Electronic device and control method therefor

Abstract

The electronic device comprises a memory storing instructions, a communication circuit connected to an AI server, and at least one processor including processing circuitry. The instructions, when executed individually or collectively by the at least one processor, instruct the electronic device to: upon receiving a first user input requesting an AI model for controlling the electronic device, obtain a user profile related to a usage history of the electronic device, generate a first prompt on the basis of the user profile, transmit the first prompt and the user profile to the AI server via the communication circuit, and receive a first AI model corresponding to the first prompt from the AI server via the communication circuit; and upon receiving a second user input requesting an AI model for controlling a target folder, obtain target folder information related to at least one application included in the target folder, generate a second prompt on the basis of the target folder information, transmit the second prompt and the target folder information to the AI server via the communication circuit, receive a second AI model corresponding to the second prompt from the AI server via the communication circuit, and store the first AI model and the second AI model in the memory.

Description

Electronic device and control method thereof

[0001] The present disclosure relates to an electronic device and a method for controlling the same, and more specifically, to an electronic device and a method for controlling the same that provide a service related to an application to a user using an AI model.

[0002] Terminal devices may include an Artificial Intelligence (AI) assistant function. An AI assistant can be a function that understands and processes tasks through natural language conversation with the user. AI assistants support daily tasks such as schedule management, information retrieval, and note-taking, and can provide customized information based on the user's commands or queries.

[0003] AI assistants can be trained to provide personalized services. However, since the training takes place on the provider's server, identical AI training may occur. If an AI assistant trained with the same data is supplied and installed on multiple devices, there may be limitations in providing personalized services, even if the input data differs for each user.

[0004] AI assistants can have an AI personality (or persona). If the same training data is used during the process of learning the AI ​​personality, there may be limitations in providing personalized services.

[0005] The present disclosure is designed to improve upon the aforementioned problem, and the purpose of the present disclosure is to provide an electronic device and a method for controlling the same that provide information related to a folder selected by a user using a plurality of AI models learned in different ways.

[0006] According to one embodiment, the electronic device includes at least one processor comprising a memory for storing instructions, a communication circuit connected to an AI server, and a processing circuitry, and when the instructions are executed individually or collectively by the at least one processor, when the electronic device receives a first user input requesting an AI model for controlling the electronic device, the electronic device acquires a user profile related to the usage history of the electronic device and generates a first prompt based on the user profile, transmits the first prompt and the user profile to the AI ​​server through the communication circuit, and receives a first AI model corresponding to the first prompt from the AI ​​server through the communication circuit, and when the second user input requesting an AI model for controlling a target folder is received, the electronic device acquires target folder information related to at least one application included in the target folder and generates a second prompt based on the target folder information, transmits the second prompt and the target folder information to the AI ​​server through the communication circuit, and receives a second AI model corresponding to the second prompt through the communication circuit. Receive from the AI ​​server and store the first AI model and the second AI model in the memory.

[0007] The above user profile may include at least one of name, account, age, gender, region, language, preferred category, application usage history, and feedback data.

[0008] The above target folder information includes application information for at least one application included in the above target folder, and the application information may include at least one of the name, representative image, and main function of the application.

[0009] The first AI model is a model trained to control the electronic device with a first AI personality, and the second AI model may be a model trained to control operations related to the target folder with a second AI personality different from the first AI personality.

[0010] The electronic device includes a display, and when the instructions are executed individually or collectively by the at least one processor, the electronic device may, upon receiving a third user input selecting the target folder, acquire target user data corresponding to the target folder among the user profiles, generate a third prompt requesting guidance for the target folder based on the target user data using the second AI model, transmit the third prompt and the target user data to the AI ​​server through the communication circuit, receive guide information corresponding to the third prompt through the communication circuit, generate a guide UI based on the guide information, and control the display to display the guide UI.

[0011] When the above instructions are executed individually or collectively by the at least one processor, the electronic device may, upon receiving a fourth user input for a search, use the second AI model to identify a search term based on the fourth user input, obtain a first target command and a second target command requesting a response to the search term, transmit the first target command to a first application server via the communication circuit, receive first application data corresponding to the first target command from the first application server via the communication circuit, transmit the second target command to a second application server via the communication circuit, receive second application data corresponding to the second target command from the second application server via the communication circuit, and store the first application data and the second application data in the memory.

[0012] When the above instructions are executed individually or collectively by the at least one processor, the electronic device may use the second AI model to generate a fourth prompt requesting a result for the fourth user input, transmit the fourth prompt, the first application data, and the second application data to the AI ​​server through the communication circuit, receive result information corresponding to the fourth prompt from the AI ​​server through the communication circuit, generate a first result UI based on the result information, and control the display to display the first result UI.

[0013] When the above instructions are executed individually or collectively by the at least one processor, the electronic device may use the first AI model to obtain a second result UI based on the result information and the user profile, and control the display to display the second result UI.

[0014] The first result UI above includes an image representing the second AI model, and the second result UI above may include an image representing the first AI model.

[0015] The above AI server may include a Large Language Model (LM).

[0016] According to one embodiment, a method for controlling an electronic device connected to an AI server comprises, when a first user input requesting an AI model for controlling the electronic device is received, obtaining a user profile related to the usage history of the electronic device; generating a first prompt based on the user profile; transmitting the first prompt and the user profile to the AI ​​server; receiving a first AI model corresponding to the first prompt from the AI ​​server; when a second user input requesting an AI model for controlling a target folder is received, obtaining target folder information related to at least one application included in the target folder; generating a second prompt based on the target folder information; transmitting the second prompt and the target folder information to the AI ​​server; receiving a second AI model corresponding to the second prompt from the AI ​​server; and storing the first AI model and the second AI model in the electronic device.

[0017] The above user profile may include at least one of name, account, age, gender, region, language, preferred category, application usage history, and feedback data.

[0018] The above target folder information includes application information for at least one application included in the above target folder, and the application information may include at least one of the name, representative image, and main function of the application.

[0019] The first AI model is a model trained to control the electronic device with a first AI personality, and the second AI model may be a model trained to control operations related to the target folder with a second AI personality different from the first AI personality.

[0020] The above control method may include the steps of: receiving a third user input selecting the target folder, obtaining target user data corresponding to the target folder among the user profiles; using the second AI model, generating a third prompt requesting a guide for the target folder based on the target user data; transmitting the third prompt and the target user data to the AI ​​server; receiving guide information corresponding to the third prompt; generating a guide UI based on the guide information; and displaying the guide UI.

[0021] The above control method may include the steps of: identifying a search term based on the fourth user input using the second AI model when a fourth user input for search is received; obtaining a first target command and a second target command requesting a response to the search term; transmitting the first target command to a first application server; receiving first application data corresponding to the first target command from the first application server; transmitting the second target command to a second application server; receiving second application data corresponding to the second target command from the second application server; and storing the first application data and the second application data in the electronic device.

[0022] The above control method may include the steps of: generating a fourth prompt requesting a result for the fourth user input using the second AI model; transmitting the fourth prompt, the first application data, and the second application data to the AI ​​server; receiving result information corresponding to the fourth prompt from the AI ​​server; generating a first result UI based on the result information; and displaying the first result UI.

[0023] The above control method may include the step of obtaining a second result UI based on the result information and the user profile using the first AI model, and the step of displaying the second result UI.

[0024] The first result UI above includes an image representing the second AI model, and the second result UI above may include an image representing the first AI model.

[0025] The above AI server may include a Large Language Model (LM).

[0026] FIG. 1 is a diagram illustrating the operation of displaying a message using AI according to one embodiment.

[0027] FIG. 2 is a block diagram illustrating an electronic device according to one embodiment.

[0028] FIG. 3 is a block diagram illustrating the specific configuration of the electronic device of FIG. 2 according to one embodiment.

[0029] FIG. 4 is a drawing for illustrating an AI management module according to one embodiment.

[0030] FIG. 5 is a drawing for explaining a plurality of modules existing in a memory area according to one embodiment.

[0031] FIG. 6 is a diagram illustrating an AI persona according to one embodiment.

[0032] FIG. 7 is a diagram illustrating the operation of acquiring a first AI model and a second AI model according to one embodiment.

[0033] FIG. 8 is a diagram illustrating the operation of setting a first AI model according to one embodiment.

[0034] FIG. 9 is a drawing for illustrating an AI server according to one embodiment.

[0035] FIG. 10 is a diagram illustrating the operation of analyzing application information according to one embodiment.

[0036] FIG. 11 is a drawing for explaining a first prompt according to one embodiment.

[0037] FIG. 12 is a drawing for explaining a second prompt according to one embodiment.

[0038] FIG. 13 is a drawing for explaining a guide UI according to one embodiment.

[0039] FIG. 14 is a drawing for explaining a third prompt according to one embodiment.

[0040] FIG. 15 is a drawing for explaining a method of displaying a guide UI according to one embodiment.

[0041] FIG. 16 is a diagram illustrating an operation of providing a guide UI using a plurality of AI models according to one embodiment.

[0042] FIG. 17 is a diagram illustrating the operation of receiving user typing input according to one embodiment.

[0043] FIG. 18 is a diagram illustrating the operation of receiving voice input from a user according to one embodiment.

[0044] FIG. 19 is a diagram illustrating the operation of receiving image input from a user according to one embodiment.

[0045] FIG. 20 is a drawing for explaining application data according to one embodiment.

[0046] FIG. 21 is a diagram illustrating the operation of acquiring application data from a plurality of servers according to one embodiment.

[0047] FIG. 22 is a drawing for explaining an application server according to one embodiment.

[0048] FIG. 23 is a diagram illustrating an operation for providing a result UI according to one embodiment.

[0049] FIG. 24 is a drawing for explaining a fourth prompt according to one embodiment.

[0050] FIG. 25 is a drawing for explaining a result UI according to one embodiment.

[0051] FIG. 26 is a diagram illustrating subsequent operations on search results according to one embodiment.

[0052] FIG. 27 is a diagram illustrating an operation for providing a result UI according to one embodiment.

[0053] FIG. 28 is a drawing for explaining the fifth prompt according to one embodiment.

[0054] FIG. 29 is a drawing for explaining a result UI that is additionally displayed according to one embodiment.

[0055] FIG. 30 is a drawing for illustrating a screen corresponding to additional user input according to one embodiment.

[0056] FIG. 31 is a drawing for illustrating a screen corresponding to additional user input according to one embodiment.

[0057] FIG. 32 is a drawing for illustrating a screen corresponding to additional user input according to one embodiment.

[0058] FIG. 33 is a drawing for explaining a method of controlling an electronic device according to one embodiment.

[0059] Figure 34 is a diagram illustrating a prompt input into an AI engine.

[0060] Figure 35 is a diagram illustrating a result UI corresponding to a prompt.

[0061] Figure 36 is a diagram illustrating a prompt input into an AI engine.

[0062] Figure 37 is a diagram illustrating a result UI corresponding to a prompt.

[0063] Figure 38 is a diagram illustrating a prompt input into an AI engine.

[0064] Figure 39 is a diagram illustrating a result UI corresponding to a prompt.

[0065] FIG. 40 is a diagram illustrating a prompt input to the first AI model.

[0066] Figure 41 is a diagram illustrating a prompt input into an AI engine.

[0067] Figure 42 is a diagram illustrating a result UI corresponding to a prompt.

[0068] Figure 43 is a diagram illustrating a prompt input into an AI engine.

[0069] Figure 44 is a diagram illustrating a result UI corresponding to a prompt.

[0070] Figure 45 is a diagram illustrating a prompt input into an AI engine.

[0071] Figure 46 is a diagram illustrating a result UI corresponding to a prompt.

[0072] Figure 47 is a diagram illustrating a prompt input into an AI engine.

[0073] Figure 48 is a diagram illustrating a result UI corresponding to a prompt.

[0074] Figure 49 is a diagram illustrating a prompt input into an AI engine.

[0075] Figure 50 is a diagram illustrating a result UI corresponding to a prompt.

[0076] Figure 51 is a diagram illustrating a function for recognizing user voice.

[0077] Figure 52 is a diagram illustrating a speech recognition module.

[0078] Figure 53 is a diagram illustrating the result UI.

[0079] Figure 54 is a diagram illustrating a result UI corresponding to a prompt.

