include another prompt used to obtain the first media content within the external electronic device. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify the portion within the first media content based on the first media content and the other prompt. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to detect the event.

[0202] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify information about a usage pattern of the media content based on the detection. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate the prompt further based on the information about the usage pattern.

[0203] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify information about a relationship between the user of the external electronic device and the user of the electronic device based on the detection. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate the prompt further based on the information about the relationship.

[0204] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify information about the size of the display based on the detection. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate the prompt further based on the information about the size of the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain the second media content, the portion of which is maintained within the display, using the generative artificial intelligence model input with the first media content and the prompt.

[0205] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to detect the event for generating the second media content by summarizing the first media content. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, based on the detection, generate the prompt for maintaining the portion indicated by the information and summarizing the first media content.

[0206] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to detect the event for generating the second media content by performing a translation of the first media content. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate, based on the detection, the prompt for maintaining the portion indicated by the information and performing the translation of the first media content.

[0207] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to detect the event for generating the second media content by providing additional information about the first media content. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, based on the detection, maintain the portion indicated by the information and generate the prompt for requesting the additional description about the first media content.

[0208] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive an input for generating third media content at least partially linked with the second media content while displaying the second media content on the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate, based on the input, another prompt for maintaining the portion maintained within the second media content. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain the third media content using the generative artificial intelligence model given the second media content and the other prompt. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display the third media content on the display as a result of the other input.

[0209] For example, the information may include information highlighting the portion within the first media content, text information indicating the portion within the first media content, and / or visual information surrounding the portion within the first media content.

[0210] As described above, the method can be performed within an electronic device including a communication circuit and a display. The method can include receiving first media content and information related to at least a portion of the first media content from an external electronic device through the communication circuit. The method can include detecting an event for generating second media content at least partially linked to the first media content. The method can include generating a prompt for maintaining the portion indicated by the information based on the detection. The method can include obtaining the second media content using a generative artificial intelligence model into which the first media content and the prompt are input. The method can include displaying the second media content on the display as a processing for the event.

[0211] For example, the information may include another prompt used to obtain the first media content within the external electronic device. The method may include an operation of identifying the portion within the first media content based on the first media content and the other prompt. The method may include an operation of detecting the event.

[0212] For example, the method may include an operation of identifying information about a usage pattern of media content based on the detection. The method may further include an operation of generating the prompt based on the information about the usage pattern.

[0213] For example, the method may include an action of identifying information about a relationship between a user of the external electronic device and a user of the electronic device, based on the detection.

[0214] For example, the method may include an operation of identifying information about the size of the display based on the detection. The method may further include an operation of generating the prompt based on the information about the size of the display. The method may include an operation of obtaining second media content, a portion of which is maintained within the display, having a size corresponding to the size, using the generative artificial intelligence model into which the first media content and the prompt are input.

[0215] For example, the method may include detecting an event for generating the second media content by summarizing the first media content. Based on the detection, the method may include generating a prompt for maintaining the portion indicated by the information and summarizing the first media content.

[0216] For example, the method may include detecting an event for generating the second media content by performing a translation of the first media content. The method may further include generating a prompt for maintaining the portion indicated by the information and performing a translation of the first media content based on the detection.

[0217] For example, the method may include detecting an event for generating the second media content by providing additional information about the first media content. Based on the detection, the method may include maintaining the portion indicated by the information and generating a prompt for requesting the additional description about the first media content.

[0218] For example, the method may include receiving an input for generating third media content that is at least partially linked with the second media content while displaying the second media content on the display. The method may include generating, based on the input, another prompt for maintaining the portion maintained within the second media content. The method may include obtaining the third media content using the generative artificial intelligence model input with the second media content and the other prompt. The method may include displaying the third media content on the display as a result of the other input.

[0219] For example, the information may include information highlighting the portion within the first media content, text information indicating the portion within the first media content, and / or visual information surrounding the portion within the first media content.

