Electronic device and method for operating electronic device

Abstract

Provided is a method for operating an electronic device. The method may comprise a step for acquiring a list on the basis of a plurality of recommendation contents acquired from a first artificial intelligence model on the basis of a user input. The method may comprise a step for acquiring a title corresponding to the list from a second artificial intelligence model on the basis of the acquired list. The method may comprise a step for acquiring an image from a third artificial intelligence model on the basis of the acquired title. The method may comprise a step for providing the list, the title corresponding to the list, and the image.

Description

Electronic device and method of operating the electronic device

[0001] The present disclosure relates to an electronic device for providing recommended content and a method for operating the electronic device.

[0002] Recently, Generative Artificial Intelligence (GAI), which generates new data based on input data, has been emerging as a technology utilizing artificial intelligence. Generative AI is a technology that learns the structure and patterns of large-scale data and generates new synthetic data based on input data. Generative AI can produce human-level results in various tasks involving text, images, voice, video, music, and more.

[0003] Meanwhile, there is a growing need for technology that provides users with new content experiences by offering recommended content using generative artificial intelligence technology.

[0004] According to one aspect of the present disclosure, a method for operating an electronic device is provided. The method may include the step of obtaining a list based on a plurality of recommended contents obtained from a first artificial intelligence model based on user input. The method may include the step of obtaining a title corresponding to the list from a second artificial intelligence model based on the obtained list. The method may include the step of obtaining an image from a third artificial intelligence model based on the obtained title. The method may include the step of providing the list, the title corresponding to the list, and the image.

[0005] According to one aspect of the present disclosure, an electronic device is provided. The electronic device comprises: a communication interface; at least one processor including processing circuitry; and a memory for storing instructions, wherein the instructions may be executed individually or collectively by the at least one processor. The electronic device may obtain a list based on a plurality of recommended contents obtained from a first artificial intelligence model based on user input. The electronic device may obtain a title corresponding to the list from a second artificial intelligence model based on the obtained list. The electronic device may obtain an image from a third artificial intelligence model based on the obtained title. The electronic device may provide the list, the title corresponding to the list, and the image.

[0006] According to one aspect of the present disclosure, a computer-readable recording medium may be provided having a program recorded thereon for operating an electronic device and / or any one of the methods described above and below.

[0007] FIG. 1 is a diagram illustrating a scenario in which an electronic device according to one embodiment of the present disclosure provides recommended content.

[0008] FIG. 2 is a drawing illustrating a system according to one embodiment of the present disclosure.

[0009] FIG. 3 is a drawing illustrating a system according to one embodiment of the present disclosure.

[0010] FIG. 4 is a flowchart illustrating an exemplary process for providing recommended content by an electronic device according to one embodiment of the present disclosure.

[0011] FIG. 5 is a diagram illustrating an exemplary process of using a generative artificial intelligence model by an electronic device according to one embodiment of the present disclosure.

[0012] FIG. 6 is a diagram illustrating an exemplary process for obtaining a plurality of recommended contents by inputting user input into a first artificial intelligence model by an electronic device according to one embodiment of the present disclosure.

[0013] FIG. 7 is a diagram illustrating an exemplary process for obtaining a plurality of recommended content by inputting user input and target viewer information into a first artificial intelligence model by an electronic device according to one embodiment of the present disclosure.

[0014] FIG. 8 is a diagram illustrating an exemplary scenario in which an electronic device according to one embodiment of the present disclosure compares recommended content with a content database.

[0015] FIG. 9 is a drawing for illustrating an exemplary scenario in which an electronic device according to one embodiment of the present disclosure obtains a list.

[0016] FIG. 10 is a drawing for illustrating an exemplary scenario in which an electronic device according to one embodiment of the present disclosure inputs a list into a second artificial intelligence model to obtain a name corresponding to the list.

[0017] FIG. 11 is a diagram illustrating an exemplary scenario in which an electronic device according to one embodiment of the present disclosure inputs a name corresponding to a list into a third artificial intelligence model to acquire an image.

[0018] FIG. 12 is a drawing for illustrating an exemplary scenario in which an electronic device according to one embodiment of the present disclosure updates a list.

[0019] FIG. 13 is a drawing for illustrating an exemplary scenario in which an electronic device according to one embodiment of the present disclosure provides a list, a name corresponding to the list, and an image.

[0020] FIG. 14 is a drawing for illustrating an exemplary process of a system according to one embodiment of the present disclosure.

[0021] FIG. 15 is a drawing for illustrating an exemplary process of a system according to one embodiment of the present disclosure.

[0022] FIG. 16 is a drawing for illustrating an exemplary process of a system according to one embodiment of the present disclosure.

[0023] FIG. 17 is a block diagram illustrating, by way of example, the configuration of an electronic device according to one embodiment of the present disclosure.

[0024] The terms used in this specification will be briefly explained, and the present disclosure will be described in detail. In the present disclosure, the expression "at least one of a, b, or c" may refer to "a," "b," "c," "a and b," "a and c," "b and c," "all of a, b, and c," or variations thereof.

[0025] The terms used in this disclosure have been selected to be as widely used and general 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 selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant explanatory sections. 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.

[0026] Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art as described in this specification. Additionally, terms including ordinal numbers, such as "first" or "second," used in this specification may be used to describe various components, but said components should not be limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another.

[0027] When a part of a specification is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "part" or "module" as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software.

[0028] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0029] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined rules of operation or artificial intelligence models configured to perform desired characteristics (or objectives) are created by a basic artificial intelligence model being trained using multiple learning data by a learning algorithm. Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0030] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include deep neural networks (DNNs), such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), or Deep Q-Networks, but are not limited to the examples mentioned above.

[0031] All functions or operations described in this document may be processed by a single processor or a combination of processors. A single processor or a combination of processors is a circuitry that performs processing and may include circuitry such as an AP (Application Processor), CP (Communication Processor), GPU (Graphical Processing Unit), NPU (Neural Processing Unit), MPU (Microprocessor Unit), SoC (System on Chip), IC (Integrated Chip), etc.

[0032] Embodiments of the present disclosure are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present disclosure in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0033] The present disclosure will be described below with reference to the attached drawings.

[0034] FIG. 1 is a diagram schematically illustrating the operation of an electronic device providing recommended content according to one embodiment of the present disclosure.

[0035] According to one embodiment of the present disclosure, an electronic device (100) may provide recommended content based on user input. The recommended content may include at least one of a list, a title corresponding to the list, or an image associated with a title corresponding to the list.

[0036] According to one embodiment of the present disclosure, the electronic device (100) may provide a list (30). The list (30) may be a list of a plurality of recommended contents related to user input or a list of information corresponding to a plurality of recommended contents related to user input.

[0037] According to one embodiment of the present disclosure, an electronic device (100) can obtain a plurality of recommended content related to user input using a generative artificial intelligence model. The electronic device (100) can generate a list (30) using the plurality of recommended content. The electronic device (100) can provide the list (30) through or to the display device (200). In one embodiment, the electronic device (100) can display the list (30) by controlling the display device (200) through a control signal.

[0038] Additionally, according to one embodiment of the present disclosure, the electronic device (100) may provide a title (40) corresponding to a list (30). The title (40) corresponding to the list (30) may include a title (40) associated with the list (30). The title (40) corresponding to the list (30) may be a word, phrase, or sentence that corresponds collectively to a plurality of recommended contents included in the list (30). For example, the title (40) corresponding to the list (30) may include a phrase, theme message, explanatory text, or recommendation slogan that introduces the recommended contents included in the list (30).

[0039] According to one embodiment of the present disclosure, an electronic device (100) can obtain a name (40) associated with and corresponding to a list (30) by using a generative artificial intelligence model. The electronic device (100) can provide the name (40) corresponding to the list (30) through or to a display device (200). In one embodiment, the electronic device (100) can display the name (40) by controlling the display device (200) through a control signal.

[0040] Additionally, according to one embodiment of the present disclosure, the electronic device (100) may provide an image (50). The image (50) may be an image representing a name (40) corresponding to a list (30). The image (50) may be an image that visually reinforces the name (40) corresponding to the list (30). For example, the image (50) may be an image that helps a viewer visually associate the meaning or characteristics of the name (40) corresponding to the list (30). Alternatively, the image (50) may be an image that complements the name (40) corresponding to the list (30). For example, the image (50) may be an image that helps a viewer understand the meaning or characteristics of the name (40) corresponding to the list (30).

[0041] According to one embodiment of the present disclosure, an electronic device (100) can acquire an image (50) associated with a name (40) corresponding to a list (30) by using a generative artificial intelligence model. The electronic device (100) can provide the image (50) through or to a display device (200). In one embodiment, the electronic device (100) can display the image (50) by controlling the display device (200) through a control signal. In one embodiment, the electronic device (100) can display the list (30), the name (40), and the image (50) by controlling the display device (200) through a control signal.

[0042] According to one embodiment of the present disclosure, an electronic device (100) may obtain user input. According to one embodiment of the present disclosure, the 'user' may include a content curator who intends to provide recommended content to a viewer or a manager who creates recommended content.

[0043] In the present disclosure, 'user input' may refer to data that a user of an electronic device (100) inputs to obtain recommended content. User input may be data including specific topics, themes, genres, people, or backgrounds. User input may be obtained through an input means of the electronic device (100), such as a remote control or a keyboard. In addition to input via a remote control or a keyboard, user input may be of various types of input (e.g., voice input, touch input, etc.). According to one embodiment of the present disclosure, the electronic device (100) may convert a voice signal into text for voice input. Alternatively, an input means of the electronic device (100) may transmit a voice signal representing voice input to the electronic device (100), and the electronic device (100) may convert the user input into text.

