System

Abstract

An object of a system according to an embodiment is to efficiently perform a localization operation of a moving image.SOLUTION: A system according to an embodiment includes an analysis unit, a translation unit, a thumbnail generation unit, a title generation unit, and an upload unit. The analysis unit analyzes the content of the moving image. The translation unit translates the subtitle or the voice based on the content analyzed by the analysis unit. The thumbnail generation unit generates a thumbnail based on the content translated by the translation unit. The title generation unit generates a title based on the content translated by the translation unit. The uploader uploads the localized video including the thumbnail and the title generated by the thumbnail generator and the title generator to the platform selected by the distributor.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, localizing videos was a time-consuming process and difficult to do efficiently.

[0005] The system according to the embodiment aims to efficiently perform video localization work. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a translation unit, a thumbnail generation unit, a title generation unit, and an upload unit. The analysis unit analyzes the content of a video. The translation unit translates subtitles or audio based on the content analyzed by the analysis unit. The thumbnail generation unit generates thumbnails based on the content translated by the translation unit. The title generation unit generates titles based on the content translated by the translation unit. The upload unit uploads the localized video, including the thumbnail and title generated by the thumbnail generation unit and the title generation unit, to a platform selected by the distributor. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently perform video localization work. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A localization support system according to an embodiment of the present invention reduces the effort required for streamers to localize videos and enables them to distribute them worldwide. In this system, streamers upload videos, the system analyzes the content of the video, and translates the subtitles and audio into the languages ​​of each country. Generative AI is used to provide natural-sounding translations. It is also possible to convert to appropriate expressions taking cultural differences into account. Furthermore, the localization support system generates thumbnails and titles that are optimal for viewers in each country based on the content of the video. Finally, the localized video is automatically uploaded to a platform selected by the streamer. For example, in this system, a streamer uploads a video. The localization support system analyzes the content of the video and translates the subtitles and audio into the languages ​​of each country. Generative AI is used to provide natural-sounding translations. For example, the generative AI receives a prompt such as "Please translate the content of this video" and translates the video content. The localization support system is also capable of converting to appropriate expressions taking cultural differences into account. For example, the generative AI receives a prompt such as "Please convert this expression into a culturally appropriate one" and converts it to the appropriate expression. Next, the localization support system generates thumbnails and titles that are optimal for viewers in each country based on the content of the video. For example, the localization support system analyzes the content of the video and generates thumbnails that are optimal for the viewer. The localization support system also analyzes the content of the video and generates titles that are optimal for the viewer. Finally, the localization support system automatically uploads the localized video to the platform selected by the distributor. This allows distributors to localize videos and distribute them worldwide without any hassle. This allows distributors to localize videos and distribute them worldwide without any hassle. For example, distributors can significantly reduce the effort required for localization and increase page views and revenue.

[0029] A localization support system according to an embodiment includes an analysis unit, a translation unit, a thumbnail generation unit, a title generation unit, and an upload unit. The analysis unit analyzes the content of a video. The content of the video may include, but is not limited to, video, audio, and text information. For example, the analysis unit analyzes the video and extracts important scenes. The analysis unit can also analyze the audio of the video and convert the audio content into text. The analysis unit can also analyze the text information of the video and extract important keywords. For example, the analysis unit uses video analysis technology to extract important scenes of the video. The analysis unit can also convert the audio content into text using speech recognition technology. The analysis unit can also extract important keywords from the text information using natural language processing technology. The translation unit uses a generation AI to translate subtitles and audio based on the content analyzed by the analysis unit. The translation may be performed by, for example, machine translation or expert translation, but is not limited to, these examples. For example, the translation unit uses a generation AI to translate subtitles. The translation unit can also translate audio using a generation AI. The translation unit can also use the generation AI to convert to appropriate expressions taking cultural differences into consideration. For example, the generation AI can translate subtitles into natural expressions using a text generation AI (e.g., LLM). The generation AI can also translate audio into natural expressions using a speech generation AI. The generation AI can also convert to appropriate expressions taking cultural differences into consideration. The thumbnail generation unit generates thumbnails based on the content translated by the translation unit. Thumbnails are generated according to, for example, image selection criteria, size, resolution, and other criteria, but are not limited to these examples. For example, the thumbnail generation unit uses image recognition technology to generate thumbnails based on the content of the video. The thumbnail generation unit can also generate optimal thumbnails taking viewer attribute information into consideration. The thumbnail generation unit can also generate optimal thumbnails taking into consideration the cultural background of the viewing region. For example, the thumbnail generation unit uses image recognition technology to generate thumbnails based on the content of the video.The thumbnail generation unit may also generate an optimal thumbnail by taking into account viewer attribute information. The thumbnail generation unit may also generate an optimal thumbnail by taking into account the cultural background of the viewing region. The title generation unit generates a title based on the content translated by the translation unit. The title may be generated according to, for example, but not limited to, criteria such as keyword selection criteria and character limit. For example, the title generation unit may generate a title based on the content of the video using natural language processing technology. The title generation unit may also generate an optimal title by taking into account viewer attribute information. The title generation unit may also generate an optimal title by taking into account the cultural background of the viewing region. For example, the title generation unit may generate a title based on the content of the video using natural language processing technology. The title generation unit may also generate an optimal title by taking into account viewer attribute information. The title generation unit may also generate an optimal title by taking into account the cultural background of the viewing region. The upload unit uploads the localized video including the thumbnail and title generated by the thumbnail generation unit and the title generation unit to a platform selected by the distributor. The upload may be performed automatically to, for example, but not limited to, the platform selected by the distributor. For example, the uploading unit may automatically upload a localized video to a platform selected by the distributor. Alternatively, the uploading unit may manually upload to a platform selected by the distributor. Alternatively, the uploading unit may upload to a platform selected by the distributor according to a schedule. For example, the uploading unit may automatically upload a localized video to a platform selected by the distributor. Alternatively, the uploading unit may manually upload to a platform selected by the distributor. Alternatively, the uploading unit may upload to a platform selected by the distributor according to a schedule. In this way, the localization support system according to the embodiment allows distributors to localize videos and distribute them worldwide without any hassle.For example, distributors can significantly reduce the effort required for localization and increase page views and revenue.

[0030] The translation unit can translate subtitles and audio using a generation AI. The generation AI includes, but is not limited to, a specific AI model and training data, for example. The translation unit translates subtitles using, for example, a generation AI. For example, the generation AI translates subtitles into natural-looking expressions using a text generation AI (e.g., LLM). The translation unit can also translate audio using the generation AI. For example, the generation AI translates audio into natural-looking expressions using an audio generation AI. The translation unit can also convert audio into appropriate expressions taking cultural differences into consideration using the generation AI. For example, the generation AI converts audio into appropriate expressions taking cultural differences into consideration. In this way, natural translations are provided by using the generation AI. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can translate subtitles and audio using a generation AI.

[0031] The translation unit can convert expressions using a generation AI while taking cultural differences into consideration. Cultural differences include, but are not limited to, differences in expressions and taboos in a particular culture. The translation unit can, for example, use a generation AI to convert to an appropriate expression while taking cultural differences into consideration. For example, the generation AI converts to an appropriate expression while taking cultural differences into consideration. The translation unit can also, for example, use a generation AI to convert to an appropriate expression while taking cultural differences into consideration. For example, the generation AI converts to an appropriate expression while taking cultural differences into consideration. The translation unit can also, for example, use a generation AI to convert to an appropriate expression while avoiding taboos. For example, the generation AI converts to an appropriate expression while avoiding taboos. This provides an appropriate expression while taking cultural differences into consideration. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can, for example, use a generation AI to convert to an appropriate expression while taking cultural differences into consideration.

[0032] The thumbnail generation unit can generate thumbnails suitable for viewers in each country. Examples of thumbnails suitable for viewers in each country include, but are not limited to, color, design, and content. The thumbnail generation unit can generate thumbnails based on the content of a video using, for example, image recognition technology. For example, the thumbnail generation unit can generate thumbnails based on the content of a video using image recognition technology. The thumbnail generation unit can also generate optimal thumbnails by taking into account viewer attribute information. For example, the thumbnail generation unit can generate optimal thumbnails by taking into account viewer attribute information. The thumbnail generation unit can also generate optimal thumbnails by taking into account the cultural background of the viewing region. For example, the thumbnail generation unit can generate optimal thumbnails by taking into account the cultural background of the viewing region. This provides optimal thumbnails to viewers in each country. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit can generate thumbnails suitable for viewers in each country using AI.

[0033] The title generation unit can generate titles suitable for viewers in each country. Examples of titles suitable for viewers in each country include, but are not limited to, language, cultural background, and trends. The title generation unit can generate titles based on the content of the video using, for example, natural language processing technology. For example, the title generation unit can generate titles based on the content of the video using natural language processing technology. The title generation unit can also generate optimal titles taking into account viewer attribute information. For example, the title generation unit can generate optimal titles taking into account viewer attribute information. The title generation unit can also generate optimal titles taking into account the cultural background of the viewing region. For example, the title generation unit can generate optimal titles taking into account the cultural background of the viewing region. This provides optimal titles to viewers in each country. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can generate titles suitable for viewers in each country using AI.

[0034] The uploading unit can upload the localized video to a platform selected by the distributor. Examples of localized videos include, but are not limited to, translation accuracy and cultural adaptation. The uploading unit, for example, automatically uploads the localized video to a platform selected by the distributor. For example, the uploading unit automatically uploads the localized video to a platform selected by the distributor. The uploading unit can also manually upload the video to a platform selected by the distributor. For example, the uploading unit manually uploads the video to a platform selected by the distributor. The uploading unit can also upload the video to a platform selected by the distributor according to a schedule. For example, the uploading unit uploads the video to a platform selected by the distributor according to a schedule. In this way, the localized video is automatically uploaded. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to upload the localized video to a platform selected by the distributor.

[0035] The localization support system includes a manual correction unit that allows a distributor to check and correct the content. The manual correction unit provides an interface for the distributor to make final checks and corrections. For example, the manual correction unit allows the distributor to check the translated content of subtitles and audio and correct it as necessary. The manual correction unit also allows the distributor to check the content of thumbnails and titles and correct it as necessary. For example, the manual correction unit provides an interface for the distributor to check and correct the translated content of subtitles. The manual correction unit can also provide an interface for the distributor to check and correct the translated content of audio. The manual correction unit can also provide an interface for the distributor to check and correct the content of thumbnails. For example, the manual correction unit provides an interface for the distributor to check and correct the content of titles. This allows the distributor to make final checks and corrections. Some or all of the above-described processing in the manual correction unit may be performed, for example, using AI or without AI. For example, the manual correction unit can use AI to provide an interface for the distributor to check and correct the content.

[0036] When analyzing the content of a video, the analysis unit can apply different analysis algorithms depending on the genre or theme of the video. Genres and themes include, but are not limited to, movies, documentaries, and education. For example, in the case of an educational video, the analysis unit applies an algorithm that emphasizes important points. For example, in the case of an educational video, the analysis unit applies an algorithm that emphasizes important points. In addition, in the case of an entertainment video, the analysis unit can also apply an algorithm that emphasizes visual elements. For example, in the case of an entertainment video, the analysis unit can also apply an algorithm that emphasizes fact-checking. In addition, in the case of a news video, the analysis unit can apply an algorithm that emphasizes fact-checking. For example, in the case of a news video, the analysis unit applies an algorithm that emphasizes fact-checking. In this way, analysis is performed depending on the genre or theme of the video. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, when analyzing the content of a video using AI, the analysis unit can apply different analysis algorithms depending on the genre or theme of the video.

[0037] When analyzing a video, the analysis unit can improve the accuracy of the analysis by referring to past analysis results. Past analysis results include, for example, analysis results of past videos of the same genre or analysis results of past videos of the same broadcaster, but are not limited to these examples. The analysis unit can improve the accuracy by referring to past analysis results of videos of the same genre. For example, the analysis unit can improve the accuracy by referring to past analysis results of videos of the same genre. The analysis unit can also improve the accuracy by referring to past analysis results of videos of the same broadcaster. For example, the analysis unit can improve the accuracy by referring to past analysis results of videos of the same broadcaster. The analysis unit can also improve the accuracy by referring to past analysis results of videos of the same viewer demographic. For example, the analysis unit can improve the accuracy by referring to past analysis results of videos of the same viewer demographic. In this way, the accuracy of the analysis is improved by referring to past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can improve the accuracy of the analysis by referring to past analysis results when analyzing a video using AI.