[0220] As described above, the non-transitory computer-readable storage medium may store one or more programs. The one or more programs may include instructions that, when executed by an electronic device including a communication circuit and a display, cause the electronic device to receive first media content and information related to at least a portion of the first media content from an external electronic device through the communication circuit. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to detect an event for generating second media content at least partially associated with the first media content. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate a prompt for maintaining the portion indicated by the information based on the input. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to obtain the second media content using the first media content and the generative artificial intelligence model input with the prompt. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to display the second media content on the display as a processing of the event.

[0221] For example, the information may include another prompt used to obtain the first media content within the external electronic device. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to identify the portion within the first media content based on the first media content and the other prompt. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to detect the event.

[0222] For example, the one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to identify information about a usage pattern of the media content based on the detection. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate the prompt further based on the information about the usage pattern.

[0223] For example, the one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to identify information about a relationship between a user of the external electronic device and a user of the electronic device based on the detection. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate the prompt further based on the information about the relationship.

[0224] For example, the one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to identify information about a size of the display based on the detection. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate the prompt further based on the information about the size of the display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to obtain second media content, a portion of which is maintained within the display, having a size corresponding to the size, using the generative artificial intelligence model into which the first media content and the prompt are input.

[0225] For example, the one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to detect the event for generating the second media content by summarizing the first media content. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate the prompt for maintaining the portion indicated by the information and summarizing the first media content based on the detection.

[0226] For example, the one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to detect the event for generating the second media content by performing a translation of the first media content. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate the prompt for maintaining the portion indicated by the information and performing the translation of the first media content based on the detection.

[0227] For example, the one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to detect the event for generating the second media content by providing additional information about the first media content. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to, based on the detection, maintain the portion indicated by the information and generate the prompt for requesting the additional description about the first media content.

[0228] For example, the one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive an input for generating third media content that is at least partially linked with the second media content while displaying the second media content on the display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate, based on the input, another prompt for maintaining the portion maintained within the second media content. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to obtain the third media content using the generative artificial intelligence model given the second media content and the other prompt. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to display the third media content on the display as a result of the other input.

[0229] For example, the information may include information highlighting the portion within the first media content, text information indicating the portion within the first media content, and / or visual information surrounding the portion within the first media content.

[0230] As described above, the electronic device may include at least one processor, including a memory storing instructions and including one or more storage media, a communication circuit, a display, and a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive an input for transmitting first media content and information representing a portion specified by a user within the first media content to an external electronic device. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to transmit the first media content and the information to the external electronic device through the communication circuit as a result of the input, to cause the electronic device to generate, based on the input, a second media content within the external electronic device that is at least partially associated with the first media content and retains the portion represented by the information.

[0231] For example, the electronic device may further include a display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive the input while displaying the first media content on the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, based on the input, display a window comprising executable objects, each of which corresponds to functions provided in connection with the portion represented by the information on the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive another input selecting, from among the executable objects, an executable object indicating that the portion represented by the information is to be retained. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to transmit the first media content and the information to the external electronic device via the communication circuit as a result of the input, thereby causing the external electronic device to generate the second media content within the external electronic device based on the other input.

[0232] For example, the electronic device may further include a display. For example, the input may be a first input. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive the first input while displaying the first media content on the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display a window, based on the first input, comprising executable objects each corresponding to functions provided in connection with the portion represented by the information on the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive a second input selecting, from among the executable objects, an executable object indicating a modification of the portion represented by the information. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display guidance instructing the electronic device to specify a portion within the first media content that is different from the portion based on the second input. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive a third input specifying another portion within the first media content.The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to transmit, as a result of the input, through the communication circuitry to the external electronic device, other information indicative of the first media content and the other portion specified by the user within the first media content, to cause the external electronic device to generate, based on the third input, the second media content at least partially linked to the first media content and the other portion retained.