[0044] In the present disclosure, "content" may refer to the content of information or materials, etc., provided on a medium or platform. Content may be in various formats, such as text, images, videos, or audio. For example, content may include audiovisual content such as movies, dramas, and documentaries; auditory content such as music; visual content such as webtoons and e-books; or interactive content such as games, but is not limited to the examples described above. In the present disclosure, "recommended content" may refer to content among various contents that is expected to be preferred or of interest to a user or viewer. In the present disclosure, "recommended content" may refer to content recommended by an artificial intelligence model.

[0045] Conventionally, users manually recommended content, but according to embodiments of the present disclosure, an electronic device (100) can recommend content using an artificial intelligence model and provide at least one of a list, a name corresponding to the list, or an image. According to embodiments of the present disclosure, the electronic device (100) can not only efficiently provide content related to user input but also rapidly analyze a vast database to provide related content. By using an artificial intelligence model, the electronic device (100) can obtain not only a list of content but also related names and images.

[0046] FIG. 2 is a drawing illustrating a system according to one embodiment of the present disclosure.

[0047] According to one embodiment of the present disclosure, the system may include an electronic device (100), a display device (200), and an artificial intelligence server (300) connected to a communication network. Referring to FIG. 2, the electronic device (100) may be connected to an artificial intelligence server (300) that operates an artificial intelligence model. The electronic device (100) may transmit a request to the artificial intelligence server (300) to use the artificial intelligence model, and accordingly receive result data obtained using the artificial intelligence model from the artificial intelligence server (300).

[0048] In the present disclosure, a neural network model may be included as an example of an artificial intelligence model. At least one operation of the artificial intelligence model of the present disclosure may be performed by performing a computation through a neural network.

[0049] In the present disclosure, the terms 'model' and 'network' used in relation to artificial intelligence may be interchangeable concepts. For example, an 'artificial intelligence model' may be referred to as an 'artificial intelligence network'. The term 'model' may include various forms of artificial intelligence models, including neural network models, and an artificial intelligence model may include neural network models having a network-like structure.

[0050] According to one embodiment of the present disclosure, an electronic device (100) may include a communication interface (110), at least one processor (120), a memory (130), and a content database (140).

[0051] According to one embodiment of the present disclosure, the electronic device (100) may be a device of various types that provides recommended content. For example, the electronic device (100) may be a server device that provides content in response to a request from a display device (200). The communication interface (110) may include various communication circuits for performing communication with at least one external device. Here, 'communication' may mean an operation of transmitting and / or receiving data, signals, requests, and / or commands, etc.

[0052] The communication interface (110) can perform wired or wireless communication with at least one external device. The external device may include a display device (200) or an artificial intelligence server (300).

[0053] For example, the communication interface (110) may include at least one of a communication module, a communication circuit, a communication device, an input / output port, or an input / output plug for performing wired or wireless communication with at least one external device.

[0054] The processor (120) can control the overall operations of the electronic device (100). The processor (120) may include a processing circuit. For example, the processor (120) can control the overall operations of the electronic device (100) providing recommended content by executing one or more instructions of a program stored in memory (130). There may be one or more processors (120).

[0055] The processor (120) may be composed of at least one of, for example, a Central Processing Unit (CPU), a Microprocessor, a Graphic Processing Unit (GPU), ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), an Application Processor (AP), a Neural Processing Unit (NPU), or an AI-dedicated processor designed with a hardware structure specialized for processing AI models, but is not limited thereto.

[0056] According to one embodiment of the present disclosure, there may be one or more processors (120). If there is one or more processors (120), the operations of the present disclosure may be performed by one or more processors by executing instructions and / or programs stored in memory (130) individually or collectively. If the method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one processor (120) or by a plurality of processors (120).

[0057] According to one embodiment of the present disclosure, one or more processors may be implemented as a single-core processor or as a multi-core processor. When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by a single core or by a plurality of cores included in one or more processors.

[0058] According to one embodiment of the present disclosure, by executing instructions contained in memory (130) individually or collectively by at least one processor (120), the electronic device (100) can obtain a list based on a plurality of recommended contents obtained from a first artificial intelligence model based on user input. The electronic device (100) can obtain a title corresponding to the list from a second artificial intelligence model based on the obtained list. The electronic device (100) can obtain an image from a third artificial intelligence model based on the title corresponding to the list. The electronic device (100) can provide the list, the title corresponding to the list, and the image.

[0059] According to one embodiment of the present disclosure, the first artificial intelligence model may include a first generative artificial intelligence model that generates text. The electronic device (100) can obtain information corresponding to each recommended content among the plurality of recommended content related to the user input by inputting the user input to the first generative artificial intelligence model.

[0060] According to one embodiment of the present disclosure, information corresponding to the recommended content may include the name of the recommended content. The information corresponding to the recommended content may further include at least one of a platform corresponding to the provision of content, the release date of the content, the creator of the content, the playback time of the content, the genre of the content, or information on the performers of the content.

[0061] According to one embodiment of the present disclosure, the electronic device (100) can obtain information corresponding to each recommended content among the plurality of recommended content related to the user input considering the target viewer through the first generative artificial intelligence model based on the user input and target viewer information.

[0062] According to one embodiment of the present disclosure, the target viewer information may include at least one of the gender of the target viewer, the platform used by the target viewer, or the preferred genre of the target viewer.

[0063] According to one embodiment of the present disclosure, the electronic device (100) can add each recommended content to a list if each recommended content is included in a content database.

[0064] According to one embodiment of the present disclosure, the second artificial intelligence model may include a second generative artificial intelligence model that generates text. The electronic device (100) may obtain a name corresponding to the list corresponding to the plurality of recommended contents included in the list through the second generative artificial intelligence model based on the list.

[0065] According to one embodiment of the present disclosure, the third artificial intelligence model may include a third generative artificial intelligence model that generates an image. The electronic device (100) may acquire the image associated with the name corresponding to the list through the third generative artificial intelligence model based on the acquired name.

[0066] According to one embodiment of the present disclosure, when the electronic device (100) receives data from a display device (200), it can transmit the list, the name corresponding to the list, and the image to the display device (200) based on the received data.

[0067] The memory (130) stores various information, data, instructions, programs, etc., necessary for the operation of the electronic device (100). The memory (130) may include at least one of volatile memory or non-volatile memory, or a combination thereof. The memory (130) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (130) may correspond to web storage or a cloud server that performs storage functions over the internet.

[0068] The content database (140) may include information corresponding to the content that the display device (200) can provide. The content database (140) may refer to a database in which information corresponding to the content is stored. The content that the display device (200) can provide may represent various forms of content provided by content providers. A content provider may refer to a terrestrial broadcasting station, a cable broadcasting station, a satellite broadcasting station that provides various types of content to viewers, an IPTV (Internet Protocol Television) service provider, an OTT (Over the Top) service provider, or a server operator that provides various types of content.

[0069] The content database (140) can store information corresponding to the content. For example, the information corresponding to the content may include detailed information such as the name of the content, the release date of the content, the creator of the content, the playback time of the content, the genre of the content, the performers of the content, the platform corresponding to the provision of the content, or the viewing age rating of the content.

[0070] The content database (140) may include at least one of volatile memory or non-volatile memory, or a combination thereof. The content database (140) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk. Additionally, the content database (140) may correspond to web storage or a cloud server that performs storage functions on the internet.

[0071] The content database (140) can be updated through a connection with an external server (not shown). For example, when new content is provided to the display device (200) from content providers, the electronic device (100) can add information corresponding to the new content to the content database (140). Additionally, for example, when the provision of content from content providers to the display device (200) is discontinued, the electronic device (100) can delete information corresponding to the discontinued content from the content database (140).

[0072] According to one embodiment of the present disclosure, a display device (200) may include a communication interface (210), a display (220), a memory (230), and at least one processor (240). The display device (200) may be implemented by more components than those illustrated and is not limited to the examples described above.

[0073] The display device (200) can be implemented as various types and forms of electronic devices capable of wired / wireless connection with the display. For example, the display device (200) may include devices capable of displaying images through the display by being wired / wireless connected to the display, such as a set-top box, a desktop PC, or a server, but is not limited thereto.

[0074] As another example, the display device (200) may be implemented as an electronic device of various types and forms including a display. The display device (200) may include devices capable of displaying images through a display, such as a TV, smart TV, smartphone, tablet PC, laptop PC, glasses-type display, head-mounted display, etc., but is not limited thereto.

[0075] The communication interface (210) may include various communication circuits for communicating with an electronic device (100) or an artificial intelligence server (300). The communication interface (210) may perform wired or wireless communication with the electronic device (100).

[0076] For example, the communication interface (210) may include a remote controller located at a short distance, for example, a short-range communication module capable of receiving control commands from an external device, for example, an IR (infrared) communication module, etc. In this case, the communication interface (210) may receive a control signal from the remote controller.

[0077] As another example, the communication interface (210) may include at least one communication module that performs communication according to wireless communication standards such as Bluetooth, Wi-Fi, BLE (Bluetooth Low Energy), NFC / RFID, Wi-Fi Direct, UWB, or ZIGBEE. Alternatively, the communication interface (210) may further include a communication module that performs communication with a server to support long-distance communication according to long-distance communication standards. For example, the communication interface (210) may include a communication module that performs communication through a network for internet communication. Additionally, the communication interface (210) may include a communication module that performs communication through a communication network according to communication standards such as 3G, 4G, 5G and / or 6G.

[0078] As another example, the communication interface (210) may include at least one port for connecting to an external device via a wired cable in order to communicate with an external device via a wired connection. For example, the communication interface (210) may include at least one of an HDMI port (High-Definition Multimedia Interface port), a component jack, a PC port, and a USB port. Accordingly, the communication interface (210) can communicate with an external device connected via a wired connection through at least one port. Here, the port may refer to a physical device configuration into which a cable, a communication line, or a plug can be connected or inserted.

