system

Abstract

The system according to this embodiment aims to individually optimize the user's viewing experience and provide an engaging viewing experience. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a provision unit, a subtitle generation unit, a dialogue unit, a management unit, and a two-way communication unit. The collection unit collects viewing history, preferences, and real-time viewing behavior. The analysis unit analyzes the data collected by the collection unit. The provision unit provides recommended videos based on the analysis results obtained by the analysis unit. The subtitle generation unit analyzes the audio of the video in real time and generates high-precision subtitles. The dialogue unit provides a dialogue function with the user. The management unit manages the viewing history. The two-way communication unit allows users to post live comments in real time.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the viewing experience of users has not been sufficiently optimized individually on video distribution platforms, and there is room for improvement.

[0005] The system according to the embodiment aims to individually optimize the viewing experience of users and provide an attractive viewing experience.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a provision unit, a subtitle generation unit, a dialogue unit, a management unit, and a two-way communication unit. The data collection unit collects viewing history, preferences, and real-time viewing behavior. The analysis unit analyzes the data collected by the data collection unit. The provision unit provides recommended videos based on the analysis results obtained by the analysis unit. The subtitle generation unit analyzes the audio of the video in real time and generates high-precision subtitles. The dialogue unit provides a function for interacting with the user. The management unit manages the viewing history. The two-way communication unit allows users to post live comments in real time. [Effects of the Invention]

[0007] The system according to this embodiment can individually optimize the user's viewing experience and provide an engaging viewing experience. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9]This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI agent system for improving the user experience of a video distribution platform according to an embodiment of the present invention is a system that collects viewing history, preferences, and real-time viewing behavior, and provides the user with the most suitable recommended videos by analyzing this data with AI. The AI ​​agent system collects viewing history, preferences, and real-time viewing behavior, and provides the user with the most suitable recommended videos by analyzing this data with AI. Furthermore, the AI ​​agent system is equipped with an automatic subtitle generation function, which analyzes the audio of videos in real time and generates highly accurate subtitles. In addition, the AI ​​agent system provides a dialogue function with the user by utilizing speech recognition technology. Furthermore, the AI ​​agent system is equipped with a viewing history management function, which allows users to easily revisit videos they have watched in the past. Finally, the AI ​​agent system provides a two-way communication function, which allows users to post live comments in real time. Thus, the AI ​​agent system is a multi-functional system for improving the user's viewing experience and can increase engagement on the video distribution platform. For example, the AI ​​agent system collects the user's viewing history, preferences, and real-time viewing behavior, and provides the user with the most suitable recommended videos by analyzing this data with AI. For example, the AI ​​agent system analyzes the audio of videos in real time and generates highly accurate subtitles. For example, an AI agent system can utilize speech recognition technology to provide conversational capabilities with users. For example, an AI agent system can have a viewing history management function, allowing users to easily revisit videos they have previously watched. For example, an AI agent system can provide two-way communication capabilities, enabling users to post live comments in real time. In this way, the AI ​​agent system can improve the user's viewing experience.

[0029] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, a provision unit, a subtitle generation unit, a dialogue unit, a management unit, and a two-way communication unit. The collection unit collects viewing history, preferences, and real-time viewing behavior. For example, the collection unit collects viewing history such as the titles, viewing time, and viewing frequency of videos watched by the user. The collection unit can also collect preferences such as videos rated by the user and genres estimated from viewing history. Furthermore, the collection unit can also collect real-time viewing behavior such as operations and reactions during viewing. For example, the collection unit can collect the titles of videos watched by the user. The collection unit can also collect the viewing time of videos watched by the user. The collection unit can also collect the viewing frequency of videos watched by the user. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit analyzes viewing history, preferences, and real-time viewing behavior and provides recommended videos based on the user's preferences. For example, the analysis unit can analyze viewing history and identify genres that the user likes. The analysis unit can also analyze preferences and understand trends in videos rated by users. Furthermore, the analysis unit can analyze real-time viewing behavior and understand user reactions during viewing. The provision unit provides recommended videos based on the analysis results obtained by the analysis unit. For example, the provision unit can provide recommended videos based on user preferences. For example, the provision unit can prioritize providing videos in genres preferred by the user. Furthermore, the provision unit can provide videos related to videos rated by the user. Furthermore, the provision unit can also provide recommended videos based on user reactions during viewing. The subtitle generation unit analyzes the video's audio in real time and generates highly accurate subtitles. For example, the subtitle generation unit can analyze the video's audio using speech recognition technology and generate subtitles. For example, the subtitle generation unit can convert the video's audio to text using speech recognition technology. Furthermore, the subtitle generation unit can generate subtitles based on the generated text. Furthermore, the subtitle generation unit can analyze the video's audio in real time using speech recognition technology and generate highly accurate subtitles. The dialogue unit provides a dialogue function with the user.The dialogue unit, for example, analyzes the user's voice using speech recognition technology and engages in dialogue. The dialogue unit can, for example, convert the user's voice into text using speech recognition technology. The dialogue unit can also engage in dialogue based on the generated text. Furthermore, the dialogue unit can analyze the user's voice in real time using speech recognition technology and engage in dialogue. The management unit manages viewing history. The management unit manages videos that the user has watched in the past. The management unit can, for example, save the history of videos that the user has watched. Furthermore, the management unit can allow the user to revisit videos that they have watched in the past based on the saved history. Furthermore, the management unit can manage viewing history and allow the user to easily revisit videos that they have watched in the past. The two-way communication unit allows users to post live comments in real time. The two-way communication unit provides, for example, a function that allows users to post live comments while watching. The two-way communication unit allows users to input comments while watching and have them displayed in real time. Furthermore, the two-way communication unit allows users to communicate with other users while watching. Furthermore, the two-way communication unit can also allow users to post live comments in real time. This allows the AI ​​agent system according to the embodiment to improve the user's viewing experience.

[0030] The data collection unit collects viewing history, preferences, and real-time viewing behavior. Specifically, it collects viewing history such as the titles of videos watched by users, viewing time, and viewing frequency. This allows the system to understand what kinds of videos users prefer to watch. The data collection unit can also collect preferences such as genres estimated from videos rated by users and their viewing history. For example, it can analyze the genres and themes of videos that users have given high ratings to identify user preferences. Furthermore, the data collection unit can collect real-time viewing behavior such as actions taken while watching and reactions during viewing. For example, it collects actions such as pausing or rewinding videos, and posting comments while watching. This allows the system to understand what parts of a video users are interested in and where their attention is distracted. The data collection unit centrally manages this data and makes it accessible to the analysis and provisioning units. Data collection is carried out while protecting user privacy and is anonymized as needed. By adjusting the frequency and accuracy of data collection, the data collection unit can respond flexibly to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The analysis unit analyzes the data collected by the data collection unit. Specifically, it analyzes viewing history, preferences, and real-time viewing behavior to provide recommended videos based on user preferences. For example, it can analyze viewing history to identify genres that users like. From viewing history, it extracts genres and themes that users frequently watch and selects recommended videos based on this. It can also analyze preferences to understand the trends in videos that users have rated highly. It analyzes the characteristics of videos that users have given high ratings and recommends videos with similar characteristics. Furthermore, it can analyze real-time viewing behavior to understand users' reactions while watching. For example, it analyzes the frequency and timing of users pausing or rewinding videos to understand changes in their interests while watching. The analysis unit processes this data in real time using AI to quickly and accurately understand user preferences and viewing behavior. The AI ​​uses machine learning algorithms to analyze data and learn users' viewing patterns and preferences. This allows the analysis unit to provide information to offer users the most suitable recommended videos. Furthermore, the analysis unit can also utilize past data and statistical information to analyze long-term viewing trends and tendencies. This allows the analysis unit to not only grasp the situation in real time but also analyze long-term viewing trends, improving the reliability and accuracy of the entire system.

[0032] The service provider provides recommended videos based on the analysis results obtained by the analysis unit. Specifically, it provides recommended videos based on user preferences. For example, it can prioritize providing videos in genres that the user likes. Based on the user's preferences and viewing history identified by the analysis unit, it selects and presents highly relevant videos to the user. The service provider can also provide videos related to videos that the user has rated highly. By recommending videos in the same genre or theme as videos that the user has highly rated, it can continue to capture the user's interest. Furthermore, the service provider can also provide recommended videos based on the user's reactions while watching. For example, if the user pauses or rewinds at a specific scene while watching, it will recommend videos related to that scene. The service provider presents these recommended videos to the user at the appropriate time, improving the viewing experience. The service provider displays recommended videos in a visually appealing way through the user interface, making them easily accessible to the user. Furthermore, the service provider can collect user feedback and continuously improve the accuracy and relevance of the videos it provides. This allows the service provider to provide the user with the most suitable videos and improve the viewing experience.

