Electronic device and method by which electronic device prevents spoiler of content by using artificial intelligence model

The electronic device uses AI to identify and obscure unwatched content data items by summarizing and vector embedding, addressing the issue of spoilers and maintaining user engagement.

WO2026240487A1PCT designated stage Publication Date: 2026-11-19SAMSUNG ELECTRONICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2026/095789
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-12
Filing Date
2026-04-10
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Electronic devices unintentionally provide spoilers about unwatched content when rendering data, leading to user disinterest.

Method used

An electronic device uses an artificial intelligence model to identify unwatched content and obscures it by summarizing and vector embedding data items, comparing vector values with an external server to determine if the content is unwatched, and then obscuring it if necessary.

Benefits of technology

Effectively prevents spoilers by identifying and obscuring unwatched content, enhancing user engagement by maintaining interest in upcoming content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2026095789_19112026_PF_FP_ABST
    Figure KR2026095789_19112026_PF_FP_ABST
Patent Text Reader

Abstract

An electronic device according to an embodiment may comprise a display, a communication circuit, a memory storing instructions, and at least one processor. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to: identify rendering data to be displayed through the display; perform, by using an encoder, summarization and vector embedding on each of at least one content data item included in the rendering data; obtain at least one vector value for each of the at least one content data item on the basis of the performing of the summarization and the vector embedding; transmit the at least one vector value to an external server that stores a plurality of content identifiers and a plurality of vector values respectively corresponding to the plurality of content identifiers; on the basis of comparisons, performed by the external server, between the plurality of vector values and the at least one vector value, receive, from the external server, a first content identifier corresponding to a first vector value among the at least one vector value; if there is no viewing history related to a user of the electronic device associated with the first content identifier corresponding to the first vector value, perform processing for hiding first content data item corresponding to the first vector value in the rendering data; and display, through the display, the rendering data in which the first content item is hidden. In addition, various other embodiments may be possible.
Need to check novelty before this filing date? Find Prior Art

Description

Method to prevent spoilers about content using artificial intelligence models in electronic devices and electronic devices

[0001] The present disclosure relates to an electronic device according to one embodiment and a method for preventing spoilers about content using an artificial intelligence model in the electronic device.

[0002] Driven by remarkable advancements in information and communication technology and semiconductor technology, the dissemination and use of various electronic devices are increasing rapidly. Electronic devices are being developed to enable users to carry them around and communicate. The term "electronic device" can refer to a device that performs specific functions according to an installed program, such as mobile communication terminals, tablet PCs, video / audio devices, desktop / laptop computers, or in-vehicle navigation systems. Electronic devices can render various data stored within the device or received from external sources and display the rendered data through a display. Rendered data can refer to data at a stage prior to displaying the stored or received data on the display. For example, an electronic device can render a web page received through a web browser application and display the rendered data on the display, or render search results obtained through a search application and display the rendered data on the display.

[0003] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0004] When rendering data, such as web pages or search results, is displayed on an electronic device, such data may contain information about content that the user has not watched. If rendering data containing information about unwatched content is displayed as is, spoilers about the content may be unintentionally provided to the user. For example, if a web page containing an article about the plot of a newly started drama is displayed to a user who has not yet watched the show, the user may receive unwanted spoilers and lose interest in watching the drama.

[0005] An electronic device according to one embodiment can identify whether information regarding content that the user has not viewed is included among various content data items (e.g., text, images, and / or videos) included in rendering data (e.g., web page data, search result data, or other data that can be displayed on a display), and can prevent information regarding content that the user has not viewed from being provided. An electronic device according to one embodiment can identify a specific content data item among the various content items included in the rendering data that contains information regarding content that the user has not viewed, and perform a process to obscure the specific content data item when displayed, thereby preventing spoilers regarding information regarding content that the user has not viewed in the rendering data.

[0006] An electronic device according to one embodiment of the present disclosure may include a communication circuit, a display, a memory for storing commands, and at least one processor. The commands according to one embodiment may, when executed individually or collectively by the at least one processor, cause the electronic device to identify rendering data to be displayed through the display. The commands may, when executed individually or collectively by the at least one processor, cause the electronic device to perform summarization and vector embedding for each of at least one content data item included in the rendering data through an encoder. The commands may, when executed individually or collectively by the at least one processor, cause the electronic device to obtain at least one vector value for each of at least one content data item based on the summarization and vector embedding. The commands may, when executed individually or collectively by the at least one processor, cause the electronic device to transmit the at least one vector value to an external server that stores a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers. When the above commands are executed individually or collectively by the at least one processor, the electronic device may receive a first content identifier corresponding to a first vector value among the at least one vector value from the external server based on a comparison of the plurality of vector values ​​and the at least one vector value by the external server.When the above commands are executed individually or collectively by the at least one processor, the electronic device may perform a process to obscure the first content data item corresponding to the first vector value in the rendering data if there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value. When the above commands are executed individually or collectively by the at least one processor, the electronic device may display the rendering data with the first content item obscured through the display.

[0007] A method for preventing spoilers regarding content using an artificial intelligence model in an electronic device according to one embodiment of the present disclosure may include an operation of identifying rendering data to be displayed through a display of the electronic device. The method may include an operation of performing a summary and vector embedding for each of at least one content data item included in the rendering data through an encoder of the electronic device. The method may include an operation of obtaining at least one vector value for each of at least one content data item based on the performance of the summary and vector embedding. The method may include an operation of transmitting the at least one vector value to an external server that stores a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers. The method may include an operation of receiving a first content identifier corresponding to a first vector value among the at least one vector values ​​from the external server through a communication circuit of the electronic device based on a comparison of the plurality of vector values ​​and the at least one vector value by the external server. The above method may include an operation to perform processing to obscure a first content data item corresponding to the first vector value in the rendering data if there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value. The above method may include an operation to display the rendering data with the first content item obscured through the display.

[0008] A server according to one embodiment of the present disclosure may include a communication circuit, a content database, a memory for storing commands, and at least one processor. According to one embodiment, when the commands are executed individually or collectively by the at least one processor, the server may obtain first content data corresponding to a first content identifier. When the commands are executed individually or collectively by the at least one processor, the server may perform summarization and vector embedding for the first content data through an encoder. When the commands are executed individually or collectively by the at least one processor, the server may obtain a first vector value corresponding to the first content data based on the summarization and vector embedding. When the commands are executed individually or collectively by the at least one processor, the server may store the first content identifier and the first vector value in the content database in a key-value format.