[0079] As described above, the communication interface (210) may include at least one support element to support communication between the display device (200) and an external device. Here, the support element may include the aforementioned communication module, communication circuit, communication device, port (for input / output of data), cable port (for input / output of data), plug (for input / output of data), etc. For example, the at least one support element included in the communication interface (210) may be an Ethernet communication module, a Wi-Fi communication module, a Bluetooth communication module, an IR communication module, a USB port, a tuner (or broadcast receiver), an HDMI port, a DP (display port), a DVI (digital visual interface) port, etc.

[0080] The display (220) can output images or data processed by the electronic device (100). For example, the display (220) can display recommended content provided by the electronic device (100) through the communication interface (210). The display (220) is depicted as being embedded in the display device (200), but is not necessarily limited thereto. The display (220) may exist outside the display device (200) and be connected to the display device (200) via wired or wireless communication, and the display device (200) may transmit content to be displayed to the display (220) using wired or wireless communication.

[0081] The memory (230) can store a program for processing and controlling the processor (240) and can store data that is input to or output from the display device (200).

[0082] The memory (230) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk.

[0083] The processor (240) includes various processing circuits for controlling the overall operation of the display device (200). For example, the processor (240) can perform the functions of the display device (200) described in the present disclosure by executing one or more instructions stored in memory (230).

[0084] According to one embodiment of the present disclosure, the processor (240) may store one or more instructions in an internally provided memory and control the execution of one or more instructions stored in the internally provided memory to perform the aforementioned operations. That is, the processor (240) may execute at least one instruction or program stored in an internal memory or memory (230) provided within the processor (240) to perform a predetermined (e.g., predetermined) operation.

[0085] According to one embodiment of the present disclosure, the processor (240) may receive a request for connection to the electronic device (100) from a user by executing one or more instructions stored in the memory (230). The processor (240) may request items to be used in a user interface that allows content provided by the electronic device (100) to be displayed and selected in accordance with the request for connection to the electronic device (100) by executing one or more instructions stored in the memory (230). The processor (240) may receive at least one of a list, a name corresponding to the list, or an image from the electronic device (100) by executing one or more instructions stored in the memory (230).

[0086] According to one embodiment of the present disclosure, a processor (240) can generate a user interface based on a list, a name corresponding to the list, and an image by executing one or more instructions stored in memory (230). The processor (240) can provide the user interface generated based on the list, a name corresponding to the list, and an image to a display (220) by executing one or more instructions stored in memory (230).

[0087] According to one embodiment of the present disclosure, the artificial intelligence server (300) may include a communication interface (310), at least one processor (320), and a memory (330). The artificial intelligence server (300) may be implemented by more components than those illustrated and is not limited to the examples described above. When the artificial intelligence server (300) receives a request from an electronic device (100), it may acquire data using one or more artificial intelligence models and transmit the acquired data to the electronic device (100).

[0088] The communication interface (310) may include various communication circuits for performing communication with an electronic device (100) or a display device (200). The communication interface (310) may perform wired or wireless communication with the electronic device (100).

[0089] The processor (320) includes various processing circuits for controlling the overall operation of the artificial intelligence server (300). For example, the processor (320) can perform the functions of the artificial intelligence server (300) described in the present disclosure by executing one or more instructions stored in memory (330).

[0090] In an embodiment of the present disclosure, the processor (320) may store one or more instructions in an internally provided memory and control the execution of one or more instructions stored in the internally provided memory to perform the aforementioned operations. That is, the processor (320) may execute at least one instruction or program stored in an internal memory or memory (330) provided within the processor (320) to perform a predetermined (e.g., predetermined) operation.

[0091] According to one embodiment of the present disclosure, when a processor (320) receives user input from an electronic device (100) by executing one or more instructions stored in memory (330), it can recommend a plurality of contents corresponding to the user input using a first artificial intelligence model (332). By executing one or more instructions stored in memory (330), the processor (320) can transmit the recommended plurality of contents to the electronic device (100).

[0092] According to one embodiment of the present disclosure, when a processor (320) receives target viewer information from an electronic device (100) by executing one or more instructions stored in memory (330), it can recommend a plurality of contents corresponding to user input and target viewer information using a first artificial intelligence model (332). By executing one or more instructions stored in memory (330), the processor (320) can transmit a plurality of contents corresponding to user input and target viewer information to the electronic device (100).

[0093] According to one embodiment of the present disclosure, a processor (320) can recommend a plurality of contents by executing one or more instructions stored in memory (330). By executing one or more instructions stored in memory (330), the processor (320) can generate information corresponding to the plurality of recommended contents and transmit the information corresponding to the generated content to an electronic device (100).

[0094] According to one embodiment of the present disclosure, when a processor (320) receives a list from an electronic device (100) by executing one or more instructions stored in memory (330), it can generate a name corresponding to the list using a second artificial intelligence model (334). The processor (320) can transmit the name corresponding to the list to the electronic device (100) by executing one or more instructions stored in memory (330).

[0095] According to one embodiment of the present disclosure, the processor (320) can generate an image associated with a name corresponding to a list by executing one or more instructions stored in memory (330). The processor (320) can transmit the image to an electronic device (100) by executing one or more instructions stored in memory (330).

[0096] The memory (330) can store a program for processing and controlling the processor (320), and can store data that is input to or output from the artificial intelligence server (300).

[0097] The memory (330) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk.

[0098] The memory (330) can store one or more instructions and one or more programs that cause the artificial intelligence server (300) to recommend content. According to one embodiment of the present disclosure, the memory (330) can store an artificial intelligence model operated by the artificial intelligence server (300). For example, the memory (330) can store a first artificial intelligence model (332), a second artificial intelligence model (334), and a third artificial intelligence model (336).

[0099] According to one embodiment of the present disclosure, the first artificial intelligence model (332) can take user input as input and output a plurality of contents corresponding to user input. The first artificial intelligence model (332) may include a generative artificial intelligence model specialized in generating text.

[0100] According to one embodiment of the present disclosure, the second artificial intelligence model (334) can take a list as input and output a name corresponding to the list. The second artificial intelligence model (334) may include a generative artificial intelligence model specialized in generating text.

[0101] According to one embodiment of the present disclosure, the third artificial intelligence model (336) can take a name corresponding to a list as input and output an image associated with the name corresponding to the list. The third artificial intelligence model (336) may include a generative artificial intelligence model specialized in generating images.

[0102] FIG. 3 is a drawing illustrating a system according to one embodiment of the present disclosure.

[0103] According to one embodiment of the present disclosure, the system may include an electronic device (100) and a display device (200) connected to a communication network. Referring to FIG. 3, the electronic device (100) may operate an artificial intelligence model within the electronic device (100) without needing to be connected to an external artificial intelligence server. For example, the electronic device (100) may operate an artificial intelligence model that is executable using the computing resources possessed by the electronic device (100).

[0104] According to one embodiment of the present disclosure, an electronic device (100) may include a communication interface (110), at least one processor (120), a memory (130), and a content database (140).

[0105] The electronic device (100), communication interface (110), at least one processor (120), memory (130), and content database (140) illustrated in FIG. 3 may correspond to the electronic device (100), communication interface (110), at least one processor (120), memory (130), and content database (140) illustrated in FIG. 2, respectively.

[0106] Referring to FIG. 3, the memory (130) may store one or more instructions and one or more programs that enable the electronic device (100) to provide recommended content. According to one embodiment of the present disclosure, the memory (130) may store an artificial intelligence model operated by the electronic device (100). For example, the memory (130) may store a first artificial intelligence model (132), a second artificial intelligence model (134), and a third artificial intelligence model (136). The artificial intelligence model stored in the memory (130) may be an artificial intelligence model that is relatively lighter than an artificial intelligence model that can be operated on an external server, but is not limited thereto.

[0107] In an embodiment of the present disclosure, the processor (120) may store one or more instructions in an internally provided memory and control the execution of one or more instructions stored in the internally provided memory to perform the aforementioned operations or operations to be described later. That is, the processor (120) may execute at least one instruction or program stored in an internal memory or memory (130) provided within the processor (120) to perform a predetermined (e.g., predetermined) operation.

[0108] According to one embodiment of the present disclosure, when a processor (120) obtains user input by executing one or more instructions stored in memory (130), it can recommend a plurality of contents corresponding to the user input using a first artificial intelligence model (132).

[0109] According to one embodiment of the present disclosure, when a processor (120) obtains target viewer information by executing one or more instructions stored in memory (130), it can recommend a plurality of contents corresponding to user input and target viewer information using a first artificial intelligence model (132).

[0110] According to one embodiment of the present disclosure, a processor (120) can recommend a plurality of contents by executing one or more instructions stored in memory (130). By executing one or more instructions stored in memory (130), the processor (120) can generate information corresponding to the plurality of recommended contents using a first artificial intelligence model (132).

[0111] According to one embodiment of the present disclosure, when a processor (120) obtains a list from an electronic device (100) by executing one or more instructions stored in memory (130), it can generate a name corresponding to the list using a second artificial intelligence model (134).

[0112] According to one embodiment of the present disclosure, the processor (120) can generate an image associated with the name corresponding to the list by executing one or more instructions stored in memory (130) to obtain a name corresponding to the list.

[0113] According to one embodiment of the present disclosure, a display device (200) may include a communication interface (210), a display (220), a memory (230), and at least one processor (240).

[0114] The display device (200), communication interface (210), display (220), memory (230), and at least one processor (240) illustrated in FIG. 3 may correspond to the display device (200), communication interface (210), display (220), memory (230), and at least one processor (240) illustrated in FIG. 2, respectively.

[0115] Hereinafter, in the attached drawings, the electronic device (100) will be described as operating through a connection with an artificial intelligence server (300) outside the electronic device (100), as shown in FIG. 2. However, the electronic device (100) can operate using an artificial intelligence model included inside the electronic device (100) without needing to be connected to an external artificial intelligence server (300), as shown in FIG. 3.