[0038] When analyzing a video, the analysis unit can determine an analysis priority based on the viewing history of the video. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the analysis unit prioritizes analyzing videos that have been viewed many times. For example, the analysis unit prioritizes analyzing videos that have been viewed many times. The analysis unit can also prioritize analyzing videos that have been viewed for a long time. For example, the analysis unit prioritizes analyzing videos that have been viewed for a long time. The analysis unit can also prioritize analyzing videos that have been highly rated by viewers. For example, the analysis unit prioritizes analyzing videos that have been highly rated by viewers. In this way, the analysis priority is determined taking into account the viewing history of the video. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use AI to determine an analysis priority based on the viewing history of the video when analyzing the video.

[0039] When analyzing a video, the analysis unit can perform analysis based on attribute information of viewers of the video. Viewer attribute information includes, for example, age, gender, region, and interests, but is not limited to these examples. The analysis unit, for example, changes the focus of analysis depending on the viewer's age group. For example, the analysis unit changes the focus of analysis depending on the viewer's age group. The analysis unit can also change the focus of analysis depending on the viewer's gender. For example, the analysis unit changes the focus of analysis depending on the viewer's gender. The analysis unit can also change the focus of analysis depending on the viewer's interests. For example, the analysis unit changes the focus of analysis depending on the viewer's interests. In this way, analysis is performed taking into account the viewer's attribute information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use AI to perform analysis based on the viewer's attribute information when analyzing a video.

[0040] When analyzing a video, the analysis unit can weight the analysis based on the viewing region of the video. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The analysis unit, for example, weights the analysis by taking into account the cultural background of the viewing region. For example, the analysis unit weights the analysis by taking into account the cultural background of the viewing region. The analysis unit can also weight the analysis by taking into account the language of the viewing region. For example, the analysis unit weights the analysis by taking into account the language of the viewing region. The analysis unit can also weight the analysis by taking into account trends in the viewing region. For example, the analysis unit weights the analysis by taking into account trends in the viewing region. In this way, the analysis is weighted based on the viewing region. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use AI to weight the analysis based on the viewing region of the video when analyzing a video.

[0041] When analyzing a video, the analysis unit can improve the accuracy of the analysis by referring to literature related to the video. Related literature includes, but is not limited to, academic papers, technical reports, industry reports, etc. For example, the analysis unit can improve the accuracy of the analysis by referring to related academic papers. For example, the analysis unit can improve the accuracy of the analysis by referring to related academic papers. The analysis unit can also improve the accuracy of the analysis by referring to related news articles. For example, the analysis unit can improve the accuracy of the analysis by referring to related news articles. The analysis unit can also improve the accuracy of the analysis by referring to related books. For example, the analysis unit can improve the accuracy of the analysis by referring to related books. In this way, the accuracy of the analysis is improved by referring to related literature. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use AI to improve the accuracy of the analysis by referring to literature related to the video when analyzing the video.

[0042] The translation unit can apply different translation algorithms depending on the genre or theme of the video during translation. Examples of translation algorithms include, but are not limited to, neural networks and rule-based translation. For example, in the case of an educational video, the translation unit applies an algorithm that accurately translates technical terms. For example, in the case of an educational video, the translation unit applies an algorithm that accurately translates technical terms. In addition, the translation unit can apply an algorithm that emphasizes visual elements in the case of an entertainment video. For example, the translation unit can apply an algorithm that emphasizes visual elements in the case of an entertainment video. In addition, the translation unit can apply an algorithm that emphasizes fact-checking in the case of a news video. For example, the translation unit applies an algorithm that emphasizes fact-checking in the case of a news video. In this way, translation is performed according to the genre or theme. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can use a generation AI to apply different translation algorithms depending on the genre or theme of the video during translation.

[0043] The translation unit can improve the accuracy of translation by referring to past translation results during translation. Past translation results include, but are not limited to, past translation results of the same genre or past translation results of the same distributor, for example. The translation unit can improve the accuracy by referring to past translation results of the same genre. For example, the translation unit can improve the accuracy by referring to past translation results of the same genre. The translation unit can also improve the accuracy by referring to past translation results of the same distributor. For example, the translation unit can improve the accuracy by referring to past translation results of the same distributor. The translation unit can also improve the accuracy by referring to past translation results of the same viewer demographic. For example, the translation unit can improve the accuracy by referring to past translation results of the same viewer demographic. In this way, the accuracy of the translation is improved by referring to past translation results. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can improve the accuracy of translation by referring to past translation results during translation using a generation AI.

[0044] The translation unit can determine the translation priority based on the video viewing history during translation. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the translation unit prioritizes translating videos that have been viewed many times. For example, the translation unit prioritizes translating videos that have been viewed many times. The translation unit can also prioritize translating videos that have been viewed for a long time. For example, the translation unit prioritizes translating videos that have been viewed for a long time. The translation unit can also prioritize translating videos that have been highly rated by viewers. For example, the translation unit prioritizes translating videos that have been highly rated by viewers. In this way, the translation priority is determined taking the viewing history into consideration. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can use a generation AI to determine the translation priority based on the video viewing history during translation.

[0045] The translation unit can perform translation based on attribute information of the viewer of the video during translation. Viewer attribute information includes, but is not limited to, age, gender, region, and interests. The translation unit, for example, changes the translation expression according to the viewer's age group. For example, the translation unit changes the translation expression according to the viewer's age group. The translation unit can also change the translation expression according to the viewer's gender. For example, the translation unit changes the translation expression according to the viewer's gender. The translation unit can also change the translation expression according to the viewer's interests. For example, the translation unit changes the translation expression according to the viewer's interests. In this way, translation is performed taking into account the viewer's attribute information. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can use a generation AI to perform translation based on the viewer's attribute information during translation.

[0046] The translation unit can weight the translation based on the viewing region of the video during translation. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The translation unit can weight the translation by taking into account the cultural background of the viewing region. For example, the translation unit can weight the translation by taking into account the cultural background of the viewing region. The translation unit can also weight the translation by taking into account the language of the viewing region. For example, the translation unit can weight the translation by taking into account the language of the viewing region. The translation unit can also weight the translation by taking into account trends in the viewing region. For example, the translation unit can weight the translation by taking into account trends in the viewing region. In this way, the translation is weighted based on the viewing region. Some or all of the above-described processing in the translation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the translation unit can weight the translation based on the viewing region of the video during translation using a generation AI.

[0047] The translation unit can improve the accuracy of the translation by referring to literature related to the video during translation. Related literature includes, but is not limited to, academic papers, technical reports, industry reports, etc. For example, the translation unit can improve the accuracy of the translation by referring to related academic papers. For example, the translation unit can improve the accuracy of the translation by referring to related academic papers. The translation unit can also improve the accuracy of the translation by referring to related news articles. For example, the translation unit can improve the accuracy of the translation by referring to related news articles. The translation unit can also improve the accuracy of the translation by referring to related books. For example, the translation unit can improve the accuracy of the translation by referring to related books. In this way, the accuracy of the translation is improved by referring to the related literature. Some or all of the above-described processing in the translation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the translation unit can improve the accuracy of the translation by referring to literature related to the video during translation using a generation AI.

[0048] The thumbnail generation unit can apply different design algorithms depending on the genre or theme of the video when generating thumbnails. Examples of design algorithms include, but are not limited to, image processing algorithms and machine learning algorithms. For example, the thumbnail generation unit can apply a design algorithm that emphasizes important points to educational videos. For example, the thumbnail generation unit can apply a design algorithm that emphasizes important points to educational videos. The thumbnail generation unit can also apply a design algorithm that emphasizes visual elements to entertainment videos. For example, the thumbnail generation unit can apply a design algorithm that emphasizes visual elements to entertainment videos. The thumbnail generation unit can also apply a design algorithm that emphasizes fact-checking to news videos. For example, the thumbnail generation unit can apply a design algorithm that emphasizes fact-checking to news videos. This allows thumbnail designs to be created depending on the genre or theme. Some or all of the above-described processing in the thumbnail generation unit can be performed using, for example, AI, or without AI. For example, the thumbnail generation unit can use AI to apply different design algorithms depending on the genre or theme of the video when generating thumbnails.

[0049] The thumbnail generation unit can improve the accuracy of the design by referring to past thumbnail results when generating thumbnails. Past thumbnail results include, but are not limited to, past thumbnail results in the same genre or past thumbnail results from the same broadcaster. The thumbnail generation unit can improve the accuracy by referring to past thumbnail results in the same genre. For example, the thumbnail generation unit can improve the accuracy by referring to past thumbnail results in the same genre. The thumbnail generation unit can also improve the accuracy by referring to past thumbnail results from the same broadcaster. For example, the thumbnail generation unit can improve the accuracy by referring to past thumbnail results from the same broadcaster. The thumbnail generation unit can also improve the accuracy by referring to past thumbnail results from the same viewer demographic. For example, the thumbnail generation unit can improve the accuracy by referring to past thumbnail results from the same viewer demographic. In this way, the accuracy of the design is improved by referring to past thumbnail results. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit can improve the accuracy of the design by referring to past thumbnail results when generating thumbnails using AI.

[0050] When generating thumbnails, the thumbnail generation unit can determine the priority of designs based on the viewing history of the videos. The viewing history includes, for example, the number of views, the viewing time, the type of videos viewed, etc., but is not limited to these examples. For example, the thumbnail generation unit prioritizes the design of videos that have been viewed many times. For example, the thumbnail generation unit prioritizes the design of videos that have been viewed many times. The thumbnail generation unit can also prioritize the design of videos that have been viewed for a long time. For example, the thumbnail generation unit prioritizes the design of videos that have been viewed for a long time. The thumbnail generation unit can also prioritize the design of videos that have been highly rated by viewers. For example, the thumbnail generation unit prioritizes the design of videos that have been highly rated by viewers. In this way, the design priority is determined taking the viewing history into consideration. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit can use AI to determine the priority of designs based on the viewing history of the videos when generating thumbnails.

[0051] The thumbnail generation unit can design thumbnails based on attribute information of viewers of the video when generating thumbnails. Viewer attribute information includes, but is not limited to, age, gender, region, and interests. The thumbnail generation unit can change the design style depending on the viewer's age group, for example. For example, the thumbnail generation unit can change the design style depending on the viewer's age group. The thumbnail generation unit can also change the color of the design depending on the viewer's gender. For example, the thumbnail generation unit can change the color of the design depending on the viewer's gender. The thumbnail generation unit can also change design elements depending on the viewer's interests. For example, the thumbnail generation unit changes design elements depending on the viewer's interests. This allows thumbnail design to take viewer attribute information into consideration. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without AI. For example, the thumbnail generation unit can use AI to design thumbnails based on attribute information of viewers of the video when generating thumbnails.

[0052] The thumbnail generation unit can weight the design based on the viewing region of the video when generating thumbnails. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The thumbnail generation unit can weight the design by taking into account the cultural background of the viewing region. For example, the thumbnail generation unit can weight the design by taking into account the cultural background of the viewing region. The thumbnail generation unit can also weight the design by taking into account the language of the viewing region. For example, the thumbnail generation unit can weight the design by taking into account the language of the viewing region. The thumbnail generation unit can also weight the design by taking into account trends in the viewing region. For example, the thumbnail generation unit can weight the design by taking into account trends in the viewing region. In this way, the thumbnail design is weighted based on the viewing region. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit can use AI to weight the design based on the viewing region of the video when generating thumbnails.