[0009] A method for storing a content identifier and a vector value in a server according to one embodiment of the present disclosure may include an operation of obtaining first content data corresponding to a first content identifier. The method may include an operation of performing a summary and vector embedding for the first content data through an encoder of the server. The method may include an operation of obtaining a first vector value corresponding to the first content data based on the performance of the summary and vector embedding. The method may include an operation of storing the first content identifier and the first vector value in a content database of the server in a key-value format.

[0010] According to one embodiment of the present disclosure, in a non-transitory storage medium storing commands, the commands are configured to cause the electronic device to perform at least one operation when executed by the electronic device, wherein the at least one operation may include an operation of identifying rendering data to be displayed through a display of the electronic device. The at least one operation may include an operation of performing a summary and vector embedding for each of at least one content data item included in the rendering data through an encoder of the electronic device. The at least one operation may include an operation of obtaining at least one vector value for each of at least one content data item based on the performance of the summary and vector embedding. The at least one operation may include an operation of transmitting the at least one vector value to an external server storing a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers. The at least one operation may include receiving a first content identifier corresponding to a first vector value among the at least one vector values ​​from the external server through the communication circuit of the electronic device based on a comparison of the plurality of vector values ​​and the at least one vector value by the external server. The at least one operation may include performing a process to obscure a first content data item corresponding to the first vector value in the rendering data if there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value. The at least one operation may include displaying the rendering data with the first content item obscured through the display.

[0011] FIG. 1 is a block diagram of an electronic device in a network environment according to one embodiment.

[0012] FIG. 2 is a block diagram of a server according to one embodiment.

[0013] FIG. 3 is a diagram illustrating an encoder of a server according to one embodiment.

[0014] FIG. 4 is a flowchart illustrating the operation of storing a content identifier and a vector value corresponding to the content identifier in a server according to one embodiment.

[0015] FIG. 5 is a block diagram of an electronic device according to one embodiment.

[0016] FIG. 6 is a diagram illustrating the operation of an encoder of an electronic device according to one embodiment.

[0017] FIG. 7 is a diagram illustrating the operation of an electronic device and a server according to one embodiment.

[0018] FIG. 8 is a flowchart illustrating an operation to prevent spoilers for content using an artificial intelligence model in an electronic device according to one embodiment.

[0019] FIG. 9 is a diagram showing an example in which a web page is displayed with a spoiler-containing content data item obscured in an electronic device according to one embodiment.

[0020] FIG. 1 is a block diagram of an electronic device (101) in a network environment (100) according to one embodiment. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or may communicate with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through the server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0021] The processor (120) can control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., a program (140)), and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use lower power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0022] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or through a separate server (e.g., server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers.An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0023] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0024] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0025] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0026] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0027] The display module (160) can visually provide information to an external (e.g., user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling said device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of the force generated by said touch.

[0028] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0029] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0030] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0031] The connection terminal (178) may include a connector through which the electronic device (101) can be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0032] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0033] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0034] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0035] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0036] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0037] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), full-dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large-scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), external electronic device (e.g., electronic device (104)), or network system (e.g., second network (199)). According to one embodiment, the wireless communication module (192) can support a Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mMTC, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for realizing URLLC.

[0038] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0039] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0040] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0041] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) through a server (108) connected to a second network (199). Each of the external electronic devices (102, or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In one embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within a second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0042] In the following detailed description, reference numbers in the drawings may be assigned identically or omitted for configurations that can be easily understood through prior embodiments, and detailed descriptions thereof may also be omitted. An electronic device according to one embodiment disclosed in this document may be implemented by selectively combining configurations of various embodiments, and a configuration of one embodiment may be replaced by a configuration of another embodiment. For example, it should be noted that this disclosure is not limited to specific drawings or embodiments.

[0043] FIG. 2 is a block diagram of a server according to one embodiment.

[0044] Referring to FIG. 2, a server (208) according to one embodiment (e.g., server (108) of FIG. 1) may include at least one processor (220) (hereinafter also referred to as processor (220)), memory (230), and communication circuit (290).

[0045] A processor (220) according to one embodiment may include some or all of a central processing unit (CPU), a neural processing unit (NPU), and a graphics processing unit (GPU), and may include a hardware structure specialized for processing an artificial intelligence (AI) model. A processor (220) according to one embodiment may perform overall control operations of a server (208). A processor (220) according to one embodiment may execute commands stored in memory (230) individually or collectively to enable the server (208) to perform an operation of storing a content identifier of the present disclosure and at least one vector value corresponding to the content identifier in a key-value format.

[0046] A processor (220) according to one embodiment may acquire content data (or content) (e.g., first content data) corresponding to a content identifier (e.g., first content identifier). The first content identifier according to one embodiment may include identification information (e.g., content name) representing the first content data. The first content data according to one embodiment may include text content data, image content data, audio content data, video content data, and / or 3D content data. For example, text content data may include news articles, blogs, essays, reviews, social network service (SNS) posts, comments, chats, e-books, web novels, and / or webtoon dialogue. Image content data may include photographs, illustrations, digital art, webtoons, comics, graphic novels, advertising banners, and / or thumbnails. Audio content data may include music, sound sources, podcasts, audiobooks, sound effects, and / or background music. Video content data may include dramas, movies, entertainment shows, documentaries, YouTube videos, vlogs, short-form videos, advertisement videos, live broadcasts, and / or lecture videos. A processor (220) according to one embodiment may obtain first content data corresponding to a first content identifier from a content providing device (or content providing server) (not shown).

[0047] A processor (220) according to one embodiment may perform summarization and vector embedding for the first content data through an encoder (235). A processor (220) according to one embodiment may perform summarization for the first content through an artificial intelligence model (e.g., LLM (multi-modal large language model), visual LLM, and / or multimodal LLM) of the encoder (235) to obtain summary data (e.g., text) for the first content data, and perform vector embedding for the summary data to obtain a first vector value corresponding to the first content data. An LLM according to one embodiment may be a deep learning-based model capable of understanding and generating natural language by learning large-scale text data. A visual LLM may be a model that learns image and text data together and may be a model capable of understanding images and describing or responding to them in text. A multimodal LLM may be a model capable of understanding and generating various forms of data (text, images, audio, video, etc.) together.