[0116] In the above, FIG. 2 describes an artificial intelligence server (300) outside the electronic device (100) that includes an artificial intelligence model, and the artificial intelligence server (300) acquires data using the artificial intelligence model and transmits it to the electronic device (100). FIG. 3 describes an artificial intelligence model that is included inside the electronic device (100), and the electronic device (100) performs operations using the artificial intelligence model stored inside the electronic device (100). However, this is not limited thereto, and among the plurality of artificial intelligence models, some artificial intelligence models may be included in the external artificial intelligence server (300) and some artificial intelligence models may be included in the electronic device (100). For example, some of the first to third artificial intelligence models may be operated in the external artificial intelligence server (300), and some may be operated in the electronic device (100).

[0117] Additionally, according to one embodiment of the present disclosure, the first artificial intelligence model, the second artificial intelligence model, and the third artificial intelligence model may be implemented as a single artificial intelligence model. For example, a single artificial intelligence model may perform the operations of the first artificial intelligence model, the second artificial intelligence model, and the third artificial intelligence model.

[0118] FIG. 4 is a flowchart illustrating, in an exemplary manner, the operation of an electronic device providing recommended content according to one embodiment of the present disclosure.

[0119] With reference to FIG. 4, the overall operation of the electronic device (100) of the present disclosure will be described. Additionally, with reference to the following drawings, specific details of the operation of the electronic device (100) will be described.

[0120] In operation S410, the electronic device (100) can obtain a list based on a plurality of recommended contents obtained from a first artificial intelligence model based on user input.

[0121] According to one embodiment of the present disclosure, an electronic device (100) receives user input and can obtain a plurality of recommended content from a first artificial intelligence model based on the user input. According to one embodiment of the present disclosure, the electronic device (100) can obtain user input. The electronic device (100) can generate a first input prompt for inputting the user input into the first artificial intelligence model. The electronic device (100) can input the first input prompt, which includes the user input, into the first artificial intelligence model. The first artificial intelligence model can recommend a plurality of content related to the user input. The first artificial intelligence model can generate information for each of the recommended content. The electronic device (100) can obtain information corresponding to the recommended content from the first artificial intelligence model.

[0122] According to one embodiment of the present disclosure, an electronic device (100) may obtain target viewer information. The target viewers may be a group of viewers who wish to receive at least one of recommended content, a list, a name or image corresponding to the list from the electronic device (100). The target viewer information may represent data collected by the electronic device (100) regarding the target viewers in order to provide recommended content. For example, the target viewer information may include information regarding the target viewer's age, the target viewer's gender, the platform used by the target viewer, the target viewer's occupation, the target viewer's preferred genre, the target viewer's preferred topic, the target viewer's previous viewing history, etc. The electronic device (100) may receive target viewer information from a display device (200) or an external server.

[0123] According to one embodiment of the present disclosure, an electronic device (100) can obtain a plurality of recommended content from a first artificial intelligence model based on user input and target viewer information. The electronic device (100) can generate a first input prompt for inputting user input and target viewer information into the first artificial intelligence model. The electronic device (100) can input the first input prompt, which includes user input and target viewer information, into the first artificial intelligence model. The first artificial intelligence model can recommend a plurality of content related to user input and target viewer information. The first artificial intelligence model can generate information for each of the recommended content. The electronic device (100) can obtain information corresponding to the recommended content from the first artificial intelligence model. Thus, by adding target viewer information as input to the first artificial intelligence model, recommended content more suitable for the target viewer or information corresponding to the recommended content can be obtained.

[0124] According to one embodiment of the present disclosure, an electronic device (100) may obtain a list based on a plurality of recommended contents obtained from a first artificial intelligence model. The electronic device (100) may obtain information regarding each of the plurality of recommended contents from the first artificial intelligence model. The electronic device (100) may generate a list (30) based on the plurality of recommended contents. In generating the list (30), the electronic device (100) may use a content database (140).

[0125] According to one embodiment of the present disclosure, the electronic device (100) may provide only content existing in the content database (140). However, a plurality of recommended content obtained using the first artificial intelligence model may include content that is not provided by the electronic device (100). Accordingly, in order to exclude content that is not provided by the electronic device (100) from the plurality of recommended content, the electronic device (100) may compare the content of the content database (140) with the plurality of recommended content obtained using the first artificial intelligence model. The electronic device (100) may compare each of the plurality of recommended content obtained from the first artificial intelligence model with the content included in the content database (140). For example, the electronic device (100) may compare the information of each of the recommended content with the information of the content included in the content database (140).

[0126] According to one embodiment of the present disclosure, an electronic device (100) may add recommended content to a list (30) if the acquired recommended content is included in a content database (140). Each recommended content added to the list (30) is content existing in the content database (140). The electronic device (100) may add information corresponding to the recommended content to the list (30). The list (30) may include only content that the electronic device (100) can provide or information corresponding to the content that the electronic device (100) can provide.

[0127] In operation S420, the electronic device (100) can obtain a title corresponding to the list from the second artificial intelligence model based on the acquired list.

[0128] According to one embodiment of the present disclosure, an electronic device (100) can obtain a name (40) corresponding to a list (30) by using a second artificial intelligence model. The electronic device (100) can generate a second input prompt for inputting the list (30) into the second artificial intelligence model. The electronic device (100) can input the second input prompt containing the list (30) into the second artificial intelligence model. The second artificial intelligence model can generate a name (40) associated with the list (30) and corresponding to the list (30). The electronic device (100) can obtain a name (40) corresponding to the list (30) from the second artificial intelligence model.

[0129] In operation S430, the electronic device (100) can obtain an image from a third artificial intelligence model based on a name corresponding to a list.

[0130] According to one embodiment of the present disclosure, an electronic device (100) can acquire an image (50) using a third artificial intelligence model. The electronic device (100) can generate a third input prompt for inputting a name (40) corresponding to a list (30) into the third artificial intelligence model. The electronic device (100) can input the third input prompt, which includes a name (40) corresponding to the list (30), into the third artificial intelligence model. The third artificial intelligence model can generate an image (50) associated with the name (40) corresponding to the list (30). The electronic device (100) can acquire an image (50) from the third artificial intelligence model.

[0131] In operation S440, the electronic device (100) can provide a list, a name corresponding to the list, and an image.

[0132] According to one embodiment of the present disclosure, an electronic device (100) may receive a request from a display device (200) for an item to be used in the Home User Interface of the display device (200). A list (30), a name (40) corresponding to the list (30), and an image (50) may be used as items in the Home User Interface of the display device (200). The electronic device (100) may transmit at least one of the list (30), the name (40) corresponding to the list (30), and the image (50) to the display device (200).

[0133] FIG. 5 is a diagram illustrating, by way of example, the operation of an electronic device according to one embodiment of the present disclosure using a generative artificial intelligence model.

[0134] According to one embodiment of the present disclosure, the first artificial intelligence model may include a first generative artificial intelligence model (510). The electronic device (100) may input user input (10) into the first generative artificial intelligence model (510). The electronic device (100) may obtain a plurality of recommended content (20) using the first generative artificial intelligence model (510).

[0135] According to one embodiment of the present disclosure, the first generative artificial intelligence model (510) may be an artificial intelligence model specialized in generating text. For example, the first generative artificial intelligence model (510) may be a Language Model (LM). More specifically, the first generative artificial intelligence model (510) may be a Large Language Model (LLM). A Large Language Model is trained using a large dataset compared to a Language Model (LM) and can perform more complex language processing tasks than a Language Model. Since a Large Language Model requires high-performance computing resources, it may be operated by a separate high-performance computer system (e.g., an artificial intelligence server (300)). However, the Large Language Model is not limited to being operated by a separate high-performance computer system, and an electronic device (100) may operate the Large Language Model.

[0136] According to one embodiment of the present disclosure, the first generative artificial intelligence model (510) may be an artificial intelligence model specialized in generating not only text but also images. For example, the first generative artificial intelligence model (510) may be a multi-modal artificial intelligence model. A multi-modal artificial intelligence model may be an artificial intelligence model capable of processing various forms of data simultaneously. For example, a multi-modal artificial intelligence model may be an artificial intelligence model capable of processing text data and image data together.

[0137] According to one embodiment of the present disclosure, the second artificial intelligence model may include a second generative artificial intelligence model (520). The electronic device (100) may input a list (30) into the second generative artificial intelligence model (520). The list (30) may be generated based on a plurality of recommended content (20). The electronic device (100) may obtain a name (40) corresponding to the list (30) using the second generative artificial intelligence model (520).

[0138] According to one embodiment of the present disclosure, the second generative artificial intelligence model (520) may be an artificial intelligence model specialized in generating text. For example, the second generative artificial intelligence model (520) may be a language model (LM). More specifically, the second generative artificial intelligence model (520) may be a large language model (LLM).

[0139] According to one embodiment of the present disclosure, the second generative artificial intelligence model (520) may be an artificial intelligence model specialized in generating images and text. For example, the second generative artificial intelligence model (520) may be a multi-modal artificial intelligence model.

[0140] According to one embodiment of the present disclosure, the third artificial intelligence model may include a third generative artificial intelligence model (530). The electronic device (100) may input a name (40) corresponding to a list (30) into the third generative artificial intelligence model (530). The electronic device (100) may acquire an image (50) using the third generative artificial intelligence model (530).

[0141] According to one embodiment of the present disclosure, the third generative artificial intelligence model (530) may be an artificial intelligence model specialized in generating images. The third generative artificial intelligence model (530) may be an artificial intelligence model that receives text as input and generates images. For example, the third generative artificial intelligence model (530) may be a CLIP (Contrastive Language-Image Pre-training) model or a Diffusion Model.

[0142] According to one embodiment of the present disclosure, the third generative artificial intelligence model (530) may be an artificial intelligence model specialized in generating images and text. For example, the third generative artificial intelligence model (530) may be a multimodal artificial intelligence model.