[0053] The thumbnail generation unit may improve the accuracy of the design by referring to literature related to the video when generating thumbnails. Examples of related literature include, but are not limited to, academic papers, technical reports, and industry reports. For example, the thumbnail generation unit may improve the accuracy of the design by referring to related academic papers. For example, the thumbnail generation unit may improve the accuracy of the design by referring to related academic papers. The thumbnail generation unit may also improve the accuracy of the design by referring to related news articles. For example, the thumbnail generation unit may improve the accuracy of the design by referring to related news articles. The thumbnail generation unit may also improve the accuracy of the design by referring to related books. For example, the thumbnail generation unit may improve the accuracy of the design by referring to related books. Thus, the accuracy of the design is improved by referring to related literature. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit may use AI to improve the accuracy of the design by referring to literature related to the video when generating thumbnails.

[0054] When generating a title, the title generation unit can apply a different title generation algorithm depending on the genre or theme of the video. Examples of title generation algorithms include, but are not limited to, natural language processing algorithms and machine learning algorithms. For example, for educational videos, the title generation unit applies a title generation algorithm that emphasizes important points. For example, for educational videos, the title generation unit applies a title generation algorithm that emphasizes important points. Furthermore, for entertainment videos, the title generation unit can also apply a title generation algorithm that emphasizes visual elements. For example, for entertainment videos, the title generation unit can also apply a title generation algorithm that emphasizes fact-checking to news videos. For example, for news videos, the title generation unit applies a title generation algorithm that emphasizes fact-checking. In this way, titles are generated according to the genre or theme. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can use AI to apply a different title generation algorithm depending on the genre or theme of the video when generating a title.

[0055] When generating a title, the title generation unit can improve the accuracy of the title generation by referring to past title results. Past title results include, but are not limited to, past title results in the same genre or past title results from the same broadcaster. For example, the title generation unit can improve the accuracy by referring to past title results in the same genre. For example, the title generation unit can improve the accuracy by referring to past title results in the same genre. The title generation unit can also improve the accuracy by referring to past title results from the same broadcaster. For example, the title generation unit can improve the accuracy by referring to past title results from the same broadcaster. The title generation unit can also improve the accuracy by referring to past title results from the same viewer demographic. For example, the title generation unit can improve the accuracy by referring to past title results from the same viewer demographic. In this way, the accuracy of the generation is improved by referring to past title results. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can improve the accuracy of the title generation by referring to past title results using AI.

[0056] When generating titles, the title generation unit can determine the priority of title generation based on the viewing history of the videos. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the title generation unit prioritizes title generation for videos that have been viewed many times. For example, the title generation unit prioritizes title generation for videos that have been viewed many times. The title generation unit can also prioritize title generation for videos that have been viewed long times. For example, the title generation unit prioritizes title generation for videos that have been viewed long times. The title generation unit can also prioritize title generation for videos that have been highly rated by viewers. For example, the title generation unit prioritizes title generation for videos that have been highly rated by viewers. In this way, the priority of title generation is determined taking the viewing history into consideration. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can use AI to determine the priority of title generation based on the viewing history of the videos when generating titles.

[0057] The title generation unit can generate a title based on attribute information of a viewer of a video. The viewer's attribute information includes, but is not limited to, age, gender, region, and interests. The title generation unit, for example, changes the expression of the title according to the viewer's age group. For example, the title generation unit changes the expression of the title according to the viewer's age group. The title generation unit can also change the expression of the title according to the viewer's gender. For example, the title generation unit changes the expression of the title according to the viewer's gender. The title generation unit can also change the expression of the title according to the viewer's interests. For example, the title generation unit changes the expression of the title according to the viewer's interests. In this way, titles are generated taking into account the viewer's attribute information. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can use AI to generate a title based on attribute information of a viewer of a video.

[0058] The title generation unit can weight the title generation based on the viewing region of the video when generating the title. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The title generation unit can weight the title generation based on, for example, the cultural background of the viewing region. For example, the title generation unit can weight the title generation based on the cultural background of the viewing region. The title generation unit can also weight the title generation based on the language of the viewing region. For example, the title generation unit can weight the title generation based on the language of the viewing region. The title generation unit can also weight the title generation based on trends in the viewing region. For example, the title generation unit can weight the title generation based on trends in the viewing region. In this way, title generation is weighted based on the viewing region. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can use AI to weight the title generation based on the viewing region of the video when generating the title.

[0059] The title generation unit can improve the accuracy of title generation by referring to literature related to the video when generating the title. Related literature includes, but is not limited to, academic papers, technical reports, industry reports, etc. For example, the title generation unit can improve the accuracy of title generation by referring to related academic papers. For example, the title generation unit can improve the accuracy of title generation by referring to related academic papers. The title generation unit can also improve the accuracy of title generation by referring to related news articles. For example, the title generation unit can improve the accuracy of title generation by referring to related news articles. The title generation unit can also improve the accuracy of title generation by referring to related books. For example, the title generation unit can improve the accuracy of title generation by referring to related books. In this way, the accuracy of title generation is improved by referring to related literature. Some or all of the above-described processing in the title generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the title generation unit can improve the accuracy of title generation by referring to literature related to the video using AI.

[0060] The uploading unit can apply different uploading algorithms depending on the genre or theme of the video when uploading. Examples of uploading algorithms include, but are not limited to, scheduling algorithms and load balancing algorithms. For example, in the case of educational videos, the uploading unit applies an algorithm that uploads during times when there are many viewers. For example, in the case of educational videos, the uploading unit applies an algorithm that uploads during times when there are many viewers. Furthermore, in the case of entertainment videos, the uploading unit can also apply an algorithm that uploads during times when viewers are relaxing. For example, in the case of entertainment videos, the uploading unit applies an algorithm that uploads during times when viewers are relaxing. Furthermore, in the case of news videos, the uploading unit can also apply an algorithm that uploads immediately with an emphasis on timeliness. For example, in the case of news videos, the uploading unit applies an algorithm that uploads immediately with an emphasis on timeliness. In this way, uploading is performed according to the genre or theme. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to apply different uploading algorithms depending on the genre or theme of the video when uploading.

[0061] The upload unit can improve the accuracy of uploading by referring to past upload results when uploading. Past upload results include, but are not limited to, past upload results in the same genre or past upload results by the same distributor. For example, the upload unit can improve the accuracy by referring to past upload results in the same genre. For example, the upload unit can improve the accuracy by referring to past upload results in the same genre. The upload unit can also improve the accuracy by referring to past upload results by the same distributor. For example, the upload unit can improve the accuracy by referring to past upload results by the same distributor. The upload unit can also improve the accuracy by referring to past upload results for the same viewer demographic. For example, the upload unit can improve the accuracy by referring to past upload results for the same viewer demographic. In this way, the accuracy of uploading is improved by referring to past upload results. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without using AI. For example, the upload unit can improve the accuracy of uploading by referring to past upload results when uploading using AI.

[0062] The uploading unit can determine the upload priority based on the viewing history of the video at the time of uploading. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the uploading unit prioritizes uploading videos with a large number of views. For example, the uploading unit prioritizes uploading videos with a large number of views. The uploading unit can also prioritize uploading videos with a long viewing time. For example, the uploading unit prioritizes uploading videos with a long viewing time. The uploading unit can also prioritize uploading videos with high viewer ratings. For example, the uploading unit prioritizes uploading videos with high viewer ratings. In this way, the upload priority is determined taking the viewing history into consideration. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to determine the upload priority based on the viewing history of the video at the time of uploading.

[0063] The uploading unit can upload a video based on attribute information of the viewer of the video at the time of uploading. The viewer's attribute information includes, but is not limited to, age, gender, region, and interests, for example. The uploading unit can change the timing of uploading according to, for example, the viewer's age group. For example, the uploading unit can change the timing of uploading according to the viewer's age group. The uploading unit can also change the timing of uploading according to the viewer's gender. For example, the uploading unit can change the timing of uploading according to the viewer's interests. For example, the uploading unit can change the timing of uploading according to the viewer's interests. In this way, uploading is performed taking into account the viewer's attribute information. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to upload a video based on the viewer's attribute information at the time of uploading.

[0064] The uploading unit can weight uploads based on the viewing region of the video at the time of uploading. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The uploading unit can weight uploads, for example, by taking into account the cultural background of the viewing region. For example, the uploading unit can weight uploads by taking into account the cultural background of the viewing region. The uploading unit can also weight uploads by taking into account the language of the viewing region. For example, the uploading unit can weight uploads by taking into account the language of the viewing region. The uploading unit can also weight uploads by taking into account trends in the viewing region. For example, the uploading unit can weight uploads by taking into account trends in the viewing region. In this way, weighting of uploads based on the viewing region is performed. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to weight uploads based on the viewing region of the video at the time of uploading.

[0065] The uploading unit may refer to literature related to the video at the time of uploading to improve the accuracy of the upload. Examples of related literature include, but are not limited to, academic papers, technical reports, and industry reports. For example, the uploading unit may refer to related academic papers to improve the accuracy of the upload. For example, the uploading unit may refer to related academic papers to improve the accuracy of the upload. The uploading unit may also refer to related news articles to improve the accuracy of the upload. For example, the uploading unit may refer to related news articles to improve the accuracy of the upload. The uploading unit may also refer to related books to improve the accuracy of the upload. For example, the uploading unit may refer to related books to improve the accuracy of the upload. In this way, the accuracy of the upload is improved by referring to the related literature. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit may use AI to refer to literature related to the video at the time of uploading to improve the accuracy of the upload.

[0066] The manual correction unit can apply different correction algorithms depending on the genre or theme of the video during manual correction. Examples of correction algorithms include, but are not limited to, error detection algorithms and optimization algorithms. For example, in the case of an educational video, the manual correction unit applies a correction algorithm that emphasizes important points. For example, in the case of an educational video, the manual correction unit applies a correction algorithm that emphasizes important points. Furthermore, in the case of an entertainment video, the manual correction unit can also apply a correction algorithm that emphasizes visual elements. For example, in the case of an entertainment video, the manual correction unit can also apply a correction algorithm that emphasizes fact checking to the news video. For example, in the case of a news video, the manual correction unit applies a correction algorithm that emphasizes fact checking. In this way, manual correction according to the genre or theme is performed. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can use AI to apply different correction algorithms depending on the genre or theme of the video during manual correction.

[0067] The manual correction unit can improve the accuracy of the correction by referring to past correction results during manual correction. Past correction results include, but are not limited to, past correction results for the same genre or past correction results for the same distributor. For example, the manual correction unit improves the accuracy by referring to past correction results for the same genre. For example, the manual correction unit improves the accuracy by referring to past correction results for the same genre. The manual correction unit can also improve the accuracy by referring to past correction results for the same distributor. For example, the manual correction unit improves the accuracy by referring to past correction results for the same distributor. The manual correction unit can also improve the accuracy by referring to past correction results for the same viewer demographic. For example, the manual correction unit improves the accuracy by referring to past correction results for the same viewer demographic. In this way, the accuracy of the correction is improved by referring to the past correction results. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can improve the accuracy of the correction by referring to past correction results during manual correction using AI.

[0068] During manual correction, the manual correction unit can determine the priority of correction based on the viewing history of the video. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the manual correction unit prioritizes correction of videos that have been viewed many times. For example, the manual correction unit prioritizes correction of videos that have been viewed many times. The manual correction unit can also prioritize correction of videos that have been viewed for a long time. For example, the manual correction unit prioritizes correction of videos that have been viewed for a long time. The manual correction unit can also prioritize correction of videos that have been highly rated by viewers. For example, the manual correction unit prioritizes correction of videos that have been highly rated by viewers. In this way, the priority of correction is determined taking the viewing history into consideration. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can use AI to determine the priority of correction based on the viewing history of the video during manual correction.

[0069] The manual correction unit can perform manual correction based on attribute information of viewers of the video during manual correction. Viewer attribute information includes, but is not limited to, age, gender, region, and interests. The manual correction unit can change the focus of correction depending on, for example, the viewer's age group. For example, the manual correction unit can change the focus of correction depending on the viewer's age group. The manual correction unit can also change the focus of correction depending on the viewer's gender. For example, the manual correction unit can change the focus of correction depending on the viewer's interests. For example, the manual correction unit can change the focus of correction depending on the viewer's interests. In this way, manual correction is performed taking into account the viewer's attribute information. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can use AI to perform manual correction based on the viewer's attribute information during manual correction.

