Electronic apparatus and control method therefor

Abstract

This electronic apparatus comprises: a memory for storing at least one neural network model; and at least one processor connected to the memory so as to control the electronic apparatus, wherein the at least one neural network model includes a model trained to acquire at least one recommended piece of content on the basis of viewing characteristics of a user of the electronic apparatus. The at least one processor executes at least one instruction stored in the memory so as to: acquire, on the basis of history information, profile information reflecting viewing characteristics of a user of the electronic apparatus; identify one context type corresponding to a current viewing situation from among a plurality of context types classified according to a viewing situation of the user of the electronic apparatus; and acquire, on the basis of at least one of the acquired profile information and the history information, at least one recommended piece content corresponding to at least one context type identified through the at least one neural network model.

Description

Electronic device and control method thereof

[0001] The present disclosure relates to an electronic device and a method for controlling the same, and more specifically, to an electronic device and a method for controlling the same that obtains recommended content through a neural network model.

[0002] Recently, the use of electronic products that allow users to search for desired content and find and provide matching content is increasing. Alternatively, the use of electronic products that provide related content based on recommendation algorithms, in addition to the content the user searched for, is also on the rise.

[0003] For electronic products that provide such content search and recommendation algorithm functions, while it is possible to provide content that reflects the user's preferences, there was a problem in that it was difficult to perform search or content recommendations that continue the search situation or context.

[0004] In addition, there was a problem where users had to accurately specify the particular title or content of the desired material to obtain the desired result.

[0005] An electronic device according to one embodiment of the present disclosure comprises a memory storing at least one neural network model and at least one processor connected to the memory to control the electronic device, wherein the at least one neural network model includes a model trained to obtain at least one recommended content based on the viewing characteristics of a user of the electronic device. The at least one processor obtains profile information reflecting the viewing characteristics of a user of the electronic device based on historical information by executing at least one instruction stored in the memory, identifies one context type corresponding to the current viewing situation among a plurality of context types classified according to the viewing situation of a user of the electronic device, and obtains at least one recommended content corresponding to the identified at least one context type through the at least one neural network model based on at least one of the obtained profile information and the historical information.

[0006] The electronic device may further include a communication device for performing communication with an external electronic device, and the at least one neural network model includes a model trained to generate the profile information based on the history information of the electronic device, and the at least one processor may obtain profile information corresponding to the user through the at least one neural network model based on the user identification information received from the external electronic device.

[0007] The electronic device may further include a communication device for performing communication with an external electronic device, and the at least one processor may receive and obtain profile information generated by the external electronic device based on the user's identification information from the external electronic device.

[0008] If the above-mentioned at least one processor identifies that the history information includes a usage history corresponding to at least one other user other than the user, it can obtain multi-user profile information reflecting the viewing characteristics of each of the plurality of users, including the user and the at least one other user, through the neural network model, and obtain the at least one recommended content based on the multi-user profile information.

[0009] The above multi-profile information may include detailed information separated by multiple categories for each of the multiple viewers, and if the at least one processor identifies that there exists at least one category among the categories included in each of the multiple profiles in which the detailed information is common, the processor may obtain the at least one recommended content based on the at least one category.

[0010] The above plurality of context types includes at least one of a first context type corresponding to a situation in which the electronic device is first used after being turned on from a turned-off state, a second context type corresponding to a situation in which the electronic device is in use after being turned on, and a third context type corresponding to a situation in which the previously selected recommended content is played again after one of at least one previously acquired recommended content is selected, and the at least one processor can acquire at least one recommended content corresponding to the identified at least one context type through the at least one neural network model based on at least one of the acquired profile information and the history information.

[0011] When the above-mentioned at least one processor identifies the current viewing situation as the first context type, it obtains the at least one recommended content through the at least one neural network model based on the history information including at least one of content information played before the electronic device was turned off, application activity information, and usage time of the electronic device; when the current viewing situation is identified as the second context type, it obtains the at least one recommended content through the neural network model based on the history information including at least one of viewing time and search history for a plurality of content previously displayed through the display; and when the current viewing situation is identified as the third context type, it obtains the at least one recommended content through the neural network model based on the history information including at least one of content information selected after the previously selected recommended content and at least one of the executed application type.

[0012] The electronic device further includes a display, and the at least one processor can control the display to display a screen including the at least one acquired recommendation content.

[0013]

[0014] The above at least one processor can control the display to display a screen including the identified context type, a preview of each of the at least one recommended content corresponding to the context type, a preview of the selected content among the at least one recommended content, and at least one video included in the selected content.

[0015] The above at least one processor controls the display to display a screen in which the plurality of contents are arranged according to a plurality of lists with different recommendation criteria, and controls the display to display the remaining plurality of previews among each of the preview images, excluding the preview of the selected content, differently from at least one of the size, brightness, color, and clarity of the preview of the selected content.

[0016] A control method for an electronic device according to one embodiment of the present disclosure comprises: acquiring profile information that reflects the viewing characteristics of a user of the electronic device based on history information; identifying one context type corresponding to the current viewing situation among a plurality of context types classified according to the viewing situation of the user; and acquiring at least one recommended content corresponding to the identified at least one context type through at least one neural network model based on at least one of the acquired profile information and the history information. The at least one neural network model includes a model trained to acquire at least one recommended content based on the viewing characteristics of a user of the electronic device.

[0017] The above at least one neural network model may include a model trained to generate the profile information based on the history information of the electronic device. The step of acquiring the profile information may include acquiring profile information corresponding to the user through the at least one neural network model based on the user identification information received from the external electronic device.

[0018] The step of acquiring the above profile information may include receiving and acquiring profile information generated by the external electronic device based on the user's identification information from the external electronic device.

[0019] The step of acquiring the profile information may include, if it is identified that the history information includes a usage history corresponding to at least one other user other than the user, acquiring multi-user profile information reflecting the viewing characteristics of each of a plurality of users, including the user and the at least one other user, through the neural network model. The step of acquiring the at least one recommended content may include, if it is identified that the history information includes a usage history corresponding to at least one other user other than the user, acquiring the at least one recommended content based on the multi-profile information.

[0020] The above multiple profile information may include detailed information classified by multiple categories for each of the multiple viewers. The step of obtaining at least one recommended content may include, if it is identified that there exists at least one category among the categories included in each of the multiple profiles that has common detailed information, the step of obtaining at least one recommended content based on the at least one category.

[0021] The plurality of context types may include at least one of a first context type corresponding to a situation in which the electronic device is used for the first time after being turned on from a turned-off state, a second context type corresponding to a situation in which the electronic device is in use after being turned on, and a third context type corresponding to a situation in which the previously selected recommended content is played again after one of at least one previously acquired recommended content is selected. The step of acquiring at least one recommended content may include the step of acquiring at least one recommended content corresponding to the identified at least one context type through at least one neural network model based on at least one of the acquired profile information and the history information.

[0022] The step of acquiring at least one content may include: a step of acquiring at least one recommended content through at least one neural network model based on history information including at least one of content information played before the electronic device was turned off, application activity information, and usage time of the electronic device, when the current viewing situation is identified as the first context type; a step of acquiring at least one recommended content through the neural network model based on history information including at least one of viewing time and search history for a plurality of content previously displayed through the display, when the current viewing situation is identified as the second context type; and a step of acquiring at least one recommended content through the neural network model based on history information including at least one of content information selected after the previously selected recommended content and at least one of the executed application type, when the current viewing situation is identified as the third context type.

[0023] The electronic device further includes a display, and the control method of the electronic device may further include the step of controlling the display to display a screen including at least one acquired recommendation content.

[0024] The step of controlling the display may include controlling the display to display a screen including the identified context type, a preview of each of the at least one recommended content corresponding to the context type, a preview of the selected content among the at least one recommended content, and at least one video included in the selected content.

[0025] The step of controlling the display may include controlling the display to display a screen in which the plurality of contents are arranged according to a plurality of lists with different recommendation criteria, and controlling the display to display the remaining plurality of previews, excluding the preview of the selected content among each of the preview images, differently from at least one of the size, brightness, color, and clarity of the preview of the selected content.

[0026] A non-transient computer-readable recording medium storing computer instructions that cause the electronic device to perform an operation when executed by a processor of an electronic device according to one embodiment of the present disclosure, wherein the operation comprises: a step of acquiring profile information reflecting the viewing characteristics of a user of the electronic device based on history information; a step of identifying one context type corresponding to the current viewing situation among a plurality of context types classified according to the viewing situation of a user; and a step of acquiring at least one recommended content corresponding to the identified at least one context type through at least one neural network model based on at least one of the acquired profile information and the history information, wherein the at least one neural network model includes a model trained to acquire at least one recommended content based on the viewing characteristics of a user of the electronic device.

[0027] FIG. 1 is a drawing for explaining the operation of an electronic device and an external electronic device according to one or more embodiments of the present disclosure.

[0028] FIG. 2 is a block diagram for explaining the configuration of an electronic device according to one or more embodiments of the present disclosure.

[0029] FIG. 3 is a detailed block diagram for explaining the detailed configuration of an electronic device according to one or more embodiments of the present disclosure.

[0030] FIG. 4 is a drawing for explaining the operation of an electronic device according to one or more embodiments of the present disclosure.

[0031] FIG. 5 is a drawing for illustrating multi-user profile information according to one or more embodiments of the present disclosure.

[0032] FIG. 6 is a drawing for explaining an image including recommended content according to one or more embodiments of the present disclosure.

[0033] FIG. 7 is a drawing for explaining an overview according to one or more embodiments of the present disclosure.

[0034] FIG. 8 is a drawing for explaining an overview according to one or more embodiments of the present disclosure.

[0035] FIG. 9 is a drawing for explaining screen effects according to one or more embodiments of the present disclosure.

[0036] FIG. 10a is a drawing for illustrating an interaction according to one or more embodiments of the present disclosure.

[0037] FIG. 10b is a drawing for illustrating an interaction according to one or more embodiments of the present disclosure.

[0038] FIG. 11 is a drawing for explaining search terms according to one or more embodiments of the present disclosure.

[0039] FIG. 12 is a drawing for explaining search terms according to one or more embodiments of the present disclosure.

[0040] FIG. 13a is a drawing for explaining content-related information according to one or more embodiments of the present disclosure.

[0041] FIG. 13b is a drawing for explaining content-related information according to one or more embodiments of the present disclosure.

[0042] FIG. 13c is a drawing for explaining content-related information according to one or more embodiments of the present disclosure.

[0043] FIG. 13d is a drawing for explaining content-related information according to one or more embodiments of the present disclosure.

