Electronic device for recommending content on basis of persona profile, method for operating same, and recording medium

Abstract

An electronic device and method for providing recommended content on the basis of a persona profile are provided. A method by which an electronic device provides recommended content on the basis of a persona profile comprises: an operation of setting a plurality of persona profiles including a first persona profile corresponding to a first application and a second persona profile corresponding to a second application; an operation of receiving a request for input of content related to the first application; an operation of identifying the first persona profile among the plurality of persona profiles in response to the request; an operation of obtaining recommended content outputted from an artificial intelligence model on the basis of the first persona profile, wherein the recommended content outputted from the artificial intelligence model is related to the content for which the input is requested; and an operation of providing the obtained recommended content through a user interface of the first application.

Description

An electronic device for recommending content based on a persona profile, a method of operation thereof, and a recording medium

[0001] The present disclosure relates to an electronic device for recommending content based on a persona profile, a method of operating the same, and a recording medium.

[0002] With the advancement of network and multimedia technologies, users can now use electronic devices to transmit or share content with others. When sharing content with others, even if the content they share (or transmit) aligns with their preferences, the sharing (or transmission) of the content can result in other users receiving a different impression of themselves than they wish to receive. Consequently, there is a growing need for technologies that can effectively provide content that reflects the diverse perspectives users desire to convey to others.

[0003] The above information may be provided as background information to aid in understanding the present disclosure. None of the above is claimed to be prior art related to the present disclosure or can be used in making decisions related to prior art.

[0004] As a technical means for achieving the above-described technical task, according to one embodiment, a method for an electronic device (1901) to provide recommended content based on a persona profile may be provided, including: an operation of setting a plurality of persona profiles including a first persona profile corresponding to a first application and a second persona profile corresponding to a second application (e.g., 210); an operation of receiving a request for inputting content related to the first application (e.g., 220); an operation of identifying the first persona profile among the plurality of persona profiles in response to the request (e.g., 230); an operation of obtaining recommended content output from an artificial intelligence model based on the first persona profile (e.g., 240); and an operation of providing the obtained recommended content through a user interface (e.g., 250).

[0005] Also, according to one embodiment, an electronic device (e.g., 1901) may be provided, including a display (e.g., 1960); a memory (1930) for storing instructions; and one or more processors (1920), wherein the instructions, when executed by the one or more processors, cause the electronic device to: set a plurality of persona profiles including a first persona profile corresponding to a first application and a second persona profile corresponding to a second application; receive a request for input of content related to the first application; identify the first persona profile among the plurality of persona profiles in response to the request; obtain recommended content based on the first persona profile; and display the obtained recommended content through a user interface of the first application.

[0006] In addition, according to one embodiment, a computer-readable recording medium having recorded thereon instructions for executing a method on a computer, the method including: setting a plurality of persona profiles including a first persona profile and a second persona profile; receiving a request for inputting content related to the first application; identifying the first persona profile among the plurality of persona profiles in response to the request; obtaining recommended content output from an artificial intelligence model based on the first persona profile; and displaying the obtained recommended content through a user interface of the first application may be provided.

[0007] Also, according to one embodiment, a method for providing recommended content by an electronic device may be provided, including: setting a plurality of persona profiles for a user of an electronic device; receiving a request from the user for transmission of content through a user interface of a first application running on the electronic device; identifying a first persona profile corresponding to the request among the plurality of user persona profiles when the request is received; providing recommended content generated based on a determination as to whether the content matches the first persona profile on the user interface; and transmitting the recommended content in response to a user input for the recommended content.

[0008] Also, according to one embodiment, an electronic device (e.g., 1901) may be provided, including a display (e.g., 1960); a memory (1930) for storing instructions; and one or more processors (1920); wherein the instructions, when executed by the one or more processors, cause the electronic device to: set a plurality of persona profiles for a user of the electronic device; receive a request from the user for transmission of content through a user interface of a first application running on the electronic device; when the request is received, identify a first persona profile corresponding to the request among the plurality of user persona profiles; provide recommended content generated based on a determination as to whether the content matches the first persona profile on the user interface; and transmit the recommended content in response to a user input for the recommended content.

[0009] Also, according to one embodiment, a computer-readable recording medium having recorded thereon instructions for causing a computer to execute a method for providing recommended content by an electronic device, the method comprising: setting a plurality of persona profiles for a user of an electronic device; receiving a request from the user for transmission of content through a user interface of a first application running on the electronic device; identifying a first persona profile corresponding to the request among the plurality of user persona profiles when the request is received; providing, on the user interface, recommended content generated based on a determination as to whether the content conforms to the first persona profile; and transmitting the recommended content in response to a user input for the recommended content.

[0010] According to one embodiment, an electronic device may be provided, comprising: a display; a memory storing instructions; and one or more processors; wherein the instructions, when executed by the one or more processors, cause the electronic device to: receive a request related to transmission of content through a first application, provide the content through a user interface according to a first persona profile corresponding to the first application among a plurality of persona profiles including a first persona profile and a second persona profile, and transmit the content based on a user input received through the user interface.

[0011] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0012] FIG. 1 is a diagram illustrating an overview of an electronic device recommending content based on a user's persona profile according to one embodiment of the present disclosure.

[0013] FIG. 2 is a flowchart of a method in which an electronic device according to one embodiment provides recommended content according to a user's content input request using a persona profile corresponding to an application.

[0014] FIG. 3 is a flowchart of a method for an electronic device to create a persona profile based on a user's content usage history according to one embodiment.

[0015] FIG. 4 is a flowchart of a method for an electronic device to generate a persona profile based on content selected by a user according to one embodiment.

[0016] FIG. 5A is a diagram illustrating an example in which a persona profile is set to correspond to an application according to one embodiment.

[0017] FIG. 5b is a diagram illustrating an example of a persona profile being set to correspond to an application and a counterpart according to one embodiment.

[0018] FIG. 5c is a diagram illustrating an example in which a persona profile is set to correspond to an electronic device or user account according to one embodiment.

[0019] FIG. 6A is a diagram illustrating an example of a persona profile set from content according to one embodiment.

[0020] FIG. 6b is a diagram illustrating an example of a persona profile set from content according to one embodiment.

[0021] FIG. 7 is a diagram illustrating an example of information regarding a persona profile displayed on a screen of an electronic device according to one embodiment.

[0022] FIG. 8 is a flowchart of a method for an electronic device according to one embodiment to select a persona profile to be used for providing recommended content from among a plurality of persona profiles.

[0023] FIG. 9 is a diagram schematically illustrating information considered by an electronic device in selecting a persona profile according to one embodiment.

[0024] FIG. 10A is a flowchart of a method for an electronic device according to one embodiment to obtain recommended content by selecting a generative artificial intelligence model corresponding to a persona profile from among a plurality of generative artificial intelligence models.

[0025] FIG. 10b is a flowchart of a method for an electronic device according to one embodiment to obtain recommended content using a generative artificial intelligence model corresponding to a plurality of persona profiles.

[0026] FIG. 11 is a diagram illustrating a generative artificial intelligence model of an electronic device and a generative artificial intelligence model of a server according to one embodiment.

[0027] FIG. 12 is a diagram illustrating an example in which an electronic device according to one embodiment provides a recommendation message based on a first persona profile.

[0028] FIG. 13 is a diagram illustrating an example in which an electronic device according to one embodiment provides a recommendation message based on a second persona profile.

[0029] FIG. 14 is a diagram illustrating an example in which an electronic device according to one embodiment provides a recommended image based on a first persona profile.

[0030] FIG. 15 is a diagram illustrating an example in which an electronic device according to one embodiment provides a recommended shooting composition for shooting a camera application based on a first persona profile.

[0031] FIG. 16 is a flowchart of a method for an electronic device to modify a persona profile based on feedback information from another user according to one embodiment.

[0032] FIG. 17 is a diagram illustrating an example of an electronic device modifying a persona profile and content based on feedback from other users on content posted by a user according to one embodiment.

[0033] Figure 18 is a block diagram of an electronic device according to one embodiment.

[0034] FIG. 19 is a block diagram of an electronic device within a network environment according to various embodiments.

[0035] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0036] Below, embodiments of the present disclosure are described in detail with reference to the attached 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 addition, for the purpose of clearly explaining the present disclosure in the drawings, parts irrelevant to the description have been omitted, and similar parts have been designated with similar reference numerals throughout the specification.

[0037] The terms used in this disclosure are described as currently common terms, taking into account the functions mentioned herein. However, these terms may mean various other terms depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Therefore, the terms used in this disclosure should not be interpreted solely based on their names, but rather based on the meanings of the terms and the overall content of this disclosure.

[0038] Additionally, while terms such as first, second, etc. may be used to describe various components, the components should not be limited by these terms. These terms are used to distinguish one component from another.

[0039] Throughout the specification, when a part is said to be "connected" to another part, this includes not only the cases where the parts are "directly connected" but also the cases where the parts are "electrically connected" with other elements intervening. Furthermore, when a part is said to "include" a component, this does not exclude other components, but rather includes other components, unless otherwise stated.

[0040] The phrases “in one embodiment” and the like appearing in various places throughout this disclosure do not necessarily all refer to the same embodiment.

[0041] An embodiment of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented by various hardware and / or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors or by circuit configurations for a given function. Furthermore, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented by algorithms that execute on one or more processors. Furthermore, the present disclosure may employ conventional techniques for electronic configuration, signal processing, and / or data processing. Terms such as “mechanism,” “element,” “means,” and “configuration” may be used broadly and are not limited to mechanical and physical configurations.

[0042] Additionally, the connecting lines or connecting members between components depicted in the drawings are merely exemplary representations of functional connections and / or physical or circuit connections. In an actual device, connections between components may be represented by various functional connections, physical connections, or circuit connections that may be replaced or added.

[0043] In this document, a persona profile may be a virtual profile reflecting multiple attributes related to a user of an electronic device. For example, a persona profile may be a profile that includes information about at least one of the user's gender, age, education level, occupation, income level, shopping habits, interests, preferred services, preferred objects, preferred animals, preferred people, preferred objects, preferred animals, preferred people, preferred content, or behavioral patterns. Furthermore, for example, a persona profile may be a profile that includes information about at least one of the user's language characteristics, preferred image characteristics, or preferred object characteristics. However, the information included in a persona profile is not limited thereto.

[0044] In this document, a generative artificial intelligence model may be an artificial intelligence model that generates a predetermined content based on a prompt input. A prompt is a clue that is conveyed so that a trained artificial intelligence model can understand a human query / request. For example, a generative artificial intelligence model may be an artificial intelligence model that receives a natural language prompt input, an image prompt input, or an audio prompt input and generates or modifies a predetermined type of content. For example, a generative artificial intelligence model may include, but is not limited to, a conversational artificial intelligence model, an image generation artificial intelligence model, an artificial intelligence model for composing, an artificial intelligence model for writing, and / or an artificial intelligence model for coding.

[0045] In this document, context information refers to information indicating a situation of an electronic device, and may include at least one of, but is not limited to, information on the surrounding environment of the electronic device, status information of the electronic device, status information of the user, and schedule information of the user. The surrounding environment information of the electronic device refers to information on the environment within a certain range from the electronic device, and may include, but is not limited to, weather information, location information, temperature information, humidity information, illuminance information, noise information, and sound information, for example. The status information of the electronic device (1901) may include, but is not limited to, mode information of the electronic device (e.g., sound mode, vibration mode, silent mode, power saving mode, blocking mode, multi-window mode, auto-rotate mode), location information of the electronic device (1901), time information, activation information of a communication module (e.g., WiFi ON / Bluetooth OFF / GPS ON / NFC ON), and network connection status information of the electronic device (1901). User status information is information about the user's movements and lifestyle patterns, and may include, but is not limited to, information about the user's walking status, exercise status, driving status, sleep status, mood status, and health status.

[0046] The present disclosure will be described in detail with reference to the attached drawings below.

[0047] FIG. 1 is a diagram illustrating an overview of an electronic device recommending content based on a user's persona profile according to one embodiment of the present disclosure.

[0048] Referring to FIG. 1, an electronic device (1901) may provide recommended content based on a plurality of persona profiles. For example, the recommended content may include content selected, modified, or generated by at least one of a processor (1920) of the electronic device (1901), a generative artificial intelligence model (2050), or an external electronic device (e.g., the electronic device (1902), the electronic device (1904), or the server (1908)). For example, the recommended content may be provided using the generative artificial intelligence model (2050). The electronic device (1901) may receive a content input request (10) through an application, identify a context (12) of the electronic device (1901), and select one of a plurality of persona profiles within the electronic device (1901) in consideration of the application and / or the context (12) of the electronic device (1901). The electronic device (1901) can generate an input prompt (14) to be input into a generative artificial intelligence model (2050) using a selected persona profile, and can obtain recommended content output from the generative artificial intelligence model (2050). According to one embodiment, the electronic device (1901) can select a persona profile from among a plurality of persona profiles by considering the type of application used for sharing and / or transmitting the content, and obtain content recommended to the user by considering the selected persona file and the situation (12) of the electronic device (1901).

[0049] According to one embodiment, the electronic device (1901) may have multiple persona profiles set, each of which may correspond to a specific application. Furthermore, the persona profiles may be set to correspond not only to each application, but also to a group of applications, a counterpart user of the application, a user's account, the status of the electronic device (1901), or at least one of services that may be provided by the electronic device (1901).

[0050] The electronic device (1901) may be, but is not limited to, a smartphone, a tablet PC, a PC, a smart TV, a mobile phone, a personal digital assistant (PDA), a laptop, a media player, a microserver, a global positioning system (GPS) device, an e-book reader, a digital broadcasting terminal, a navigation device, a kiosk, an MP3 player, a digital camera, a home appliance, or other mobile or non-mobile computing device. In addition, the electronic device (1901) may be a wearable device such as a watch, glasses, a hair band, or a ring, having communication and data processing functions. However, the present invention is not limited thereto.