[0048] A processor (220) according to one embodiment may store a first content identifier and a first vector value in a content database (239) in a key-value format. A processor (220) according to one embodiment may store a plurality of content identifiers including the first content identifier and a plurality of vector values ​​corresponding to each of the plurality of content identifiers and including the first vector value in a key-value format in the content database (239).

[0049] A processor (220) according to one embodiment can, when at least one vector value is received from an external electronic device (e.g., electronic device (101) of FIG. 1) through a communication circuit (290), compare the received at least one vector value among a plurality of vector values ​​in a content database (239) to identify a matching vector value (e.g., a first vector value) that has a high similarity or has a similarity value greater than or equal to a specified similarity value. A processor (220) according to one embodiment can identify a first content identifier (value) corresponding to the identified first vector value (key) and transmit the first content identifier to the electronic device (101).

[0050] A memory (230) according to one embodiment may include one or more storage media for storing. A memory (230) according to one embodiment may store instructions (e.g., instructions), an encoder (235), and a content database (content DB) (239). A memory (230) according to one embodiment may store various data used by at least one component of a server (208) (e.g., a processor (220), and / or a communication circuit (290)). The data may include, for example, software (e.g., a software module or program) and input data or output data for related instructions.

[0051] The encoder (235) of the memory (235) according to one embodiment may include an artificial intelligence model. The artificial intelligence model may be created through learning. Here, being created through learning means that a basic artificial intelligence model is trained using a number of training data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model configured to perform a desired characteristic (or purpose). Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is performed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0052] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include deep neural networks (DNNs), such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), or Deep Q-Networks, but are not limited to the examples mentioned above. An encoder (235) according to one embodiment may include an LLM, a visual LLM, or a multimodal LLM. An LLM according to one embodiment may be a deep learning-based model capable of understanding and generating natural language by learning large-scale text data. A visual LLM may be a model that learns image and text data together and may be a model capable of understanding images and describing or responding to them in text. A multimodal LLM may be a model capable of understanding and generating various forms of data (text, images, audio, video, etc.) together.

[0053] A communication circuit (290) according to one embodiment can communicate with an external electronic device (101). A communication circuit (290) according to one embodiment can transmit at least one content identifier to the electronic device (101) through communication with the external electronic device (101).

[0054] In one embodiment, the main components of the server (208) of FIG. 2 have been described. However, in various embodiments, not all components illustrated in FIG. 2 are essential components, and the connection relationships of the main components of the server (208) described in FIG. 2 may be changed according to various embodiments.

[0055] A server according to one embodiment of the present disclosure (e.g., server (108) of FIG. 1 or server (208) of FIG. 2) may include a communication circuit (290), a content database (239), a memory (230) for storing commands, and at least one processor (220). When the commands are executed individually or collectively by the at least one processor, the server may obtain first content data corresponding to a first content identifier. When the commands are executed individually or collectively by the at least one processor, the server may perform summarization and vector embedding of the first content data through an encoder. When the commands are executed individually or collectively by the at least one processor, the server may obtain a first vector value corresponding to the first content data based on the summarization and vector embedding. When the above commands are executed individually or collectively by the at least one processor, the server may store the first content identifier and the first vector value in the content database in a key-value format.

[0056] According to one embodiment, the content database may include a plurality of content identifiers including the first content identifier and a plurality of vector values ​​corresponding to each of the plurality of content identifiers and including the first vector value.

[0057] The encoder according to one embodiment may include an LLM, a visual LLM, or a multimodal LLM.

[0058] FIG. 3 is a diagram illustrating the operation of an encoder of a server according to one embodiment.

[0059] Referring to FIG. 3, a processor (220) according to one embodiment may obtain content data from a content providing device (or content providing server) (not shown). The content data may include first content data (300-1) to Nth content data (300-N). For example, the first content identifier of the first content data (300-1) may be “X1 Series Episode 1”. The second content identifier of the second content data (300-2) may be “X1 Series Episode 2”. The Nth content identifier of the Nth content data (300-N) may be “X2 Movie”.

[0060] A processor (220) according to one embodiment can summarize each of the first content data (300-1) to the Nth content data (300-N) using a prompt (e.g., summary prompt) through the multimodal LLM (310) of the encoder (235) (310). A processor (220) according to one embodiment can obtain summary data (e.g., summary(text)) for each of the first content data (300-1) to the Nth content data (300-N) (320). A processor (220) according to one embodiment can perform vector embedding on the summary data (330). A processor (220) according to one embodiment can obtain a first vector value (Vector #1) to a Nth vector value (Vector #N) for each of the first content data (300-1) to the Nth content data (300-N) based on summarizing and vector embedding. A processor (220) according to one embodiment can store the first content identifier to the Nth content identifier (“X1 Series Episode 1”, “X1 Series Episode 2”, …, “X2 Movie”) and the first vector value to the Nth vector value (Vector #1, Vector #2, …, Vector #N) corresponding to each of the first content data (300-1) to the Nth content data (300-N) in a key-value format in a content database (239). A processor (220) according to one embodiment can update a content database (239) whenever new content data is obtained from a content providing device (or content providing server) (not shown).

[0061] FIG. 4 is a flowchart illustrating the operation of storing a content identifier and a vector value corresponding to the content identifier in a server according to one embodiment.

[0062] Referring to FIG. 4, the processor (220) of a server according to one embodiment (e.g., server (108) of FIG. 1 or server (208) of FIG. 2) can perform at least one of 410 operations to 440 operations.