[0080] Figure 55 is a diagram illustrating a result UI corresponding to a prompt.

[0081] Figure 56 is a diagram illustrating a result UI corresponding to a prompt.

[0082] Figure 57 is a diagram illustrating a result UI corresponding to a prompt.

[0083] Figure 58 is a diagram illustrating a result UI corresponding to a prompt.

[0084] Figure 59 is a diagram illustrating a result UI corresponding to a prompt.

[0085] Figure 60 is a diagram illustrating a result UI corresponding to a prompt.

[0086] The present disclosure will be described in detail below with reference to the attached drawings.

[0087] The terms used in the embodiments of this disclosure have been selected to be as widely used as possible, taking into account their functions within this disclosure; however, these terms may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant explanatory section of this disclosure. Therefore, terms used in this disclosure should be defined not merely by their names, but based on their meanings and the overall content of this disclosure.

[0088] In this specification, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of such features (e.g., numerical values, functions, operations, or components such as parts) and do not exclude the presence of additional features.

[0089] The expression "at least one of A or / and B" should be understood as representing either "A" or "B" or "A and B".

[0090] Expressions such as "first," "second," "first," or "second" used in this specification may modify various components regardless of order and / or importance, and are used only to distinguish one component from another and do not limit said components.

[0091] Where it is stated that a component (e.g., Component 1) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., Component 2), it should be understood that the component may be directly connected to the other component or connected through the other component (e.g., Component 3).

[0092] The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "consisting of" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0093] In the present disclosure, a "module" or "part" performs at least one function or operation and may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of "modules" or a plurality of "parts" may be integrated into at least one module and implemented by at least one processor, except for a "module" or "part" that needs to be implemented in specific hardware.

[0094] In this specification, the term "user" may refer to a person using an electronic device or a device using an electronic device (e.g., an artificial intelligence electronic device).

[0095] An embodiment of the present disclosure will be described in more detail below with reference to the attached drawings.

[0096] FIG. 1 is a diagram illustrating the operation of displaying a message using AI according to one embodiment.

[0097] Referring to FIG. 1, the electronic device (100) can provide a screen (1) for a folder. When a user selects a specific folder, the electronic device (100) can provide a screen (1) for the selected folder. The provided screen (1) may include UIs (A, B, C, D, E, F, G) for a plurality of applications.

[0098] While providing the screen (1), the electronic device (100) may display a guide UI (2). The guide UI (2) may be a UI generated based on a selected folder. Through the guide UI (2), the electronic device (100) can easily make the user aware of the available services.

[0099] FIG. 2 is a block diagram illustrating an electronic device according to one embodiment.

[0100] The electronic device (100) may include at least one processor (110) comprising a memory (120) for storing instructions, a communication circuit (160) connected to an AI server (e.g., the AI ​​server (200) of FIG. 4), and a processing circuitry.

[0101] The AI ​​server (200) may include a Large Language Model (LM).

[0102] At least one processor (110) can obtain a user profile related to the usage history of the electronic device (100) when a first user input requesting an AI model to control the electronic device (100) is received.

[0103] At least one processor (110) can generate a first prompt based on a user profile. A description of the first prompt is given in FIG. 11.

[0104] A user profile may include at least one of name, account, age, gender, region, language, preferred category, application usage history, and feedback data.

[0105] At least one processor (110) can transmit a first prompt and a user profile to an AI server (200) through a communication circuit (160).

[0106] At least one processor (110) can receive a first AI model (11) corresponding to a first prompt from an AI server (200) through a communication circuit (160).

[0107] At least one processor (110) can obtain target folder information related to at least one application included in the target folder when a second user input requesting an AI model to control the target folder is received.

[0108] Target folder information may include application information for at least one application contained in the target folder. The application information may include at least one of the application's name, representative image, and main function.

[0109] At least one processor (110) can generate a second prompt based on target folder information. A description of the second prompt is provided in FIG. 12.

[0110] At least one processor (110) can transmit second prompt and target folder information to the AI ​​server (200) through the communication circuit (160).

[0111] At least one processor (110) can receive a second AI model (12) corresponding to a second prompt from an AI server (200) through a communication circuit (160).

[0112] At least one processor (110) can store the first AI model (11) and the second AI model (12) in memory (120).

[0113] The first AI model (11) may be a model trained to control the electronic device (100) with the first AI personality. The second AI model (12) may be a model trained to control operations related to the target folder with a second AI personality different from the first AI personality.

[0114] The first AI model (11) and the second AI model (12) can be replaced with expressions such as an AI assistant, an AI chatbot program, etc.

[0115] The first AI model (11) may be an AI model trained to have the first persona tendency.

[0116] The second AI model (12) may be an AI model trained to have a second persona tendency.

[0117] Descriptions related to the first AI model (11) and the second AI model (12) are described in FIGS. 6 and FIGS. 7.

[0118] The electronic device (100) may include a display (140). When at least one processor (110) receives a third user input selecting a target folder, it may obtain target user data corresponding to the target folder among user profiles.

[0119] At least one processor (110) can use the second AI model (12) to generate a third prompt requesting guidance for a target folder based on target user data. A description of the third prompt is provided in FIG. 14.

[0120] At least one processor (110) can transmit third prompt and target user data to the AI ​​server (200) through the communication circuit (160).

[0121] At least one processor (110) can receive guide information corresponding to a third prompt through a communication circuit (160). At least one processor (110) can generate a guide UI based on the guide information. At least one processor (110) can control a display (140) to display the guide UI. The operation of displaying the guide UI is described in FIGS. 13, 15, and 16. The guide UI may correspond to the UI (1511, 1521) of FIG. 15.

[0122] When a fourth user input for a search is received, at least one processor (110) can identify a search term based on the fourth user input using a second AI model (12). A method for receiving the fourth user input is described in FIGS. 17 to 19.

[0123] At least one processor (110) can obtain a first target command and a second target command requesting a response to a search term.

[0124] At least one processor (110) can transmit a first target command to a first application server (e.g., the first application server (310) of FIG. 20) through a communication circuit (160).

[0125] At least one processor (110) can receive first application data corresponding to a first target command from the first application server (310) through a communication circuit (160).

[0126] At least one processor (110) can transmit a second target command to a second application server (e.g., the second application server (320) of FIG. 21) through a communication circuit (160).

[0127] At least one processor (110) can receive second application data corresponding to a second target command from a second application server (320) through a communication circuit (160).

[0128] At least one processor (110) can store first application data and second application data in memory (120). An explanation related to this is described in FIG. 21.

[0129] At least one processor (110) can use the second AI model (12) to generate a fourth prompt requesting a result for the fourth user input. A description of the fourth prompt is provided in FIG. 24.

[0130] At least one processor (110) can transmit a fourth prompt, first application data, and second application data to an AI server (200) through a communication circuit (160). At least one processor (110) can receive result information corresponding to the fourth prompt from the AI ​​server (200) through the communication circuit (160).

[0131] At least one processor (110) can generate a first result UI based on result information. At least one processor (110) can control a display (140) to display the first result UI. An operation to display the first result UI is described in FIGS. 23 and 25.

[0132] At least one processor (110) can obtain a second result UI based on result information and a user profile using the first AI model (11). At least one processor (110) can control a display (140) to display the second result UI. An operation to display the second result UI is described in FIG. 26.

[0133] The first result UI may include an image representing the second AI model (12). The second result UI may include an image representing the first AI model (11).

[0134] The first result UI can correspond to the screen (2500) of FIG. 25.

[0135] The second result UI can correspond to the screen (2910) of FIG. 29.

[0136] An image representing the second AI model (12) may correspond to the UI (2512) of FIG. 25.

[0137] An image representing the first AI model (11) may correspond to the UI (2911) of FIG. 29.

[0138] In the description above and the description below, the electronic device (100) is described as being connected to the AI ​​server (200) using a communication circuit (160). However, according to other embodiments, at least one operation (or function) performed by the AI ​​server (200) may be performed on-device within the electronic device (100). The electronic device (100) may store an AI engine included in the AI ​​server (200). When the electronic device (100) performs the function of the AI ​​server in an on-device format, the AI ​​server (200) may be described as an AI engine. The communication circuit (160) may include an internal communication circuit of the electronic device (100).

[0139] FIG. 3 is a block diagram illustrating the specific configuration of the electronic device of FIG. 2 according to one embodiment.

[0140] FIG. 3 is a block diagram of an exemplary electronic device (100) capable of performing the operations described in this document.

[0141] Referring to FIG. 3, the electronic device (100) may be one of various forms of electronic devices, such as a notebook (190), smartphones (191) having various form factors (e.g., a bar-type smartphone (191-1), a foldable-type smartphone (191-2), or a sliderable (or rollable)-type smartphone (191-3)), a tablet (192), a cellular phone (not shown), and other similar computing devices (not shown). The components, their relationships, and their functions illustrated in FIG. 3 are illustrative only and are not intended to limit the implementations described or claimed herein. The electronic device (100) may be referred to as a mobile device, a user device, a multifunction device, a portable device, or a server.

[0142] The electronic device (100) may include components comprising at least one processor (110) (hereinafter referred to as processor (110)), at least one memory (120) (hereinafter referred to as memory (120)), at least one display (140) (hereinafter referred to as display (140)), at least one image sensor (150) (hereinafter referred to as image sensor (150)), at least one communication circuit (160) (hereinafter referred to as communication circuit (160)), and / or at least one sensor (170) (hereinafter referred to as sensor (170)). The components are merely exemplary. For example, the electronic device (100) may include other components (e.g., power management integrated circuitry (PMIC), audio processing circuit, antenna, rechargeable battery, or input / output interface). For example, some components may be omitted from the electronic device (100). For example, some components may be integrated into a single component.

[0143] The processor (110) may be implemented as one or more integrated circuit (or circuitry) chips and may perform various data processing operations. The processor (110) may include at least one electrical circuit and may process instructions (or programs, data) stored in memory (120) individually or collectively in a distributed manner. The processor (110) may include a processor assembly comprising one or more processing circuits. The processor (110) may include any processing circuit that is operative to control the performance and operations of one or more components of the electronic device (100) (e.g., memory (120), display (140), image sensor (150), communication circuit (160), and / or sensor (170)). For example, the processor (110) (e.g., application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or chipset). For example, the processor (110) may be implemented with a plurality of cores (or at least one core circuit), a plurality of chips, or a plurality of chipsets. For example, the processor (110) may include one or more processing circuits. For example, the processor (110) may include one or more processing circuits configured to perform the various functions of the present disclosure individually and / or collectively. As an example without limitation, at least a portion of the processor (110) may be included in a first chip of the electronic device (100), and at least another portion of the processor (110) may be included in a second chip of the electronic device (100) different from the first chip of the electronic device (100).

[0144] For example, the processor (110) may include a central processing unit (111), a graphics processing unit (112), a neural processing unit (113), an image signal processor (114), a display controller (115), a memory controller (116), a storage controller (117), a communication processor (118), and / or a sensor interface (119). These components of the processor (110) are merely exemplary. For example, the processor (110) may include other components. For example, some components of the processor (110) may be omitted from the processor (110). For example, some components of the processor (110) may be included as separate components of the electronic device (100) outside of the processor (110). For example, some components of the processor (110) (e.g., memory controller (116)) may be included in other components (e.g., at least part of memory (120), an interface (e.g. available for connection to at least one component of the electronic device (100)), a display (140) and / or an image sensor (150)).

[0145] The processor (110) may cause other components of the electronic device (100) to perform various operations by executing instructions stored in memory (120). The CPU (111) (or central processing circuit) may be configured to control the components of the processor (110) based on the execution of instructions stored in memory (120) (e.g., volatile memory (121) and / or non-volatile memory (122)). The GPU (112) (or graphics processing circuit) may be configured to execute parallel operations (e.g., rendering). The NPU (113) (or neural processing circuit, or AI (artificial intelligence) chip) may be configured to execute operations for an artificial intelligence model (e.g., convolution computation). An ISP (114) (or image signal processing circuit) may be configured to process a raw image acquired through an image sensor (150) into a format suitable for a component within the electronic device (100) or a component of the processor (110). A display controller (115) (or display control circuit, or DPU (display processing unit)) may be configured to process an image acquired from a CPU (111), GPU (112), ISP (114), or memory (120) (e.g., volatile memory (121)) into a format suitable for a display (140). A memory controller (116) (or memory control circuit) may be configured to control reading data from the volatile memory (121) and writing data to the volatile memory (121). A storage controller (117) (or storage control circuit) may be configured to control reading data from the non-volatile memory (122) and writing data to the non-volatile memory (122).The CP (118) (communication processing circuit) may be configured to process data obtained from a component of the processor (110) into a format suitable for transmitting to another electronic device via the communication circuit (160), or to process data obtained from another electronic device via the communication circuit (160) into a format suitable for processing by the component of the processor (110). For example, the communication circuit (160) may include one or more communication circuits. The sensor interface (119) (or sensing data processing circuit, sensor hub) may be configured to process data regarding the state of the electronic device (100) and / or the state around the electronic device (100), obtained through the sensor (170), into a format suitable for the component of the processor (110).