[0051] FIG. 2 is a flowchart of a method in which an electronic device according to one embodiment provides recommended content according to a user's content input request using a persona profile corresponding to an application.

[0052] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0053] In operation 210, according to one embodiment, the electronic device (1901) can generate a plurality of persona profiles including a first persona profile corresponding to a first application and a second persona profile corresponding to a second application. The electronic device (1901) can set a persona profile for each application. For example, the electronic device (1901) can set a first persona profile corresponding to the first application for generating content to be input through the first application. For example, the electronic device (1901) can set a second persona profile corresponding to the second application for generating content to be input through the second application.

[0054] A persona profile may be a virtual profile that reflects multiple attributes related to a user of an electronic device (1901). For example, a persona profile may include data collected for reference in expressing a user's behavioral patterns or personality in a specific situation or environment. For example, a persona profile may be a user profile for a virtual character or target person representing the electronic device (1901) or a user of the electronic device (1901). For example, a persona profile may include data collected by the electronic device (1901) to reflect the user's behavioral patterns or personality in data or content input into the electronic device (1901) by the user of the electronic device (1901). For example, a persona profile may include data collected by the electronic device (1901) to reflect the user's behavioral patterns or personality in data or content transmitted through or displayed on the electronic device (1901). According to one embodiment, the electronic device (1901) can generate a plurality of different profiles. According to one embodiment, the electronic device (1901) can set a plurality of persona profiles to correspond to at least one of information about an application (e.g., application identification information, application type, application usage time, application usage cycle), a counterpart connected through the application, a user's account, the type (or identification value) of the electronic device (1901), or a situation of the electronic device. According to one embodiment, the electronic device (1901) can generate a plurality of persona profiles based on the usage history of content used through applications and the situation of the electronic device (1901) when using the content.According to one embodiment, the electronic device (1901) can generate a persona profile based on a user's selection input via a graphical user interface (GUI) for selecting content to be used to generate the persona profile.

[0055] The context of the electronic device (1901) may include, but is not limited to, at least one of the surrounding environment of the electronic device (1901), the status of the electronic device (1901), the user's status, and the user's schedule. The surrounding environment of the electronic device (1901) refers to an environment within a predetermined range from the electronic device (1901), and may include, but is not limited to, weather, location, temperature, humidity, illumination, noise, and sound, for example. The status of the electronic device (1901) may include, but is not limited to, the mode of the electronic device (1901) (e.g., sound mode, vibration mode, silent mode, power saving mode, blocking mode, multi-window mode, auto-rotate mode), the location of the electronic device (1901), the time, whether a communication module is activated (e.g., WiFi ON / Bluetooth OFF / GPS ON / NFC ON), and the network connection status of the electronic device (1901). The user's state includes the user's movements and lifestyle patterns, and may include, but is not limited to, the user's walking state, exercising state, driving state, sleeping state, and the user's mood state.

[0056] According to one embodiment, in order to determine the situation of the electronic device (1901), the electronic device (1901) may generate and / or collect situation information related to the situation of the electronic device.

[0057] Although the above description describes multiple persona profiles being generated by the electronic device (1901), this is not limiting. Persona profiles may be generated and modified by the processor of the electronic device (1901) and / or the processor of another electronic device (e.g., a server).

[0058] How the electronic device (1901) generates a persona profile is described in more detail in FIGS. 3 and 4.

[0059] In operation 220, according to one embodiment, the electronic device (1901) may receive a content input request through a first application. The electronic device (1901) may receive a user input for sharing content through the first application. For example, the electronic device (1901) may receive a user input for entering a message to be sent to a counterpart through a messaging application, and / or a user input for requesting the creation of a message to be sent to a counterpart through a messaging application. For example, the electronic device (1901) may receive a user input for uploading an image on an execution screen of an application providing a social network service (SNS) service, and / or a user input for requesting a list of images to be uploaded. For example, the SNS service may include an SNS service for sharing video content and / or music content. For example, the SNS service may include an SNS service for sharing content for networking, recruiting, marketing, and / or education between businesses and / or individuals. The type of first application receiving user input is not limited thereto, and the first application may include any type of application capable of providing and / or sharing content between users.

[0060] According to one embodiment, the first application may be an application for configuring the settings of the electronic device (1901). For example, the first application may correspond to one or more functions or settings that can set the theme, sound effects, and / or vibration of the screen of the electronic device (1901). In this case, the settings of the electronic device (1901) may be changed according to the user's persona profile corresponding to the first application. For example, according to the user's persona profile, at least one of the background screen, icon design, sound effects, or font of the electronic device (1901) may be changed, or the application or content to be displayed on the screen of the electronic device (1901) may be changed. According to one embodiment, the above-described changes in settings may also be operated based on the persona profile mapped to the electronic device (1901) or a user account.

[0061] In one embodiment, the electronic device (1901) may receive user input for entering content (e.g., a message, an image) into the first application. Alternatively, the electronic device (1901) may receive user input for specifying the type (or characteristics) of content to be entered into the first application.

[0062] According to one embodiment, the electronic device (1901) may receive a user input for selecting an image to be input. For example, the electronic device (1901) may receive a user input for selecting a button that provides a function for attaching content (e.g., an image) on an execution screen of an application, and display a list of contents that can be selected by the user. For example, the application may include, but is not limited to, a messaging application, a chat application, and a mailing application. In addition, for example, the list of contents may include, but is not limited to, contents stored in the electronic device (1901), contents stored in another electronic device (e.g., a server) under the account of the user of the electronic device (1901), and contents provided from another electronic device (e.g., a server) that the electronic device (1901) can access. Thereafter, the electronic device (1901) may receive a user input for selecting at least one content from the list of contents.

[0063] In one embodiment, the electronic device (1901) may receive a text input from a user requesting input of content. For example, the electronic device (1901) may receive a text input such as “I’ll send you a picture of a cat” entered by the user into an input window of a messaging application, a chat application, or an email application, or may receive an input of the user selecting a function button to attach an image after entering the text.

[0064] Alternatively, the electronic device (1901) may receive user input after receiving a message. For example, after receiving a message from the other party containing text such as “I want to see pictures of cats,” the electronic device may receive user input for pressing a function button to attach an image.

[0065] According to one embodiment, the electronic device (1901) may generate a persona profile by considering the context of the electronic device (1901) without considering the application. For example, the electronic device (1901) may generate a persona profile corresponding to a first context of the electronic device (1901) and another persona profile corresponding to a second context of the electronic device (1901). In this case, the settings of the electronic device (1901) may be changed depending on the current context of the electronic device (1901). For example, at least one of the background screen, icon design, sound effect, or font of the electronic device (1901) may be changed, or an application or content to be displayed on the screen of the electronic device (1901) may be changed depending on the user's persona profile corresponding to the current context of the electronic device (1901) (e.g., the location of the electronic device (1901).

[0066] Content may refer to digital information provided through an electronic device (e.g., electronic device (1901)). For example, content may include, but is not limited to, video content (e.g., TV program video, VOD (video on demand), user-created content (UCC), music videos, YouTube videos), still image content (e.g., photographs, drawings), text content (e.g., e-books (poems, novels), letters, work files), music content (e.g., music, musical pieces, radio broadcasts), web pages, and messages.

[0067] In operation 230, according to one embodiment, the electronic device (1901) may identify a first persona profile corresponding to a first application among a plurality of persona profiles. Upon receiving a content input request through the first application, the electronic device (1901) may identify the first application and select the first persona profile corresponding to the first application among the plurality of persona profiles.

[0068] According to one embodiment, the electronic device (1901) can identify at least one of an application, a counterpart connected through the application, a user's account, a type (or identification value) of the electronic device (1901), or a situation of the electronic device. In addition, the electronic device (1901) can select a first persona profile corresponding to at least one of the identified application, the counterpart connected through the application, the user's account, the type (or identification value) of the electronic device (1901), or a situation of the electronic device from among a plurality of persona profiles.

[0069] For example, the electronic device (1901) can identify a first application and at least one counterpart connected through the first application, and select a first persona profile corresponding to the identified first application and the identified at least one counterpart.

[0070] For example, the electronic device (1901) may identify a first application and an account of a user of the first application, and select a first persona profile corresponding to the identified first application and account of the identified user.

[0071] For example, the electronic device (1901) may identify a first application and a type (or identification value) of the electronic device (1901), and select a first persona profile corresponding to the identified first application and the type (or identification value) of the identified electronic device (1901).

[0072] However, the information used to select the first persona profile is not limited thereto. Furthermore, the method by which the electronic device (1901) identifies the first persona among multiple persona profiles will be described in more detail in FIG. 8.

[0073] According to one embodiment, upon receiving a content input request through a first application, the electronic device (1901) may determine whether to provide a function to modify and / or change the content based on a persona profile. For example, the electronic device (1901) may determine whether to provide a function to modify and / or change the content based on a persona profile by considering at least one of the other party sharing the content, the identification value of the application, the type of the application, the current situation of the electronic device (1901) (e.g., location, time), the type of content to be input, or the content of the conversation through the application. For example, the electronic device (1901) may determine whether to provide a function to modify and / or change the content based on a persona profile, based on who the other party is, what the application is, where the application is being used, and what the previous conversation content or the content to be input is.

[0074] According to one embodiment, upon receiving a content input request via a first application, the electronic device (1901) may display a graphical user interface (GUI) for selecting whether to provide a function to modify and / or change the content based on a persona profile. In this case, the electronic device (1901) may determine whether to provide a function to modify and / or change the content based on a persona profile based on a user's selection input to the GUI.

[0075] In operation 240, the electronic device (1901) can obtain recommended content output from a generative artificial intelligence model based on the first persona profile.

[0076] The electronic device (1901) may generate an input prompt to be input into a generative artificial intelligence model based on the first persona profile, and provide the generated input prompt to the generative artificial intelligence model. The generative artificial intelligence model may include a model that generates images (e.g., still images, moving images). For example, the generative artificial intelligence model may be, but is not limited to, a generative model using a generative adversarial network (GAN), a variational auto encoder (VAE), a diffusion, or a transformer structure.

[0077] According to one embodiment, the electronic device (1901) may select a generative artificial intelligence model to be used for generating recommended content from among a plurality of generative artificial intelligence models. For example, when there are a plurality of generative artificial intelligence models corresponding to at least one of a type of application, a type of recommended content, or a type of service, the electronic device (1901) may select a generative artificial intelligence model to be used for generating recommended content from among the plurality of generative artificial intelligence models by considering the type of the first application, the type of recommended content to be generated, and / or the type of service provided by the first application.

[0078] According to one embodiment, in the case where there is a generative artificial intelligence model that provides an integrated artificial intelligence service by providing recommended content for multiple types of applications, multiple types of recommended content, and multiple types of services, the electronic device (1901) can utilize the generative artificial intelligence model that provides the integrated artificial intelligence service.

[0079] In one embodiment, the electronic device (1901) may generate an input prompt including information about the first persona profile, the type of recommended content, a method for generating the recommended content, and / or information to be used for generating the recommended content. For example, the input prompt may be generated in the form of a script containing sentences in natural language format.

[0080] For example, when content (e.g., a message or an image) is input into a first application in response to a user's content input request, the input prompt may include the content input by the user's content input request, and the generative artificial intelligence model may output recommended content generated by modifying the input content. For example, when the user's content input request is an input that specifies the type (or characteristic) of the input content, the input prompt may include information indicating the type (or characteristic) of the content requested by the user, and the generative artificial intelligence model may generate new recommended content and output the generated recommended content.

[0081] In one embodiment, the input prompt may include information about content considered for generating the persona profile. For example, the input prompt may include an image or video considered for generating the persona profile. For example, the input prompt may include metadata about the image or video considered for generating the persona profile. For example, the input prompt may include attribute data analyzed from the image or video considered for generating the persona profile.

[0082] According to one embodiment, the electronic device (1901) can obtain recommended content output from the generative artificial intelligence model by providing an input prompt to the generative artificial intelligence model. For example, when the electronic device (1901) uses the generative artificial intelligence model within the electronic device (1901), the electronic device (1901) can provide the input prompt to the generative artificial intelligence model within the electronic device (1901). For example, when the electronic device (1901) uses the generative artificial intelligence model within another electronic device (e.g., a server), the electronic device (1901) can transmit the input prompt to the other electronic device. For example, the electronic device (1901) can obtain recommended content by using the generative artificial intelligence model within the electronic device (1901) and the generative artificial intelligence model within another electronic device together.

[0083] In one embodiment, when information regarding content considered in generating a persona profile is passed to a generative artificial intelligence model, the information regarding the content considered in generating the persona profile may be included in an input prompt and input to the generative artificial intelligence model. If, for example, information regarding the content considered in generating the persona profile is not included in the input prompt, the information regarding the content considered in generating the persona profile may be input to the generative artificial intelligence model separately from the input prompt.

[0084] Meanwhile, according to one embodiment, the input prompt may not include detailed information of the first persona profile, but may only include information for obtaining detailed information of the first persona profile. The detailed information of the first persona profile may include detailed items and values ​​corresponding to the detailed items within the first persona profile. For example, the input prompt may include an identification value of the first persona profile or link information for downloading detailed information of the first persona. In this case, the generative artificial intelligence model may obtain detailed information of the first persona profile by using the link information for downloading detailed information of the first persona profile included in the input prompt or the identification value of the first persona profile.

[0085] In one embodiment, a generative artificial intelligence model may be included in an electronic device (1901). In this case, the electronic device (1901) may receive link information for downloading detailed information of a first persona profile or an identification value of the persona profile from another electronic device (e.g., a server). Thereafter, the generative artificial intelligence model of the electronic device (1901) may obtain detailed information of the first persona profile using the link information for downloading detailed information of the first persona profile or the identification value of the first persona profile.