[0063] In operation 410, a processor (220) according to one embodiment may obtain first content data corresponding to a first content identifier. The first content identifier according to one embodiment may include identification information (e.g., content name) representing the first content data. The first content data according to one embodiment may include text content data, image content data, audio content data, video content data, and / or 3D content data. For example, text content data may include news articles, blogs, essays, reviews, social media posts, comments, chats, e-books, web novels, and / or webtoon dialogue. Image content data may include photographs, illustrations, digital art, webtoons, comics, graphic novels, advertising banners, and / or thumbnails. Audio content data may include music, sound sources, podcasts, audiobooks, sound effects, and / or background music. Video content data may include dramas, movies, entertainment shows, documentaries, YouTube videos, vlogs, short-form videos, advertisement videos, live broadcasts, and / or lecture videos. A processor (220) according to one embodiment may obtain first content data corresponding to a first content identifier from a content providing device (or content providing server) (not shown).

[0064] In operation 420, a processor (220) according to one embodiment may perform a summary of the first content data to obtain first summary data corresponding to the first content data. A processor (220) according to one embodiment may perform a summary of the first content through an artificial intelligence model of an encoder (235) (e.g., LLM (multi-modal large language model), visual LLM, and / or multimodal LLM) to obtain first summary data (e.g., text) for the first content data. An LLM according to one embodiment may be a deep learning-based model capable of understanding and generating natural language by learning large-scale text data. A visual LLM may be a model that learns image and text data together and may be a model capable of understanding images and describing or responding to them in text. A multimodal LLM may be a model capable of understanding and generating various forms of data (text, images, audio, video, etc.) together.

[0065] In operation 430, a processor (220) according to one embodiment can perform vector embedding for the first summary data to obtain a first vector value corresponding to the first content identifier.

[0066] In operation 440, a processor (220) according to one embodiment may store a first content identifier and a first vector value in a key-value format in a content database (239). A processor (220) according to one embodiment may store a plurality of content identifiers including the first content identifier and a plurality of vector values ​​corresponding to each of the plurality of content identifiers and including the first vector value in a key-value format in a content database (239).

[0067] A method for storing a content identifier and a vector value in a server of the present disclosure (e.g., the server (108) of FIG. 1 or the server (208) of FIG. 2) may include an operation of obtaining a first content data corresponding to a first content identifier. The method may include an operation of performing a summary and vector embedding for the first content data through an encoder of the server. The method may include an operation of obtaining a first vector value corresponding to the first content data based on the performance of the summary and vector embedding. The method may include an operation of storing the first content identifier and the first vector value in a key-value format in a content database of the server.

[0068] In the method according to one embodiment, the content database may include a plurality of content identifiers including the first content identifier and a plurality of vector values ​​corresponding to each of the plurality of content identifiers and including the first vector value.

[0069] In the method according to one embodiment, the encoder may include an LLM, a visual LLM, or a multimodal LLM.

[0070] FIG. 5 is a block diagram of an electronic device according to one embodiment.

[0071] Referring to FIG. 5, an electronic device (501) according to one embodiment (e.g., the electronic device (101) of FIG. 1) may include at least one processor (520) (hereinafter also referred to as processor (520)), memory (530), display (560), and communication circuit (590). The electronic device (501) according to one embodiment is not limited thereto and may be configured to include various additional components or to exclude some of the components. The electronic device (501) according to one embodiment may further include all or part of the electronic device (101) shown in FIG. 1.

[0072] A processor (520) according to one embodiment can perform overall control operations of an electronic device (501) and can perform operations (or methods) to prevent spoilers for content using the artificial intelligence model of the present disclosure.

[0073] A processor (520) according to one embodiment may be composed of one or more processors. In this case, the one or more processors may be a general-purpose processor such as a CPU, AP, DSP (digital signal processor), a graphics-dedicated processor such as a GPU, VPU (vision processing unit), or an artificial intelligence-dedicated processor such as an NPU. The one or more processors may be controlled to process input data according to a predefined operation rule or artificial intelligence model stored in memory (530). Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0074] A processor (520) according to one embodiment can identify rendering data to be displayed through a display (260). Rendering data according to one embodiment may be a data structure of the stage immediately preceding to be displayed on the display (260). A web page through a web browser application according to one embodiment may include web page data before it is displayed on the display (260). Rendering data according to one embodiment may include a render tree, a rendering structure combining a document object model (DOM) and a CSS object model (CSSOM). Rendering data according to one embodiment may include at least one content data item. Each of the at least one content data item according to one embodiment may or may not include an article, comment, review, or summary containing spoilers for content data (e.g., e-book, drama, movie, or other types of content data). According to one embodiment, at least the content data items may include text content data items, image content data items, audio content data items, video content data items, and / or 3D content data items. For example, text content data items may include news articles, blogs, essays, reviews, social media posts, comments, chats, e-books, web novels, and / or webtoon dialogue. Image content data items may include photographs, illustrations, digital art, webtoons, comics, graphic novels, advertising banners, and / or thumbnails. Audio content data items may include music, sound sources, podcasts, audiobooks, sound effects, and / or background music. Video content data items may include dramas, movies, variety shows, documentaries, YouTube videos, vlogs, short-form videos, advertising videos, live broadcasts, and / or lecture videos.

[0075] A processor (520) according to one embodiment can obtain at least one vector value for each of at least one content data item through summarization and vector embedding for at least one content data item included in the rendering data. A processor (520) according to one embodiment can obtain summary data (e.g., text) for each of at least one content data item by performing summarization for each of at least one content data item through an artificial intelligence model (e.g., multi-modal large language model (LM), visual LLM, and / or multimodal LLM) of an encoder (535). A processor (220) according to one embodiment can obtain at least one vector value for each of at least one content data item by performing vector embedding for the summary data for each of at least one content data item.

[0076] A processor (520) according to one embodiment may transmit at least one vector value for each of at least one content data item to an external server (e.g., server (108) of FIG. 1 or server (208) of FIG. 2). When the server (208) according to one embodiment receives at least one vector value from an electronic device (501), it may compare at least one vector value with a plurality of vector values ​​in a content database (239), and if there is a matching vector value (e.g., a first vector value) among the plurality of vector values ​​(e.g., a first vector value) that has a high similarity or has a similarity value greater than or equal to a specified similarity value), identify a first content identifier (value) corresponding to the first vector value (key), and transmit the first content identifier to the electronic device (101).

[0077] A processor (520) according to one embodiment can identify whether a first content identifier corresponding to a first vector value is received from a server (208) in response to the transmission of at least one vector value.

