system

Abstract

The system according to this embodiment aims to enable users aiming to debut in video streaming to easily select characters and concepts, edit videos, optimize for SEO, and prevent online controversies. [Solution] The system according to the embodiment comprises a proposal unit, an editing unit, an optimization unit, and a prevention unit. The proposal unit proposes characters and concepts that suit the user. The editing unit edits the video based on the characters and concepts proposed by the proposal unit. The optimization unit performs SEO optimization on the video edited by the editing unit. The prevention unit prevents the video optimized by the optimization unit from becoming a source of online controversy.

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 performed by at least one processor, the method including 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 as a 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 conventional technology, there is a problem that users aiming for a video distribution debut need to perform complex tasks such as selecting characters or concepts, video editing, SEO optimization, and preventing going viral on their own, which is difficult for beginners.

[0005] The system according to the embodiment aims to enable users aiming for a video distribution debut to easily select characters or concepts, perform video editing, SEO optimization, and prevent going viral.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a proposal unit, an editing unit, an optimization unit, and a prevention unit. The proposal unit proposes characters and concepts that suit the user. The editing unit edits a video based on the characters and concepts proposed by the proposal unit. The optimization unit performs SEO optimization on the video edited by the editing unit. The prevention unit prevents the video optimized by the optimization unit from becoming a source of online controversy. [Effects of the Invention]

[0007] The system according to this embodiment can enable users aiming to debut in video streaming to easily select characters and concepts, edit videos, optimize for SEO, and prevent online controversies. [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 manages communication between multiple 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 receiving 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 receiving 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) The video streaming debut support system according to an embodiment of the present invention is a support service that enables anyone to easily make their video streaming debut by utilizing an AI agent. This video streaming debut support system is equipped with features such as suggesting characters and concepts that suit the user, automating video editing, SEO optimization, and a function to prevent online controversies, making it easy for beginners and professionals alike to use. It also has a robust avatar generation function that does not require showing one's face, and a function that proposes project ideas based on trend analysis. For example, the video streaming debut support system has a function that suggests characters and concepts that suit the user. The AI ​​analyzes the user's personality and hobbies and suggests "the perfect video streaming style for you." For example, cooking x ASMR or game commentary x a soothing character. Next, for people who are hesitant to show their face, there is a function that generates 2D / 3D avatars using AI. This makes it easy to create VTuber-style videos. Furthermore, there is a function that suggests video ideas based on trends and search volume using AI. Thumbnail ideas and titles are also automatically suggested. After shooting, the AI ​​automatically edits the video, adding cuts, background music, text overlays, effects, etc. Editing styles can be selected from "casual" and "professional". Furthermore, the AI ​​automatically generates SEO-optimized titles, descriptions, and tags, and the posting timing is optimized based on data analysis. There is also a function that analyzes post-post data and provides suggestions for improvement to the next video. Improvement suggestions are made based on viewer reactions. In addition, it has a mechanism to prevent controversies from occurring. The content auditing AI performs pre-checks and provides comment filtering, moderation, a controversy detection system, and response guidelines. This realizes a new era platform that can be used with confidence by everyone from beginners to professionals. As a result, the video distribution debut support system can suggest characters and concepts that suit the user, video editing, SEO optimization, and controversy prevention.

[0029] The video streaming debut support system according to this embodiment comprises a proposal unit, an editing unit, an optimization unit, and a prevention unit. The proposal unit proposes characters and concepts that suit the user. For example, the proposal unit uses AI to analyze the user's personality and hobbies and proposes "the perfect video streaming style for you." For example, the proposal unit can propose cooking x ASMR or game commentary x a soothing character. The editing unit edits the video based on the characters and concepts proposed by the proposal unit. For example, the editing unit uses AI to automatically edit the video, adding cuts, background music, text overlays, effects, etc. The editing style can be selected from "casual" or "professional." The optimization unit performs SEO optimization of the video edited by the editing unit. For example, the optimization unit uses AI to automatically generate SEO-optimized titles, descriptions, and tags, and optimizes the posting timing based on data analysis. The prevention unit prevents the video optimized by the optimization unit from becoming a source of online controversy. For example, the prevention unit uses content auditing AI to perform pre-checks and provides comment filtering, moderation, a controversy detection system, and response guidelines. As a result, the video distribution debut support system according to the embodiment can propose characters and concepts that suit the user, perform video editing, optimize for SEO, and prevent online controversies.

[0030] The proposal team suggests characters and concepts tailored to each user. For example, the AI ​​analyzes the user's personality and hobbies to propose "the perfect video streaming style for you." Specifically, the AI ​​analyzes the user's profile information, past social media posts, and survey results to understand their interests, skills, and personality traits. Using natural language processing technology, the AI ​​analyzes the emotions and tone from the user's writing and comments to determine what kind of content the user is interested in and what style is suitable. For example, a user who is good at cooking and has a calm personality might be suggested a cooking x ASMR concept, while a user who likes games and has a sense of humor might be suggested a game commentary x soothing character concept. The proposal team also considers the user's target audience and market trends to select the most effective concept. This allows the proposal team to suggest the optimal video streaming style for the user, increasing the chances of success. Furthermore, the proposal team can provide feedback to the user on the suggested concept and fine-tune the concept as needed. This allows users to make their video streaming debut in the style that best suits them.

[0031] The editorial team edits videos based on characters and concepts proposed by the proposal team. For example, the editorial team uses AI to automatically edit, adding cuts, background music, text overlays, and effects. Specifically, the AI ​​analyzes raw footage shot by the user and automatically extracts important scenes and highlights. The AI ​​analyzes the content and audio of the video, cuts out unnecessary parts, and creates a video that is appealing to viewers. For example, in cooking videos, appropriate cuts and zooms are made to emphasize the cooking process and the beauty of the finished product. In game commentary videos, replays and slow motion are added to emphasize interesting moments and important gameplay scenes. The editorial team also adds background music, text overlays, and effects according to the editing style chosen by the user. A casual style uses bright and poppy background music and colorful text overlays, while a professional style uses calm background music and simple and sophisticated text overlays. This allows the editorial team to efficiently produce high-quality videos that match the user's concept. Furthermore, the editorial team provides an interface that allows users to review the edited content and request revisions as needed. This enables users to create videos that align with their intentions and deliver highly satisfying content.

[0032] The optimization team optimizes the SEO of videos edited by the editorial team. For example, the optimization team automatically generates SEO-optimized titles, descriptions, and tags using AI, and optimizes posting timing based on data analysis. Specifically, the AI ​​analyzes the video content and target audience, and selects keywords optimized for search engines and video distribution algorithms. For example, for cooking videos, it generates titles and descriptions that include keywords such as "easy recipes," "beginner-friendly," and "quick and easy cooking." The AI ​​also automatically generates tags related to the video content to make it easier for viewers to search. Furthermore, the optimization team analyzes past data and trends to suggest the optimal posting timing. For example, if there are many viewers on a particular day or time, posting the video at that time can maximize the number of views. This allows the optimization team to make it easier for users' videos to reach more viewers and promote channel growth. In addition, the optimization team can collect performance data after posting and suggest improvements for the next post. This allows users to continuously improve their SEO and enhance channel performance.

[0033] The prevention unit prevents controversies in videos optimized by the optimization unit. For example, the prevention unit uses content auditing AI for pre-checks and provides comment filtering, moderation, a controversy detection system, and response guidelines. Specifically, the content auditing AI analyzes video content to check for discriminatory, offensive, or inappropriate language. If a problem is detected, it sends a notification to the user prompting correction and provides specific correction suggestions as needed. The comment filtering system monitors posted comments in real time and automatically removes inappropriate comments. Furthermore, it provides moderation tools to allow users to manually manage comments. The controversy detection system monitors sudden changes in videos and comments to detect early signs of controversy. For example, it issues alerts if a specific keyword suddenly appears or if negative comments increase. Response guidelines provide specific methods for responding if a controversy occurs, supporting users in responding quickly and appropriately. This allows the prevention unit to minimize the risk of users' videos becoming controversial and support safe and healthy channel management. Furthermore, the prevention unit can continuously improve the system based on user feedback, providing more effective fire prevention measures.

[0034] The avatar generation unit can generate 2D / 3D avatars for people who are hesitant to show their faces. For example, the avatar generation unit uses AI to analyze the user's facial features and generate a 2D or 3D avatar. For example, the avatar generation unit can receive a photo of the user's face as input, and the AI ​​generates an avatar based on that photo. The avatar generation unit can also generate avatars based on a character style selected by the user. For example, the avatar generation unit can generate an avatar that matches the character style selected by the user. This makes it possible for people who are hesitant to show their faces to create VTuber-style videos. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input a photo of the user's face into a generation AI and have the generation AI perform avatar generation.

[0035] The planning and proposal department can propose video ideas based on trends and search volume. For example, the planning and proposal department can use AI to analyze trends and search volume and propose the most suitable video ideas to users. For example, the planning and proposal department can use AI to analyze current trends and propose video ideas based on those trends. The planning and proposal department can also analyze search volume and propose video ideas based on popular keywords. For example, the planning and proposal department can use AI to analyze search volume and propose video ideas based on popular keywords. This makes it possible to propose video ideas based on trends and search volume. Some or all of the above processes in the planning and proposal department may be performed using AI, or not. For example, the planning and proposal department can input trend and search volume data into a generating AI and have the generating AI generate video idea suggestions.

