WO2025198384A1 - Electronic device, method, server, and storage medium for performing generative task for language-based command - Google Patents

Abstract

According to an embodiment, a method for processing a language-based command may comprise an operation of providing a first user interface for inputting a language-based command. The method may include an operation of receiving the language-based command input on the basis of the first user interface. The method may include an operation of providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected on the basis of the results of analyzing the language-based command. The method may include an operation of receiving an execution command input on the basis of the second user interface. The method may include an operation of providing an execution result based on the first generative AI model in response to the execution command.

Description

Electronic devices, methods, servers, and storage media for performing generative operations on language-based commands

The present disclosure relates to an electronic device, method, server, and storage medium for performing a generative operation on language-based commands.

Analytical AI (analytical AI) models can perform data analysis and/or pattern recognition. In contrast, generative AI models can generate data or content in response to user input and provide this generated content. As the development of deep learning models used in generative AI models advances, the quality of the data or content they provide is also improving.

The types of generation tasks may include, for example, text generation, image generation, code generation, voice generation, and/or video generation. Users can select an AI model that supports the desired generation task, access the entity providing the service for that AI model, and check the execution results of the AI model.

The above information may be provided as background information to aid in understanding this document. None of the above is claimed to be prior art related to this document or can be used to determine prior art.

According to one embodiment, a method for processing a language-based command may include providing a first user interface for inputting a language-based command. The method may include receiving a language-based command input based on the first user interface. The method may include providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected based on an analysis result of the language-based command. The method may include receiving an execution command input based on the second user interface. The method may include providing an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, a storage medium storing at least one computer-readable instruction may be provided. The at least one instruction, when executed individually or collectively by one or more processors comprising processing circuitry of an electronic device, may cause the electronic device to perform at least one operation. The at least one method may include providing a first user interface for inputting a language-based command. The at least one method may include receiving a language-based command input based on the first user interface. The at least one method may include providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected based on an analysis result of the language-based command. The at least one method may include receiving an execution command input based on the second user interface. The at least one method may include providing an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, an electronic device may include one or more processors including processing circuitry. According to one embodiment, the electronic device may include a memory storing at least one instruction. The at least one instruction, when individually or collectively executed by the one or more processors of the electronic device, may cause the electronic device to perform at least one operation. The at least one operation may include providing a first user interface for receiving a language-based command. The at least one operation may include receiving a language-based command input based on the first user interface. The at least one operation may include providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected based on an analysis result of the language-based command. The at least one operation may include receiving an execution command input based on the second user interface. The at least one action may include an action that provides an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, a method for processing a language-based command may include receiving a language-based command. The method may include identifying a type of a generation task based on an analysis result of the language-based command. The method may include identifying a first generative artificial intelligence (AI) model corresponding to the identified type of the generation task. The method may include providing an execution result based on the first generative AI model.

According to one embodiment, a storage medium storing at least one computer-readable instruction may be provided. The at least one instruction, when executed individually or collectively by one or more processors comprising processing circuitry of an electronic device, may cause the electronic device to perform at least one operation. The at least one operation may include receiving a language-based instruction. The at least one operation may include identifying a type of a generation task based on an analysis result of the language-based instruction. The at least one operation may include identifying a first generative artificial intelligence (AI) model corresponding to the identified type of generation task. The at least one method may include providing an execution result based on the first generative AI model.

According to one embodiment, an electronic device may include one or more processors including processing circuitry. According to one embodiment, the electronic device may include a memory storing at least one instruction. The at least one instruction, when individually or collectively executed by one or more processors of the electronic device, may cause the electronic device to perform at least one operation. The at least one operation may include receiving a language-based instruction. The at least one operation may include identifying a type of a generation task based on an analysis result of the language-based instruction. The at least one operation may include identifying a first generative artificial intelligence (AI) model corresponding to the identified type of the generation task. The at least one operation may include providing an execution result based on the first generative AI model.

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

FIG. 1A is a diagram illustrating an electronic device and a server according to one embodiment.

FIG. 1b is a drawing for explaining an electronic device and a server according to one embodiment.

FIG. 1c is a drawing for explaining an electronic device and a server according to one embodiment.

FIG. 1D is a drawing for explaining an electronic device and a server according to one embodiment.

FIG. 2 is a drawing for explaining an electronic device and a server according to one embodiment.

FIG. 3 is a drawing for explaining an operation method of an electronic device and a server according to one embodiment.

Figure 4a is an example of various UIs.

Figure 4b is an example of various UIs.

Figure 4c is an example of various UIs.

Figure 4d is an example of various UIs.

FIG. 5a is a diagram for explaining an operation method of a server according to one embodiment.

FIG. 5b is a diagram for explaining the operation of a module of a server according to one embodiment.

FIG. 6a is a diagram for explaining an operation method of a server according to one embodiment.

Figure 6b is an example of a UI according to one embodiment.

FIG. 7a is a diagram for explaining an operation method of a server according to one embodiment.

Figure 7b is an example of a UI according to one embodiment.

FIG. 8a is a diagram for explaining an operation method of a server according to one embodiment.

Figure 8b is an example of a UI according to one embodiment.

FIG. 9a is a diagram for explaining an operation method of a server according to one embodiment.

Figure 9b is an example of a UI according to one embodiment.

FIG. 10 is a drawing for explaining an operating method of an electronic device according to one embodiment.

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

FIG. 1A is a drawing for explaining an electronic device and a server according to one embodiment.

Referring to FIG. 1A, a server (100) can transmit and/or receive data with an electronic device (101). The electronic device (101) is not limited to any device capable of transmitting and receiving data with the server (100), such as a computer or a mobile electronic device (e.g., a smart phone or a tablet PC). The server (100) may include and/or execute a frontend module (111), a prompt processing module (112), an AI model selection module (113), a UI generation module (114), and/or at least one AI model repository (120, 130, 140). At least one module (111, 112, 113, 114) may be executed by, for example, at least one processor included in the server (100), or may be included as at least a part of the processor. At least some of the operations performed by at least one module (111, 112, 113, 114) in the present disclosure may be understood to be performed by, for example, at least one processor included in the server (100) and/or another entity under the control of the processor. For example, the electronic device (101) may provide an execution result of an AI model in conjunction with the server (100), and this may be referred to as a non-standalone type. Meanwhile, depending on the implementation, the electronic device (101) alone may provide an execution result of an AI model, and this may be referred to as a standalone type or an on-device type, which will be described with reference to FIGS. 1c and/or 1d. The server (100) may include a cloud server, an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server, and may be implemented as one or more entities, and there is no limitation on the form of implementation.

The front-end module (111) can perform at least one operation for exchanging data with, for example, the electronic device (101). For example, the front-end module (111) can provide data that can configure a UI that can input user input in the electronic device (101). For example, the front-end module (111) can be implemented as a web server, but there is no limitation thereto. The electronic device (101) can access the front-end module (111), for example, based on a URL entered in a web browsing application, or by executing an application, but there is no limitation on the access method. The front-end module (111) can provide processing for a user request to at least one other module. The at least one other module can be referred to as a back-end module. The back-end module can provide a generated result corresponding to an input language-based command to the front-end module (111). The front-end module (111) can provide a generation result corresponding to a language-based command to the electronic device (101).