[0143] FIG. 6 is a diagram illustrating, in an exemplary manner, the operation of an electronic device according to one embodiment of the present disclosure to input user input into a first artificial intelligence model to obtain a plurality of recommended contents.

[0144] According to one embodiment of the present disclosure, an electronic device (100) can transmit user input (10) to a first generative artificial intelligence model (510). The electronic device (100) can generate a first input prompt (610) for inputting user input (10) to the first generative artificial intelligence model (510).

[0145] According to one embodiment of the present disclosure, the first input prompt (610) may include text-based commands, instructions, and inputs that are input to the first generative artificial intelligence model (510). For example, a command may be a request for the generative artificial intelligence model to perform a task. An instruction may be a method or procedure for a task that the generative artificial intelligence model is to perform. An input may be data or information that the generative artificial intelligence model is to process.

[0146] According to one embodiment of the present disclosure, an electronic device (100) may generate a first input prompt (610) in a rule-based manner. For example, the electronic device (100) may generate a first input prompt (610) requesting a plurality of content recommendations by inserting user input (10) into a placeholder of a first prompt template. According to one embodiment of the present disclosure, the first prompt template may be stored in the memory (130) of the electronic device (100). Alternatively, the electronic device (100) may receive the first prompt template from an external server.

[0147] According to one embodiment of the present disclosure, a first prompt template may predefine and provide at least one of a command, instruction, or input for a task to be performed by a first generative artificial intelligence model (510). A placeholder may be a location pre-designated in the first prompt template where a user input (10) is inserted. According to one embodiment of the present disclosure, a placeholder to which the user input (10) is mapped may be pre-set according to the attributes of the user input (10).

[0148] For example, the first prompt template may include a command (612). The command (612) may be a request for the first generative artificial intelligence model (510) to perform a 'content recommendation' task. The command (612) may include a placeholder into which a type of content (621) (e.g., movies, dramas, etc.) is inserted. Additionally, the command (612) may include a placeholder into which a theme (623) of the content is inserted.

[0149] Additionally, for example, the first prompt template may include instructions (614). Instructions (614) may include information corresponding to content that the first generative AI model (510) must include when performing a 'content recommendation' task. Instructions (614) may include placeholders (625, 627) into which details are inserted. For example, instructions (614) may include the name (625) of the recommended content. Additionally, instructions (614) may include the release year (627) of the recommended content.

[0150] Additionally, for example, the first prompt template may include instructions (616). The instructions (616) may include information about the format in which the first generative artificial intelligence model (510) outputs the result of the task execution.

[0151] According to one embodiment of the present disclosure, a first generative artificial intelligence model (510) can recommend a plurality of contents based on a first input prompt (610). For example, the first generative artificial intelligence model (510) can perform a content recommendation task according to a command or instruction of the first input prompt (610).

[0152] According to one embodiment of the present disclosure, the first generative artificial intelligence model (510) can perform a content recommendation task. Specifically, the first generative artificial intelligence model (510) can generate information for each recommended content. For example, the first generative artificial intelligence model (510) can generate a name of the recommended content. Additionally, for example, the first generative artificial intelligence model (510) can generate at least one of a platform corresponding to the provision of the recommended content, the release date of the recommended content, the creator of the recommended content, the playback time of the recommended content, the genre of the recommended content, or information on the performers of the recommended content.

[0153] According to one embodiment of the present disclosure, an electronic device (100) can obtain a plurality of recommended content (630) output by a first generative artificial intelligence model (510). The electronic device (100) can obtain information for each of the plurality of recommended content (630) generated by the first generative artificial intelligence model (510). For example, the electronic device (100) can obtain the name of the content recommended by the first generative artificial intelligence model (510) and the year of release of the content.

[0154] FIG. 7 is a diagram illustrating, in an exemplary manner, the operation of an electronic device according to one embodiment of the present disclosure to input user input and target viewer information into a first artificial intelligence model to obtain a plurality of recommended contents.

[0155] According to one embodiment of the present disclosure, an electronic device (100) can input user input (10) and target viewer information (70) into a first generative artificial intelligence model (510). The electronic device (100) can generate a first input prompt (710) for inputting user input (10) and target viewer information (70) into the first generative artificial intelligence model (510). According to one embodiment of the present disclosure, the first input prompt (710) may further include an instruction (712) that includes target viewer information (70) in the first input prompt (610).

[0156] According to one embodiment of the present disclosure, an electronic device (100) can generate a first input prompt (710) in a rule-based manner. For example, the electronic device (100) can generate a first input prompt (710) requesting a plurality of content recommendations by inserting user input (10) and target viewer information (70) into placeholders of a first prompt template.

[0157] For example, the first prompt template may include instructions (712). The instructions (712) may include target viewer information (70) that the first generative AI model (510) must consider when performing a 'content recommendation' task. For example, the instructions (712) may include a placeholder (721) to insert the gender of the target viewer. Additionally, the instructions (712) may include a placeholder (723) to insert the age range of the target viewer. Additionally, for example, the instructions (712) may include a placeholder (725) to insert the preferred genre of the target viewer.

[0158] According to one embodiment of the present disclosure, the first input prompt (710) may be generated in a manner similar to the first input prompt (610). Since the description of the operations for generating the first input prompt (610) has already been described in the description of FIG. 6, a repetitive description is omitted.

[0159] According to one embodiment of the present disclosure, a first generative artificial intelligence model (510) can recommend a plurality of contents based on a first input prompt (710). For example, the first generative artificial intelligence model (510) can perform a content recommendation task according to a command or instruction of the first input prompt (710).

[0160] According to one embodiment of the present disclosure, a first generative artificial intelligence model (510) can perform a content recommendation task. According to one embodiment of the present disclosure, by inputting a first input prompt (710) containing user input (10) and target viewer information (70) to the first generative artificial intelligence model (510), the first generative artificial intelligence model (510) can recommend a plurality of content that takes into account the target viewer. For example, the plurality of recommended content (730) may be different from the plurality of recommended content (720) as an output that takes into account the target viewer information (70).

[0161] According to one embodiment of the present disclosure, the first generative artificial intelligence model (510) can perform a content recommendation task. Since the description of the operations related to the first generative artificial intelligence model (510) performing the content recommendation task has already been described in the description of FIG. 6, a repetitive description is omitted.

[0162] Additionally, according to one embodiment of the present disclosure, the electronic device (100) may obtain information for each of a plurality of recommended content (730) in a manner similar to the operation of obtaining information for each of a plurality of recommended content (630). Since the description related to the operations of obtaining information for each of a plurality of recommended content (630) has already been described in the description of FIG. 6, a repetitive description is omitted.

[0163] FIG. 8 is a diagram illustrating, in an exemplary manner, the operation of an electronic device according to one embodiment of the present disclosure comparing recommended content with a content database.

[0164] According to one embodiment of the present disclosure, an electronic device (100) can generate a list (30) based on a plurality of recommended content (20). The electronic device (100) can obtain a plurality of recommended content (20) from a first artificial intelligence model. The electronic device (100) can generate a list (30) by comparing (810) the plurality of recommended content (20) with a content database (140).

[0165] According to one embodiment of the present disclosure, an electronic device (100) can compare (810) each recommended content included in a plurality of recommended content (20) with a content database (140). The electronic device (100) can compare information regarding each recommended content with information regarding each content included in the content database (140). The electronic device (100) can compare detailed information regarding the recommended content with detailed information regarding the content included in the content database (140). Specifically, the electronic device (100) can compare information in the content database (140) that has the same attributes as the information of the recommended content.

[0166] For example, the electronic device (100) can identify whether the name of the recommended content matches the name of the content included in the content database (140). The electronic device (100) can identify whether the release date of the recommended content matches the release date of the content included in the content database (140). The electronic device (100) can identify whether the genre of the recommended content matches the genre of the content included in the content database (140).

[0167] According to one embodiment of the present disclosure, the electronic device (100) can identify whether each recommended content is stored in the content database (140). For example, the electronic device (100) can identify whether the first recommended content (22) is included in the content database (140).

[0168] According to one embodiment of the present disclosure, an electronic device (100) can determine whether information regarding a first recommended content (22) matches information corresponding to content included in a content database (140). For example, the electronic device (100) can compare the name of the first recommended content (22) with the name of content stored in the content database (140). Additionally, for example, the electronic device (100) can compare the release date of the first recommended content (22) with the release date of content stored in the content database (140).

[0169] According to one embodiment of the present disclosure, an electronic device (100) can identify whether the first recommended content (22) to the Nth recommended content (28) are included in the content database (140). In FIG. 8, the name or release date of the recommended content is described as an example of comparing it with the content database (140), but it is not limited to comparing such detailed information. For example, the electronic device (100) can compare the detailed information generated by the first artificial intelligence model for each of the multiple recommended content (20).

[0170] FIG. 9 is a drawing for exemplarily illustrating the operation of an electronic device acquiring a list according to one embodiment of the present disclosure.

[0171] According to one embodiment of the present disclosure, an electronic device (100) can obtain a list (30) based on a plurality of recommended content (20) and a content database (140). The electronic device (100) can generate a list (30) using the result of comparing (810) the plurality of recommended content (20) and the content database (140).

[0172] According to one embodiment of the present disclosure, an electronic device (100) can compare a plurality of recommended content (20) with a content database (140) to identify whether each of the recommended content is stored in the content database (140). The electronic device (100) can identify whether the information in the content database (140) having the same attributes as the information of the recommended content matches.

[0173] According to one embodiment of the present disclosure, the electronic device (100) can determine that recommended content is stored in the content database (140) if the information in the content database (140) having the same attributes as the information of the recommended content matches. The electronic device (100) can add the recommended content determined to be stored in the content database (140) to the list (30).