[0146] Memory (120) may include one or more storage media (or one or more storage devices). For example, memory (120) may include a memory assembly comprising one or more storage media. For example, the one or more storage media may include a hard drive, a permanent memory such as flash memory, read-only memory (ROM) (e.g., non-volatile memory (122)), a semi-permanent memory such as random access memory (RAM) (e.g., volatile memory (121)), any other suitable type of storage (or storage assembly), or any combination thereof. Memory (120) may include a cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (100). As an example not limited to, the cache memory may be included within the processor (110). The memory (120) may be fixedly embedded within the electronic device (100) or incorporated into one or more suitable types of components (e.g., a SIM (subscriber identity module) card and / or an SD (secure digital) card) that can be repeatedly inserted into and removed from the electronic device (100).

[0147] For example, memory (120) may store one or more software applications, such as operating system (or system) software applications, firmware software applications, driver software applications, plugin (e.g., add-in, add-on, and / or applet) software applications, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (110). For example, memory (120) may store instructions that can be called by an application programming interface (API). For example, memory (120) may store instructions within a library.

[0148] FIG. 4 is a drawing for illustrating an AI management module according to one embodiment.

[0149] Referring to FIG. 4, the electronic device (100) may include at least one of an AI management module (10), a personal data management module (20), a data collection module (30), a folder management module (40), and an application management module (50).

[0150] The AI ​​management module (10) can store at least one AI model. The AI ​​model may be a model received from the AI ​​server (200). The AI ​​server (200) can generate a specialized AI model based on information transmitted from the AI ​​management module (10).

[0151] The personal data management module (20) can store a user profile. The user profile may include various information about the user of the electronic device (100). The user profile may represent information that stores various information related to the user in a defined format. The electronic device (100) can generate a user profile by analyzing data through a feature analysis model.

[0152] The data collection module (30) can collect multiple data. The data collection module (30) can collect at least one of application data, location data, usage data, phone data, message data, and system data. The data collection module (30) can request application data from the application management module (50). The application management module (50) can transmit application data for a stored application to the data collection module (30).

[0153] The data collection module (30) can transmit the collected data to the personal data management module (20). The personal data management module (20) can analyze the data collected from the data collection module (30) using a feature analysis model. The personal data management module (20) can generate a user profile as a result of the analysis. The personal data management module (20) can store the user profile.

[0154] The feature analysis model included in the personal data management module (20) may be a model learned by the learning platform (400). The learning platform (400) may generate a model that creates a user profile corresponding to the input data based on an algorithm that analyzes features. The learning platform (400) may provide a feature analysis model. The personal data management module (20) may generate a user profile corresponding to the collected data based on the feature analysis model provided by the learning platform (400).

[0155] The personal data management module (20) can transmit the user profile to the AI ​​management module (10). The AI ​​management module (10) can transmit the user profile to the AI ​​server (200). The AI ​​server (200) can provide an AI model based on the user profile. A specific description related to this is provided in FIG. 7.

[0156] The AI ​​management module (10) can store the first AI model (11) and the second AI model (12) received from the AI ​​server (200). The electronic device (100) can control the folder management module (40) or the application management module (50) based on the first AI model (11) and the second AI model (12).

[0157] For example, the first AI model (11) may be a model learned based on a user profile. The first AI model (11) may be a model learned based on at least one of a setting value related to the electronic device (100), information on the usage pattern of the electronic device (100), and a user's preferred topic.

[0158] For example, an electronic device (100) can provide a UI based on events such as folder execution or application execution.

[0159] The folder management module (40) can manage multiple folders (first folder, second folder). Information about at least one application can be stored in one folder. For example, at least one application can be matched (or included) in one folder.

[0160] The application management module (50) can manage multiple applications (first application, second application). The folder management module (40) and the application management module (50) can be interconnected.

[0161] FIG. 5 is a drawing for explaining a plurality of modules existing in a memory area according to one embodiment.

[0162] Referring to FIG. 5, the non-volatile memory (122) may include a general area (122-1) and a security area (122-2).

[0163] The general area (122-1) may include at least one of an application management module (50), a UI providing module (13), a first AI model (11), and a second AI model (12).

[0164] The UI providing module (13) may be a module included in the AI ​​management module (10). The UI providing module (13) may be a module that determines how to provide UI. The UI providing module (13) may determine the method of providing UI to the user. For example, the UI providing module (13) may determine to output image information through a display. For example, the UI providing module (13) may determine to output audio information through a speaker.

[0165] The security area (122-2) may include a personal data management module (20).

[0166] The electronic device (100) can distinguish between a general area (122-1) and a security area (122-2). To control the personal data management module (20) of the security area (122-2), the electronic device (100) may request additional authentication (e.g., biometric authentication, pattern authentication) from the user.

[0167] FIG. 5 corresponds to an embodiment, and modules or models stored in a secure area may be added depending on the user's settings.

[0168] FIG. 6 is a diagram illustrating an AI persona according to one embodiment.

[0169] Referring to FIG. 6, the electronic device (100) can store various artificial intelligence models. Each artificial intelligence model may have an AI personality. An AI personality may represent the personality or behavioral pattern of the AI ​​designed to perform various roles according to the user's needs. An AI personality may be described as a persona or a character. A persona may represent the personality, attitude, or style provided by the AI ​​when interacting with the user. Interaction with the user may represent the action of the AI ​​model providing output data suitable for the user when the user inputs input data into the AI ​​model. A persona may represent the setting value of at least one parameter used by the AI ​​model to generate output data. If the personas are different, at least one parameter used by the AI ​​model may be different, and the output data may also be different.

[0170] The electronic device (100) may acquire a first AI model (11) according to the user's needs. The first AI model (11) may be a model generated (or learned) based on a first persona. The second AI model (12) may be a model generated (or learned) based on a second persona.

[0171] FIG. 7 is a diagram illustrating the operation of acquiring a first AI model and a second AI model according to one embodiment.

[0172] Referring to FIG. 7, the electronic device (100) can be connected to an AI server (200).

[0173] The electronic device (100) can identify whether a first user input for requesting an AI model is received (S705). The first user input may include a command requesting the creation of a representative AI model related to the overall control of the electronic device (100).

[0174] When the first user input is received (S705-Y), the electronic device (100) can obtain a user profile (S710). The user profile may represent information related to the user. The electronic device (100) may generate a user profile based on user information. User information may represent data collected through the data collection module (30) in FIG. 4. The user profile may represent information generated based on a predetermined format.

[0175] The electronic device (100) can generate a first prompt for generating an AI model (S715). The prompt may include information used to generate the AI ​​model. The prompt may include at least one of a condition (or command), a description, or an example. The prompt may be changed according to the user's settings. The prompt may be changed (or updated) based on pre-set information. A description of the first prompt is provided in FIG. 11. The electronic device (100) may transmit the first prompt and the user profile to the AI ​​server (200) (S720).

[0176] The AI ​​server (200) can receive a first prompt and a user profile from the electronic device (100). The AI ​​server (200) can generate a first AI model (11) based on the first prompt and the user profile (S725). The AI ​​server (200) can transmit the first AI model (11) to the electronic device (100).

[0177] The electronic device (100) can receive the first AI model (11) from the AI ​​server (200). The electronic device (100) can store the first AI model (11) in memory (120) (S735). The electronic device (100) can store the first AI model (11) in the AI ​​management module (10).

[0178] The electronic device (100) can identify whether a second user input for requesting an AI model is received (S740). The second user input may include a command requesting the creation of an AI model for a specific purpose (or topic). For example, the second user input may be an input for creating an AI model corresponding to a specific folder. The specific folder may be designated as the target folder.

[0179] When a second user input is received (S740-Y), the electronic device (100) can obtain target folder information corresponding to the second user input (S745). The target folder information may include various information about the folder selected by the user. The target folder information may include information about at least one application included in the folder selected by the user. The information about the application may include at least one of the name of the application, a representative image corresponding to the application, and the main function of the application.

[0180] The electronic device (100) can generate a second prompt for generating an AI model corresponding to a target folder (S750). The electronic device (100) can generate a second prompt for generating an AI model based on the target folder information. A description of the second prompt is provided in FIG. 12. The electronic device (100) can transmit the second prompt and the target folder information to the AI ​​server (200) (S755).

[0181] The AI ​​server (200) can receive a second prompt and target folder information from the electronic device (100). The AI ​​server (200) can generate a second AI model (12) based on the second prompt and target folder information (S760). The AI ​​server (200) can transmit the second AI model (12) to the electronic device (100) (S765). The AI ​​server (200) can identify the main function of the application based on at least one of the application name and application image included in the target folder information. The AI ​​server (200) can generate a second AI model (12) for controlling the main function of the application.

[0182] The electronic device (100) can receive a second AI model (12) from an AI server (200). The electronic device (100) can store the second AI model (12) in memory (120) (S770). The electronic device (100) can store the second AI model (12) in an AI management module (10).

[0183] In FIG. 7, it is described that the first prompt and the user profile are transmitted individually to the AI ​​server (200). According to another embodiment, the first prompt may include a user profile. The electronic device (100) may generate a first prompt including a user profile. The electronic device (100) may transmit the first prompt including a user profile to the AI ​​server (200).

[0184] In FIG. 7, it is described that the second prompt and target folder information are transmitted individually to the AI ​​server (200). According to another embodiment, the second prompt may include target folder information. The electronic device (100) may generate a second prompt including target folder information. The electronic device (100) may transmit the second prompt including target folder information to the AI ​​server (200).

[0185] The electronic device (100) can store a second AI model (12) corresponding to a target folder. The electronic device (100) can use the second AI model (12) when performing a function (or operation) related to the target folder.

[0186] For example, when user input to add a new application to a target folder is received, the electronic device (100) can perform an action related to the new application using the second AI model (12). When executing the new application, the electronic device (100) can use (or apply) the second AI model (12).

[0187] For example, when user input to add a new application to a target folder is received, the electronic device (100) can obtain information about the new application. The information about the new application may include at least one of application data and usage data. The second AI model (12) may be updated based on the information about the new application. The update operation may be performed on the electronic device (100) or the AI ​​server (200).

[0188] When the AI ​​server (200) performs an update operation, the electronic device (100) can transmit information about a new application to the AI ​​server (200). The AI ​​server (200) can update the second AI model (12) based on the information about the new application and transmit the updated second AI model (12) to the electronic device (100). The electronic device (100) can store the updated second AI model (12). When a new application included in the target folder is executed, the electronic device (100) can use the updated second AI model (12).

[0189] FIG. 8 is a diagram illustrating the operation of setting a first AI model according to one embodiment.

[0190] Referring to FIG. 8, the electronic device (100) can display a settings screen (810). The screen (810) may include a UI (811) related to a user account. When user input is received through the UI (811), the electronic device (100) can display a screen (820) related to a user account.

[0191] The screen (820) may be a screen related to an AI persona associated with an AI model. The screen (820) may include a UI (821) for the first AI model (11) and a UI (822) for the second AI model (12).

[0192] The screen (820) may be a screen that is displayed when the first AI model (11) and the second AI model (12) have already been created.

[0193] The UI (821) may include text (821-1) indicating an explanation regarding the use of the first AI model (11). The UI (821) may include an image (821-2) representing the first AI model (11). The UI (821) may include text (821-3) describing the first persona of the first AI model (11).

[0194] The UI (822) may include text (822-1) indicating an explanation regarding the use of the second AI model (12). The UI (822) may include an image (822-2) representing the second AI model (12).

