system

Abstract

The system according to this embodiment aims to allow users to easily create AITubers without programming skills. [Solution] The system according to the embodiment comprises an avatar generation unit, a script generation unit, a speech synthesis unit, a motion synchronization unit, and a subtitle generation unit. The avatar generation unit generates avatars using 3D or Live2D. The script generation unit generates a script for content based on the avatars generated by the avatar generation unit. The speech synthesis unit synthesizes speech based on the script generated by the script generation unit. The motion synchronization unit synchronizes the movements of the avatars based on the speech synthesized by the speech synthesis unit. The subtitle generation unit generates subtitles based on the speech synthesized by the speech synthesis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the production of an AITuber requires advanced programming skills and it is difficult for ordinary users to produce it easily.

[0005] The system according to the embodiment aims to easily produce an AITuber even without programming skills.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an avatar generation unit, a script generation unit, a speech synthesis unit, a motion synchronization unit, and a subtitle generation unit. The avatar generation unit generates avatars using 3D or Live2D. The script generation unit generates a script for content based on the avatars generated by the avatar generation unit. The speech synthesis unit synthesizes speech based on the script generated by the script generation unit. The motion synchronization unit synchronizes the movements of the avatars based on the speech synthesized by the speech synthesis unit. The subtitle generation unit generates subtitles based on the speech synthesized by the speech synthesis unit. [Effects of the Invention]

[0007] The system according to this embodiment allows for the easy creation of an AITuber even without programming skills. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AITuber creation platform according to an embodiment of the present invention is a system that allows anyone to easily create an AI-based AITuber, or AITuber for short, without any programming skills. This system allows users to access an interface for creating an AITuber through a social networking app and sequentially perform common steps such as creating 3D or Live2D avatars, writing content scripts, synthesizing speech, synchronizing motion to match the speech, and adding subtitles. All of these steps are supported by AI, allowing users to operate intuitively. For example, when creating a 3D or Live2D avatar, the user can intuitively generate an avatar using an image generation AI. When the user uploads a photo, the AI ​​generates an avatar based on that photo. Next, the user creates a content script. Here, an LLM (Large-Scale Language Model) is used to generate AITuber speech based on text entered by the user. For example, if the user enters "Today I will introduce a new game," the AI ​​generates a script based on that statement. Furthermore, speech synthesis is performed. The AI ​​synthesizes speech based on the generated script. For example, the AI ​​generates speech to match the tone and accent of the voice chosen by the user. Finally, motion synchronization is performed to match the speech. The AI ​​synchronizes the avatar's movements based on the generated audio. For example, it makes the avatar's mouth move in accordance with the speech. Finally, it adds subtitles. The AI ​​automatically generates subtitles based on the generated audio and adds them to the video. This allows viewers to understand the content not only through audio but also through subtitles. In this way, anyone can easily create an AITuber without any programming skills. This mechanism is expected to lead to the rapid expansion of the domestic AITuber market, and the increase in creative content will spread new forms of entertainment. As a result, the AITuber creation platform makes it easy for anyone to create an AITuber, even without programming skills.

[0029] The AITuber creation platform according to this embodiment comprises an avatar generation unit, a script generation unit, a speech synthesis unit, a motion synchronization unit, and a subtitle generation unit. The avatar generation unit generates avatars using 3D or Live2D. The avatar generation unit generates avatars using, for example, an image generation AI. For example, if a user uploads their own photo, the AI ​​can generate an avatar based on that photo. The avatar generation unit can also customize avatars based on styles and characteristics chosen by the user. For example, it can generate avatars based on hairstyles and clothing chosen by the user. The script generation unit generates a script for content based on the avatar generated by the avatar generation unit. The script generation unit generates scripts using, for example, an LLM (Large-Scale Language Model). For example, if a user inputs "Today I will introduce a new game," the AI ​​can generate a script based on that statement. The script generation unit can also customize scripts based on topics and themes chosen by the user. For example, it can add relevant information to the script based on the theme chosen by the user. The speech synthesis unit synthesizes speech based on the script generated by the script generation unit. The speech synthesis unit synthesizes speech according to the tone and accent of the voice selected by the user, for example. For example, it can generate speech based on the characteristics of the voice selected by the user. The speech synthesis unit can also customize speech based on the language or dialect selected by the user, for example. For example, it can generate speech based on the language selected by the user. The motion synchronization unit synchronizes the avatar's movements based on the speech synthesized by the speech synthesis unit. For example, the motion synchronization unit synchronizes the avatar's mouth movements with the speech, for example. For example, it can customize the avatar's movements based on movements selected by the user. The motion synchronization unit can also synchronize the avatar's movements based on gestures or facial expressions selected by the user, for example. For example, it can generate avatar movements based on gestures selected by the user. The subtitle generation unit generates subtitles based on the speech synthesized by the speech synthesis unit. For example, the subtitle generation unit automatically generates subtitles based on the generated speech and adds them to the video.For example, subtitles can be customized based on the font and style selected by the user. The subtitle generation unit can also generate subtitles based on the language and format selected by the user. For instance, subtitles can be generated based on the language selected by the user. This allows anyone to easily create an AITuber using the AITuber creation platform according to this embodiment, even without programming skills.