[0078] A processor (520) according to one embodiment can identify whether there is a viewing history associated with the first content identifier (e.g., a viewing history by a user (or user account) of an electronic device (501)) when a first content identifier corresponding to the first vector value is received from a server (208) in response to the transmission of at least one vector value. A processor (520) according to one embodiment can determine whether there is a user's viewing history for the first content corresponding to the first content identifier by using the first content identifier and user information (e.g., user account) through a content provider (e.g., another pre-designated server (e.g., OTT server (not shown)) that provides the first content corresponding to the first content identifier.

[0079] A processor (520) according to one embodiment may process rendering data such that a first content data item corresponding to the first content identifier is obscured if there is a viewing history associated with the first content identifier (a viewing history by a user (or user account) of the electronic device (501)). A processor (520) according to one embodiment may display rendering data processed to obscure the first content data item through a display (560). A processor (520) according to one embodiment may perform blur processing, deletion processing, or masking processing on the first content data item to obscure the first content data item in the rendering data.

[0080] A processor (520) according to one embodiment may display rendering data as is (without obscuring) through a display (560) if a first content identifier corresponding to a first vector value is not received from a server (208) or if there is no viewing history associated with the first content identifier (viewing history by a user (or user account) of an electronic device (501)).

[0081] A memory (530) according to one embodiment may include one or more storage media for storing. A memory (530) according to one embodiment may store various data used by at least one component of an electronic device (501) (e.g., processor (520), display (260) and / or communication circuit (590)). The data may include, for example, software (e.g., software modules or programs and input data or output data for instructions related thereto). A memory (530) according to one embodiment may store instructions (e.g., instructions) and an encoder (535). A memory (530) according to one embodiment may store instructions or software modules (or programs) for performing actions (or methods) to prevent spoilers for content using the artificial intelligence model of the present disclosure.

[0082] The encoder (535) of the memory (535) according to one embodiment may include an artificial intelligence model. The artificial intelligence model may be created through learning. Here, being created through learning means that a basic artificial intelligence model is trained using a number of learning data by a learning algorithm, thereby creating a predefined operation rule or artificial intelligence model configured to perform a desired characteristic (or purpose). Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is performed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0083] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include deep neural networks (DNNs), such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), or Deep Q-Networks, but are not limited to the examples mentioned above. An encoder (535) according to one embodiment may include an LLM, a visual LLM, or a multimodal LLM.

[0084] A communication circuit (590) according to one embodiment can communicate with a server (208). A communication circuit (590) according to one embodiment can receive at least one content identifier from the server (208) through communication with the server (208).

[0085] According to one embodiment, the electronic device (501) is not limited to the configuration shown in FIG. 5 and may be configured to include various additional components. In one embodiment, the main components of the electronic device were described through the electronic device (501) of FIG. 5. However, in various embodiments, not all components shown through FIG. 5 are essential components, and the connection relationships of the main components of the electronic device (501) described through FIG. 5 may be changed according to various embodiments.

[0086] An electronic device according to one embodiment of the present disclosure (e.g., the electronic device (101) of FIG. 1 or the electronic device (501) of FIG. 5) may include a communication circuit (190 or 590), a display (160 or 560), a memory (130 or 530) for storing commands, and at least one processor (120 or 520). According to one embodiment, the commands, when executed individually or collectively by the at least one processor, may cause the electronic device to identify rendering data to be displayed through the display. The commands, when executed individually or collectively by the at least one processor, may cause the electronic device to perform summarization and vector embedding for each of at least one content data item included in the rendering data through an encoder. When executed individually or collectively by the at least one processor, the above commands may cause the electronic device to obtain at least one vector value for each of at least one content data item based on the summarization and the vector embedding operation. When executed individually or collectively by the at least one processor, the above commands may cause the electronic device to transmit the at least one vector value to an external server storing a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers. When executed individually or collectively by the at least one processor, the above commands may cause the electronic device to receive a first content identifier corresponding to a first vector value among the at least one vector value from the external server based on a comparison of the plurality of vector values ​​and the at least one vector value by the external server.When the above commands are executed individually or collectively by the at least one processor, the electronic device may perform a process to obscure the first content data item corresponding to the first vector value in the rendering data if there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value. When the above commands are executed individually or collectively by the at least one processor, the electronic device may display the rendering data with the first content item obscured through the display.

[0087] When the commands according to one embodiment are executed individually or collectively by the at least one processor, the electronic device may perform blur processing, deletion processing, or masking processing to obscure the first content data item in the rendering data.

[0088] When the commands according to one embodiment are executed individually or collectively by the at least one processor, the electronic device may be configured to display the rendering data through the display if the first content identifier corresponding to the first vector value among the at least one vector value is not received from the external server.

[0089] When the commands according to one embodiment are executed individually or collectively by the at least one processor, the electronic device may be able to display the rendering data through the display if there is a viewing history associated with the first content identifier corresponding to the first vector value.

[0090] According to one embodiment, the at least one content data item of the rendering data may include text, images, and / or videos included in the web page data.

[0091] The encoder according to one embodiment may include an AI model.

[0092] According to one embodiment, the AI ​​model may include a large language model (LM), a visual LLM, or a multimodal LLM.

[0093] FIG. 6 is a diagram illustrating the operation of an encoder of an electronic device according to one embodiment.

[0094] Referring to FIG. 6, a processor (520) according to one embodiment can identify rendering data to be displayed on a display (560). Rendering data according to one embodiment may be a data structure of the stage immediately preceding to be displayed on the display (260). A web page (e.g., web page 1) through a web browser application according to one embodiment may include web page data before being displayed on the display (260). Rendering data (e.g., web page data) according to one embodiment may include at least one content data item (e.g., content data item 1 (600-1), content data item 2 (600-2), , content data item N (600-N)). According to one embodiment, each of the content data item 1 (600-1), content data item 2 (600-2), and content data item N (600-N) may or may not include articles, comments, reviews, or summaries containing spoilers for content data (e.g., e-books, dramas, movies, or other types of content data). According to one embodiment, at least a portion of the content data item 1 (600-1), content data item 2 (600-2), and content data item N (600-N) (e.g., content data item 2 (600-2)) may include data from at least one other web page (e.g., web page 2) linked to web page 1. According to one embodiment, each of the content data item 1 (600-1), content data item 2 (600-2), and content data item N (600-N) may include a text content data item, an image content data item, an audio content data item, a video content data item, and / or a 3D content data item. For example, the text content data item may include news articles, blogs, essays, reviews, social media posts, comments, chats, e-books, web novels, and / or webtoon dialogue.Image content data items may include photos, illustrations, digital art, webtoons, comics, graphic novels, advertising banners, and / or thumbnails. Audio content data items may include music, sound sources, podcasts, audiobooks, sound effects, and / or background music. Video content data items may include dramas, movies, variety shows, documentaries, YouTube videos, vlogs, short-form videos, advertising videos, live broadcasts, and / or lecture videos.