[0033] The subtitle generation unit analyzes the video's audio in real time and generates highly accurate subtitles. Specifically, it uses speech recognition technology to analyze the video's audio and generate subtitles. Speech recognition technology is used to convert the video's audio into text. For example, it analyzes the video's audio in real time and extracts the audio content as text. The generated text is then displayed as subtitles. The subtitle generation unit can analyze the video's audio in real time using speech recognition technology and generate highly accurate subtitles. This makes it easier for users to understand the video's content. The subtitle generation unit can use machine learning algorithms to improve the accuracy of speech recognition technology. For example, it can train a speech recognition model using a large amount of audio data to improve the accuracy of speech recognition. Furthermore, the subtitle generation unit can evaluate the quality of the generated subtitles and make corrections as needed. This ensures that the accuracy and quality of the subtitles are maintained. The subtitle generation unit can also support multiple languages. For example, even if the video's audio is in a different language, it can generate subtitles in the corresponding language. This allows it to accommodate users who speak different languages ​​and improves the viewing experience.

[0034] The dialogue unit provides interaction functions with the user. Specifically, it analyzes the user's voice using speech recognition technology and engages in dialogue. The dialogue unit converts the user's voice into text and conducts dialogue based on that text. For example, if a user asks a question by voice, the dialogue unit analyzes the question and generates an appropriate answer. The dialogue unit can then conduct dialogue based on the generated text. It can analyze the user's voice in real time using speech recognition technology and conduct dialogue. The dialogue unit uses natural language processing technology to understand the user's intent and generate appropriate responses. For example, if a user asks a question about a specific video, the dialogue unit will provide information about that video. The dialogue unit can respond to user questions quickly and accurately. Furthermore, based on the user's past dialogue history, the dialogue unit can understand the user's preferences and interests and provide more personalized dialogue. Through dialogue with the user, the dialogue unit can improve the user's viewing experience.

[0035] The management department manages viewing history. Specifically, it manages videos that users have watched in the past. The management department saves the history of videos that users have watched and allows users to revisit videos they have watched in the past. For example, it saves information such as the title of the video the user has watched, the viewing time, and the viewing frequency. This allows users to easily revisit videos they have watched in the past. The management department centrally manages viewing history and allows users to search for videos they have watched in the past. For example, if a user wants to watch a particular video again, the management department will quickly search for that video and make it available to the user. Furthermore, the management department can analyze user preferences and viewing trends based on viewing history and provide information to the analytics department and the content delivery department. In this way, the management department can play an important role in improving the user's viewing experience.

[0036] The interactive communication section allows users to post live comments in real time. Specifically, it provides a function that allows users to post live comments while watching. Users can enter comments while watching and have them displayed in real time. This allows users to communicate with other viewers. The interactive communication section allows users to exchange opinions with other users while watching. For example, users can post their feelings and opinions as comments while watching and share them with other users. The interactive communication section improves the viewing experience by allowing users to post live comments in real time. Furthermore, the interactive communication section can analyze user comments and understand viewer reactions and opinions. This can be used to improve the overall system and develop new features. The interactive communication section can improve the viewing experience by allowing users to communicate with other users while watching.

[0037] The data collection unit can analyze the user's past viewing history and select the optimal data collection method. For example, the data collection unit can analyze the genres of videos the user has watched in the past and prioritize the collection of videos of similar genres. For example, the data collection unit can analyze the user's viewing times and determine the optimal data collection timing. The data collection unit can also analyze the user's viewing device and select the optimal data collection method for that device. In this way, the optimal data collection method can be selected by analyzing the user's past viewing history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's viewing history data into a generating AI and have the generating AI select the optimal data collection method.

[0038] The data collection unit can filter the collected viewing history based on the user's current viewing environment and device. For example, if the user is viewing on a smartphone, the data collection unit can adjust the amount of data collected considering mobile data usage. For example, if the user is viewing on a home Wi-Fi network, the data collection unit can prioritize collecting high-definition viewing history. Furthermore, if the user is viewing in a public place, the data collection unit can limit the data collected with privacy in mind. This allows for the collection of appropriate data by filtering based on the user's viewing environment and device. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's viewing environment data into a generating AI and have the generating AI perform the filtering.

[0039] The collection unit can prioritize the collection of highly relevant viewing history by considering the user's geographical location information when collecting viewing history. For example, if the user is in a specific region, the collection unit can prioritize the collection of viewing history of videos related to that region. For example, if the user is traveling, the collection unit can prioritize the collection of viewing history of videos related to the travel destination. Furthermore, if the user is at home, the collection unit can prioritize the collection of viewing history at home. In this way, by considering the user's geographical location information, highly relevant viewing history can be prioritized. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location information into a generating AI and have the generating AI select highly relevant viewing history.

[0040] The data collection unit can analyze the user's social media activity and collect relevant history when collecting viewing history. For example, the data collection unit can prioritize collecting viewing history of videos that the user has shared on social media. For example, the data collection unit can prioritize collecting viewing history of videos that the user has "liked" on social media. The data collection unit can also prioritize collecting viewing history of videos that the user has commented on on social media. In this way, relevant viewing history can be collected by analyzing the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's social media activity data into a generating AI and have the generating AI select relevant history.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the viewing history. For example, the analysis unit can perform a detailed analysis on important viewing history. For example, it can perform a simplified analysis on general viewing history. The analysis unit can also adjust the level of detail of the analysis based on the user's preferences. This allows for the provision of appropriate analysis results by adjusting the level of detail of the analysis based on the importance of the viewing history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input viewing history data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0042] The analysis unit can apply different analysis algorithms depending on the category of the viewing history during analysis. For example, the analysis unit can apply an analysis algorithm specifically for entertainment to entertainment-related viewing history. For example, the analysis unit can apply an analysis algorithm specifically for education-related viewing history. Furthermore, the analysis unit can apply a news-specific analysis algorithm to news-related viewing history. By applying different analysis algorithms depending on the category of viewing history, appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input viewing history data into a generating AI and have the generating AI execute the application of different analysis algorithms.

[0043] The analysis unit can determine the priority of analysis based on when the viewing history was submitted. For example, the analysis unit may prioritize analyzing recent viewing history. For example, the analysis unit may prioritize analyzing the viewing history of a user during a specific period. The analysis unit can also determine the priority of analysis based on the user's viewing pattern. This allows for the provision of appropriate analysis results by determining the priority of analysis based on when the viewing history was submitted. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input viewing history data into a generating AI and have the generating AI perform the determination of the analysis priority.

[0044] The analysis unit can adjust the order of analysis based on the relevance of viewing history during the analysis process. For example, the analysis unit may prioritize the analysis of highly relevant viewing history. For example, the analysis unit may postpone the analysis of less relevant viewing history. The analysis unit can also adjust the order of analysis based on user preferences. This allows for the provision of appropriate analysis results by adjusting the order of analysis based on the relevance of viewing history. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input viewing history data into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0045] The service provider can adjust the level of detail provided based on the importance of the video at the time of delivery. For example, the service provider can provide detailed information for important videos, and concise information for general videos. The service provider can also adjust the level of detail based on user preferences. This allows for the provision of appropriate information by adjusting the level of detail based on the importance of the video. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail.

[0046] The distribution unit can apply different distribution algorithms depending on the video category at the time of distribution. For example, the distribution unit can apply an entertainment-specific distribution algorithm to entertainment videos. For example, the distribution unit can apply an education-specific distribution algorithm to educational videos. Furthermore, the distribution unit can apply a news-specific distribution algorithm to news videos. In this way, appropriate videos can be provided by applying different distribution algorithms depending on the video category. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without using AI. For example, the distribution unit can input video category data into a generating AI and have the generating AI execute the application of different distribution algorithms.

[0047] The distribution unit can determine the priority of video distribution based on the submission date of the videos at the time of distribution. For example, the distribution unit may prioritize the distribution of recent videos. For example, the distribution unit may prioritize the distribution of videos that the user has watched during a specific period. The distribution unit may also determine the priority of distribution based on the user's viewing patterns. This allows for the provision of appropriate videos by determining the priority of distribution based on the submission date of the videos. Some or all of the above processing in the distribution unit may be performed using AI, for example, or not using AI. For example, the distribution unit may input video submission date data into a generating AI and have the generating AI perform the determination of the distribution priority.

[0048] The distribution unit can adjust the order of video distribution based on the relevance of the videos at the time of distribution. For example, the distribution unit may prioritize the distribution of highly relevant videos. For example, the distribution unit may postpone the distribution of less relevant videos. The distribution unit can also adjust the order of distribution based on user preferences. In this way, appropriate videos can be provided by adjusting the order of distribution based on the relevance of the videos. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input video relevance data into a generating AI and have the generating AI perform the adjustment of the distribution order.

[0049] The subtitle generation unit can adjust the level of detail of subtitles based on the importance of the audio in the video during subtitle generation. For example, the subtitle generation unit can provide detailed subtitles for important audio, and concise subtitles for general audio. The subtitle generation unit can also adjust the level of detail of subtitles based on user preferences. This allows for the provision of appropriate subtitles by adjusting the level of detail based on the importance of the audio in the video. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input audio importance data into a generation AI and have the generation AI perform the adjustment of the level of detail of the subtitles.

[0050] The subtitle generation unit can apply different subtitle generation algorithms depending on the video category when generating subtitles. For example, the subtitle generation unit can apply an entertainment-specific subtitle generation algorithm to entertainment videos. For example, the subtitle generation unit can apply an education-specific subtitle generation algorithm to educational videos. Furthermore, the subtitle generation unit can apply a news-specific subtitle generation algorithm to news videos. By applying different subtitle generation algorithms depending on the video category, appropriate subtitles can be provided. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input video category data into a generation AI and cause the generation AI to execute the application of different subtitle generation algorithms.