For example, the prompt processing module (112) may process a language-based command received from the electronic device (101) and provide the processing result to the AI model selection module (113). The AI model selection module (113) may select an AI model to perform a generation task corresponding to the language-based command among a plurality of AI models (120A, 120B, ..., 120L, 130A, 130B, ..., 130M, 140A, 140B, ..., 140N). Meanwhile, those skilled in the art will understand that the prompt processing module (112) and the AI model selection module (113) may be implemented as one.

In one example, the prompt processing module (112) and/or the AI model selection module (113) can identify a type (or, which may be named a category) of a generation task corresponding to a language-based command based on a rule-based approach, such as comparing the parsing result for the language-based command with keywords. The type of generation task may include, but is not limited to, text generation, image generation, code generation, voice generation, and/or video generation. The generative AI model may include, for example, a text generation AI model. The text generation AI model may provide various text-based outputs in response to a user's prompt, such as an essay on a specific topic, a summary of an input paragraph, or an answer to an inquiry. The generative AI model may include, for example, an image generation AI model. The image generation AI model may generate and provide an image corresponding to a prompt input by the user. The generative AI model may include, for example, a code generation AI model. A code-generating AI model can generate and provide executable code in response to a user-entered prompt. Generative AI models may include, for example, a voice-generating AI model. The voice-generating AI model can generate and provide music in response to a user-entered prompt, or generate and provide a voice that mimics a human voice in response to a user-entered prompt. Generative AI models may include, for example, a video-generating AI model. The video-generating AI model can generate and provide a video in response to a user-entered prompt.

The prompt processing module (112) and/or the AI model selection module (113) may select at least one AI model corresponding to the type of the identified generation task. For example, the prompt processing module (112) and/or the AI model selection module (113) may determine that “draw” corresponds to a keyword of the category of the image generation task in the parsing result of the language-based command “draw a picture of a boy with a lonely face walking down a dark night street in a cartoon style.” For example, the prompt processing module (112) and/or the AI model selection module (113) may select any one of the image generation AI models (130A, 130B, ..., 130M) stored in a storage (e.g., storage (130)) corresponding to the category of the image generation task. For example, the prompt processing module (112) and/or the AI model selection module (113) may select an image generation AI model based on the analysis result of the language-based command. For example, the prompt processing module (112) and/or the AI model selection module (113) may select an AI model that is confirmed to have relatively good cartoon image generation performance based on the keyword “cartoon style.” Meanwhile, those skilled in the art will understand that the above-described keyword-based category and/or AI model confirmation method is merely exemplary, and that this may also be performed based on NLU (natural language understanding) (or natural language processing, NLP). The server (100) may also confirm the category and/or AI model based on the execution result of, for example, an LLM (large language model) for AI model selection, for example, a sLLM (small LLM). Meanwhile, those skilled in the art will understand that, depending on the implementation, the prompt processing module (112) and/or the AI model selection module (113) may confirm an AI model that will perform the generation task directly without performing the process of confirming the category. Meanwhile, in the embodiment of FIG. 1a, although the category-specific repositories (120, 130, 140) are shown as being separated, this is exemplary and there is no limitation on the management and/or number of repositories.

The UI generation module (114) can generate a UI based on the selected AI model. For example, the UI generation module (114) can generate a UI for receiving input values of the selected AI model. Alternatively, the UI generation module (114) can generate a UI that selects and/or reflects at least some of the input values of the selected AI model. For example, the UI generation module (114) can identify parameters that constitute the UI and their corresponding values based on the analysis results of language-based commands. The UI generation module (114) can also generate a UI based on the identified information.

FIG. 1b is a drawing for explaining an electronic device and a server according to one embodiment.

In contrast to the embodiment of FIG. 1A, in the embodiment of FIG. 1B, the server (100) may not store and/or manage AI models. The server (100) may transmit and/or receive data with external AI model providers (121A, 121B, ..., 121L, 131A, 131B, ..., 131M, 141A, 141B, ..., 141N). As described above, the server (100) may receive language-based commands from the electronic device (101). Based on the analysis results of the language-based commands, the server (100) may identify a category of a generation task corresponding to the language-based commands and/or an AI model to perform the generation task.

For example, the server (100) may identify the second image AI model as an AI model to perform a generation task. In this case, the server (100) may request the second image AI model provider (131B) to perform a generation task. The generation task performance request may include at least one piece of information identified based on the UI of the second image AI model, but is not limited thereto. The second image AI model provider (131B) may generate an image in response to the received request and provide the image to the server (100). The server (100) may provide the received image to the electronic device (101). Alternatively, the second image AI model provider (131B) may directly transmit the generated image to the electronic device (101).

Alternatively, the server (100) may provide the electronic device (101) with information indicating that the second image AI model is selected, information for executing an application corresponding to the second image AI model, and/or connection information corresponding to the second image AI model provider (121B). The electronic device (101) may directly connect to the second image AI model provider (131B) based on the information received from the server (100). In this case, the electronic device (101) may request the second image AI model provider (131B) to perform a generation task. The second image AI model provider (131B) may generate an image in response to the received request and provide the image to the electronic device (101).

FIG. 1c is a drawing for explaining an electronic device and a server according to one embodiment.

In the embodiment of FIG. 1C, the electronic device (101) can perform AI model selection without being connected to the server (100). For example, the electronic device (101) may include a prompt processing module (112), an AI model selection module (113), and/or a UI generation module (114). As described above, at least one module (112, 113, 114) may identify an AI model to perform a generation task based on a language-based command. The electronic device (101) may not store and/or manage the AI model. The electronic device (101) may transmit and/or receive data with external AI model providers (121A, 121B, ..., 121L, 131A, 131B, ..., 131M, 141A, 141B, ..., 141N). For example, the electronic device (101) may identify the second image AI model as an AI model to perform a generation task. In this case, the electronic device (101) may request the second image AI model provider (131B) to perform a generation task. The request to perform the generation task may include at least one piece of information identified based on the UI of the second image AI model, but there is no limitation. The second image AI model provider (131B) may generate an image in response to the received request and provide the image to the electronic device (101). The server (100) may provide the received image to the electronic device (101).

FIG. 1d is a drawing for explaining an electronic device and a server according to one embodiment.

In the embodiment of FIG. 1D, the electronic device (101) can perform AI model selection without being connected to the server (100). For example, the electronic device (101) can include a prompt processing module (112), an AI model selection module (113), and/or a UI generation module (114). The electronic device (101) can store and/or manage a plurality of AI models (120A, 120B, ..., 120L, 130A, 130B, ..., 130M, 140A, 140B, ..., 140N). As described above, at least one module (112, 113, 114) can identify an AI model to perform a generation task based on a language-based command. The electronic device (101) can, for example, execute a second image AI model (120B) and provide a result of the generation task.