[0195] Images (821-2, 822-2) may be described as avatar images or character images, etc.

[0196] FIG. 9 is a drawing for illustrating an AI server according to one embodiment.

[0197] The AI ​​management module (10), personal data management module (20), data collection module (30), AI server (200), and learning platform (400) of FIG. 9 may correspond to the description of FIG. 4. Redundant descriptions are omitted.

[0198] The AI ​​server (200) may include a first AI engine (210), a second AI engine (220), and a third AI engine (230). The AI ​​engines may return results in response to a user's request. The AI ​​engines may return results based on a prompt.

[0199] The first AI engine (210) may include a Large Language Model (LM). The LLM may represent a language model trained on a large dataset. The LLM may perform various natural language processing tasks such as text generation, translation, summarization, and question answering.

[0200] The second AI engine (220) may include an image generation model. The image generation model may be a model that generates a new image based on input data (text, image, etc.).

[0201] The third AI engine (230) may include a Large Action Model (LAM). The LAM may be an AI model that performs a specific action by learning user behavior (or patterns of user behavior). The LAM may be an AI model that performs a specific task (or action) by using results corresponding to user behavior (e.g., order of operation, target of operation, preference, etc.) as training data. The LAM may represent an AI model that performs a specific action corresponding to user behavior by utilizing natural language processing, reinforcement learning, behavior prediction, etc.

[0202] The AI ​​server (200) can select an AI engine suitable for a request received from the AI ​​management module (10). The AI ​​server (200) can transmit return data back to the electronic device (100) based on the selected AI engine.

[0203] FIG. 10 is a diagram illustrating the operation of analyzing application information according to one embodiment.

[0204] Referring to FIG. 10, the electronic device (100) can acquire application information (S1005). The electronic device (100) can store multiple applications. The electronic device (100) can store application information representing information about multiple applications installed on the electronic device (100) in a memory (120).

[0205] The electronic device (100) can classify applications based on pre-set categories (S1010). The electronic device (100) can classify applications into pre-set categories using application information.

[0206] The electronic device (100) can collect personal data (S1015). The electronic device (100) can collect various data related to user behavior through the data collection module (30) of FIG. 4.

[0207] The electronic device (100) can obtain a user profile by analyzing personal data (S1020). The user profile may be a data unit representing various information related to the user.

[0208] The electronic device (100) can generate a second prompt based on a user profile (S1025). A description of the second prompt is given in FIG. 12.

[0209] The electronic device (100) can acquire a second AI model (12) based on a second prompt (S1030).

[0210] The electronic device (100) can manage applications installed on the electronic device (100) based on the second AI model (12) (S1035). Application management can be performed through the application management module (50) of FIG. 4.

[0211] The electronic device (100) can manage folders that group applications installed on the electronic device (100). Folder management can be performed through the folder management module (40) of FIG. 4. For example, folder management operations may include application management operations.

[0212] FIG. 11 is a drawing for explaining a first prompt according to one embodiment.

[0213] Referring to FIG. 11, the electronic device (100) can generate a first prompt (1100). The first prompt (1100) may include a command to request an AI model to perform an AI assistant function based on a user profile.

[0214] The first prompt (1100) may include information about the user language.

[0215] The first prompt (1100) may include information about the method of providing the answer.

[0216] The first prompt (1100) may include a command requesting the return of a result using various information related to the user.

[0217] The electronic device (100) can transmit a first prompt (1100) and a user profile to an AI engine. The AI ​​engine can generate a first AI model (11) based on the first prompt (1100) and the user profile. The AI ​​engine can transmit (or return) the first AI model (11) to the electronic device (100).

[0218] FIG. 12 is a drawing for explaining a second prompt according to one embodiment.

[0219] Referring to FIG. 12, a second prompt (1200) can be generated. The second prompt (1200) may include a command requesting an AI model to control operations related to the management of a target folder.

[0220] The second prompt (1200) may include a command to collect metadata for multiple applications. The metadata may include application names, icons, descriptions, developer information, etc.

[0221] The second prompt (1200) may include a command to collect user reviews from an application data store. The application data store may represent an external server for receiving applications. The second prompt (1200) may include information indicating a method for obtaining user reviews from the application data store.

[0222] The second prompt (1200) may include a command to perform a preprocessing process on collected information (metadata, user reviews). The preprocessing process may include removing unnecessary symbols and tokenizing.

[0223] The second prompt (1200) may include a command to classify user reviews as positive, negative, or neutral using Natural Language Processing (NLP).

[0224] The second prompt (1200) may include a command to extract topics (or keywords) that are frequently mentioned in user reviews through a topic modeling method.

[0225] The second prompt (1200) may include a command to identify the main functions of an application included in the target folder. The second prompt (1200) may include a command to classify the application based on a pre-set category. The second prompt (1200) may include examples of main functions (price comparison, review provision, detailed product description, shipping options, payment methods, UI, promotions, discounts, etc.).

[0226] The second prompt (1200) may include a command to compare the characteristics of the application based on the main function and to generate a comparison matrix as a result of the comparison.

[0227] The second prompt (1200) may include a command to generate an AI model based on the contents described.

[0228] The electronic device (100) can transmit a second prompt (1200) and target folder information to the AI ​​engine. The AI ​​engine can generate a second AI model (12) based on the second prompt (1200) and target folder information. The AI ​​engine can transmit (or return) the second AI model (12) to the electronic device (100).

[0229] FIGS. 7 to 12 describe the process of generating the first AI model (11) and the second AI model (12). Below, the operation of using the generated first AI model (11) and the second AI model (12) is described.

[0230] FIG. 13 is a drawing for explaining a guide UI according to one embodiment.

[0231] Referring to FIG. 13, it can be identified whether a third user input for selecting a target folder is received (S1305). When the third user input is received (S1305-Y), the electronic device (100) can obtain target user data corresponding to the target folder (S1310). For example, the electronic device (100) can obtain target user data using a second AI model (12). When a target folder is selected, the electronic device (100) can identify a second AI model (12) corresponding to the target folder. The electronic device (100) can provide a guide UI related to the target folder using the second AI model (12).

[0232] Target user data may represent data related to a target folder selected by the user among multiple user data. Multiple user data may be data included in a user profile stored in the personal data management module (20) of FIG. 4. The electronic device (100) may extract (or acquire) target user data based on the user profile and the target folder of the third user input.

[0233] The electronic device (100) can generate a third prompt requesting guide information (S1315). The electronic device (100) can generate a third prompt requesting guide information related to folder selection. Folder selection may indicate the selection of a target folder. For example, the electronic device (100) can generate the third prompt using a second AI model (12). A description of the third prompt is provided in FIG. 14. The electronic device (100) can transmit the third prompt and target user data to the AI ​​server (200) (S1320).

[0234] The AI ​​server (200) can receive a third prompt and target user data from the electronic device (100). The AI ​​server (200) can generate guide information based on the third prompt and target user data (S1325). The guide information may be information displayed on the electronic device (100) in response to a user action of selecting a target folder. The AI ​​server (200) can transmit the guide information to the electronic device (100) (S1330).

[0235] The electronic device (100) can receive guide information from the AI ​​server (200). The electronic device (100) can generate a guide UI based on the guide information (S1335). For example, the electronic device (100) can generate a guide UI using a second AI model (12).

[0236] The electronic device (100) can display a guide UI on the display (140) (S1340). For example, the electronic device (100) can display the guide UI using a second AI model (12). The electronic device (100) can obtain a target location for displaying the guide UI among the entire locations of the display (140) using the second AI model (12). The electronic device (100) can display the guide UI at the target location.

[0237] In FIG. 13, it is described that the third prompt and target user data are transmitted individually to the AI ​​server (200). According to another embodiment, the third prompt may include target user data. The electronic device (100) may generate a third prompt containing target user data. The electronic device (100) may transmit the third prompt containing target user data to the AI ​​server (200).

[0238] FIG. 14 is a drawing for explaining a third prompt according to one embodiment.

[0239] Referring to FIG. 14, the electronic device (100) can generate a third prompt (1400). The third prompt (1400) may include a command to generate a guide sentence (or guide information) using target user data. The third prompt (1400) may include information about the user's language.

[0240] The third prompt (1400) may include information indicating that the user has selected a target folder. The third prompt (1400) may include a command that generates a guide sentence for the target folder selected by the user.

[0241] The electronic device (100) can transmit the third prompt (1400) and target user data to the AI ​​engine. The AI ​​engine can generate guide information based on the third prompt (1400) and target user data. The AI ​​engine can transmit (or return) the guide information to the electronic device (100).

[0242] FIG. 15 is a drawing for explaining a method of displaying a guide UI according to one embodiment.

[0243] Referring to FIG. 15, the electronic device (100) may display a folder screen (1510, 1520) including a guide UI (1511, 1521). When a target folder is selected by a user, the electronic device (100) may display a screen (1510, 1520) corresponding to the target folder. The folder screen (1510, 1520) may include a UI (A, B, C, D, E, F, G) representing a plurality of applications.

[0244] When a target folder is selected, the first AI model (11) can transmit a user profile to the second AI model (12). The second AI model (12) can receive the user profile from the first AI model (11). The second AI model (12) can obtain guide information based on the user profile. The second AI model (12) can generate a guide UI (1511, 1521) based on the guide information. The second AI model (12) can display a guide screen (1510, 1520) including the guide UI (1511, 1521).

[0245] For example, the screen (1510) may include a guide UI (1511) and an input UI (1512). The guide UI (1511) may include guide information. The electronic device (100) may obtain a fourth user input through the input UI (1512). The display position of the input UI (1512) may be below the guide UI (1511). However, it is not limited thereto.

[0246] For example, the screen (1520) may include a guide UI (1521) and an input UI (1522). The guide UI (1521) may include guide information. The electronic device (100) may obtain a fourth user input through the input UI (1522). The display position of the input UI (1522) may be above the guide UI (1521). However, it is not limited thereto.

[0247] FIG. 16 is a diagram illustrating an operation of providing a guide UI using a plurality of AI models according to one embodiment.

[0248] Referring to FIG. 16, the electronic device (100) may display a folder screen (1600) including a plurality of guide UIs (1611, 1613). When a target folder is selected, the electronic device (100) may display the folder screen (1600). The folder screen (1600) may include UIs (A, B, C, D, E, F, G) representing a plurality of applications.

[0249] The electronic device (100) can obtain a guide UI (1611) obtained through the second AI model (12).

[0250] The electronic device (100) can obtain a guide UI (1613) obtained through the first AI model (11).

[0251] The electronic device (100) may display a folder screen (1600) including a guide UI (1613) of the first AI model (11) and a guide UI (1611) of the second AI model (12). The folder screen (1600) may include an input UI (1612).

[0252] FIG. 17 is a diagram illustrating the operation of receiving user typing input according to one embodiment.

[0253] Referring to FIG. 17, the electronic device (100) can display a folder screen (1700) including an input UI (1710). When user input selecting the input UI (1710) is received, the electronic device (100) can display a folder screen (1700) including an input UI (1710) and a keyboard UI (1720).

[0254] Through the keyboard UI (1720), the electronic device (100) can obtain user input (e.g., a fourth user input).

[0255] FIG. 18 is a diagram illustrating the operation of receiving voice input from a user according to one embodiment.

[0256] Referring to FIG. 18, the electronic device (100) may include a microphone. The electronic device (100) may obtain voice input from a user through the microphone. The electronic device (100) may display a UI (1810) indicating that voice input from a user is possible.

[0257] The electronic device (100) can display a folder screen (1800) including a UI (1810).

[0258] FIG. 19 is a diagram illustrating the operation of receiving image input from a user according to one embodiment.

[0259] Referring to FIG. 19, the electronic device (100) may include an image sensor (150). The electronic device (100) may acquire a captured image through the image sensor (150). The electronic device (100) may identify a code object included in the captured image. The code object may include a bar code or a QR code. The electronic device (100) may acquire user input based on the code object included in the captured image.

[0260] The electronic device (100) can display a UI (1910) related to a shooting function on a folder screen (1900). The UI (1910) may be a UI that displays an image being shot in real time or a UI that displays a captured image.

[0261] FIG. 20 is a drawing for explaining application data according to one embodiment.