[0036] The data analysis department can analyze data after posting and provide suggestions for improvement to the next video. For example, the data analysis department can use AI to analyze data after posting and provide suggestions for improvement to the next video. For example, the data analysis department can analyze data such as the number of views, viewing time, and user feedback and provide suggestions for improvement to the next video. The data analysis department can also propose improvements based on viewer reactions. For example, the data analysis department can analyze viewer comments and ratings and propose improvements based on that. In this way, it can provide suggestions for improvement to the next video based on post-post data analysis. Some or all of the above processing in the data analysis department may be performed using AI, for example, or without AI. For example, the data analysis department can input data after posting into a generating AI and have the generating AI execute suggestions for improvement.

[0037] The comment filtering unit can perform comment filtering and moderation. For example, the comment filtering unit can use AI to filter comments and exclude spam and inappropriate comments. For example, the comment filtering unit can automatically filter comments containing specific keywords. The comment filtering unit can also use AI to analyze the content of comments and moderate inappropriate comments. For example, the comment filtering unit can use AI to analyze the content of comments and automatically delete inappropriate comments. This enables comment filtering and moderation. Some or all of the above processing in the comment filtering unit may be performed using AI, or without AI. For example, the comment filtering unit can input comment data into a generating AI and have the generating AI perform filtering and moderation.

[0038] The suggestion unit can analyze a user's past video viewing history and propose the most suitable characters and concepts. For example, the suggestion unit can analyze the genres of videos the user has watched in the past and propose characters and concepts of the same genre. For example, the suggestion unit can also refer to the styles of creators the user frequently watches and propose similar characters and concepts. For example, the suggestion unit can analyze comments and ratings of videos the user has watched and propose popular characters and concepts. This allows the suggestion unit to propose the most suitable characters and concepts based on the user's past video viewing history. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's past video viewing history data into a generating AI and have the generating AI propose characters and concepts.

[0039] The suggestion unit can filter suggestions based on the user's current trends and areas of interest. For example, the suggestion unit can analyze topics the user is currently interested in and suggest characters and concepts related to those topics. The suggestion unit can also suggest relevant characters and concepts by referring to trends and hashtags the user is following. The suggestion unit can also suggest relevant characters and concepts based on keywords the user has recently searched for. This allows the suggestion unit to suggest characters and concepts based on the user's current trends and areas of interest. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input data on the user's current trends and areas of interest into a generating AI and have the generating AI perform the filtering of characters and concepts.

[0040] The suggestion unit can prioritize suggesting characters and concepts that are highly relevant to the user, taking into account the user's geographical location information. For example, the suggestion unit can suggest characters and concepts based on the culture and trends of the area where the user lives. For example, if the user is traveling, the suggestion unit can also suggest characters and concepts related to the tourist attractions and local products of that area. For example, if the user is participating in a specific event, the suggestion unit can also suggest characters and concepts related to that event. This allows for the suggestion of characters and concepts based on the user's geographical location information. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input the user's geographical location information data into a generating AI and have the generating AI perform the character and concept suggestion.

[0041] The suggestion unit can analyze the user's social media activity and propose relevant characters and concepts when making suggestions. For example, the suggestion unit can analyze the content of accounts the user follows on social media and propose relevant characters and concepts. For example, the suggestion unit can propose relevant characters and concepts based on content the user has shared on social media. For example, the suggestion unit can propose relevant characters and concepts by referring to topics in groups and communities the user participates in on social media. This allows for the suggestion of characters and concepts based on the user's social media activity. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's social media activity data into a generating AI and have the generating AI produce character and concept suggestions.

[0042] The editorial team can adjust the level of detail in editing based on the importance of the video. For example, they can perform detailed editing on important scenes to make them easier for viewers to understand. They can also perform simplified editing on less important scenes to maintain the overall pace of the video. They can also add special effects or background music to emphasize important scenes. This allows them to adjust the level of detail in editing based on the importance of the video. Some or all of the above processes in the editorial team may be performed using AI, for example, or not. For example, the editorial team can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in editing.

[0043] The editorial team can apply different editing algorithms depending on the video category during editing. For example, for cooking videos, the editorial team can apply an editing algorithm that makes the cooking process easy to understand. For game commentary videos, the editorial team can also apply an editing algorithm that highlights important scenes during gameplay. For ASMR videos, the editorial team can also apply an editing algorithm that emphasizes the sound. This allows for the application of different editing algorithms depending on the video category. Some or all of the above processing in the editorial team may be performed using AI, for example, or not using AI. For example, the editorial team can input video category data into a generating AI and have the generating AI execute the application of the editing algorithm.

[0044] The editorial team can determine editing priorities based on when the videos were filmed. For example, they might prioritize editing the latest videos to provide trending content. They might also prioritize editing seasonal videos to attract viewers' attention. They might prioritize editing videos related to specific events to provide timely content. This allows them to determine editing priorities based on when the videos were filmed. Some or all of the above processes in the editorial team may be performed using AI, for example, or not. For example, the editorial team could input video filming date data into a generating AI and have the generating AI determine the editing priorities.

[0045] The editorial team can adjust the editing order based on the relevance of the videos during the editing process. For example, the editorial team can edit videos from the same series consecutively to ensure viewers enjoy consistent content. The editorial team can also edit videos on related topics together to provide viewers with highly relevant content. The editorial team can also prioritize editing videos on topics of high viewer interest to increase viewership. This allows for adjusting the editing order based on the relevance of the videos. Some or all of the above processes in the editorial team may be performed using AI, for example, or not. For example, the editorial team can input video relevance data into a generating AI and have the generating AI perform the adjustment of the editing order.

[0046] The optimization unit can adjust the level of detail of the optimization based on the importance of the video during the optimization process. For example, the optimization unit can perform detailed SEO optimization on important videos to ensure they rank higher in search results. For example, the optimization unit can perform simplified SEO optimization on less important videos to optimize them efficiently. For example, the optimization unit can also optimize on highly important videos by emphasizing specific keywords. This allows the level of detail of the optimization to be adjusted based on the importance of the video. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the optimization.

[0047] The optimization unit can apply different optimization algorithms depending on the video category during optimization. For example, for cooking videos, the optimization unit can perform SEO optimization including keywords related to cooking. For example, for game commentary videos, the optimization unit can also perform SEO optimization including keywords related to games. For example, for ASMR videos, the optimization unit can also perform SEO optimization including keywords related to relaxation and healing. This allows different optimization algorithms to be applied depending on the video category. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video category data into a generating AI and have the generating AI execute the application of the optimization algorithm.

[0048] The optimization unit can determine optimization priorities based on the video's shooting date during the optimization process. For example, the optimization unit can prioritize optimizing the latest videos to provide content that aligns with trends. The optimization unit can also prioritize optimizing seasonal videos to attract viewer interest. For example, the optimization unit can prioritize optimizing videos related to specific events to provide timely content. This allows the optimization priority to be determined based on the video's shooting date. Some or all of the above-described processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video shooting date data into a generating AI and have the generating AI determine the optimization priority.

[0049] The optimization unit can adjust the optimization order based on the relevance of the videos during the optimization process. For example, the optimization unit can optimize videos from the same series consecutively to ensure viewers enjoy consistent content. The optimization unit can also optimize videos on related topics together to provide viewers with highly relevant content. For example, the optimization unit can prioritize the optimization of videos on topics of high viewer interest to increase viewership. This allows the optimization order to be adjusted based on the relevance of the videos. Some or all of the above-described processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video relevance data into a generating AI and have the generating AI perform the adjustment of the optimization order.

[0050] The prevention unit can adjust the level of detail in prevention measures based on the importance of the video. For example, for important videos, the prevention unit can implement detailed crisis prevention measures to minimize risk. For less important videos, the prevention unit can implement simplified crisis prevention measures to efficiently prevent problems. For high-importance videos, the prevention unit can also emphasize specific keywords or phrases in its prevention measures. This allows the level of detail in prevention measures to be adjusted based on the importance of the video. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video importance data into a generating AI and have the generating AI adjust the level of detail in prevention measures.

[0051] The prevention unit can apply different prevention algorithms depending on the video category during prevention. For example, in cooking videos, the prevention unit can apply an algorithm to prevent controversy related to ingredients and cooking methods. For example, in game commentary videos, the prevention unit can apply an algorithm to prevent controversy related to violence or extreme language in games. For example, in ASMR videos, the prevention unit can apply an algorithm to prevent controversy related to sound and visual effects. This allows different prevention algorithms to be applied depending on the video category. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video category data into a generating AI and have the generating AI execute the application of the prevention algorithm.

[0052] The prevention unit can determine the priority of prevention based on the video's shooting date. For example, the prevention unit can prioritize preventing the latest videos and provide content that aligns with trends. The prevention unit can also prioritize preventing seasonal videos to attract viewers' attention. The prevention unit can also prioritize preventing videos related to specific events to provide timely content. This allows the prevention unit to determine the priority of prevention based on the video's shooting date. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video shooting date data into a generating AI and have the generating AI determine the priority of prevention.