FIG. 2 is a drawing for explaining an electronic device and a server according to one embodiment.

Referring to FIG. 2, the electronic device (101) may include a processor (211), a memory (212), a communication device (213), a display (214), and/or an input device (215). The server (100) may include a processor (221), a memory (222), and/or a communication device (223). As described with reference to FIGS. 1A to 1D , at least some of at least one operation performed by the server (100) described in the present disclosure may also be performed by the electronic device (101). For example, as instructions stored in the memory (212) of the electronic device (101) are performed by the processor (211), the electronic device (101) may perform at least some of the various operations of the present disclosure. For example, as instructions stored in the memory (222) of the server (100) are executed by the processor (221), the server (100) can perform at least some of the various operations of the present disclosure.

The processor (211) and/or the processor (221) may, for example, execute software (e.g., a program) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) and/or the server (100), and may perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (211) and/or the processor (221) may store instructions or data received from another component (e.g., a communication device (213) and/or a communication device (223)) in the memory (212) and/or the memory (222) (e.g., but not limited to, a volatile memory), process the instructions or data stored in the volatile memory, and store the resulting data in the memory (212) and/or the memory (222) (e.g., but not limited to, a non-volatile memory). According to one embodiment, the processor (211) and/or the processor (221) may include, but is not limited to, a central processing unit (CPU), a GPU, and/or a neural processing unit (NPU), including circuitry.

The memory (212) and/or the memory (222) may store various data used by at least one component of the electronic device (101) and/or the server (100). The data may include, for example, software (e.g., a program) and input data or output data for commands related thereto. The electronic device (101) and/or the server (100) may include volatile memory and/or non-volatile memory. The electronic device (101) and/or the server (100) may include a hard disk, a ROM, a RAM, a cache memory, and/or a register, and the implementation thereof is not limited thereto. Some of the above-described entities (e.g., a register, but is not limited thereto) may be implemented as a part of the electronic device (101) and/or the server (100), and the implementation form thereof is not limited thereto. The electronic device (101) and/or the server (100) may store at least one generative AI model.

The processor (211) and/or the processor (221) may execute instructions in, for example, the memory (212) and/or the memory (222). The memory (212) and/or the memory (222) may store at least one instruction, and the at least one instruction may be executed by the processor (211) and/or the processor (221). The at least one instruction, when executed by the processor (211) and/or the processor (221), may cause the electronic device (101) and/or the server (100) to perform at least one operation. For example, as the at least one instruction is executed, at least one other component may be controlled, and/or various data processing or operations may be performed. As at least a part of data processing or calculation, the processor (211) and/or the processor (221) may store instructions or data received from other components in at least a part of the memory (212) and/or the memory (222), process the instructions or data stored in the memory (212) and/or the memory (222), and store result data in the memory (212) and/or the memory (222). The fact that one operation is performed by the processor (211) and/or the processor (221) may mean, for example, that the operation is performed by (or under the control of) one entity included in the processor (211) and/or the processor (221) (for example, but not limited to, a main processor). For example, the fact that one operation is performed may mean, for example, that a specific operation is performed by (or under the control of) a plurality of entities (for example, a plurality of processors). For example, performing a plurality of operations may mean that all of the operations are performed by (or under the control of) a single entity (e.g., but not limited to, a main processor). For example, performing a plurality of operations may mean that some of the operations are performed by at least one entity, and some of the operations are performed by at least another entity. For example, at least one instruction causing one or more operations to be performed may be stored in a single memory, or may be stored distributedly in each of a plurality of memories.

The communication device (213) and/or the communication device (223) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and the server (100), and the performance of communication through the established communication channel. The communication device (213) and/or the communication device (223) may include one or more communication processors that support direct (e.g., wired) communication or wireless communication, but is not limited thereto. According to one embodiment, the communication device (213) and/or the communication device (223) may include an Ethernet-based wired communication module (e.g., a local area network (LAN) communication module, or a power line communication module). The communication device (213) and/or the communication device (223) may also include a wireless communication module, but is not limited thereto. At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

The display (214) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display (214) can include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. The input device (215) can receive input from the user. According to one embodiment, the display (214) and the input device (215) can be implemented as a touch display. Meanwhile, although not shown, an input/output device based on voice input/output, such as a microphone/speaker, may be further included in the electronic device (101).

FIG. 3 is a diagram for explaining an operation method of an electronic device and a server according to one embodiment. The embodiment of FIG. 3 will be described with reference to FIGS. 4A to 4D . FIGS. 4A to 4D are examples of various UIs. Meanwhile, as described with reference to FIGS. 1A to 1D , those skilled in the art will understand that at least some of the operations performed by the server (100) may be performed by the electronic device (101), and/or some operations may be omitted.

According to one embodiment, the server (100) may, in operation 301, provide at least one first data for representing a first UI for inputting a language-based command to the electronic device (101). The electronic device (101), in operation 303, may perform at least one operation for representing a first UI (410) for inputting a language-based command, for example, as in FIG. 4A, based on the at least one first data. Referring to FIG. 4A, the first UI (410) may include an input window (420) for inputting a language-based command. The input window (420) may include a language-based command, and thus, a user may confirm the language-based command currently input by the user. In the example of FIG. 4a, it is illustrated that the input window (420) includes an icon (421) for sending a language-based command, an icon (422) for attaching a file, and/or a placeholder (423) for inducing message input, but this is exemplary and there is no limitation on the implementation of the input window (420).

For example, the first UI (410) may include an existing language-based command/response history (411, 412) as a UI corresponding to a text-generating AI model, but this is exemplary. The electronic device (101) and/or the server (100) may provide a UI of a generative AI model other than a text-generating AI model as the first UI. Alternatively, the electronic device (101) and/or the server (100) may provide a UI for selecting an AI model as the first UI. The UI for selecting an AI model may include, for example, an input window (420) as in FIG. 4A, but there is no limitation on its implementation form. Meanwhile, the UI (410) may be provided in an auditory manner in addition to a visual expression manner. For example, the electronic device (101) may induce the user to utter a language-based command by outputting a voice such as "How may I help you?"

Referring back to FIG. 3, the electronic device (101) may receive a language-based command through the first UI in operation 305. The electronic device (101) may transmit the language-based command to the server (100) in operation 307. For example, the electronic device (101) may additionally display a soft input panel (SIP) and may express a language-based command input through the SIP in the input window (420). Alternatively, the electronic device (101) may express a language-based command corresponding to an input through an accessory (e.g., a keyboard) in the input window (420). For example, as in FIG. 4b, the electronic device (101) may express the received language-based command (428) in the input window (420), and there is no limitation on the expression method. For example, the electronic device (101) may transmit a language-based command (428) to the server (100) based on the detection of selection of an icon (421) for transmission.