[0174] For example, if the first recommended content (22) is identified as being stored in the content database (140), the electronic device (100) can add the first recommended content (22) to the list (30). The electronic device (100) can add information about the first recommended content (22) to the list (30). The list (30) may include the first recommended content (32) and information about the first recommended content (32).

[0175] Additionally, for example, if it is identified that the second recommended content (24) is not stored in the content database (140), the electronic device (100) may not add the second recommended content (24) to the list (30). The electronic device (100) may not add information about the second recommended content (24) to the list (30).

[0176] Additionally, for example, if it is identified that the third recommended content (26) is stored in the content database (140), the electronic device (100) may add the third recommended content (26) to the list (30). The electronic device (100) may add information about the third recommended content (26) to the list (30). The list (30) may include the third recommended content (34) and information about the third recommended content (34).

[0177] FIG. 10 is a diagram illustrating, in an exemplary manner, the operation of an electronic device according to one embodiment of the present disclosure inputting a list into a second artificial intelligence model to obtain a name corresponding to the list.

[0178] According to one embodiment of the present disclosure, an electronic device (100) can input a list (30) into a second generative artificial intelligence model (520). The electronic device (100) can generate a second input prompt (1010) for inputting the list (30) into the second generative artificial intelligence model (520).

[0179] According to one embodiment of the present disclosure, the second input prompt (1010) may include text-based commands, instructions, and inputs that are input to the second generative artificial intelligence model (520).

[0180] According to one embodiment of the present disclosure, an electronic device (100) can generate a second input prompt (1010) in a rule-based manner. For example, the electronic device (100) can generate a second input prompt (1010) that requests the generation of a name (40) corresponding to the list (30) by inserting a list (30) into a placeholder of the second prompt template. Alternatively, for example, the electronic device (100) can generate a second input prompt (1010) that requests the generation of a name (40) corresponding to the list (30) by inserting the list (30) and target viewer information (70) into a placeholder of the second prompt template.

[0181] According to one embodiment of the present disclosure, the second prompt template may be stored in the memory (130) of the electronic device (100). Alternatively, the electronic device (100) may receive the second prompt template from an external server.

[0182] According to one embodiment of the present disclosure, the second prompt template may predefine and provide at least one of a command, instruction, or input for a task to be performed by the second generative artificial intelligence model (520). The placeholder may be a location pre-designated in the second prompt template where the list (30) or target viewer information (70) is inserted. According to one embodiment of the present disclosure, a placeholder to which the list (30) is mapped may be pre-set according to the details of the recommended content included in the list (30).

[0183] For example, the second prompt template may include instructions (1012). The instructions (1012) may include target viewer information (70) that the second generative AI model (520) must consider when performing the generation of a name (40) corresponding to the list (30). For example, the instructions (1012) may include a placeholder (1022) designated to insert information about the target viewer.

[0184] Additionally, for example, the second prompt template may include a command (1014). The command (1014) may be a request for the second generative artificial intelligence model (520) to perform a generation operation of a name (40) corresponding to the list (30). The command (1014) may include a placeholder (1024) into which the type of name (40) corresponding to the list (30) (e.g., word, phrase, or sentence, etc.) is to be inserted.

[0185] Additionally, for example, the second prompt template may include instructions (1016). The instructions (1016) may include details of recommended content included in the list (30) that the second generative AI model (520) must consider when performing the task of generating a name (40) corresponding to the list (30). The instructions (1016) may include placeholders designated to insert details of the recommended content (e.g., the name of the recommended content, or the release year of the recommended content).

[0186] For example, the instruction (1016) may include a placeholder (1032) designated to insert the name of the first recommended content. The instruction (1016) may include a placeholder (1034) designated to insert the release year of the first recommended content. Additionally, for example, the instruction (1016) may include a placeholder (1036) designated to insert the name of the second recommended content. The instruction (1016) may include a placeholder (1038) designated to insert the release year of the second recommended content.

[0187] According to one embodiment of the present disclosure, a second generative artificial intelligence model (520) can generate a name (40) corresponding to a list (30) based on a second input prompt (1010). For example, the second generative artificial intelligence model (520) can perform a generation operation of a name (40) corresponding to a list (30) according to a command or instruction of the second input prompt (1010).

[0188] According to one embodiment of the present disclosure, the second generative artificial intelligence model (520) can perform a generation operation of a name (40) corresponding to the list (30). For example, the second generative artificial intelligence model (520) can generate a phrase, theme message, explanatory text, or recommendation slogan that introduces the recommended content included in the list (30).

[0189] According to one embodiment of the present disclosure, a second generative artificial intelligence model (520) can output result data (1040) including a name (40) corresponding to a list (30). An electronic device (100) can obtain a name (40) corresponding to a list (30) output by the second generative artificial intelligence model (520).

[0190] FIG. 11 is a diagram illustrating, in an exemplary manner, the operation of an electronic device according to one embodiment of the present disclosure to acquire an image by inputting a name corresponding to a list into a third artificial intelligence model.

[0191] According to one embodiment of the present disclosure, an electronic device (100) can input a name (40) corresponding to a list (30) into a third generative artificial intelligence model (530). The electronic device (100) can generate a third input prompt (1110) for inputting a name (40) corresponding to a list (30) into the third generative artificial intelligence model (530).

[0192] According to one embodiment of the present disclosure, the third input prompt (1110) may include text-based commands, instructions, and inputs that are input to the third generative artificial intelligence model (530).

[0193] According to one embodiment of the present disclosure, an electronic device (100) can generate a third input prompt (1110) in a rule-based manner. For example, the electronic device (100) can generate a third input prompt (1110) that requests the generation of an image (50) by inserting a name (40) corresponding to a list (30) into a placeholder of a third prompt template. Alternatively, for example, the electronic device (100) can generate a third input prompt (1110) that requests the generation of an image (50) by inserting a name (40) corresponding to a list (30) and target viewer information (70) into a placeholder of a third prompt template.

[0194] According to one embodiment of the present disclosure, the third prompt template may be stored in the memory (130) of the electronic device (100). Alternatively, the electronic device (100) may receive the third prompt template from an external server.

[0195] According to one embodiment of the present disclosure, the third prompt template may predefine and provide at least one of a command, instruction, or input for a task to be performed by the third generative artificial intelligence model (530). The placeholder may be a location pre-designated in the third prompt template where a name (40) corresponding to the list (30) or target viewer information (70) is inserted. According to one embodiment of the present disclosure, a placeholder to which the name (40) corresponding to the list (30) is mapped may be pre-set.

[0196] For example, the third prompt template may include instructions (1112). The instructions (1112) may include target viewer information (70) that the third generative AI model (530) must consider when performing an image (50) generation task. For example, the instructions (1112) may include a placeholder (1122) designated to insert the target viewer information (70).

[0197] Additionally, for example, the third prompt template may include a command (1114). The command (1114) may be a request for the third generative artificial intelligence model (530) to perform an image (50) generation task. The command (1114) may include a placeholder (1124) into which a name (40) corresponding to the list (30) is to be inserted.

[0198] According to one embodiment of the present disclosure, a third generative artificial intelligence model (530) can generate an image (50) based on a third input prompt (1110). For example, the third generative artificial intelligence model (530) can perform an image (50) generation operation according to a command or instruction of the third input prompt (1110).

[0199] According to one embodiment of the present disclosure, a third generative artificial intelligence model (530) can perform an image (50) generation operation. For example, the third generative artificial intelligence model (530) can generate an image representing a name (40) corresponding to a list (30).

[0200] According to one embodiment of the present disclosure, a third generative artificial intelligence model (530) can output a result (1130) including an image (50). An electronic device (100) can acquire the image (50) output by the third generative artificial intelligence model (530).

[0201] FIG. 12 is a drawing for exemplarily illustrating the operation of an electronic device updating a list according to one embodiment of the present disclosure.

[0202] According to one embodiment of the present disclosure, an electronic device (100) can obtain a list (30) based on a content database (140). When the content database (140) is updated (1210), the electronic device (100) can re-obtain (1220) a list (1230) based on the updated content database (142). The electronic device (100) can obtain a new content list (1230) by updating the list (30).

[0203] For example, if the updated content database (142) contains the first recommended content (32), the electronic device (100) may retain the first recommended content (1232) in the list (1230). For example, if the updated content database (142) does not contain the third recommended content (34), the electronic device (100) may delete the third recommended content (34) from the list (30). Additionally, for example, if the updated content database (142) contains the fourth recommended content (1234), the electronic device (100) may add the fourth recommended content (1234) to the list (1230).

[0204] According to one embodiment of the present disclosure, an electronic device (100) can re-acquire a plurality of recommended content (20) from a first artificial intelligence model at a first cycle. The electronic device (100) can update a plurality of recommended content (20) from a first artificial intelligence model at a first cycle. The first cycle can be pre-set. For example, the first cycle can be set to 1 day.

[0205] According to one embodiment of the present disclosure, the electronic device (100) can regenerate a list (30) based on a plurality of recommended content (20) at a first cycle. The electronic device (100) can update the list (30) based on a plurality of recommended content (20) at a first cycle.

[0206] According to one embodiment of the present disclosure, the electronic device (100) may re-obtain a name (40) corresponding to a list (30) from a second artificial intelligence model at a second period. The electronic device (100) may update a name (40) corresponding to a list (30) from a second artificial intelligence model at a second period. The second period may be pre-set. For example, the second period may be set to a relatively longer period than the first period. For example, the second period may be set to 3 days.

[0207] According to one embodiment of the present disclosure, the electronic device (100) can reacquire an image (50) from a third artificial intelligence model every third period. The electronic device (100) can update the image (50) from the third artificial intelligence model every third period. The third period can be pre-set. For example, the third period can be set to a relatively longer period than the second period. For example, the third period can be set to 7 days.