[0262] Referring to FIG. 20, the electronic device (100) can identify whether a fourth user input for searching has been received (S2005). For example, after the operation S1340 of FIG. 13 is performed, the electronic device (100) can identify whether a fourth user input, which is a subsequent input for searching, has been received. The method of receiving the fourth user input is described in FIGs. 17 to 19.

[0263] When a fourth user input is received (S2005-Y), the electronic device (100) can identify a search term in the fourth user input (S2010). For example, the electronic device (100) can identify a search term in the fourth user input using a second AI model (12).

[0264] The electronic device (100) can obtain a first target command for a search term (S2015). For example, the electronic device (100) can obtain a first target command requesting results for a search term using a second AI model (12). The electronic device (100) can transmit the first target command to a first application server (310) (S2020).

[0265] The first application server (310) can receive a first target command from the electronic device (100). The first application server (310) can obtain first application data corresponding to the first target command (S2025). The first application data may be result information (or response information) corresponding to the first target command. The first application server (310) can transmit the first application data to the electronic device (100) (S2030).

[0266] The electronic device (100) can receive first application data from the first application server (310). The electronic device (100) can store the first application data in memory (120) (S2035). For example, the electronic device (100) can store the first application data in the second AI model (12).

[0267] FIG. 21 is a diagram illustrating the operation of acquiring application data from a plurality of servers according to one embodiment.

[0268] The operations S2105, S2110, S2120, S2125, S2130, and S2135 of FIG. 21 may correspond to the operations S2005, S2010, S2020, S2025, S2030, and S2035 of FIG. 20.

[0269] After identifying a search term in the fourth user input, the electronic device (100) can obtain a first target command and a second target command for the search term (S2115). For example, the electronic device (100) can obtain a first target command and a second target command requesting results for the search term included in the fourth user input through a second AI model (12).

[0270] The electronic device (100) can obtain a first target command requesting results for a search term from a first application. The electronic device (100) can obtain a second target command requesting results for a search term from a second application.

[0271] The electronic device (100) can transmit a first target command to a first application server (310) (S2120). The first application server (310) may be a server connected to a first application installed in the electronic device (100).

[0272] The electronic device (100) can transmit a second target command to a second application server (320) (S2140). The second application server (320) may be a server connected to a second application installed in the electronic device (100).

[0273] The second application server (320) can receive a second target command from the electronic device (100). The second application server (320) can obtain second application data corresponding to the second target command (S2145). The second application data may be result information (or response information) corresponding to the second target command. The second application server (320) can transmit the second application data to the electronic device (100) (S2150).

[0274] The electronic device (100) can receive second application data from the second application server (320). The electronic device (100) can store the second application data in memory (120) (S2155). For example, the electronic device (100) can store the second application data in the second AI model (12).

[0275] FIG. 22 is a drawing for explaining an application server according to one embodiment.

[0276] Referring to the embodiment (2210) of FIG. 22, an electronic device (100) can request search content from an application server through an application. The application server can obtain application data corresponding to the search content request. The application server can transmit the application data to the application.

[0277] For example, search content may include content with the lowest price for the search term. Application data may include products with the lowest price related to the search term.

[0278] Referring to the embodiment (2220) of FIG. 22, an electronic device (100) can request search content from an application server through an application. The application server can obtain application data corresponding to the feedback content request. The application server can transmit the application data to the application.

[0279] For example, feedback content may be content that represents user reactions. Application data may include reviews, star ratings, and evaluation information related to search terms.

[0280] Referring to the embodiment (2230) of FIG. 22, an electronic device (100) can request a screen context from an application server through an application. The application server can obtain application data corresponding to the screen context request. The application server can transmit the application data to the application.

[0281] For example, screen context can represent information contained on the screen. Application data can include screen analysis results.

[0282] FIG. 23 is a diagram illustrating an operation for providing a result UI according to one embodiment.

[0283] The operation S2305 of FIG. 23 may correspond to the operations S2135 and S2155 of FIG. 21. Redundant descriptions are omitted.

[0284] The electronic device (100) can generate a fourth prompt requesting first result information corresponding to the fourth user input (S2310). For example, the electronic device (100) can generate the fourth prompt using the second AI model (12). The electronic device (100) can generate a fourth prompt requesting a search result corresponding to the fourth user input based on the first application data and the second application data. The electronic device (100) can transmit the fourth prompt, the first application data, and the second application data to the AI ​​server (200) (S2315).

[0285] The AI ​​server (200) can receive a fourth prompt, first application data, and second application data from the electronic device (100). The AI ​​server (200) can generate first result information based on the fourth prompt, first application data, and second application data (S2320). The electronic device (100) can obtain first result information to provide a suitable response to the user among the first application data and second application data. The AI ​​server (200) can transmit the first result information to the electronic device (100) (S2325).

[0286] The electronic device (100) can receive first result information from the AI ​​server (200). The electronic device (100) can store the first result information in memory (120) (S2330). For example, the electronic device (100) can store the first result information in the AI ​​server (200).

[0287] The electronic device (100) can generate a first result UI based on first result information (S2335). For example, the electronic device (100) can generate a first result UI including the first result information using a second AI model (12).

[0288] The electronic device (100) can display a first result UI on a display (140) (S2340). For example, the electronic device (100) can display the first result UI using a second AI model (12). The electronic device (100) can determine the display location of the first result UI using the second AI model (12). The electronic device (100) can display the first result information at the display location determined using the second AI model (12).

[0289] In FIG. 23, it is described that the fourth prompt, the first application data, and the second application data are individually transmitted to the AI ​​server (200). According to another embodiment, the fourth prompt may include the first application data and the second application data. The electronic device (100) may generate a fourth prompt including the first application data and the second application data. The electronic device (100) may transmit the fourth prompt including the first application data and the second application data to the AI ​​server (200).

[0290] FIG. 24 is a drawing for explaining a fourth prompt according to one embodiment.

[0291] Referring to FIG. 24, the electronic device (100) may generate a fourth prompt (2400). The fourth prompt (2400) may include a command to generate first result information (or response information) using application data. The fourth prompt (2400) may include information indicating that there may be multiple application data.

[0292] The fourth prompt (2400) may include information about the user language. The fourth prompt (2400) may include information indicating that the user has selected a target folder. The fourth prompt (2400) may include text for user input for a search.

[0293] The fourth prompt (2400) may include information indicating the application server connected to the time when each of the multiple application data is received.

[0294] The electronic device (100) can transmit the fourth prompt (2400), the first application data, and the second application data to the AI ​​engine. The AI ​​engine can generate first result information based on the fourth prompt (2400), the first application data, and the second application data. The AI ​​engine can transmit (or return) the first result information to the electronic device (100).

[0295] FIG. 25 is a drawing for explaining a result UI according to one embodiment.

[0296] Referring to FIG. 25, the electronic device (100) may display a screen (2500) containing first result information. The screen (2500) may include a search result corresponding to a fourth user input. The screen (2500) may include at least one of a UI (2510) indicating that the search result is by an AI model or a UI (2512) indicating a second AI model (12).

[0297] The screen (2500) may include a UI (2520) for receiving subsequent user input for the search results.

[0298] For example, the screen (2500) may correspond to the first result UI in the S2335 operation of FIG. 23. When the S2335 operation is performed by the second AI model (12), the electronic device (100) may display the screen (2500) including a UI (2512) representing the second AI model (12).

[0299] For example, the screen (2500) may include search results. The search results may include at least one of text information (2513) for describing the search results or content information (2514) corresponding to the search results. The text information (2513) may include text for guiding the search results. The electronic device (100) may generate the text information (2513) using at least one of the first AI model (11) or the second AI model (12).

[0300] The first AI model (11) or the second AI model (12) may each include tone information. The first AI model (11) may include a first tone. The second AI model (12) may include a second tone. The electronic device (100) may generate text information (2513) based on the first tone of the first AI model (11) or the second tone of the second AI model (12). The first tone and the second tone may be different.

[0301] For example, the first AI model (11) can generate text that is lively and emotionally connected. For example, the second AI model (12) can generate text that represents calm and practical information related to rational choices.

[0302] In the above description, the operation of generating text information using the first AI model (11) or the second AI model (12) is described. As another example, the electronic device (100) can generate a text sentence using both the first AI model (11) and the second AI model (12).

[0303] FIG. 26 is a diagram illustrating subsequent operations on search results according to one embodiment.

[0304] The operation S2605 of FIG. 26 can correspond to the operation S2340 of FIG. 23. Redundant explanation is omitted.

[0305] After the first result UI is displayed, the electronic device (100) can obtain a second result UI based on the first result information and user profile (S2610). For example, the electronic device (100) can obtain the second result UI using a first AI model (11). The first AI model (11) can return output data using information related to the user. The first AI model (11) can generate the second result UI by changing the first result UI to reflect user preferences.

[0306] The electronic device (100) can display a second result UI (S2615). For example, the second result UI can be obtained through the first AI model (11). The electronic device (100) can obtain the display location of the second result UI using the first AI model (11). The electronic device (100) can display the second result UI based on the display location. The second result UI is described in FIG. 27.

[0307] After the first result UI or the second result UI is displayed, the electronic device (100) can identify whether a fifth user input for selecting a result is received (S2620). The fifth user input may represent an input for a subsequent action through the first result UI or the second result UI.

[0308] When the fifth user input is received (S2620-Y), the electronic device (100) can obtain a third target command based on the fifth user input (S2625). The electronic device (100) can identify whether the fifth user input was received through the first result UI or through the second result UI.

[0309] When a fifth user input is received through the first result UI, the electronic device (100) can perform a subsequent operation using the second AI model (12). The electronic device (100) can obtain a third target command for the fifth user input using the second AI model (12).

[0310] When a fifth user input is received through a second result UI, the electronic device (100) can perform a subsequent operation using the first AI model (11). The electronic device (100) can obtain a third target command for the fifth user input using the first AI model (11).

[0311] It is assumed that the fifth user input includes a command requesting a subsequent action from the first application server (310). The electronic device (100) can transmit a third target command to the first application server (310) (S2630).

[0312] The first application server (310) can receive a third target command from the electronic device (100). The first application server (310) can perform a function corresponding to the third target command. The first application server (310) can obtain third application data as a result of performing the function corresponding to the third target command (S2635). The first application server (310) can transmit the third application data to the electronic device (100) (S2640).

[0313] The electronic device (100) can receive third application data from the first application server (310). The electronic device (100) can store the third application data in memory (120) (S2645).

[0314] For example, when a fifth user input is received through a first result UI, the electronic device (100) can store third application data in a second AI model (12).

[0315] For example, when a fifth user input is received through a second result UI, the electronic device (100) can store third application data in the first AI model (11).

[0316] In FIG. 26, it is described that the electronic device (100) uses the first AI model to generate the second result UI in operation S2610. According to one embodiment, the electronic device (100) may use an AI server (200) to generate the second result UI. The electronic device (100) may generate a prompt based on result information and a user profile. The electronic device (100) may transmit the prompt, result information, and user profile to the AI ​​server (200). The AI ​​server (200) may generate result information corresponding to the prompt. The AI ​​server (200) may transmit the result information to the electronic device (100). The electronic device (100) may receive result information from the AI ​​server. The electronic device (100) may generate the second result UI based on the result information. Ordinal expressions modifying the prompt and result information may be added according to the combination of embodiments.

[0317] FIG. 27 is a diagram illustrating an operation for providing a result UI according to one embodiment.

[0318] The operation S2705 of FIG. 27 may correspond to the operation S2645 of FIG. 26. Redundant explanation is omitted.

[0319] The electronic device (100) can generate a fifth prompt requesting second result information corresponding to the fifth user input (S2710). For example, the electronic device (100) can generate the fifth prompt using the first AI model (11) or the second AI model (12). The electronic device (100) can generate a fifth prompt requesting a search result corresponding to the fifth user input based on third application data. The electronic device (100) can transmit the fifth prompt and the third application data to the AI ​​server (200) (S2715).

[0320] The AI ​​server (200) can receive a fifth prompt and third application data from the electronic device (100). The AI ​​server (200) can generate second result information based on the fifth prompt and third application data (S2720). The electronic device (100) can obtain second result information to provide a suitable response to the user based on the third application data. The AI ​​server (200) can transmit the second result information to the electronic device (100) (S2725).