Referring back to FIG. 3, the server (100) may, in operation 309, select an AI model to perform a generation task based on a language-based command. For example, the server (100) may identify the type of generation task based on the analysis results of the language-based command (e.g., rule-based analysis, NLU, and/or LLM, but not limited thereto). For example, the server (100) may identify the type of generation task as image generation based on the analysis results of “Draw a cartoon-style picture of a boy with a lonely face walking down a dark night street.” The server (100) may identify any one of the stored and/or accessible image generation AI models as the AI model to perform the generation task. For example, the server (100) may identify the AI model based on the analysis results of the language-based command. For example, the server (100) may select an AI model with relatively good quality for generating a "cartoon" image based on the analysis results for "draw a picture of a boy with a lonely face walking down a dark night street in a cartoon style", but there is no limitation on the method of confirmation.

For example, Table 1 is an example of characteristics of each image generation AI model managed by the server (100) (or electronic device (101)).

AI model characteristic makeimageAI A bright-toned comic cartoon AI A serious cartoon japan AI Japanese-style comics drawing AI oil painting

The characteristics of each AI model can be set, for example, by an AI model training entity, and/or by an AI model selection entity (e.g., an electronic device (101) and/or a server (100)), but there is no limitation on this, and there is no limitation on the method of setting them. The server (100) can select an AI model to perform a generation task based on the analysis result of “Draw a picture of a boy with a lonely face walking down a dark night street in a cartoon style” and the characteristics of each AI model set as in Table 1, but there is no limitation on this.

The server (100) may, in operation 311, configure a second UI (440) based on a selected AI model, for example, as in FIG. 4c. In operation 313, the server (100) may provide at least one second data for representing the second UI (440) to the electronic device (101). The electronic device (101) may, in operation 315, represent the second UI (440) based on the received at least one second data. As in FIG. 4c, the second UI (440) may include at least one parameter (440, 445, 450, 455, 460, 465) and corresponding values (442, 446, 461, 456, 461, 466) required by the selected AI model (or received as an input value). The server (100) can set a value (442, 446, 461, 456, 461, 466) corresponding to at least one parameter (440, 445, 450, 455, 460, 465) based on the analysis result of the language-based command and/or set it as a default value.

For example, a value corresponding to a parameter (441) of a filter may be set to "cartoon" (442). For example, the server (100) may determine that the value corresponding to the parameter (441) of the filter is the value (442) of "cartoon" based on the analysis result of the language-based command. Accordingly, the server (100) may set the value corresponding to the parameter (441) of the filter of the second UI (440) to "cartoon" (442). If a value corresponding to the parameter of the filter is not determined from the language-based command, the server (100) may set the value corresponding to the parameter of the filter to a default value or a value determined based on the usage history (e.g., a value used in the past). Alternatively, if a value corresponding to the parameter of the filter is not determined from the language-based command, the server (100) may exclude the corresponding parameter from the UI. Meanwhile, in the example of FIG. 4C, a function icon (443) for selecting another filter may be further included. When icon (443) is selected, other selectable values may be provided.

For example, the value corresponding to the parameter (445) of the prompt can be set to "Draw a picture of a boy with a lonely face walking down a dark night street in a cartoon style" (446). The server (100) can, for example, set a language-based command as the value corresponding to the parameter (445) of the prompt. Meanwhile, this is exemplary, and a modified and/or replacement text for the language-based command can also be set as the value corresponding to the parameter (445) of the prompt, which will be described with reference to FIGS. 6A and 6B. Meanwhile, the value corresponding to the excluded image parameter (450) can be set to custom (451), the value corresponding to the image size parameter (455) can be set to "1024x1024" (456), the value corresponding to the work speed and quality parameter (460) can be set to "fast", and the value of the dimming parameter (465) can be set to "dark" (466). As described above, the value corresponding to the parameter may be a value set based on the analysis result of the language-based command, a default value, and/or history, but there is no limitation.

The second UI may be configured, for example, in response to the selected AI model and/or the identified generation task. For example, in the case of a task generating a summary or translation, a second UI including a relatively large text input/output screen (or window) may be provided. For example, in the case of a task generating a question answer, a second UI including a relatively small question input window may be provided. For example, if an image generation AI model is selected, a second UI may be provided that divides the screen according to the number of images to be output. For example, if a code generation AI model is selected, a second UI may be provided that applies markup, such as line numbers and highlighting, to improve code readability.

Referring back to FIG. 3, the electronic device (101) may obtain an AI model execution command through the second UI (440) in operation 317. For example, the user may check at least one parameter-specific value of the second UI (440) expressed by the electronic device (101). The user may also additionally adjust at least some of the at least one parameter-specific value through the second UI (440). When the user confirms that the at least one parameter-specific value of the second UI (440) is appropriate, the user may input an AI model execution command through the second UI (440). The electronic device (101) may transmit the AI model execution command to the server (100) in operation 319. The server (100) may obtain an AI model execution result in operation 321. If the server (100) has stored an AI model, the server (100) may obtain the AI model execution result by inputting an input value composed of parameter-specific values into the AI model. If the server (100) does not store the AI model, it may provide an input value composed of parameter values for the AI model to the AI model provider. The server (100) may also obtain an AI model execution result from the AI model provider. In operation 323, the server (100) may provide at least one third data for expressing the execution result of the AI model to the electronic device (101). In operation 325, the electronic device (101) may provide the AI model execution result. For example, the electronic device (101) may provide an AI model execution result (470) as in FIG. 4d. The AI model execution result (470) may include a generated image (471) and interactive text (472) associated with the generation task, but there is no limitation on the form of implementation. For example, the AI model execution result (470) may include information on which AI model was used. Meanwhile, in the example of FIG. 4d, the generated image (471) may be expressed in the format of the first UI (410) that inputs a language-based command, but this is merely exemplary. For example, the server (100) may provide the generated image (471) based on the format of the second UI or another format, and there is no limitation on the method of expression. As described above, the user can utilize various generative AI models based on text without having to select a different AI model for each generation task or connect to a specific generation task service provider. In addition, at least a portion of the parameter settings of various generative AI models that are difficult for non-experts to access can be automatically generated, thereby improving user accessibility.

FIG. 5A is a diagram for explaining an operation method of a server according to one embodiment. The embodiment of FIG. 5A will be explained with reference to FIG. 5B. FIG. 5B is a diagram for explaining the operation of a module of a server according to one embodiment.

According to one embodiment, the server (108), for example, the prompt processing module (112) in FIG. 5B, may perform analysis of a language-based command in operation 501. For example, the prompt processing module (112) may analyze the language-based command based on, but not limited to, rule-based and/or NLU, and may also obtain analysis results for the language-based command using LLM (e.g., sLLM). The prompt processing module (112) may provide the analysis results to the AI model selection module (113). The server (108), for example, the AI model selection module (113), may select an AI model based on the analysis results in operation 503. For example, the AI model selection module (113) may select one of a plurality of AI models corresponding to the type of the identified generation task, but this is exemplary. The AI model selection module (113) may also select an AI model to perform the generation task without specifying the type of the generation task.