[0051] The subtitle generation unit can determine the priority of subtitles based on the video submission date when generating subtitles. For example, the subtitle generation unit can prioritize subtitle generation for recent videos. For example, the subtitle generation unit can prioritize subtitle generation for videos that the user has watched within a specific period. The subtitle generation unit can also determine the priority of subtitles based on the user's viewing patterns. This allows for the provision of appropriate subtitles by determining the priority of subtitles based on the video submission date. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input video submission date data into a generation AI and have the generation AI perform the determination of subtitle priority.

[0052] The subtitle generation unit can adjust the order of subtitles based on the relevance of the videos during subtitle generation. For example, the subtitle generation unit can prioritize generating subtitles for highly relevant videos. For example, the subtitle generation unit can postpone generating subtitles for less relevant videos. The subtitle generation unit can also adjust the order of subtitles based on user preferences. This allows for the provision of appropriate subtitles by adjusting the order of subtitles based on the relevance of the videos. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input video relevance data into a generation AI and have the generation AI perform the adjustment of the subtitle order.

[0053] The dialogue unit can select the optimal dialogue method by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can select the optimal dialogue method based on the user's preferred dialogue style in the past. For example, the dialogue unit can prioritize incorporating preferred topics into the conversation from the user's past dialogue history. The dialogue unit can also analyze the user's past dialogue history and select the most effective dialogue method. In this way, the optimal dialogue method can be selected by referring to the user's past dialogue history. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input the user's dialogue history data into a generating AI and have the generating AI perform the selection of the optimal dialogue method.

[0054] The dialogue unit can customize the means of dialogue based on the user's current situation during a conversation. For example, if the user is on the move, the dialogue unit may prioritize voice dialogue. For example, if the user is in a quiet environment, the dialogue unit may prioritize text dialogue. The dialogue unit may also prioritize short conversations if the user is busy. In this way, by customizing the means of dialogue based on the user's current situation, an appropriate conversation can be provided. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input the user's current situation data into a generating AI and have the generating AI perform the customization of the means of dialogue.

[0055] The dialogue unit can select the optimal dialogue method during a conversation by considering the user's geographical location. For example, if the user is in a specific region, the dialogue unit can engage in a conversation on topics related to that region. If the user is traveling, the dialogue unit can engage in a conversation on topics related to the travel destination. Furthermore, if the user is at home, the dialogue unit can engage in a conversation on topics related to activities at home. In this way, the optimal dialogue method can be selected by considering the user's geographical location. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input the user's geographical location data into a generating AI and have the generating AI select the optimal dialogue method.

[0056] The dialogue unit can analyze the user's social media activity during a conversation and propose a means of dialogue. For example, the dialogue unit can conduct a conversation based on what the user has shared on social media. For example, the dialogue unit can conduct a conversation based on what the user has "liked" on social media. Furthermore, the dialogue unit can conduct a conversation based on what the user has commented on social media. In this way, by analyzing the user's social media activity, it can propose an appropriate means of dialogue. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input the user's social media activity data into a generating AI and have the generating AI propose a means of dialogue.

[0057] The management unit can select the optimal management method by referring to the user's past viewing history during management. For example, the management unit can select the optimal management method based on the genre of videos the user has watched in the past. For example, the management unit can select the optimal management method based on the user's viewing time. Furthermore, the management unit can also select the optimal management method based on the user's viewing device. In this way, the optimal management method can be selected by referring to the user's past viewing history. Some or all of the above processing in the management unit may be performed using AI, for example, or without AI. For example, the management unit can input the user's viewing history data into a generating AI and have the generating AI perform the selection of the optimal management method.

[0058] The management unit can customize management methods based on the user's current viewing environment during management. For example, if the user is viewing on a smartphone, the management unit can adjust the management method considering mobile data usage. For example, if the user is viewing in a home Wi-Fi environment, the management unit can prioritize managing high-definition viewing history. Furthermore, if the user is viewing in a public place, the management unit can adjust the management method considering privacy. This allows for appropriate management by customizing management methods based on the user's current viewing environment. Some or all of the above processing in the management unit may be performed using AI, for example, or not using AI. For example, the management unit can input user viewing environment data into a generating AI and have the generating AI perform the customization of management methods.

[0059] The management unit can select the optimal management method by considering the user's geographical location information during management. For example, if the user is in a specific region, the management unit can prioritize managing the viewing history of videos related to that region. For example, if the user is traveling, the management unit can prioritize managing the viewing history of videos related to the travel destination. Furthermore, if the user is at home, the management unit can prioritize managing the viewing history at home. In this way, the optimal management method can be selected by considering the user's geographical location information. Some or all of the above processing in the management unit may be performed using AI, for example, or without AI. For example, the management unit can input the user's geographical location information data into a generating AI and have the generating AI select the optimal management method.

[0060] The management department can analyze users' social media activity and propose management methods during management. For example, the management department can prioritize managing the viewing history of videos that users have shared on social media. For example, the management department can prioritize managing the viewing history of videos that users have "liked" on social media. Furthermore, the management department can also prioritize managing the viewing history of videos that users have commented on on social media. In this way, by analyzing users' social media activity, appropriate management methods can be proposed. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input user social media activity data into a generating AI and have the generating AI execute proposals for management methods.

[0061] The interactive communication unit can select the optimal display method when displaying live comments by referring to the user's past comment history. For example, the interactive communication unit can select the optimal display method based on the comment style the user has preferred in the past. For example, the interactive communication unit can prioritize displaying the user's preferred topics from the user's past comment history. The interactive communication unit can also analyze the user's past comment history and select the most effective display method. In this way, the optimal display method for live comments can be selected by referring to the user's past comment history. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input the user's comment history data into a generating AI and have the generating AI select the optimal display method.

[0062] The interactive communication unit can customize the display method for live comments based on the user's current viewing environment. For example, if the user is viewing on a smartphone, the interactive communication unit can provide a live comment display method that is adapted to the screen size. For example, if the user is viewing on a tablet, the interactive communication unit can provide a live comment display method optimized for a larger screen. Furthermore, if the user is viewing on a smart TV, the interactive communication unit can provide a live comment display method that is highly visible. In this way, appropriate live comments can be provided by customizing the display method based on the user's current viewing environment. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input the user's viewing environment data into a generating AI and have the generating AI perform the customization of the display method.

[0063] The interactive communication unit can select the optimal display method for live comments by considering the user's geographical location information. For example, if the user is in a specific region, the interactive communication unit can prioritize displaying live comments related to that region. For example, if the user is traveling, the interactive communication unit can prioritize displaying live comments related to the travel destination. Furthermore, if the user is at home, the interactive communication unit can prioritize displaying live comments related to viewing at home. In this way, the optimal display method for live comments can be selected by considering the user's geographical location information. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input the user's geographical location information data into a generating AI and have the generating AI select the optimal display method.

[0064] The interactive communication unit can analyze the user's social media activity and suggest display methods when displaying live comments. For example, the interactive communication unit can display live comments based on content shared by the user on social media. For example, the interactive communication unit can display live comments based on content "liked" by the user on social media. Furthermore, the interactive communication unit can also display live comments based on content commented by the user on social media. In this way, by analyzing the user's social media activity, it is possible to suggest appropriate means of displaying live comments. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input the user's social media activity data into a generating AI and have the generating AI execute suggestions for display methods.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] The data collection unit can analyze the content of videos watched by users based on their viewing history and optimize the method of collecting viewing history. For example, the data collection unit can analyze the genre and theme of videos watched by users and prioritize the collection of videos of similar genres and themes. It can also analyze the viewing time and frequency of videos watched by users and prioritize the collection of videos with long viewing times or high viewing frequencies. Furthermore, the data collection unit can analyze the ratings and comments on videos watched by users and prioritize the collection of videos with many high ratings and positive comments. In this way, the data collection unit can optimize the method of collecting viewing history based on the user's viewing history.

[0067] The analytics unit can analyze a user's viewing history and identify patterns in that history. For example, if a user tends to watch videos during a specific time period, the analytics unit can prioritize analyzing videos related to that time period. Furthermore, if a user prefers videos of a particular genre or theme, the analytics unit can prioritize analyzing videos related to that genre or theme. Additionally, if a user tends to watch videos on a specific device, the analytics unit can prioritize analyzing videos optimized for that device. This allows the analytics unit to identify patterns in a user's viewing history and optimize its analysis methods.

[0068] The service provider can optimize the content of videos offered based on the user's viewing history. For example, it can analyze the genres and themes of videos the user has watched and prioritize providing videos of similar genres and themes. It can also analyze the viewing time and frequency of videos the user has watched and prioritize providing videos with long viewing times or high viewing frequencies. Furthermore, it can analyze the ratings and comments on videos the user has watched and prioritize providing videos with many high ratings and positive comments. In this way, the service provider can optimize the content of videos offered based on the user's viewing history.

[0069] The subtitle generation unit can optimize the subtitle generation method based on the user's viewing history. For example, the subtitle generation unit can analyze the genre and theme of videos the user has watched and generate optimal subtitles for videos of similar genres and themes. It can also analyze the viewing time and frequency of videos the user has watched and generate optimal subtitles for videos with long viewing times or high viewing frequency. Furthermore, the subtitle generation unit can analyze the ratings and comments on videos the user has watched and generate optimal subtitles for videos with many high ratings and positive comments. In this way, the subtitle generation unit can optimize the subtitle generation method based on the user's viewing history.