[0053] The prevention unit can adjust the order of prevention based on the relevance of the videos. For example, the prevention unit can prevent videos from the same series consecutively so that viewers can enjoy consistent content. The prevention unit can also prevent videos on related topics together to provide viewers with highly relevant content. The prevention unit can also prioritize preventing videos on topics of high viewer interest to increase the number of views. This allows the order of prevention to be adjusted based on the relevance of the videos. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video relevance data into a generating AI and have the generating AI perform the adjustment of the prevention order.

[0054] The avatar generation unit can generate the optimal avatar by analyzing the user's past avatar usage history during avatar generation. For example, the avatar generation unit can analyze the style of avatars the user has used in the past and generate similar avatars. For example, the avatar generation unit can generate the optimal avatar by referring to the characteristics of avatars that the user frequently uses. For example, the avatar generation unit can generate the optimal avatar based on the design of avatars that the user has evaluated in the past. This allows the system to generate the optimal avatar based on the user's past avatar usage history. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's past avatar usage history data into a generation AI and have the generation AI perform avatar generation.

[0055] The avatar generation unit can prioritize the generation of highly relevant avatars by considering the user's geographical location information during avatar generation. For example, the avatar generation unit can generate avatars based on the culture and trends of the region where the user lives. For example, if the user is traveling, the avatar generation unit can also generate avatars related to tourist attractions or local products of that region. For example, if the user is participating in a specific event, the avatar generation unit can also generate avatars related to that event. This allows for the generation of highly relevant avatars based on the user's geographical location information. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's geographical location information data into a generation AI and have the generation AI perform avatar generation.

[0056] The planning and proposal department can adjust the level of detail in a planning proposal based on the importance of the video. For example, for important videos, the planning and proposal department can provide a detailed planning proposal to make it easier for viewers to understand. For less important videos, the planning and proposal department can provide a simplified planning proposal to maintain the overall pace of the video. For highly important videos, the planning and proposal department can add special effects or background music to emphasize them. This allows the level of detail in the planning proposal to be adjusted based on the importance of the video. Some or all of the above processes in the planning and proposal department may be performed using AI, for example, or not. For example, the planning and proposal department can input video importance data into a generating AI and have the generating AI adjust the level of detail in the planning proposal.

[0057] The data analysis unit can adjust the level of detail in its data analysis based on the importance of the video. For example, for important videos, the data analysis unit can perform detailed data analysis to make it easier for viewers to understand. For less important videos, the data analysis unit can perform simplified data analysis to maintain the overall pace of the video. For highly important videos, the data analysis unit can add special effects or background music to emphasize them. This allows the level of detail in the data analysis to be adjusted based on the importance of the video. Some or all of the above processes in the data analysis unit may be performed using AI, for example, or not. For example, the data analysis unit can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the data analysis.

[0058] The data analysis department can prioritize data analysis based on the video's shooting date. For example, the data analysis department can prioritize analyzing the latest videos to provide trending content. It can also prioritize analyzing seasonal videos to attract viewer interest. Furthermore, it can prioritize analyzing videos related to specific events to provide timely content. This allows the data analysis department to prioritize data analysis based on the video's shooting date. Some or all of the above processes in the data analysis department may be performed using AI, for example, or without AI. For example, the data analysis department can input video shooting date data into a generating AI and have the generating AI determine the priority of data analysis.

[0059] The comment filtering unit can adjust the level of detail of the filtering based on the importance of the video when filtering comments. For example, the comment filtering unit can perform detailed comment filtering on important videos to minimize risk. For example, the comment filtering unit can perform simplified comment filtering on less important videos to filter efficiently. For example, the comment filtering unit can also emphasize specific keywords or phrases when filtering on high-importance videos. This allows the level of detail of the filtering to be adjusted based on the importance of the video. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the filtering.

[0060] The comment filtering unit can apply different filtering algorithms depending on the video category when filtering comments. For example, in cooking videos, the comment filtering unit can apply an algorithm that filters out negative comments about ingredients or cooking methods. For game commentary videos, the comment filtering unit can also apply an algorithm that filters out negative comments about violence or extreme language in games. For ASMR videos, the comment filtering unit can also apply an algorithm that filters out negative comments about sound or visual effects. This allows different filtering algorithms to be applied depending on the video category. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video category data into a generating AI and have the generating AI execute the application of the filtering algorithm.

[0061] The comment filtering unit can determine filtering priorities based on the video's shooting date during comment filtering. For example, the comment filtering unit can prioritize filtering the latest videos to provide content that aligns with trends. For example, the comment filtering unit can prioritize filtering videos that are relevant to a particular season to attract viewers' attention. For example, the comment filtering unit can prioritize filtering videos related to a specific event to provide timely content. This allows the filtering priority to be determined based on the video's shooting date. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video shooting date data into a generating AI and have the generating AI determine the filtering priority.

[0062] The comment filtering unit can adjust the filtering order based on the relevance of the videos when filtering comments. For example, the comment filtering unit can filter videos from the same series consecutively so that viewers can enjoy consistent content. For example, the comment filtering unit can filter videos on related topics together to provide viewers with highly relevant content. For example, the comment filtering unit can prioritize filtering videos on topics of high interest to viewers to increase the number of views. This allows the filtering order to be adjusted based on the relevance of the videos. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video relevance data into a generating AI and have the generating AI perform the adjustment of the filtering order.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The suggestion unit can analyze a user's past video viewing history and propose the most suitable characters and concepts. For example, the suggestion unit can analyze the genres of videos the user has watched in the past and propose characters and concepts of the same genre. For example, the suggestion unit can also refer to the styles of creators the user frequently watches and propose similar characters and concepts. For example, the suggestion unit can analyze comments and ratings of videos the user has watched and propose popular characters and concepts. This allows the suggestion unit to propose the most suitable characters and concepts based on the user's past video viewing history. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's past video viewing history data into a generating AI and have the generating AI propose characters and concepts.

[0065] The suggestion unit can filter suggestions based on the user's current trends and areas of interest. For example, the suggestion unit can analyze topics the user is currently interested in and suggest characters and concepts related to those topics. The suggestion unit can also suggest relevant characters and concepts by referring to trends and hashtags the user is following. The suggestion unit can also suggest relevant characters and concepts based on keywords the user has recently searched for. This allows the suggestion unit to suggest characters and concepts based on the user's current trends and areas of interest. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input data on the user's current trends and areas of interest into a generating AI and have the generating AI perform the filtering of characters and concepts.

[0066] The editorial team can adjust the level of detail in editing based on the importance of the video. For example, they can perform detailed editing on important scenes to make them easier for viewers to understand. They can also perform simplified editing on less important scenes to maintain the overall pace of the video. They can also add special effects or background music to emphasize important scenes. This allows them to adjust the level of detail in editing based on the importance of the video. Some or all of the above processes in the editorial team may be performed using AI, for example, or not. For example, the editorial team can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in editing.

[0067] The optimization unit can adjust the level of detail of the optimization based on the importance of the video during the optimization process. For example, the optimization unit can perform detailed SEO optimization on important videos to ensure they rank higher in search results. For example, the optimization unit can perform simplified SEO optimization on less important videos to optimize them efficiently. For example, the optimization unit can also optimize on highly important videos by emphasizing specific keywords. This allows the level of detail of the optimization to be adjusted based on the importance of the video. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the optimization.

[0068] The prevention unit can apply different prevention algorithms depending on the video category during prevention. For example, in cooking videos, the prevention unit can apply an algorithm to prevent controversy related to ingredients and cooking methods. For example, in game commentary videos, the prevention unit can apply an algorithm to prevent controversy related to violence or extreme language in games. For example, in ASMR videos, the prevention unit can apply an algorithm to prevent controversy related to sound and visual effects. This allows different prevention algorithms to be applied depending on the video category. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video category data into a generating AI and have the generating AI execute the application of the prevention algorithm.

[0069] The comment filtering unit can apply different filtering algorithms depending on the video category when filtering comments. For example, in cooking videos, the comment filtering unit can apply an algorithm that filters out negative comments about ingredients or cooking methods. For game commentary videos, the comment filtering unit can also apply an algorithm that filters out negative comments about violence or extreme language in games. For ASMR videos, the comment filtering unit can also apply an algorithm that filters out negative comments about sound or visual effects. This allows different filtering algorithms to be applied depending on the video category. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video category data into a generating AI and have the generating AI execute the application of the filtering algorithm.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The proposal team suggests characters and concepts that suit the user. For example, the proposal team uses AI to analyze the user's personality and hobbies and suggest "the perfect video streaming style for you." Specifically, they can suggest things like cooking x ASMR or game commentary x soothing characters. Step 2: The editorial team edits the video based on the characters and concepts proposed by the proposal team. The editorial team, for example, uses AI to automatically edit, adding cuts, background music, text overlays, effects, etc. Editing styles can be selected from "Casual" or "Professional". Step 3: The optimization team performs SEO optimization on the videos edited by the editorial team. For example, the optimization team automatically generates SEO-optimized titles, descriptions, and tags using AI, and also optimizes the posting timing based on data analysis. Step 4: The prevention unit prevents the video optimized by the optimization unit from going viral. For example, the prevention unit uses content auditing AI to perform pre-checks and provides comment filtering and moderation, a viral content detection system, and response guidelines.