The server (100), for example, the UI generation module (114), can, in operation 505, check at least one parameter of the UI corresponding to the selected AI model. The server (100), for example, the UI generation module (114), can, in operation 507, check at least a portion and a value of at least one parameter based on the language-based command. The server (100), in operation 509, can configure a UI by applying the checked parameters and values. The UI corresponding to the selected AI model can be generated. For example, the parameter extraction module (114b) can extract a value corresponding to at least a portion of at least one parameter corresponding to the AI model based on the analysis result of the language-based command. For example, as described with reference to FIG. 4c, a value corresponding to the filter parameter (440) from the "cartoon style" of the language-based command can be set to "cartoon." Meanwhile, the inclusion of the parameter extraction module (114b) in the UI generation module (114) is exemplary, and those skilled in the art will understand that the parameter extraction module (114b) may be included in another module (e.g., the prompt processing module (112) and/or the AI model selection module) or implemented independently from another module. The UI configuration module (114a) may generate a UI based on information about the selected AI model and the parameter extraction results. For example, the UI generation module (114) may exclude parameters that are not confirmed from language-based commands from the UI or set default values.

FIG. 6A is a diagram illustrating a method of operating a server according to one embodiment. The embodiment of FIG. 6A will be described with reference to FIG. 6B. FIG. 6B is an example of a UI according to one embodiment.

According to one embodiment, the server (100) may analyze a language-based command in operation 601. The server (100) may select an AI model based on the analysis result of the language-based command in operation 603. The server (100) may change at least a portion of the language-based command in response to the selected AI model in operation 605. For example, the server (100) may identify an image generation AI model as the AI model to perform the generation task based on the analysis of the language-based command. The image generation AI model may request, for example, elements of the prompt, a description of an object included in the image, a description of the background, a description of a scene, a description of a filter, a description of an attribute (e.g., brightness), etc. The server (100) may identify at least one element of the prompt based on the language-based command. For example, the server (100) may identify, from the language-based command, that the description of the object is "a boy with a lonely face." For example, the server (100) can determine from the language-based command that the description of the background is "the background is a dark night street." For example, the server (100) can determine from the language-based command that the description of the scene is "the scene description is a boy walking down a street at night." For example, the server (100) can determine from the language-based command that the description of the filter is "the filter is cartoon-style." For example, the server (100) can determine from the language-based command that the description of the attribute is "the brightness is set to dark." In operation 607, the server (100) can configure a UI that includes the changed command. For example, referring to FIG. 6b, the value (446) corresponding to the prompt parameter (445) of the second UI (440) may be different from "Draw a picture of a boy with a lonely face walking down a dark night street in a cartoon-style" (446) in FIG. 4c. The server (100) can identify a value (446) corresponding to a prompt parameter (445) of the second UI (440) by distinguishing elements of the prompt corresponding to the selected AI model identified as described above, such as a description of an object included in an image, a description of a background, a description of a scene, a description of a filter, and a description of a property (e.g., brightness). By distinguishing elements of the prompt corresponding to the selected AI model, the accuracy of the generation task can be improved.

FIG. 7A is a diagram illustrating a method of operating a server according to one embodiment. The embodiment of FIG. 7A will be described with reference to FIG. 7B. FIG. 7B is an example of a UI according to one embodiment.

The server (100) may, in operation 701, provide at least one first data for representing a first UI for inputting a language-based command to the electronic device (101). The electronic device (101) may, in operation 703, perform at least one operation for representing a first UI for inputting a language-based command based on the at least one first data. The electronic device (101) may, in operation 705, receive a language-based command through the first UI. For example, as described with reference to FIG. 3, the electronic device (101) may receive a language-based command based on an input through SIP or an input through a connected accessory (e.g., a keyboard), but there is no limitation on the method of receiving the command, and the language-based command may also be received through a voice recognition function. The electronic device (101) may, in operation 707, transmit the language-based command to the server (100). The server (100) may, in operation 709, select an AI model based on a language-based command. The server (100) may analyze the language-based command based on rules and/or NLU, but is not limited thereto, and may also obtain analysis results for the language-based command using LLM (e.g., sLLM). The server (100) may select an AI model based on the analysis results. For example, the server (100) may select any one of a plurality of AI models corresponding to the type of the identified generation task, but this is exemplary. The server (100) may also select an AI model to perform the generation task without specifying the type of the generation task.

The server (100) may, in operation 711, inquire about whether to use the selected AI model. For example, the server (100) may transmit information about the selected AI model to the electronic device (101). The electronic device (101) may, for example, provide a text (722) inquiring about the results of understanding language-based commands and whether to use the selected AI model, as in FIG. 7B . The electronic device (101) may provide an icon (723) indicating the use of the selected AI model and an icon (724) indicating that the AI model is not to be used.

Referring back to FIG. 7A, the electronic device (101) can confirm the use of the selected AI model in operation 713. For example, the electronic device (101) can confirm the use of the selected AI model by confirming the selection of the icon (723) as in FIG. 7B, but there is no limitation on the method of confirmation. The electronic device (101) can provide the server (100) with confirmation of the use of the selected AI model in operation 715. The server (100) can obtain an AI model execution result based on the confirmation of the use of the selected AI model in operation 717. For example, the server (100) can obtain the AI model execution result by executing a stored AI model or connecting to a corresponding AI model provider. The server (100) can provide the electronic device (101) with at least one third data for representing the AI model execution result in operation 719. The electronic device (101) can provide the AI model execution result in operation 721.

FIG. 8A is a diagram illustrating a method of operating a server according to one embodiment. The embodiment of FIG. 8A will be described with reference to FIG. 8B. FIG. 8B is an example of a UI according to one embodiment.

In operation 801, the server (100) may provide at least one first data for representing a first UI for inputting a language-based command to the electronic device (101). In operation 803, the electronic device (101) may perform at least one operation for representing a first UI for inputting a language-based command based on the at least one first data. In operation 805, the electronic device (101) may receive a language-based command through the first UI. In operation 807, the electronic device (101) may transmit the language-based command to the server (100).

The server (100), in operation 809, can check a list of AI models based on a language-based command. For example, the server (100) can check a list of AI models capable of performing the identified generation task based on the language-based command, or a list of AI models suitable for performing the generation task. For example, the server (100) can check that the type of the generation task is an image generation type, and can check a list of AI models capable of performing image generation. The server (100) can analyze the language-based command based on a rule basis and/or NLU, but is not limited thereto, and can also obtain analysis results for the language-based command using an LLM (e.g., sLLM). For example, the server (100) can check a list of AI models corresponding to the type of the identified generation task, but this is exemplary. The server (100) can also check a list of AI models capable of performing the generation task even without the type of the generation task. The server (100) can provide a list of AI models to the electronic device (101) in operation 811.