[0044] FIG. 14 is a flowchart illustrating a method for controlling an electronic device capable of communicating with a plurality of display devices according to one or more embodiments of the present disclosure.

[0045] The embodiments described herein are subject to various modifications and may have various forms; specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope of specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives of the embodiments of the present disclosure. In relation to the description of the drawings, similar reference numerals may be used for similar components.

[0046] In describing the present disclosure, if it is determined that a detailed description of related known functions or configurations could unnecessarily obscure the essence of the present disclosure, such detailed description is omitted.

[0047] Additionally, the following embodiments may be modified in various other forms, and the scope of the technical concept of the present disclosure is not limited to the following embodiments. Rather, these embodiments are provided to make the present disclosure more faithful and complete and to fully convey the technical concept of the present disclosure to those skilled in the art.

[0048] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit the scope of the rights. The singular expression includes the plural expression unless the context clearly indicates otherwise.

[0049] In the present disclosure, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of such features (e.g., numerical values, functions, actions, or components such as parts) and do not exclude the presence of additional features.

[0050] In the present disclosure, expressions such as “A or B,” “at least one of A or / and B,” or “one or more of A or / and B” may include all possible combinations of items listed together. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” may refer to cases including (1) at least one A, (2) at least one B, or (3) both at least one A and at least one B.

[0051] Expressions such as "first," "second," "first," or "second" used in this disclosure may modify various components regardless of order and / or importance, and are used only to distinguish one component from another and do not limit said components.

[0052] When it is stated that a certain component (e.g., a first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that the said certain component may be directly connected to the said other component or connected through another component (e.g., a third component).

[0053] On the other hand, when it is stated that a certain component (e.g., a first component) is "directly connected" or "directly coupled" to another component (e.g., a second component), it may be understood that no other component (e.g., a third component) exists between said certain component and said other component.

[0054] As used in this disclosure, the expression “configured to” may be replaced, depending on the context, with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of.” The term “configured to” may not necessarily mean only “specifically designed to” in hardware.

[0055] Instead, in some situations, the expression “device configured to do something” may mean that the device is “capable of doing something” in conjunction with other devices or components. For example, the phrase “processor configured (or set) to perform A, B, and C” may refer to a dedicated processor for performing those operations (e.g., an embedded processor), or a generic-purpose processor (e.g., a CPU or application processor) capable of performing those operations by executing one or more software programs stored in a memory device.

[0056] In the embodiments, a 'module' or 'part' performs at least one function or operation and may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of 'modules' or a plurality of 'parts' may be integrated into at least one module and implemented by at least one processor, except for the 'module' or 'part' that needs to be implemented in specific hardware.

[0057] Meanwhile, various elements and areas in the drawings are depicted schematically. Accordingly, the technical concept of the present invention is not limited by the relative sizes or spacing depicted in the attached drawings.

[0058] Hereinafter, embodiments according to the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement them.

[0059] FIG. 1 is a drawing for explaining the operation of an electronic device and an external electronic device according to one or more embodiments of the present disclosure.

[0060] According to FIG. 1, an electronic device (100) and an external electronic device (200) are illustrated. The electronic device (100) can communicate with the external electronic device (200) and can output a screen containing at least one piece of content.

[0061] Here, the electronic device (100) and the external electronic device (200) may be implemented as at least one of a smartphone, tablet PC, desktop PC, laptop PC, PC, set-top box, OTT service (Over-the-top media service) server, console (video game console), Blu-ray player, DVD player, home automation control panel, security control panel, media box (e.g., Samsung HomeSync™, Apple TV™, or Google TV™), and game console (e.g., Xbox™, PlayStation™).

[0062] For example, if the electronic device (100) is implemented as a set-top box, the electronic device (100) can provide content received from an external source to an external display device equipped with a display. Here, the electronic device (100) can identify at least one of a plurality of contents received from an external content source. Here, the electronic device (100) can identify content recommended to the user based on user data regarding the user of the electronic device (100). Here, the user data may correspond to data received from an external electronic device (200) or data already stored in the electronic device (100). At this time, the electronic device (100) can acquire at least one identified content as at least one recommended content.

[0063] At this time, the electronic device (100) may provide the acquired recommendation content to an external display device. However, it is not limited thereto, and may also provide information for identifying the acquired recommendation content or the aforementioned user data to an external display device.

[0064] Meanwhile, if the electronic device (100) is equipped with a display device (e.g., smartphone, tablet, TV, etc.) that has a display for outputting an image included in the content, the image included in the content can be output through the provided display. Here, the content may include at least one of text, images, and videos received from an external content source or stored in the electronic device (100).

[0065] For example, the external electronic device (200) may be implemented as a mobile device such as a smartphone or tablet, and the electronic device (100) may be implemented as a display device equipped with a display.

[0066] For example, an electronic device (100) may communicate with an external electronic device (200) to receive necessary information (e.g., user data) and output content corresponding to the received information. In this case, the external electronic device (200) may provide information (or data) necessary for the electronic device (100) to identify and output recommended content. The necessary information may include information about a user utilizing the electronic device (100) (e.g., ID, preferred content information, viewing history, etc.).

[0067] Meanwhile, the electronic device (100) can output a screen containing acquired recommended content. Here, the user of the electronic device (100) may operate the electronic device (100) or operate it through an external electronic device (200) to search for content. Here, the recommended content may correspond to the search results. At this time, the electronic device (100) may not only display recommended content based on the search but also display related information.

[0068] For example, a user can search for 'past national team soccer matches,' and the electronic device (100) can output news about the national team soccer matches as shown in FIG. 1. At this time, the electronic device (100) can display a video of the past national team soccer match (e.g., a news video including a highlight video) on the screen as recommended content. Here, the electronic device (100) can display not only the news video corresponding to the search results, but also text providing information on the schedule of the national team soccer match scheduled for the future (South Korea vs. Japan soccer match).

[0069] The text provided here may correspond to a phrase that guides the functions that the electronic device (100) can provide, such as "There is a South Korea vs. Japan soccer match this week! Tell me if you want to make a reservation," while simultaneously inducing user input. Here, the user's input may be provided through the operation interface of a remote control, touchpad, microphone, or external electronic device (200) used in conjunction with the electronic device (100). Subsequently, when the user inputs an operation to reserve (or receive a reminder) watching the soccer match, a message indicating that the soccer match viewing reservation has been completed may be displayed.

[0070] Although the above description describes an example in which content corresponding to a user search input is output and related information is provided together as in FIG. 1, it is not limited thereto. The electronic device (100) can display various types of information (e.g., ratings, plot, next recommended video, etc.) depending on the type of content recommended to the user, and the electronic device (100) can display multiple types of content in various ways. This will be explained in detail in the following section.

[0071] FIG. 2 is a block diagram for explaining the configuration of an electronic device according to one or more embodiments of the present disclosure.

[0072] According to FIG. 2, the electronic device (100) may include memory (110) and a processor (120).

[0073] The memory (110) is electrically connected to at least one processor (120) and can store data necessary for various embodiments of the present disclosure. For example, the memory (110) may be implemented as an internal memory such as ROM (e.g., EEPROM (electrically erasable programmable read-only memory)) or RAM included in the processor (120), or it may be implemented as a memory separate from at least one processor (120).

[0074] Depending on the purpose of data storage, the memory (110) may be implemented in the form of a memory embedded in the electronic device (100) or in the form of a memory that can be attached to and detached from the electronic device (100). For example, data for operating the electronic device (100) may be stored in a memory embedded in the electronic device (100), and data for the expansion function of the electronic device (100) may be stored in a memory that can be attached to and detached from the display device (210). When implemented as memory embedded in a display device (210), the memory (110) may be at least one of volatile memory (e.g., DRAM (dynamic RAM), SRAM (static RAM), or SDRAM (synchronous dynamic RAM), non-volatile memory (e.g., OTPROM (one time programmable ROM), PROM (programmable ROM), EPROM (erasable and programmable ROM), EEPROM (electrically erasable and programmable ROM), mask ROM, flash ROM, flash memory (e.g., NAND flash or NOR flash), hard drive, or solid state drive (SSD).

[0075] Meanwhile, although the illustrated example shows the electronic device (100) being composed of a single memory, when distinguishing between volatile memory and non-volatile memory, the electronic device (100) may be described as including multiple memories.

[0076] A memory (110) according to one or more embodiments may store at least one instruction. Here, the at least one instruction may correspond to at least one command for the electronic device (100) to obtain at least one recommended content. In addition, the memory (110) may store information necessary for the operation of the electronic device (100).

[0077] According to one or more embodiments, the memory (110) may store at least one neural network model. Here, the neural network model is a computer system or software module for implementing human-level intelligence, and has the characteristic that the machine learns and makes judgments on its own and the recognition rate improves with use.

[0078] Neural network models consist of machine learning (deep learning) technology that uses algorithms to self-classify and learn the features of input data, and elemental technologies that utilize machine learning algorithms to mimic functions such as cognition and judgment of the human brain.

[0079] The elemental technologies may include, for example, at least one of linguistic understanding technology that recognizes human language / characters, visual understanding technology that recognizes objects like human vision, reasoning / prediction technology that judges information to logically reason and predict, and knowledge representation technology that processes human experience information into knowledge data.

[0080] Meanwhile, neural network models can correspond to Generative Artificial Intelligence (Generative AI) models. Generative AI is an AI system focused on generating new data; it learns patterns from given data to generate data that is similar or entirely new. Generative AI can be distinguished from general artificial intelligence, which aims at data interpretation and pattern recognition.

[0081] According to one or more embodiments, at least one neural network model may include a model trained to obtain at least one recommended content based on the viewing characteristics of a user of the electronic device (100). For example, at least one neural network model may include a generative artificial intelligence model trained to obtain recommended content suitable for a user based on the viewing characteristics of a user of the electronic device (e.g., viewing time, patterns, preferred content, preferred application information, etc.).

[0082] According to one or more embodiments, at least one neural network model may include a model trained to generate profile information based on historical information (viewed content, applications used, usage time, etc.) of an electronic device (100). Here, the profile information may correspond to information including viewing characteristics based on a user's personal viewing history and personal information (gender, age, etc.). For example, at least one neural network model may include a generative artificial intelligence model trained to generate profile information reflecting the viewing characteristics of a specific user based on the usage history of the electronic device (100).

[0083] According to one or more embodiments, the memory (110) can store content received from an external electronic device (200), etc., and can store information about the acquired recommended content as well as the user profile information and viewing history described above. Here, if there are multiple users of the electronic device (100), the viewing history may be stored in the memory (110) in the form of data distinguished by user. However, it is not limited thereto, and the electronic device (100) may store various information (or data) for acquiring at least one recommended content.