[0321] The electronic device (100) can receive second result information from the AI ​​server (200). The electronic device (100) can store the second result information in memory (120) (S2730). For example, the electronic device (100) can store the second result information in the AI ​​server (200).

[0322] The electronic device (100) can generate a third result UI based on the second result information (S2735). For example, the electronic device (100) can generate a third result UI including the second result information using the first AI model (11) or the second AI model (12).

[0323] The electronic device (100) can display a third result UI on a display (140) (S2740). For example, the electronic device (100) can display the third result UI using a first AI model (11) or a second AI model (12). The electronic device (100) can determine the display location of the third result UI using the first AI model (11) or the second AI model (12). The electronic device (100) can display the third result UI at the display location determined using the first AI model (11) or the second AI model (12).

[0324] When the fifth user input is input through the first result UI in the S2620 operation of FIG. 26, the electronic device (100) can perform S2705, S2710, S2730, S2735, and S2740 operations using the second AI model (12).

[0325] When the fifth user input is input through the second result UI in the S2620 operation of FIG. 26, the electronic device (100) can perform S2705, S2710, S2730, S2735, and S2740 operations using the first AI model (11).

[0326] The electronic device (100) can update the user profile based on the third user input, the fourth user input, the fifth user input, and the second result information (S2745).

[0327] In FIG. 27, it is described that the fifth prompt and the third application data are transmitted individually to the AI ​​server (200). According to another embodiment, the fifth prompt may include the third application data. The electronic device (100) may generate a fifth prompt including the third application data. The electronic device (100) may transmit the fifth prompt including the third application data to the AI ​​server (200).

[0328] FIG. 28 is a drawing for explaining the fifth prompt according to one embodiment.

[0329] Referring to FIG. 28, the electronic device (100) may generate a fifth prompt (2800) for a subsequent operation. The fifth prompt (2800) may include a command to generate result information using third application data. The fifth prompt (2800) may include information about the user language.

[0330] The fifth prompt (2800) may include information indicating that the user has entered a fifth user input for a subsequent action.

[0331] The fifth prompt (2800) may include information indicating that the electronic device (100) has received third application data from a specific application server at a third time.

[0332] The electronic device (100) can transmit the fifth prompt (2800) and the third application data to the AI ​​engine. The AI ​​engine can generate second result information based on the fifth prompt (2800) and the third application data. The AI ​​engine can transmit (or return) the second result information to the electronic device (100).

[0333] FIG. 29 is a drawing for explaining a result UI that is additionally displayed according to one embodiment.

[0334] The screen (2910) of FIG. 29 may correspond to the second result UI described in operations S2610 and S2615 of FIG. 26. The screen (2910) may include a UI (2915) for subsequent operations. It is assumed that the second result UI included in the screen (2910) was generated through the first AI model (11). The electronic device (100) may include a UI (2911) that displays the first AI model (11) on the screen (2910).

[0335] For example, the screen (2500) containing the first result UI of FIG. 25 and the screen (2910) containing the second result UI may be different. The first AI model (11) may change the content displayed in the first result UI based on the user profile. The second result UI may be a UI that additionally reflects information related to the user.

[0336] When a fifth user input is received for selecting a UI (2915) for a subsequent action, the electronic device (100) may display a new result screen (2920). The screen (2920) may correspond to the third result UI described in actions S2735 and S2740 of FIG. 27. It is assumed that the third result UI was generated through the AI ​​server (200). The electronic device (100) may include a UI (2921) that displays the first AI model (11) on the screen (2920).

[0337] In FIG. 29, it is described that a fifth user input is received through a UI (2915) for subsequent actions displayed on a screen (2910). According to another embodiment, the electronic device (100) may receive a fifth user input through an input UI (3010) and a keyboard UI (3020).

[0338] FIG. 30 is a drawing for illustrating a screen corresponding to additional user input according to one embodiment.

[0339] Referring to FIG. 30, the electronic device (100) can display a folder screen (3010) including an input UI (3010). When user input selecting the input UI (3010) is received, the electronic device (100) can display a folder screen (3010) including the input UI (3010) and a keyboard UI (3020). Through the keyboard UI (3020), the electronic device (100) can obtain user input (e.g., a fifth user input).

[0340] FIG. 31 is a drawing for illustrating a screen corresponding to additional user input according to one embodiment.

[0341] Referring to FIG. 31, the electronic device (100) can display a screen (3100). While the first result UI and the second result UI are displayed, the electronic device (100) assumes that a fifth user input is received through the second result UI.

[0342] The screen (3100) may include a first area (3110), a second area (3120), and a third area (3130).

[0343] The first area (3110) may correspond to the first result UI of the S2340 operation of FIG. 23 and the screen (2500) of FIG. 25.

[0344] The second area (3120) may correspond to the second result UI of the S2615 operation of FIG. 26, and the screen (2910) of FIG. 29.

[0345] The third area (3130) may correspond to the third result UI of the S2740 operation of FIG. 27 and the screen (2920) of FIG. 29.

[0346] The electronic device (100) can display multiple result UIs in the order shown on a single screen (3100).

[0347] FIG. 32 is a drawing for illustrating a screen corresponding to additional user input according to one embodiment.

[0348] Referring to FIG. 32, the electronic device (100) can display a screen (3200). While the first result UI and the second result UI are displayed, the electronic device (100) assumes that a fifth user input has been received through the first result UI.

[0349] The screen (3200) may include a first area (3210), a second area (3220), and a third area (3230).

[0350] The first area (3210) may correspond to the first result UI of the S2340 operation of FIG. 23, and the screen (2500) of FIG. 25.

[0351] The second area (3220) may correspond to the second result UI of the S2615 operation of FIG. 26, and the screen (2910) of FIG. 29.

[0352] The third area (3230) can correspond to the third result UI of the S2740 operation of FIG. 27.

[0353] The electronic device (100) can display multiple result UIs in the order shown on a single screen (3200).

[0354] FIG. 33 is a drawing for explaining a method of controlling an electronic device according to one embodiment.

[0355] Referring to FIG. 33, a control method for an electronic device (100) connected to an AI server (200) comprises the steps of: when a first user input requesting an AI model for controlling the electronic device (100) is received, obtaining a user profile related to the usage history of the electronic device (100) (S3310); generating a first prompt based on the user profile (S3320); transmitting the first prompt and the user profile to the AI ​​server (200) (S3330); receiving a first AI model (11) corresponding to the first prompt from the AI ​​server (200) (S3340); when a second user input requesting an AI model for controlling a target folder is received, obtaining target folder information related to at least one application included in the target folder (S3350); generating a second prompt based on the target folder information (S3360); transmitting the second prompt and the target folder information to the AI ​​server (200) (S3370); and receiving a second AI model (12) corresponding to the second prompt. It may include the step of receiving from the AI ​​server (200) (S3380), and the step of storing the first AI model (11) and the second AI model (12) in the electronic device (100) (S3390).

[0356] A user profile may include at least one of name, account, age, gender, region, language, preferred category, application usage history, and feedback data.

[0357] Target folder information includes application information for at least one application included in the target folder, and the application information may include at least one of the application's name, representative image, and main function.

[0358] The first AI model (11) is a model trained to control the electronic device (100) with the first AI personality, and the second AI model (12) may be a model trained to control operations related to the target folder with the second AI personality different from the first AI personality.

[0359] The control method may include the steps of: receiving a third user input selecting a target folder, obtaining target user data corresponding to the target folder among user profiles; using a second AI model (12), generating a third prompt requesting guidance for the target folder based on the target user data; transmitting the third prompt and target user data to an AI server (200); receiving guidance information corresponding to the third prompt; generating a guide UI based on the guide information; and displaying the guide UI.

[0360] The control method may include the steps of: when a fourth user input for search is received, identifying a search term based on the fourth user input using a second AI model (12); obtaining a first target command and a second target command requesting a response to the search term; transmitting the first target command to a first application server (310); receiving first application data corresponding to the first target command from the first application server (310); transmitting the second target command to a second application server (320); receiving second application data corresponding to the second target command from the second application server (320); and storing the first application data and the second application data in an electronic device (100).

[0361] The control method may include the steps of: generating a fourth prompt requesting a result for a fourth user input using a second AI model (12); transmitting the fourth prompt, first application data, and second application data to an AI server (200); receiving result information corresponding to the fourth prompt from the AI ​​server (200); generating a first result UI based on the result information; and displaying the first result UI.

[0362] The control method may include the step of obtaining a second result UI based on result information and a user profile using a first AI model (11) and the step of displaying the second result UI.

[0363] The first result UI includes an image representing the second AI model (12), and the second result UI may include an image representing the first AI model (11).

[0364] The AI ​​server (200) may include a Large Language Model (LM).

[0365] FIGS. 34 to 50 illustrate an operation that displays a result UI corresponding to a user command.

[0366] Figure 34 is a diagram illustrating a prompt input into an AI engine.

[0367] Referring to FIG. 34, the electronic device (100) may receive user input. The user input may be an input for a search corresponding to the entered text (summer dress). The electronic device (100) may generate a prompt (3400) for search results using the second AI model (12). The electronic device (100) may generate a prompt (3400) corresponding to the user input using the second AI model (12). The electronic device (100) may transmit the prompt (3400) to an AI engine. For example, the AI ​​engine may include an LLM.

[0368] The prompt (3400) may be a prompt for generating a description of the initial product information.

[0369] The AI ​​engine can receive a prompt (3400) generated by the second AI model (12). The AI ​​engine can generate result information based on the prompt (3400). The AI ​​engine can transmit the result information to the second AI model (12).

[0370] The second AI model (12) can receive result information from the AI ​​engine. The electronic device (100) can use the second AI model (12) to generate a result UI based on the result information received by the second AI model (12). The electronic device (100) can provide the result UI to the user. A result UI corresponding to the prompt (3400) is described in FIG. 35.

[0371] Figure 35 is a diagram illustrating a result UI corresponding to a prompt.

[0372] Referring to FIG. 35, the electronic device (100) can generate a screen (3500) containing a result UI corresponding to the prompt (3400) of FIG. 34. The electronic device (100) can display the screen (3500) through a display (140).

[0373] Figure 36 is a diagram illustrating a prompt input into an AI engine.

[0374] Referring to FIG. 36, the electronic device (100) can generate a prompt (3600) for search results using a second AI model (12).

[0375] The prompt (3600) may be a prompt for requesting a search from the application server. For example, the prompt (3600) may include a command to request price, review, popularity ranking information, etc. from the application server.

[0376] The electronic device (100) can generate a prompt (3600) based on the result UI of FIG. 35 (or result information corresponding to the prompt (3400) of FIG. 34) and a search request to the application server.

[0377] The electronic device (100) can transmit a prompt (3600) to the AI ​​engine. For example, the AI ​​engine may include a LAM.

[0378] The AI ​​engine can receive a prompt (3600) generated by the second AI model (12). The AI ​​engine can send a search result request to the application server. The application server can send the search results to the AI ​​engine in response to the request. The AI ​​engine can generate result information based on the search results. The AI ​​engine can send the result information to the second AI model (12).

[0379] The second AI model (12) can receive result information from the AI ​​engine. The electronic device (100) can use the second AI model (12) to generate a result UI based on the result information received by the second AI model (12). The electronic device (100) can provide the result UI to the user. A result UI corresponding to the prompt (3600) is described in FIG. 37.

[0380] Figure 37 is a diagram illustrating a result UI corresponding to a prompt.

[0381] Referring to FIG. 37, the electronic device (100) can generate a screen (3700) containing a result UI corresponding to the prompt (3600) of FIG. 36. The electronic device (100) can display the screen (3700) through a display (140).

[0382] FIG. 38 is a diagram illustrating a prompt input to an AI engine. Referring to FIG. 38, the electronic device (100) can generate a prompt (3800) for adjusting the final recommendation using a second AI model (12).

[0383] The electronic device (100) can generate a prompt (3800) based on the result UI of FIG. 37 (or result information corresponding to the prompt (3600) of FIG. 36) and the final recommendation request.

[0384] The electronic device (100) can transmit a prompt (3800) to the AI ​​engine. For example, the AI ​​engine may include an LLM.

[0385] The AI ​​engine can receive a prompt (3800) generated by the second AI model (12). The AI ​​engine can generate result information based on the prompt (3800). The AI ​​engine can transmit the result information to the second AI model (12).