[0095] A processor (520) according to one embodiment can summarize each of content data item 1 (600-1) to content data item N (600-N) using a summary prompt through the multimodal LLM of the encoder (535) (610). A processor (520) according to one embodiment can obtain summary data (e.g., summary(text)) for each of content data item 1 (600-1) to content data item N (600-N) (620). A processor (520) according to one embodiment can perform vector embedding on the summary data (630). A processor (220) according to one embodiment can obtain at least one vector value (Vector #1' to Vector #N') for each of content data item 1 (600-1) to content data item N (600-N) based on the summarization and vector embedding performance.

[0096] FIG. 7 is a diagram illustrating the operation of transmitting at least one vector value to a server in an electronic device according to one embodiment.

[0097] Referring to FIG. 7, an electronic device (501) (or a processor (520) of the electronic device (501)) according to one embodiment can transmit at least one vector value (Vector #1' to Vector #N') for each of content data item 1 (600-1) to content data item N (600-N) obtained through an encoder (535) to a server (208) through a communication circuit (290) (710). According to one embodiment, when a server (208) receives at least one vector value (Vector #1' to Vector #N') from an electronic device (501), it compares the at least one vector value (Vector #1' to Vector #N') with a plurality of vector values ​​in a content database (239), and if there is a matching vector value (e.g., a first vector value) among the plurality of vector values ​​(e.g., a first vector value) that has a high similarity or has a similarity value greater than or equal to a specified similarity value, it identifies a first content identifier (value) corresponding to the first vector value (key) and transmits the first content identifier to the electronic device (501) (720).

[0098] For example, if the content data item 1 (500-1) of FIG. 6 contains a spoiler for the first content identifier “Episode 1 of X1 Series”, the vector value (Vector #1') of the content data item 1 (500-1) may have a high similarity to the first vector value (Vector #1) of the first content identifier of the “Episode 1 of X1 Series” in the content DB (230) or may have a similarity value greater than a specified similarity value, and the server (208) may transmit the first content identifier to the electronic device (201).

[0099] FIG. 8 is a flowchart illustrating an operation to prevent spoilers for content using an artificial intelligence model in an electronic device according to one embodiment.

[0100] Referring to FIG. 8, the processor (520) of an electronic device according to one embodiment (e.g., the electronic device (101) of FIG. 1 or the electronic device (501) of FIG. 5) can perform at least one of 810 operations to 880 operations.

[0101] In operation 810, a processor (520) according to one embodiment can identify rendering data to be displayed through a display (260). Rendering data according to one embodiment may be a data structure of the stage immediately preceding to be displayed on the display (260). A web page through a web browser application according to one embodiment may include web page data before it is displayed on the display (260). Rendering data according to one embodiment may include a render tree, a rendering structure combining a document object model (DOM) and a CSS object model (CSSOM). Rendering data according to one embodiment may include at least one content data item. Each of the at least one content data item according to one embodiment may or may not include an article, comment, review, or summary containing spoilers for content data (e.g., e-book, drama, movie, or other types of content data). According to one embodiment, at least the content data items may include text content data items, image content data items, audio content data items, video content data items, and / or 3D content data items. For example, text content data items may include news articles, blogs, essays, reviews, social media posts, comments, chats, e-books, web novels, and / or webtoon dialogue. Image content data items may include photographs, illustrations, digital art, webtoons, comics, graphic novels, advertising banners, and / or thumbnails. Audio content data items may include music, sound sources, podcasts, audiobooks, sound effects, and / or background music. Video content data items may include dramas, movies, variety shows, documentaries, YouTube videos, vlogs, short-form videos, advertising videos, live broadcasts, and / or lecture videos.

[0102] In step 820, a processor (520) according to one embodiment may obtain at least one vector value for each of at least one content data item through summary and vector embedding for at least one content data item included in the rendering data. A processor (520) according to one embodiment may obtain summary data (e.g., text) for each of at least one content data item by performing summary for each of at least one content data item through an artificial intelligence model (e.g., multi-modal large language model (LM), visual LLM, and / or multimodal LLM) of an encoder (535). A processor (220) according to one embodiment may obtain at least one vector value for each of at least one content data item by performing vector embedding for the summary data for each of at least one content data item.

[0103] In operation 830, a processor (520) according to one embodiment may transmit at least one vector value for each of at least one content data item to an external device (e.g., an external server (e.g., the server (108) of FIG. 1 or the server (208) of FIG. 2)). When the server (208) according to one embodiment receives at least one vector value from an electronic device (501), it may compare at least one vector value with a plurality of vector values ​​in a content database (239) and, if there is a matching vector value (e.g., a first vector value) among the plurality of vector values ​​(e.g., a first vector value) that has a high similarity or has a specified similarity value or higher), identify a first content identifier (value) corresponding to the first vector value (key) and transmit the first content identifier to the electronic device (101).

[0104] In operation 840, the processor (520) according to one embodiment may identify whether a first content identifier corresponding to the first vector value is received from the server (208) in response to the transmission of at least one vector value. If the content identifier is not received from the server (208) in response to the transmission of at least one vector value, the processor (520) according to one embodiment may perform operation 880. If the first content identifier corresponding to the first vector value is received from the server (208) in response to the transmission of at least one vector value, the processor (520) according to one embodiment may perform operation 850.