The electronic device (101) may provide a list of received AI models in operation 813. For example, as shown in FIG. 8B, the electronic device (101) may provide a UI (820) including information (822) related to the AI model list. The UI (820) may also include language-based commands (821). Referring again to FIG. 8A, the electronic device (101) may confirm a selection of one of the AI model lists in operation 813. For example, the user may input information about one of the selections based on information (822) about the list. The electronic device (101) may provide the selected AI model information to the server (100) in operation 815. The server (100) may obtain an AI model execution result based on the selected AI model information in operation 817. For example, the server (100) may obtain an AI model execution result by executing a stored AI model or by connecting to the corresponding AI model provider. In operation 819, the server (100) may provide at least one third data for representing the AI model execution result to the electronic device (101). In operation 821, the electronic device (101) may provide the AI model execution result.

FIG. 9A is a diagram illustrating a method of operating a server according to one embodiment. The embodiment of FIG. 9A will be described with reference to FIG. 9B. FIG. 9B is an example of a UI according to one embodiment.

In operation 901, the server (100) may provide at least one first data for representing a first UI for inputting a language-based command to the electronic device (101). In operation 903, the electronic device (101) may perform at least one operation for representing a first UI for inputting a language-based command based on the at least one first data. In operation 905, the electronic device (101) may receive a language-based command through the first UI. In operation 907, the electronic device (101) may transmit the language-based command to the server (100).

The server (100) may select an AI model based on a language-based command in operation 909. The server (100) may analyze the language-based command based on, but is not limited to, rule-based and/or NLU, and may also obtain analysis results for the language-based command using LLM (e.g., sLLM). The server (100) may select an AI model based on the analysis results. For example, the server (100) may select any one of a plurality of AI models corresponding to the type of the identified generation task, but this is exemplary. The server (100) may also select an AI model to perform the generation task without specifying the type of the generation task. The server (100) may obtain an AI model execution result in operation 911. For example, the server (100) may obtain an AI model execution result by executing a stored AI model or by connecting to a corresponding AI model provider. In the embodiment of FIG. 9A, the selected AI model can be executed without providing a UI associated with the selected AI model. The server (100) may, in operation 911, provide at least one third data for representing the AI model execution result to the electronic device (101). The electronic device (101) may, in operation 913, provide the AI model execution result. Along with the AI model execution result, information related to the AI model may also be provided to the electronic device (101). For example, as in FIG. 9B, the electronic device (101) may provide a screen (920) including a generated image (921). For example, the electronic device (101) may also provide information (922) related to the AI model used to generate the image along with the generated image (921).

FIG. 10 is a drawing for explaining an operation method of an electronic device according to one embodiment.

For example, the electronic device (101) may be implemented as a robot including at least one driving device (e.g., an actuator and/or a motor). The electronic device (101) may cause movement of at least a portion of the electronic device (101) by driving at least a portion of the at least one driving device of the electronic device (101) in response to a language-based command. Accordingly, the electronic device (101) may perform at least one action requested by the user. In order for the electronic device (101), such as a robot, to be capable of performing general-purpose driving for various purposes rather than only performing actions for specific purposes, the electronic device (101) needs to utilize multiple action AI models specialized for each purpose. For example, an action AI model for “performing dishwashing” and an action AI model for “carrying luggage” need to be trained differently. The electronic device (101) may, for example, store and/or be able to access multiple action AI models.

For example, the electronic device (101) may analyze a language-based command in operation 1001. The electronic device (101) may select an action AI model based on the analysis result in operation 1003. The electronic device (101) may identify an action task corresponding to the language-based command based on, for example, the analysis result of the language-based command (which may be, for example, rule-based analysis, NLU, and/or LLM, but is not limited thereto). For example, the electronic device (101) may identify the action task based on a keyword included in the language-based command. For example, the electronic device (101) may identify the action task based on the intention for the language-based command. For example, the electronic device (101) may identify the intention by using an artificial intelligence model for intent analysis or by performing prompting to inquire about the intention of the language-based command, but there is no limitation on the method of identifying the intention.

The electronic device (101) can, in operation 1005, check at least a portion and a value of at least one parameter corresponding to the selected action AI model. In operation 1007, the electronic device (101) can check the execution result of the action AI model based on the checked parameters and values. In operation 1009, the electronic device (101) can drive at least a portion of the electronic device (101) based on the execution result. For example, the electronic device (101) may assume that a language-based command such as “Clean the floor thoroughly for 30 minutes” has been obtained. The electronic device (101) can check the action type as “Cleaning” based on the language-based command. The electronic device (101) can, based on the analysis result of the language-based command, check the cleaning type (e.g., clean the floor), the cleaning time (e.g., 30 minutes), and the cleaning intensity (e.g., do it thoroughly) as at least a portion of the at least one parameter corresponding to the action type of “Cleaning.” The electronic device (101) can be driven based on at least a portion of at least one identified parameter and its value, thereby driving the identified floor cleaning at a thorough level for 30 minutes.

According to one embodiment, a method for processing a language-based command may include providing a first user interface for inputting a language-based command. The method may include receiving a language-based command input based on the first user interface. The method may include providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected based on an analysis result of the language-based command. The method may include receiving an execution command input based on the second user interface. The method may include providing an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, the second user interface may include information about at least one parameter required by a generation task by the first generative AI model and at least one value corresponding to each of the at least one parameter.

According to one embodiment, a value corresponding to at least some of the at least one parameter can be identified based on an analysis result of the language-based command.

According to one embodiment, a parameter among the at least one parameter required by the generation task by the first generative AI model that is not confirmed based on the language-based command may be excluded from the second user interface.

According to one embodiment, among the at least one parameter required by the generation task by the first generative AI model, a parameter identified based on the language-based command and a parameter not identified based on the language-based command can be expressed to be distinct.

According to one embodiment, the second user interface may include a prompting field as one of the information for at least one parameter required by the generation task by the first generative AI model.

According to one embodiment, the prompting field may include the language-based command.

In one embodiment, the prompting field may include text that is adjusted based on the language-based command and/or generated based on the language-based command.

According to one embodiment, the operation of providing a second user interface corresponding to the first generative AI model selected based on the analysis result of the language-based command may include the operation of providing a list of AI models capable of performing a generation task corresponding to the language-based command based on the analysis result of the language-based command. The operation of providing the second user interface may include the operation of providing a second user interface corresponding to the first generative AI model based on confirming a selection of the first generative AI model from the list of AI models.

According to one embodiment, the method may include selecting the first generative AI model based on the analysis results of the language-based command.

According to one embodiment, the method may include an operation of identifying a type of generation task corresponding to the language-based command based on the analysis result of the language-based command. The method may include an operation of identifying a first generative AI model among at least one generative AI model corresponding to the identified type of generation task.