[0070] The dialogue unit can optimize the content of conversations based on the user's viewing history. For example, the dialogue unit can analyze the genre and theme of videos the user has watched and provide conversations related to similar genres and themes. It can also analyze the viewing time and frequency of videos the user has watched and provide conversations related to videos with long viewing times or high viewing frequency. Furthermore, the dialogue unit can analyze the ratings and comments on videos the user has watched and provide conversations related to videos with many high ratings and positive comments. In this way, the dialogue unit can optimize the content of conversations based on the user's viewing history.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The data collection unit collects viewing history, preferences, and real-time viewing behavior. For example, it collects viewing history such as the titles of videos the user has watched, viewing time, and viewing frequency, as well as preferences such as videos the user has rated and genres estimated from the viewing history. It also collects real-time viewing behavior such as actions taken while watching and reactions while watching. Step 2: The analysis unit analyzes the data collected by the collection unit. For example, it analyzes viewing history, preferences, and real-time viewing behavior to generate information for providing recommended videos based on user preferences. Step 3: The provisioning unit provides recommended videos based on the analysis results obtained by the analysis unit. For example, it provides recommended videos based on the user's preferences, prioritizing videos in genres the user likes. Step 4: The subtitle generation unit analyzes the video's audio in real time and generates highly accurate subtitles. For example, it uses speech recognition technology to convert the video's audio into text, and then generates subtitles based on the generated text. Step 5: The dialogue unit provides a function for interacting with the user. For example, it analyzes the user's voice using speech recognition technology and engages in dialogue. Step 6: The management department manages viewing history. For example, it saves a history of videos that users have watched in the past and allows users to revisit videos they have watched previously. Step 7: The interactive communication section will enable users to post live comments in real time. For example, it will provide a function that allows users to enter comments while watching and have them displayed in real time.

[0073] (Example of form 2) An AI agent system for improving the user experience of a video distribution platform according to an embodiment of the present invention is a system that collects viewing history, preferences, and real-time viewing behavior, and provides the user with the most suitable recommended videos by analyzing this data with AI. The AI ​​agent system collects viewing history, preferences, and real-time viewing behavior, and provides the user with the most suitable recommended videos by analyzing this data with AI. Furthermore, the AI ​​agent system is equipped with an automatic subtitle generation function, which analyzes the audio of videos in real time and generates highly accurate subtitles. In addition, the AI ​​agent system provides a dialogue function with the user by utilizing speech recognition technology. Furthermore, the AI ​​agent system is equipped with a viewing history management function, which allows users to easily revisit videos they have watched in the past. Finally, the AI ​​agent system provides a two-way communication function, which allows users to post live comments in real time. Thus, the AI ​​agent system is a multi-functional system for improving the user's viewing experience and can increase engagement on the video distribution platform. For example, the AI ​​agent system collects the user's viewing history, preferences, and real-time viewing behavior, and provides the user with the most suitable recommended videos by analyzing this data with AI. For example, the AI ​​agent system analyzes the audio of videos in real time and generates highly accurate subtitles. For example, an AI agent system can utilize speech recognition technology to provide conversational capabilities with users. For example, an AI agent system can have a viewing history management function, allowing users to easily revisit videos they have previously watched. For example, an AI agent system can provide two-way communication capabilities, enabling users to post live comments in real time. In this way, the AI ​​agent system can improve the user's viewing experience.

[0074] The AI ​​agent system according to this embodiment comprises a collection unit, an analysis unit, a provision unit, a subtitle generation unit, a dialogue unit, a management unit, and a two-way communication unit. The collection unit collects viewing history, preferences, and real-time viewing behavior. For example, the collection unit collects viewing history such as the titles, viewing time, and viewing frequency of videos watched by the user. The collection unit can also collect preferences such as videos rated by the user and genres estimated from viewing history. Furthermore, the collection unit can also collect real-time viewing behavior such as operations and reactions during viewing. For example, the collection unit can collect the titles of videos watched by the user. The collection unit can also collect the viewing time of videos watched by the user. The collection unit can also collect the viewing frequency of videos watched by the user. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit analyzes viewing history, preferences, and real-time viewing behavior and provides recommended videos based on the user's preferences. For example, the analysis unit can analyze viewing history and identify genres that the user likes. The analysis unit can also analyze preferences and understand trends in videos rated by users. Furthermore, the analysis unit can analyze real-time viewing behavior and understand user reactions during viewing. The provision unit provides recommended videos based on the analysis results obtained by the analysis unit. For example, the provision unit can provide recommended videos based on user preferences. For example, the provision unit can prioritize providing videos in genres preferred by the user. Furthermore, the provision unit can provide videos related to videos rated by the user. Furthermore, the provision unit can also provide recommended videos based on user reactions during viewing. The subtitle generation unit analyzes the video's audio in real time and generates highly accurate subtitles. For example, the subtitle generation unit can analyze the video's audio using speech recognition technology and generate subtitles. For example, the subtitle generation unit can convert the video's audio to text using speech recognition technology. Furthermore, the subtitle generation unit can generate subtitles based on the generated text. Furthermore, the subtitle generation unit can analyze the video's audio in real time using speech recognition technology and generate highly accurate subtitles. The dialogue unit provides a dialogue function with the user.The dialogue unit, for example, analyzes the user's voice using speech recognition technology and engages in dialogue. The dialogue unit can, for example, convert the user's voice into text using speech recognition technology. The dialogue unit can also engage in dialogue based on the generated text. Furthermore, the dialogue unit can analyze the user's voice in real time using speech recognition technology and engage in dialogue. The management unit manages viewing history. The management unit manages videos that the user has watched in the past. The management unit can, for example, save the history of videos that the user has watched. Furthermore, the management unit can allow the user to revisit videos that they have watched in the past based on the saved history. Furthermore, the management unit can manage viewing history and allow the user to easily revisit videos that they have watched in the past. The two-way communication unit allows users to post live comments in real time. The two-way communication unit provides, for example, a function that allows users to post live comments while watching. The two-way communication unit allows users to input comments while watching and have them displayed in real time. Furthermore, the two-way communication unit allows users to communicate with other users while watching. Furthermore, the two-way communication unit can also allow users to post live comments in real time. This allows the AI ​​agent system according to the embodiment to improve the user's viewing experience.

[0075] The data collection unit collects viewing history, preferences, and real-time viewing behavior. Specifically, it collects viewing history such as the titles of videos watched by users, viewing time, and viewing frequency. This allows the system to understand what kinds of videos users prefer to watch. The data collection unit can also collect preferences such as genres estimated from videos rated by users and their viewing history. For example, it can analyze the genres and themes of videos that users have given high ratings to identify user preferences. Furthermore, the data collection unit can collect real-time viewing behavior such as actions taken while watching and reactions during viewing. For example, it collects actions such as pausing or rewinding videos, and posting comments while watching. This allows the system to understand what parts of a video users are interested in and where their attention is distracted. The data collection unit centrally manages this data and makes it accessible to the analysis and provisioning units. Data collection is carried out while protecting user privacy and is anonymized as needed. By adjusting the frequency and accuracy of data collection, the data collection unit can respond flexibly to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0076] The analysis unit analyzes the data collected by the data collection unit. Specifically, it analyzes viewing history, preferences, and real-time viewing behavior to provide recommended videos based on user preferences. For example, it can analyze viewing history to identify genres that users like. From viewing history, it extracts genres and themes that users frequently watch and selects recommended videos based on this. It can also analyze preferences to understand the trends in videos that users have rated highly. It analyzes the characteristics of videos that users have given high ratings and recommends videos with similar characteristics. Furthermore, it can analyze real-time viewing behavior to understand users' reactions while watching. For example, it analyzes the frequency and timing of users pausing or rewinding videos to understand changes in their interests while watching. The analysis unit processes this data in real time using AI to quickly and accurately understand user preferences and viewing behavior. The AI ​​uses machine learning algorithms to analyze data and learn users' viewing patterns and preferences. This allows the analysis unit to provide information to offer users the most suitable recommended videos. Furthermore, the analysis unit can also utilize past data and statistical information to analyze long-term viewing trends and tendencies. This allows the analysis unit to not only grasp the situation in real time but also analyze long-term viewing trends, improving the reliability and accuracy of the entire system.

[0077] The service provider provides recommended videos based on the analysis results obtained by the analysis unit. Specifically, it provides recommended videos based on user preferences. For example, it can prioritize providing videos in genres that the user likes. Based on the user's preferences and viewing history identified by the analysis unit, it selects and presents highly relevant videos to the user. The service provider can also provide videos related to videos that the user has rated highly. By recommending videos in the same genre or theme as videos that the user has highly rated, it can continue to capture the user's interest. Furthermore, the service provider can also provide recommended videos based on the user's reactions while watching. For example, if the user pauses or rewinds at a specific scene while watching, it will recommend videos related to that scene. The service provider presents these recommended videos to the user at the appropriate time, improving the viewing experience. The service provider displays recommended videos in a visually appealing way through the user interface, making them easily accessible to the user. Furthermore, the service provider can collect user feedback and continuously improve the accuracy and relevance of the videos it provides. This allows the service provider to provide the user with the most suitable videos and improve the viewing experience.