[0208] FIG. 13 is a drawing for exemplarily illustrating the operation of an electronic device according to one embodiment of the present disclosure that provides a list, a name corresponding to the list, and an image.

[0209] According to one embodiment of the present disclosure, an electronic device (100) may provide a list (30), a name (40) corresponding to the list (30), and an image (50). The electronic device (100) may transmit the list (30), the name (40) corresponding to the list (30), and the image (50) to the display device (200) upon a request from the display device (200). For example, when the electronic device (100) receives data from the display device (200), it may transmit the list (30), the name (40) corresponding to the list (30), and the image (50) to the display device (200) based on the received data. The display device (200) may generate a recommended content image (1310) by combining the list (30), the name (40) corresponding to the list (30), and the image (50) by means of an algorithm stored within the display device (200). The recommended content image (1310) may be an image including a list (30), a name (40) corresponding to the list (30), and an image (50). The display device (200) may display the recommended content image (1310) on the user interface of the display device (200).

[0210] According to one embodiment of the present disclosure, an electronic device (100) can obtain a recommended content image (1310) by combining a list (30), a name (40) corresponding to the list (30), and an image (50). For example, the electronic device (100) can arrange the list (30) and the name (40) corresponding to the list (30) so that they do not overlap on the display. The electronic device (100) can arrange the list (30) and the name (40) corresponding to the list (30) on the top layer. The electronic device (100) can arrange the image (50) and the list (30) so that they overlap on the display. The electronic device (100) can arrange the image (50) and the name (40) corresponding to the list (30) so that they overlap on the display. The electronic device (100) can arrange the image (50) on the bottom layer.

[0211] According to one embodiment of the present disclosure, an electronic device (100) may provide a generated recommended content image (1310) to a display device (200) upon a request from a display device (200). When the electronic device (100) receives data from the display device (200), it may provide a generated recommended content image (1310) to the display device (200) based on the received data.

[0212] FIG. 14 is a drawing for exemplarily explaining the operation of a system according to one embodiment of the present disclosure.

[0213] According to one embodiment of the present disclosure, an electronic device (100) may acquire user input (10) (1402). The electronic device (100) may transmit user input (10) to an artificial intelligence server (300) (1404). The electronic device (100) may receive a plurality of recommended content (20) from the artificial intelligence server (300) (1408). Based on the plurality of recommended content, the electronic device (100) may acquire a list (30) (1410). The electronic device (100) may transmit the generated list (30) to the artificial intelligence server (300) (1412). The electronic device (100) may receive a name (40) corresponding to the list (30) from the artificial intelligence server (300) (1416). The electronic device (100) may receive an image (50) from the artificial intelligence server (300) (1420).

[0214] According to one embodiment of the present disclosure, an artificial intelligence server (300) may receive user input (10) from an electronic device (100). The artificial intelligence server (300) may recommend a plurality of contents (1406). The artificial intelligence server (300) may transmit a plurality of recommended contents (20) to the electronic device (100). The artificial intelligence server (300) may receive a list (30) from the electronic device (100). The artificial intelligence server (300) may generate (1414) a name (40) corresponding to the list (30). The artificial intelligence server (300) may transmit the name (40) corresponding to the list (30) to the electronic device (100). The artificial intelligence server (300) may generate (1418) an image (50). The artificial intelligence server (300) may transmit the image (50) to the electronic device (100).

[0215] FIG. 15 is a drawing for exemplarily illustrating the operation of a system according to one embodiment of the present disclosure.

[0216] According to one embodiment of the present disclosure, an electronic device (100) may acquire user input (10) (1502). An electronic device (100) may acquire target viewer information (70) (1504). An electronic device (100) may transmit user input (10) to an artificial intelligence server (300) (1506). An electronic device (100) may transmit target viewer information (70) to an artificial intelligence server (300) (1506). An electronic device (100) may receive a plurality of recommended content (20) from an artificial intelligence server (300) (1510). An electronic device (100) may acquire a list (30) based on the plurality of recommended content (1512). An electronic device (100) may transmit the generated list (30) to an artificial intelligence server (300) (1514). The electronic device (100) can receive (1518) a name (40) corresponding to a list (30) from the artificial intelligence server (300). The electronic device (100) can receive (1522) an image (50) from the artificial intelligence server (300).

[0217] According to one embodiment of the present disclosure, an artificial intelligence server (300) may receive user input (10) from an electronic device (100). An artificial intelligence server (300) may receive target viewer information (70) from an electronic device (100). An artificial intelligence server (300) may recommend a plurality of content (1508). An artificial intelligence server (300) may transmit a plurality of recommended content (20) to an electronic device (100). An artificial intelligence server (300) may receive a list (30) from an electronic device (100). An artificial intelligence server (300) may generate (1516) a name (40) corresponding to the list (30). An artificial intelligence server (300) may transmit the name (40) corresponding to the list (30) to an electronic device (100). An artificial intelligence server (300) may generate an image (50) (1520). The artificial intelligence server (300) can transmit an image (50) to an electronic device (100).

[0218] FIG. 16 is a drawing for exemplarily illustrating the operation of a system according to one embodiment of the present disclosure.

[0219] According to one embodiment of the present disclosure, an electronic device (100) may receive a request for an item to be used in a user interface of a display device (200). The item to be used in a user interface of the display device (200) may include a list (30), a name (40) corresponding to the list (30), and an image (50). The electronic device (100) may provide (1606) the list (30), the name (40) corresponding to the list, and the image (50) to the display device (200).

[0220] According to one embodiment of the present disclosure, a display device (200) may receive a request (1602) from a user who wishes to connect to an electronic device (100). The display device (200) may request (1604) from the electronic device (100) an item to be used in the user interface of the display device (200). For example, the display device (200) may provide data requesting an item to be used in the user interface to the electronic device (100). The item to be used in the user interface of the display device (200) may include a list (30), a name (40) corresponding to the list (30), and an image (50). The display device (200) may receive the list (30), the name (40) corresponding to the list (30), and the image (50) from the electronic device (100).

[0221] According to one embodiment of the present disclosure, a display device (200) can generate a user interface (1608) based on a list (30), a name (40) corresponding to the list (30), and an image (50). For example, the display device (200) can generate a user interface using an algorithm stored within the display device (200).

[0222] According to one embodiment of the present disclosure, a display device (200) may provide a user interface generated based on a list (30), a name (40) corresponding to the list (30), and an image (50). For example, the display device (200) may display (1610) a user interface including a list (30), a name (40) corresponding to the list (30), and an image (50).

[0223] According to one embodiment of the present disclosure, an electronic device (100) can generate a user interface of a display device (200) based on a list (30), a name (40) corresponding to the list (30), and an image (50). The electronic device (100) can provide the generated user interface to the display device (200).

[0224] FIG. 17 is a block diagram illustrating, by way of example, the configuration of an electronic device according to one embodiment of the present disclosure.

[0225] According to one embodiment of the present disclosure, the electronic device (100) may include a communication interface (1710), one or more processors (1720), a memory (1730), and a display unit (1740).

[0226] The communication interface (1710) can perform data communication with other electronic devices under the control of the processor (1720). The communication interface (1710) may include a communication circuit.

[0227] The communication interface (1710) can perform data communication between an electronic device (100) and another electronic device (e.g., a display device (200), an artificial intelligence server (300), etc.) by using at least one of the data communication methods including, for example, a wired LAN (e.g., Ethernet), a wireless LAN (e.g., Wi-Fi), a cellular network (e.g., 4G, 5G, etc.), Bluetooth, BLE (Bluetooth Low Energy), ZigBee, infrared communication (IrDA, infrared Data Association), NFC (Near Field Communication), RF communication, and various other types of known wireless / wired communication technologies.

[0228] The electronic device (100) can transmit and receive recommended content, a list, a name corresponding to the list, or an image to and from another electronic device (e.g., a display device (200), an artificial intelligence server (300), etc.) using a communication interface (1710).

[0229] The processor (1720) can control the overall operations of the electronic device (100). The processor (1720) may include a processing circuit. For example, the processor (1720) can control the overall operations of the electronic device (100) providing a list, a name corresponding to the list, and an image by executing one or more instructions of a program stored in memory (1730). There may be one or more processors (1720).

[0230] The processor (1720) may be composed of at least one of, for example, a Central Processing Unit (CPU), a Microprocessor, a Graphic Processing Unit (GPU), ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), an Application Processor (AP), a Neural Processing Unit (NPU), or an AI-dedicated processor designed with a hardware structure specialized for processing AI models, but is not limited thereto.

[0231] Since the description of the operations of the processor (1720) has already been described in the description of the previous drawings, a repetitive description is omitted.

[0232] The memory (1730) may include various types of memory. The memory (1730) may include flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), non-volatile memory including at least one of ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk, and volatile memory such as RAM (Random Access Memory) or SRAM (Static Random Access Memory).

[0233] The memory (1730) can store one or more instructions and one or more programs that allow the electronic device (100) to provide a list, a name and an image corresponding to the list.

[0234] The display unit (1740) may include at least one of a liquid crystal display, a thin film transistor-liquid crystal display, an organic light-emitting diode, a flexible display, a 3D display, and an electrophoretic display. Additionally, depending on the implementation form of the display unit (1740), two or more display units (1740) may be included. When the display unit (1740) is implemented as a touch screen, the display unit (1740) may be used as an input device, such as a user interface, in addition to an output device.

[0235] Meanwhile, the electronic device (100) may further include additional components to perform the operations described in the above-described embodiment. For example, the electronic device (100) may further include one or more sensors (1750), a video processing module (1760), an audio processing module (1770), a power module (1780), or an input / output interface (1790), etc.

[0236] According to one aspect of the present disclosure, a method for operating an electronic device is provided.

[0237] The above method may include the step of obtaining a list based on a plurality of recommended contents obtained from a first artificial intelligence model based on user input.