[0070] The manual correction unit can weight the correction based on the viewing region of the video during manual correction. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The manual correction unit can weight the correction, for example, by taking into account the cultural background of the viewing region. For example, the manual correction unit can weight the correction by taking into account the cultural background of the viewing region. The manual correction unit can also weight the correction by taking into account the language of the viewing region. For example, the manual correction unit can weight the correction by taking into account the language of the viewing region. The manual correction unit can also weight the correction by taking into account trends in the viewing region. For example, the manual correction unit can weight the correction by taking into account trends in the viewing region. In this way, the weighting of the correction is based on the viewing region. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can weight the correction based on the viewing region of the video during manual correction using AI.

[0071] The manual correction unit can improve the accuracy of the correction by referring to related literature of the video during manual correction. Related literature includes, but is not limited to, academic papers, technical reports, industry reports, etc. For example, the manual correction unit can improve the accuracy of the correction by referring to related academic papers. For example, the manual correction unit can improve the accuracy of the correction by referring to related academic papers. The manual correction unit can also improve the accuracy of the correction by referring to related news articles. For example, the manual correction unit can improve the accuracy of the correction by referring to related news articles. The manual correction unit can also improve the accuracy of the correction by referring to related books. For example, the manual correction unit can improve the accuracy of the correction by referring to related books. In this way, the accuracy of the correction is improved by referring to the related literature. Some or all of the above-described processing in the manual correction unit can be performed using, for example, AI, or can be performed without using AI. For example, the manual correction unit can improve the accuracy of the correction by referring to related literature of the video during manual correction using AI.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The localization support system can also analyze a user's viewing history and customize the video localization method based on the viewer's preferences. For example, it can adjust the subtitle and audio translation style based on the genre and theme of the videos the viewer has previously watched. If a viewer is interested in a particular actor or character, it can generate thumbnails and titles based on that information. It can also analyze the viewer's viewing time and frequency to suggest the optimal upload timing. This enables localization that is tailored to the viewer's preferences and improves the viewing experience.

[0074] When analyzing the content of a video, the analysis unit can collect feedback from viewers of the video in real time and adjust the analysis method based on that feedback. For example, if a viewer gives a high rating to a particular scene, the analysis unit can perform an analysis that emphasizes that scene. Also, if a viewer gives a low rating to a particular scene, the analysis unit can perform an analysis that omits that scene. Furthermore, it is possible to reconstruct the content of the video based on viewer feedback. This allows for an analysis that reflects viewer feedback, improving the viewing experience.

[0075] The title generation unit can change the font style of the title based on the attribute information of the video viewer. For example, a pop font style can be used for younger viewers, and an easy-to-read font style can be used for older viewers. The unit can also adjust the font weight and color according to the viewer's gender. Furthermore, it can customize the title design according to the viewer's interests. This provides titles that match the viewer's attribute information, improving the viewing experience.

[0076] When analyzing the content of a video, the analysis unit can determine the analysis priority based on the attribute information of the video's viewers. For example, if there are many young viewers, the analysis can be focused on entertainment elements. Alternatively, if there are many older viewers, the analysis can be focused on providing information. Furthermore, if there are many viewers from a specific region, the analysis can take into account the cultural background of that region. This allows for analysis based on viewer attribute information, improving the viewing experience.

[0077] The thumbnail generator can customize the design of the thumbnail based on the demographic information of the viewer of the video. For example, a pop design can be used for younger viewers, while a simple, highly visible design can be used for older viewers. The color and layout can also be adjusted depending on the viewer's gender. Furthermore, it is possible to customize the elements of the thumbnail based on the viewer's interests. This provides thumbnails that match the viewer's demographic information, improving the viewing experience.

[0078] The processing flow of the first embodiment will be briefly explained below.

[0079] Step 1: The analysis unit analyzes the content of the video. The video content includes video, audio, and text information. The analysis unit uses video analysis technology to extract important scenes, speech recognition technology to convert the audio content into text, and natural language processing technology to extract important keywords from the text information. Step 2: The translation unit uses generation AI to translate subtitles and audio based on the content analyzed by the analysis unit. Translation is performed using methods such as machine translation or translation by experts. The generation AI uses text generation AI to translate subtitles into natural expressions, and speech generation AI to translate audio into natural expressions. It also converts to appropriate expressions taking cultural differences into account. Step 3: The thumbnail generator generates thumbnails based on the content translated by the translation unit. Thumbnails are generated based on the content of the video using image recognition technology, and the optimal thumbnail is generated taking into account the viewer's demographic information and the cultural background of the viewing area. Step 4: The title generation unit generates a title based on the content translated by the translation unit. The title is generated based on the content of the video using natural language processing technology, and the optimal title is generated taking into account the viewer's attribute information and the cultural background of the viewing area. Step 5: The uploading unit uploads the localized video, including the thumbnails and titles generated by the thumbnail and title generators, to the platform selected by the distributor. Uploading can be done automatically to the platform selected by the distributor, or manually or according to a schedule.

[0080] (Example 2) A localization support system according to an embodiment of the present invention reduces the effort required for streamers to localize videos and enables them to distribute them worldwide. In this system, streamers upload videos, the system analyzes the content of the video, and translates the subtitles and audio into the languages ​​of each country. Generative AI is used to provide natural-sounding translations. It is also possible to convert to appropriate expressions taking cultural differences into account. Furthermore, the localization support system generates thumbnails and titles that are optimal for viewers in each country based on the content of the video. Finally, the localized video is automatically uploaded to a platform selected by the streamer. For example, in this system, a streamer uploads a video. The localization support system analyzes the content of the video and translates the subtitles and audio into the languages ​​of each country. Generative AI is used to provide natural-sounding translations. For example, the generative AI receives a prompt such as "Please translate the content of this video" and translates the video content. The localization support system is also capable of converting to appropriate expressions taking cultural differences into account. For example, the generative AI receives a prompt such as "Please convert this expression into a culturally appropriate one" and converts it to the appropriate expression. Next, the localization support system generates thumbnails and titles that are optimal for viewers in each country based on the content of the video. For example, the localization support system analyzes the content of the video and generates thumbnails that are optimal for the viewer. The localization support system also analyzes the content of the video and generates titles that are optimal for the viewer. Finally, the localization support system automatically uploads the localized video to the platform selected by the distributor. This allows distributors to localize videos and distribute them worldwide without any hassle. This allows distributors to localize videos and distribute them worldwide without any hassle. For example, distributors can significantly reduce the effort required for localization and increase page views and revenue.

[0081] A localization support system according to an embodiment includes an analysis unit, a translation unit, a thumbnail generation unit, a title generation unit, and an upload unit. The analysis unit analyzes the content of a video. The content of the video may include, but is not limited to, video, audio, and text information. For example, the analysis unit analyzes the video and extracts important scenes. The analysis unit can also analyze the audio of the video and convert the audio content into text. The analysis unit can also analyze the text information of the video and extract important keywords. For example, the analysis unit uses video analysis technology to extract important scenes of the video. The analysis unit can also convert the audio content into text using speech recognition technology. The analysis unit can also extract important keywords from the text information using natural language processing technology. The translation unit uses a generation AI to translate subtitles and audio based on the content analyzed by the analysis unit. The translation may be performed by, for example, machine translation or expert translation, but is not limited to, these examples. For example, the translation unit uses a generation AI to translate subtitles. The translation unit can also translate audio using a generation AI. The translation unit can also use the generation AI to convert to appropriate expressions taking cultural differences into consideration. For example, the generation AI can translate subtitles into natural expressions using a text generation AI (e.g., LLM). The generation AI can also translate audio into natural expressions using a speech generation AI. The generation AI can also convert to appropriate expressions taking cultural differences into consideration. The thumbnail generation unit generates thumbnails based on the content translated by the translation unit. Thumbnails are generated according to, for example, image selection criteria, size, resolution, and other criteria, but are not limited to these examples. For example, the thumbnail generation unit uses image recognition technology to generate thumbnails based on the content of the video. The thumbnail generation unit can also generate optimal thumbnails taking viewer attribute information into consideration. The thumbnail generation unit can also generate optimal thumbnails taking into consideration the cultural background of the viewing region. For example, the thumbnail generation unit uses image recognition technology to generate thumbnails based on the content of the video.The thumbnail generation unit may also generate an optimal thumbnail by taking into account viewer attribute information. The thumbnail generation unit may also generate an optimal thumbnail by taking into account the cultural background of the viewing region. The title generation unit generates a title based on the content translated by the translation unit. The title may be generated according to, for example, but not limited to, criteria such as keyword selection criteria and character limit. For example, the title generation unit may generate a title based on the content of the video using natural language processing technology. The title generation unit may also generate an optimal title by taking into account viewer attribute information. The title generation unit may also generate an optimal title by taking into account the cultural background of the viewing region. For example, the title generation unit may generate a title based on the content of the video using natural language processing technology. The title generation unit may also generate an optimal title by taking into account viewer attribute information. The title generation unit may also generate an optimal title by taking into account the cultural background of the viewing region. The upload unit uploads the localized video including the thumbnail and title generated by the thumbnail generation unit and the title generation unit to a platform selected by the distributor. The upload may be performed automatically to, for example, but not limited to, the platform selected by the distributor. For example, the uploading unit may automatically upload a localized video to a platform selected by the distributor. Alternatively, the uploading unit may manually upload to a platform selected by the distributor. Alternatively, the uploading unit may upload to a platform selected by the distributor according to a schedule. For example, the uploading unit may automatically upload a localized video to a platform selected by the distributor. Alternatively, the uploading unit may manually upload to a platform selected by the distributor. Alternatively, the uploading unit may upload to a platform selected by the distributor according to a schedule. In this way, the localization support system according to the embodiment allows distributors to localize videos and distribute them worldwide without any hassle.For example, distributors can significantly reduce the effort required for localization and increase page views and revenue.

[0082] The translation unit can translate subtitles and audio using a generation AI. The generation AI includes, but is not limited to, a specific AI model and training data, for example. The translation unit translates subtitles using, for example, a generation AI. For example, the generation AI translates subtitles into natural-looking expressions using a text generation AI (e.g., LLM). The translation unit can also translate audio using the generation AI. For example, the generation AI translates audio into natural-looking expressions using an audio generation AI. The translation unit can also convert audio into appropriate expressions taking cultural differences into consideration using the generation AI. For example, the generation AI converts audio into appropriate expressions taking cultural differences into consideration. In this way, natural translations are provided by using the generation AI. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can translate subtitles and audio using a generation AI.

[0083] The translation unit can convert expressions using a generation AI while taking cultural differences into consideration. Cultural differences include, but are not limited to, differences in expressions and taboos in a particular culture. The translation unit can, for example, use a generation AI to convert to an appropriate expression while taking cultural differences into consideration. For example, the generation AI converts to an appropriate expression while taking cultural differences into consideration. The translation unit can also, for example, use a generation AI to convert to an appropriate expression while taking cultural differences into consideration. For example, the generation AI converts to an appropriate expression while taking cultural differences into consideration. The translation unit can also, for example, use a generation AI to convert to an appropriate expression while avoiding taboos. For example, the generation AI converts to an appropriate expression while avoiding taboos. This provides an appropriate expression while taking cultural differences into consideration. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can, for example, use a generation AI to convert to an appropriate expression while taking cultural differences into consideration.

[0084] The thumbnail generation unit can generate thumbnails suitable for viewers in each country. Examples of thumbnails suitable for viewers in each country include, but are not limited to, color, design, and content. The thumbnail generation unit can generate thumbnails based on the content of a video using, for example, image recognition technology. For example, the thumbnail generation unit can generate thumbnails based on the content of a video using image recognition technology. The thumbnail generation unit can also generate optimal thumbnails by taking into account viewer attribute information. For example, the thumbnail generation unit can generate optimal thumbnails by taking into account viewer attribute information. The thumbnail generation unit can also generate optimal thumbnails by taking into account the cultural background of the viewing region. For example, the thumbnail generation unit can generate optimal thumbnails by taking into account the cultural background of the viewing region. This provides optimal thumbnails to viewers in each country. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit can generate thumbnails suitable for viewers in each country using AI.