[0233] For example, the electronic device may further include a display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive the input while displaying the first media content on the display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display an input field on the display based on the input. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive another input specifying another portion within the first media content through the input field. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to transmit, as a result of the input, through the communication circuitry to the external electronic device, other information indicative of the first media content and the other portion specified by the user within the first media content, to cause the external electronic device to generate, based on the other input, the second media content, the second media content being at least partially linked to the first media content and the other portion being maintained.

[0234] For example, the information may include information highlighting the portion within the first media content, text information indicating the portion within the first media content, and / or visual information surrounding the portion within the first media content.

[0235] As described above, the method can be performed within an electronic device including a communication circuit and a display. The method can include receiving an input for transmitting first media content and information representing a portion of the first media content specified by a user to an external electronic device. The method can include transmitting the first media content and the information to the external electronic device through the communication circuit as a result of the input, so as to cause the external electronic device to generate, based on the input, a second media content that is at least partially associated with the first media content and that retains the portion represented by the information.

[0236] For example, the electronic device may further include a display. The method may include, based on the input, displaying a window on the display, the window including executable objects each corresponding to functions provided in relation to the portion indicated by the information. The method may include receiving another input for selecting, from among the executable objects, an executable object indicating that the portion indicated by the information is to be maintained. The method may include, based on the other input, transmitting, to the external electronic device via the communication circuit, the first media content and the information as a result of the input, so as to cause the external electronic device to generate the second media content.

[0237] For example, the electronic device may further include a display. For example, the input may be a first input. The method may include receiving the first input while displaying the first media content on the display. The method may include displaying a window, based on the first input, which includes executable objects, each corresponding to a function provided in relation to the portion indicated by the information on the display. The method may include receiving a second input for selecting an executable object from among the executable objects, the executable object indicating a modification of the portion indicated by the information. The method may include displaying guidance, based on the second input, that instructs to specify a portion different from the portion within the first media content. The method may include receiving a third input for specifying another portion within the first media content. The method may include, based on the third input, transmitting to the external electronic device, through the communication circuit, other information representing the first media content and another portion specified by the user within the first media content, as a result of the input, to cause the external electronic device to generate the second media content, the second media content being at least partially linked to the first media content and the other portion being maintained.

[0238] For example, the electronic device may further include a display. The method may include receiving an input while displaying the first media content on the display. The method may include displaying an input field on the display based on the input. The method may include receiving another input, via the input field, specifying another portion within the first media content. The method may include transmitting, to the external electronic device through the communication circuitry, other information representing the first media content and the other portion specified by the user within the first media content as a result of the input, so as to cause the external electronic device to generate, based on the other input, the second media content, wherein the second media content is at least partially linked to the first media content and the other portion is maintained within the external electronic device.

[0239] For example, the information may include information highlighting the portion within the first media content, text information indicating the portion within the first media content, and / or visual information surrounding the portion within the first media content.

[0240] As described above, the non-transitory computer-readable storage medium may store one or more programs. The one or more programs may include instructions that, when executed by an electronic device including a communication circuit and a display, cause the electronic device to receive an input for transmitting first media content and information representing a portion of the first media content specified by a user to an external electronic device. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to transmit the first media content and the information to the external electronic device through the communication circuit as a result of the input, so as to cause the electronic device to generate, based on the input, second media content in the external electronic device that is at least partially associated with the first media content and that retains the portion represented by the information.

[0241] For example, the electronic device may further include a display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive the input while displaying the first media content on the display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to display, based on the input, a window including executable objects each corresponding to functions provided in connection with the portion represented by the information on the display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive another input selecting, from among the executable objects, an executable object indicating that the portion represented by the information is to be retained. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to transmit the first media content and the information to the external electronic device via the communication circuit as a result of the input, thereby causing the external electronic device to generate the second media content within the external electronic device based on the other input.