[0238] The above method may include the step of obtaining a title associated with the list from a second artificial intelligence model based on the obtained list.

[0239] The above method may include the step of obtaining an image from a third artificial intelligence model based on a name associated with the above list.

[0240] The above method may include the step of providing the list, the name associated with the list, and the image.

[0241] The above first artificial intelligence model may include a first generative artificial intelligence model that generates text.

[0242] The step of obtaining a list based on a plurality of recommended contents obtained from the first artificial intelligence model based on the user input may include the step of obtaining information related to each recommended content among the plurality of recommended contents related to the user input through the first generative artificial intelligence model.

[0243] Information related to each of the above recommended contents may include the name of each of the above recommended contents.

[0244] The information related to each of the above recommended content may further include at least one of the platform corresponding to the provision of the content, the release date of the content, the creator of the content, the playback time of the content, the genre of the content, or the performer information of the content.

[0245] The step of obtaining a list based on the plurality of recommended contents obtained from the first artificial intelligence model based on the user input may include the step of obtaining information related to a subset of each recommended content among the plurality of recommended contents through the first generative artificial intelligence model based on the user input and target viewer information.

[0246] A subset of the above recommended content may include content that takes into account the target audience and may include content related to the user input.

[0247] The above target viewer information may include at least one of the target viewer's gender, the platform used by the target viewer, or the target viewer's preferred genre.

[0248] The step of obtaining a list based on a plurality of recommended contents obtained from the first artificial intelligence model based on the above user input may include the step of adding each recommended content to the list if each recommended content is included in the content database.

[0249] The above second artificial intelligence model may include a second generative artificial intelligence model that generates text.

[0250] The step of obtaining a title related to the list from a second artificial intelligence model based on the above-mentioned obtained list may include the step of obtaining a title related to the list corresponding to the plurality of recommended contents included in the list through the second generative artificial intelligence model based on the above-mentioned list.

[0251] The above third artificial intelligence model may include a third generative artificial intelligence model that generates images.

[0252] The step of obtaining an image from a third artificial intelligence model based on the above-mentioned obtained name may include the step of obtaining the image related to the name related to the list through the third generative artificial intelligence model based on the above-mentioned obtained name.

[0253] The step of providing the above list, the name associated with the above list, and the above image may include the step of transmitting the above list, the name associated with the above list, and the above image to the display device based on the received data when data is received from the display device.

[0254] At least one of the first artificial intelligence model, the second artificial intelligence model, or the third artificial intelligence model may include a multimodal artificial intelligence model that generates images and text.

[0255] According to one aspect of the present disclosure, an electronic device is provided. The electronic device comprises: a communication interface; at least one processor including processing circuitry; and a memory for storing instructions, wherein the instructions may be executed individually or collectively by the at least one processor.

[0256] The above at least one processor can obtain a list based on a plurality of recommended contents obtained from a first artificial intelligence model based on user input.

[0257] The above at least one processor can obtain a title associated with the list from the second artificial intelligence model based on the obtained list.

[0258] The above at least one processor can acquire an image from a third artificial intelligence model based on a name associated with the above list.

[0259] The above at least one processor may provide the list, the name associated with the list, and the image.

[0260] The above first artificial intelligence model may include a first generative artificial intelligence model that generates text.

[0261] The above at least one processor can obtain information related to each recommended content among the plurality of recommended contents related to the user input through the first generative artificial intelligence model.

[0262] Information related to each of the above recommended contents may include the name of each of the above recommended contents.

[0263] The information related to each of the above recommended content may further include at least one of the platform related to the provision of content, the release date of the content, the creator of the content, the playback time of the content, the genre of the content, or the performer information of the content.

[0264] The above at least one processor can obtain information related to a part of each recommended content among the plurality of recommended content through the first generative artificial intelligence model based on the user input and target viewer information.

[0265] A subset of the recommended content may include content that takes the target viewer into consideration and may include content related to the user input. The target viewer information may include at least one of the target viewer's gender, the platform used by the target viewer, or the target viewer's preferred genre.

[0266] The above at least one processor can add each recommended content to a list if each recommended content is included in the content database.

[0267] The above second artificial intelligence model may include a second generative artificial intelligence model that generates text.

[0268] The above at least one processor can obtain a name associated with the list corresponding to the plurality of recommended contents included in the list through the second generative artificial intelligence model based on the list.

[0269] The above third artificial intelligence model may include a third generative artificial intelligence model that generates images.

[0270] The above at least one processor can obtain the image associated with the name associated with the list through the third generative artificial intelligence model based on the acquired name.

[0271] When the above-mentioned at least one processor receives data from a display device, it can transmit the list, the name corresponding to the list, and the image to the display device based on the received data.

[0272] According to one aspect of the present disclosure, a computer-readable recording medium may be provided having a program recorded thereon for operating an electronic device and / or any one of the methods described above and below.

[0273] A device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory storage medium' simply means that it is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily. For example, a 'non-transitory storage medium' may include a buffer in which data is stored temporarily.

[0274] According to one embodiment, the method according to the various embodiments disclosed herein may be provided by being 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 distributed online (e.g., download or upload) through an application store or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., downloadable app) may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

Claims

1. In a method of operating an electronic device, The above method is executed by at least one processor, and the method is, A step of obtaining a list (30) based on a plurality of recommended contents (20; 630; 730) obtained from a first artificial intelligence model (132; 332;) based on user input (10); A step of obtaining a title (40) related to the list (30) from a second artificial intelligence model (134; 334;) based on the list (30); A step of acquiring an image (50) from a third artificial intelligence model (136; 336;) based on the above name (40); and A step of providing the above list (30), a name (40) associated with the above list (30), and the above image (50); A method including 2. In Paragraph 1, The above first artificial intelligence model (132; 332;) includes a first generative artificial intelligence model (510) that generates text, and The step of obtaining the above list (30) is, A step of obtaining information related to each recommended content among the plurality of recommended content (20) related to the user input (10) through the first generative artificial intelligence model (510) based on the user input (10); A method including 3. In Paragraph 2, A method comprising at least one of the information related to each of the above recommended content, each name (625) of each of the above recommended content, a platform corresponding to the provision of content, the release date of the content, the creator of the content, the playback time of the content, the genre of the content, or the performer information of the content.

4. In any one of paragraphs 1 through 3, The step of obtaining the above list (30) is, Based on the user input (10) and target viewer information (70), the method obtains information related to a subset of recommended content among the plurality of recommended content (20; 630; 730) through the first generative artificial intelligence model (510), wherein the subset of recommended content includes content that considers the target viewer and content related to the user input; A method that further includes.

5. In Paragraph 4, The above target viewer information (70) is, A method comprising at least one of the gender of the target viewer, the platform used by the target viewer, or the preferred genre of the target viewer.

6. In any one of paragraphs 1 through 5, The step of obtaining the above list (30) is, If each recommended content is included in the content database (140), the step of adding each recommended content to the list (30); A method including 7. In any one of paragraphs 1 through 6, The above second artificial intelligence model (134; 334;) includes a second generative artificial intelligence model (520) that generates text, and The step of obtaining the above title (40) is, A step of obtaining a name (40) associated with the list (30) corresponding to the plurality of recommended contents (20; 630; 730) included in the list (30) through the second generative artificial intelligence model (520) based on the list (30); A method including 8. In any one of paragraphs 1 through 7, The above third artificial intelligence model (136; 336;) includes a third generative artificial intelligence model (530) that generates images, and The step of acquiring the above image (50) is, A step of obtaining the image (50) associated with the name (40) associated with the list (30) through the third generative artificial intelligence model (530) based on the above-mentioned name (40); A method including 9. In any one of paragraphs 1 through 8, The step of providing the above list (30), the name (40) associated with the above list (30), and the above image (50) is, When data is received from a display device (200), a step of transmitting the list (30), a name (40) associated with the list (30), and the image (50) to the display device (200) based on the received data; A method including 10. In any one of paragraphs 1 through 9, A method comprising at least one of the first artificial intelligence model (132; 332;), the second artificial intelligence model (134; 334;), or the third artificial intelligence model (136; 336;) including a multi-modal artificial intelligence model that generates images and text.

11. In an electronic device (100), Communication interface (110); At least one processor (120) including processing circuitry; and It includes a memory (130) for storing instructions, By executing the above instructions individually or collectively by the at least one processor (120), the electronic device (100) A list (30) is obtained based on a plurality of recommended contents (20; 630; 730) obtained from a first artificial intelligence model (132; 332;) based on user input (10), and Based on the above list (30), a title (40) related to the above list (30) is obtained from the second artificial intelligence model (134; 334;), and Based on the above name (40), an image (50) is obtained from a third artificial intelligence model (136; 336;), and An electronic device (100) providing the above list (30), a name (40) associated with the above list (30), and the above image (50).

12. In Paragraph 11, The above first artificial intelligence model (132; 332;) includes a first generative artificial intelligence model (510) that generates text, and By executing the above instructions by the at least one processor (120), the electronic device (100) An electronic device (100) that obtains information related to each recommended content among the plurality of recommended content (20) related to the user input (10) through the first generative artificial intelligence model (510) based on the user input (10).

13. In Paragraph 12, The electronic device (100) includes information related to the above recommended content, each name (625) of the above recommended content and at least one of the platform related to the provision of the content, the release date of the content, the creator of the content, the playback time of the content, the genre of the content, or the performer information of the content.

14. In any one of paragraphs 11 through 13, By executing the above instructions by the at least one processor (120), the electronic device (100) An electronic device (100) that obtains information related to each recommended content among the plurality of recommended content (20; 630; 730) related to the user input (10) considering the target viewer through the first generative artificial intelligence model (510) based on the user input (10) and target viewer information (70).

15. A computer-readable recording medium having a program recorded thereon for performing the method of any one of paragraphs 1 through 10 on a computer.

Images