[0105] In operation 850, the processor (520) according to one embodiment can identify whether there is a viewing history associated with the first content identifier (e.g., a viewing history by a user (or user account) of the electronic device (501). A processor (520) according to one embodiment may check whether there is a user's viewing history for the first content corresponding to the first content identifier by using the first content identifier and user information (e.g., user account) through a content provider (e.g., another pre-specified server (e.g., OTT server (not shown)) that provides the first content corresponding to the first content identifier. A processor (520) according to one embodiment may perform an 880 operation if there is no viewing history associated with the first content identifier (viewing history by the user (or user account) of the electronic device (501)). A processor (520) according to one embodiment may perform an 860 operation if there is a viewing history associated with the first content identifier (viewing history by the user (or user account) of the electronic device (501)).

[0106] In operation 860, the processor (520) according to one embodiment can process the first content data item corresponding to the first content identifier among the rendering data so that if there is a viewing history associated with the first content identifier (a viewing history by a user (or user account) of the electronic device (501)), the first content data item corresponding to the first content identifier is obscured.

[0107] In operation 870, the processor (520) according to one embodiment may display the rendered data processed so that the first content data item is obscured through the display (560). The processor (520) according to one embodiment may perform a blur process, a deletion process, or a masking process on the first content data item to obscure the first content data item in the rendered data.

[0108] In operation 880, the processor (520) according to one embodiment may display the rendering data as is (without obscuring) through the display (560) if the first content identifier corresponding to the first vector value is not received from the server (208) or if there is no viewing history associated with the first content identifier (viewing history by the user (or user account) of the electronic device (501)).

[0109] A method for preventing spoilers regarding content using an artificial intelligence model in an electronic device (e.g., the electronic device (101) of FIG. 1 or the electronic device (501) of FIG. 5) according to one embodiment of the present disclosure may include an operation of identifying rendering data to be displayed through a display of the electronic device. The method may include an operation of performing a summary and vector embedding for each of at least one content data item included in the rendering data through an encoder of the electronic device. The method may include an operation of obtaining at least one vector value for each of at least one content data item based on the performance of the summary and vector embedding. The method may include an operation of transmitting the at least one vector value to an external server that stores a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers. The method may include an operation of receiving a first content identifier corresponding to a first vector value among the at least one vector value from the external server through a communication circuit of the electronic device based on a comparison of the plurality of vector values ​​and the at least one vector value by the external server. The above method may include an operation to perform processing to obscure a first content data item corresponding to the first vector value in the rendering data if there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value. The above method may include an operation to display the rendering data with the first content item obscured through the display.

[0110] The method according to one embodiment may include an operation of performing a blur process, a deletion process, or a masking process to obscure the first content data item in the rendering data.

[0111] The method according to one embodiment may include an operation of displaying the rendering data through the display if the first content identifier corresponding to the first vector value among the at least one vector value is not received from the external server.

[0112] The method according to one embodiment may include an operation of displaying the rendering data through the display if there is a viewing history associated with the first content identifier corresponding to the first vector value.

[0113] In the method according to one embodiment, the at least one content data item of the rendering data may include text, images, and / or videos included in the web page data.

[0114] In the method according to one embodiment, the encoder includes an AI model, and the AI ​​model may include a large language model (LM), a visual LLM, or a multimodal LLM.

[0115] FIG. 9 is a drawing showing a screen in which rendering data processed so that a first content data item according to one embodiment is obscured is displayed through a display.

[0116] Referring to FIG. 9, an electronic device (501) (or a processor (520) of the electronic device (501)) according to one embodiment can obtain vector values ​​corresponding to each of the content data items (e.g., 911 to 918) through a summary and vector embedding of the content data items (e.g., 911 to 918) included in the rendering data. A processor (520) according to one embodiment can transmit the vector values ​​to a server (208). A processor (520) according to one embodiment may receive a content identifier corresponding to at least some of the content data vector values ​​from the server (208) in response to transmitting vector values ​​to the server (208), and if there is a viewing history associated with the received content identifier (e.g., a viewing history by a user (or user account) of the electronic device (501), the content data item (912) corresponding to the received content identifier in the rendering data may be obscured. A processor (520) according to one embodiment may perform a blur process, a deletion process, or a masking process on the content data item (912) to obscure the content data item (912) in the rendering data. A processor (520) according to one embodiment may display a screen (901) of the rendering data processed to obscure the content data item (912) through a display (560).

[0117] An electronic device (501) according to one embodiment can identify a specific content data item among various content items included in rendering data that contains information about content that the user has not watched, and perform a process to obscure the specific content data item when displaying it, thereby preventing spoilers of information about content that the user has not watched among the rendering data.

[0118] The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs.

[0119] The electronic device according to the various embodiments disclosed in this document may be a device of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the devices described above.

[0120] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, each of phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as “first,” “second,” or “first” or “second” may be used simply to distinguish a component from another component and do not limit the components in any other aspect (e.g., importance or order). Where any (e.g., first) component is referred to as “coupled” or “connected” to another (e.g., second) component, with or without the terms “functionally” or “communicationally,” it means that said component may be connected to said other component directly (e.g., wired), wirelessly, or through a third component.

[0121] The term “module” as used in the various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0122] Various embodiments of the present document may be implemented as software (e.g., program (140)) comprising one or more instructions stored in a storage medium (e.g., internal memory (136) or external memory (138)) readable by a machine (e.g., electronic device (101)). For example, a processor (e.g., processor (120)) of the machine (e.g., electronic device (101)) may call at least one of the one or more instructions stored in the storage medium and execute it. This enables the machine to be operated to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0123] 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 the computer program product 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.

[0124] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the components or operations among the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0125] As used herein, the term “if” will be understood, depending on the context, to mean “when, upon,” “in response to a decision,” or “in response to a detection.” Similarly, “when decided to,” or “when [the mentioned condition or event] is detected,” will be understood, optionally, to mean “when decided,” or “in response to a decision,” “when [the mentioned condition or event] is detected,” or “in response to detecting [the mentioned condition or event].”

[0126] The device described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the device and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit (or processing circuit) may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0127] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be embodied in any type of machine, component, physical device, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0128] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. In this case, the medium may continuously store a program executable by a computer, or temporarily store it for execution or download. Additionally, the medium may be various recording or storage means in the form of a single or several hardware combined, and may not be limited to a medium directly connected to a computer system but may exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by an app store that distributes applications or a site or server that supplies or distributes various other software.