According to one embodiment, a storage medium storing at least one computer-readable instruction may be provided. The at least one instruction, when individually or collectively executed by one or more processors (221, 211) including processing circuitry of an electronic device (100, 101), may cause the electronic device (100, 101) to perform at least one operation. The at least one operation may include providing a first user interface for inputting a language-based command. The at least one operation may include receiving a language-based command input based on the first user interface. The at least one operation may include providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected based on an analysis result of the language-based command. The at least one method may include receiving an execution command input based on the second user interface. The at least one method may include an action of providing an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, the second user interface may include information about at least one parameter required by a generation task by the first generative AI model and at least one value corresponding to each of the at least one parameter.

According to one embodiment, a value corresponding to at least some of the at least one parameter can be identified based on an analysis result of the language-based command.

According to one embodiment, a parameter among the at least one parameter required by the generation task by the first generative AI model that is not confirmed based on the language-based command may be excluded from the second user interface.

According to one embodiment, among the at least one parameter required by the generation task by the first generative AI model, a parameter identified based on the language-based command and a parameter not identified based on the language-based command can be expressed to be distinct.

According to one embodiment, the second user interface may include a prompting field as one of the information for at least one parameter required by the generation task by the first generative AI model.

According to one embodiment, the prompting field may include the language-based command.

In one embodiment, the prompting field may include text that is adjusted based on the language-based command and/or generated based on the language-based command.

According to one embodiment, the operation of providing a second user interface corresponding to the first generative AI model selected based on the analysis result of the language-based command may include the operation of providing a list of AI models capable of performing a generation task corresponding to the language-based command based on the analysis result of the language-based command. The operation of providing the second user interface may include the operation of providing a second user interface corresponding to the first generative AI model based on confirming a selection of the first generative AI model from the list of AI models.

In one embodiment, the at least one action may include selecting the first generative AI model based on the analysis results of the language-based command.

In one embodiment, the at least one operation may include an operation of identifying a type of generation task corresponding to the language-based command based on the analysis result of the language-based command. The at least one operation may include an operation of identifying a first generative AI model among at least one generative AI model corresponding to the identified type of generation task.

According to one embodiment, the electronic device (100, 101) may include one or more processors (221, 211) including processing circuitry. According to one embodiment, the electronic device (100, 101) may include a memory (222, 212) storing at least one instruction. The at least one instruction, when executed by the one or more processors (221, 211) of the electronic device (100, 101), may cause the electronic device (100, 101) to perform at least one operation. The at least one operation may include providing a first user interface for inputting a language-based command. The at least one operation may include receiving a language-based command input based on the first user interface. The at least one operation may include providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected based on the analysis results of the language-based command. The at least one operation may include receiving an execution command input based on the second user interface. The at least one operation may include providing an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, the second user interface may include information about at least one parameter required by a generation task by the first generative AI model and at least one value corresponding to each of the at least one parameter.

According to one embodiment, a value corresponding to at least some of the at least one parameter can be identified based on an analysis result of the language-based command.

According to one embodiment, a parameter among the at least one parameter required by the generation task by the first generative AI model that is not confirmed based on the language-based command may be excluded from the second user interface.

According to one embodiment, among the at least one parameter required by the generation task by the first generative AI model, a parameter identified based on the language-based command and a parameter not identified based on the language-based command can be expressed to be distinct.

According to one embodiment, the second user interface may include a prompting field as one of the information for at least one parameter required by the generation task by the first generative AI model.

According to one embodiment, the prompting field may include the language-based command.

In one embodiment, the prompting field may include text that is adjusted based on the language-based command and/or generated based on the language-based command.

According to one embodiment, the operation of providing a second user interface corresponding to the first generative AI model selected based on the analysis result of the language-based command may include the operation of providing a list of AI models capable of performing a generation task corresponding to the language-based command based on the analysis result of the language-based command. The operation of providing the second user interface may include the operation of providing a second user interface corresponding to the first generative AI model based on confirming a selection of the first generative AI model from the list of AI models.

In one embodiment, the at least one action may include selecting the first generative AI model based on the analysis results of the language-based command.

In one embodiment, the at least one operation may include an operation of identifying a type of generation task corresponding to the language-based command based on the analysis result of the language-based command. The at least one operation may include an operation of identifying a first generative AI model among at least one generative AI model corresponding to the identified type of generation task.

According to one embodiment, a method for processing a language-based command may include receiving a language-based command. The method may include identifying a type of a generation task based on an analysis result of the language-based command. The method may include identifying a first generative artificial intelligence (AI) model corresponding to the identified type of the generation task. The method may include providing an execution result based on the first generative AI model.

According to one embodiment, the operation of identifying a first generative AI model corresponding to the type of the identified generation task may include an operation of identifying the first generative AI model among at least one generative AI model corresponding to the type of the identified generation task.

According to one embodiment, the operation of identifying the first generative AI model among the at least one generative AI model corresponding to the type of the identified generative task may include an operation of identifying the first generative AI model among the at least one generative AI model based on the analysis result of the language-based command.

According to one embodiment, the operation of identifying the first generative AI model among the at least one generative AI model corresponding to the type of the identified generative task may include the operation of providing an AI model list representing the at least one generative AI model. The operation of identifying the first generative AI model may include the operation of identifying the first generative AI model based on identifying a selection of the first generative AI model from the AI model list.

In one embodiment, the act of receiving the language-based command may include the act of providing a first user interface for inputting the language-based command. The act of receiving the language-based command may include the act of receiving the language-based command input based on the first user interface.

According to one embodiment, the operation of providing an execution result based on the first generative AI model may include an operation of providing a second user interface corresponding to the first generative AI model selected based on a result of analyzing the language-based command. The operation of providing an execution result based on the first generative AI model may include an operation of receiving an execution command input based on the second user interface. The operation of providing an execution result based on the first generative AI model may include an operation of providing an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, the second user interface may include information about at least one parameter required by a generation task by the first generative AI model and at least one value corresponding to each of the at least one parameter.

According to one embodiment, a value corresponding to at least some of the at least one parameter can be identified based on an analysis result of the language-based command.

According to one embodiment, a storage medium storing at least one computer-readable instruction may be provided. The at least one instruction, when individually or collectively executed by one or more processors (221, 211) including processing circuitry of an electronic device (100, 101), may cause the electronic device (100, 101) to perform at least one operation. The at least one operation may include receiving a language-based instruction. The at least one operation may include identifying a type of a generation task based on an analysis result of the language-based instruction. The at least one operation may include identifying a first generative artificial intelligence (AI) model corresponding to the identified type of the generation task. The at least one operation may include providing an execution result based on the first generative AI model.

According to one embodiment, the operation of identifying a first generative AI model corresponding to the type of the identified generation task may include an operation of identifying the first generative AI model among at least one generative AI model corresponding to the type of the identified generation task.

According to one embodiment, the operation of identifying the first generative AI model among the at least one generative AI model corresponding to the type of the identified generative task may include an operation of identifying the first generative AI model among the at least one generative AI model based on the analysis result of the language-based command.

According to one embodiment, the operation of identifying the first generative AI model among the at least one generative AI model corresponding to the type of the identified generative task may include the operation of providing an AI model list representing the at least one generative AI model. The operation of identifying the first generative AI model may include the operation of identifying the first generative AI model based on identifying a selection of the first generative AI model from the AI model list.