[0086] In one embodiment, the generative AI model may be included in another electronic device (e.g., a server). In this case, the electronic device (1901) may provide link information for downloading detailed information of the first persona profile or an identification value of the persona profile to the other electronic device (e.g., the server). Thereafter, the generative AI model of the other electronic device (e.g., the server) may use the link information for downloading detailed information of the first persona profile or the identification value of the first persona profile to obtain detailed information of the first persona profile.

[0087] In one embodiment, the input prompt may not include information for identifying a persona profile, but may include information regarding whether a function for providing recommended content based on a persona profile is activated. In this case, the generative artificial intelligence model of the electronic device (1901) and / or another electronic device (e.g., a server) may identify, through the input prompt, that the function for providing recommended content based on a persona profile is activated, determine which persona profile to apply, and obtain and utilize detailed information about the persona profile pre-stored in the electronic device (1901) and / or another electronic device (e.g., a server).

[0088] The method by which the electronic device (1901) obtains recommended content using a generative artificial intelligence model will be described in more detail in FIGS. 10a and 10b.

[0089] In operation 250, according to one embodiment, the electronic device (1901) may output recommended content through a user interface. For example, the electronic device (1901) may display recommended content generated by a generative artificial intelligence model on the user interface of the first application. According to one embodiment, when a plurality of recommended contents are provided from the generative artificial intelligence model, the electronic device (1901) may display a recommendation list including the plurality of recommended contents on the screen of the first application, receive a user input for selecting some of the plurality of recommended contents in the recommendation list, and input the selected some of the recommended contents into the first application.

[0090] In one embodiment, the use of content that does not conform to a persona profile may be restricted by the electronic device (1901). For example, if a persona profile is selected and restrictions on the use of content that does not conform to the selected persona profile are set, access to or transmission (or uploading) of content that does not conform to the selected persona profile may be blocked.

[0091] In one embodiment, the electronic device (1901) may perform actions that not only input recommended content into an application based on the persona profile, but also recommend specific actions for the user to take that align with the persona. For example, the electronic device (1901) may recommend that the user visit a specific location, recommend a specific book or music, or recommend contacting a specific person.

[0092] FIG. 3 is a flowchart illustrating a method for an electronic device, according to one embodiment, to create a persona profile based on a user's content usage history. Operations 310 to 330 of FIG. 3 may correspond to operation 210 of FIG. 2 .

[0093] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0094] In operation 310, according to one embodiment, the electronic device (1901) may obtain context information related to the user's content usage history. The electronic device (1901) may collect information about the usage history of content used through applications and the situation of the electronic device (1901) when using the content. The electronic device (1901) may identify content used by the user through each application. The content used by the user may include, but is not limited to, content selected by the user and / or content input by the user. The content used by the user may include color information of the GUI of the application used by the user. According to one embodiment, the electronic device (1901) may obtain, according to one application, context information about the situation of the electronic device (1901) when content is selected or input by the user through each application. In one embodiment, content utilized through the application may be utilized to create a user's persona profile, and the acquired contextual information may be utilized to set a situation in which to utilize the persona profile, but is not limited thereto.

[0095] In operation 320, according to one embodiment, the electronic device (1901) may obtain user account information. The electronic device (1901) may collect user account information for each application. According to one embodiment, the user account information may be used to determine which user is using the application. For example, the account information of the application may include, but is not limited to, at least one of a service ID (identifier) ​​of a user using the application's service, profile information of the application's user account, and feedback information from other users regarding the user account or content uploaded to the user account.

[0096] In operation 330, according to one embodiment, the electronic device (1901) may generate a user persona profile for each application. The electronic device (1901) may generate a persona profile corresponding to each of a plurality of applications. For example, the electronic device (1901) may generate a first persona profile corresponding to a first application and a second persona profile corresponding to a second application. For example, the second persona profile may include information indicating a different behavioral pattern or personality of the user than the first persona profile. For example, the first persona profile and the second persona profile may include information that can be used to create impressions, tastes, or values ​​of different individuals. For example, the impressions, tastes, and / or values ​​of an individual corresponding to the first persona profile may differ from the impressions, tastes, and / or values ​​of an individual corresponding to the second persona profile.

[0097] According to one embodiment, the electronic device (1901) can generate a persona profile based on content used by a user through an application. In this case, the electronic device (1901) can generate the persona profile using information obtained from the content. For example, the electronic device (1901) can generate a persona profile corresponding to the application by analyzing messages input by the user into the application, media content (e.g., images, videos, audio, text) input by the user into the application, and media content (e.g., images, videos, audio) executed by the application. By generating a persona profile based on content used by the user through the application, a persona profile reflecting the characteristics of the user when using the application can be generated.

[0098] According to one embodiment, the electronic device (1901) can create a persona profile by analyzing the characteristics of content used by the user through an application. The electronic device (1901) can extract the characteristics of the content used by the user through the application and create a persona profile based on the extracted characteristics. For example, if the content used by the user through the application is a message entered by the user, the electronic device (1901) can obtain information about the user's preferred vocabulary and tone of voice from the message. For example, if the content used by the user through the application is movie content or music content, the electronic device (1901) can obtain information about the genre of the content and the characteristics of the artist of the content. For example, if the content used by the user through the application is an image, the electronic device (1901) can obtain information about the color tone of the image, the theme of the image, the type of object within the image, and / or the arrangement composition of the object within the image.

[0099] In one embodiment, the electronic device (1901) may additionally utilize the user's personal information to create a persona profile. For example, the electronic device (1901) may additionally utilize personal information regarding the user's age, gender, occupation, position, and / or relationships with others (e.g., friends, coworkers) to create a persona profile.

[0100] According to one embodiment, the electronic device (1901) can generate a persona profile using a separate artificial intelligence model for generating a persona profile. For example, the electronic device (1901) can obtain a persona profile output from the artificial intelligence model by applying information regarding the characteristics of the content to the artificial intelligence model. If the separate artificial intelligence model for generating the persona profile is a generative artificial intelligence model, the electronic device (1901) can obtain a persona profile by generating an input prompt including information regarding the characteristics of the content and inputting the generated input prompt into the separate artificial intelligence model for generating the persona profile.

[0101] According to one embodiment, the electronic device (1901) can create a persona profile by additionally considering at least one of the application, the counterpart of the application, the user account of the application, or the context of the electronic device.

[0102] For example, the electronic device (1901) may create a persona profile corresponding to a first application and a first counterpart, a persona profile corresponding to the first application and a second counterpart, a persona profile corresponding to a second application and a third counterpart, and a persona profile corresponding to the second application and a fourth counterpart. In this case, the counterpart may be a counterpart who uses a service provided by the application and may be a counterpart who receives recommended content through the application. Additionally, the counterpart may be identified by account information (e.g., service ID) of the service provided by the application.

[0103] For example, the electronic device (1901) may create a persona profile corresponding to a first application and a first account of the user, a persona profile corresponding to a second account of the first application and the user, a persona profile corresponding to a third account of the second application and the user, and a persona profile corresponding to a fourth account of the second application and the user. The user's account may be identified by an account of a service provided by the application (e.g., a service ID).

[0104] For example, the electronic device (1901) may generate a persona profile corresponding to a first application and a first situation of the electronic device (1901), a persona profile corresponding to a second situation of the first application and the electronic device (1901), a persona profile corresponding to a third situation of the first application and the electronic device (1901), and a persona profile corresponding to a fourth situation of the first application and the electronic device (1901). In this case, the situation of the electronic device corresponding to the persona profile may be preset.

[0105] In one embodiment, the electronic device (1901) may generate a persona profile by considering the context of the electronic device (1901) without considering the application. For example, the electronic device (1901) may generate a persona profile corresponding to a first context of the electronic device (1901) and generate another persona profile corresponding to a second context of the electronic device (1901).

[0106] According to one embodiment, the electronic device (1901) can display a GUI for modifying a generated persona profile and can modify the persona profile based on user input through the GUI.

[0107] Although FIG. 3 describes an electronic device (1901) obtaining the user's account information as a separate operation, this is not limited to operation 320. Operation 320 may be performed concurrently with operation 310.

[0108] Additionally, although FIG. 3 illustrates that multiple persona profiles are generated by the electronic device (1901), this is not limiting. Persona profiles may be generated and modified by the processor of the electronic device (1901) and / or the processor of another electronic device (e.g., a server).

[0109] FIG. 4 is a flowchart illustrating a method for an electronic device, according to one embodiment, to generate a persona profile based on content selected by a user. Operations 410 to 460 of FIG. 4 may correspond to operation 210 of FIG. 2 .

[0110] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0111] In operation 410, according to one embodiment, the electronic device (1901) may receive user input for generating a persona profile. For example, the electronic device (1901) may receive user input for generating a persona profile for at least one specific application. For example, the electronic device (1901) may receive user input for generating a persona profile for an application while the application is running (or while the running screen is displayed). For example, the electronic device (1901) may receive user input for selecting at least a specific application from an application list and user input for generating a persona profile. For example, the electronic device (1901) may receive user input for selecting at least one application from an application list, or user input for selecting a group of applications.

[0112] For example, the electronic device (1901) may receive user input to create a persona profile by additionally considering at least one of the counterpart of the application, the user account of the application, or the context of the electronic device. In this case, the counterpart may be a counterpart who uses a service provided by the application and may be provided with recommended content through the application. Additionally, the counterpart may be identified by account information (e.g., service ID) of the service provided by the application. In this case, the user's account may be identified by an account (e.g., service ID) of the service provided by the application.

[0113] For example, the electronic device (1901) may receive user input to create a persona profile, taking into account the context of the electronic device (1901) without considering the application.

[0114] For example, the electronic device (1901) may receive user input to create a persona profile considering the context of a conversation with the other party via a messaging application.

[0115] In operation 420, according to one embodiment, the electronic device (1901) may identify an application corresponding to a persona profile to be generated. For example, if the electronic device (1901) receives a user input for generating a persona profile for an application while the application is running (or a running screen is displayed), the electronic device (1901) may identify the running application (or the application on the displayed running screen) as an application corresponding to the persona profile to be generated. For example, if the electronic device (1901) receives a user input for selecting a specific application from an application list and a user input for generating a persona profile, the electronic device (1901) may identify the application selected by the user as an application corresponding to the persona profile to be generated. For example, if the electronic device (1901) receives a user input for selecting an application group from an application list, the electronic device (1901) may identify identification values ​​of applications included in the application group.

[0116] For example, if the electronic device (1901) receives user input to create a persona profile by additionally considering at least one of the counterpart of the application, the user account of the application, or the context of the electronic device, the electronic device (1901) may identify information about at least one of the counterpart of the application, the user account of the application, or the context of the electronic device, in addition to the identification value of the application.

[0117] For example, if the electronic device (1901) receives user input to create a persona profile by considering the context of the electronic device (1901) without considering the application, the electronic device (1901) can obtain context information to determine the current context of the electronic device (1901) or the context to which the persona will be applied.

[0118] For example, if an electronic device (1901) receives user input for creating a persona profile by considering the context of a conversation with a counterpart through a messaging application, the electronic device (1901) can obtain information about the context of the conversation with the counterpart. For example, the electronic device (1901) can obtain information about the context of the conversation by inputting text reflecting the conversation with the counterpart into a separate artificial intelligence model for conversation analysis.

[0119] In operation 430, according to one embodiment, the electronic device (1901) may display a graphical user interface (GUI) for selecting content for creating a persona profile. The GUI for creating a persona profile may include a content list including content items that can be selected by the user. For example, the content items in the content list may include content items representing content stored in the electronic device (1901) and content items of content that are not stored in the electronic device (1901) but are pre-designated for determining the user's persona profile. Content for creating a persona profile may include, but is not limited to, video content (e.g., TV program videos, VOD (video on demand), user-created contents (UCC), music videos, YouTube videos), still image content (e.g., photographs, drawings), text content (e.g., e-books (poems, novels), letters, work files), music content (e.g., music, musical pieces, radio broadcasts), web pages, and messages.

[0120] In operation 440, according to one embodiment, the electronic device (1901) can identify content selected by the user through the GUI, and in operation 450, the electronic device (1901) can use the identified content to create a persona profile corresponding to the application.

[0121] The electronic device (1901) can generate a persona profile by analyzing the characteristics of the selected content. The electronic device (1901) can extract the characteristics of the selected content and generate a persona profile based on the extracted characteristics. For example, if the selected content is a message, the electronic device (1901) can obtain information about the user's preferred vocabulary and tone of voice from the message. For example, if the selected content is movie content or music content, the electronic device (1901) can obtain information about the genre of the content and / or the characteristics of the artist of the content. For example, if the selected content is an image, the electronic device (1901) can obtain information about the color of the image, the theme of the image, the type of objects within the image, and / or the arrangement composition of objects within the image. In addition, the electronic device (1901) can generate a persona profile using the information obtained from the content.

[0122] In one embodiment, the electronic device (1901) may additionally utilize the user's personal information to create a persona profile. For example, the electronic device (1901) may additionally utilize personal information regarding the user's age, gender, occupation, position, and relationships with others (e.g., friends, coworkers) to create a persona profile.

[0123] According to one embodiment, the electronic device (1901) can generate a persona profile using a separate artificial intelligence model for generating a persona profile. For example, the electronic device (1901) can obtain a persona profile output from the artificial intelligence model by applying information regarding the characteristics of the content to the artificial intelligence model. If the separate artificial intelligence model for generating the persona profile is a generative artificial intelligence model, the electronic device (1901) can obtain a persona profile by inputting an input prompt including information regarding the characteristics of the content to the separate artificial intelligence model for generating the persona profile.

[0124] According to one embodiment, the electronic device (1901) can create a persona profile by additionally considering at least one of the application, the counterpart of the application, the user account of the application, or the context of the electronic device.