[0078] The subtitle generation unit analyzes the video's audio in real time and generates highly accurate subtitles. Specifically, it uses speech recognition technology to analyze the video's audio and generate subtitles. Speech recognition technology is used to convert the video's audio into text. For example, it analyzes the video's audio in real time and extracts the audio content as text. The generated text is then displayed as subtitles. The subtitle generation unit can analyze the video's audio in real time using speech recognition technology and generate highly accurate subtitles. This makes it easier for users to understand the video's content. The subtitle generation unit can use machine learning algorithms to improve the accuracy of speech recognition technology. For example, it can train a speech recognition model using a large amount of audio data to improve the accuracy of speech recognition. Furthermore, the subtitle generation unit can evaluate the quality of the generated subtitles and make corrections as needed. This ensures that the accuracy and quality of the subtitles are maintained. The subtitle generation unit can also support multiple languages. For example, even if the video's audio is in a different language, it can generate subtitles in the corresponding language. This allows it to accommodate users who speak different languages ​​and improves the viewing experience.

[0079] The dialogue unit provides interaction functions with the user. Specifically, it analyzes the user's voice using speech recognition technology and engages in dialogue. The dialogue unit converts the user's voice into text and conducts dialogue based on that text. For example, if a user asks a question by voice, the dialogue unit analyzes the question and generates an appropriate answer. The dialogue unit can then conduct dialogue based on the generated text. It can analyze the user's voice in real time using speech recognition technology and conduct dialogue. The dialogue unit uses natural language processing technology to understand the user's intent and generate appropriate responses. For example, if a user asks a question about a specific video, the dialogue unit will provide information about that video. The dialogue unit can respond to user questions quickly and accurately. Furthermore, based on the user's past dialogue history, the dialogue unit can understand the user's preferences and interests and provide more personalized dialogue. Through dialogue with the user, the dialogue unit can improve the user's viewing experience.

[0080] The management department manages viewing history. Specifically, it manages videos that users have watched in the past. The management department saves the history of videos that users have watched and allows users to revisit videos they have watched in the past. For example, it saves information such as the title of the video the user has watched, the viewing time, and the viewing frequency. This allows users to easily revisit videos they have watched in the past. The management department centrally manages viewing history and allows users to search for videos they have watched in the past. For example, if a user wants to watch a particular video again, the management department will quickly search for that video and make it available to the user. Furthermore, the management department can analyze user preferences and viewing trends based on viewing history and provide information to the analytics department and the content delivery department. In this way, the management department can play an important role in improving the user's viewing experience.

[0081] The interactive communication section allows users to post live comments in real time. Specifically, it provides a function that allows users to post live comments while watching. Users can enter comments while watching and have them displayed in real time. This allows users to communicate with other viewers. The interactive communication section allows users to exchange opinions with other users while watching. For example, users can post their feelings and opinions as comments while watching and share them with other users. The interactive communication section improves the viewing experience by allowing users to post live comments in real time. Furthermore, the interactive communication section can analyze user comments and understand viewer reactions and opinions. This can be used to improve the overall system and develop new features. The interactive communication section can improve the viewing experience by allowing users to communicate with other users while watching.

[0082] The data collection unit can estimate the user's emotions and adjust the timing of viewing history collection based on the estimated emotions. For example, if the user is relaxed, the data collection unit can collect viewing history frequently and gather detailed data. For example, if the user is stressed, the data collection unit can reduce the amount of viewing history collected to lessen the user's burden. Furthermore, if the user is excited, the data collection unit can collect viewing history in real time to obtain immediate data. This reduces the user's burden by adjusting the timing of viewing history collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0083] The data collection unit can analyze the user's past viewing history and select the optimal data collection method. For example, the data collection unit can analyze the genres of videos the user has watched in the past and prioritize the collection of videos of similar genres. For example, the data collection unit can analyze the user's viewing times and determine the optimal data collection timing. The data collection unit can also analyze the user's viewing device and select the optimal data collection method for that device. In this way, the optimal data collection method can be selected by analyzing the user's past viewing history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's viewing history data into a generating AI and have the generating AI select the optimal data collection method.

[0084] The data collection unit can filter the collected viewing history based on the user's current viewing environment and device. For example, if the user is viewing on a smartphone, the data collection unit can adjust the amount of data collected considering mobile data usage. For example, if the user is viewing on a home Wi-Fi network, the data collection unit can prioritize collecting high-definition viewing history. Furthermore, if the user is viewing in a public place, the data collection unit can limit the data collected with privacy in mind. This allows for the collection of appropriate data by filtering based on the user's viewing environment and device. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's viewing environment data into a generating AI and have the generating AI perform the filtering.

[0085] The data collection unit can estimate the user's emotions and determine the priority of viewing history to collect based on the estimated emotions. For example, if the user is relaxed, the data collection unit may prioritize collecting entertainment-related viewing history. If the user is stressed, the data collection unit may prioritize collecting viewing history of relaxing videos. Furthermore, if the user is excited, the data collection unit may prioritize collecting action-oriented viewing history. This allows for the collection of more appropriate data by prioritizing viewing history according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0086] The collection unit can prioritize the collection of highly relevant viewing history by considering the user's geographical location information when collecting viewing history. For example, if the user is in a specific region, the collection unit can prioritize the collection of viewing history of videos related to that region. For example, if the user is traveling, the collection unit can prioritize the collection of viewing history of videos related to the travel destination. Furthermore, if the user is at home, the collection unit can prioritize the collection of viewing history at home. In this way, by considering the user's geographical location information, highly relevant viewing history can be prioritized. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location information into a generating AI and have the generating AI select highly relevant viewing history.

[0087] The data collection unit can analyze the user's social media activity and collect relevant history when collecting viewing history. For example, the data collection unit can prioritize collecting viewing history of videos that the user has shared on social media. For example, the data collection unit can prioritize collecting viewing history of videos that the user has "liked" on social media. The data collection unit can also prioritize collecting viewing history of videos that the user has commented on on social media. In this way, relevant viewing history can be collected by analyzing the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's social media activity data into a generating AI and have the generating AI select relevant history.

[0088] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. If the user is stressed, the analysis unit can provide concise analysis results. Furthermore, if the user is excited, the analysis unit can provide visually stimulating analysis results. In this way, by adjusting the presentation of the analysis according to the user's emotions, the analysis unit can provide analysis results that are appropriate for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0089] The analysis unit can adjust the level of detail of the analysis based on the importance of the viewing history. For example, the analysis unit can perform a detailed analysis on important viewing history. For example, it can perform a simplified analysis on general viewing history. The analysis unit can also adjust the level of detail of the analysis based on the user's preferences. This allows for the provision of appropriate analysis results by adjusting the level of detail of the analysis based on the importance of the viewing history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input viewing history data into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0090] The analysis unit can apply different analysis algorithms depending on the category of the viewing history during analysis. For example, the analysis unit can apply an analysis algorithm specifically for entertainment to entertainment-related viewing history. For example, the analysis unit can apply an analysis algorithm specifically for education-related viewing history. Furthermore, the analysis unit can apply a news-specific analysis algorithm to news-related viewing history. By applying different analysis algorithms depending on the category of viewing history, appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input viewing history data into a generating AI and have the generating AI execute the application of different analysis algorithms.

[0091] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and provide a longer analysis result. If the user is stressed, for example, the analysis unit can perform a concise analysis and provide a shorter analysis result. Furthermore, if the user is excited, the analysis unit can perform a visually stimulating analysis and provide an analysis result of an appropriate length. In this way, by adjusting the length of the analysis according to the user's emotions, an analysis result suitable for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0092] The analysis unit can determine the priority of analysis based on when the viewing history was submitted. For example, the analysis unit may prioritize analyzing recent viewing history. For example, the analysis unit may prioritize analyzing the viewing history of a user during a specific period. The analysis unit can also determine the priority of analysis based on the user's viewing pattern. This allows for the provision of appropriate analysis results by determining the priority of analysis based on when the viewing history was submitted. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input viewing history data into a generating AI and have the generating AI perform the determination of the analysis priority.

[0093] The analysis unit can adjust the order of analysis based on the relevance of viewing history during the analysis process. For example, the analysis unit may prioritize the analysis of highly relevant viewing history. For example, the analysis unit may postpone the analysis of less relevant viewing history. The analysis unit can also adjust the order of analysis based on user preferences. This allows for the provision of appropriate analysis results by adjusting the order of analysis based on the relevance of viewing history. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input viewing history data into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0094] The service provider can estimate the user's emotions and adjust the presentation of the video based on the estimated emotions. For example, if the user is relaxed, the service provider can provide a video that progresses at a relaxed pace. If the user is stressed, the service provider can provide a video with a relaxing effect. Furthermore, if the user is excited, the service provider can provide a visually stimulating video. In this way, by adjusting the presentation of the video according to the user's emotions, the service provider can provide a video that is suitable for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0095] The service provider can adjust the level of detail provided based on the importance of the video at the time of delivery. For example, the service provider can provide detailed information for important videos, and concise information for general videos. The service provider can also adjust the level of detail based on user preferences. This allows for the provision of appropriate information by adjusting the level of detail based on the importance of the video. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail.