[0072] (Example of form 2) The video streaming debut support system according to an embodiment of the present invention is a support service that enables anyone to easily make their video streaming debut by utilizing an AI agent. This video streaming debut support system is equipped with features such as suggesting characters and concepts that suit the user, automating video editing, SEO optimization, and a function to prevent online controversies, making it easy for beginners and professionals alike to use. It also has a robust avatar generation function that does not require showing one's face, and a function that proposes project ideas based on trend analysis. For example, the video streaming debut support system has a function that suggests characters and concepts that suit the user. The AI ​​analyzes the user's personality and hobbies and suggests "the perfect video streaming style for you." For example, cooking x ASMR or game commentary x a soothing character. Next, for people who are hesitant to show their face, there is a function that generates 2D / 3D avatars using AI. This makes it easy to create VTuber-style videos. Furthermore, there is a function that suggests video ideas based on trends and search volume using AI. Thumbnail ideas and titles are also automatically suggested. After shooting, the AI ​​automatically edits the video, adding cuts, background music, text overlays, effects, etc. Editing styles can be selected from "casual" and "professional". Furthermore, the AI ​​automatically generates SEO-optimized titles, descriptions, and tags, and the posting timing is optimized based on data analysis. There is also a function that analyzes post-post data and provides suggestions for improvement to the next video. Improvement suggestions are made based on viewer reactions. In addition, it has a mechanism to prevent controversies from occurring. The content auditing AI performs pre-checks and provides comment filtering, moderation, a controversy detection system, and response guidelines. This realizes a new era platform that can be used with confidence by everyone from beginners to professionals. As a result, the video distribution debut support system can suggest characters and concepts that suit the user, video editing, SEO optimization, and controversy prevention.

[0073] The video streaming debut support system according to this embodiment comprises a proposal unit, an editing unit, an optimization unit, and a prevention unit. The proposal unit proposes characters and concepts that suit the user. For example, the proposal unit uses AI to analyze the user's personality and hobbies and proposes "the perfect video streaming style for you." For example, the proposal unit can propose cooking x ASMR or game commentary x a soothing character. The editing unit edits the video based on the characters and concepts proposed by the proposal unit. For example, the editing unit uses AI to automatically edit the video, adding cuts, background music, text overlays, effects, etc. The editing style can be selected from "casual" or "professional." The optimization unit performs SEO optimization of the video edited by the editing unit. For example, the optimization unit uses AI to automatically generate SEO-optimized titles, descriptions, and tags, and optimizes the posting timing based on data analysis. The prevention unit prevents the video optimized by the optimization unit from becoming a source of online controversy. For example, the prevention unit uses content auditing AI to perform pre-checks and provides comment filtering, moderation, a controversy detection system, and response guidelines. As a result, the video distribution debut support system according to the embodiment can propose characters and concepts that suit the user, perform video editing, optimize for SEO, and prevent online controversies.

[0074] The proposal team suggests characters and concepts tailored to each user. For example, the AI ​​analyzes the user's personality and hobbies to propose "the perfect video streaming style for you." Specifically, the AI ​​analyzes the user's profile information, past social media posts, and survey results to understand their interests, skills, and personality traits. Using natural language processing technology, the AI ​​analyzes the emotions and tone from the user's writing and comments to determine what kind of content the user is interested in and what style is suitable. For example, a user who is good at cooking and has a calm personality might be suggested a cooking x ASMR concept, while a user who likes games and has a sense of humor might be suggested a game commentary x soothing character concept. The proposal team also considers the user's target audience and market trends to select the most effective concept. This allows the proposal team to suggest the optimal video streaming style for the user, increasing the chances of success. Furthermore, the proposal team can provide feedback to the user on the suggested concept and fine-tune the concept as needed. This allows users to make their video streaming debut in the style that best suits them.

[0075] The editorial team edits videos based on characters and concepts proposed by the proposal team. For example, the editorial team uses AI to automatically edit, adding cuts, background music, text overlays, and effects. Specifically, the AI ​​analyzes raw footage shot by the user and automatically extracts important scenes and highlights. The AI ​​analyzes the content and audio of the video, cuts out unnecessary parts, and creates a video that is appealing to viewers. For example, in cooking videos, appropriate cuts and zooms are made to emphasize the cooking process and the beauty of the finished product. In game commentary videos, replays and slow motion are added to emphasize interesting moments and important gameplay scenes. The editorial team also adds background music, text overlays, and effects according to the editing style chosen by the user. A casual style uses bright and poppy background music and colorful text overlays, while a professional style uses calm background music and simple and sophisticated text overlays. This allows the editorial team to efficiently produce high-quality videos that match the user's concept. Furthermore, the editorial team provides an interface that allows users to review the edited content and request revisions as needed. This enables users to create videos that align with their intentions and deliver highly satisfying content.

[0076] The optimization team optimizes the SEO of videos edited by the editorial team. For example, the optimization team automatically generates SEO-optimized titles, descriptions, and tags using AI, and optimizes posting timing based on data analysis. Specifically, the AI ​​analyzes the video content and target audience, and selects keywords optimized for search engines and video distribution algorithms. For example, for cooking videos, it generates titles and descriptions that include keywords such as "easy recipes," "beginner-friendly," and "quick and easy cooking." The AI ​​also automatically generates tags related to the video content to make it easier for viewers to search. Furthermore, the optimization team analyzes past data and trends to suggest the optimal posting timing. For example, if there are many viewers on a particular day or time, posting the video at that time can maximize the number of views. This allows the optimization team to make it easier for users' videos to reach more viewers and promote channel growth. In addition, the optimization team can collect performance data after posting and suggest improvements for the next post. This allows users to continuously improve their SEO and enhance channel performance.

[0077] The prevention unit prevents controversies in videos optimized by the optimization unit. For example, the prevention unit uses content auditing AI for pre-checks and provides comment filtering, moderation, a controversy detection system, and response guidelines. Specifically, the content auditing AI analyzes video content to check for discriminatory, offensive, or inappropriate language. If a problem is detected, it sends a notification to the user prompting correction and provides specific correction suggestions as needed. The comment filtering system monitors posted comments in real time and automatically removes inappropriate comments. Furthermore, it provides moderation tools to allow users to manually manage comments. The controversy detection system monitors sudden changes in videos and comments to detect early signs of controversy. For example, it issues alerts if a specific keyword suddenly appears or if negative comments increase. Response guidelines provide specific methods for responding if a controversy occurs, supporting users in responding quickly and appropriately. This allows the prevention unit to minimize the risk of users' videos becoming controversial and support safe and healthy channel management. Furthermore, the prevention unit can continuously improve the system based on user feedback, providing more effective fire prevention measures.

[0078] The avatar generation unit can generate 2D / 3D avatars for people who are hesitant to show their faces. For example, the avatar generation unit uses AI to analyze the user's facial features and generate a 2D or 3D avatar. For example, the avatar generation unit can receive a photo of the user's face as input, and the AI ​​generates an avatar based on that photo. The avatar generation unit can also generate avatars based on a character style selected by the user. For example, the avatar generation unit can generate an avatar that matches the character style selected by the user. This makes it possible for people who are hesitant to show their faces to create VTuber-style videos. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input a photo of the user's face into a generation AI and have the generation AI perform avatar generation.

[0079] The planning and proposal department can propose video ideas based on trends and search volume. For example, the planning and proposal department can use AI to analyze trends and search volume and propose the most suitable video ideas to users. For example, the planning and proposal department can use AI to analyze current trends and propose video ideas based on those trends. The planning and proposal department can also analyze search volume and propose video ideas based on popular keywords. For example, the planning and proposal department can use AI to analyze search volume and propose video ideas based on popular keywords. This makes it possible to propose video ideas based on trends and search volume. Some or all of the above processes in the planning and proposal department may be performed using AI, or not. For example, the planning and proposal department can input trend and search volume data into a generating AI and have the generating AI generate video idea suggestions.

[0080] The data analysis department can analyze data after posting and provide suggestions for improvement to the next video. For example, the data analysis department can use AI to analyze data after posting and provide suggestions for improvement to the next video. For example, the data analysis department can analyze data such as the number of views, viewing time, and user feedback and provide suggestions for improvement to the next video. The data analysis department can also propose improvements based on viewer reactions. For example, the data analysis department can analyze viewer comments and ratings and propose improvements based on that. In this way, it can provide suggestions for improvement to the next video based on post-post data analysis. Some or all of the above processing in the data analysis department may be performed using AI, for example, or without AI. For example, the data analysis department can input data after posting into a generating AI and have the generating AI execute suggestions for improvement.

[0081] The comment filtering unit can perform comment filtering and moderation. For example, the comment filtering unit can use AI to filter comments and exclude spam and inappropriate comments. For example, the comment filtering unit can automatically filter comments containing specific keywords. The comment filtering unit can also use AI to analyze the content of comments and moderate inappropriate comments. For example, the comment filtering unit can use AI to analyze the content of comments and automatically delete inappropriate comments. This enables comment filtering and moderation. Some or all of the above processing in the comment filtering unit may be performed using AI, or without AI. For example, the comment filtering unit can input comment data into a generating AI and have the generating AI perform filtering and moderation.