[0125] For example, the electronic device (1901) may create a persona profile corresponding to a first application and a first counterpart, a persona profile corresponding to the first application and a second counterpart, a persona profile corresponding to the second application and a third counterpart, and a persona profile corresponding to the second application and a fourth counterpart. In this case, the person may be a counterpart who uses a service provided by the application and receives recommended content through the application. Additionally, the counterpart may be identified by account information (e.g., service ID) of the service provided by the application.

[0126] For example, the electronic device (1901) may create a persona profile corresponding to a first application and a first account of the user, a persona profile corresponding to a second account of the first application and the user, a persona profile corresponding to a third account of the second application and the user, and a persona profile corresponding to a fourth account of the second application and the user. The user's account may be identified by an account of a service provided by the application (e.g., a service ID).

[0127] For example, the electronic device (1901) may generate a persona profile corresponding to a first application and a first situation of the electronic device (1901), a persona profile corresponding to a second situation of the first application and the electronic device (1901), a persona profile corresponding to a third situation of the first application and the electronic device (1901), and a persona profile corresponding to a fourth situation of the first application and the electronic device (1901). In this case, the situation of the electronic device corresponding to the persona profile may be preset.

[0128] In one embodiment, the electronic device (1901) may generate a persona profile by considering the context of the electronic device (1901) without considering the application. For example, the electronic device (1901) may generate a first persona profile corresponding to a first context of the electronic device (1901) and a second persona profile corresponding to a second context of the electronic device (1901).

[0129] According to one embodiment, the electronic device (1901) may display a GUI for receiving user input for creating a persona profile. In this case, the electronic device (1901) may create a persona profile based on the user input via the GUI. For example, the user may select detailed items (e.g., age, gender, hobbies, special skills, personality, and reference model) of the persona profile via the GUI. In this case, for example, the content acquired for creating the persona profile may be used to assist the user in selecting detailed items of the persona profile. For example, the content acquired for creating the persona profile may be used by the electronic device (1901) to provide recommended detailed items to the user via the GUI, and the user may select at least one of the recommended detailed items. Alternatively, for example, the content acquired for creating the persona profile may be used by the electronic device (1901) to provide a modification guide for detailed items selected by the user.

[0130] According to one embodiment, the electronic device (1901) may display a list of recommended persona profiles via a graphical user interface (GUI) for receiving user input for creating a persona profile. In this case, the electronic device (1901) may determine the recommended persona profiles to be included in the list of recommended persona profiles based on a priority that takes into account, for example, the conversation context between the user and the other party and / or the user's persona profile selection history.

[0131] According to one embodiment, the electronic device (1901) can display a preview screen of content modified or created according to a recommended persona profile determined according to the above priority, and the user can select at least one of the recommended persona profiles by considering the modified or created content in the preview screen.

[0132] In operation 460, according to one embodiment, the electronic device (1901) can modify a persona profile based on user input. The electronic device (1901) can display a GUI for modifying the persona profile and modify the persona profile based on the user input to the GUI.

[0133] Although FIG. 3 describes a method for generating a persona profile based on a user's content usage history, and FIG. 4 separately describes a method for generating a persona profile based on content selected by a user, the present invention is not limited thereto. The electronic device (1901) may also generate a persona profile by taking into account both the user's content usage history and the content selected by the user.

[0134] Additionally, although FIG. 4 illustrates that multiple persona profiles are generated by the electronic device (1901), this is not limiting. Persona profiles may be generated and modified by the processor of the electronic device (1901) and / or the processor of another electronic device (e.g., a server).

[0135] FIG. 5A is a diagram illustrating an example in which a persona profile is set to correspond to an application according to one embodiment.

[0136] Referring to FIG. 5A, a first persona profile may be created to correspond to a first application, and a second persona profile may be created to correspond to a second application.

[0137] While FIG. 5A illustrates a single application corresponding to a single persona profile, this is not a limitation. Multiple applications may correspond to a single persona profile, or a single application may correspond to multiple persona profiles. If a single application corresponds to multiple persona profiles, the electronic device (1901) may display a GUI allowing the user to select one of the multiple persona profiles before generating recommended content through the application.

[0138] According to one embodiment, the electronic device (1901) may display a GUI for selecting a persona profile corresponding to an application. For example, when a specific application is selected by a user, the electronic device (1901) may display a list of recommended persona profiles to allow the user to select a persona profile corresponding to the selected application. In this case, the electronic device (1901) may determine the recommended persona profiles to be included in the list of recommended persona profiles based on a priority that takes into account, for example, the conversation context between the user and the other party and / or the user's persona profile selection history. When a specific persona profile is selected from the list of recommended persona profiles, the electronic device (1901) may map the selected persona profile to the application.

[0139] According to one embodiment, the electronic device (1901) may display a GUI for selecting an application corresponding to a persona profile. For example, when a specific persona profile is selected by a user, the electronic device (1901) may display a list of recommended applications to allow the user to select an application corresponding to the selected persona profile. In this case, the electronic device (1901) may determine the recommended applications to be included in the list of recommended applications based on a priority that takes into account, for example, the conversation context between the user and the other party and / or the user's application selection history. When a specific application is selected from the list of recommended applications, the electronic device (1901) may map the selected application to the persona profile.

[0140] According to one embodiment, the electronic device (1901) can display a preview screen of content modified or created according to a recommended persona profile determined according to the above priority, and the user can select at least one of the recommended persona profiles by considering the modified or created content in the preview screen.

[0141] FIG. 5b is a diagram illustrating an example of a persona profile being set to correspond to an application and a counterpart according to one embodiment.

[0142] Referring to FIG. 5b, a first persona profile may correspond to a first application and a counterpart A, a second persona profile may correspond to a first application and a counterpart B, a third persona profile may correspond to a second application and a counterpart C, and a fourth persona profile may correspond to a second application and a counterpart D.

[0143] Although FIG. 5b illustrates that one application and one counterpart correspond to one persona profile, this is not a limitation. One or more applications and one or more counterparts may correspond to one or more persona profiles. If there are multiple persona profiles corresponding to generating recommended content through an application, the electronic device (1901) may display a GUI that allows the user to select one of the multiple persona profiles before generating recommended content through the application.

[0144] FIG. 5c is a diagram illustrating an example in which a persona profile is set to correspond to an electronic device or user account according to one embodiment.

[0145] Referring to FIG. 5c, a first persona profile may correspond to a first electronic device (or a first account of the user), and a second persona profile may correspond to a second electronic device (or a second account of the user).

[0146] Although FIG. 5c illustrates that one electronic device (or user account) corresponds to one persona profile, this is not a limitation. One or more electronic devices (or one or more user accounts) may correspond to one or more persona profiles. If there are multiple persona profiles corresponding to generating recommended content through the application, the electronic device (1901) may display a GUI that allows the user to select one of the multiple persona profiles before generating recommended content through the application.

[0147] Although examples in which a persona profile corresponds to at least one of a corresponding application, counterpart, electronic device, or user account are described in FIGS. 5A through 5C , the present invention is not limited thereto. For example, various situations of the electronic device (1901) may correspond to a persona profile.

[0148] FIG. 6A is a diagram illustrating an example of a persona profile set from content according to one embodiment.

[0149] Referring to FIG. 6A, a first persona profile (62) may be generated based on content executed in a music application and content selected by a user. The electronic device (1901) may, for example, obtain information about the cover image, genre, and artist of a music video (60) executed in the music application. Additionally, the electronic device (1901) may, for example, obtain images (61) selected by the user for generating a persona profile.

[0150] The electronic device (1901) may generate a first persona profile (62) based on information about the music video (60) and information about images (61) selected by the user. For example, the first persona profile (62) may include, but is not limited to, information about the user's language characteristics, preferred music genre, preferred colors, and preferred objects.

[0151] For example, if there are statistics that the music video (60) and the artist of the music video (60) of FIG. 6a are mainly preferred by women in their 20s living in Seoul, the artist of the music video (60) prefers a friendly tone of speech, cats frequently appear in the music video (60) or cats are relatively preferred as pets by people / age groups who like the genre of the music video (60), and the images (61) selected by the user of FIG. 6a are mainly images related to cats that include pastel colors with a hint of pink, the electronic device (1901) can set the persona profile of the user as “female in her 20s living in Seoul, friendly tone of speech, prefers pastel colors, Tone and Manner type Pink, preferred object: cat.”

[0152] FIG. 6b is a diagram illustrating an example of a persona profile set from content according to one embodiment.

[0153] Referring to FIG. 6B, a second persona profile (68) may be generated based on user-selected photos and user-written messages in a mail application. The electronic device (1901) may, for example, obtain user-selected images (66) for generating the persona profile. Additionally, the electronic device (1901) may, for example, obtain user-written messages (67) in a mail application.

[0154] The electronic device (1901) may generate a second persona profile (68) based on information about user-selected photos (66) and user-written messages (67). For example, the second persona profile (68) may include, but is not limited to, information about the user's language characteristics, place of residence, age, preferred colors, and preferred objects.

[0155] For example, if the photos (66) in FIG. 6b are mainly photos of achromatic cityscapes, which are mainly selected by working women in their 20s, and the message (67) contains text with a polite but cold tone, the electronic device (1901) can set the user's persona profile as "a working woman in her 20s living in Seoul, polite but cold tone, prefers achromatic colors."

[0156] FIG. 7 is a diagram illustrating an example of information regarding a persona profile displayed on a screen of an electronic device according to one embodiment.

[0157] Referring to FIG. 7, a screen representing a persona profile may include details (70) of the persona profile, a list of applications (72) corresponding to the persona profile, and a list of counterparts (74) corresponding to the persona profile. For example, the details (70) of the persona profile may include values ​​representing attributes of a user included in the persona profile. For example, the list of applications (72) may include identifiers (e.g., application names, icons) of applications to which the persona profile is applied. The list of counterparts (74) may include identifiers (e.g., names, IDs, phone numbers) of counterparts who will receive recommended content generated by reflecting the persona profile.

[0158] For example, the application list (72) may include not only applications corresponding to a persona profile generated by user input, but also identification values ​​of other applications similar to the application. In this case, the other applications included in the application list (72) may be applications that are determined by the artificial intelligence model to be suitable for corresponding to the persona profile. For example, the other applications may include, but are not limited to, applications that provide similar functions to the application in question, or applications used in similar situations to those in which the application in question is used.

[0159] For example, the counterparty list (74) may include not only counterparts corresponding to a persona profile generated by user input, but also other counterparts with similar attributes to the corresponding counterparty. In this case, the other counterparty included in the counterparty list (74) may be a counterparty determined by the artificial intelligence model to be suitable even if it corresponds to the corresponding persona profile. For example, the other counterparty may include, but is not limited to, a counterparty who has a similar relationship with the user of the electronic device (1901) to the corresponding counterparty, or a counterparty who has shared content with the user in a similar situation to the situation in which the corresponding counterparty shared content with the user.

[0160] According to one embodiment, when a user attempts to input content through an application, the electronic device (1901) may display a screen representing the persona profile so that the user can confirm the persona profile associated with the content input. For example, when the user inputs content reflecting the attributes of the persona profile, the electronic device (1901) may display an icon capable of displaying a screen representing the persona profile, and upon receiving a user selection input for the icon, the electronic device (1901) may display a screen representing the persona profile.

[0161] FIG. 8 is a flowchart illustrating a method by which an electronic device, according to one embodiment, selects a persona profile to be used for providing recommended content from among multiple persona profiles. Operations 810 to 850 of FIG. 8 may correspond to operation 230 of FIG. 2 .

[0162] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0163] In operation 810, according to one embodiment, the electronic device (1901) can identify the first application that has received the content input request. When a user input for inputting content is received through the execution screen of the first application, the electronic device (1901) can identify the first application. For example, when a function for providing recommended content reflecting a persona profile is activated and a persona profile corresponding to the first application is preset, when a content input request through the first application is received, the electronic device (1901) can identify the first application to generate recommended content to be input through the first application. In this case, the function for providing recommended content reflecting a persona profile can be activated or deactivated through a separate setting screen of the electronic device (1901).

[0164] The electronic device (1901) may identify the first application when receiving a user input for inputting content through the first application or a user input requesting the generation of content to be input. For example, the electronic device (1901) may obtain an identification value of the message application upon receiving a user input for inputting a message to be sent to a counterpart through the message application. Alternatively, for example, the electronic device (1901) may obtain an identification value of the message application upon receiving a user input for requesting the generation of a message to be sent to a counterpart through the message application.

[0165] According to one embodiment, the electronic device (1901) may receive a user input for selecting a first application to transmit content. In this case, upon receiving a user input for sharing content, the electronic device (1901) may display an application list including identification values ​​of applications capable of transmitting the content to be shared. Additionally, the electronic device (1901) may receive a user input for selecting a first application within the application list. The electronic device (1901) may identify the first application selected by the user.

[0166] In operation 820, the electronic device (1901) can identify at least one counterparty to receive recommended content through the first application. For example, if the first application is a messaging application, the electronic device (1901) can identify at least one counterparty participating in a conversation window of the messaging application. For example, if the first application is a social networking service (SNS) application, the electronic device (1901) can identify at least one counterparty who has a preset friendship relationship with the user of the electronic device (1901).

[0167] In operation 830, the electronic device (1901) may identify an electronic device running a first application. For example, the electronic device (1901) may identify an identification value (e.g., a service set identifier (SSID)) of the electronic device (1901). According to one embodiment, the electronic device (1901) may also identify account information of a user of the electronic device (1901). In this case, the user's account information may be, for example, but is not limited to, user account information for a service provided by the first application.

[0168] In operation 840, the electronic device (1901) can identify the current status of the electronic device (1901).