[0386] The second AI model (12) can receive result information from the AI ​​engine. The electronic device (100) can use the second AI model (12) to generate a result UI based on the result information received by the second AI model (12). The electronic device (100) can provide the result UI to the user. A result UI corresponding to the prompt (3800) is described in FIG. 39.

[0387] Figure 39 is a diagram illustrating a result UI corresponding to a prompt.

[0388] Referring to FIG. 39, the electronic device (100) can generate a screen (3900) containing a result UI corresponding to the prompt (3800) of FIG. 38. The electronic device (100) can display the screen (3900) through a display (140).

[0389] FIG. 40 is a diagram illustrating a prompt input to the first AI model.

[0390] Referring to FIG. 40, the electronic device (100) can generate a screen (3900) of FIG. 39 and then generate a prompt (4000) for requesting additional recommendations using the second AI model (12).

[0391] The electronic device (100) can generate a prompt (4000) based on the result UI of FIG. 39 (or result information corresponding to the prompt (3800) of FIG. 38) and a search result request for a new style. The new style may be a style associated with the first AI model (11).

[0392] The electronic device (100) can transmit a prompt (4000) generated in the second AI model (12) to the first AI model (11). The first AI model (11) can receive the prompt (4000). The prompt (4000) can be transmitted from the second AI model (12) to the first AI model (11).

[0393] Figure 41 is a diagram illustrating a prompt input into an AI engine.

[0394] The electronic device (100) can receive the prompt (4000) of FIG. 40 for requesting additional search results of a new style. The electronic device (100) can generate a prompt (4100) based on the prompt (4000) and the additional search request through the first AI model (11).

[0395] For example, an electronic device (100) can generate a prompt (4100) based on result information corresponding to the prompt (3600) of FIG. 36, the prompt (4000) of FIG. 40, and a recommendation message request through a first AI model (11). The target item (or product) included in the prompt (4000) of FIG. 40 and the target item included in the prompt (4100) of FIG. 41 may be different.

[0396] The electronic device (100) can transmit a prompt (4100) to the AI ​​engine. For example, the AI ​​engine may include an LLM.

[0397] The AI ​​engine can generate result information corresponding to the prompt (4100). The AI ​​engine can transmit the result information corresponding to the prompt (4100) to the first AI model (11).

[0398] The first AI model (11) can receive result information from the AI ​​engine. The electronic device (100) can use the first AI model (11) to generate a result UI based on the result information received by the first AI model (11). The electronic device (100) can provide the result UI to the user. A result UI corresponding to the prompt (4100) is described in FIG. 42.

[0399] Figure 42 is a diagram illustrating a result UI corresponding to a prompt.

[0400] Referring to FIG. 42, the electronic device (100) can generate a screen (4200) containing a result UI corresponding to the prompt (4100) of FIG. 41. The electronic device (100) can display the screen (4200) through a display (140).

[0401] Figure 43 is a diagram illustrating a prompt input into an AI engine.

[0402] Referring to FIG. 43, the electronic device (100) can generate a screen (4200) of FIG. 42 and then generate a prompt (4300) for requesting an additional message using the first AI model (11).

[0403] The electronic device (100) can generate a prompt (4300) based on the result UI of FIG. 42 (or result information corresponding to the prompt (4100) of FIG. 41) and additional message requests through the first AI model (11).

[0404] The electronic device (100) can transmit a prompt (4300) generated in the first AI model (11) to the AI ​​engine. The AI ​​engine can receive the prompt (4300). For example, the AI ​​engine may include an LLM.

[0405] The AI ​​engine can generate result information corresponding to the prompt (4300). The AI ​​engine can transmit the result information corresponding to the prompt (4300) to the first AI model (11).

[0406] The first AI model (11) can receive result information from the AI ​​engine. The electronic device (100) can use the first AI model (11) to generate a result UI based on the result information received by the first AI model (11). The electronic device (100) can provide the result UI to the user. A result UI corresponding to the prompt (4300) is described in FIG. 44.

[0407] Figure 44 is a diagram illustrating a result UI corresponding to a prompt.

[0408] Referring to FIG. 44, the electronic device (100) can generate a screen (4400) containing a result UI corresponding to the prompt (4300) of FIG. 43. The electronic device (100) can display the screen (4400) through a display (140).

[0409] Figure 45 is a diagram illustrating a prompt input into an AI engine.

[0410] Referring to FIG. 45, the electronic device (100) can generate a prompt (4500) for requesting an explanation of the final recommendation list using the first AI model (11) and the second AI model (12) after generating the screen (4400) of FIG. 44. The electronic device (100) can generate the prompt (4500) using both the first AI model (11) and the second AI model (12).

[0411] The electronic device (100) can generate a prompt (4500) based on a request for explanation of the result UI (or result information corresponding to the prompt (4300) of FIG. 43) and the final recommendation list through the first AI model (11) and the second AI model (12).

[0412] The electronic device (100) generates a prompt (4500) using both the first AI model (11) and the second AI model (12), but the main calculation may use the first AI model (11). The first AI model (11) may receive necessary information from the second AI model (12). The prompt (4500) may ultimately be generated through the first AI model (11).

[0413] The electronic device (100) can transmit a prompt (4500) generated in the first AI model (11) to the AI ​​engine. The AI ​​engine can receive the prompt (4500). For example, the AI ​​engine may include an LLM.

[0414] The AI ​​engine can generate result information corresponding to the prompt (4500). The AI ​​engine can transmit the result information corresponding to the prompt (4500) to the first AI model (11).

[0415] The first AI model (11) can receive result information from the AI ​​engine. The electronic device (100) can use the first AI model (11) to generate a result UI based on the result information received by the first AI model (11). The electronic device (100) can provide the result UI to the user. A result UI corresponding to the prompt (4500) is described in FIG. 46.

[0416] Figure 46 is a diagram illustrating a result UI corresponding to a prompt.

[0417] Referring to FIG. 46, the electronic device (100) can generate a screen (4600) containing a result UI corresponding to the prompt (4500) of FIG. 45. The electronic device (100) can display the screen (4600) through a display (140).

[0418] Figure 47 is a diagram illustrating a prompt input into an AI engine.

[0419] Referring to FIG. 47, the electronic device (100) can receive user input after generating the screen (4600) of FIG. 46. The user input may be an input for selecting one of at least one item included in the screen (4600) of FIG. 46. The user input may include a command for ordering the selected item.

[0420] The electronic device (100) can generate a prompt (4700) for ordering an item corresponding to user input using a second AI model (12). The electronic device (100) can generate the prompt (4700) based on the result UI of FIG. 46 (or the prompt (4500) of FIG. 45) and the final order request.

[0421] The electronic device (100) can transmit a prompt (4700) generated in the second AI model (12) to the AI ​​engine. The AI ​​engine can receive the prompt (4700). For example, the AI ​​engine may include a LAM.

[0422] The AI ​​engine can generate result information corresponding to the prompt (4700). The AI ​​engine can transmit the result information corresponding to the prompt (4700) to the second AI model (12).

[0423] The second AI model (12) can receive result information from the AI ​​engine. The electronic device (100) can use the second AI model (12) to generate a result UI based on the result information received by the second AI model (12). The electronic device (100) can provide the result UI to the user. A result UI corresponding to the prompt (4700) is described in FIG. 48.

[0424] Figure 48 is a diagram illustrating a result UI corresponding to a prompt.

[0425] Referring to FIG. 48, the electronic device (100) can generate a screen (4800) containing a result UI corresponding to the prompt (4700) of FIG. 47. The electronic device (100) can display the screen (4800) through a display (140).

[0426] Figure 49 is a diagram illustrating a prompt input into an AI engine.

[0427] Referring to FIG. 49, after generating the screen (4800) of FIG. 48, the electronic device (100) can generate a prompt (4900) for requesting feedback information corresponding to user input. The electronic device (100) can generate the prompt (4900) through the first AI model (11).

[0428] The electronic device (100) can generate a prompt (4900) based on the result UI of FIG. 48 (or the prompt (4700) of FIG. 47) and a feedback request.

[0429] The electronic device (100) can transmit a prompt (4900) generated in the first AI model (11) to the AI ​​engine. The AI ​​engine can receive the prompt (4900). For example, the AI ​​engine may include an LLM.

[0430] The AI ​​engine can generate result information corresponding to the prompt (4900). The AI ​​engine can transmit the result information corresponding to the prompt (4900) to the first AI model (11).

[0431] The first AI model (11) can receive result information from the AI ​​engine. The electronic device (100) can use the first AI model (11) to generate a result UI based on the result information received by the first AI model (11). The electronic device (100) can provide the result UI to the user. A result UI corresponding to the prompt (4900) is described in FIG. 50.

[0432] Figure 50 is a diagram illustrating a result UI corresponding to a prompt.

[0433] Referring to FIG. 50, the electronic device (100) can generate a screen (5000) containing a result UI corresponding to the prompt (4900) of FIG. 49. The electronic device (100) can display the screen (5000) through a display (140).

[0434] FIGS. 51 to 60 illustrate an operation that displays a result UI corresponding to a user's voice.

[0435] Figure 51 is a diagram illustrating a function for recognizing user voice.

[0436] Referring to FIG. 51, the electronic device (100) may include a microphone. The electronic device (100) may receive a user voice through the microphone. The electronic device (100) may analyze the user voice and perform an action (or function) corresponding to the user voice.

[0437] The electronic device (100) can identify a wake-up word (e.g., Bixby) included in the user's voice. When the wake-up word is identified, the electronic device (100) can display a screen (5110) related to the voice recognition function. The screen (5110) may include a graphic UI representing the voice recognition function. The wake-up word may be a word for calling a voice assistant.

[0438] The electronic device (100) can obtain text corresponding to the remaining part of the user's voice excluding the wake-up word. The electronic device (100) can display a screen (5120) containing the text.

[0439] Figure 52 is a diagram illustrating a speech recognition module.

[0440] Referring to FIG. 52, the electronic device (100) may include at least one of an AI management module (10), a personal data management module (20), an application management module (50), or a voice recognition module (60).

[0441] Descriptions of the AI ​​management module (10), personal data management module (20), and application management module (50) are provided in FIG. 4. Duplicate descriptions are omitted.

[0442] The voice recognition module (60) may be a module that recognizes user voice. The voice recognition module (60) may recognize user voice and convert an audio signal into a digital signal. The voice recognition module (60) may obtain text information corresponding to the digital signal. The voice recognition module (60) may transmit the text information to the AI ​​management module (10).

[0443] The AI ​​management module (10) may include a first AI model (11) and a second AI model (12).

[0444] The AI ​​management module (10) can generate a prompt based on received text information. The AI ​​management module (10) can use information stored in the personal data management module (20) to generate the prompt. The AI ​​management module (10) can use information stored in the application management module (50) to generate the prompt.

[0445] Figure 53 is a diagram illustrating the result UI.

[0446] Referring to FIG. 53, the electronic device (100) can receive a user voice. The electronic device (100) can obtain text information corresponding to the user voice. The electronic device (100) can obtain a result UI corresponding to the text information.

[0447] For example, an electronic device (100) may generate a prompt requesting result information corresponding to a user's voice using a first AI model (11) or a second AI model (12). The electronic device (100) may transmit the generated prompt to an AI engine. The AI ​​engine may generate result information corresponding to a user's voice based on the prompt received from the electronic device (100). The AI ​​engine may transmit the result information to the electronic device (100).

[0448] The electronic device (100) can receive result information. The electronic device (100) can generate a result UI based on the result information. The electronic device (100) can generate a screen (5300) containing the result UI. The electronic device (100) can display the screen (5300) corresponding to the user's voice through a display (140).

[0449] FIGS. 54 to 60 illustrate an operation that provides a result UI corresponding to user input (or voice).

[0450] Figure 54 is a diagram illustrating a result UI corresponding to a prompt.

[0451] Referring to FIG. 54, the electronic device (100) can generate a prompt (5410) for processing a result corresponding to a user voice. The electronic device (100) can generate the prompt (5410) using a first AI model (11). The electronic device (100) can generate the prompt (5410) using tendency information (e.g., fashion tendency) corresponding to the first AI model (11).