[0085] The title generation unit can generate titles suitable for viewers in each country. Examples of titles suitable for viewers in each country include, but are not limited to, language, cultural background, and trends. The title generation unit can generate titles based on the content of the video using, for example, natural language processing technology. For example, the title generation unit can generate titles based on the content of the video using natural language processing technology. The title generation unit can also generate optimal titles taking into account viewer attribute information. For example, the title generation unit can generate optimal titles taking into account viewer attribute information. The title generation unit can also generate optimal titles taking into account the cultural background of the viewing region. For example, the title generation unit can generate optimal titles taking into account the cultural background of the viewing region. This provides optimal titles to viewers in each country. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can generate titles suitable for viewers in each country using AI.

[0086] The uploading unit can upload the localized video to a platform selected by the distributor. Examples of localized videos include, but are not limited to, translation accuracy and cultural adaptation. The uploading unit, for example, automatically uploads the localized video to a platform selected by the distributor. For example, the uploading unit automatically uploads the localized video to a platform selected by the distributor. The uploading unit can also manually upload the video to a platform selected by the distributor. For example, the uploading unit manually uploads the video to a platform selected by the distributor. The uploading unit can also upload the video to a platform selected by the distributor according to a schedule. For example, the uploading unit uploads the video to a platform selected by the distributor according to a schedule. In this way, the localized video is automatically uploaded. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to upload the localized video to a platform selected by the distributor.

[0087] The localization support system includes a manual correction unit that allows a distributor to check and correct the content. The manual correction unit provides an interface for the distributor to make final checks and corrections. For example, the manual correction unit allows the distributor to check the translated content of subtitles and audio and correct it as necessary. The manual correction unit also allows the distributor to check the content of thumbnails and titles and correct it as necessary. For example, the manual correction unit provides an interface for the distributor to check and correct the translated content of subtitles. The manual correction unit can also provide an interface for the distributor to check and correct the translated content of audio. The manual correction unit can also provide an interface for the distributor to check and correct the content of thumbnails. For example, the manual correction unit provides an interface for the distributor to check and correct the content of titles. This allows the distributor to make final checks and corrections. Some or all of the above-described processing in the manual correction unit may be performed, for example, using AI or without AI. For example, the manual correction unit can use AI to provide an interface for the distributor to check and correct the content.

[0088] The analysis unit can estimate the user's emotions and change the video analysis method based on the estimated user's emotions. Examples of user emotions include, but are not limited to, excitement, relaxation, stress, etc. For example, when the user is excited, the analysis unit can speed up the analysis to provide results more quickly. For example, when the user is excited, the analysis unit can speed up the analysis to provide results more quickly. Furthermore, when the user is relaxed, the analysis unit can perform a detailed analysis to provide more information. For example, when the user is relaxed, the analysis unit can perform a detailed analysis to provide more information. Furthermore, when the user is stressed, the analysis unit can provide a concise summary of the analysis results. For example, when the user is stressed, the analysis unit provides a concise summary of the analysis results. This adjusts the video analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may use AI to estimate a user's emotion and change the analysis method for the video based on the estimated user's emotion.

[0089] When analyzing the content of a video, the analysis unit can apply different analysis algorithms depending on the genre or theme of the video. Genres and themes include, but are not limited to, movies, documentaries, and education. For example, in the case of an educational video, the analysis unit applies an algorithm that emphasizes important points. For example, in the case of an educational video, the analysis unit applies an algorithm that emphasizes important points. In addition, in the case of an entertainment video, the analysis unit can also apply an algorithm that emphasizes visual elements. For example, in the case of an entertainment video, the analysis unit can also apply an algorithm that emphasizes fact-checking. In addition, in the case of a news video, the analysis unit can apply an algorithm that emphasizes fact-checking. For example, in the case of a news video, the analysis unit applies an algorithm that emphasizes fact-checking. In this way, analysis is performed depending on the genre or theme of the video. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, when analyzing the content of a video using AI, the analysis unit can apply different analysis algorithms depending on the genre or theme of the video.

[0090] When analyzing a video, the analysis unit can improve the accuracy of the analysis by referring to past analysis results. Past analysis results include, for example, analysis results of past videos of the same genre or analysis results of past videos of the same broadcaster, but are not limited to these examples. The analysis unit can improve the accuracy by referring to past analysis results of videos of the same genre. For example, the analysis unit can improve the accuracy by referring to past analysis results of videos of the same genre. The analysis unit can also improve the accuracy by referring to past analysis results of videos of the same broadcaster. For example, the analysis unit can improve the accuracy by referring to past analysis results of videos of the same broadcaster. The analysis unit can also improve the accuracy by referring to past analysis results of videos of the same viewer demographic. For example, the analysis unit can improve the accuracy by referring to past analysis results of videos of the same viewer demographic. In this way, the accuracy of the analysis is improved by referring to past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can improve the accuracy of the analysis by referring to past analysis results when analyzing a video using AI.

[0091] When analyzing a video, the analysis unit can determine an analysis priority based on the viewing history of the video. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the analysis unit prioritizes analyzing videos that have been viewed many times. For example, the analysis unit prioritizes analyzing videos that have been viewed many times. The analysis unit can also prioritize analyzing videos that have been viewed for a long time. For example, the analysis unit prioritizes analyzing videos that have been viewed for a long time. The analysis unit can also prioritize analyzing videos that have been highly rated by viewers. For example, the analysis unit prioritizes analyzing videos that have been highly rated by viewers. In this way, the analysis priority is determined taking into account the viewing history of the video. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use AI to determine an analysis priority based on the viewing history of the video when analyzing the video.

[0092] The analysis unit can estimate the user's emotion and change the display method of the analysis results based on the estimated user's emotion. Examples of display methods for the analysis results include, but are not limited to, graph display, text display, and interactive display. For example, if the user is excited, the analysis unit provides a visually stimulating display method. For example, if the user is excited, the analysis unit provides a visually stimulating display method. Furthermore, if the user is relaxed, the analysis unit can provide a calm display method. For example, if the user is relaxed, the analysis unit provides a calm display method. Furthermore, if the user is stressed, the analysis unit can provide a concise and easy-to-understand display method. For example, if the user is stressed, the analysis unit provides a concise and easy-to-understand display method. This adjusts the display method of the analysis results according to the user's emotion. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can 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 processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can use AI to estimate the user's emotions and change the way the analysis results are displayed based on the estimated user emotions.

[0093] When analyzing a video, the analysis unit can perform analysis based on attribute information of viewers of the video. Viewer attribute information includes, for example, age, gender, region, and interests, but is not limited to these examples. The analysis unit, for example, changes the focus of analysis depending on the viewer's age group. For example, the analysis unit changes the focus of analysis depending on the viewer's age group. The analysis unit can also change the focus of analysis depending on the viewer's gender. For example, the analysis unit changes the focus of analysis depending on the viewer's gender. The analysis unit can also change the focus of analysis depending on the viewer's interests. For example, the analysis unit changes the focus of analysis depending on the viewer's interests. In this way, analysis is performed taking into account the viewer's attribute information. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use AI to perform analysis based on the viewer's attribute information when analyzing a video.

[0094] When analyzing a video, the analysis unit can weight the analysis based on the viewing region of the video. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The analysis unit, for example, weights the analysis by taking into account the cultural background of the viewing region. For example, the analysis unit weights the analysis by taking into account the cultural background of the viewing region. The analysis unit can also weight the analysis by taking into account the language of the viewing region. For example, the analysis unit weights the analysis by taking into account the language of the viewing region. The analysis unit can also weight the analysis by taking into account trends in the viewing region. For example, the analysis unit weights the analysis by taking into account trends in the viewing region. In this way, the analysis is weighted based on the viewing region. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use AI to weight the analysis based on the viewing region of the video when analyzing a video.

[0095] When analyzing a video, the analysis unit can improve the accuracy of the analysis by referring to literature related to the video. Related literature includes, but is not limited to, academic papers, technical reports, industry reports, etc. For example, the analysis unit can improve the accuracy of the analysis by referring to related academic papers. For example, the analysis unit can improve the accuracy of the analysis by referring to related academic papers. The analysis unit can also improve the accuracy of the analysis by referring to related news articles. For example, the analysis unit can improve the accuracy of the analysis by referring to related news articles. The analysis unit can also improve the accuracy of the analysis by referring to related books. For example, the analysis unit can improve the accuracy of the analysis by referring to related books. In this way, the accuracy of the analysis is improved by referring to related literature. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use AI to improve the accuracy of the analysis by referring to literature related to the video when analyzing the video.

[0096] The translation unit can estimate the user's emotions and change the translation expression style based on the estimated user's emotions. Examples of translation expression styles include, but are not limited to, formal expressions and casual expressions. For example, when the user is relaxed, the translation unit uses soft expressions. For example, when the user is relaxed, the translation unit uses soft expressions. Furthermore, when the user is in a hurry, the translation unit can use concise expressions. For example, when the user is in a hurry, the translation unit uses concise expressions. Furthermore, when the user is excited, the translation unit can use emphasized expressions. For example, when the user is excited, the translation unit uses emphasized expressions. In this way, the translation expression style is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the translation unit can use a generation AI to estimate the user's emotions and change the way the translation is expressed based on the estimated user emotions.

[0097] The translation unit can apply different translation algorithms depending on the genre or theme of the video during translation. Examples of translation algorithms include, but are not limited to, neural networks and rule-based translation. For example, in the case of an educational video, the translation unit applies an algorithm that accurately translates technical terms. For example, in the case of an educational video, the translation unit applies an algorithm that accurately translates technical terms. In addition, the translation unit can apply an algorithm that emphasizes visual elements in the case of an entertainment video. For example, the translation unit can apply an algorithm that emphasizes visual elements in the case of an entertainment video. In addition, the translation unit can apply an algorithm that emphasizes fact-checking in the case of a news video. For example, the translation unit applies an algorithm that emphasizes fact-checking in the case of a news video. In this way, translation is performed according to the genre or theme. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can use a generation AI to apply different translation algorithms depending on the genre or theme of the video during translation.

[0098] The translation unit can improve the accuracy of translation by referring to past translation results during translation. Past translation results include, but are not limited to, past translation results of the same genre or past translation results of the same distributor, for example. The translation unit can improve the accuracy by referring to past translation results of the same genre. For example, the translation unit can improve the accuracy by referring to past translation results of the same genre. The translation unit can also improve the accuracy by referring to past translation results of the same distributor. For example, the translation unit can improve the accuracy by referring to past translation results of the same distributor. The translation unit can also improve the accuracy by referring to past translation results of the same viewer demographic. For example, the translation unit can improve the accuracy by referring to past translation results of the same viewer demographic. In this way, the accuracy of the translation is improved by referring to past translation results. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can improve the accuracy of translation by referring to past translation results during translation using a generation AI.

[0099] The translation unit can determine the translation priority based on the video viewing history during translation. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the translation unit prioritizes translating videos that have been viewed many times. For example, the translation unit prioritizes translating videos that have been viewed many times. The translation unit can also prioritize translating videos that have been viewed for a long time. For example, the translation unit prioritizes translating videos that have been viewed for a long time. The translation unit can also prioritize translating videos that have been highly rated by viewers. For example, the translation unit prioritizes translating videos that have been highly rated by viewers. In this way, the translation priority is determined taking the viewing history into consideration. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can use a generation AI to determine the translation priority based on the video viewing history during translation.

[0100] The translation unit can estimate the user's emotions and change the length of the translation based on the estimated user's emotions. Examples of translation length include, but are not limited to, character limits and time limits. For example, if the user is in a hurry, the translation unit provides a short, concise translation. For example, if the user is in a hurry, the translation unit provides a short, concise translation. Furthermore, if the user is relaxed, the translation unit can provide a longer translation with detailed explanations. For example, if the user is relaxed, the translation unit can provide a longer translation with detailed explanations. Furthermore, if the user is excited, the translation unit can provide a translation with emphasized expressions. For example, if the user is excited, the translation unit provides a translation with emphasized expressions. In this way, the length of the translation is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can 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 processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit may use a generation AI to estimate the user's emotion and change the length of the translation based on the estimated user emotion.