[0169] The electronic device (1901) can identify the state of the electronic device (1901) when a user's content input request is received. The electronic device (1901) can identify the state of the electronic device (1901) by using at least one sensor within the electronic device (1901). In addition, the electronic device (1901) can identify the state of the electronic device (1901) by checking various setting values ​​of the electronic device (1901) and functions being executed in the electronic device (1901).

[0170] In operation 850, the electronic device (1901) may select a first persona profile from among a plurality of persona profiles. The electronic device (1901) may select the first persona profile corresponding to at least one of an identification value of the first application, an identification value of the counterpart, an identification value of the electronic device (1901), account information of the user of the electronic device (1901), or a current situation of the electronic device. According to one embodiment, priorities and / or weights may be set for the identification value of the first application, the identification value of the counterpart, the identification value of the electronic device (1901), account information of the user of the electronic device (1901), and the current situation of the electronic device. In this case, the first persona profile may be selected from among the plurality of persona profiles in consideration of the priorities and / or weights for the identification value of the first application, the identification value of the counterpart, the identification value of the electronic device (1901), account information of the user of the electronic device (1901), and the current situation of the electronic device.

[0171] In one embodiment, the electronic device (1901) may select a portion of a plurality of persona profiles and display a list of the selected portion of persona profiles. In this case, the electronic device (1901) may receive a user input selecting a first persona profile from the list of selected portion of persona profiles.

[0172] FIG. 9 is a diagram schematically illustrating information considered by an electronic device in selecting a persona profile according to one embodiment.

[0173] Referring to FIG. 9, the electronic device (1901) may select a persona profile by considering at least one of an application (91), a service (90), a user account (93), an identification value (94) of the electronic device, or a current situation (95) of the electronic device (1901). For example, the electronic device (1901) may select a persona profile by considering a priority or weight of at least one of the application (91), a service (92), a user account (93), an identification value (94) of the electronic device, or a current situation (95) of the electronic device (1901).

[0174] According to one embodiment, when a persona profile corresponding to an electronic device (1901) and a persona profile corresponding to an application conflict, a persona profile may be selected based on the priority of the persona profile corresponding to the electronic device (1901) and the priority of the persona profile corresponding to the application.

[0175] According to one embodiment, when a persona profile corresponding to an electronic device (1901) is selected, an application recommended for prohibition may be set. In this case, when execution of an application recommended for prohibition is requested, the electronic device (1901) may display a guidance message and not execute the application.

[0176] In one embodiment, content that is recommended to be prohibited from being shared may be configured based on a selected persona profile, in a specific application, or in a specific situation, on the electronic device (1901). In this case, when uploading or transmitting content for which sharing is recommended is requested, the electronic device (1901) may display a notification message indicating that sharing of the content is prohibited and may restrict the upload or transmission of the content.

[0177] FIG. 10A is a flowchart illustrating a method for an electronic device, according to one embodiment, to obtain recommended content by selecting a generative artificial intelligence model corresponding to a persona profile from among multiple generative artificial intelligence models. Operations 1010 to 1025 of FIG. 10A may correspond to operation 240 of FIG. 2 .

[0178] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0179] In operation 1010, according to one embodiment, the electronic device (1901) may identify a generative artificial intelligence model corresponding to a first persona profile from among a plurality of generative artificial intelligence models. According to one embodiment, when each of the plurality of generative artificial intelligence models supports a different application, each of the plurality of generative artificial intelligence models supports generation of a different type of recommended content, or each of the plurality of generative artificial intelligence models supports a different service, the electronic device (1901) may identify a generative artificial intelligence model corresponding to the first persona profile from among the plurality of generative artificial intelligence models. For example, when there are a plurality of generative artificial intelligence models corresponding to at least one of a type of application, a type of recommended content, or a type of service, the electronic device (1901) may select a generative artificial intelligence model to be used for generating recommended content from among the plurality of generative artificial intelligence models in consideration of the type of the first application, the type of recommended content to be generated, and / or the type of service provided by the first application. For example, the electronic device (1901) may select a first generative artificial intelligence model when entering a message into a first application, and may select a second generative artificial intelligence model when entering an image into a second application. For example, the electronic device (1901) may select a third generative artificial intelligence model when entering a message through a first service, and may select a fourth generative artificial intelligence model when entering an image through a second service. However, examples of selecting a generative artificial intelligence model are not limited thereto.

[0180] In operation 1015, according to one embodiment, the electronic device (1901) may generate an input prompt for generating recommended content. The electronic device (1901) may generate an input prompt including information about a first persona profile, a type of recommended content, a method for generating recommended content, and / or information to be used for generating recommended content. The input prompt may be generated in the form of a script including sentences in a natural language format. The input prompt may be generated in a format supported by the identified generative artificial intelligence model.

[0181] For example, when content (e.g., a message) is input into the first application by a user's content input request, the electronic device (1901) may generate an input prompt such as "Modify the input message to generate a recommended message, input message: "I have to cancel my appointment today. I'm sorry.", and reflect the persona profile to be input next when generating the recommended content, input persona profile: "Female in her 20s living in Seoul, friendly tone of voice, prefers pastel colors, Tone and Manner type Pink, preferred object: cat."

[0182] For example, when a request for generating recommended content (e.g., a message) is input for a first application, the electronic device (1901) may generate an input prompt such as “Generate a recommended message for canceling an appointment with coworkers, reflect the persona profile to be input next when generating the recommended content, input persona profile: “20s office worker living in Seoul, polite but cold speech, prefers neutral colors.”

[0183] However, examples of input prompts generated are not limited to this.

[0184] In operation 1020, according to one embodiment, the electronic device (1901) may provide the generated input prompt to the generative artificial intelligence model. According to one embodiment, if the generative artificial intelligence model is a model within the electronic device (1901), the electronic device (1901) may input the input prompt to the generative artificial intelligence model. According to one embodiment, if the generative artificial intelligence model is a model within another electronic device (e.g., a server), the electronic device (1901) may transmit the input prompt to the other electronic device.

[0185] In operation 1025, according to one embodiment, the electronic device (1901) may obtain recommended content output from a generative artificial intelligence model. According to one embodiment, if the generative artificial intelligence model is a model within the electronic device (1901), the electronic device (1901) may obtain recommended content output from the generative artificial intelligence model. According to one embodiment, if the generative artificial intelligence model is a model within another electronic device (e.g., a server), the electronic device (1901) may receive recommended content output from the generative artificial intelligence model from the other electronic device.

[0186] In one embodiment, the recommended content may be content modified by a generative AI model from content input into the first application. In one embodiment, the recommended content may be text, and the recommended text may be generated by modifying the input text by the generative AI model. For example, if an input prompt inputted into the generative AI model is "Modify the input message to generate a recommended message, input message: "I have to cancel my appointment today. Sorry.", and when generating the recommended content, reflect the persona profile to be input next, input persona profile: "Female in her 20s living in Seoul, friendly speech, prefers pastel colors, Tone and Manner type: Pink, preferred object: cat," then the content modified by the generative AI model may be a message modified by reflecting the attributes included in the input persona profile. For example, the input message "I have to cancel my appointment today. Sorry." may be converted by the generative AI model to "I... can't meet you today. Sorry. Cutie, will you forgive me? It can be modified to “I’ll buy you coffee.”

[0187] In one embodiment, the recommended content may be an image. In this case, the recommended content may be generated by modifying the input image using a generative AI model. For example, the recommended image may be generated by applying an effect to emphasize a specific subject within the input image. For example, the recommended image may be generated by deleting a specific subject within the input image. For example, the recommended image may be generated by cropping a necessary portion of the input image. For example, the recommended image may be generated by changing the resolution of at least a portion of the input image.

[0188] In one embodiment, if the user of the electronic device (1901) or a specific person is included as a subject in a photo (or video), the electronic device (1901) may decide to generate recommended content by modifying the photo. Furthermore, the electronic device (1901) may include a photo including the user as a subject in the input prompt, and the recommended content may be generated by modifying the photo using a generative artificial intelligence model.

[0189] In one embodiment, the recommended content may be audio. In this case, the recommended content may be generated by modifying the input audio using a generative AI model. For example, if an input prompt containing an audio file is provided to a generative AI model, the recommended content may be generated by the generative AI model by cropping the necessary portion of the audio.

[0190] In one embodiment, the recommended content may be content generated by a generative AI model, reflecting the conditions for generating recommended content included in the input prompt. For example, the recommended content may include content from another electronic device (e.g., a server) (e.g., pre-stored content linked to the user's account) or content modified by the generative AI model (2050). For example, the recommended content may be content generated by the generative AI model modifying input content by considering the context of the conversation.

[0191] FIG. 10B is a flowchart illustrating a method for an electronic device, according to one embodiment, to obtain recommended content using a generative artificial intelligence model corresponding to multiple persona profiles. Operations 1050 to 1060 of FIG. 10B may correspond to operation 240 of FIG. 2 .

[0192] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0193] In operation 1050, according to one embodiment, the electronic device (1901) may generate an input prompt including information of a first persona profile for generating recommended content. The electronic device (1901) may generate an input prompt including information about the first persona profile, a type of recommended content, a method for generating recommended content, and / or information to be used for generating recommended content. The input prompt may be generated in the form of a script including sentences in a natural language format. The input prompt may be generated in a format supported by a generative artificial intelligence model.

[0194] For example, when content (e.g., a message) is input into the first application by a user's content input request, the electronic device (1901) may generate an input prompt such as "Modify the input message to generate a recommended message, input message: "I have to cancel my appointment today. I'm sorry.", and reflect the persona profile to be input next when generating the recommended content, input persona profile: "Female in her 20s living in Seoul, friendly tone of voice, prefers pastel colors, Tone and Manner type Pink, preferred object: cat."

[0195] For example, when a request for generating recommended content (e.g., a message) is input for a first application, the electronic device (1901) may generate an input prompt such as “Generate a recommended message for canceling an appointment with coworkers, reflect the persona profile to be input next when generating the recommended content, input persona profile: “20s office worker living in Seoul, polite but cold speech, prefers neutral colors.”

[0196] However, examples of generated input prompts are not limited thereto. In one embodiment, the input prompt may not include detailed information of the first persona profile, but may only include information for obtaining detailed information of the first persona profile. The detailed information of the first persona profile may include detailed items and values ​​corresponding to the detailed items within the first persona profile. For example, the input prompt may include an identification value of the first persona profile or link information for downloading detailed information of the first persona. In this case, the generative artificial intelligence model may obtain detailed information of the first persona profile by using the link information for downloading detailed information of the first persona profile included in the input prompt or the identification value of the first persona profile.

[0197] In one embodiment, a generative artificial intelligence model may be included in an electronic device (1901). In this case, the electronic device (1901) may receive link information for downloading detailed information of a first persona profile or an identification value of the persona profile from another electronic device (e.g., a server). Thereafter, the generative artificial intelligence model of the electronic device (1901) may obtain detailed information of the first persona profile using the link information for downloading detailed information of the first persona profile or the identification value of the first persona profile.

[0198] In one embodiment, the generative AI model may be included in another electronic device (e.g., a server). In this case, the electronic device (1901) may provide link information for downloading detailed information of the first persona profile or an identification value of the persona profile to the other electronic device (e.g., the server). Thereafter, the generative AI model of the other electronic device (e.g., the server) may use the link information for downloading detailed information of the first persona profile or the identification value of the first persona profile to obtain detailed information of the first persona profile.

[0199] In one embodiment, the input prompt may not include information for identifying a persona profile, but may include information regarding whether a function for providing recommended content based on a persona profile is activated. In this case, the generative artificial intelligence model of the electronic device (1901) and / or another electronic device (e.g., a server) may identify, through the input prompt, that the function for providing recommended content based on a persona profile is activated, determine which persona profile to apply, and obtain and utilize detailed information about the persona profile pre-stored in the electronic device (1901) and / or another electronic device (e.g., a server).

[0200] In operation 1055, according to one embodiment, the electronic device (1901) may provide an input prompt to the generative artificial intelligence model. According to one embodiment, if the generative artificial intelligence model is a generative artificial intelligence model that provides an integrated artificial intelligence service capable of providing recommended content for multiple types of applications, multiple types of recommended content, and multiple types of services, the electronic device (1901) may utilize the generative artificial intelligence model that provides the integrated artificial intelligence service. In this case, the operation of the electronic device (1901) selecting the generative artificial intelligence model from among the multiple generative artificial intelligence models may be omitted.

[0201] In operation 1060, according to one embodiment, the electronic device (1901) may obtain recommended content output from a generative artificial intelligence model.

[0202] According to one embodiment, when the generative artificial intelligence model is a model within the electronic device (1901), the electronic device (1901) can input an input prompt to the generative artificial intelligence model and obtain recommended content output from the generative artificial intelligence model. According to one embodiment, when the generative artificial intelligence model is a model within another electronic device (e.g., a server), the electronic device (1901) can transmit the input prompt to the other electronic device and receive recommended content output from the generative artificial intelligence model from the other electronic device.

[0203] In one embodiment, the recommended content may be content modified by a generative artificial intelligence model from content input into the first application. Alternatively, in one embodiment, the recommended content may be content generated by a generative artificial intelligence model, reflecting the conditions for generating recommended content included in the input prompt.

[0204] FIG. 11 is a diagram illustrating a generative artificial intelligence model of an electronic device and a generative artificial intelligence model of a server according to one embodiment.

[0205] According to one embodiment, the electronic device (1901) may include a generative artificial intelligence model (2050), and the server (3000) may include a generative artificial intelligence model (3050).

[0206] According to one embodiment, the generative artificial intelligence model (2050) of the electronic device (1901) may be a generative artificial intelligence model capable of providing recommended content for a small number of applications, a small number of recommended contents, and a small number of services, and the generative artificial intelligence model (3050) of the server (3000) may be an integrated generative artificial intelligence model capable of providing recommended content for a large number of applications, a large number of recommended contents, and a large number of services.