In one embodiment, the act of receiving the language-based command may include the act of providing a first user interface for inputting the language-based command. The act of receiving the language-based command may include the act of receiving the language-based command input based on the first user interface.

According to one embodiment, the operation of providing an execution result based on the first generative AI model may include an operation of providing a second user interface corresponding to the first generative AI model selected based on a result of analyzing the language-based command. The operation of providing an execution result based on the first generative AI model may include an operation of receiving an execution command input based on the second user interface. The operation of providing an execution result based on the first generative AI model may include an operation of providing an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, the second user interface may include information about at least one parameter required by a generation task by the first generative AI model and at least one value corresponding to each of the at least one parameter.

According to one embodiment, a value corresponding to at least some of the at least one parameter can be identified based on an analysis result of the language-based command.

According to one embodiment, the electronic device (100, 101) may include one or more processors (221, 211) including processing circuitry. According to one embodiment, the electronic device (100, 101) may include a memory (222, 212) storing at least one instruction. The at least one instruction, when executed by the one or more processors (221, 211) of the electronic device (100, 101), may cause the electronic device (100, 101) to perform at least one operation. The at least one operation may include an operation of receiving a language-based instruction. The at least one operation may include an operation of identifying a type of a generation task based on an analysis result of the language-based instruction. The at least one operation may include an operation of identifying a first generative artificial intelligence (AI) model corresponding to the identified type of the generation task. The at least one action may include an action that provides an execution result based on the first generative AI model.

According to one embodiment, the operation of identifying a first generative AI model corresponding to the type of the identified generation task may include an operation of identifying the first generative AI model among at least one generative AI model corresponding to the type of the identified generation task.

According to one embodiment, the operation of identifying the first generative AI model among the at least one generative AI model corresponding to the type of the identified generative task may include an operation of identifying the first generative AI model among the at least one generative AI model based on the analysis result of the language-based command.

According to one embodiment, the operation of identifying the first generative AI model among the at least one generative AI model corresponding to the type of the identified generative task may include the operation of providing an AI model list representing the at least one generative AI model. The operation of identifying the first generative AI model may include the operation of identifying the first generative AI model based on identifying a selection of the first generative AI model from the AI model list.

In one embodiment, the act of receiving the language-based command may include the act of providing a first user interface for inputting the language-based command. The act of receiving the language-based command may include the act of receiving the language-based command input based on the first user interface.

According to one embodiment, the operation of providing an execution result based on the first generative AI model may include an operation of providing a second user interface corresponding to the first generative AI model selected based on a result of analyzing the language-based command. The operation of providing an execution result based on the first generative AI model may include an operation of receiving an execution command input based on the second user interface. The operation of providing an execution result based on the first generative AI model may include an operation of providing an execution result based on the first generative AI model in response to the execution command.

According to one embodiment, the second user interface may include information about at least one parameter required by a generation task by the first generative AI model and at least one value corresponding to each of the at least one parameter.

According to one embodiment, a value corresponding to at least some of the at least one parameter can be identified based on an analysis result of the language-based command.

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

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

One embodiment of the present document may be implemented as software (e.g., a program) including one or more instructions stored in a storage medium (e.g., built-in memory or external memory) readable by a machine (e.g., an electronic device (101) and/or a server (100)). For example, a processor of the machine (e.g., an electronic device (101) and/or a server (100)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

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

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

Claims (15)

In a method of processing language-based commands, An action providing a first user interface for entering language-based commands; An operation of receiving a language-based command input based on the first user interface; An action of providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected based on the analysis results of the language-based command; An operation of receiving an execution command input based on the second user interface; and In response to the above execution command, an operation for providing an execution result based on the first generative AI model How to include. In the first paragraph, A method wherein the second user interface includes information about at least one parameter required by a generation task by the first generative AI model and at least one value corresponding to each of the at least one parameter. In any one of paragraphs 1 and 2, A method in which a value corresponding to at least some of the at least one parameter is identified based on the analysis result of the language-based command. In any one of paragraphs 1 to 3, A method in which a parameter among the at least one parameter required by the generation task by the first generative AI model is excluded from the second user interface if the parameter is not confirmed based on the language-based command. In any one of paragraphs 1 to 4, A method in which at least one parameter required by the generation task by the first generative AI model is expressed so as to be distinct from a parameter identified based on the language-based command and a parameter not identified based on the language-based command. In any one of paragraphs 1 to 5, A method wherein the second user interface includes a prompting field as one of the information for at least one parameter required by a generation task by the first generative AI model. In any one of paragraphs 1 to 6, The above prompting field includes a method for including the above language-based command. In any one of paragraphs 1 to 7, A method wherein the prompting field includes text that is adjusted based on the language-based command and/or generated based on the language-based command. In any one of paragraphs 1 to 8, An action of providing a second user interface corresponding to a first generative AI model selected based on the analysis results of the above language-based commands is: An operation of providing a list of AI models capable of performing a generation task corresponding to the language-based command based on the analysis result of the language-based command; and An operation of providing a second user interface corresponding to the first generative AI model based on confirming a selection of the first generative AI model from the list of AI models. How to include. In any one of paragraphs 1 to 9, An operation of selecting the first AI model based on the analysis results of the above language-based command. How to include more. In any one of paragraphs 1 to 10, An operation of confirming the type of a generation task corresponding to the language-based command based on the analysis result of the language-based command; and An operation of confirming the first generative AI model among at least one generative AI model corresponding to the type of the above-mentioned confirmed generation task. How to include more. In a method of processing language-based commands, Actions that receive language-based commands; An action to determine the type of a creation task based on the analysis results of the above language-based command; An operation of identifying a first generative artificial intelligence (AI) model corresponding to the type of the above-identified generation task; and An operation that provides execution results based on the first generative AI model. How to include. In paragraph 12, The operation of verifying the first generative AI model corresponding to the type of the above-mentioned generation task is as follows: An operation of confirming the first generative AI model among at least one generative AI model corresponding to the type of the above-mentioned generation task. How to include. In any one of paragraphs 12 to 13, Among at least one generative AI model corresponding to the type of the above-mentioned generation task, the operation of confirming the first generative AI model is as follows: An operation of identifying the first generative AI model among the at least one generative AI model based on the analysis result of the language-based command. How to include. In a storage medium storing at least one instruction readable by a computer, The at least one instruction, when executed individually or collectively by one or more processors (221, 211) comprising processing circuitry of the electronic device (100, 101), causes the electronic device (100, 101) to perform at least one operation, At least one of the above actions: An action providing a first user interface for entering language-based commands; An operation of receiving a language-based command input based on the first user interface; An action of providing a second user interface corresponding to a first generative artificial intelligence (AI) model selected based on the analysis results of the language-based command; An operation of receiving an execution command input based on the second user interface; and In response to the above execution command, an operation for providing an execution result based on the first generative AI model A storage medium containing .