[0082] The suggestion unit can estimate the user's emotions and adjust the suggested characters and concepts based on those emotions. For example, if the user is stressed, the suggestion unit can suggest relaxing, soothing characters and concepts. If the user is excited, the suggestion unit can suggest energetic and lively characters and concepts. If the user is depressed, the suggestion unit can suggest uplifting, positive characters and concepts. This allows the suggested characters and concepts to be adjusted based on 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 processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the suggested characters and concepts.

[0083] The suggestion unit can analyze a user's past video viewing history and propose the most suitable characters and concepts. For example, the suggestion unit can analyze the genres of videos the user has watched in the past and propose characters and concepts of the same genre. For example, the suggestion unit can also refer to the styles of creators the user frequently watches and propose similar characters and concepts. For example, the suggestion unit can analyze comments and ratings of videos the user has watched and propose popular characters and concepts. This allows the suggestion unit to propose the most suitable characters and concepts based on the user's past video viewing history. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's past video viewing history data into a generating AI and have the generating AI propose characters and concepts.

[0084] The suggestion unit can filter suggestions based on the user's current trends and areas of interest. For example, the suggestion unit can analyze topics the user is currently interested in and suggest characters and concepts related to those topics. The suggestion unit can also suggest relevant characters and concepts by referring to trends and hashtags the user is following. The suggestion unit can also suggest relevant characters and concepts based on keywords the user has recently searched for. This allows the suggestion unit to suggest characters and concepts based on the user's current trends and areas of interest. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input data on the user's current trends and areas of interest into a generating AI and have the generating AI perform the filtering of characters and concepts.

[0085] The suggestion unit can estimate the user's emotions and determine the priority of characters and concepts to suggest based on the estimated emotions. For example, if the user is relaxed, the suggestion unit will prioritize suggesting relaxing characters and concepts. If the user is excited, the suggestion unit may also prioritize suggesting energetic characters and concepts. If the user is depressed, the suggestion unit may also prioritize suggesting uplifting characters and concepts. This allows the priority of characters and concepts to be determined based on 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 suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI determine the priority of characters and concepts.

[0086] The suggestion unit can prioritize suggesting characters and concepts that are highly relevant to the user, taking into account the user's geographical location information. For example, the suggestion unit can suggest characters and concepts based on the culture and trends of the area where the user lives. For example, if the user is traveling, the suggestion unit can also suggest characters and concepts related to the tourist attractions and local products of that area. For example, if the user is participating in a specific event, the suggestion unit can also suggest characters and concepts related to that event. This allows for the suggestion of characters and concepts based on the user's geographical location information. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input the user's geographical location information data into a generating AI and have the generating AI perform the character and concept suggestion.

[0087] The suggestion unit can analyze the user's social media activity and propose relevant characters and concepts when making suggestions. For example, the suggestion unit can analyze the content of accounts the user follows on social media and propose relevant characters and concepts. For example, the suggestion unit can propose relevant characters and concepts based on content the user has shared on social media. For example, the suggestion unit can propose relevant characters and concepts by referring to topics in groups and communities the user participates in on social media. This allows for the suggestion of characters and concepts based on the user's social media activity. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's social media activity data into a generating AI and have the generating AI produce character and concept suggestions.

[0088] The editorial team can estimate the user's emotions and adjust the editing style based on those emotions. For example, if the user is relaxed, the editorial team can apply a relaxed editing style. If the user is in a hurry, the editorial team can also apply a fast-paced editing style. If the user is excited, the editorial team can also apply an editing style with visually stimulating effects. This allows the editorial team to adjust the editing style based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 editorial team may be performed using AI or not. For example, the editorial team can input user emotion data into a generative AI and have the generative AI perform the editing style adjustments.

[0089] The editorial team can adjust the level of detail in editing based on the importance of the video. For example, they can perform detailed editing on important scenes to make them easier for viewers to understand. They can also perform simplified editing on less important scenes to maintain the overall pace of the video. They can also add special effects or background music to emphasize important scenes. This allows them to adjust the level of detail in editing based on the importance of the video. Some or all of the above processes in the editorial team may be performed using AI, for example, or not. For example, the editorial team can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in editing.

[0090] The editorial team can apply different editing algorithms depending on the video category during editing. For example, for cooking videos, the editorial team can apply an editing algorithm that makes the cooking process easy to understand. For game commentary videos, the editorial team can also apply an editing algorithm that highlights important scenes during gameplay. For ASMR videos, the editorial team can also apply an editing algorithm that emphasizes the sound. This allows for the application of different editing algorithms depending on the video category. Some or all of the above processing in the editorial team may be performed using AI, for example, or not using AI. For example, the editorial team can input video category data into a generating AI and have the generating AI execute the application of the editing algorithm.

[0091] The editorial team can estimate the user's emotions and adjust the length of the edit based on those emotions. For example, if the user is relaxed, the editorial team can create a longer video with more detail. If the user is in a hurry, the editorial team can create a shorter, more concise video. If the user is excited, the editorial team can create a video with more visually stimulating effects. This allows the length of the edit to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editorial team may be performed using AI or not. For example, the editorial team can input user emotion data into a generative AI and have the generative AI adjust the length of the edit.

[0092] The editorial team can determine editing priorities based on when the videos were filmed. For example, they might prioritize editing the latest videos to provide trending content. They might also prioritize editing seasonal videos to attract viewers' attention. They might prioritize editing videos related to specific events to provide timely content. This allows them to determine editing priorities based on when the videos were filmed. Some or all of the above processes in the editorial team may be performed using AI, for example, or not. For example, the editorial team could input video filming date data into a generating AI and have the generating AI determine the editing priorities.

[0093] The editorial team can adjust the editing order based on the relevance of the videos during the editing process. For example, the editorial team can edit videos from the same series consecutively to ensure viewers enjoy consistent content. The editorial team can also edit videos on related topics together to provide viewers with highly relevant content. The editorial team can also prioritize editing videos on topics of high viewer interest to increase viewership. This allows for adjusting the editing order based on the relevance of the videos. Some or all of the above processes in the editorial team may be performed using AI, for example, or not. For example, the editorial team can input video relevance data into a generating AI and have the generating AI perform the adjustment of the editing order.

[0094] The optimization unit can estimate the user's emotions and adjust the SEO optimization content based on the estimated user emotions. For example, if the user is relaxed, the optimization unit can perform SEO optimization that includes relaxing keywords. For example, if the user is in a hurry, the optimization unit can also perform SEO optimization that will quickly appear in search results. For example, if the user is excited, the optimization unit can also perform SEO optimization that includes visually stimulating keywords. This allows the content of SEO optimization to be adjusted based on 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 optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input user emotion data into a generative AI and have the generative AI perform adjustments to the SEO optimization content.

[0095] The optimization unit can adjust the level of detail of the optimization based on the importance of the video during the optimization process. For example, the optimization unit can perform detailed SEO optimization on important videos to ensure they rank higher in search results. For example, the optimization unit can perform simplified SEO optimization on less important videos to optimize them efficiently. For example, the optimization unit can also optimize on highly important videos by emphasizing specific keywords. This allows the level of detail of the optimization to be adjusted based on the importance of the video. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the optimization.

[0096] The optimization unit can apply different optimization algorithms depending on the video category during optimization. For example, for cooking videos, the optimization unit can perform SEO optimization including keywords related to cooking. For example, for game commentary videos, the optimization unit can also perform SEO optimization including keywords related to games. For example, for ASMR videos, the optimization unit can also perform SEO optimization including keywords related to relaxation and healing. This allows different optimization algorithms to be applied depending on the video category. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video category data into a generating AI and have the generating AI execute the application of the optimization algorithm.

[0097] The optimization unit can estimate the user's emotions and determine optimization priorities based on the estimated emotions. For example, if the user is relaxed, the optimization unit will prioritize optimizing relaxing content. If the user is in a hurry, the optimization unit can also prioritize content that requires quick optimization. If the user is excited, the optimization unit can also prioritize optimizing visually stimulating content. This allows the optimization priority to be determined based on 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 optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input user emotion data into a generative AI and have the generative AI determine the optimization priority.

[0098] The optimization unit can determine optimization priorities based on the video's shooting date during the optimization process. For example, the optimization unit can prioritize optimizing the latest videos to provide content that aligns with trends. The optimization unit can also prioritize optimizing seasonal videos to attract viewer interest. For example, the optimization unit can prioritize optimizing videos related to specific events to provide timely content. This allows the optimization priority to be determined based on the video's shooting date. Some or all of the above-described processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video shooting date data into a generating AI and have the generating AI determine the optimization priority.

[0099] The optimization unit can adjust the optimization order based on the relevance of the videos during the optimization process. For example, the optimization unit can optimize videos from the same series consecutively to ensure viewers enjoy consistent content. The optimization unit can also optimize videos on related topics together to provide viewers with highly relevant content. For example, the optimization unit can prioritize the optimization of videos on topics of high viewer interest to increase viewership. This allows the optimization order to be adjusted based on the relevance of the videos. Some or all of the above-described processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video relevance data into a generating AI and have the generating AI perform the adjustment of the optimization order.