[0084] At least one processor (120) can perform overall control operations of the electronic device (100). Specifically, at least one processor (120) functions to control the overall operation of the electronic device (100).

[0085] At least one processor (120) may be implemented as a digital signal processor (DSP), microprocessor, or time controller (TCON) that processes digital signals. However, it is not limited thereto, and may include or be defined by one or more of a central processing unit (CPU), micro controller unit (MCU), micro processing unit (MPU), controller, application processor (AP), graphics-processing unit (GPU), communication processor (CP), or ARM processor. Additionally, at least one processor (120) may be implemented as a System on Chip (SoC) or large-scale integration (LSI) with a built-in processing algorithm, or may be implemented in the form of a Field Programmable Gate Array (FPGA). Furthermore, at least one processor (120) can perform various functions by executing computer executable instructions stored in memory (110). Meanwhile, in FIG. 2, only one processor in the electronic device (100) Although it is described as being included, when implementing it, multiple processors (e.g., CPU + GPU, CPU + DSP) may be included.

[0086] According to one or more embodiments, in an electronic device, at least one processor (120) can obtain profile information reflecting the viewing characteristics of a user of the electronic device based on history information by executing at least one instruction stored in memory.

[0087] According to one or more embodiments, at least one neural network model may include a model trained to generate profile information based on the history information of an electronic device.

[0088] At this time, at least one processor (120) can obtain profile information corresponding to the user through at least one neural network model based on user identification information received from an external electronic device.

[0089] According to one or more embodiments, at least one processor (120) can receive and obtain profile information generated by an external electronic device based on user identification information from an external electronic device.

[0090] According to one or more embodiments, at least one processor (120) can identify one context type corresponding to the current viewing situation among a plurality of context types distinguished according to the user's viewing situation. Here, the context may include various information surrounding the user using the electronic device (100) in a specific situation. For example, the context may refer to a specific time, place, or state in which the user uses the electronic device (100). At this time, the plurality of context types may be categorized by the user's viewing situation and stored in memory (110) in the form of data.

[0091] Here, the plurality of context types may include at least one of a first context type corresponding to a situation in which the electronic device is used for the first time after being turned on from a turned-off state, a second context type corresponding to a situation in which the electronic device is in use after being turned on, and a third context type corresponding to a situation in which the previously selected recommended content is played again after one of at least one previously acquired recommended content is selected.

[0092] According to one or more embodiments, at least one processor (120) can obtain at least one recommendation content corresponding to at least one context type identified through at least one neural network model based on at least one of the obtained profile information and history information.

[0093] According to one or more embodiments, if at least one processor (120) identifies that the history information includes a usage history corresponding to at least one other user other than the user, it can obtain multi-user profile information reflecting the viewing characteristics of each of the multiple users, including the user and at least one other user, through a neural network model, and obtain at least one recommended content based on the multi-user profile information.

[0094] Here, multi-profile information may include detailed information separated by multiple categories for each of multiple viewers.

[0095] According to one or more embodiments, if at least one processor (120) identifies that there is at least one category among the categories included in each of the multiple profiles that has common details, it can obtain at least one recommended content based on at least one category.

[0096] According to one or more embodiments, if at least one processor (120) identifies the current viewing situation as a first context type, it can obtain at least one recommended content through at least one neural network model based on history information including at least one of content information played before the electronic device was turned off, application activity information, and usage time of the electronic device.

[0097] According to one or more embodiments, if at least one processor (120) identifies the current viewing situation as a second context type, it obtains at least one recommended content through a neural network model based on history information including at least one of a plurality of content-specific viewing times and search history previously displayed through a display, and

[0098] According to one or more embodiments, if at least one processor (120) identifies the current viewing situation as a third context type, it can obtain at least one recommended content through a neural network model based on history information including at least one content information selected after previously selected recommended content and at least one of the types of applications executed.

[0099] According to one or more embodiments, at least one processor (120) may control a display to display a screen containing at least one acquired recommendation content. Here, the image containing the recommendation content may refer to a screen displaying not only the recommendation content but also information related to the recommendation content, as illustrated in FIG. 1. However, it is not limited thereto. A more specific description of the image containing the recommendation content will be described in detail below in FIG. 6.

[0100] According to one or more embodiments, at least one processor (120) can control a display to display a screen including an identified context type, a preview of each of at least one recommended content corresponding to the context type, a preview of a selected content among at least one recommended content, and at least one image included in the selected content.

[0101] According to one or more embodiments, at least one processor (120) can control the display to display a screen in which multiple contents are arranged in multiple lists with different recommendation criteria. Additionally, at least one processor (120) can control the display to display multiple previews, excluding the preview of the selected content among each preview video, differently from at least one of the size, brightness, color, and clarity of the preview of the selected content. This will be explained in detail below in FIG. 7.

[0102] Meanwhile, at least one processor (120) may perform various operations of the present disclosure using the neural network model described above.

[0103] According to one or more embodiments, the memory (110) may store at least one neural network model. Here, the at least one neural network model may include a model trained to generate profile information based on the history information of the electronic device (100) as described above. Additionally, the at least one neural network model may include a model trained to obtain at least one recommended content based on the viewing characteristics of the user of the electronic device (100).

[0104] However, at least one neural network model is not implemented only by the example described above, and in addition, the neural network model in the present disclosure may perform operations such as identifying one context type corresponding to the current viewing situation among a plurality of context types by the execution of at least one processor (120), acquiring multi-user profile information reflecting the viewing characteristics of each of a plurality of users, acquiring relevant information regarding the acquired recommended content (e.g., content related to search results, etc.) and configuring a screen containing the recommended content and relevant information to correspond to the user profile information.

[0105] Below, the operation of an electronic device (100) acquiring at least one recommended content corresponding to at least one context type identified through at least one neural network model based on at least one of the acquired profile information and history information will be described in detail.

[0106] Although the electronic device (100) in FIG. 2 is illustrated as including only basic components (i.e., memory, processor), the electronic device (100) may include various additional components in addition to the components described above. Examples of such cases will be explained below with reference to FIG. 3.

[0107] FIG. 3 is a detailed block diagram for explaining the detailed configuration of an electronic device according to one or more embodiments of the present disclosure.

[0108] Referring to FIG. 3, the electronic device (100) may include a memory (110), a processor (120), a display (130), a communication device (140), a microphone (150), and a speaker (160).

[0109] As the memory (110) and at least one processor (120) were previously described in FIG. 2, a redundant description is omitted.

[0110] The electronic device (100) displays video data through a display (130). The display (130) may be implemented as a TV, but is not limited thereto; any device equipped with a display function, such as a video wall, LFD (large format display), Digital Signage, DID (Digital Information Display), projector display, etc., can be applied without limitation.

[0111] Additionally, the display (130) can be implemented as various types of displays such as LCD (liquid crystal display), OLED (organic light-emitting diode), LCoS (Liquid Crystal on Silicon), DLP (Digital Light Processing), QD (quantum dot) display panel, QLED (quantum dot light-emitting diodes), μLED (Micro light-emitting diodes), Mini LED, etc. Meanwhile, the display (130) can be implemented as a touch screen combined with a touch sensor, a flexible display, a rollable display, a 3D display, a display in which multiple display modules are physically connected, etc.

[0112] According to one or more embodiments, at least one processor (120) can control a display to display a screen containing at least one acquired recommended content. For example, the display can be controlled to display a screen containing an identified context type, a preview of each of at least one recommended content corresponding to the context type, a preview of a selected content among at least one recommended content, and at least one image included in the selected content. For example, the at least one processor (120) can control the display (130) to display not only the recommended content acquired based on user profile information, but also information about the context type related to the recommendation of the content, and multiple previews so that the user can select one content when there are multiple recommended contents. A detailed explanation thereof will be provided later in FIG. 6.

[0113] According to one or more embodiments, at least one processor (120) can control the display (130) to display a screen in which multiple contents are arranged in multiple lists with different recommendation criteria. For example, at least one processor (120) can control the display (130) to display multiple previews other than the preview of the selected content among each preview video, with a size, brightness, color, and clarity different from at least one of the preview of the selected content. For example, at least one processor (120) can control the display (130) so that the preview of the selected content is displayed with relative emphasis compared to the previews of the remaining recommended content. A detailed explanation thereof will be provided later in FIG. 7.

[0114] The communication device (140) is configured to communicate with various types of external devices according to various types of communication methods. The communication device (140) may include a Wi-Fi module, a Bluetooth module, an infrared communication module, and a wireless communication module, etc. Here, each communication module may be implemented in the form of at least one hardware chip.

[0115] Wi-Fi modules and Bluetooth modules can perform communication using Wi-Fi and Bluetooth methods, respectively. When using a Wi-Fi module or a Bluetooth module, various connection information, such as SSID and session key, is transmitted and received first; after establishing a communication connection using this information, various information can be transmitted and received.

[0116] The infrared communication module performs communication according to infrared communication (IrDA, Infrared Data Association) technology, which uses infrared rays located between visible light and millimeter waves to wirelessly transmit data over short distances.

[0117] In addition to the communication method described above, the wireless communication module may include at least one communication chip that performs communication according to various wireless communication standards such as Zigbee, 3G (3rd Generation), 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), LTE-A (LTE Advanced), 4G (4th Generation), and 5G (5th Generation).

[0118] In addition, the communication device (140) may include at least one wired communication module that performs communication using a LAN (Local Area Network) module, an Ethernet module, a pair cable, a coaxial cable, a fiber optic cable, or an UWB (Ultra Wide-Band) module, etc. Such a communication device (140) may also be referred to as a transceiver.

[0119] According to one or more embodiments, profile information corresponding to a user can be obtained through at least one neural network model based on user identification information received from an external electronic device through a communication device (140). For example, identification information can be received from a terminal used by a user of the electronic device (100). Here, the identification information may include information related to the user, such as the user's age, gender, and location. At least one processor (120) can obtain profile information based on the received identification information by using a neural network model trained to generate profile information based on the history information of the electronic device (100). A detailed explanation thereof will be provided later in FIG. 4.

[0120] According to one or more embodiments, at least one processor (120) may receive profile information generated by an external electronic device based on user identification information from an external electronic device via a communication device (140). Here, the profile information generated by the external electronic device may correspond to information generated using a neural network model stored in the external electronic device, similar to the profile information obtained by at least one processor (120) based on usage history. Additionally, the profile information for a specific user generated by the external electronic device may correspond to information reflecting the viewing characteristics of the specific user's electronic device (100). A detailed explanation thereof will be provided in detail later in FIG. 4.