[0096] The distribution unit can apply different distribution algorithms depending on the video category at the time of distribution. For example, the distribution unit can apply an entertainment-specific distribution algorithm to entertainment videos. For example, the distribution unit can apply an education-specific distribution algorithm to educational videos. Furthermore, the distribution unit can apply a news-specific distribution algorithm to news videos. In this way, appropriate videos can be provided by applying different distribution algorithms depending on the video category. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without using AI. For example, the distribution unit can input video category data into a generating AI and have the generating AI execute the application of different distribution algorithms.

[0097] The service provider can estimate the user's emotions and adjust the length of the video provided based on the estimated emotions. For example, if the user is relaxed, the service provider can provide a longer video. If the user is stressed, the service provider can provide a shorter video. The service provider can also provide a video of an appropriate length if the user is excited. In this way, by adjusting the length of the video provided according to the user's emotions, the service provider can provide a video that is suitable for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0098] The distribution unit can determine the priority of video distribution based on the submission date of the videos at the time of distribution. For example, the distribution unit may prioritize the distribution of recent videos. For example, the distribution unit may prioritize the distribution of videos that the user has watched during a specific period. The distribution unit may also determine the priority of distribution based on the user's viewing patterns. This allows for the provision of appropriate videos by determining the priority of distribution based on the submission date of the videos. Some or all of the above processing in the distribution unit may be performed using AI, for example, or not using AI. For example, the distribution unit may input video submission date data into a generating AI and have the generating AI perform the determination of the distribution priority.

[0099] The distribution unit can adjust the order of video distribution based on the relevance of the videos at the time of distribution. For example, the distribution unit may prioritize the distribution of highly relevant videos. For example, the distribution unit may postpone the distribution of less relevant videos. The distribution unit can also adjust the order of distribution based on user preferences. In this way, appropriate videos can be provided by adjusting the order of distribution based on the relevance of the videos. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input video relevance data into a generating AI and have the generating AI perform the adjustment of the distribution order.

[0100] The subtitle generation unit can estimate the user's emotions and adjust the subtitle presentation based on the estimated emotions. For example, if the user is relaxed, the subtitle generation unit can provide subtitles that proceed at a leisurely pace. If the user is stressed, the subtitle generation unit can provide concise and highly legible subtitles. Furthermore, if the user is excited, the subtitle generation unit can provide visually stimulating subtitles. In this way, by adjusting the subtitle presentation according to the user's emotions, subtitles suitable for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0101] The subtitle generation unit can adjust the level of detail of subtitles based on the importance of the audio in the video during subtitle generation. For example, the subtitle generation unit can provide detailed subtitles for important audio, and concise subtitles for general audio. The subtitle generation unit can also adjust the level of detail of subtitles based on user preferences. This allows for the provision of appropriate subtitles by adjusting the level of detail based on the importance of the audio in the video. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input audio importance data into a generation AI and have the generation AI perform the adjustment of the level of detail of the subtitles.

[0102] The subtitle generation unit can apply different subtitle generation algorithms depending on the video category when generating subtitles. For example, the subtitle generation unit can apply an entertainment-specific subtitle generation algorithm to entertainment videos. For example, the subtitle generation unit can apply an education-specific subtitle generation algorithm to educational videos. Furthermore, the subtitle generation unit can apply a news-specific subtitle generation algorithm to news videos. By applying different subtitle generation algorithms depending on the video category, appropriate subtitles can be provided. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input video category data into a generation AI and cause the generation AI to execute the application of different subtitle generation algorithms.

[0103] The subtitle generation unit can estimate the user's emotions and adjust the length of the subtitles based on the estimated emotions. For example, if the user is relaxed, the subtitle generation unit can provide longer subtitles. For example, if the user is stressed, the subtitle generation unit can provide shorter subtitles. Furthermore, if the user is excited, the subtitle generation unit can provide subtitles of an appropriate length. In this way, by adjusting the length of the subtitles according to the user's emotions, subtitles suitable for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0104] The subtitle generation unit can determine the priority of subtitles based on the video submission date when generating subtitles. For example, the subtitle generation unit can prioritize subtitle generation for recent videos. For example, the subtitle generation unit can prioritize subtitle generation for videos that the user has watched within a specific period. The subtitle generation unit can also determine the priority of subtitles based on the user's viewing patterns. This allows for the provision of appropriate subtitles by determining the priority of subtitles based on the video submission date. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input video submission date data into a generation AI and have the generation AI perform the determination of subtitle priority.

[0105] The subtitle generation unit can adjust the order of subtitles based on the relevance of the videos during subtitle generation. For example, the subtitle generation unit can prioritize generating subtitles for highly relevant videos. For example, the subtitle generation unit can postpone generating subtitles for less relevant videos. The subtitle generation unit can also adjust the order of subtitles based on user preferences. This allows for the provision of appropriate subtitles by adjusting the order of subtitles based on the relevance of the videos. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input video relevance data into a generation AI and have the generation AI perform the adjustment of the subtitle order.

[0106] The dialogue unit can estimate the user's emotions and adjust the way the dialogue is presented based on the estimated emotions. For example, if the user is relaxed, the dialogue unit will engage in a relaxed conversation. If the user is stressed, the dialogue unit can engage in a concise and visually clear conversation. If the user is excited, the dialogue unit can also engage in a visually stimulating conversation. In this way, by adjusting the way the dialogue is presented according to the user's emotions, a conversation suitable for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0107] The dialogue unit can select the optimal dialogue method by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can select the optimal dialogue method based on the user's preferred dialogue style in the past. For example, the dialogue unit can prioritize incorporating preferred topics into the conversation from the user's past dialogue history. The dialogue unit can also analyze the user's past dialogue history and select the most effective dialogue method. In this way, the optimal dialogue method can be selected by referring to the user's past dialogue history. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input the user's dialogue history data into a generating AI and have the generating AI perform the selection of the optimal dialogue method.

[0108] The dialogue unit can customize the means of dialogue based on the user's current situation during a conversation. For example, if the user is on the move, the dialogue unit may prioritize voice dialogue. For example, if the user is in a quiet environment, the dialogue unit may prioritize text dialogue. The dialogue unit may also prioritize short conversations if the user is busy. In this way, by customizing the means of dialogue based on the user's current situation, an appropriate conversation can be provided. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input the user's current situation data into a generating AI and have the generating AI perform the customization of the means of dialogue.

[0109] The dialogue unit can estimate the user's emotions and determine the priority of the dialogue based on the estimated emotions. For example, if the user is relaxed, the dialogue unit may prioritize entertainment-related dialogue. If the user is stressed, the dialogue unit may prioritize relaxing dialogue. Furthermore, if the user is excited, the dialogue unit may prioritize action-oriented dialogue. This allows for the provision of appropriate dialogue by prioritizing dialogue according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the dialogue unit may be performed using AI, or not. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0110] The dialogue unit can select the optimal dialogue method during a conversation by considering the user's geographical location. For example, if the user is in a specific region, the dialogue unit can engage in a conversation on topics related to that region. If the user is traveling, the dialogue unit can engage in a conversation on topics related to the travel destination. Furthermore, if the user is at home, the dialogue unit can engage in a conversation on topics related to activities at home. In this way, the optimal dialogue method can be selected by considering the user's geographical location. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input the user's geographical location data into a generating AI and have the generating AI select the optimal dialogue method.

[0111] The dialogue unit can analyze the user's social media activity during a conversation and propose a means of dialogue. For example, the dialogue unit can conduct a conversation based on what the user has shared on social media. For example, the dialogue unit can conduct a conversation based on what the user has "liked" on social media. Furthermore, the dialogue unit can conduct a conversation based on what the user has commented on social media. In this way, by analyzing the user's social media activity, it can propose an appropriate means of dialogue. Some or all of the above processing in the dialogue unit may be performed using AI, for example, or without AI. For example, the dialogue unit can input the user's social media activity data into a generating AI and have the generating AI propose a means of dialogue.

[0112] The management unit can estimate the user's emotions and adjust the viewing history management method based on the estimated user emotions. For example, if the user is relaxed, the management unit can provide a detailed viewing history. For example, if the user is stressed, the management unit can provide a concise viewing history. The management unit can also provide a visually stimulating viewing history if the user is excited. This allows for appropriate management by adjusting the viewing history management method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the management unit may be performed using AI, for example, or not using AI. For example, the management unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0113] The management unit can select the optimal management method by referring to the user's past viewing history during management. For example, the management unit can select the optimal management method based on the genre of videos the user has watched in the past. For example, the management unit can select the optimal management method based on the user's viewing time. Furthermore, the management unit can also select the optimal management method based on the user's viewing device. In this way, the optimal management method can be selected by referring to the user's past viewing history. Some or all of the above processing in the management unit may be performed using AI, for example, or without AI. For example, the management unit can input the user's viewing history data into a generating AI and have the generating AI perform the selection of the optimal management method.