[0207] In this case, according to one embodiment, the electronic device (1901) may preferentially use the generative artificial intelligence model (2050) of the electronic device (1901) and may auxiliaryly use the generative artificial intelligence model (3050) of the server (3000). According to one embodiment, the electronic device (1901) may preferentially use the generative artificial intelligence model (3050) of the server (3000) and may auxiliaryly use the generative artificial intelligence model (2050) of the electronic device (1901). According to one embodiment, the electronic device (1901) may use both the generative artificial intelligence model (2050) of the electronic device (1901) and the generative artificial intelligence model (3050) of the server (3000).

[0208] For example, when the electronic device (1901) receives a message input request for a message application, the electronic device (1901) may determine whether a function of generating a recommendation message input into the message application based on a first persona profile is supported by the generative artificial intelligence model (2050) of the electronic device (1901). If the function is supported by the generative artificial intelligence model (2050) of the electronic device (1901), the electronic device (1901) may generate a recommendation message using the generative artificial intelligence model (2050) of the electronic device (1901). Alternatively, if the function is not supported by the generative artificial intelligence model (2050) of the electronic device (1901), the electronic device (1901) may obtain a recommendation message using the generative artificial intelligence model (3050) of the server (3000).

[0209] According to one embodiment, the electronic device (1901) may select and use at least one of the generative artificial intelligence model (2050) of the electronic device (1901) or the generative artificial intelligence model (3050) of the server (3000), for example, taking into account the real-time nature of the service provided by the application and the amount of computation for generating recommended content.

[0210] For example, a device (e.g., electronic device (1901), server (3000)) or a generative artificial intelligence model to be used to generate recommended content can be determined by considering at least one of the type of service provided by the application, the type of recommended content, the operating mode of the electronic device (1901), or the communication status of the electronic device (1901).

[0211] For example, in an application providing an instant messaging service, if the content to be recommended is text, a generative artificial intelligence model (2050) of an electronic device (1901) can be used to generate the recommended content.

[0212] For example, in an application providing an email service, if the content to be recommended is email content, the generative artificial intelligence model (3050) of the server (3000) can be used to generate the recommended content.

[0213] For example, in an application providing an email service, if the content to be recommended is email content and the operating mode of the electronic device (1901) is a data saving mode or the electronic device (1901) uses a cellular network, the generative artificial intelligence model (2050) of the electronic device (1901) can be used to generate the recommended content.

[0214] For example, in an application providing an email service, if the content to be recommended is email content and the operating mode of the electronic device (1901) is a low power mode or the electronic device (1901) uses a WiFi network, the generative artificial intelligence model (3050) of the server (3000) can be used to generate the recommended content.

[0215] FIG. 12 is a diagram illustrating an example in which an electronic device according to one embodiment provides a recommendation message based on a first persona profile.

[0216] Referring to FIG. 12 , an electronic device (1901) may receive a message composition request (120) to cancel an appointment with friends via a messaging application. For example, the electronic device may receive a message entered by a user to cancel an appointment with friends, or may receive user input requesting the creation of a message to cancel an appointment with friends. For example, the electronic device (1901) may receive a text input requesting the creation of a message to cancel an appointment with friends. Alternatively, for example, the electronic device (1901) may receive a text input requesting the creation of a message to cancel an appointment with friends.

[0217] Thereafter, the electronic device (1901) may select a first persona profile corresponding to the message application from among a plurality of persona profiles set in the electronic device (1901). In this case, the electronic device (1901) may select the first persona profile by additionally considering at least one counterpart of the message application, an account of the user of the electronic device (1901), and / or a current situation of the electronic device (1901). For example, the electronic device (1901) may identify identifiers of counterparts participating in a chat window of the message application, a service ID of the user of the electronic device (1901), and a current situation of the electronic device (1901), and select a first persona profile corresponding to the message application, the identified counterparts, the service ID of the user, and the current situation of the electronic device (1901). According to one embodiment, when multiple counterparts are identified and multiple persona profiles corresponding to the multiple counterparts are competing, the electronic device (1901) may select at least one of the multiple persona profiles based on the priorities of the multiple persona profiles. In this case, the priorities of the multiple personas may be preset. For example, when a persona profile corresponding to a counterpart with whom one engages in casual conversation is competing with a persona profile corresponding to a counterpart with whom one engages in formal conversation, the persona profile corresponding to the counterpart with whom one engages in formal conversation may have a higher priority.

[0218] Thereafter, the electronic device (1901) may generate an input prompt (122) including information of the first persona profile. The electronic device (1901) may generate the input prompt (122) in the form of a natural language script including, for example, information regarding the first persona profile, the type of recommended content, and the method for generating the recommended content. The input prompt (122) may include information regarding the user's previous messages and the other party's previous messages displayed in the chat window of the electronic device (1901).

[0219] Thereafter, the electronic device (1901) may provide an input prompt (122) to the generative artificial intelligence model (2050) and display a recommendation message (124) output from the generative artificial intelligence model (2050) on the execution screen of the message application. The recommendation message (124) may be a message reflecting attributes included in the first persona profile.

[0220] For example, a recommendation message may include multiple types of content that reflect the attributes included in the first persona profile. For example, the recommendation message may be a message that combines at least one of text, emoticons, photos, or images that reflect the attributes included in the first persona profile.

[0221] FIG. 13 is a diagram illustrating an example in which an electronic device according to one embodiment provides a recommendation message based on a second persona profile.

[0222] Referring to FIG. 13, an electronic device (1901) may receive a message composition request (130) to cancel an appointment with coworkers via a messaging application. For example, the electronic device may receive a message entered by a user to cancel an appointment with coworkers, or may receive user input requesting the creation of a message to cancel an appointment with coworkers.

[0223] Thereafter, the electronic device (1901) may select a second persona profile corresponding to the message application from among a plurality of persona profiles set in the electronic device (1901). In this case, the electronic device (1901) may select the second persona profile by additionally considering at least one of at least one counterpart of the message application, an account of the user of the electronic device (1901), and / or a current situation of the electronic device (1901). For example, the electronic device (1901) may identify identifiers of counterparts participating in a chat window of the message application, a service ID of the user of the electronic device (1901), and a current situation of the electronic device (1901), and select a second persona profile corresponding to the message application, the identified counterparts, the service ID of the user, and the current situation of the electronic device (1901).

[0224] Thereafter, the electronic device (1901) may generate an input prompt (132) including information of the second persona profile. The electronic device (1901) may generate the input prompt (132) in the form of a natural language script including, for example, information regarding the second persona profile, the type of recommended content, and the method for generating the recommended content. The input prompt (132) may include information regarding the user's previous messages and the other party's previous messages displayed in the chat window of the electronic device (1901).

[0225] Thereafter, the electronic device (1901) may provide an input prompt (132) to the generative artificial intelligence model (2050) and display a recommendation message (134) output from the generative artificial intelligence model (2050) on the execution screen of the message application. The recommendation message (134) may be a message reflecting attributes included in the second persona profile.

[0226] FIG. 14 is a diagram illustrating an example in which an electronic device according to one embodiment provides a recommended image based on a first persona profile.

[0227] Referring to FIG. 14, an electronic device (1901) may receive a user input (140) requesting input of a cat image. According to one embodiment, the electronic device (1901) may receive a user input for selecting an image to be input. For example, the electronic device (1901) may receive a user input for selecting a button that provides a function for attaching an image on an execution screen of an application, and display a list of images that can be selected by the user. For example, the application may include, but is not limited to, a message application, a chat application, and a mailing application. In addition, for example, the list of images may include, but is not limited to, images stored in the electronic device (1901), images stored in a server (not shown) under a user's account of the electronic device (1901), and images provided from a server (not shown) that the electronic device (1901) can access. Thereafter, the electronic device (1901) may receive a user input for selecting at least one cat image from the list of images.

[0228] In one embodiment, the electronic device (1901) may receive a user text input requesting input of a cat image. For example, if the user enters the text “Send me a picture of a cat” into an input field of a messaging application, a chat application, or an email application (or if the user selects a function button to attach an image after entering the text), the electronic device (1901) may identify that it has received a user input (140) requesting input of a cat image.

[0229] Alternatively, for example, if a message is received from the other party containing text such as “I want to see pictures of cats” (or if the user presses a function button to attach an image after receiving the message), the electronic device (1901) may identify that it has received user input (140) requesting input of a cat image.

[0230] Thereafter, the electronic device (1901) may select a first persona profile corresponding to the recommended image provision service from among a plurality of persona profiles set in the electronic device (1901). In this case, the electronic device (1901) may select the first persona profile by considering at least one of the type of application into which the image will be input, the account of the user of the electronic device (1901), and / or the current status of the electronic device (1901).

[0231] Thereafter, the electronic device (1901) may generate an input prompt (142) including information of the first persona profile. The electronic device (1901) may generate the input prompt (142) in the form of a natural language script including, for example, information regarding the first persona profile, the type of recommended content, and the method for generating the recommended content. For example, the input prompt (142) may include information regarding operations performed by the application prior to the electronic device (1901) receiving the image input request so that the generative artificial intelligence model can determine why the user inputs (or shares) an image.

[0232] Thereafter, the electronic device (1901) may provide an input prompt (142) to the generative artificial intelligence model (2050) and display a list of recommended images (144) output from the generative artificial intelligence model (2050). The recommended images included in the list of recommended images (144) may be images that reflect attributes included in the first persona profile, and the user may select at least one of the recommended images in the list of recommended images (144). The recommended image may include, but is not limited to, at least one of an image stored in the electronic device (1901), an image of another electronic device (e.g., a server), or an image generated (or modified) by the generative artificial intelligence model (2050). According to one embodiment, at least some of the images in the list of recommended images (144) may be determined based on a selection history of recommended images related to recommended images selected by the user in the past. In addition, at least some of the images in the list of recommended images (144) may be arranged in a predetermined order according to a probability-based priority determined by the generative artificial intelligence model. According to one embodiment, the electronic device (1901) displays a list of recommended images (144), and may distinguish between a list of recommended images selected by the user in the past and a list of recommended images recommended by a generative artificial intelligence model.

[0233] FIG. 15 is a diagram illustrating an example in which an electronic device according to one embodiment provides a recommended shooting composition for shooting a camera application based on a first persona profile.

[0234] Referring to FIG. 15, an electronic device (1901) may execute a camera application. The electronic device (1901) may identify that a photographing service function based on a persona profile is activated and select a first persona profile corresponding to the camera application. The electronic device (1901) may select the first persona profile by considering at least one of an identification value of the camera application, an account of a user of the electronic device (1901), and / or a current status of the electronic device (1901).

[0235] Thereafter, the electronic device (1901) may generate an input prompt (152) including information about the first persona profile. The electronic device (1901) may generate the input prompt (152) in the form of a natural language script that includes information about the first persona profile and requests that a recommended shooting composition for the camera be provided, for example.

[0236] Thereafter, the electronic device (1901) may provide an input prompt (152) to the generative artificial intelligence model (2050, 3050) and receive information about a recommended composition output from the generative artificial intelligence model (2050, 3050). For example, the electronic device (1901) may display information (154) guiding the user to take a picture according to the recommended composition on the preview screen based on the information about the recommended composition. For example, the information (154) guiding the picture taking according to the recommended composition may include a phrase guiding the picture taking, such as “Zoom in 3 times and take a picture in grayscale.” In addition, for example, the information (154) guiding the picture taking according to the recommended composition may include a thumbnail (155) of the picture taken when the picture is taken according to the guide.

[0237] Additionally, the electronic device (1901) may provide an input prompt (152) to the generative artificial intelligence model (2050, 3050) and suggest recommended shooting settings output from the generative artificial intelligence model (2050, 3050). For example, the electronic device (1901) may display an object (e.g., a button, an icon) on the preview screen to change the shooting settings of the camera to recommended shooting settings for capturing an image that matches the first persona profile.

[0238] Additionally, the electronic device (1901) may provide an input prompt (152) to the generative artificial intelligence model (2050, 3050) and receive information about a recommended subject output from the generative artificial intelligence model (2050, 3050). For example, the electronic device (1901) may display a message recommending the shooting of a recommended subject on the preview screen.

[0239] FIG. 16 is a flowchart illustrating a method for an electronic device to modify a persona profile based on feedback information from another user, according to one embodiment. Operation 1600 of FIG. 16 may be performed after operation 250 of FIG. 2 , but is not limited thereto.

[0240] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0241] In operation 1600, according to one embodiment, the electronic device (1901) may collect feedback information from other users. The electronic device (1901) may collect feedback information from other users regarding recommended content generated by a generative artificial intelligence model and input into the application. Additionally, the electronic device (1901) may collect feedback information from other users regarding content directly input into the application by the user.

[0242] For example, feedback information from other users may include reply messages from other users to messages entered in a messaging application and / or comments from other users to images posted in a social networking service application. For example, feedback information from other users may include the number of times other users pressed the 'like' button and / or the 'dislike' button for the entered recommended content and / or the entered content. For example, feedback information from other users may include the number of times other users saved and / or shared the entered recommended content and / or the entered content. For example, feedback information from other users may include information regarding an increase or decrease in the number of followers and / or subscribers of the user after the user's post including the entered recommended content and / or the entered content was posted.

[0243] In operation 1610, according to one embodiment, the electronic device (1901) may modify a persona profile. The electronic device (1901) may modify the persona profile of a user of the electronic device (1901) based on input recommended content and / or feedback information from other users regarding the input content. The electronic device (1901) may identify an application from which feedback information from other users has been extracted and select a persona profile corresponding to the application.

[0244] According to one embodiment, the electronic device (1901) can modify a persona profile by analyzing feedback information from other users. The electronic device (1901) can analyze other users' preferences for content input through the application and / or recommended content using the feedback information, and modify the persona profile based on the analyzed preference information.