[0121] Although the above description describes an example in which at least one processor (120) receives information related to user profile information through a communication device (140), it is not limited thereto. In cases where the electronic device (100) is implemented as a device connected to an external display device, etc. (e.g., a set-top box, etc.), it may receive information necessary to obtain at least one recommended content, such as multiple contents and information related to the content, from the external electronic device through the communication device (140). However, it is not limited thereto.

[0122] A microphone (150) provided in an electronic device (100) receives a user voice and can transmit the received user voice to at least one processor (120). Subsequently, the at least one processor (120) can input the received user voice into a speech recognition model to perform speech recognition. For example, the at least one processor (120) can perform speech recognition on the user voice by performing STT (Speech to Text) on the user voice.

[0123] According to one or more embodiments, when an electronic device (100) receives a user voice through a microphone (150) to obtain at least one recommended content, at least one processor (120) can obtain at least one recommended content based on user profile information, etc. However, it is not limited thereto.

[0124] For example, if a user speaks through a microphone (150) saying, "What is the movie about growing potatoes on Mars?", at least one processor (120) performs STT on the user's voice to convert the user's voice into text, and can obtain recommended content suitable for the user's speech intent through at least one neural network model (e.g., LLM (large language model)).

[0125] Meanwhile, in addition to the case where the electronic device (100) is equipped with a microphone, such user voice may be input as an analog voice signal to a microphone of an external device, such as a remote control. The remote control, etc., may digitize the analog voice signal and transmit it to the electronic device (100). However, it is not limited thereto.

[0126] For example, if an external electronic device that communicates with the electronic device (100) and provides data necessary for the electronic device (100) to obtain recommended content is implemented as a smartphone, the user can remotely control the electronic device (100) through the smartphone based on the user's voice input through the microphone provided in the smartphone. Specifically, the smartphone can perform voice recognition functions through an installed remote control application. However, the external device that performs these voice recognition and remote control functions is not limited to being performed only by the smartphone, and the same functions can also be performed through an AI speaker and other electronic devices on which applications can be installed.

[0127] Meanwhile, the electronic device (100) can output a rendered acoustic signal through a speaker (160). In this case, the speaker (160) may be implemented as at least one speaker (160) unit. For example, the speaker (160) may include a plurality of speakers (160) for multi-channel playback. For example, the speaker (160) may include a plurality of speakers (160) responsible for each channel that is mixed and output. In some cases, the speaker (160) responsible for at least one channel may be implemented as a speaker (160) array including a plurality of speaker (160) units for playing different frequency bands.

[0128] For example, at least one processor (120) can control a speaker (160) to output at least one acquired recommended content and information about the recommended content as voice. Additionally, at least one processor (120) can control a speaker (160) to output information about context related to the recommended content as voice. For example, if a user enters a search term such as "What is the movie about growing potatoes on Mars?" through a microphone (150), at least one processor (120) can control a speaker (160) to output the title of the recommended content, such as "The movie about growing potatoes on Mars that you searched for is XX," as voice, and can control a speaker (160) to output information about related content as voice, such as "I will recommend a video of an experiment to see if potatoes can be grown on Mars." Additionally, at least one processor (120) can also display context (information about the current viewing time) as, such as "I will recommend a video produced by the AA channel that you have been watching frequently at this time recently."

[0129] Meanwhile, although an electronic device including various additional configurations is illustrated in FIG. 3, some of the illustrated configurations may be implemented in an omitted form. Additionally, other configurations not illustrated may be included.

[0130] Hereinafter, the operation of the electronic device (100) acquiring at least one recommended content by the various configurations described above will be explained in detail.

[0131] FIG. 4 is a drawing for explaining the operation of an electronic device according to one or more embodiments of the present disclosure.

[0132] According to FIG. 4, the electronic device (100) can acquire a user profile based on screen activity data (11) and acquire and display curation content based on the acquired profile information. At this time, the electronic device (100) can communicate with an external electronic device (200) to receive at least one of user identification information (21) and generated profile information (22).

[0133] Specifically, at least one processor of the electronic device (100) may include a user profile creation and management unit (121) and a curation unit (122) through generative AI. The user profile creation and management unit (121) may include a user screen activity data analysis module (121-1), a user profile update determination module (121-2), and a user profile creation and loading module (121-3).

[0134] The screen activity data analysis module (121-1) can analyze screen activity data (11). Here, screen activity data (11) may refer to the history of a user's use of the electronic device (100) and may include information on viewed content, viewing period information, viewing time information, and information on applications used. However, it is not limited thereto. In the present disclosure, screen activity data (11) may also be referred to as the aforementioned 'viewing history'. The screen activity data analysis module (121-1) can categorize and classify the information included in the screen activity data (11) by viewer (user).

[0135] The user profile update determination module (121-2) can determine whether to update the user profile information based on analyzed screen activity data. The user profile update determination module (121-2) can determine whether to update the user profile information based on newly generated screen activity data as the user uses the electronic device (100). That is, if a viewing history with characteristics different from the viewing characteristics corresponding to the previously stored profile is recorded, it can determine whether to update the profile information to reflect the new viewing characteristics based on this viewing history.

[0136] For example, if profile information reflecting viewing characteristics that do not prefer game-related content is already stored, the user may watch game-related content, thereby generating a viewing history related to it. In this case, the user profile update judgment module (121-2) can determine whether the user's viewing tendency has changed or whether the user temporarily watched game-related content regardless of existing viewing characteristics. Specifically, the user profile update judgment module (121-2) can determine whether the user's viewing characteristics (tendency) have changed based on the period during which the user watched game-related content, the genre of content watched thereafter, etc. If the user profile update judgment module (121-2) determines that the user's viewing characteristics have changed, the user profile creation / load module (121-3) can update the user's profile information based on the newly generated viewing history (e.g., viewing history of game-related content).

[0137] The user profile creation / loading module (121-3) can create user profile information (12) through a generative artificial intelligence model or receive profile information (22) created from an external electronic device (200). Additionally, the user profile creation / loading module (121-3) can obtain newly created profile information (12) by updating the generated profile information (22) based on the user's screen activity data (11).

[0138] The user profile creation / loading module (121-3) can directly generate profile information (12) through an On Device method. At this time, the electronic device (100) can directly receive identification information (21) stored in an external electronic device (200) and generate profile information (12) based thereon. However, it is not limited thereto, and the electronic device (100) may also generate profile information (12) based on identification information stored in the electronic device (100) (e.g., user account, gender, location, etc. of the electronic device (100)).

[0139] Meanwhile, the electronic device (100) can share the profile information (12) generated through the On Device method as described above with an external electronic device (200). That is, the electronic device (100) can provide the generated profile information (12) to the external electronic device (200). Accordingly, the external electronic device (200) can obtain recommended content suitable for the user of the external electronic device (200) by using the provided profile information (12).

[0140] Additionally, the user profile creation / loading module (121-3) can obtain profile information (22) via an On Mobile method. At this time, the external electronic device (200) can generate profile information (22) based on identification information (21) stored in the external electronic device (200). Here, the profile information (22) may correspond to information generated using a generative AI model stored in the external electronic device (200). The electronic device (100) can receive the profile information (22) generated by the external electronic device (200).

[0141] In this case, the user profile creation / load module (121-3) can update the received profile information (22) with new profile information (12). FIG. 4 illustrates an example where the new profile information (12) and the generated profile information (22) are different information, but it is not necessarily limited to this, and the user profile creation / load module (121-3) may receive profile information (22) generated by an external electronic device (200) and provide it directly to the curation unit (122) without the update process.

[0142] For example, the user profile generation / loading module (121-3) can generate profile information using a neural network model trained to generate profile information based on screen activity data (11) of the electronic device (100). Specifically, profile information (12) can be generated based on user identification information (21) and screen activity data (11). That is, profile information (12) can be generated based not only on the user's viewing characteristics predicted solely by the identification information (21), but also on screen activity data (11) that is newly updated in real time according to the user's viewing activity.

[0143] Through this, the electronic device (100) can generate profile information that reflects the user's viewing characteristics in accordance with the current viewing situation. That is, compared to using only fixed data such as the user's identification information (21) (e.g., account information, gender, location, etc.), the user's viewing characteristics can be determined more accurately and efficiently, and this can be used for content recommendation.

[0144] Meanwhile, the profile information (22) generated by the external electronic device (200) can also be generated by a model similar to the neural network model described above. That is, the external electronic device (200) can generate profile information that reflects the user's viewing characteristics through a neural network model by utilizing the user's identification information (21) and the viewing history of the electronic device (100) or the external electronic device (200). For example, if the external electronic device (200) utilizes the viewing history of the external electronic device (200), it can utilize information on content viewed through the external electronic device (200), viewing time, and preferred application information.

[0145] The curation unit (122) can obtain recommended content using generated (acquired) profile information and arrange it in an appropriate layout. Here, curation may refer to the process of selecting and organizing content suitable for a specific topic or interest and providing it to the user. Here, selecting content may mean recommending content suitable for the user's interests and specific topics.

[0146] That is, the curation unit (122) can not only recommend content to the user using the generated profile information, but also arrange the recommended content in a way that the user might prefer.

[0147] Accordingly, users can go beyond simply consuming recommended content and receive various other recommended content by consuming similar content displayed alongside the recommended content or by searching for related content.

[0148] The profile-based curation context determination AI module (122-1) can determine the context corresponding to the current viewing situation. At this time, the profile-based curation context determination AI module (122-1) may include a model trained to acquire context information regarding the current viewing situation based on profile information (12). Here, the context may be categorized into multiple context types distinguished according to various viewing situations. Here, a viewing situation may refer to various situations surrounding the electronic device (100) and the user at the time when the electronic device (100) provides a content recommendation function to the user.

[0149] According to one or more embodiments, a plurality of context types may include at least one of a first context type corresponding to a situation in which the electronic device is first used after being turned on from a turned-off state, a second context type corresponding to a situation in which the electronic device is in use after being turned on, and a third context type corresponding to a situation in which the previously selected recommended content is played again after one of at least one previously acquired recommended content is selected.

[0150] For example, an electronic device (100) may store multiple context types in advance. Subsequently, when the electronic device (100) provides a content recommendation function, it may use information about the previously stored context types to identify the user's viewing situation as one of the multiple context types.

[0151] For example, a user may turn off the electronic device (100) after viewing content through the electronic device (100) and ending the viewing. When the electronic device (100) is turned on again, the viewing situation may correspond to a first context type. Subsequently, when the user uses the electronic device (100) in a normal mode, such as by searching for or viewing recommended content through the electronic device (100), the viewing situation may correspond to a second context type. Meanwhile, if the user has a history of viewing other content after viewing content recommended by the electronic device (100), there may be a situation where the user is currently watching previously recommended content. In this case, the current viewing situation may correspond to a third context type.