[0114] The management unit can customize management methods based on the user's current viewing environment during management. For example, if the user is viewing on a smartphone, the management unit can adjust the management method considering mobile data usage. For example, if the user is viewing in a home Wi-Fi environment, the management unit can prioritize managing high-definition viewing history. Furthermore, if the user is viewing in a public place, the management unit can adjust the management method considering privacy. This allows for appropriate management by customizing management methods based on the user's current viewing environment. Some or all of the above processing in the management unit may be performed using AI, for example, or not using AI. For example, the management unit can input user viewing environment data into a generating AI and have the generating AI perform the customization of management methods.

[0115] The management unit can estimate the user's emotions and determine the priority of viewing history management based on the estimated emotions. For example, if the user is relaxed, the management unit can prioritize managing entertainment-related viewing history. For example, if the user is stressed, the management unit can prioritize managing viewing history of relaxing videos. Furthermore, if the user is excited, the management unit can prioritize managing viewing history of action-oriented content. This allows for appropriate management by determining the priority of viewing history management according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the management unit may be performed using AI, for example, or not using AI. For example, the management unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0116] The management unit can select the optimal management method by considering the user's geographical location information during management. For example, if the user is in a specific region, the management unit can prioritize managing the viewing history of videos related to that region. For example, if the user is traveling, the management unit can prioritize managing the viewing history of videos related to the travel destination. Furthermore, if the user is at home, the management unit can prioritize managing the viewing history at home. In this way, the optimal management method can be selected by considering the user's geographical location information. Some or all of the above processing in the management unit may be performed using AI, for example, or without AI. For example, the management unit can input the user's geographical location information data into a generating AI and have the generating AI select the optimal management method.

[0117] The management department can analyze users' social media activity and propose management methods during management. For example, the management department can prioritize managing the viewing history of videos that users have shared on social media. For example, the management department can prioritize managing the viewing history of videos that users have "liked" on social media. Furthermore, the management department can also prioritize managing the viewing history of videos that users have commented on on social media. In this way, by analyzing users' social media activity, appropriate management methods can be proposed. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input user social media activity data into a generating AI and have the generating AI execute proposals for management methods.

[0118] The interactive communication unit can estimate the user's emotions and adjust how live comments are displayed based on the estimated emotions. For example, if the user is relaxed, the interactive communication unit can display live comments that proceed at a relaxed pace. If the user is stressed, for example, the interactive communication unit can display concise and highly visible live comments. Furthermore, if the user is excited, the interactive communication unit can display visually stimulating live comments. In this way, appropriate live comments can be provided by adjusting how live comments are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0119] The interactive communication unit can select the optimal display method when displaying live comments by referring to the user's past comment history. For example, the interactive communication unit can select the optimal display method based on the comment style the user has preferred in the past. For example, the interactive communication unit can prioritize displaying the user's preferred topics from the user's past comment history. The interactive communication unit can also analyze the user's past comment history and select the most effective display method. In this way, the optimal display method for live comments can be selected by referring to the user's past comment history. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input the user's comment history data into a generating AI and have the generating AI select the optimal display method.

[0120] The interactive communication unit can customize the display method for live comments based on the user's current viewing environment. For example, if the user is viewing on a smartphone, the interactive communication unit can provide a live comment display method that is adapted to the screen size. For example, if the user is viewing on a tablet, the interactive communication unit can provide a live comment display method optimized for a larger screen. Furthermore, if the user is viewing on a smart TV, the interactive communication unit can provide a live comment display method that is highly visible. In this way, appropriate live comments can be provided by customizing the display method based on the user's current viewing environment. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input the user's viewing environment data into a generating AI and have the generating AI perform the customization of the display method.

[0121] The interactive communication unit can estimate the user's emotions and determine the priority of live comments based on the estimated emotions. For example, if the user is relaxed, the interactive communication unit can prioritize displaying entertainment-related live comments. For example, if the user is stressed, the interactive communication unit can prioritize displaying live comments with a relaxing effect. Furthermore, if the user is excited, the interactive communication unit can prioritize displaying action-oriented live comments. In this way, by determining the priority of live comments according to the user's emotions, appropriate live comments can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0122] The interactive communication unit can select the optimal display method for live comments by considering the user's geographical location information. For example, if the user is in a specific region, the interactive communication unit can prioritize displaying live comments related to that region. For example, if the user is traveling, the interactive communication unit can prioritize displaying live comments related to the travel destination. Furthermore, if the user is at home, the interactive communication unit can prioritize displaying live comments related to viewing at home. In this way, the optimal display method for live comments can be selected by considering the user's geographical location information. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input the user's geographical location information data into a generating AI and have the generating AI select the optimal display method.

[0123] The interactive communication unit can analyze the user's social media activity and suggest display methods when displaying live comments. For example, the interactive communication unit can display live comments based on content shared by the user on social media. For example, the interactive communication unit can display live comments based on content "liked" by the user on social media. Furthermore, the interactive communication unit can also display live comments based on content commented by the user on social media. In this way, by analyzing the user's social media activity, it is possible to suggest appropriate means of displaying live comments. Some or all of the above processing in the interactive communication unit may be performed using AI, for example, or without AI. For example, the interactive communication unit can input the user's social media activity data into a generating AI and have the generating AI execute suggestions for display methods.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The data collection unit can analyze the content of videos watched by users based on their viewing history and optimize the method of collecting viewing history. For example, the data collection unit can analyze the genre and theme of videos watched by users and prioritize the collection of videos of similar genres and themes. It can also analyze the viewing time and frequency of videos watched by users and prioritize the collection of videos with long viewing times or high viewing frequencies. Furthermore, the data collection unit can analyze the ratings and comments on videos watched by users and prioritize the collection of videos with many high ratings and positive comments. In this way, the data collection unit can optimize the method of collecting viewing history based on the user's viewing history.

[0126] The data collection unit can estimate the user's emotions and adjust the method of collecting viewing history based on those emotions. For example, if the user is relaxed, the data collection unit can collect viewing history more frequently and gather more detailed data. Conversely, if the user is stressed, the data collection unit can reduce the amount of viewing history collected to lessen the user's burden. Furthermore, if the user is excited, the data collection unit can collect viewing history in real time to obtain immediate data. In this way, the data collection unit can adjust the method of collecting viewing history according to the user's emotions.

[0127] The analytics unit can analyze a user's viewing history and identify patterns in that history. For example, if a user tends to watch videos during a specific time period, the analytics unit can prioritize analyzing videos related to that time period. Furthermore, if a user prefers videos of a particular genre or theme, the analytics unit can prioritize analyzing videos related to that genre or theme. Additionally, if a user tends to watch videos on a specific device, the analytics unit can prioritize analyzing videos optimized for that device. This allows the analytics unit to identify patterns in a user's viewing history and optimize its analysis methods.

[0128] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. If the user is stressed, the analysis unit can provide concise analysis results. Furthermore, if the user is excited, the analysis unit can provide visually stimulating analysis results. In this way, the analysis unit can adjust how the analysis results are displayed according to the user's emotions.

[0129] The service provider can optimize the content of videos offered based on the user's viewing history. For example, it can analyze the genres and themes of videos the user has watched and prioritize providing videos of similar genres and themes. It can also analyze the viewing time and frequency of videos the user has watched and prioritize providing videos with long viewing times or high viewing frequencies. Furthermore, it can analyze the ratings and comments on videos the user has watched and prioritize providing videos with many high ratings and positive comments. In this way, the service provider can optimize the content of videos offered based on the user's viewing history.

[0130] The service provider can estimate the user's emotions and adjust the content of the videos it provides based on those emotions. For example, if the user is relaxed, the service provider can provide videos with a relaxing effect. If the user is stressed, the service provider can provide videos with a stress-relieving effect. Furthermore, if the user is excited, the service provider can provide videos that maintain that excitement. In this way, the service provider can adjust the content of the videos it provides according to the user's emotions.

[0131] The subtitle generation unit can optimize the subtitle generation method based on the user's viewing history. For example, the subtitle generation unit can analyze the genre and theme of videos the user has watched and generate optimal subtitles for videos of similar genres and themes. It can also analyze the viewing time and frequency of videos the user has watched and generate optimal subtitles for videos with long viewing times or high viewing frequency. Furthermore, the subtitle generation unit can analyze the ratings and comments on videos the user has watched and generate optimal subtitles for videos with many high ratings and positive comments. In this way, the subtitle generation unit can optimize the subtitle generation method based on the user's viewing history.

[0132] The subtitle generation unit can estimate the user's emotions and adjust how subtitles are displayed based on those emotions. For example, if the user is relaxed, the subtitle generation unit can provide subtitles that proceed at a leisurely pace. If the user is stressed, the subtitle generation unit can provide concise and easy-to-read subtitles. Furthermore, if the user is excited, the subtitle generation unit can provide visually stimulating subtitles. In this way, the subtitle generation unit can adjust how subtitles are displayed according to the user's emotions.

[0133] The dialogue unit can optimize the content of conversations based on the user's viewing history. For example, the dialogue unit can analyze the genre and theme of videos the user has watched and provide conversations related to similar genres and themes. It can also analyze the viewing time and frequency of videos the user has watched and provide conversations related to videos with long viewing times or high viewing frequency. Furthermore, the dialogue unit can analyze the ratings and comments on videos the user has watched and provide conversations related to videos with many high ratings and positive comments. In this way, the dialogue unit can optimize the content of conversations based on the user's viewing history.