[0245] In one embodiment, the electronic device (1901) can modify a persona profile by analyzing information related to another user who provided feedback information. In this case, the electronic device (1901) can obtain the persona profile of another user who provided the feedback information based on the service account of the other user. For example, the electronic device (1901) can modify the persona profile of the user of the electronic device (1901) by comparing the persona profile of the other user who provided the feedback information with the persona profile of the user of the electronic device (1901). In this case, the other user who provided the feedback information may be, for example, a famous entertainer and / or a celebrity of a social networking service (SNS).

[0246] For example, the electronic device (1901) can modify the persona profile of the user of the electronic device (1901) by comparing the content input by another user who provided feedback information with the content input by the user of the electronic device (1901). In this case, the electronic device (1901) can obtain the content input by the other user into the other user's account based on the service account of the other user who provided the feedback information. The electronic device (1901) can modify the persona profile of the user so that recommended content similar to the other user's content can be generated based on the similarity between the other user's content and the user's content. The other user who provided the feedback information may be, for example, a famous entertainer and / or a celebrity of an SNS service.

[0247] In one embodiment, the electronic device (1901) can modify a persona profile by changing at least some of the items included in the persona profile. For example, the electronic device (1901) can change the items in the persona profile from "20s" and "prefers pastel colors" to "30s" and "prefers neutral colors."

[0248] According to one embodiment, the electronic device (1901) can modify a persona profile by adjusting the level of a detail item included in the persona profile. The level of a detail item included in the persona profile may be a value indicating the degree of preference for the detail item within the profile. For example, the electronic device (1901) can increase the level of "preference for pastel colors" among the items within the persona profile.

[0249] According to one embodiment, the electronic device (1901) can display a modified persona profile and modify the modified persona profile based on user input for editing the modified persona.

[0250] In operation 1620, according to one embodiment, the electronic device (1901) may provide recommended content based on the modified persona profile. The electronic device (1901) may generate an input prompt including information about the modified persona profile and provide the input prompt to a generative artificial intelligence model, thereby obtaining recommended content based on the modified persona profile.

[0251] In FIG. 16, the persona profile is described as being modified by the electronic device (1901), but is not limited thereto. The persona profile may be modified by the processor of the electronic device (1901) and / or the processor of another electronic device (e.g., a server).

[0252] FIG. 17 is a diagram illustrating an example of an electronic device according to one embodiment modifying a persona profile and content based on feedback from other users on content posted by a user.

[0253] Referring to FIG. 17, at identification numbers 170, 171, and 172, the electronic device (1901) can display the user's content on the bulletin board of the SNS application and display other users' feedback on the content.

[0254] In one embodiment, as shown in identification number 173, the electronic device (1901) may collect feedback information from other users. For example, the electronic device (1901) may collect preference information (e.g., likes), text, and images (e.g., icons, emojis) included in comments made by other users regarding the user's content. The electronic device (1901) may analyze the feedback information from other users and use the analysis results to modify the persona profile.

[0255] In one embodiment, as shown in identification number 174, the electronic device (1901) can compare the content of another user with the user's content. In this case, the other user may be, for example, a famous celebrity and / or a celebrity from a social networking service (SNS). The electronic device (1901) can collect content posted by the other user through his or her social networking service (SNS) account and compare the collected content of the other user with the user's content. The electronic device (1901) can use the comparison results to modify the user's persona profile.

[0256] According to one embodiment of the invention, as illustrated in identification number 175, the electronic device (1901) may modify the user's persona profile. The electronic device (1901) may modify the user's persona profile based on feedback from other users and / or comparisons between the user's content and other users' content. For example, the electronic device (1901) may modify the user's persona profile based on content posted by the user that is highly preferred by other users. For example, the electronic device (1901) may modify the user's persona profile so that recommended content similar to the other user's content is recommended. In this case, the electronic device (1901) may display the modified persona profile and further modify the modified persona profile based on user input for modifying the modified persona profile.

[0257] According to one embodiment of the invention, as illustrated in FIG. 176, the electronic device (1901) may suggest modifications to content through a user interface for editing content. For example, the electronic device (1901) may display a user interface for editing content of the identification number 170. The electronic device (1901) may display recommended content based on the modified persona profile through the user interface. The recommended content may be generated by modifying the content of the identification number 170. The electronic device (1901) may modify the content based on user input regarding the recommended content through the user interface.

[0258] According to one embodiment of the invention, as illustrated in identification number 177, the electronic device (1901) can post modified content on a bulletin board. Accordingly, modified content based on the modified persona profile can be entered into the bulletin board via the user's SNS application. In this case, the modified content may be content modified from previously posted content, and the modified content may be posted in place of the previously posted content.

[0259] While the above description describes content posted by a user as being modified, the present invention is not limited thereto. In one embodiment, not only the content itself posted by the user, but also the cover image of the content (e.g., the thumbnail image of video content), the description and / or tags of the content, or the public scope of the content may be modified. Furthermore, when video content is modified, the content may be modified by deleting some of the multiple frames included in the video. Furthermore, when image content is modified, some objects included in the image may be deleted and / or modified. Furthermore, the modified content may be posted in place of the content prior to modification.

[0260] In FIG. 17, modification of the persona profile and content is described as being modified by the electronic device (1901), but is not limited thereto. Modification of the persona profile and modification of the content may be performed by the processor of the electronic device (1901) and / or the processor of another electronic device (e.g., a server).

[0261] According to one embodiment, a method for providing recommended content based on a persona profile by an electronic device (1901) may be provided, including: an operation of setting a plurality of persona profiles including a first persona profile corresponding to a first application and a second persona profile corresponding to a second application (e.g., 210); an operation of receiving a request for inputting content related to the first application (e.g., 220); an operation of identifying the first persona profile among the plurality of persona profiles in response to the request (e.g., 230); an operation of obtaining recommended content output from an artificial intelligence model based on the first persona profile (e.g., 240); and an operation of providing the obtained recommended content through a user interface (e.g., 250).

[0262] According to one embodiment, the operation of identifying the first persona profile may include an operation of identifying at least one counterparty to be provided with the recommended content through the first application (e.g., 820); and an operation of selecting, from among the plurality of persona profiles, the first persona profile corresponding to the first application and the identified at least one counterparty (e.g., 850).

[0263] According to one embodiment, the operation of identifying the first persona profile may include an operation of identifying the electronic device executing the first application (e.g., 830); and an operation of selecting the first persona profile corresponding to the first application and the electronic device from among the plurality of persona profiles (e.g., 850).

[0264] According to one embodiment, the operation of setting the plurality of persona profiles may include an operation of obtaining information related to a usage history of content used through the first application (e.g., 310); and an operation of setting the first persona profile corresponding to the first application based on the information related to the usage history of the content (e.g., 330).

[0265] According to one embodiment, the method may further include an operation of obtaining account information of a user of the electronic device (e.g., 320); and an operation of setting the first persona profile corresponding to the first application and the account information of the user.

[0266] According to one embodiment, the operation of setting the first persona profile may include an operation of obtaining the first persona profile output from another artificial intelligence model by applying information related to the usage history of the content to another artificial intelligence model trained for generating the persona profile.

[0267] According to one embodiment, the operation of obtaining the recommended content output from the artificial intelligence model based on the first persona profile may include the operation of generating an input prompt including information about the first persona profile and information about a method for generating the recommended content (e.g., 1015); and the operation of obtaining the recommended content output from the artificial intelligence model by providing the generated input prompt to the artificial intelligence model (e.g., 1020) (e.g., 1025).

[0268] In one embodiment, the request for input of said content may include input of text requesting input of said content.

[0269] In one embodiment, the recommended content may be output from the artificial intelligence model based on the text and the first persona profile.

[0270] In one embodiment, the recommended content may be generated by modifying at least a portion of content stored in connection with the user's account.

[0271] In one embodiment, the content includes an image, and the recommended content may include an image from which one or more objects have been removed.

[0272] According to one embodiment, the operation of obtaining the recommended content may further include the operation of providing settings for taking a photo corresponding to the first persona profile as the recommended content.

[0273] According to one embodiment, the method may further include an operation of transmitting the recommended content, an operation of obtaining feedback information from another user regarding the transmitted recommended content (e.g., 1600); and an operation of modifying the first persona profile based on the feedback information (e.g., 1610).

[0274] According to one embodiment, the method may further include transmitting the recommended content to a server.

[0275] In one embodiment, the method may include an operation of modifying the first persona profile by comparing the recommended content with other content shared by the other user.

[0276] Figure 18 is a block diagram of an electronic device according to one embodiment.

[0277] Referring to FIG. 18, the electronic device (1901) may include a display module (1960), a communication module (1990), a processor (1920), and a memory (1930). The memory (1930) may include a persona profile setting module (2010), a context information collection module (2020), a persona profile selection module (2030), a recommended content generation module (2040), a generative artificial intelligence model (2050), and a persona profile modification module (2060).

[0278] The display module (1960) can visually provide information to an external party (e.g., a user) of the electronic device (1901). The display module (1960) 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 (1960) 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.

[0279] The communication module (1990) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (1901) and an external electronic device (e.g., electronic device (1902), electronic device (1904), or server (1908)), and the performance of communication through the established communication channel. The communication module (1990) may operate independently from the processor (1920) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication.

[0280] The processor (1920) can control the operations of the electronic device (1901) of FIGS. 1 to 17 by executing instructions stored in the memory (1930). For example, the processor (1920) can correspond to multiple processors that collectively perform multiple operations by dividing them among the processors.

[0281] The memory (1930) may store various data used by at least one component of the electronic device (1901). The data may include, for example, input data or output data for software (e.g., a program) and commands related thereto. According to one embodiment, the persona profile setting module (2010) may be executed by the processor (1920) to cause the electronic device (1901) to perform operations for setting a persona profile. The context information collection module (2020) may be executed by the processor (1920) to cause the electronic device (1901) to perform operations for setting a persona profile and collecting context information used for selecting a persona profile. The persona profile selection module (2030) may be executed by the processor (1920) to cause the electronic device (1901) to perform operations of FIGS. 1 to 17 for selecting at least one persona profile from among a plurality of persona profiles. The recommended content generation module (2040) may be executed by the processor (1920) to cause the electronic device (1901) to perform the operations of FIGS. 1 to 17 to generate recommended content by generating an input prompt and applying the input prompt to a generative artificial intelligence model (2050). The persona profile modification module (2060) may be executed by the processor (1920) to cause the electronic device (1901) to perform the operations of FIGS. 1 to 17 to modify a persona profile.

[0282] However, the persona profile setting module (2010), the situation information collection module (2020), the persona profile selection module (2030), the recommended content generation module (2040), the generative artificial intelligence model (2050), and the persona profile modification module (2060) included in the memory (1930) are merely examples. According to one embodiment, the memory (1930) may include various software modules, and the various software modules may be executed by the processor (1920) so that the electronic device (1901) may perform the operations of FIGS. 1 to 17.

[0283] FIG. 19 is a block diagram of an electronic device (1901) within a network environment (1900) according to various embodiments. Referring to FIG. 19 , in the network environment (1900), the electronic device (1901) may communicate with the electronic device (1902) via a first network (1998) (e.g., a short-range wireless communication network), or may communicate with the electronic device (1904) or a server (1908) via a second network (1999) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (1901) may communicate with the electronic device (1904) via the server (1908). According to one embodiment, the electronic device (1901) may include a processor (1920), a memory (1930), an input module (1950), an audio output module (1955), a display module (1960), an audio module (1970), a sensor module (1976), an interface (1977), a connection terminal (1978), a haptic module (1979), a camera module (1980), a power management module (1988), a battery (1989), a communication module (1990), a subscriber identification module (1996), or an antenna module (1997). In some embodiments, the electronic device (1901) may omit at least one of these components (e.g., the connection terminal (1978)), or may have one or more other components added. In some embodiments, some of these components (e.g., sensor module (1976), camera module (1980), or antenna module (1997)) may be integrated into a single component (e.g., display module (1960)).

[0284] The processor (1920) may control at least one other component (e.g., a hardware or software component) of the electronic device (1901) connected to the processor (1920) by executing, for example, software (e.g., a program (1940)), and may perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (1920) may store commands or data received from other components (e.g., a sensor module (1976) or a communication module (1990)) in a volatile memory (1932), process the commands or data stored in the volatile memory (1932), and store result data in a non-volatile memory (1934). According to one embodiment, the processor (1920) may include a main processor (1921) (e.g., a central processing unit or an application processor) or a secondary processor (1923) (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 (1921). For example, when the electronic device (1901) includes the main processor (1921) and the secondary processor (1923), the secondary processor (1923) may be configured to use less power than the main processor (1921) or to be specialized for a given function. The secondary processor (1923) may be implemented separately from the main processor (1921) or as a part thereof.

[0285] The auxiliary processor (1923) may control at least a portion of functions or states associated with at least one component (e.g., a display module (1960), a sensor module (1976), or a communication module (1990)) of the electronic device (1901), for example, on behalf of the main processor (1921) while the main processor (1921) is in an inactive (e.g., sleep) state, or together with the main processor (1921) while the main processor (1921) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (1923) (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 (1980) or a communication module (1990)). In one embodiment, the auxiliary processor (1923) (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 (1901) where the artificial intelligence is performed, or can be performed through a separate server (e.g., server (1908)). 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.

[0286] The memory (1930) can store various data used by at least one component (e.g., the processor (1920) or the sensor module (1976)) of the electronic device (1901). The data can include, for example, software (e.g., the program (1940)) and input data or output data for commands related thereto. The memory (1930) can include volatile memory (1932) or non-volatile memory (1934).

[0287] The program (1940) may be stored as software in memory (1930) and may include, for example, an operating system (1942), middleware (1944), or an application (1946).