[0152] Although multiple context types corresponding to a user's viewing situation have been described using the first to third context types mentioned above as examples, they are not limited thereto, and various other context types corresponding to different viewing situations may exist.

[0153] Subsequently, the context-appropriate content configuration module (122-2) can obtain recommended content based on at least one of screen activity data (11) and profile information (12) and configure it. Here, the content configuration module (122-2) may include a neural network model trained to recommend content suitable for the current viewing situation based on the determined context type.

[0154] According to one or more embodiments, if the content configuration module (122-2) identifies the current viewing situation as a first context type, it can obtain at least one recommended content through at least one neural network model based on screen activity data (11) which includes at least one of content information played before the electronic device was turned off, application activity information, and the usage time of the electronic device. For example, if the electronic device (100) is turned off while a user is watching content of a specific topic, and the electronic device (100) is turned on again thereafter, the content configuration module (122-2) can recommend content for that topic.

[0155] According to one or more embodiments, when the content configuration module (122-2) identifies the current viewing situation as a second context type, it can obtain at least one recommended content through a neural network model based on history information including at least one of a plurality of content-specific viewing times and search records previously displayed through a display.

[0156] For example, when a user inputs an operation to activate the content recommendation mode (e.g., user voice through a microphone, remote control input, etc.) or when recommended content is currently playing, the electronic device (100) can be used in general, and the viewing time and search history of previously played content can be analyzed to obtain content that the user is likely to prefer through a neural network model. For instance, if a user is watching a drama starring a specific actor, and there is a record in the screen activity data (11) that the user frequently watched a specific channel, the content configuration module (122-2) can obtain content featuring the said actor on that specific channel as recommended content, such as 'content to watch next'.

[0157] For example, in screen activity data (11), there may be a high proportion of records of a user subsequently watching a documentary related to the content of the movie after watching the movie. In this case, the content configuration module (122-2) can obtain a science documentary about the subject as recommended content if the viewer watched a SF movie, and can obtain a history documentary as recommended content if the viewer watched a movie about history.

[0158] According to one or more embodiments, if the current viewing situation is identified as a third context type, at least one recommended content can be obtained through a neural network model based on history information including at least one content information selected after previously selected recommended content and at least one of the types of applications executed.

[0159] For example, if a user receives recommendations for multiple contents through an electronic device (100) and selects and watches one of them, Content A, then multiple additional contents corresponding to the watched content may be recommended. In this case, if the user selects and watches Content B, which is one of the multiple additional recommended contents, such a series of viewing history may be stored in the screen activity data. Subsequently, if the user watches Content A again, the content configuration module (122-2) may recommend Content B. However, this is not limited thereto, and even if the user watches content similar to Content A, that is, content where the genre, production year, producer, and cast members, etc., of Content A match, or content with a plot similar to the plot of Content A, the content configuration module (122-2) may recommend Content B, or content similar to Content B, that is, content where the genre, production year, producer, and cast members, etc., of Content B match, or content with a plot similar to the plot of Content B.

[0160] In addition to obtaining at least one recommended content based on the context type as described above, the content configuration module (122-2) can configure the screen to suit each of the obtained at least one recommended content, such as user viewing characteristics. For example, if there are multiple recommended contents, the content that is more suitable for the user's viewing characteristics can be placed in the center of the screen or in a relatively large area. A detailed explanation regarding this will be provided later.

[0161] The context-appropriate content display module (122-3) can control the display to display a screen containing at least one recommended content obtained based on the context type as described above. If the content configuration module (122-2) configures the screen to suit each of the at least one recommended content obtained, such as user viewing characteristics, the display can be controlled to display the configured screen.

[0162] FIG. 5 is a drawing for illustrating multi-user profile information according to one or more embodiments of the present disclosure.

[0163] According to FIG. 5, the electronic device (100) can obtain multi-user profile information (13) based on screen activity data (11) and obtain at least one recommended content based on the multi-user profile (13).

[0164] According to one or more embodiments, if the electronic device (100) is identified as including a usage history corresponding to at least one other user other than the user in the history information, it can obtain multi-user profile information reflecting the viewing characteristics of each of the multiple users, including the user and at least one other user, through a neural network model.

[0165] Specifically, the user situation determination model can determine whether there are multiple users of the electronic device (100). For example, the user situation determination model can determine that there are multiple users if the viewing history of multiple users is stored in the screen activity data (11).

[0166] At this time, information regarding viewing history in the screen activity data (11) may be stored in a form distinguished by viewer. In this case, the electronic device (100) can identify whether information regarding multiple viewers is stored in the screen activity data (11). If information regarding multiple viewers is stored in the screen activity data (11), the electronic device (100) can identify that the viewing history information includes viewing history corresponding to users other than the user.

[0167] Here, information about the viewer can be obtained based on login information. For example, if there are multiple viewers, each user can start watching after entering their account information after the electronic device (100) is turned on. The electronic device (100) can store the viewing history of the viewer along with the entered account information.

[0168] Meanwhile, the electronic device (100) can identify whether there are multiple viewers based on screen activity data (11) even when viewer information is not stored.

[0169] For example, an electronic device (100) can extract multiple viewing patterns based on viewing time periods, channels, programs, genres, etc. included in screen activity data (11). The electronic device (100) can analyze each of the multiple patterns to identify whether the screen activity data (11) includes the viewing history of multiple viewers.

[0170] For example, if the electronic device (100) identifies, based on screen activity data (11), that there is a history of news and children's programs being watched alternately during a specific time period, it can estimate that there are viewers of different age groups. Additionally, if the electronic device (100) identifies, based on screen activity data (11), that content of various genres is frequently switched and watched within a short period of time, it can estimate the possibility that there are multiple viewers.

[0171] However, it is not limited to this, and if there are multiple external electronic devices that have a history of communicating with the electronic device (100), the electronic device (100) may identify that there are multiple viewers. For example, if the electronic device (100) has a history of sharing profile information, etc. with multiple external electronic devices (200), it may identify that there are multiple viewers.

[0172] When the electronic device (100) is identified as having one user, it can obtain at least one recommended content based on the generated profile information of the user as described above.

[0173] On the other hand, if the electronic device (100) is identified as having multiple users, it can obtain multiple user profile information (13) based on screen activity data (11) through the user profile creation and management unit (121). Here, the screen activity data (11) may include the viewing history of users other than the current user of the electronic device (100). The multiple profile information generated here may correspond to information reflecting the viewing characteristics of multiple users.

[0174] According to one or more embodiments, the electronic device (100) can obtain at least one recommended content based on multiple profile information (13) that reflects the viewing characteristics of multiple users.

[0175] Through this, the electronic device (100) can recommend content to the current user by reflecting the viewing trends of multiple users, even when there is a lack of information related to content recommendation, such as viewing characteristics of the current user.

[0176] According to one or more embodiments, the multiple profile information may include detailed information classified by multiple categories for each of the multiple viewers. The multiple categories may include at least one of recently viewed content, preferred applications, and preferred genres.

[0177] According to one or more embodiments, if at least one processor (120) identifies that there is at least one category with common detailed information among the categories included in each of the multiple profiles, it can obtain at least one recommended content based on at least one category. For example, if there are multiple users A, B, and C, the electronic device (100) can obtain multiple user profile information (13) based on each user's viewing history, etc. Here, the multiple profile information (13) may include detailed information regarding recently viewed content, preferred applications, and preferred genres for each user A, B, and C. If the preferred applications corresponding to each of A, B, and C match, the electronic device (100) can obtain recommended content based on the category regarding preferred applications among the multiple profile information (13). Even if one of A, B, or C is watching the electronic device (100), the electronic device (100) can display and recommend content that can be executed with the corresponding application.

[0178] Meanwhile, if there is no category with common detailed information in the multi-profile information (13), the electronic device (100) can obtain recommended content based on the latest trend information provided by a CP (Contents provider), etc. For example, if there is no detailed information common to each of users A, B, and C in the multi-profile information (13), the electronic device (100) can obtain recommended content through information on the latest trends preferred by A, B, C and many other people.

[0179] Accordingly, when the characteristics of multiple users match, the electronic device (100) obtains recommended content based on these characteristics, so it can recommend content by more accurately reflecting multiple viewing characteristics.

[0180] At this time, when content is recommended based on a multi-user profile, the electronic device (100) may not reflect the multi-user screen activity data (11) in the generated profile information (12). Accordingly, since the contamination of the individual user's profile information (12) can be minimized, the viewing characteristics of each user may not be affected by the multi-viewer profile information (13).

[0181] FIG. 6 is a drawing for explaining an image including recommended content according to one or more embodiments of the present disclosure.

[0182] According to FIG. 6, the electronic device (100) can display images (30-1, 30-2, 30-3, 30-4) associated with at least one acquired content.

[0183] According to one or more embodiments, the electronic device (100) can display an image (30-2, 30-3, 30-4) containing at least one acquired recommendation content.

[0184] Here, the video containing at least one recommended content (30-2, 30-3, 30-4) may correspond to a video that has been reconstructed by adjusting the arrangement of the acquired recommended content, etc. For example, a video that induces the user to consume (watch) the recommended content, or various content that the user is likely to prefer, may be reconstructed and displayed to suit the user's viewing characteristics.

[0185] For example, an electronic device (100) may display a screen including an identified context type (31), a preview of each of at least one recommended content corresponding to the context type (33-1, 33-2, 33-3, ..., 33-N), a preview of a selected content among at least one recommended content (33-1), and at least one video included in the selected content. Here, the preview of each of at least one recommended content (33-1, 33-2, 33-3, ..., 33-N) may be an image or video representing each recommended content, and may correspond to a trailer video, a representative screen, a poster, etc. of each content.

[0186] A video (30-2, 30-3, 30-4) containing at least one recommended content can be implemented in various forms including various types of information as described above. At this time, the electronic device (100) can display the video (30-2, 30-3, 30-4) containing the recommended content in various forms depending on various situations, such as when the electronic device (100) is turned on or when a user inputs an operation.

[0187] For example, the electronic device (100) can display an image (30-1) containing a context type (31) after the electronic device (100) is turned on.

[0188] The context type (31) identified here may include various information related to the current viewing situation in addition to one of the first to third context types described above.

[0189] For example, in the case of the first video (30-1) containing the context type (31), if the user falls asleep while watching the mobile new product unpack video on the electronic device (100) and then turns the electronic device (100) back on, the electronic device (100) can display text for the context type (31) such as "You fell asleep while watching the smartphone unpack video yesterday" through the display (130).