[0101] The translation unit can perform translation based on attribute information of the viewer of the video during translation. Viewer attribute information includes, but is not limited to, age, gender, region, and interests. The translation unit, for example, changes the translation expression according to the viewer's age group. For example, the translation unit changes the translation expression according to the viewer's age group. The translation unit can also change the translation expression according to the viewer's gender. For example, the translation unit changes the translation expression according to the viewer's gender. The translation unit can also change the translation expression according to the viewer's interests. For example, the translation unit changes the translation expression according to the viewer's interests. In this way, translation is performed taking into account the viewer's attribute information. Some or all of the above-described processing in the translation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the translation unit can use a generation AI to perform translation based on the viewer's attribute information during translation.

[0102] The translation unit can weight the translation based on the viewing region of the video during translation. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The translation unit can weight the translation by taking into account the cultural background of the viewing region. For example, the translation unit can weight the translation by taking into account the cultural background of the viewing region. The translation unit can also weight the translation by taking into account the language of the viewing region. For example, the translation unit can weight the translation by taking into account the language of the viewing region. The translation unit can also weight the translation by taking into account trends in the viewing region. For example, the translation unit can weight the translation by taking into account trends in the viewing region. In this way, the translation is weighted based on the viewing region. Some or all of the above-described processing in the translation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the translation unit can weight the translation based on the viewing region of the video during translation using a generation AI.

[0103] The translation unit can improve the accuracy of the translation by referring to literature related to the video during translation. Related literature includes, but is not limited to, academic papers, technical reports, industry reports, etc. For example, the translation unit can improve the accuracy of the translation by referring to related academic papers. For example, the translation unit can improve the accuracy of the translation by referring to related academic papers. The translation unit can also improve the accuracy of the translation by referring to related news articles. For example, the translation unit can improve the accuracy of the translation by referring to related news articles. The translation unit can also improve the accuracy of the translation by referring to related books. For example, the translation unit can improve the accuracy of the translation by referring to related books. In this way, the accuracy of the translation is improved by referring to the related literature. Some or all of the above-described processing in the translation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the translation unit can improve the accuracy of the translation by referring to literature related to the video during translation using a generation AI.

[0104] The thumbnail generation unit can estimate the user's emotions and change the thumbnail design based on the estimated user's emotions. Examples of thumbnail designs include, but are not limited to, color, layout, and font. For example, when the user is excited, the thumbnail generation unit provides a visually stimulating design. For example, when the user is excited, the thumbnail generation unit provides a visually stimulating design. The thumbnail generation unit can also provide a calm design when the user is relaxed. For example, when the user is relaxed, the thumbnail generation unit provides a calm design. For example, when the user is stressed, the thumbnail generation unit provides a simple and easy-to-understand design. In this way, the thumbnail design is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit may use AI to estimate a user's emotion and change the thumbnail design based on the estimated user's emotion.

[0105] The thumbnail generation unit can apply different design algorithms depending on the genre or theme of the video when generating thumbnails. Examples of design algorithms include, but are not limited to, image processing algorithms and machine learning algorithms. For example, the thumbnail generation unit can apply a design algorithm that emphasizes important points to educational videos. For example, the thumbnail generation unit can apply a design algorithm that emphasizes important points to educational videos. The thumbnail generation unit can also apply a design algorithm that emphasizes visual elements to entertainment videos. For example, the thumbnail generation unit can apply a design algorithm that emphasizes visual elements to entertainment videos. The thumbnail generation unit can also apply a design algorithm that emphasizes fact-checking to news videos. For example, the thumbnail generation unit can apply a design algorithm that emphasizes fact-checking to news videos. This allows thumbnail designs to be created depending on the genre or theme. Some or all of the above-described processing in the thumbnail generation unit can be performed using, for example, AI, or without AI. For example, the thumbnail generation unit can use AI to apply different design algorithms depending on the genre or theme of the video when generating thumbnails.

[0106] The thumbnail generation unit can improve the accuracy of the design by referring to past thumbnail results when generating thumbnails. Past thumbnail results include, but are not limited to, past thumbnail results in the same genre or past thumbnail results from the same broadcaster. The thumbnail generation unit can improve the accuracy by referring to past thumbnail results in the same genre. For example, the thumbnail generation unit can improve the accuracy by referring to past thumbnail results in the same genre. The thumbnail generation unit can also improve the accuracy by referring to past thumbnail results from the same broadcaster. For example, the thumbnail generation unit can improve the accuracy by referring to past thumbnail results from the same broadcaster. The thumbnail generation unit can also improve the accuracy by referring to past thumbnail results from the same viewer demographic. For example, the thumbnail generation unit can improve the accuracy by referring to past thumbnail results from the same viewer demographic. In this way, the accuracy of the design is improved by referring to past thumbnail results. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit can improve the accuracy of the design by referring to past thumbnail results when generating thumbnails using AI.

[0107] When generating thumbnails, the thumbnail generation unit can determine the priority of designs based on the viewing history of the videos. The viewing history includes, for example, the number of views, the viewing time, the type of videos viewed, etc., but is not limited to these examples. For example, the thumbnail generation unit prioritizes the design of videos that have been viewed many times. For example, the thumbnail generation unit prioritizes the design of videos that have been viewed many times. The thumbnail generation unit can also prioritize the design of videos that have been viewed for a long time. For example, the thumbnail generation unit prioritizes the design of videos that have been viewed for a long time. The thumbnail generation unit can also prioritize the design of videos that have been highly rated by viewers. For example, the thumbnail generation unit prioritizes the design of videos that have been highly rated by viewers. In this way, the design priority is determined taking the viewing history into consideration. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit can use AI to determine the priority of designs based on the viewing history of the videos when generating thumbnails.

[0108] The thumbnail generation unit can estimate the user's emotion and change the thumbnail display method based on the estimated user's emotion. Examples of the thumbnail display method include, but are not limited to, image size, display position, and display time. For example, when the user is excited, the thumbnail generation unit provides a visually stimulating display method. For example, when the user is excited, the thumbnail generation unit provides a visually stimulating display method. Furthermore, when the user is relaxed, the thumbnail generation unit can provide a calm display method. For example, when the user is relaxed, the thumbnail generation unit provides a calm display method. Furthermore, when the user is stressed, the thumbnail generation unit can provide a simple and easy-to-understand display method. For example, when the user is stressed, the thumbnail generation unit provides a simple and easy-to-understand display method. In this way, the thumbnail display method is adjusted according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit may use AI to estimate a user's emotion and change the way thumbnails are displayed based on the estimated user's emotion.

[0109] The thumbnail generation unit can design thumbnails based on attribute information of viewers of the video when generating thumbnails. Viewer attribute information includes, but is not limited to, age, gender, region, and interests. The thumbnail generation unit can change the design style depending on the viewer's age group, for example. For example, the thumbnail generation unit can change the design style depending on the viewer's age group. The thumbnail generation unit can also change the color of the design depending on the viewer's gender. For example, the thumbnail generation unit can change the color of the design depending on the viewer's gender. The thumbnail generation unit can also change design elements depending on the viewer's interests. For example, the thumbnail generation unit changes design elements depending on the viewer's interests. This allows thumbnail design to take viewer attribute information into consideration. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without AI. For example, the thumbnail generation unit can use AI to design thumbnails based on attribute information of viewers of the video when generating thumbnails.

[0110] The thumbnail generation unit can weight the design based on the viewing region of the video when generating thumbnails. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The thumbnail generation unit can weight the design by taking into account the cultural background of the viewing region. For example, the thumbnail generation unit can weight the design by taking into account the cultural background of the viewing region. The thumbnail generation unit can also weight the design by taking into account the language of the viewing region. For example, the thumbnail generation unit can weight the design by taking into account the language of the viewing region. The thumbnail generation unit can also weight the design by taking into account trends in the viewing region. For example, the thumbnail generation unit can weight the design by taking into account trends in the viewing region. In this way, the thumbnail design is weighted based on the viewing region. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit can use AI to weight the design based on the viewing region of the video when generating thumbnails.

[0111] The thumbnail generation unit may improve the accuracy of the design by referring to literature related to the video when generating thumbnails. Examples of related literature include, but are not limited to, academic papers, technical reports, and industry reports. For example, the thumbnail generation unit may improve the accuracy of the design by referring to related academic papers. For example, the thumbnail generation unit may improve the accuracy of the design by referring to related academic papers. The thumbnail generation unit may also improve the accuracy of the design by referring to related news articles. For example, the thumbnail generation unit may improve the accuracy of the design by referring to related news articles. The thumbnail generation unit may also improve the accuracy of the design by referring to related books. For example, the thumbnail generation unit may improve the accuracy of the design by referring to related books. Thus, the accuracy of the design is improved by referring to related literature. Some or all of the above-described processing in the thumbnail generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the thumbnail generation unit may use AI to improve the accuracy of the design by referring to literature related to the video when generating thumbnails.

[0112] The title generation unit can estimate the user's emotions and change the way the title is expressed based on the estimated user's emotions. Examples of title expression methods include, but are not limited to, formal expressions and casual expressions. For example, when the user is relaxed, the title generation unit uses soft expressions. For example, when the user is relaxed, the title generation unit uses soft expressions. Furthermore, when the user is in a hurry, the title generation unit can also use concise expressions. For example, when the user is in a hurry, the title generation unit uses concise expressions. Furthermore, when the user is excited, the title generation unit can also use emphasized expressions. For example, when the user is excited, the title generation unit uses emphasized expressions. In this way, the way the title is expressed is adjusted according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or without AI. For example, the title generation unit can use AI to estimate the user's emotions and change the way the title is expressed based on the estimated user's emotions.

[0113] When generating a title, the title generation unit can apply a different title generation algorithm depending on the genre or theme of the video. Examples of title generation algorithms include, but are not limited to, natural language processing algorithms and machine learning algorithms. For example, for educational videos, the title generation unit applies a title generation algorithm that emphasizes important points. For example, for educational videos, the title generation unit applies a title generation algorithm that emphasizes important points. Furthermore, for entertainment videos, the title generation unit can also apply a title generation algorithm that emphasizes visual elements. For example, for entertainment videos, the title generation unit can also apply a title generation algorithm that emphasizes fact-checking to news videos. For example, for news videos, the title generation unit applies a title generation algorithm that emphasizes fact-checking. In this way, titles are generated according to the genre or theme. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can use AI to apply a different title generation algorithm depending on the genre or theme of the video when generating a title.

[0114] When generating a title, the title generation unit can improve the accuracy of the title generation by referring to past title results. Past title results include, but are not limited to, past title results in the same genre or past title results from the same broadcaster. For example, the title generation unit can improve the accuracy by referring to past title results in the same genre. For example, the title generation unit can improve the accuracy by referring to past title results in the same genre. The title generation unit can also improve the accuracy by referring to past title results from the same broadcaster. For example, the title generation unit can improve the accuracy by referring to past title results from the same broadcaster. The title generation unit can also improve the accuracy by referring to past title results from the same viewer demographic. For example, the title generation unit can improve the accuracy by referring to past title results from the same viewer demographic. In this way, the accuracy of the generation is improved by referring to past title results. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can improve the accuracy of the title generation by referring to past title results using AI.

[0115] When generating titles, the title generation unit can determine the priority of title generation based on the viewing history of the videos. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the title generation unit prioritizes title generation for videos that have been viewed many times. For example, the title generation unit prioritizes title generation for videos that have been viewed many times. The title generation unit can also prioritize title generation for videos that have been viewed long times. For example, the title generation unit prioritizes title generation for videos that have been viewed long times. The title generation unit can also prioritize title generation for videos that have been highly rated by viewers. For example, the title generation unit prioritizes title generation for videos that have been highly rated by viewers. In this way, the priority of title generation is determined taking the viewing history into consideration. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can use AI to determine the priority of title generation based on the viewing history of the videos when generating titles.