[0288] The input module (1950) can receive commands or data to be used in a component of the electronic device (1901) (e.g., a processor (1920)) from an external source (e.g., a user) of the electronic device (1901). The input module (1950) can include, for example, a microphone, a mouse, a keyboard, keys (e.g., buttons), or a digital pen (e.g., a stylus pen).

[0289] The audio output module (1955) can output audio signals to the outside of the electronic device (1901). The audio output module (1955) 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.

[0290] The display module (1960) can visually provide information to an external party (e.g., a user) of the electronic device (1901). The display module (1960) 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 (1960) 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.

[0291] The audio module (1970) can convert sound into an electrical signal, or vice versa. According to one embodiment, the audio module (1970) can acquire sound through the input module (1950), output sound through the sound output module (1955), or an external electronic device (e.g., electronic device (1902)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (1901).

[0292] The sensor module (1976) can detect the operating status (e.g., power or temperature) of the electronic device (1901) 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 (1976) 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.

[0293] The interface (1977) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (1901) with an external electronic device (e.g., the electronic device (1902)). In one embodiment, the interface (1977) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0294] The connection terminal (1978) may include a connector through which the electronic device (1901) may be physically connected to an external electronic device (e.g., the electronic device (1902)). In one embodiment, the connection terminal (1978) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0295] A haptic module (1979) 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 (1979) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0296] The camera module (1980) can capture still images and moving images. In one embodiment, the camera module (1980) may include one or more lenses, image sensors, image signal processors, or flashes.

[0297] The power management module (1988) can manage the power supplied to the electronic device (1901). According to one embodiment, the power management module (1988) can be implemented as at least a part of, for example, a power management integrated circuit (PMIC).

[0298] A battery (1989) may power at least one component of the electronic device (1901). In one embodiment, the battery (1989) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0299] The communication module (1990) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (1901) and an external electronic device (e.g., electronic device (1902), electronic device (1904), or server (1908)), and the performance of communication through the established communication channel. The communication module (1990) may operate independently from the processor (1920) (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 (1990) may include a wireless communication module (1992) (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 (1994) (e.g., a local area network (LAN) communication module, or a power line communication module). Any of these communication modules may communicate with an external electronic device (1904) via a first network (1998) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (1999) (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 may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (1992) may use subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (1996) to identify or authenticate the electronic device (1901) within a communication network such as the first network (1998) or the second network (1999).

[0300] The wireless communication module (1992) 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 (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (1992) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (1992) 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 (1992) may support various requirements specified in the electronic device (1901), an external electronic device (e.g., the electronic device (1904)), or a network system (e.g., the second network (1999)). According to one embodiment, the wireless communication module (1992) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0301] The antenna module (1997) 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 (1997) 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 (1997) 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 (1998) or the second network (1999), may be selected from the plurality of antennas by, for example, the communication module (1990). A signal or power may be transmitted or received between the communication module (1990) 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 (1997).

[0302] According to various embodiments, the antenna module (1997) 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.

[0303] 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)).

[0304] According to one embodiment, commands or data may be transmitted or received between the electronic device (1901) and an external electronic device (1904) via a server (1908) connected to a second network (1999). Each of the external electronic devices (1902 or 1904) may be the same or a different type of device as the electronic device (1901). According to one embodiment, all or part of the operations executed in the electronic device (1901) may be executed in one or more of the external electronic devices (1902, 1904, or 1908). For example, when the electronic device (1901) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (1901) 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 additional functions or services related to the request, and transmit the result of the execution to the electronic device (1901). The electronic device (1901) 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 (1901) may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (1904) may include an Internet of Things (IoT) device. The server (1908) may be an intelligent server utilizing machine learning and / or a neural network.According to one embodiment, an external electronic device (1904) or server (1908) may be included within the second network (1999). The electronic device (1901) 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.

[0305] FIG. 20 is a diagram illustrating a system including a generative artificial intelligence model according to one embodiment.

[0306] Referring to FIG. 20, the User Query / Response Interface (2310) can receive user input. The user input may be in the form of natural language, images, and / or videos. Additionally, context information may also be transmitted when the user input is transmitted. Context information may include various additional information at the time of user input. For example, information about the application the user is currently using or the user's location information. Furthermore, the user input may be in a mixed form of the aforementioned 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 (2310) can output the results of a generative artificial intelligence system 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 Interface can output the results of a generative artificial intelligence system 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.

[0307] The AI ​​framework (2320) can receive user input and coordinate and control each component necessary to perform the user's intention based on the user's query.

[0308] User input received from the User Query / Response Interface (2310) can be transmitted to the Prompt design component (2321). The Prompt design component (2321) can be used to generate a prompt suitable for inputting the user input into a Large Language Model (LLM) or a large multimodal model (LMM). The Prompt design component (2321) 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 (2321) can access a knowledge component (e.g., knowledge repositories (2340)) 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.

[0309] The API / Plug-in management component (2323) can communicate with external information when there is a request for additional information when passing user input as input to a generative model. The API / Plug-in management component (2323) can establish a channel for communicating with the outside of the AI ​​Interface through the API, and can enable access to various data sources (e.g., knowledge repositories (2340)) through the established channel. In addition, if the API / Plug-in management component (2323) needs to perform an action that performs the user input as a final result rather than an intermediate result in an application or service, it can request the action to the application / service component (2330) through the API. Information obtained from an external source can be used to generate a prompt in the prompt design component (2321) together with the user input, or can be passed as input to the generative model.

[0310] The Refiner component (e.g., the output modification component (2325)) can fine-tune the output from a generative model. For example, the Refiner component can verify that the content generated by the LLM and / or LMM is not irrelevant, biased, or harmful. Furthermore, the Refiner component can determine the degree to which the output matches the user's desired result and, if necessary, perform additional processing. The Refiner component can also configure and provide hints to the user to avoid undesirable output.

[0311] Generative AI Model (2350) can generally refer to an artificial intelligence neural network that creates new types of data based on user input information. Generative AI Model (2350) can 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 autoencoder (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 statistically output the most appropriate output value based on input values, and representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, there is also an LMM that can recognize various types of data input, such as text, images, and voice, and generate new data corresponding to them.

[0312] According to one embodiment, the electronic device (1901) of FIGS. 1 to 19 may be configured to include at least a portion of the User Query / Response Interface (2310), the AI ​​framework (2320), the application / service component (2330), the knowledge repositories (2340), or the Generative AI Model (2350) of FIG. 20. According to one embodiment, at least a portion of the User Query / Response Interface (2310), the AI ​​framework (2320), the application / service component (2330), the knowledge repositories (2340), or the Generative AI Model (2350) of FIG. 20 may be included in another electronic device (e.g., a server).

[0313] An electronic device (e.g., 1901) according to one embodiment includes a display (e.g., 1960); a memory (1930) for storing instructions; and one or more processors (1920); wherein the instructions, when executed by the one or more processors, cause the electronic device to: set a plurality of persona profiles including a first persona profile corresponding to a first application and a second persona profile corresponding to a second application; receive a request for input of content related to the first application; identify the first persona profile among the plurality of persona profiles in response to the request; obtain recommended content based on the first persona profile; and display the obtained recommended content through a user interface of the first application.

[0314] According to one embodiment, the instructions, when executed by the one or more processors, may cause the electronic device to: identify at least one counterparty to be provided with the recommended content through the first application, and select, from among the plurality of persona profiles, the first persona profile corresponding to the at least one identified counterparty.

[0315] According to one embodiment, the instructions, when executed by the one or more processors, may cause the electronic device to: identify the electronic device running the first application, and select at least one of the first persona profiles, from among the plurality of persona profiles, that corresponds to the first application or the electronic device.

[0316] According to one embodiment, the instructions, when executed by the one or more processors, may cause the electronic device to: obtain information related to a usage history of content used through the first application, obtain account information of a user of the electronic device, and set the first persona profile corresponding to the first application and the account information of the user based on the information related to the usage history of the content.

[0317] According to one embodiment, the instructions, when executed by the one or more processors, may cause the electronic device to: generate at least one input prompt comprising a first data set for the first persona profile and a second data set for the second persona profile, and request an artificial intelligence-based computing device to model the first user persona corresponding to the first data set and the second user persona corresponding to the second data set.

[0318] According to one embodiment, the instructions, when executed by the one or more processors, may cause the electronic device to: obtain a first persona profile output from the artificial intelligence model by applying information related to the usage history of the content to an artificial intelligence model trained for generating a persona profile.

[0319] According to one embodiment, the instructions, when executed by the one or more processors, may cause the electronic device to: select the first persona profile from among a persona profile corresponding to the electronic device and a persona profile corresponding to the first application, according to a preset priority.

[0320] According to one embodiment, the instructions, when executed by the one or more processors, may cause the electronic device to: generate an input prompt including information about the first persona profile and information about a method for generating the recommended content, and provide the generated input prompt to an artificial intelligence model, thereby obtaining the recommended content output from the generative artificial intelligence model.

[0321] In one embodiment, the request for input of the content includes input of text requesting input of the content, and the recommended content can be output from the artificial intelligence model based on the text and the first persona profile.

[0322] In one embodiment, the recommended content may be generated by modifying at least a portion of content stored in connection with the user's account.

[0323] According to one embodiment, the instructions, when executed by the one or more processors, may cause the electronic device to: obtain feedback information of other users regarding the displayed recommended content, and modify the first persona profile based on the feedback information.

[0324] According to one embodiment, a computer-readable recording medium having recorded thereon instructions for executing a method on a computer, the method comprising: setting a plurality of persona profiles including a first persona profile and a second persona profile; receiving a request for inputting content related to the first application; identifying the first persona profile among the plurality of persona profiles in response to the request; obtaining recommended content output from an artificial intelligence model based on the first persona profile; and displaying the obtained recommended content through a user interface of the first application may be provided.

[0325] 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.

[0326] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0327] 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).

[0328] Various embodiments of the present document may be implemented as software (e.g., a program (1940)) including one or more instructions stored in a storage medium (e.g., an internal memory (1936) or an external memory (1938)) readable by a machine (e.g., an electronic device (1901)). For example, a processor (e.g., a processor (1920)) of the machine (e.g., an electronic device (1901)) 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.

[0329] 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 product 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) through 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.

[0330] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. A method for an electronic device to provide recommended content based on a persona profile, An action of setting a plurality of persona profiles including a first persona profile corresponding to a first application and a second persona profile corresponding to a second application; An action for receiving a request for input of content related to the first application; An action of identifying a first persona profile from among the plurality of persona profiles in response to the request; An operation of obtaining recommended content related to the request from an artificial intelligence model based on the first persona profile; and An action of providing the above recommended content through a user interface; A method comprising:

2. In paragraph 1, The action of setting the above multiple persona profiles is: An operation for obtaining information related to the usage history of content used through the first application; and An action of setting the first persona profile corresponding to the first application based on information related to the usage history of the content; A method comprising:

3. In paragraph 2, The action of setting the above first persona profile is: An operation of obtaining a first persona profile output from another artificial intelligence model by applying information related to the usage history of the above content to another artificial intelligence model trained for generating a persona profile; A method comprising:

4. In any one of paragraphs 1 to 3, The operation of obtaining the recommended content output from the artificial intelligence model based on the first persona profile is as follows: An action to generate an input prompt including information about the first persona profile and information about a method for generating the recommended content; and An operation of obtaining the recommended content output from the artificial intelligence model by providing the generated input prompt to the artificial intelligence model; A method comprising:

5. In any one of paragraphs 1 to 4, A request for input of said content includes input of text requesting input of said content, A method wherein the above recommended content is output from the artificial intelligence model based on the above text and the first persona profile.

6. In any one of paragraphs 1 to 5, A method wherein the above recommended content is generated by modifying at least a portion of the content stored in connection with the user's account.

7. In paragraph 1, The above content includes images, A method wherein the above recommended content includes an image from which one or more objects have been removed.

8. In paragraph 1, The action of obtaining the above recommended content is as follows: An action providing settings for taking a photo corresponding to the first persona profile as the above recommended content; A method comprising:

9. In any one of paragraphs 1 to 8, Further comprising an action of transmitting the above recommended content, An action to obtain feedback information from other users on the recommended content transmitted above; and An action of modifying the first persona profile based on the above feedback information; A method comprising:

10. In paragraph 1, An action of comparing said recommended content with other content shared by said other users; and An action of modifying the first persona profile based on the comparison result; A method comprising:

11. In electronic devices, display; memory for storing commands; and One or more processors; Including, The above instructions, when executed by the one or more processors, cause the electronic device to: Receives a request related to the transmission of content through the first application, Among a plurality of persona profiles including a first persona profile and a second persona profile, the content is provided through a user interface according to the first persona profile corresponding to the first application, An electronic device that transmits the content based on user input received through the user interface.

12. In paragraph 11, The above instructions, when executed by the one or more processors, cause the electronic device to: Identifying at least one counterparty to be provided with the content through the first application; An electronic device that selects the first persona profile among the plurality of persona profiles based on at least one identified counterpart.

13. In paragraph 11, The above instructions, when executed by the one or more processors, cause the electronic device to: An electronic device that generates at least one input prompt comprising a first data set for the first persona profile and a second data set for the second persona profile, and requests an artificial intelligence model to model the first user persona corresponding to the first data set and the second user persona corresponding to the second data set.

14. In any one of paragraphs 11 to 13, The above instructions, when executed by the one or more processors, cause the electronic device to: Generate an input prompt that includes information about the first persona profile and information about how to create the content; An electronic device that obtains the content output from the artificial intelligence model by providing the generated input prompt to the artificial intelligence model.

15. In paragraph 14, A request relating to the transmission of said content includes the input of text requesting the input of said content, An electronic device, wherein the content is output from the artificial intelligence model based on the text and the first persona profile.

Images