[0100] The prevention unit can estimate the user's emotions and adjust the content of its crisis prevention measures based on those emotions. For example, if the user is feeling stressed, the prevention unit may suggest avoiding content that is likely to cause a crisis. For example, if the user is excited, the prevention unit may display an alert to encourage calm judgment. For example, if the user is depressed, the prevention unit may prioritize suggesting positive content. This allows the content of crisis prevention measures to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the prevention unit may be performed using AI or not using AI. For example, the prevention unit can input user emotion data into a generative AI and have the generative AI adjust the content of crisis prevention measures.

[0101] The prevention unit can adjust the level of detail in prevention measures based on the importance of the video. For example, for important videos, the prevention unit can implement detailed crisis prevention measures to minimize risk. For less important videos, the prevention unit can implement simplified crisis prevention measures to efficiently prevent problems. For high-importance videos, the prevention unit can also emphasize specific keywords or phrases in its prevention measures. This allows the level of detail in prevention measures to be adjusted based on the importance of the video. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video importance data into a generating AI and have the generating AI adjust the level of detail in prevention measures.

[0102] The prevention unit can apply different prevention algorithms depending on the video category during prevention. For example, in cooking videos, the prevention unit can apply an algorithm to prevent controversy related to ingredients and cooking methods. For example, in game commentary videos, the prevention unit can apply an algorithm to prevent controversy related to violence or extreme language in games. For example, in ASMR videos, the prevention unit can apply an algorithm to prevent controversy related to sound and visual effects. This allows different prevention algorithms to be applied depending on the video category. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video category data into a generating AI and have the generating AI execute the application of the prevention algorithm.

[0103] The prevention unit can estimate the user's emotions and determine prevention priorities based on the estimated user emotions. For example, if the user is relaxed, the prevention unit will prioritize preventing relaxing content. For example, if the user is in a hurry, the prevention unit may also prioritize preventing content that requires quick prevention. For example, if the user is excited, the prevention unit may also prioritize preventing visually stimulating content. This allows the prevention priority to be determined based on 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 prevention unit may be performed using AI, for example, or not using AI. For example, the prevention unit can input user emotion data into a generative AI and have the generative AI determine the prevention priority.

[0104] The prevention unit can determine the priority of prevention based on the video's shooting date. For example, the prevention unit can prioritize preventing the latest videos and provide content that aligns with trends. The prevention unit can also prioritize preventing seasonal videos to attract viewers' attention. The prevention unit can also prioritize preventing videos related to specific events to provide timely content. This allows the prevention unit to determine the priority of prevention based on the video's shooting date. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video shooting date data into a generating AI and have the generating AI determine the priority of prevention.

[0105] The prevention unit can adjust the order of prevention based on the relevance of the videos. For example, the prevention unit can prevent videos from the same series consecutively so that viewers can enjoy consistent content. The prevention unit can also prevent videos on related topics together to provide viewers with highly relevant content. The prevention unit can also prioritize preventing videos on topics of high viewer interest to increase the number of views. This allows the order of prevention to be adjusted based on the relevance of the videos. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video relevance data into a generating AI and have the generating AI perform the adjustment of the prevention order.

[0106] The avatar generation unit can estimate the user's emotions and adjust the generated avatar based on the estimated emotions. For example, if the user is relaxed, the avatar generation unit can generate a relaxing avatar. For example, if the user is excited, the avatar generation unit can also generate an energetic avatar. For example, if the user is depressed, the avatar generation unit can also generate an uplifting avatar. In this way, the generated avatar can be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation 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 avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input user emotion data into the generation AI and have the generation AI adjust the generated avatar.

[0107] The avatar generation unit can generate the optimal avatar by analyzing the user's past avatar usage history during avatar generation. For example, the avatar generation unit can analyze the style of avatars the user has used in the past and generate similar avatars. For example, the avatar generation unit can generate the optimal avatar by referring to the characteristics of avatars that the user frequently uses. For example, the avatar generation unit can generate the optimal avatar based on the design of avatars that the user has evaluated in the past. This allows the system to generate the optimal avatar based on the user's past avatar usage history. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's past avatar usage history data into a generation AI and have the generation AI perform avatar generation.

[0108] The avatar generation unit can estimate the user's emotions and determine avatar priorities based on the estimated emotions. For example, if the user is relaxed, the avatar generation unit will prioritize generating relaxing avatars. For example, if the user is excited, the avatar generation unit may also prioritize generating energetic avatars. For example, if the user is depressed, the avatar generation unit may also prioritize generating uplifting avatars. This allows the avatar priorities to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 avatar generation unit may be performed using AI, or not using AI. For example, the avatar generation unit can input user emotion data into the generative AI and have the generative AI determine the avatar priorities.

[0109] The avatar generation unit can prioritize the generation of highly relevant avatars by considering the user's geographical location information during avatar generation. For example, the avatar generation unit can generate avatars based on the culture and trends of the region where the user lives. For example, if the user is traveling, the avatar generation unit can also generate avatars related to tourist attractions or local products of that region. For example, if the user is participating in a specific event, the avatar generation unit can also generate avatars related to that event. This allows for the generation of highly relevant avatars based on the user's geographical location information. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's geographical location information data into a generation AI and have the generation AI perform avatar generation.

[0110] The planning and proposal department can estimate the user's emotions and adjust the content of the proposal based on the estimated emotions. For example, if the user is relaxed, the planning and proposal department can propose a relaxing proposal. For example, if the user is excited, the planning and proposal department can propose an energetic proposal. For example, if the user is depressed, the planning and proposal department can propose an uplifting proposal. In this way, the content of the proposal can be adjusted based on 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 planning and proposal department may be performed using AI or not using AI. For example, the planning and proposal department can input user emotion data into a generative AI and have the generative AI adjust the content of the proposal.

[0111] The planning and proposal department can adjust the level of detail in a planning proposal based on the importance of the video. For example, for important videos, the planning and proposal department can provide a detailed planning proposal to make it easier for viewers to understand. For less important videos, the planning and proposal department can provide a simplified planning proposal to maintain the overall pace of the video. For highly important videos, the planning and proposal department can add special effects or background music to emphasize them. This allows the level of detail in the planning proposal to be adjusted based on the importance of the video. Some or all of the above processes in the planning and proposal department may be performed using AI, for example, or not. For example, the planning and proposal department can input video importance data into a generating AI and have the generating AI adjust the level of detail in the planning proposal.

[0112] The planning and proposal department can estimate the user's emotions and determine the priority of planning and proposals based on the estimated emotions. For example, if the user is relaxed, the planning and proposal department will prioritize suggesting relaxing ideas. For example, if the user is excited, the planning and proposal department may also prioritize suggesting energetic ideas. For example, if the user is depressed, the planning and proposal department may also prioritize suggesting uplifting ideas. This allows the department to determine the priority of planning and proposals based on 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 planning and proposal department may be performed using AI or not using AI. For example, the planning and proposal department can input user emotion data into a generative AI and have the generative AI determine the priority of planning and proposals.

[0113] The planning and proposal department can prioritize proposals based on the video shooting period when submitting proposals. For example, the planning and proposal department can prioritize proposing the latest videos to provide content that aligns with trends. For example, the planning and proposal department can also prioritize proposing seasonal videos to attract viewers' attention. For example, the planning and proposal department can prioritize proposing videos related to specific events to provide timely content. This allows the content of data analysis to be adjusted based on user emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, 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 analysis department may be performed using AI or not. For example, the data analysis department can input user emotion data into a generative AI and have the generative AI adjust the content of the data analysis.

[0114] The data analysis unit can adjust the level of detail in its data analysis based on the importance of the video. For example, for important videos, the data analysis unit can perform detailed data analysis to make it easier for viewers to understand. For less important videos, the data analysis unit can perform simplified data analysis to maintain the overall pace of the video. For highly important videos, the data analysis unit can add special effects or background music to emphasize them. This allows the level of detail in the data analysis to be adjusted based on the importance of the video. Some or all of the above processes in the data analysis unit may be performed using AI, for example, or not. For example, the data analysis unit can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the data analysis.

[0115] The data analysis unit can estimate the user's emotions and determine the priority of data analysis based on the estimated user emotions. For example, if the user is relaxed, the data analysis unit will prioritize relaxing data analysis. For example, if the user is excited, the data analysis unit may also prioritize energetic data analysis. For example, if the user is depressed, the data analysis unit may also prioritize uplifting data analysis. This allows the data analysis priority to be determined based on 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 analysis unit may be performed using AI or not using AI. For example, the data analysis unit can input user emotion data into a generative AI and have the generative AI determine the priority of data analysis.

[0116] The data analysis department can prioritize data analysis based on the video's shooting date. For example, the data analysis department can prioritize analyzing the latest videos to provide trending content. It can also prioritize analyzing seasonal videos to attract viewer interest. Furthermore, it can prioritize analyzing videos related to specific events to provide timely content. This allows the data analysis department to prioritize data analysis based on the video's shooting date. Some or all of the above processes in the data analysis department may be performed using AI, for example, or without AI. For example, the data analysis department can input video shooting date data into a generating AI and have the generating AI determine the priority of data analysis.

[0117] The comment filtering unit can estimate the user's emotions and adjust the content of the comment filtering based on the estimated emotions. For example, if the user is stressed, the comment filtering unit may prioritize filtering negative comments. For example, if the user is relaxed, the comment filtering unit may also prioritize displaying positive comments. For example, if the user is excited, the comment filtering unit may also filter out extreme comments. This allows the content of the comment filtering to be adjusted based on the user's emotions. 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 comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the comment filtering content.