[0129] In a non-transient storage medium storing commands according to one embodiment, the commands are configured to cause the electronic device (101, 501) to perform at least one operation when executed by the electronic device, wherein the at least one operation may include an operation of identifying rendering data to be displayed through the display of the electronic device. The at least one operation may include an operation of performing a summary and vector embedding for each of at least one content data item included in the rendering data through an encoder of the electronic device. The at least one operation may include an operation of obtaining at least one vector value for each of at least one content data item based on the performance of the summary and vector embedding. The at least one operation may include an operation of transmitting the at least one vector value to an external server that stores a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers. The at least one operation may include receiving a first content identifier corresponding to a first vector value among the at least one vector values ​​from the external server through the communication circuit of the electronic device based on a comparison of the plurality of vector values ​​and the at least one vector value by the external server. The at least one operation may include performing a process to obscure a first content data item corresponding to the first vector value in the rendering data if there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value. The at least one operation may include displaying the rendering data with the first content item obscured through the display.

[0130] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents. Therefore, other implementations, other embodiments, and equivalents to the claims below are also within the scope of the claims.

Claims

1. In an electronic device (101, 501), Display(160, 560); Communication circuit (190, 590); Memory for storing commands (130, 530); and It includes at least one processor (120, 520), and When the above commands are executed individually or collectively by the at least one processor, the electronic device, Identify rendering data to be displayed through the above display, and Summarization and vector embedding are performed for each of at least one content data item included in the rendering data through an encoder, and Based on the summary and vector embedding performed above, at least one vector value for each of at least one content data item is obtained, and Transmitting at least one vector value to an external server that stores a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers, and Based on the comparison of the plurality of vector values ​​and the at least one vector value by the external server, a first content identifier corresponding to the first vector value among the at least one vector value is received from the external server, and If there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value, a process is performed to obscure the first content data item corresponding to the first vector value in the rendering data, and An electronic device that displays the rendering data, in which the first content item is obscured, through the display.

2. In Paragraph 1, When the above commands are executed individually or collectively by the at least one processor, the electronic device, An electronic device that performs blur processing, deletion processing, or masking processing to obscure the first content data item in the rendering data.

3. In Paragraph 1 or 2, When the above commands are executed individually or collectively by the at least one processor, the electronic device, An electronic device that displays the rendering data through the display if the first content identifier corresponding to the first vector value among the at least one vector value is not received from the external server.

4. In any one of paragraphs 1 through 3, When the above commands are executed individually or collectively by the at least one processor, the electronic device, An electronic device that displays the rendering data through the display if there is a viewing history associated with the first content identifier corresponding to the first vector value.

5. In any one of paragraphs 1 through 4, The at least one content data item of the rendering data is an electronic device comprising text, images, and / or video included in web page data.

6. In any one of paragraphs 1 through 5, The above encoder is an electronic device including an AI model.

7. In any one of paragraphs 1 through 6, The above AI model is an electronic device including an LLM (large language model), a visual LLM, or a multimodal LLM.

8. In the server (208), Communication circuit (290); Content database (239); Memory (230) for storing commands; and It includes at least one processor (220), When the above commands are executed individually or collectively by the at least one processor, the server, Acquire first content data corresponding to the first content identifier, and Summarization and vector embedding of the first content data are performed through an encoder, and Based on the summary and vector embedding performed above, a first vector value corresponding to the first content data is obtained, and A server that stores the first content identifier and the first vector value in the content database in a key-value format.

9. In Paragraph 8, The above content database is a server comprising a plurality of content identifiers including the first content identifier and a plurality of vector values ​​corresponding to each of the plurality of content identifiers and including the first vector value.

10. In Paragraph 8 or 9, The above encoder is a server including an LLM, visual LLM, or multimodal LLM.

11. A method for preventing spoilers about content using an artificial intelligence model in an electronic device, An operation to identify rendering data to be displayed through the display of the electronic device; The operation of performing summarization and vector embedding for each of at least one content data item included in the rendering data through the encoder of the electronic device; An operation to obtain at least one vector value for each of at least one content data item based on the above summary and the above vector embedding execution; The operation of transmitting at least one vector value to an external server that stores a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers; An operation of receiving a first content identifier corresponding to a first vector value among the at least one vector value from an external server through a communication circuit of an electronic device based on a comparison of the plurality of vector values ​​and the at least one vector value by the external server; If there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value, an operation to perform processing to obscure the first content data item corresponding to the first vector value in the rendering data; and A method including the operation of displaying the rendering data, in which the first content item is obscured, through the display.

12. In Paragraph 11, A method including an operation to perform blurring, deletion, or masking to obscure the first content data item in the rendering data.

13. In Paragraph 11 or 12, A method including the operation of displaying the rendering data through the display if the first content identifier corresponding to the first vector value among the at least one vector value is not received from the external server.

14. In any one of paragraphs 11 through 13, A method including the operation of displaying the rendering data through the display if there is a viewing history associated with the first content identifier corresponding to the first vector value.

15. In a non-transient storage medium storing instructions, said instructions are set to cause said electronic device (101, 501) to perform at least one operation when said electronic device is executed, said at least one operation being, said at least one operation An operation to identify rendering data to be displayed through the display of the electronic device; The operation of performing summarization and vector embedding for each of at least one content data item included in the rendering data through the encoder of the electronic device; An operation to obtain at least one vector value for each of at least one content data item based on the above summary and the above vector embedding execution; The operation of transmitting at least one vector value to an external server that stores a plurality of content identifiers and a plurality of vector values ​​corresponding to each of the plurality of content identifiers; An operation of receiving a first content identifier corresponding to a first vector value among the at least one vector value from an external server through a communication circuit of an electronic device based on a comparison of the plurality of vector values ​​and the at least one vector value by the external server; If there is no viewing history related to the electronic device user associated with the first content identifier corresponding to the first vector value, an operation to perform processing to obscure the first content data item corresponding to the first vector value in the rendering data; and A storage medium comprising the operation of displaying the rendering data, in which the first content item is obscured, through the display.