[0116] The title generation unit can estimate the user's emotions and change the length of the title based on the estimated user's emotions. Examples of title length include, but are not limited to, a character limit and a time limit. For example, if the user is in a hurry, the title generation unit provides a short and to-the-point title. For example, if the user is in a hurry, the title generation unit provides a short and to-the-point title. Furthermore, if the user is relaxed, the title generation unit can provide a longer title with detailed explanations. For example, if the user is relaxed, the title generation unit can provide a longer title with detailed explanations. Furthermore, if the user is excited, the title generation unit can provide a title with emphasized expressions. For example, if the user is excited, the title generation unit provides a title with emphasized expressions. In this way, the length of the title is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can 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 processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit may use AI to estimate the user's emotion and change the length of the title based on the estimated user's emotion.

[0117] The title generation unit can generate a title based on attribute information of a viewer of a video. The viewer's attribute information includes, but is not limited to, age, gender, region, and interests. The title generation unit, for example, changes the expression of the title according to the viewer's age group. For example, the title generation unit changes the expression of the title according to the viewer's age group. The title generation unit can also change the expression of the title according to the viewer's gender. For example, the title generation unit changes the expression of the title according to the viewer's gender. The title generation unit can also change the expression of the title according to the viewer's interests. For example, the title generation unit changes the expression of the title according to the viewer's interests. In this way, titles are generated taking into account the viewer's attribute information. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can use AI to generate a title based on attribute information of a viewer of a video.

[0118] The title generation unit can weight the title generation based on the viewing region of the video when generating the title. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The title generation unit can weight the title generation based on, for example, the cultural background of the viewing region. For example, the title generation unit can weight the title generation based on the cultural background of the viewing region. The title generation unit can also weight the title generation based on the language of the viewing region. For example, the title generation unit can weight the title generation based on the language of the viewing region. The title generation unit can also weight the title generation based on trends in the viewing region. For example, the title generation unit can weight the title generation based on trends in the viewing region. In this way, title generation is weighted based on the viewing region. Some or all of the above-described processing in the title generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the title generation unit can use AI to weight the title generation based on the viewing region of the video when generating the title.

[0119] The title generation unit can improve the accuracy of title generation by referring to literature related to the video when generating the title. Related literature includes, but is not limited to, academic papers, technical reports, industry reports, etc. For example, the title generation unit can improve the accuracy of title generation by referring to related academic papers. For example, the title generation unit can improve the accuracy of title generation by referring to related academic papers. The title generation unit can also improve the accuracy of title generation by referring to related news articles. For example, the title generation unit can improve the accuracy of title generation by referring to related news articles. The title generation unit can also improve the accuracy of title generation by referring to related books. For example, the title generation unit can improve the accuracy of title generation by referring to related books. In this way, the accuracy of title generation is improved by referring to related literature. Some or all of the above-described processing in the title generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the title generation unit can improve the accuracy of title generation by referring to literature related to the video using AI.

[0120] The upload unit can estimate the user's emotions and change the timing of uploading based on the estimated user's emotions. Examples of upload timing include, but are not limited to, viewer activity times and optimal distribution times. For example, the upload unit can upload immediately when the user is excited. For example, the upload unit can upload immediately when the user is excited. Furthermore, the upload unit can also upload at the optimal timing when the user is relaxed. For example, the upload unit can upload at the optimal timing when the user is relaxed. Furthermore, the upload unit can upload at a time convenient for the user when the user is stressed. For example, the upload unit can upload at a time convenient for the user when the user is stressed. In this way, the upload timing is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the upload unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the upload unit can use AI to estimate the user's emotions and change the timing of uploading based on the estimated user emotions.

[0121] The uploading unit can apply different uploading algorithms depending on the genre or theme of the video when uploading. Examples of uploading algorithms include, but are not limited to, scheduling algorithms and load balancing algorithms. For example, in the case of educational videos, the uploading unit applies an algorithm that uploads during times when there are many viewers. For example, in the case of educational videos, the uploading unit applies an algorithm that uploads during times when there are many viewers. Furthermore, in the case of entertainment videos, the uploading unit can also apply an algorithm that uploads during times when viewers are relaxing. For example, in the case of entertainment videos, the uploading unit applies an algorithm that uploads during times when viewers are relaxing. Furthermore, in the case of news videos, the uploading unit can also apply an algorithm that uploads immediately with an emphasis on timeliness. For example, in the case of news videos, the uploading unit applies an algorithm that uploads immediately with an emphasis on timeliness. In this way, uploading is performed according to the genre or theme. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to apply different uploading algorithms depending on the genre or theme of the video when uploading.

[0122] The upload unit can improve the accuracy of uploading by referring to past upload results when uploading. Past upload results include, but are not limited to, past upload results in the same genre or past upload results by the same distributor. For example, the upload unit can improve the accuracy by referring to past upload results in the same genre. For example, the upload unit can improve the accuracy by referring to past upload results in the same genre. The upload unit can also improve the accuracy by referring to past upload results by the same distributor. For example, the upload unit can improve the accuracy by referring to past upload results by the same distributor. The upload unit can also improve the accuracy by referring to past upload results for the same viewer demographic. For example, the upload unit can improve the accuracy by referring to past upload results for the same viewer demographic. In this way, the accuracy of uploading is improved by referring to past upload results. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without using AI. For example, the upload unit can improve the accuracy of uploading by referring to past upload results when uploading using AI.

[0123] The uploading unit can determine the upload priority based on the viewing history of the video at the time of uploading. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the uploading unit prioritizes uploading videos with a large number of views. For example, the uploading unit prioritizes uploading videos with a large number of views. The uploading unit can also prioritize uploading videos with a long viewing time. For example, the uploading unit prioritizes uploading videos with a long viewing time. The uploading unit can also prioritize uploading videos with high viewer ratings. For example, the uploading unit prioritizes uploading videos with high viewer ratings. In this way, the upload priority is determined taking the viewing history into consideration. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to determine the upload priority based on the viewing history of the video at the time of uploading.

[0124] The upload unit can estimate the user's emotions and change the display method of the upload based on the estimated user's emotions. Examples of the display method of the upload include, but are not limited to, a notification method, a display position, and a display time. For example, when the user is excited, the upload unit provides a visually stimulating display method. For example, when the user is excited, the upload unit provides a visually stimulating display method. The upload unit can also provide a calm display method when the user is relaxed. For example, when the user is relaxed, the upload unit provides a calm display method. The upload unit can also provide a simple and easy-to-understand display method when the user is stressed. For example, when the user is stressed, the upload unit provides a simple and easy-to-understand display method. This adjusts the display method of the upload according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the upload unit may be performed using, for example, an AI, or without using an AI. For example, the upload unit can use AI to estimate a user's emotions and change the way the upload is displayed based on the estimated user emotions.

[0125] The uploading unit can upload a video based on attribute information of the viewer of the video at the time of uploading. The viewer's attribute information includes, but is not limited to, age, gender, region, and interests, for example. The uploading unit can change the timing of uploading according to, for example, the viewer's age group. For example, the uploading unit can change the timing of uploading according to the viewer's age group. The uploading unit can also change the timing of uploading according to the viewer's gender. For example, the uploading unit can change the timing of uploading according to the viewer's interests. For example, the uploading unit can change the timing of uploading according to the viewer's interests. In this way, uploading is performed taking into account the viewer's attribute information. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to upload a video based on the viewer's attribute information at the time of uploading.

[0126] The uploading unit can weight uploads based on the viewing region of the video at the time of uploading. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The uploading unit can weight uploads, for example, by taking into account the cultural background of the viewing region. For example, the uploading unit can weight uploads by taking into account the cultural background of the viewing region. The uploading unit can also weight uploads by taking into account the language of the viewing region. For example, the uploading unit can weight uploads by taking into account the language of the viewing region. The uploading unit can also weight uploads by taking into account trends in the viewing region. For example, the uploading unit can weight uploads by taking into account trends in the viewing region. In this way, weighting of uploads based on the viewing region is performed. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit can use AI to weight uploads based on the viewing region of the video at the time of uploading.

[0127] The uploading unit may refer to literature related to the video at the time of uploading to improve the accuracy of the upload. Examples of related literature include, but are not limited to, academic papers, technical reports, and industry reports. For example, the uploading unit may refer to related academic papers to improve the accuracy of the upload. For example, the uploading unit may refer to related academic papers to improve the accuracy of the upload. The uploading unit may also refer to related news articles to improve the accuracy of the upload. For example, the uploading unit may refer to related news articles to improve the accuracy of the upload. The uploading unit may also refer to related books to improve the accuracy of the upload. For example, the uploading unit may refer to related books to improve the accuracy of the upload. In this way, the accuracy of the upload is improved by referring to the related literature. Some or all of the above-described processing in the uploading unit may be performed using, for example, AI, or may be performed without using AI. For example, the uploading unit may use AI to refer to literature related to the video at the time of uploading to improve the accuracy of the upload.

[0128] The manual correction unit can estimate the user's emotions and change the manual correction interface based on the estimated user emotions. Examples of the manual correction interface include, but are not limited to, the design and operation method of the user interface. For example, when the user is nervous, the manual correction unit provides a calm interface to reduce visual stress. For example, when the user is nervous, the manual correction unit provides a calm interface to reduce visual stress. Furthermore, when the user is having fun, the manual correction unit can provide a bright interface to make inputting work more enjoyable. For example, when the user is having fun, the manual correction unit provides a bright interface to make inputting work more enjoyable. Furthermore, when the user is tired, the manual correction unit can provide a simple, highly visible interface. For example, when the user is tired, the manual correction unit provides a simple, highly visible interface. Thus, the manual correction interface is adjusted according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit may use AI to estimate the user's emotion and change the manual correction interface based on the estimated user's emotion.

[0129] The manual correction unit can apply different correction algorithms depending on the genre or theme of the video during manual correction. Examples of correction algorithms include, but are not limited to, error detection algorithms and optimization algorithms. For example, in the case of an educational video, the manual correction unit applies a correction algorithm that emphasizes important points. For example, in the case of an educational video, the manual correction unit applies a correction algorithm that emphasizes important points. Furthermore, in the case of an entertainment video, the manual correction unit can also apply a correction algorithm that emphasizes visual elements. For example, in the case of an entertainment video, the manual correction unit can also apply a correction algorithm that emphasizes fact checking to the news video. For example, in the case of a news video, the manual correction unit applies a correction algorithm that emphasizes fact checking. In this way, manual correction according to the genre or theme is performed. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can use AI to apply different correction algorithms depending on the genre or theme of the video during manual correction.

[0130] The manual correction unit can improve the accuracy of the correction by referring to past correction results during manual correction. Past correction results include, but are not limited to, past correction results for the same genre or past correction results for the same distributor. For example, the manual correction unit improves the accuracy by referring to past correction results for the same genre. For example, the manual correction unit improves the accuracy by referring to past correction results for the same genre. The manual correction unit can also improve the accuracy by referring to past correction results for the same distributor. For example, the manual correction unit improves the accuracy by referring to past correction results for the same distributor. The manual correction unit can also improve the accuracy by referring to past correction results for the same viewer demographic. For example, the manual correction unit improves the accuracy by referring to past correction results for the same viewer demographic. In this way, the accuracy of the correction is improved by referring to the past correction results. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can improve the accuracy of the correction by referring to past correction results during manual correction using AI.

[0131] During manual correction, the manual correction unit can determine the priority of correction based on the viewing history of the video. The viewing history includes, for example, the number of views, the viewing time, the type of video viewed, etc., but is not limited to these examples. For example, the manual correction unit prioritizes correction of videos that have been viewed many times. For example, the manual correction unit prioritizes correction of videos that have been viewed many times. The manual correction unit can also prioritize correction of videos that have been viewed for a long time. For example, the manual correction unit prioritizes correction of videos that have been viewed for a long time. The manual correction unit can also prioritize correction of videos that have been highly rated by viewers. For example, the manual correction unit prioritizes correction of videos that have been highly rated by viewers. In this way, the priority of correction is determined taking the viewing history into consideration. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can use AI to determine the priority of correction based on the viewing history of the video during manual correction.