[0242] For example, the electronic device may further include a display. For example, the input may be a first input. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive the first input while displaying the first media content on the display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to display a window, based on the first input, the window including executable objects each corresponding to functions provided in connection with the portion represented by the information on the display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive a second input that selects, from among the executable objects, an executable object indicating a change to the portion represented by the information. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to display guidance that instructs the electronic device to specify a portion different from the portion within the first media content based on the second input. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive a third input that specifies another portion within the first media content.The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to transmit, as a result of the input, through the communication circuitry to the external electronic device the first media content and other information representing the other portion specified by the user within the first media content, to cause the external electronic device to generate the second media content, the second media content being at least partially linked to the first media content and the other portion being maintained based on the third input.

[0243] For example, the electronic device may further include a display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive the input while displaying the first media content on the display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to display an input field on the display based on the input. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive another input specifying another portion within the first media content through the input field. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to transmit, as a result of the input, through the communication circuitry to the external electronic device, the first media content and other information representing another portion specified by the user within the first media content, to cause the external electronic device to generate, based on the other input, the second media content, the second media content being at least partially linked to the first media content and having the other portion maintained.

[0244] For example, the information may include information highlighting the portion within the first media content, text information indicating the portion within the first media content, and / or visual information surrounding the portion within the first media content.

[0245] As described above, the electronic device may include at least one processor, which may store instructions and include a memory comprising one or more storage media, a communication circuit, a display, and a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive an input for generating first media content to transmit the first media content to an external electronic device. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate a prompt for inclusion of a portion specified by a user in the first media content to be generated based on the input. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain the first media content including the portion using a generative artificial intelligence model into which the prompt has been input. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to transmit the first media content and the prompt as a result of the input to the external electronic device via the communication circuitry, thereby causing the external electronic device to generate second media content that is at least partially associated with the first media content and retains the portion indicated by the prompt.

[0246] For example, the electronic device may further include a display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, based on obtaining the first media content using the generative artificial intelligence model, display a window through the display for inquiring about whether to transmit the first media content and the first media content to the external electronic device. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to, based on receiving another input indicating to transmit the first media content to the external electronic device through the window, transmit the first media content and the prompt to the external electronic device as a result of the input.

[0247] For example, the electronic device may further include a display. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display a window through the display for requesting a change in the first media content and the prompt based on obtaining the first media content using the generative artificial intelligence model. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to receive another input for changing the prompt through the window. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate another prompt changed by the other input based on the other input. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain third media content including a portion indicated by the other prompt within the third media content using the generative artificial intelligence model in which the other prompt has been input. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to transmit the third media content and the other prompt as a result of the input to the external electronic device via the communication circuitry to cause the external electronic device to generate fourth media content that is at least partially associated with the third media content and retains the portion indicated by the other prompt.

[0248] For example, the generative artificial intelligence model may include a machine learning model, a deep learning model, and / or a generative artificial intelligence model.

[0249] As described above, the method may be performed within an electronic device including a communication circuit and a display. The method may include receiving an input for generating first media content to transmit the first media content to an external electronic device. The method may include generating a prompt for inclusion of a portion specified by a user within the first media content to be generated based on the input. The method may include obtaining the first media content including the portion using a generative artificial intelligence model into which the prompt has been input. The method may include transmitting the first media content and the prompt to the external electronic device as a result of the input, via the communication circuit, to cause generation of a second media content within the external electronic device that is at least partially linked to the first media content and retains the portion indicated by the prompt.

[0250] For example, the electronic device may further include a display. The method may include, based on obtaining the first media content using the generative artificial intelligence model, displaying a window through the display for inquiring about whether to transmit the first media content and the first media content to the external electronic device. The method may include, based on receiving another input indicating to transmit the first media content to the external electronic device through the window, transmitting the first media content and the prompt to the external electronic device as a result of the input through the communication circuit.