[0452] The electronic device (100) can obtain a result UI (5420) corresponding to a prompt (5410). The electronic device (100) can display the result UI (5420). The electronic device (100) can obtain result information by inputting the prompt (5410) into an AI engine. The electronic device (100) can obtain a result UI (5420) based on the result information. The AI ​​engine may include an LLM.

[0453] FIG. 54 illustrates an operation for processing user voice using a first AI model (11). According to another embodiment, user voice may be processed using a second AI model (12). An explanation related to this is provided in FIG. 55.

[0454] Figure 55 is a diagram illustrating a result UI corresponding to a prompt.

[0455] Referring to FIG. 55, the electronic device (100) can generate a prompt (5510) for processing results corresponding to user voice. The electronic device (100) can generate the prompt (5510) using a second AI model (12). The electronic device (100) can generate the prompt (5510) using information on tendencies (e.g., fashion tendencies) corresponding to the second AI model (12). Tendencies for a specific field may differ depending on the AI ​​model. In a specific field, the tendencies of the first AI model (11) and the second AI model (12) may differ.

[0456] The electronic device (100) can obtain a result UI (5520) corresponding to a prompt (5510). The electronic device (100) can display the result UI (5520). The electronic device (100) can obtain result information by inputting the prompt (5510) into an AI engine. The electronic device (100) can obtain a result UI (5520) based on the result information. The AI ​​engine may include LAM.

[0457] Figure 56 is a diagram illustrating a result UI corresponding to a prompt.

[0458] Referring to FIG. 56, the electronic device (100) may generate a prompt (5610) requesting an explanation of an action processed from user voice. After obtaining at least one of the result UI (5420) of FIG. 54 or the result UI (5520) of FIG. 55, the electronic device (100) may generate a prompt (5610) through the second AI model (12). The electronic device (100) may generate a prompt (5610) for requesting a recommendation message for at least one of the result UI (5420) of FIG. 54 or the result UI (5520) of FIG. 55.

[0459] The electronic device (100) can obtain a result UI (5620) corresponding to a prompt (5610). The electronic device (100) can display the result UI (5620). The electronic device (100) can obtain result information by inputting the prompt (5610) into an AI engine. The electronic device (100) can obtain a result UI (5620) based on the result information. The AI ​​engine may include an LLM.

[0460] According to another embodiment, the embodiment of FIG. 54 and the embodiment of FIG. 55 may be performed simultaneously. The electronic device (100) may simultaneously obtain and provide a processing result using the first AI model (11) and a processing result using the second AI model (12). An explanation related to this is described in FIG. 57.

[0461] Figure 57 is a diagram illustrating a result UI corresponding to a prompt.

[0462] Referring to FIG. 57, the electronic device (100) can obtain the result UI (5420) of FIG. 54 and the result UI (5520) of FIG. 55. Based on the result UI (5420) of FIG. 54 and the result UI (5520) of FIG. 55, the electronic device (100) can generate a prompt (5710) for requesting a final search result corresponding to the user's voice. The electronic device (100) can generate the prompt (5710) through the first AI model (11) and the second AI model (12).

[0463] The electronic device (100) can obtain a result UI (5720) corresponding to a prompt (5710). The electronic device (100) can display the result UI (5720). The electronic device (100) can obtain result information by inputting the prompt (5710) into an AI engine. The electronic device (100) can obtain a result UI (5720) based on the result information. The AI ​​engine may include an LLM.

[0464] Figure 58 is a diagram illustrating a result UI corresponding to a prompt.

[0465] Referring to FIG. 58, the electronic device (100) can provide feedback after providing a processing result corresponding to the user's voice. The electronic device (100) can generate a prompt (5810) for feedback. The electronic device (100) can generate a prompt (5810) for generating feedback through the first AI model (11).

[0466] The electronic device (100) can obtain a result UI (5820) corresponding to a prompt (5810). The electronic device (100) can display the result UI (5820). The electronic device (100) can obtain result information by inputting the prompt (5810) into an AI engine. The electronic device (100) can obtain a result UI (5820) based on the result information. The AI ​​engine may include an LLM.

[0467] Figure 59 is a diagram illustrating a result UI corresponding to a prompt.

[0468] Referring to FIG. 59, the electronic device (100) can receive user input after providing a processing result corresponding to the user's voice. After a result UI containing the processing result corresponding to the user's voice is displayed, the electronic device (100) can receive user input through the result UI. For example, the user input may include a user command to order an item included in the result UI.

[0469] The electronic device (100) can generate a prompt (5910) for executing a user command included in the user input. The electronic device (100) can generate a prompt (5910) for executing a user command through a second AI model (12).

[0470] The electronic device (100) can obtain a result UI (5920) corresponding to a prompt (5910). The electronic device (100) can display the result UI (5920). The electronic device (100) can obtain result information by inputting the prompt (5910) into an AI engine. The electronic device (100) can obtain a result UI (5920) based on the result information. The AI ​​engine may include LAM.

[0471] Figure 60 is a diagram illustrating a result UI corresponding to a prompt.

[0472] Referring to FIG. 60, the electronic device (100) can update the first AI model (11) after performing a user command. The electronic device (100) can provide feedback on the update operation of the first AI model (11). The electronic device (100) can generate a prompt (6010) for generating an update command and feedback for the first AI model (11) through the first AI model (11).

[0473] The electronic device (100) can obtain a result UI (6020) corresponding to a prompt (6010). The electronic device (100) can display the result UI (6020). The electronic device (100) can obtain result information by inputting the prompt (6010) into an AI engine. The electronic device (100) can obtain a result UI (6020) based on the result information. The AI ​​engine may include LAM.

[0474] The methods according to the various embodiments of the present disclosure described above can be implemented in the form of an application that can be installed on an existing electronic device.

[0475] The methods according to the various embodiments of the present disclosure described above can be implemented by software upgrades or hardware upgrades alone for existing electronic devices.

[0476] The various embodiments of the present disclosure described above may also be performed through an embedded server equipped in an electronic device, or through an external server among at least one of the electronic device and the display device.

[0477] According to a specific example of the present disclosure, the various embodiments described above may be implemented as software comprising instructions stored on a machine-readable storage medium (e.g., a computer). The machine may include an electronic device according to the disclosed embodiments, which is a device capable of calling instructions stored from the storage medium and operating according to the called instructions. When instructions are executed by a processor, the processor may perform a function corresponding to the instructions directly or by using other components under the control of the processor. Instructions may include code generated or executed by a compiler or an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, "non-transitory" means only that the storage medium does not contain a signal and is tangible, and does not distinguish whether data is stored semi-permanently or temporarily in the storage medium.

[0478] According to one embodiment of the present disclosure, the method according to the various embodiments described above may be provided as included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or online through an application store. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a storage medium such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0479] Each component (e.g., module or program) according to the various embodiments described above may be composed of a single or multiple entities, and some of the aforementioned sub-components may be omitted, or other sub-components may be additionally included in the various embodiments. Generally or additionally, some components (e.g., module or program) may be integrated into a single entity to perform the functions performed by each of the respective components prior to integration in the same or similar manner. The operations performed by the module, program, or other components according to the various embodiments may be executed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be executed in a different order, omitted, or other operations added.

[0480] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the scope of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit of the present disclosure.

Claims

1. In an electronic device, Memory for storing instructions; Communication circuit connected to the AI ​​server; and at least one processor including processing circuitry; and When the above instructions are executed individually or collectively by the at least one processor, the electronic device, When a first user input requesting an AI model for controlling the electronic device is received, a user profile related to the usage history of the electronic device is obtained, and Generate a first prompt based on the above user profile, and Through the communication circuit above, the first prompt and the user profile are transmitted to the AI ​​server, and Through the communication circuit above, a first AI model corresponding to the first prompt is received from the AI ​​server, and When a second user input requesting an AI model to control a target folder is received, target folder information related to at least one application included in the target folder is obtained, and Based on the above target folder information, a second prompt is generated, and Through the communication circuit above, the second prompt and the target folder information are transmitted to the AI ​​server, and Through the communication circuit above, a second AI model corresponding to the second prompt is received from the AI ​​server, and An electronic device that stores the first AI model and the second AI model in the memory.

2. In Paragraph 1, The above user profile is, An electronic device comprising at least one of name, account, age, gender, region, language, preferred category, application usage history, and feedback data.

3. In Paragraph 1, The above target folder information is, It includes application information for at least one application included in the above target folder, and The above application information is, An electronic device comprising at least one of an application name, a representative image, and a main function.

4. In Paragraph 1, The above-mentioned first AI model is, It is a model trained to control the aforementioned electronic device as a first AI personality, and The above second AI model is, An electronic device, which is a model trained to control operations related to the target folder with a second AI personality different from the first AI personality.

5. In Paragraph 1, The above electronic device is, Includes a display; When the above instructions are executed individually or collectively by the at least one processor, the electronic device, When a third user input selecting the above target folder is received, target user data corresponding to the above target folder among the above user profiles is obtained, and Using the above second AI model, a third prompt requesting a guide for the target folder is generated based on the above target user data, and Through the communication circuit above, the third prompt and the target user data are transmitted to the AI ​​server, and Through the communication circuit above, guide information corresponding to the third prompt is received, and Based on the above guide information, create a guide UI, and An electronic device that controls the display to display the above guide UI.

6. In Paragraph 5, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, When a fourth user input for a search is received, the second AI model is used to identify a search term based on the fourth user input, and Obtaining a first target command and a second target command requesting a response to the above search term, Through the communication circuit above, the first target command is transmitted to the first application server, and Through the communication circuit above, first application data corresponding to the first target command is received from the first application server, and Through the communication circuit above, the second target command is transmitted to the second application server, and Through the communication circuit above, second application data corresponding to the second target command is received from the second application server, and An electronic device that stores the first application data and the second application data in the memory.

7. In Paragraph 6, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Using the above second AI model, a fourth prompt requesting a result for the above fourth user input is generated, and Through the communication circuit above, the fourth prompt, the first application data, and the second application data are transmitted to the AI ​​server, and Through the communication circuit above, result information corresponding to the fourth prompt is received from the AI ​​server, and Based on the above result information, a first result UI is generated, and An electronic device that controls the display to display the first result UI.

8. In Paragraph 7, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Using the above-mentioned first AI model, a second result UI is obtained based on the above-mentioned result information and the above-mentioned user profile, and An electronic device that controls the display to display the second result UI.

9. In Paragraph 8, The above first result UI is, Includes an image representing the above-mentioned second AI model, The above second result UI is, An electronic device comprising an image representing the first AI model.

10. In Paragraph 1, The above AI server is, An electronic device including an LLM (Large Language Model).

11. A method for controlling an electronic device connected to an AI server, When a first user input requesting an AI model for controlling the electronic device is received, a step of obtaining a user profile related to the usage history of the electronic device; A step of generating a first prompt based on the above user profile; A step of transmitting the first prompt and the user profile to the AI ​​server; A step of receiving a first AI model corresponding to the first prompt from the AI ​​server; When a second user input requesting an AI model to control a target folder is received, a step of obtaining target folder information related to at least one application included in the target folder; A step of generating a second prompt based on the above target folder information; A step of transmitting the second prompt and the target folder information to the AI ​​server; A step of receiving a second AI model corresponding to the second prompt from the AI ​​server; and A control method comprising the step of storing the first AI model and the second AI model in the electronic device.

12. In Paragraph 11, The above user profile is, A control method comprising at least one of name, account, age, gender, region, language, preferred category, application usage history, and feedback data.

13. In Paragraph 11, The above target folder information is, It includes application information for at least one application included in the above target folder, and The above application information is, A control method comprising at least one of an application name, a representative image, and a main function.

14. In Paragraph 11, The above-mentioned first AI model is, It is a model trained to control the aforementioned electronic device as a first AI personality, and The above second AI model is, A control method, which is a model trained to control operations related to the target folder with a second AI personality different from the first AI personality.

15. In Paragraph 11, The above control method is, When a third user input selecting the target folder is received, a step of obtaining target user data corresponding to the target folder among the user profiles; A step of generating a third prompt requesting a guide for the target folder based on the target user data using the second AI model; A step of transmitting the above third prompt and the above target user data to the AI ​​server; A step of receiving guide information corresponding to the third prompt above; A step of generating a guide UI based on the above guide information; and A control method comprising the step of displaying the above guide UI.

Images