[0132] The manual correction unit can estimate the user's emotions and change the display method of the manual corrections based on the estimated user's emotions. Examples of display methods of the manual corrections include, but are not limited to, notification methods, display positions, and display times. For example, when the user is nervous, the manual correction unit provides a simple, highly visible display method. For example, when the user is nervous, the manual correction unit provides a simple, highly visible display method. Furthermore, when the user is relaxed, the manual correction unit can also provide a display method that includes detailed information. For example, when the user is relaxed, the manual correction unit provides a display method that includes detailed information. Furthermore, when the user is in a hurry, the manual correction unit can also provide a display method that focuses on the main points. For example, when the user is in a hurry, the manual correction unit provides a display method that focuses on the main points. This adjusts the display method of the manual corrections according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit may use AI to estimate the user's emotion and change the display method of the manual correction based on the estimated user's emotion.

[0133] The manual correction unit can perform manual correction based on attribute information of viewers of the video during manual correction. Viewer attribute information includes, but is not limited to, age, gender, region, and interests. The manual correction unit can change the focus of correction depending on, for example, the viewer's age group. For example, the manual correction unit can change the focus of correction depending on the viewer's age group. The manual correction unit can also change the focus of correction depending on the viewer's gender. For example, the manual correction unit can change the focus of correction depending on the viewer's interests. For example, the manual correction unit can change the focus of correction depending on the viewer's interests. In this way, manual correction is performed taking into account the viewer's attribute information. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can use AI to perform manual correction based on the viewer's attribute information during manual correction.

[0134] The manual correction unit can weight the correction based on the viewing region of the video during manual correction. The viewing region includes, but is not limited to, for example, a country, a city, or a region. The manual correction unit can weight the correction, for example, by taking into account the cultural background of the viewing region. For example, the manual correction unit can weight the correction by taking into account the cultural background of the viewing region. The manual correction unit can also weight the correction by taking into account the language of the viewing region. For example, the manual correction unit can weight the correction by taking into account the language of the viewing region. The manual correction unit can also weight the correction by taking into account trends in the viewing region. For example, the manual correction unit can weight the correction by taking into account trends in the viewing region. In this way, the weighting of the correction is based on the viewing region. Some or all of the above-described processing in the manual correction unit may be performed using, for example, AI, or may be performed without using AI. For example, the manual correction unit can weight the correction based on the viewing region of the video during manual correction using AI.

[0135] The manual correction unit can improve the accuracy of the correction by referring to related literature of the video during manual correction. Related literature includes, but is not limited to, academic papers, technical reports, industry reports, etc. For example, the manual correction unit can improve the accuracy of the correction by referring to related academic papers. For example, the manual correction unit can improve the accuracy of the correction by referring to related academic papers. The manual correction unit can also improve the accuracy of the correction by referring to related news articles. For example, the manual correction unit can improve the accuracy of the correction by referring to related news articles. The manual correction unit can also improve the accuracy of the correction by referring to related books. For example, the manual correction unit can improve the accuracy of the correction by referring to related books. In this way, the accuracy of the correction is improved by referring to the related literature. Some or all of the above-described processing in the manual correction unit can be performed using, for example, AI, or can be performed without using AI. For example, the manual correction unit can improve the accuracy of the correction by referring to related literature of the video during manual correction using AI. === Hard Collateral 1-1 === Each of the multiple elements, including the analysis unit, translation unit, thumbnail generation unit, title generation unit, upload unit, manual correction unit, and emotion estimation function, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12 and analyzes the content of the video. The translation unit uses a generation AI to translate subtitles and audio based on the analyzed content and is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The thumbnail generation unit and title generation unit are implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 and generate thumbnails and titles optimal for the viewer. The upload unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 and automatically uploads the localized video to a platform selected by the distributor. The manual correction unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and provides an interface for the distributor to make final confirmation and corrections. The emotion estimation function is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the analysis method. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, translation unit, thumbnail generation unit, title generation unit, upload unit, manual correction unit, and emotion estimation function, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and analyzes the content of the video. The translation unit uses a generation AI to translate subtitles and audio based on the analyzed content and is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The thumbnail generation unit and title generation unit are realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and generate thumbnails and titles optimal for the viewer. The upload unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and automatically uploads the localized video to a platform selected by the distributor. The manual correction unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and provides an interface for the broadcaster to make final confirmation and corrections. The emotion estimation function is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the analysis method. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned analysis unit, translation unit, thumbnail generation unit, title generation unit, upload unit, manual correction unit, and emotion estimation function, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12 and analyzes the content of the video. The translation unit uses a generation AI to translate subtitles and audio based on the analyzed content and is realized by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12. The thumbnail generation unit and title generation unit are realized by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12 and generate thumbnails and titles optimal for the viewer. The upload unit is realized by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12 and automatically uploads the localized video to a platform selected by the distributor. The manual correction unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and provides an interface for the distributor to make final confirmation and corrections. The emotion estimation function is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the analysis method. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned analysis unit, translation unit, thumbnail generation unit, title generation unit, upload unit, manual correction unit, and emotion estimation function, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12 and analyzes the content of the video. The translation unit uses a generation AI to translate subtitles and audio based on the analyzed content and is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The thumbnail generation unit and title generation unit are realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12 and generate thumbnails and titles optimal for the viewer. The upload unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12 and automatically uploads the localized video to a platform selected by the distributor. The manual correction unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and provides an interface for the distributor to make final confirmation and corrections. The emotion estimation function is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and estimates the user's emotion and adjusts the analysis method.

[0136] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0137] The localization support system can also analyze a user's viewing history and customize the video localization method based on the viewer's preferences. For example, it can adjust the subtitle and audio translation style based on the genre and theme of the videos the viewer has previously watched. If a viewer is interested in a particular actor or character, it can generate thumbnails and titles based on that information. It can also analyze the viewer's viewing time and frequency to suggest the optimal upload timing. This enables localization that is tailored to the viewer's preferences and improves the viewing experience.

[0138] The translation unit can estimate the user's emotions and adjust the tone of the translation based on the estimated user emotions. For example, if the user is relaxed, the translation can be performed in a softer tone. If the user is excited, the translation can be performed in an energetic tone. Furthermore, if the user is stressed, the translation can be performed in a concise and easy-to-understand tone. This provides a translation that matches the user's emotions, improving the viewing experience.

[0139] When analyzing the content of a video, the analysis unit can collect feedback from viewers of the video in real time and adjust the analysis method based on that feedback. For example, if a viewer gives a high rating to a particular scene, the analysis unit can perform an analysis that emphasizes that scene. Also, if a viewer gives a low rating to a particular scene, the analysis unit can perform an analysis that omits that scene. Furthermore, it is possible to reconstruct the content of the video based on viewer feedback. This allows for an analysis that reflects viewer feedback, improving the viewing experience.

[0140] The thumbnail generation unit can estimate the user's emotion and change the color of the thumbnail based on the estimated user emotion. For example, if the user is relaxed, a thumbnail with a calm color can be provided. If the user is excited, a thumbnail with a vivid color can be provided. Furthermore, if the user is stressed, a thumbnail with a simple, highly visible color can be provided. This provides thumbnails that correspond to the user's emotion, improving the viewing experience.

[0141] The title generation unit can change the font style of the title based on the attribute information of the video viewer. For example, a pop font style can be used for younger viewers, and an easy-to-read font style can be used for older viewers. The unit can also adjust the font weight and color according to the viewer's gender. Furthermore, it can customize the title design according to the viewer's interests. This provides titles that match the viewer's attribute information, improving the viewing experience.

[0142] The upload unit can estimate the user's emotions and change the upload notification method based on the estimated user's emotions. For example, if the user is excited, a visually stimulating notification method can be provided. If the user is relaxed, a calm notification method can be provided. Furthermore, if the user is stressed, a simple and easy-to-understand notification method can be provided. This provides a notification method that corresponds to the user's emotions, improving the viewing experience.

[0143] The manual correction unit can estimate the user's emotions and change the layout of the manual correction interface based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible layout can be provided. If the user is relaxed, a layout including detailed information can be provided. Furthermore, if the user is in a hurry, a layout that focuses on the main points can be provided. This provides an interface that corresponds to the user's emotions, making correction work more efficient.

[0144] When analyzing the content of a video, the analysis unit can determine the analysis priority based on the attribute information of the video's viewers. For example, if there are many young viewers, the analysis can be focused on entertainment elements. Alternatively, if there are many older viewers, the analysis can be focused on providing information. Furthermore, if there are many viewers from a specific region, the analysis can take into account the cultural background of that region. This allows for analysis based on viewer attribute information, improving the viewing experience.

[0145] The translation unit can estimate the user's emotions and adjust the length of the translation based on the estimated user emotions. For example, if the user is in a hurry, a short, to-the-point translation can be provided. If the user is relaxed, a longer translation with detailed explanations can be provided. Furthermore, if the user is excited, a translation with emphasized expressions can be provided. This provides a translation that matches the user's emotions, improving the viewing experience.

[0146] The thumbnail generator can customize the design of the thumbnail based on the demographic information of the viewer of the video. For example, a pop design can be used for younger viewers, while a simple, highly visible design can be used for older viewers. The color and layout can also be adjusted depending on the viewer's gender. Furthermore, it is possible to customize the elements of the thumbnail based on the viewer's interests. This provides thumbnails that match the viewer's demographic information, improving the viewing experience.

[0147] The processing flow of the second embodiment will be briefly explained below.

[0148] Step 1: The analysis unit analyzes the content of the video. The video content includes video, audio, and text information. The analysis unit uses video analysis technology to extract important scenes, speech recognition technology to convert the audio content into text, and natural language processing technology to extract important keywords from the text information. Step 2: The translation unit uses generation AI to translate subtitles and audio based on the content analyzed by the analysis unit. Translation is performed using methods such as machine translation or translation by experts. The generation AI uses text generation AI to translate subtitles into natural expressions, and speech generation AI to translate audio into natural expressions. It also converts to appropriate expressions taking cultural differences into account. Step 3: The thumbnail generator generates thumbnails based on the content translated by the translation unit. Thumbnails are generated based on the content of the video using image recognition technology, and the optimal thumbnail is generated taking into account the viewer's demographic information and the cultural background of the viewing area. Step 4: The title generation unit generates a title based on the content translated by the translation unit. The title is generated based on the content of the video using natural language processing technology, and the optimal title is generated taking into account the viewer's attribute information and the cultural background of the viewing area. Step 5: The uploading unit uploads the localized video, including the thumbnails and titles generated by the thumbnail and title generators, to the platform selected by the distributor. Uploading can be done automatically to the platform selected by the distributor, or manually or according to a schedule.

[0149] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0150] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0154] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0155] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0162] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0170] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0171] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0177] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0178] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0179] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0180] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0181] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0182] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0183] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0184] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0185] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0186] 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.

[0187] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0188] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0189] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0191] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0192] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0193] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0194] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0195] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0196] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0197] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0198] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0199] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0200] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0201] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0202] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0203] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0204] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0205] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0206] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0207] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0208] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0209] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0210] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0211] 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.

[0212] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0213] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0214] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0215] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0216] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0217] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0218] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0219] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0220] [Explanation of symbols]

[0221] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the content of the video; a translation unit that translates subtitles or audio based on the content analyzed by the analysis unit; a thumbnail generation unit that generates thumbnails based on the content translated by the translation unit; a title generation unit that generates a title based on the content translated by the translation unit; an uploading unit that uploads the localized video, including the thumbnail and title generated by the thumbnail generating unit and the title generating unit, to a platform selected by a distributor. A system characterized by:

2. The translation unit Translating subtitles and audio using generative AI 2. The system of claim 1.

3. The translation unit Generative AI converts expressions taking cultural differences into account 2. The system of claim 1.

4. The thumbnail generation unit Generate thumbnails appropriate for different audiences 2. The system of claim 1.

5. The title generation unit Generate titles appropriate for each country's audience 2. The system of claim 1.

6. The upload unit Upload localized videos to the distributor's platform of choice 2. The system of claim 1.

7. It has a manual correction section that allows streamers to check and correct content.

2. The system of claim 1.

8. The analysis unit Estimate the user's emotions and change the video analysis method based on the estimated user emotions.

2. The system of claim 1.

9. The analysis unit When analyzing the content of a video, different analysis algorithms are applied depending on the genre or theme of the video.

2. The system of claim 1.

Images