[0118] The comment filtering unit can adjust the level of detail of the filtering based on the importance of the video when filtering comments. For example, the comment filtering unit can perform detailed comment filtering on important videos to minimize risk. For example, the comment filtering unit can perform simplified comment filtering on less important videos to filter efficiently. For example, the comment filtering unit can also emphasize specific keywords or phrases when filtering on high-importance videos. This allows the level of detail of the filtering to be adjusted based on the importance of the video. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the filtering.

[0119] The comment filtering unit can apply different filtering algorithms depending on the video category when filtering comments. For example, in cooking videos, the comment filtering unit can apply an algorithm that filters out negative comments about ingredients or cooking methods. For game commentary videos, the comment filtering unit can also apply an algorithm that filters out negative comments about violence or extreme language in games. For ASMR videos, the comment filtering unit can also apply an algorithm that filters out negative comments about sound or visual effects. This allows different filtering algorithms to be applied depending on the video category. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video category data into a generating AI and have the generating AI execute the application of the filtering algorithm.

[0120] The comment filtering unit can estimate the user's emotions and determine the priority of comment filtering based on the estimated user emotions. For example, if the user is relaxed, the comment filtering unit will prioritize displaying relaxing comments. For example, if the user is excited, the comment filtering unit may also prioritize displaying energetic comments. For example, if the user is depressed, the comment filtering unit may also prioritize displaying uplifting comments. This allows the priority of comment filtering to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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 comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input user emotion data into the generative AI and have the generative AI perform the determination of the comment filtering priority.

[0121] The comment filtering unit can determine filtering priorities based on the video's shooting date during comment filtering. For example, the comment filtering unit can prioritize filtering the latest videos to provide content that aligns with trends. For example, the comment filtering unit can prioritize filtering videos that are relevant to a particular season to attract viewers' attention. For example, the comment filtering unit can prioritize filtering videos related to a specific event to provide timely content. This allows the filtering priority to be determined based on the video's shooting date. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video shooting date data into a generating AI and have the generating AI determine the filtering priority.

[0122] The comment filtering unit can adjust the filtering order based on the relevance of the videos when filtering comments. For example, the comment filtering unit can filter videos from the same series consecutively so that viewers can enjoy consistent content. For example, the comment filtering unit can filter videos on related topics together to provide viewers with highly relevant content. For example, the comment filtering unit can prioritize filtering videos on topics of high interest to viewers to increase the number of views. This allows the filtering order to be adjusted based on the relevance of the videos. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video relevance data into a generating AI and have the generating AI perform the adjustment of the filtering order.

[0123] The comment filtering unit can estimate the user's emotions and determine the priority of comment filtering based on the estimated user emotions. For example, if the user is relaxed, the comment filtering unit will prioritize displaying relaxing comments. For example, if the user is excited, the comment filtering unit may also prioritize displaying energetic comments. For example, if the user is depressed, the comment filtering unit may also prioritize displaying uplifting comments. This allows the priority of comment filtering to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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 comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input user emotion data into the generative AI and have the generative AI perform the determination of the comment filtering priority.

[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 suggestion unit can analyze a user's past video viewing history and propose the most suitable characters and concepts. For example, the suggestion unit can analyze the genres of videos the user has watched in the past and propose characters and concepts of the same genre. For example, the suggestion unit can also refer to the styles of creators the user frequently watches and propose similar characters and concepts. For example, the suggestion unit can analyze comments and ratings of videos the user has watched and propose popular characters and concepts. This allows the suggestion unit to propose the most suitable characters and concepts based on the user's past video viewing history. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's past video viewing history data into a generating AI and have the generating AI propose characters and concepts.

[0126] The avatar generation unit can estimate the user's emotions and adjust the generated avatar based on the estimated emotions. For example, if the user is relaxed, the avatar generation unit can generate a relaxing avatar. For example, if the user is excited, the avatar generation unit can also generate an energetic avatar. For example, if the user is depressed, the avatar generation unit can also generate an uplifting avatar. In this way, the generated avatar can be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation 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 avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input user emotion data into the generation AI and have the generation AI adjust the generated avatar.

[0127] The planning and proposal department can estimate the user's emotions and adjust the content of the proposal based on the estimated emotions. For example, if the user is relaxed, the planning and proposal department can propose a relaxing proposal. For example, if the user is excited, the planning and proposal department can propose an energetic proposal. For example, if the user is depressed, the planning and proposal department can propose an uplifting proposal. In this way, the content of the proposal can be adjusted based on 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 planning and proposal department may be performed using AI or not using AI. For example, the planning and proposal department can input user emotion data into a generative AI and have the generative AI adjust the content of the proposal.

[0128] The data analysis unit can estimate the user's emotions and determine the priority of data analysis based on the estimated user emotions. For example, if the user is relaxed, the data analysis unit will prioritize relaxing data analysis. For example, if the user is excited, the data analysis unit may also prioritize energetic data analysis. For example, if the user is depressed, the data analysis unit may also prioritize uplifting data analysis. This allows the data analysis priority to be determined based on 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 analysis unit may be performed using AI or not using AI. For example, the data analysis unit can input user emotion data into a generative AI and have the generative AI determine the priority of data analysis.

[0129] The comment filtering unit can estimate the user's emotions and adjust the content of the comment filtering based on the estimated emotions. For example, if the user is stressed, the comment filtering unit may prioritize filtering negative comments. For example, if the user is relaxed, the comment filtering unit may also prioritize displaying positive comments. For example, if the user is excited, the comment filtering unit may also filter out extreme comments. This allows the content of the comment filtering to be adjusted based on the user's emotions. 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 comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the comment filtering content.

[0130] The suggestion unit can filter suggestions based on the user's current trends and areas of interest. For example, the suggestion unit can analyze topics the user is currently interested in and suggest characters and concepts related to those topics. The suggestion unit can also suggest relevant characters and concepts by referring to trends and hashtags the user is following. The suggestion unit can also suggest relevant characters and concepts based on keywords the user has recently searched for. This allows the suggestion unit to suggest characters and concepts based on the user's current trends and areas of interest. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input data on the user's current trends and areas of interest into a generating AI and have the generating AI perform the filtering of characters and concepts.

[0131] The editorial team can adjust the level of detail in editing based on the importance of the video. For example, they can perform detailed editing on important scenes to make them easier for viewers to understand. They can also perform simplified editing on less important scenes to maintain the overall pace of the video. They can also add special effects or background music to emphasize important scenes. This allows them to adjust the level of detail in editing based on the importance of the video. Some or all of the above processes in the editorial team may be performed using AI, for example, or not. For example, the editorial team can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in editing.

[0132] The optimization unit can adjust the level of detail of the optimization based on the importance of the video during the optimization process. For example, the optimization unit can perform detailed SEO optimization on important videos to ensure they rank higher in search results. For example, the optimization unit can perform simplified SEO optimization on less important videos to optimize them efficiently. For example, the optimization unit can also optimize on highly important videos by emphasizing specific keywords. This allows the level of detail of the optimization to be adjusted based on the importance of the video. Some or all of the above processes in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input video importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the optimization.

[0133] The prevention unit can apply different prevention algorithms depending on the video category during prevention. For example, in cooking videos, the prevention unit can apply an algorithm to prevent controversy related to ingredients and cooking methods. For example, in game commentary videos, the prevention unit can apply an algorithm to prevent controversy related to violence or extreme language in games. For example, in ASMR videos, the prevention unit can apply an algorithm to prevent controversy related to sound and visual effects. This allows different prevention algorithms to be applied depending on the video category. Some or all of the above processing in the prevention unit may be performed using AI, for example, or without AI. For example, the prevention unit can input video category data into a generating AI and have the generating AI execute the application of the prevention algorithm.

[0134] The comment filtering unit can apply different filtering algorithms depending on the video category when filtering comments. For example, in cooking videos, the comment filtering unit can apply an algorithm that filters out negative comments about ingredients or cooking methods. For game commentary videos, the comment filtering unit can also apply an algorithm that filters out negative comments about violence or extreme language in games. For ASMR videos, the comment filtering unit can also apply an algorithm that filters out negative comments about sound or visual effects. This allows different filtering algorithms to be applied depending on the video category. Some or all of the above processing in the comment filtering unit may be performed using AI, for example, or without AI. For example, the comment filtering unit can input video category data into a generating AI and have the generating AI execute the application of the filtering algorithm.

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

[0136] Step 1: The proposal team suggests characters and concepts that suit the user. For example, the proposal team uses AI to analyze the user's personality and hobbies and suggest "the perfect video streaming style for you." Specifically, they can suggest things like cooking x ASMR or game commentary x soothing characters. Step 2: The editorial team edits the video based on the characters and concepts proposed by the proposal team. The editorial team, for example, uses AI to automatically edit, adding cuts, background music, text overlays, effects, etc. Editing styles can be selected from "Casual" or "Professional". Step 3: The optimization team performs SEO optimization on the videos edited by the editorial team. For example, the optimization team automatically generates SEO-optimized titles, descriptions, and tags using AI, and also optimizes the posting timing based on data analysis. Step 4: The prevention unit prevents the video optimized by the optimization unit from going viral. For example, the prevention unit uses content auditing AI to perform pre-checks and provides comment filtering and moderation, a viral content detection system, and response guidelines.