[0251] For example, the electronic device may further include a display. The method may include an operation of displaying a window for requesting a change of the first media content and the prompt through the display based on obtaining the first media content using the generative artificial intelligence model. The method may include an operation of receiving another input for changing the prompt through the window. The method may include an operation of generating another prompt changed by the other input based on the other input. The method may include an operation of obtaining a third media content including a portion indicated by the other prompt within the third media content using the generative artificial intelligence model in which the other prompt is input. The method may include an operation of transmitting the third media content and the other prompt to the external electronic device as a result of the input, so as to cause a fourth media content to be generated within the external electronic device that is at least partially linked with the third media content and retains the portion indicated by the other prompt.

[0252] For example, the generative artificial intelligence model may include a machine learning model, a deep learning model, and / or a generative artificial intelligence model.

[0253] As described above, the non-transitory computer-readable storage medium may store one or more programs. The one or more programs may include instructions that, when executed by an electronic device including a communication circuit and a display, cause the electronic device to receive an input to generate first media content for transmitting the first media content to an external electronic device. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate a prompt for inclusion of a portion specified by a user in the first media content to be generated based on the input. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to obtain the first media content including the portion using a generative artificial intelligence model into which the prompt has been input. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to transmit the first media content and the prompt to the external electronic device via the communication circuit as a result of the input, thereby causing the external electronic device to generate second media content that is at least partially associated with the first media content and that retains the portion indicated by the prompt.

[0254] For example, the electronic device may further include a display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to, based on obtaining the first media content using the generative artificial intelligence model, display a window through the display for inquiring about whether to transmit the first media content and the first media content to the external electronic device. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to, based on receiving another input indicating to transmit the first media content to the external electronic device through the window, transmit the first media content and the prompt as a result of the input to the external electronic device through the communication circuit.

[0255] For example, the electronic device may further include a display. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to display a window through the display for requesting a change in the first media content and the prompt based on obtaining the first media content using the generative artificial intelligence model. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to receive another input for changing the prompt through the window. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to generate another prompt changed by the other input based on the other input. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to obtain, using the generative artificial intelligence model in which the other prompt has been input, third media content that includes a portion indicated by the other prompt within the third media content. The one or more programs may include instructions that, when executed by the electronic device, cause the electronic device to transmit, via the communication circuit, the third media content and the other prompt as a result of the input to the external electronic device, to cause a fourth media content to be generated within the external electronic device that is at least partially associated with the third media content and retains the portion indicated by the other prompt.

[0256] For example, the generative artificial intelligence model may include a machine learning model, a deep learning model, and / or a generative artificial intelligence model.

Claims

1. In an electronic device (200), A memory (220) storing instructions and including one or more storage media; Communication circuit (230); display (240); and At least one processor comprising a processing circuit, The above instructions, when individually or collectively executed by the at least one processor, Receive first media content (405) and information related to at least a portion of the first media content (405) from an external electronic device (301) through the communication circuit (230), Detecting an event for generating a second media content (1105) at least partially linked to the first media content (405), Based on the above detection, a prompt (1100) is generated for maintaining the portion (410) indicated by the above information; Obtaining the second media content (1105) using the generative artificial intelligence model (710) into which the first media content (405) and the prompt (1100) are input; and To display the second media content (1105) on the display (240) as processing for the event, causing the above electronic device (200), Electronic device (200).

2. In claim 1, The above information is, Including another prompt (700) used to obtain the first media content (405) within the external electronic device (301), The above instructions, when individually or collectively executed by the at least one processor, Based on the first media content (405) and the other prompt (700), identifying the portion (410) within the first media content (405), and To detect the above event, causing the above electronic device (200), Electronic device (200).

3. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, Based on the above detection, information about the usage pattern of media content is identified, and To generate the prompt (1100) based further on the above information about the above usage pattern, causing the above electronic device (200), Electronic device (200).

4. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, Based on the above detection, information about the relationship between the user of the external electronic device (301) and the user of the electronic device (200) is identified, and Based further on the above information about the above relationship, to generate the above prompt (1100), causing the above electronic device (200), Electronic device (200).

5. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, Based on the above detection, information about the size of the display (240) is identified, Further based on the above information about the size of the above display (240), the prompt (1100) is generated, and Using the generative artificial intelligence model (710) into which the first media content (405) and the prompt (1100) are input, the second media content (1105) is obtained in which the part is maintained within the size. causing the above electronic device (200), Electronic device (200).

6. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, Detecting the event for generating the second media content (1105) by summarizing the first media content (405), and Based on the above detection, to generate the prompt for maintaining the part (410) indicated by the above information and summarizing the first media content (405). causing the above electronic device (200), Electronic device (200).

7. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, Detecting the event for generating the second media content (1105) by performing translation of the first media content (405), and Based on the above detection, to generate the prompt for maintaining the part (410) indicated by the above information and performing the translation of the first media content (405). causing the above electronic device (200), Electronic device (200).

8. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, Detecting the event for generating the second media content (1105) by providing additional information about the first media content (405), and Based on the above detection, to maintain the portion (410) indicated by the above information and generate the prompt for requesting the additional description for the first media content (405). causing the above electronic device (200), Electronic device (200).

9. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, While displaying the second media content (1105) on the display (240), receiving an input for generating a third media content at least partially linked with the second media content (1105), Based on the above input, another prompt (1100) is generated for maintaining the portion (410) maintained within the second media content (1105), Obtaining the third media content using the generative artificial intelligence model into which the second media content (1105) and the other prompt (1100) are input, and To display the third media content on the display (240) as a result of the input, causing the above electronic device (200), Electronic device (200).

10. In claim 1, The above information is, Information highlighting the portion (410) within the first media content (405), text information indicating the portion (410) within the first media content (405), and / or visual information surrounding the portion (410) within the first media content (405). Electronic device (200).

11. A method for executing within an electronic device (200) including a communication circuit (230) and a display (240), the method comprising: An operation of receiving first media content (405) and information related to at least a portion of the first media content (405) from an external electronic device (301) through the communication circuit (230); An operation of detecting an event for generating a second media content (1105) at least partially linked to the first media content (405), An operation of generating a prompt (1100) for maintaining the portion (410) indicated by the information based on the above detection; An operation of obtaining the second media content (1105) using a generative artificial intelligence model (710) into which the first media content (405) and the prompt (1100) are input; and Including an operation of displaying the second media content (1105) on the display (240) as a processing for the event. method.

12. In claim 11, The above information is, Including another prompt (700) used to obtain the first media content (405) within the external electronic device (301), The above method, An operation of identifying a portion (410) within the first media content (405) based on the first media content (405) and the other prompt (700), and comprising an action for detecting the above event, method.

13. In claim 11, the method comprises: Based on the above detection, an action is taken to identify information about the usage pattern of media content, and further comprising an action of generating the prompt (1100) based on the information about the usage pattern; method.

14. In claim 11, the method comprises: Based on the above detection, an operation of identifying information about the relationship between the user of the external electronic device (301) and the user of the electronic device (200), and Further based on the above information about the above relationship, including an action of generating the prompt (1100), method.

15. In a non-transitory computer-readable storage medium storing one or more programs, when the one or more programs are executed by an electronic device (200) including a communication circuit (230) and a display (240), Receive first media content (405) and information related to at least a portion of the first media content (405) from an external electronic device (301) through the communication circuit (230), Detecting an event for generating a second media content (1105) at least partially linked to the first media content (405), Based on the above detection, a prompt (1100) is generated for maintaining the portion (410) indicated by the above information; Obtaining the second media content (1105) using the generative artificial intelligence model (710) into which the first media content (405) and the prompt (1100) are input; and To display the second media content (1105) on the display (240) as processing for the event, Including instructions that cause the above electronic device (200), Non-transitory computer-readable storage medium.

Citation Information

Patent Citations

  • Color barley sikhye and Manufacturing method thereof

    KR1020250054459A

  • Finishing process apparatus for quilted fabrics

    KR1020250163066A

  • A floor post for construction and floor post system for construction

    KR102915480B1

  • Generative text using a personality model

    US20190236148A1

  • Systems and methods for machine content generation

    US20220237368A1