[0190] However, it is not limited to this, and the electronic device (100) can display a preview of each of the related recommended content (e.g., multiple videos related to the mobile product) in addition to the above context type (31).

[0191] Afterward, when a preset time elapses without user input after the first video (30-1) containing the context type (31) is displayed, the electronic device (100) can display a preview (33-1) of the selected content among at least one recommended content.

[0192] Here, the selected content may correspond to the recommended content most suitable for the user's viewing characteristics based on user profile information among multiple recommended contents. Alternatively, the selected content may correspond to content selected by user input for viewing content.

[0193] In other words, the selected content may correspond to content recommended as being most suitable for the user's viewing characteristics without any user input, or it may correspond to content selected based on user input to watch one of several pieces of content.

[0194]

[0195] For example, when a user sees a preview of multiple recommended contents on a screen (30-1) where a context type (31) is displayed, a preview (33-1) of one selected content among the multiple recommended contents may be displayed on the screen (30-2) with the largest proportion. At this time, the electronic device (100) may also display related information corresponding to the content (e.g., movie title, genre, production year, etc.).

[0196] Meanwhile, when a preview (33-1) of one content is displayed in an enlarged manner, the electronic device (100) may also display an enlarged screen in which the video is played. For example, after a preset time has elapsed without user input after the preview (33-1) of the selected content is displayed, or if there is user input to play the selected content, the screen in which the selected content is played may be displayed in an enlarged manner.

[0197] Meanwhile, when a preview (33-1) of selected content is displayed on the electronic device (100), if there is user input to zoom out the preview (33-1) or to search for recommended content other than the selected content, the electronic device (100) can display an overview screen (Over-view) (30-3) in which previews (33-1, 33-2, 33-3, ..., 33-N) of multiple recommended content are listed.

[0198] At this time, when multiple previews of recommended content (33-1, 33-2, 33-3, ..., 33-N) are displayed first, if there is user input to select a preview (33-4) of one of the content, the electronic device (100) can enlarge and display a preview (33-1) of the selected content. The screen (30-4) displayed at this time may include relevant information (e.g., movie title, genre, production year, etc.), just like the previously displayed screen (30-2).

[0199] Accordingly, the electronic device (100) can acquire multiple recommended contents and recommend one of them that a viewer is likely to prefer, and can also display other recommended contents based on user input, such as operation input, to explore other content. Through this, the electronic device (100) can provide the user with a harmonious viewing experience and a search experience.

[0200] FIG. 7 is a drawing for explaining an overview according to one or more embodiments of the present disclosure.

[0201] According to FIG. 7, previews of multiple recommended content may be displayed on overview screens (30-3a, 30-3b, 30-3c) in various ways. The 'brightness', 'size', and 'color' displayed on the left side of each overview screen (30-3a, 30-3b, 30-3c) may correspond to the way each overview screen (30-3a, 30-3b, 30-3c) is displayed.

[0202] According to one or more embodiments, the electronic device (100) displays a screen (overview screen) (30-3a, 30-3b, 30-3c) in which a plurality of contents are arranged in a plurality of lists with different recommendation criteria, and can display the remaining plurality of previews, excluding the preview of the selected content (33-1a, 33-1b, 33-1c) among each preview video, differently from at least one of the size, luminance (brightness), color, and clarity of the preview of the selected content (33-1a, 33-1b, 33-1c).

[0203] For example, when one of the multiple recommended contents is selected, the electronic device (100) may display the preview (33-1a, 33-1b, 33-1c) of the selected content with a higher luminance (brightness) or display it larger so that it is distinguished from the previews of the remaining recommended contents. Additionally, the electronic device (100) may apply one or more color filters to the remaining previews excluding the preview (33-1c) of the selected content so that the preview (33-1c) of the selected content is displayed with relative emphasis. Additionally, the electronic device (100) may lower the clarity of the remaining previews excluding the preview of the selected content. Accordingly, the electronic device (100) may make the preview of the selected content appear clearer than the surrounding previews.

[0204] FIG. 7 illustrates the operation in which the display method of multiple recommended content previews (33-1, 33-2, 33-3, ..., 33-N) changes in the order of brightness, size, and color, but this is merely an example, and the display method of the overview screens (30-3a, 30-3b, 30-3c) can be changed in various other orders.

[0205] FIG. 8 is a drawing for explaining an overview according to one or more embodiments of the present disclosure.

[0206] According to FIG. 8, an overview screen (30-3d, 30-3e, 30-3f) arranged for multiple lists (34-1a, 34-2a, 34-3a, 34-1b, 34-2b, 34-3b, 34-1c, 34-2c) with different recommendation criteria is shown. 'Vertical', 'Horizontal', and 'Spiral' on the left side of each overview screen (30-3d, 30-3e, 30-3f) may indicate the arrangement of multiple lists in each overview screen (30-3d, 30-3e, 30-3f).

[0207] According to one or more embodiments, the electronic device (100) may display a screen (30-3d, 30-3e, 30-3f) in which a plurality of contents are arranged in a plurality of lists with different recommendation criteria. Here, the plurality of recommendation criteria may include information used by the electronic device (100) to obtain each of the plurality of recommended contents.

[0208] For example, multiple recommendation criteria may include at least one of 'current curation', 'current curation-based CP content', and 'likes'. Recommended content based on 'current curation' may correspond to recommended content obtained based on the user profile information described above. Recommended content based on 'current curation-based CP content' may correspond to recommended content obtained based on user profile information related to the CP (e.g., a genre that the user is likely to prefer among the content genres provided by the CP). Recommended content based on 'likes' may include content similar to the content for which the user clicked the 'Like' UI. Multiple recommendation criteria are not limited to this and may include various information that the electronic device (100) can use to obtain recommended content.

[0209] Meanwhile, the electronic device (100) can display multiple contents by arranging multiple lists with different recommendation criteria in one of vertical, horizontal, or spiral ways. As shown in the first screen (30-3d) corresponding to the vertical way, the electronic device (100) can display vertically arranged lists (34-1a, 34-2a, 34-3a). As shown in the second screen (30-3e) corresponding to the horizontal way, the electronic device (100) can display horizontally arranged lists (34-1b, 34-2b, 34-3b). As shown in the third screen (30-3f) corresponding to the spiral way, the electronic device (100) can display lists (34-1c, 34-2c) through two circles of different sizes. The above-described list arrangement method (vertical, horizontal, and spiral method) is merely an example, and the list arrangement method (34-1a, 34-2a, 34-3a, 34-1b, 34-2b, 34-3b, 34-1c, 34-2c) may include various methods in which multiple recommended contents can be visually distinguished according to recommendation criteria.

[0210] Through this, multiple recommended contents can be visually distinguished according to recommendation criteria, and users can select a list based on their desired recommendation criteria and choose to watch one of the multiple recommended contents included in the selected list.

[0211] FIG. 8 illustrates the operation of changing the display method of multiple lists (34-1a, 34-2a, 34-3a, 34-1b, 34-2b, 34-3b, 34-1c, 34-2c) in a vertical, horizontal, and spiral order, but this is merely an example, and the arrangement method of the lists (34-1a, 34-2a, 34-3a, 34-1b, 34-2b, 34-3b, 34-1c, 34-2c) can be changed in various other orders.

[0212] FIG. 9 is a drawing for explaining a screen effect according to one or more embodiments of the present disclosure.

[0213] FIG. 9 illustrates a screen (30-4) in which content is played when at least one of the recommended contents is selected. The screen (30-4) in which content is played may be displayed as a full screen. Three boxes (35-1, 35-2, 35-3) in the lower left corner, which are displayed together with the screen (30-4) in which content is played, may indicate information about the effects applied to the current screen.

[0214] For example, when a soccer match content is selected among at least one recommended content and the electronic device (100) displays a soccer match screen, screen and sound effects corresponding to the soccer match content may be applied.

[0215] At this time, screen and sound effects can be obtained by a neural network model stored in the electronic device (100). Here, the neural network model may be a model trained to obtain effects to be applied to the current screen based on the attributes of recommended content or user profile information, etc. That is, the electronic device (100) can play content by applying the attributes of the content currently being played or screen effects that the user is likely to prefer through this neural network model.

[0216] For example, when soccer match content is played, 'Auto motion Plus' and 'Picturemode dynamic' effects can be applied as screen effects suitable for sports matches, and 'Soundmode Sports' effect can be applied as a sound effect suitable for sports matches.

[0217] Meanwhile, the electronic device (100) may apply and display a special effect on the screen for a short period of time so that the user can recognize the application of the effect when the above screen and sound effects are applied. For example, the electronic device (100) may apply and display a sparkling special effect on a part of the screen for a period of time to allow the user to recognize that an effect (screen and sound effect) is being applied to the current screen, without interfering with the user's current viewing.

[0218] Meanwhile, the electronic device (100) may display boxes (35-1, 35-2, 35-3) with text such as 'Auto motion Plus', 'Picturemode dynamic', and 'Soundmode Sports' to indicate that the above effect has been applied to the current screen.

[0219] Accordingly, the electronic device (100) can not only play selected content among multiple recommended contents, but also improve user satisfaction by applying effects suitable for the user's viewing characteristics or the attributes of the selected content.

[0220] FIG. 10a is a drawing for illustrating an interaction according to one or more embodiments of the present disclosure.

[0221] According to FIG. 10a, the electronic device (100) may display a preview (33-1) of selected content among multiple recommended content. A preview (33-4, 33-5) located above the preview (33-1) of selected content may correspond to a preview (33-4, 33-5) of previously selected or viewed content among multiple recommended content. A preview (33-2, 33-3) located below the preview (33-1) of selected content may correspond to newly acquired recommended content among multiple recommended content that corresponds to the current context type.

[0222] At this time, the electronic device (100) can perform interaction with external electronic devices, etc. Here, interaction may refer to the process of a user interacting with a digital system such as a computer, software, a website, a mobile app, etc. Here, interaction may include the process of receiving user input from various interfaces (mouse, keyboard, microphone, motion sensor, etc.) and the process of outputting various content such as text, images, and videos corresponding to the user input.

[0223] The electronic device (100) can change the selected content among multiple recommended contents or activate an AI solution function related to the selected content through the above interaction while the preview (33-1) of the selected content is displayed.

[0224] For example, if the electronic device (100) can perform interaction through inputs corresponding to the top, bottom, left, and right, when the electronic device (100) receives an input corresponding to the 'top', one of the contents previously viewed by the user may be selected. When the electronic device (100) receives an input corresponding to the 'bottom', one of the subsequent contents recommended to be suitable for the current context may be selected. When the electronic device (100) receives an input corresponding to the 'right', content related to the current content (e.g., in the case of movie content, additional trailers, movie reviews, ratings, etc.) may be generated and displayed together. When the electronic device (100) receives an input corresponding to the 'left', an AI solution function related to the selected content may be activated.