[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 mentioned above, including the proposal unit, editing unit, optimization unit, prevention unit, avatar generation unit, project proposal unit, data analysis unit, and comment filtering unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the proposal unit is implemented by the control unit 46A of the smart device 14 and proposes characters and concepts that suit the user. The editing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and edits the video. The optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs SEO optimization. The prevention unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and prevents online firestorms. The avatar generation unit is implemented by, for example, the control unit 46A of the smart device 14 and generates 2D / 3D avatars. The project proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes video ideas. The data analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes data after posting and provides improvement suggestions. The comment filtering unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and performs comment filtering and moderation. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[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 mentioned above, including the proposal unit, editing unit, optimization unit, prevention unit, avatar generation unit, planning proposal unit, data analysis unit, and comment filtering unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the proposal unit is implemented by the control unit 46A of the smart glasses 214 and proposes characters and concepts that suit the user. The editing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs video editing. The optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs SEO optimization. The prevention unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and prevents online controversies. The avatar generation unit is implemented by, for example, the control unit 46A of the smart glasses 214 and generates 2D / 3D avatars. The planning proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes video ideas. The data analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the data after posting and provides improvement suggestions. The comment filtering unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and performs comment filtering and moderation. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[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 mentioned above, including the proposal unit, editing unit, optimization unit, prevention unit, avatar generation unit, project proposal unit, data analysis unit, and comment filtering unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the proposal unit is implemented by the control unit 46A of the headset terminal 314 and proposes characters and concepts that suit the user. The editing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs video editing. The optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs SEO optimization. The prevention unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and prevents online controversies. The avatar generation unit is implemented by, for example, the control unit 46A of the headset terminal 314 and generates 2D / 3D avatars. The project proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes video ideas. The data analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the data after posting and provides improvement suggestions. The comment filtering unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and performs comment filtering and moderation. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[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 mentioned above, including the proposal unit, editing unit, optimization unit, prevention unit, avatar generation unit, planning proposal unit, data analysis unit, and comment filtering unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the proposal unit is implemented by the control unit 46A of the robot 414 and proposes characters and concepts that suit the user. The editing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and edits the video. The optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs SEO optimization. The prevention unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and prevents online controversies. The avatar generation unit is implemented by, for example, the control unit 46A of the robot 414 and generates 2D / 3D avatars. The planning proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes video ideas. The data analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes data after posting and provides improvement suggestions. The comment filtering unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and performs comment filtering and moderation. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[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) The proposal department proposes characters and concepts that suit the user, The editorial department edits the video based on the characters and concepts proposed by the aforementioned proposal department, The Optimization Department performs SEO optimization on videos edited by the aforementioned Editorial Department, The system includes a prevention unit that prevents the video optimized by the optimization unit from becoming controversial. A system characterized by the following features. (Note 2) For people who are hesitant to show their face, It includes an avatar generation unit that generates 2D / 3D avatars. The system described in Appendix 1, characterized by the features described herein. (Note 3) Based on trends and search volume, We have a planning and proposal department that proposes video ideas. The system described in Appendix 1, characterized by the features described herein. (Note 4) Analyze the data after posting, We have a data analysis department that provides suggestions for improvement to the next video. The system described in Appendix 1, characterized by the features described herein. (Note 5) Perform comment filtering and moderation. Equipped with a comment filtering function. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned proposal section is, The system estimates the user's emotions and adjusts the proposed characters and concepts based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned proposal section is, We analyze the user's past video viewing history and suggest the most suitable characters and concepts. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned proposal section is, When making suggestions, filter them based on the user's current trends and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned proposal section is, It estimates the user's emotions and determines the priority of suggested characters and concepts based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned proposal section is, When making proposals, we prioritize suggesting characters and concepts that are highly relevant to the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned proposal section is, When making a proposal, we analyze the user's social media activity and suggest relevant characters and concepts. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned editorial department, It estimates the user's emotions and adjusts the editing style based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned editorial department, During editing, 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 14) The aforementioned editorial department, During editing, different editing algorithms are applied depending on the video category. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned editorial department, It estimates the user's emotions and adjusts the length of the edit based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned editorial department, When editing, prioritize editing based on when the video was shot. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned editorial department, During editing, adjust the editing order based on the relevance of the videos. The system described in Appendix 1, characterized by the features described herein. (Note 18) The optimization unit, It estimates user sentiment and adjusts SEO optimization based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The optimization unit, During optimization, 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 20) The optimization unit, During optimization, different optimization algorithms are applied depending on the video category. The system described in Appendix 1, characterized by the features described herein. (Note 21) The optimization unit, It estimates user emotions and determines optimization priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The optimization unit, During optimization, the optimization priority is determined based on when the video was shot. The system described in Appendix 1, characterized by the features described herein. (Note 23) The optimization unit, During optimization, the optimization order is adjusted based on the relevance of the videos. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned prevention unit is We estimate user sentiment and adjust the content of our crisis prevention measures based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned prevention unit is When preventing an attack, 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 26) The aforementioned prevention unit is When preventing unauthorized access, different prevention algorithms are applied depending on the video category. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned prevention unit is The system estimates user sentiment and determines prevention priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned prevention unit is When implementing preventative measures, prioritize prevention based on when the video was recorded. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned prevention unit is When preventing an attack, adjust the order of prevention based on the relevance of the videos. The system described in Appendix 1, characterized by the features described herein. (Note 30) The avatar generation unit is, It estimates the user's emotions and adjusts the generated avatar based on those emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The avatar generation unit is, When generating an avatar, the system analyzes the user's past avatar usage history to create the most suitable avatar. The system described in Appendix 2, characterized by the features described herein. (Note 32) The avatar generation unit is, It estimates the user's emotions and determines avatar priorities based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The avatar generation unit is, When generating avatars, the system prioritizes generating highly relevant avatars by taking into account the user's geographical location information. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned Planning and Proposal Department, We estimate the user's emotions and adjust the content of the project proposal based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned Planning and Proposal Department When proposing a project, adjust the level of detail in the proposal based on the importance of the video. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned Planning and Proposal Department, The system estimates user emotions and prioritizes project proposals based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned Planning and Proposal Department, When proposing a project, prioritize the project proposals based on the timing of the video shoots. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned data analysis unit, We estimate the user's emotions and adjust the data analysis based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned data analysis unit, When analyzing data, adjust the level of detail based on the importance of the video. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned data analysis unit, We estimate user sentiment and prioritize data analysis based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned data analysis unit, When analyzing data, prioritize data analysis based on when the videos were filmed. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned comment filtering unit is, It estimates the user's sentiment and adjusts the comment filtering based on the estimated sentiment. The system described in Appendix 5, characterized by the features described herein. (Note 43) The aforementioned comment filtering unit is, When filtering comments, adjust the level of filtering based on the importance of the video. The system described in Appendix 5, characterized by the features described herein. (Note 44) The aforementioned comment filtering unit is, When filtering comments, different filtering algorithms are applied depending on the video category. The system described in Appendix 5, characterized by the features described herein. (Note 45) The aforementioned comment filtering unit is, The system estimates the user's sentiment and determines the priority of comment filtering based on the estimated user sentiment. The system described in Appendix 5, characterized by the features described herein. (Note 46) The aforementioned comment filtering unit is, When filtering comments, the filtering priority is determined based on when the video was filmed. The system described in Appendix 5, characterized by the features described herein. (Note 47) The aforementioned comment filtering unit is, When filtering comments, adjust the filtering order based on the relevance of the video. The system described in Appendix 5, 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. The proposal department proposes characters and concepts that suit the user, The editorial department edits the video based on the characters and concepts proposed by the aforementioned proposal department, The Optimization Department performs SEO optimization on videos edited by the aforementioned Editorial Department, The system includes a prevention unit that prevents the video optimized by the optimization unit from becoming controversial. A system characterized by the following features.

2. For people who are hesitant to show their face, It includes an avatar generation unit that generates 2D / 3D avatars. The system according to feature 1.

3. Based on trends and search volume, We have a planning and proposal department that proposes video ideas. The system according to feature 1.

4. Analyze the data after posting, We have a data analysis department that provides suggestions for improvement to the next video. The system according to feature 1.

5. Perform comment filtering and moderation. Equipped with a comment filtering function. The system according to feature 1.

6. The aforementioned proposal section is, The system estimates the user's emotions and adjusts the proposed characters and concepts based on those estimated emotions. The system according to feature 1.

7. The aforementioned proposal section is, We analyze the user's past video viewing history and suggest the most suitable characters and concepts. The system according to feature 1.

8. The aforementioned proposal section is, When making suggestions, filter them based on the user's current trends and areas of interest. The system according to feature 1.

9. The aforementioned proposal section is, It estimates the user's emotions and determines the priority of suggested characters and concepts based on those estimated emotions. The system according to feature 1.

10. The aforementioned proposal section is, When making proposals, we prioritize suggesting characters and concepts that are highly relevant to the user's geographical location. The system according to feature 1.

Images