[0134] The dialogue unit can estimate the user's emotions and adjust the content of the dialogue based on those emotions. For example, if the user is relaxed, the dialogue unit can provide a relaxing dialogue. If the user is stressed, the dialogue unit can provide a stress-relieving dialogue. Furthermore, if the user is excited, the dialogue unit can provide a dialogue that maintains that excitement. In this way, the dialogue unit can adjust the content of the dialogue according to the user's emotions.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The data collection unit collects viewing history, preferences, and real-time viewing behavior. For example, it collects viewing history such as the titles of videos the user has watched, viewing time, and viewing frequency, as well as preferences such as videos the user has rated and genres estimated from the viewing history. It also collects real-time viewing behavior such as actions taken while watching and reactions while watching. Step 2: The analysis unit analyzes the data collected by the collection unit. For example, it analyzes viewing history, preferences, and real-time viewing behavior to generate information for providing recommended videos based on user preferences. Step 3: The provisioning unit provides recommended videos based on the analysis results obtained by the analysis unit. For example, it provides recommended videos based on the user's preferences, prioritizing videos in genres the user likes. Step 4: The subtitle generation unit analyzes the video's audio in real time and generates highly accurate subtitles. For example, it uses speech recognition technology to convert the video's audio into text, and then generates subtitles based on the generated text. Step 5: The dialogue unit provides a function for interacting with the user. For example, it analyzes the user's voice using speech recognition technology and engages in dialogue. Step 6: The management department manages viewing history. For example, it saves a history of videos that users have watched in the past and allows users to revisit videos they have watched previously. Step 7: The interactive communication section will enable users to post live comments in real time. For example, it will provide a function that allows users to enter comments while watching and have them displayed in real time.

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0139] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the collection unit, analysis unit, provision unit, subtitle generation unit, dialogue unit, management unit, and two-way communication unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects viewing history, preferences, and real-time viewing behavior. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides recommended videos based on the analysis results. The subtitle generation unit is implemented by the control unit 46A of the smart device 14 and analyzes the audio of the video in real time and generates high-precision subtitles. The dialogue unit is implemented by the control unit 46A of the smart device 14 and provides a dialogue function with the user using speech recognition technology. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the viewing history. The two-way communication section is implemented, for example, by the control unit 46A of the smart device 14, allowing users to post live comments in real time. The correspondence between each section and the device or control unit is not limited to the example described above and can be modified in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0144] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0148] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the collection unit, analysis unit, provision unit, subtitle generation unit, dialogue unit, management unit, and two-way communication unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects viewing history, preferences, and real-time viewing behavior. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides recommended videos based on the analysis results. The subtitle generation unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the audio of the video in real time and generates high-precision subtitles. The dialogue unit is implemented by the control unit 46A of the smart glasses 214 and provides a dialogue function with the user using speech recognition technology. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the viewing history. The two-way communication section is implemented, for example, by the control unit 46A of the smart glasses 214, allowing users to post live comments in real time. The correspondence between each section and the device or control unit is not limited to the example described above and can be modified in various ways.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0160] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0164] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0165] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0166] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0167] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0168] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0169] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0170] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0172] Each of the multiple elements described above, including the collection unit, analysis unit, provision unit, subtitle generation unit, dialogue unit, management unit, and two-way communication unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects viewing history, preferences, and real-time viewing behavior. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides recommended videos based on the analysis results. The subtitle generation unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the audio of the video in real time and generates high-precision subtitles. The dialogue unit is implemented by the control unit 46A of the headset terminal 314 and provides a dialogue function with the user using speech recognition technology. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the viewing history. The two-way communication section is implemented, for example, by the control unit 46A of the headset-type terminal 314, allowing users to post live comments in real time. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0175] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0176] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0177] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0179] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0180] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0181] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0182] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0183] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0184] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0185] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0186] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0187] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0189] Each of the multiple elements described above, including the collection unit, analysis unit, provision unit, subtitle generation unit, dialogue unit, management unit, and two-way communication unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects viewing history, preferences, and real-time viewing behavior. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The provision unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides recommended videos based on the analysis results. The subtitle generation unit is implemented by, for example, the control unit 46A of the robot 414 and analyzes the audio of the video in real time and generates high-precision subtitles. The dialogue unit is implemented by, for example, the control unit 46A of the robot 414 and provides a dialogue function with the user using speech recognition technology. The management unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and manages the viewing history. The two-way communication unit is implemented, for example, by the control unit 46A of the robot 414, allowing users to post live comments in real time. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0190] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0191] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0192] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0193] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0194] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0195] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0196] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0197] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0198] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0199] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0200] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0201] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0202] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0203] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0204] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0205] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0206] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0207] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0208] (Note 1) A data collection unit that collects viewing history, preferences, and real-time viewing behavior, An analysis unit analyzes the data collected by the aforementioned collection unit, A provisioning unit provides recommended videos based on the analysis results obtained by the aforementioned analysis unit, A subtitle generation unit that analyzes the audio of a video in real time and generates highly accurate subtitles, A dialogue unit that provides interaction functions with the user, The management department manages viewing history, It features a two-way communication section that allows users to post live comments in real time. A system characterized by the following features. (Note 2) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of viewing history collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Analyze the user's past viewing history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is When collecting viewing history, filtering is performed based on the user's current viewing environment and device. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is It estimates the user's emotions and determines the priority of viewing history to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting viewing history, the system prioritizes collecting highly relevant history by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting viewing history, the system analyzes the user's social media activity and collects relevant history. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, During analysis, the level of detail is adjusted based on the importance of viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the viewing history was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned supply unit is, It estimates the user's emotions and adjusts the way the video is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned supply unit is, When providing the content, adjust the level of detail based on the importance of the video. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned supply unit is, When providing content, different distribution algorithms are applied depending on the video category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned supply unit is, It estimates the user's emotions and adjusts the length of the video provided based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned supply unit is, When providing the videos, we will prioritize their delivery based on when the videos were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, When providing videos, the order of delivery will be adjusted based on their relevance. The system described in Appendix 1, characterized by the features described herein. (Note 20) The subtitle generation unit, It estimates the user's emotions and adjusts the way subtitles are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The subtitle generation unit, When generating subtitles, adjust the level of detail based on the importance of the video's audio. The system described in Appendix 1, characterized by the features described herein. (Note 22) The subtitle generation unit, When generating subtitles, different subtitle generation algorithms are applied depending on the video category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The subtitle generation unit, It estimates the user's emotions and adjusts the length of subtitles based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The subtitle generation unit, When generating subtitles, the priority of subtitles is determined based on when the video was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The subtitle generation unit, When generating subtitles, the order of subtitles is adjusted based on the relevance of the video. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the way the dialogue is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned dialogue unit, During a conversation, the system selects the optimal conversation method by referring to the user's past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned dialogue unit, During a conversation, customize the conversational methods based on the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned dialogue unit, It estimates the user's emotions and determines the priority of the conversation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned dialogue unit, During the interaction, the system selects the optimal interaction method, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned dialogue unit, During the conversation, we analyze the user's social media activity and suggest ways to communicate. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned management department, We estimate the user's emotions and adjust how viewing history is managed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned management department, During management, the system selects the optimal management method by referring to the user's past viewing history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned management department, During management, customize the management methods based on the user's current viewing environment. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned management department, It estimates the user's emotions and determines the priority of managing viewing history based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned management department, During management, the optimal management method is selected considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned management department, During management, we analyze users' social media activity and propose management methods. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned two-way communication unit is It estimates the user's emotions and adjusts how live comments are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned two-way communication unit is When displaying live comments, the system will refer to the user's past comment history to select the most suitable display method. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned two-way communication unit is When displaying live comments, the display method is customized based on the user's current viewing environment. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned two-way communication unit is It estimates user sentiment and prioritizes live comments based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned two-way communication unit is When displaying live comments, the system selects the optimal display method by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned two-way communication unit is When displaying live comments, the system analyzes the user's social media activity and suggests display methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0209] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A data collection unit that collects viewing history, preferences, and real-time viewing behavior, An analysis unit analyzes the data collected by the aforementioned collection unit, A provisioning unit provides recommended videos based on the analysis results obtained by the aforementioned analysis unit, A subtitle generation unit that analyzes the audio of a video in real time and generates highly accurate subtitles, A dialogue unit that provides interaction functions with the user, The management department manages viewing history, It features a two-way communication section that allows users to post live comments in real time. A system characterized by the following features.

2. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of viewing history collection based on the estimated user emotions. The system according to feature 1.

3. The aforementioned collection unit is Analyze the user's past viewing history and select the optimal data collection method. The system according to feature 1.

4. The aforementioned collection unit is When collecting viewing history, filtering is performed based on the user's current viewing environment and device. The system according to feature 1.

5. The aforementioned collection unit is It estimates the user's emotions and determines the priority of viewing history to collect based on the estimated user emotions. The system according to feature 1.

6. The aforementioned collection unit is When collecting viewing history, the system prioritizes collecting highly relevant history by considering the user's geographical location. The system according to feature 1.

7. The aforementioned collection unit is When collecting viewing history, the system analyzes the user's social media activity and collects relevant history. The system according to feature 1.

8. The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system according to feature 1.

Images