[0225] Here, the AI ​​solution function may refer to a function in which an electronic device (100) receives a question or search term (prompt) from a user in a conversational format in relation to selected content and provides a corresponding answer. For example, when the AI ​​solution function is activated by user input, the user may enter a search term related to the selected content, and the electronic device (100) may generate and provide an answer corresponding to the search term through a generative artificial intelligence model.

[0226] Meanwhile, the electronic device (100) can receive up, down, left, and right inputs via a remote control, and can also receive them via other external electronic devices (100) capable of communicating with the electronic device (100). For example, a user can perform operations corresponding to up, down, left, and right by linking the electronic device (100) with a smartphone. Here, operations corresponding to up, down, left, and right can be input by touching the screen of the smartphone.

[0227] Meanwhile, the electronic device (100) can perform interactions based on the user's speech in addition to interactions based on directions such as up, down, left, and right. For example, the electronic device (100) can receive the user's spoken voice through a microphone provided in the electronic device (100), and based on the input voice, it can select other recommended content, activate an AI solution function, or provide content related to the selected content.

[0228] FIG. 10b is a drawing for illustrating an interaction according to one or more embodiments of the present disclosure.

[0229] According to FIG. 10b, the electronic device (100) may display a screen (30-2) containing a preview (33-1) of selected content, and the previews (33-2, 33-3) at the bottom of the preview (33-1) of selected content may correspond to previews (33-2, 33-3) of recommended content other than selected content. In this case, the screen (30-2) containing the preview (33-1) of selected content may include only a portion of the preview (33-2) of the first recommended content and may not include the preview (33-3) of the second recommended content.

[0230] The electronic device (100) can update at least one next recommended content. Specifically, the electronic device (100) can obtain at least one recommended content through a neural network model based on user profile information and existing viewing history. Subsequently, the electronic device (100) can determine content interest through a neural network model based on user interaction data. Here, content interest can be obtained by analyzing user interactions such as preview viewing time, content entry, and skip behavior. Based on content interest, the electronic device (100) can obtain at least one new recommended content in real time or adjust the order of recommended content.

[0231] For example, the electronic device (100) can obtain multiple recommended content based on user profile information and existing viewing history. Subsequently, new recommended content can be obtained through a neural network model based on the time spent watching a preview (33-1) of the currently selected content.

[0232] For example, if the viewing time of the preview (33-1) is shorter than that of other recommended content, new recommended content that is less relevant to the content corresponding to the preview (33-1) can be obtained. However, this is not limited to this, and if the user has watched the preview (33-1) of the currently selected content for a relatively long time or has entered search terms related to the content, or shows a high level of interest in the selected content, new recommended content that is more relevant to the currently selected content can be obtained.

[0233] Afterwards, the electronic device (100) can display a preview (33-6, 33-7) corresponding to the new recommended content according to user input for selecting the new recommended content.

[0234] Accordingly, the electronic device (100) does not recommend content based solely on the fixed viewing characteristics of the user, but can update recommended content based on the viewing history or context that is updated in real time as the user uses the electronic device (100), thereby allowing for more appropriate recommendation of content that is suitable for the user's viewing characteristics or current situation.

[0235] FIG. 11 is a drawing for explaining search terms according to one or more embodiments of the present disclosure.

[0236] FIG. 11 is a flowchart illustrating the operation in which an electronic device (100) generates a new search term through a neural network model according to a search term entered by a user to obtain recommended content and related content.

[0237] For example, an electronic device (100) can receive a search term (user input) from a user through an interface (microphone, remote control, keyboard, etc.) of the electronic device (100) (S1110). For example, the user can speak a voice saying "What would be good to do in Bali?" and the voice input received through the microphone can be converted into data in the form of text.

[0238] Next, the electronic device (100) can determine whether there is a connection with currently displayed content based on the search term converted into text through a neural network model (S1120). The electronic device (100) can analyze the search term through a Natural Language Processing (NLP) process. Here, the Natural Language Processing process may correspond to a technology that enables a computer to understand and process human language, and may be implemented through a Large Language Model (LLM). The aforementioned neural network model may include a Large Language Model and may be implemented as the aforementioned generative artificial intelligence model. The electronic device (100) can determine whether there is a connection between the search term converted into text and currently displayed content (e.g., selected recommended content) based on the Large Language Model. For example, the electronic device (100) can determine whether there is a connection between the search term and currently displayed content by determining whether the keywords extracted from the currently displayed content and the keywords of the search term have similar meanings.

[0239] Next, if it is determined that the search term is associated with the currently displayed content, the electronic device (100) can generate the search term through a neural network model (S1130). Here, the neural network model can be implemented as a generative artificial intelligence model implemented as a large-scale language model, similar to the previous operation. The same applies below. The electronic device (100) can generate the search term based on at least one of screen data (i.e., screen activity data such as usage history), the current context, and user profile information. For example, if the user has frequently watched content related to children, has a history of frequently searching for places good to go with children, or has a history of frequently watching travel-related content during specific viewing times, the electronic device (100) can generate a new search term, such as "travel with children in Bali," based on the search term "what to do in Bali" entered via the user's voice. That is, the electronic device (100) can regenerate the search term to suit the viewing characteristics of a user with children and the viewing characteristics of primarily searching for travel-related content during the current time. In other words, the electronic device (100) can change the search term entered by the user to suit the user's characteristics in order to obtain content that is more suitable for the user.

[0240] Next, the electronic device (100) can obtain search results based on the regenerated search term and provide related content (S1140). For example, after the electronic device (100) regenerates the search term 'travel with a child in Bali', it can provide blog reviews of travel with a child in Bali, travel review videos, content, and information on family travel package products related to Bali as recommended content.

[0241] Meanwhile, if the electronic device (100) determines that the entered search term is not associated with the currently displayed content, it can maintain the currently displayed content and generate content related to the search term through a neural network model (S1150). For example, if a user enters the search term "what to do in Bali" while a preview of a sci-fi movie is displayed, the electronic device (100) can maintain the currently displayed movie preview and provide general search results corresponding to the search term (e.g., Bali local tour information) through text.

[0242] Meanwhile, even if the electronic device (100) determines that the search term entered by the user is linked to the currently displayed content, it can generate content related to the content provided as recommended content through a neural network model (S1160). For example, if a 'video review of traveling with children in Bali' is provided as a search result, information such as accommodation and flight tickets included in the video content can be provided as text. Here, the electronic device (100) can extract text from the review video through speech-to-text conversion, and generate related content to be provided to the user by extracting keywords from the extracted text.

[0243] FIG. 12 is a drawing for explaining search terms according to one or more embodiments of the present disclosure.

[0244] According to Fig. 12, when a user inputs the search term "what to do in Bali" via voice while watching content, a screen is displayed that provides a preview (33) of recommended content related to this and related information (32).

[0245] For example, the electronic device (100) can provide content such as a review video of a trip to Bali with children as a preview (33) of related content based on a new search term such as 'travel to Bali with children'. The electronic device (100) can also display hotel information included in the review video and provide text guiding this as related information (32). However, the above example is merely an example, and the electronic device (100) can not only provide recommended content in the form of a preview (33) but also play the recommended content from the beginning. Additionally, the electronic device (100) can output the related information (32) as voice through a speaker built into the electronic device (100) or as voice through an external speaker (e.g., a smart speaker) connected to the electronic device (100).

[0246] Accordingly, when a user enters a related search term while watching recommended content, the electronic device (100) can generate a search term that is more suitable to the current viewing situation or the user's viewing characteristics and search, so the electronic device (100) can integrate the viewing experience and the search experience of the content by providing content and related information that is more suitable to the viewing situation and personal characteristics.

[0247] FIG. 13a is a drawing for explaining content-related information according to one or more embodiments of the present disclosure.

[0248] According to FIG. 13a, a table (1) showing the types of generative information by content type and examples thereof is shown.

[0249] The multiple content types described in Table (1) may include informational content, story content, and real-time content depending on the content content (plot), etc. However, they are not limited thereto, and the multiple content types may also include various other content types classified according to the content content, etc.

[0250] As described above in FIGS. 11 and 12, etc., the generative information type may refer to related information generated in relation to recommended content (or content selected from a plurality of recommended content; hereinafter the same applies in FIGS. 13a to 13d). Here, 'generative information' may refer to related information generated by such a generative artificial intelligence model.

[0251] According to Table (1), for informational content such as documentaries, informational summaries may be provided as related information, for story content (with a production company) such as movies and dramas, critic / public rating information may be provided as related information, and for live broadcasts or real-time sports content provided on channels / applications, viewing reservation functions and timetables may be provided as related information.

[0252] Below, we will explain in detail the generative information provided according to each content type.

[0253] FIG. 13b is a drawing for explaining content-related information according to one or more embodiments of the present disclosure.

[0254] If the selected content corresponds to an informational content type such as a documentary, text summarizing the content of such content may be provided as generative information.

[0255] However, as shown in FIG. 13b, even when sports matches other than documentaries are provided as recommended content, information summaries may be provided according to the user's search terms or other request information. For example, if a video related to a golf tournament is provided as recommended content, and the user searches for a method to "increase driving distance," the electronic device (100) may provide "information on increasing driving distance" as text as related information (32) based on information extracted from the video. At this time, the electronic device (100) may provide the recommended content in the form of a preview (33) and display the related information (32) in the form of a speech bubble.

[0256] FIG. 13c is a drawing for explaining content-related information according to one or more embodiments of the present disclosure.

[0257] According to FIG. 13c, if the recommended content corresponds to a story content type such as movie content, rating information, etc., may be displayed together as related information. For example, the electronic device (100) may display a preview (33) of the movie that is the recommended content, and the movie's rating and plot may be displayed as related information (32).

[0258] FIG. 13d is a drawing for explaining content-related information according to one or more embodiments of the present disclosure.

[0259] According to Fig. 13d, if the recommended content is sports news, the type of recommended content may correspond to 'live content'. That is, not only is the recommended content provided in real time (live sports broadcast video), but content related to content provided in real time, such as news about past sports matches, may also correspond to the type of live content.

[0260] For example, the electronic device (100) can display a preview (33) of sports news about a past soccer match and can provide a function to schedule viewing of the soccer match related to the content of the news. The electronic device (100) can provide information regarding this function as related information (32). When the electronic device (100) provides news about the past match of the national soccer team as recommended content, it can provide information (32-1) about a future soccer match, such as, "There is a national team match this week! Tell me if you want to schedule it." At this time, the electronic device (100) can provide text such as "South Korea vs. Japan" along with a calendar display. Next, if there is user input to schedule viewing of the next soccer match, the electronic device (100) can provide a UI containing information about the date the soccer match was scheduled as related information (32-2).

[0261] Accordingly, the electronic device (100) can generate and provide relevant information to the user in real time based on the type of content or recommended content that the user is watching. Therefore, the user can search for relevant information and search for other similar content to watch later using only the electronic device (100) without needing to use a separate mobile device, etc., so that the user can continuously experience the functions of watching and searching for content.

[0262] FIG. 14 is a flowchart illustrating a method for controlling an electronic device capable of communicating with a plurality of display devices according to one or more embodiments of the present disclosure.

[0263] The electronic device (100) can obtain profile information that reflects the viewing characteristics of the user of the display device based on historical information (S1410).

[0264] According to one or more embodiments, the electronic device (100) can obtain profile information corresponding to a user through at least one neural network model based on user identification information received from an external electronic device.

[0265] According to one or more embodiments, the electronic device (100) can receive and obtain profile information generated by an external electronic device based on user identification information from an external electronic device.

[0266] Next, one context type corresponding to the current viewing situation among multiple context types distinguished according to the user's viewing situation can be identified (S1420).

[0267] According to one or more embodiments, a plurality of context types may include at least one of a first context type corresponding to a situation in which the electronic device is first used after being turned on from a turned-off state, a second context type corresponding to a situation in which the electronic device is in use after being turned on, and a third context type corresponding to a situation in which the previously selected recommended content is played again after one of at least one previously acquired recommended content is selected.

[0268] Next, the electronic device (100) can obtain at least one recommendation content corresponding to at least one context type identified through at least one neural network model based on at least one of the acquired profile information and history information (S1430).

[0269] According to one or more embodiments, if the electronic device (100) identifies the current viewing situation as a first context type, it can obtain at least one recommended content through at least one neural network model based on history information including at least one of content information played before the electronic device was turned off, application activity information, and usage time of the electronic device.

[0270] According to one or more embodiments, if the electronic device (100) identifies the current viewing situation as a second context type, it can obtain at least one recommended content through a neural network model based on history information including at least one of a plurality of content-specific viewing times and search records previously displayed through a display.

[0271] According to one or more embodiments, if the electronic device (100) identifies the current viewing situation as a third context type, it can obtain at least one recommended content through a neural network model based on history information including at least one content information selected after previously selected recommended content and at least one of the types of applications executed.

[0272] Through this, the electronic device (100) can continuously update profile information reflecting the user's viewing characteristics using newly generated viewing history, and by obtaining recommended content based on the user's viewing characteristics and the user's current viewing situation, it can provide content that is more suitable to the user's characteristics or intentions. Accordingly, the electronic device (100) can provide the user with a content navigation experience that allows for continuous experience of content viewing and searching.

[0273] Meanwhile, in FIG. 14, the order of all steps has been mapped for convenience of explanation, but it goes without saying that the order of steps that are not related to the order or can be performed in parallel is not necessarily limited to that order.

[0274] Meanwhile, methods according to at least some of the various embodiments of the present disclosure described above can be implemented in the form of an application that can be installed on an existing electronic device.

[0275] In addition, methods according to at least some of the various embodiments of the present disclosure described above may be implemented by software upgrades or hardware upgrades alone for existing electronic devices.

[0276] In addition, methods according to at least some of the various embodiments of the present disclosure described above may also be performed through an embedded server equipped in an electronic device, or through at least one external server among the electronic devices.

[0277] Meanwhile, according to one embodiment of the present disclosure, the various embodiments described above may be implemented as software containing instructions stored on a machine-readable storage medium (e.g., a computer). The machine may include an electronic device (e.g., electronic device (A)) according to the disclosed embodiments, which is a device capable of calling instructions stored from the storage medium and operating according to the called instructions. When instructions are executed by a processor, the processor may perform a function corresponding to the instructions directly or by using other components under the control of the processor. Instructions may include code generated or executed by a compiler or an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, "non-transitory storage medium" simply means that it is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium. For example, A 'non-transient storage medium' may include a buffer in which data is temporarily stored. 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 (e.g., Play Store™) or directly between two user devices (e.g., smartphones).In the case of online distribution, at least a portion of a computer program product (e.g., a 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.

[0278] Various embodiments of the present disclosure may be implemented as software comprising instructions stored on a machine-readable storage medium (e.g., a computer). The machine may include an electronic device (e.g., an electronic device (100-1)) according to the disclosed embodiments, which is a device capable of calling instructions stored from the storage medium and operating according to the called instructions.

[0279] When the above-described instruction is executed by a processor, the processor may perform the function corresponding to the instruction directly or by using other components under the control of the processor. The instruction may include code generated or executed by a compiler or an interpreter.

[0280] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure.

Claims

1. In an electronic device, Memory for storing at least one neural network model; and It includes at least one processor connected to the memory and controlling the electronic device; and The above at least one neural network model includes a model trained to acquire at least one recommended content based on the viewing characteristics of the user of the electronic device, and The above at least one processor executes at least one instruction stored in the memory, Based on historical information, profile information reflecting the viewing characteristics of the user of the electronic device is obtained, and Identifying one context type corresponding to the current viewing situation among a plurality of context types distinguished according to the viewing situation of the user of the above electronic device, and An electronic device that obtains at least one recommendation content corresponding to at least one identified context type through at least one neural network model based on at least one of the above-mentioned acquired profile information and above-mentioned history information.

2. In Paragraph 1, A communication device for performing communication with an external electronic device; further comprising, The above at least one neural network model It includes a model trained to generate the profile information based on the history information of the electronic device, and The above-mentioned at least one processor is, An electronic device that obtains profile information corresponding to the user through at least one neural network model based on the identification information of the user received from the external electronic device.

3. In Paragraph 1, A communication device for performing communication with an external electronic device; further comprising, The above-mentioned at least one processor is, An electronic device that receives and obtains profile information generated by the external electronic device based on the user's identification information from the external electronic device.

4. In Paragraph 2, The above-mentioned at least one processor is, If it is identified that the above history information includes usage history corresponding to at least one other user other than the user, multi-user profile information reflecting the viewing characteristics of each of the plurality of users, including the user and the at least one other user, is obtained through the neural network model. An electronic device that obtains at least one recommended content based on the above multi-profile information.

5. In Paragraph 4, The above multi-profile information includes detailed information classified by multiple categories for each of the multiple viewers, and The above-mentioned at least one processor is, An electronic device that obtains at least one recommended content based on at least one category when it is identified that there is at least one category with common details among the categories included in each of the multiple profiles.

6. In Paragraph 1, The above plurality of context types are, It includes at least one of a first context type corresponding to a situation in which the electronic device is used for the first time after being turned on from a turned-off state, a second context type corresponding to a situation in which the electronic device is in use after being turned on, and a third context type corresponding to a situation in which the previously selected recommended content is played again after one of at least one previously acquired recommended content is selected. The above-mentioned at least one processor is, An electronic device that obtains at least one recommendation content corresponding to at least one identified context type through at least one neural network model based on at least one of the above-mentioned acquired profile information and above-mentioned history information.

7. In Paragraph 6, The above-mentioned at least one processor is, When the current viewing situation is identified as the first context type, the at least one recommended content is obtained through the at least one neural network model based on the history information including at least one of content information played before the electronic device was turned off, application activity information, and the usage time of the electronic device. When the current viewing situation is identified as the second context type, the at least one recommended content is obtained through the neural network model based on the history information including at least one of a plurality of content-specific viewing times and search records, and An electronic device that, when the current viewing situation is identified as a third context type, obtains at least one recommended content through the neural network model based on the history information including at least one content information selected after the previously selected recommended content and at least one of the executed application type.

8. In Paragraph 1, Including a display; further The above-mentioned at least one processor is, An electronic device that controls the display to display a screen including at least one recommended content obtained above.

9. In Paragraph 8, The above-mentioned at least one processor is, An electronic device for controlling a display to display a screen comprising at least one of the identified context type, a preview of each of the at least one recommended content corresponding to the context type, a preview of a selected content among the at least one recommended content, and a video included in the selected content.

10. In Paragraph 9, The above-mentioned at least one processor is, The display is controlled to display a screen in which the above-mentioned plurality of contents are arranged according to a plurality of lists with different recommendation criteria, and An electronic device that controls a display to display a plurality of previews, excluding the preview of the selected content among each of the above preview images, differently from at least one of the size, brightness, color, and clarity of the preview of the selected content.

11. In a method for controlling an electronic device, A step of obtaining profile information that reflects the viewing characteristics of the user of the electronic device based on historical information; A step of identifying one context type corresponding to the current viewing situation among a plurality of context types distinguished according to the viewing situation of the user; and Based on at least one of the above-mentioned acquired profile information and the above-mentioned history information, the method includes the step of acquiring at least one recommended content corresponding to at least one identified context type through at least one neural network model. A control method comprising at least one neural network model trained to acquire at least one recommended content based on the viewing characteristics of a user of the electronic device.

12. In Paragraph 11, The above-mentioned at least one neural network model is, It includes a model trained to generate the profile information based on the history information of the electronic device, and The step of obtaining the above profile information is, A control method comprising the step of obtaining profile information corresponding to the user through at least one neural network model based on the identification information of the user received from an external electronic device.

13. In Paragraph 11, The step of obtaining the above profile information is, A control method comprising the step of receiving and obtaining profile information generated by an external electronic device based on the user's identification information from the external electronic device.

14. In Paragraph 12, The step of obtaining the above profile information is, If it is identified that the history information includes a usage history corresponding to at least one other user other than the user, the method comprises the step of obtaining multi-user profile information reflecting the viewing characteristics of each of a plurality of users, including the user and the at least one other user, through the neural network model. The step of obtaining at least one recommended content above is, If it is identified that the above history information includes usage history corresponding to at least one other user other than the above user, A control method comprising the step of obtaining at least one recommended content based on the above multiple profile information.

15. A non-transient computer-readable recording medium storing computer instructions that cause said electronic device to perform an operation when executed by a processor of said electronic device, wherein said operation is, A step of obtaining profile information that reflects the viewing characteristics of the user of the electronic device based on historical information; A step of identifying one context type corresponding to the current viewing situation among a plurality of context types distinguished according to the user's viewing situation; and Based on at least one of the above-mentioned acquired profile information and the above-mentioned history information, the method includes the step of acquiring at least one recommended content corresponding to at least one identified context type through at least one neural network model. A non-transient computer-readable recording medium comprising at least one neural network model trained to acquire at least one recommended content based on the viewing characteristics of a user of the electronic device.

Images