[0030] The avatar generation unit generates avatars using 3D and Live2D methods. For example, it uses image generation AI to create avatars. Specifically, when a user uploads a photo, the AI ​​can generate an avatar based on that photo. This AI uses deep learning technology to extract facial features from the photo and convert them into a 3D or Live2D model. Furthermore, the avatar generation unit can customize avatars based on styles and features chosen by the user. For example, it can generate avatars based on the user's chosen hairstyle and clothing. The user selects hair color, eye shape, clothing type, etc., through the interface, and the AI ​​generates the avatar in real time based on these selections. This allows users to easily create avatars tailored to their preferences. The avatar generation unit can also add backgrounds and accessories chosen by the user, allowing for the creation of more unique avatars. For example, it can adjust the avatar's shadows and light reflections to match the background chosen by the user. This makes the avatar more realistic and appealing. Additionally, the avatar generation unit can save the generated avatars and allow for later re-editing. This allows users to customize their avatars multiple times and use them in different content.

[0031] The script generation unit generates content scripts based on avatars generated by the avatar generation unit. The script generation unit uses, for example, a Large-Scale Language Model (LLM) to generate scripts. Specifically, if a user inputs "Today I'll introduce a new game," the AI ​​can generate a script based on that statement. This LLM utilizes natural language processing technology to understand user input and generate an appropriate script accordingly. For example, the script can be customized based on a user-selected topic or theme. Relevant information can be added to the script based on the user's chosen theme. For instance, if a user selects "Review of a new game" as their theme, the AI ​​will generate a detailed script including the game's features, gameplay, and ratings. Furthermore, the script generation unit can learn from the user's past inputs and preferences to provide more personalized scripts. This allows users to create consistent content. Additionally, the script generation unit provides an interface for editing the generated scripts, allowing users to modify them in their own words. This enables users to create content tailored to their own style and tone, based on the AI-generated script.

[0032] The speech synthesis unit synthesizes speech based on the script generated by the script generation unit. The speech synthesis unit can, for example, synthesize speech to match the tone and accent of the user's voice. Specifically, it can generate speech based on the voice characteristics selected by the user. This speech synthesis technology uses a deep learning model to generate natural-sounding speech from text. For example, it can adjust the pitch, speed, and intonation of the speech based on the tone and accent of the user's voice. The speech synthesis unit can also customize the speech based on the language or dialect selected by the user. For example, it can generate speech based on the language selected by the user. This allows users to easily create speech that is best suited to their content. Furthermore, the speech synthesis unit also provides a real-time preview function of the generated speech, allowing users to check the quality of the speech and adjust it as needed. This enables users to easily create high-quality speech and enhance the appeal of their content.

[0033] The motion synchronization unit synchronizes the avatar's movements based on the speech synthesized by the speech synthesis unit. For example, the motion synchronization unit synchronizes the avatar's mouth movements to match the user's speech. Specifically, it analyzes the waveform and pitch of the speech and adjusts the avatar's mouth movements in real time based on that analysis. It can also customize the avatar's movements based on movements selected by the user. For example, it can synchronize the avatar's movements based on gestures and facial expressions selected by the user. This allows the avatar to move more naturally and realistically. Furthermore, the motion synchronization unit can adjust the avatar's movements to match the background and situation selected by the user. For example, it can adjust the avatar's movements and position to match the background selected by the user. This allows the avatar to move more consistently, improving the quality of the content. In addition, the motion synchronization unit can also capture the user's own movements and reflect them in the avatar. This allows users to reflect their own movements in the avatar and create more unique content.

[0034] The subtitle generation unit generates subtitles based on the audio synthesized by the speech synthesis unit. For example, the subtitle generation unit automatically generates subtitles based on the generated audio and adds them to the video. Specifically, it uses speech recognition technology to convert audio into text and displays it as subtitles. For example, users can customize subtitles based on their chosen font and style. Users can select font type, size, color, etc., through the interface and generate subtitles accordingly. The subtitle generation unit can also generate subtitles based on the user's chosen language and format. For example, it can generate subtitles based on the user's chosen language. This allows users to easily create multilingual content. Furthermore, the subtitle generation unit provides a real-time preview function for the generated subtitles, allowing users to check the quality of the subtitles and adjust them as needed. This enables users to easily create high-quality subtitles and improve the content viewing experience. The subtitle generation unit also has a function to automatically synchronize subtitles with the timing of the audio, allowing users to generate accurate subtitles without any effort.

[0035] The project management department performs project management. For example, the project management department handles tasks, progress tracking, and resource allocation. For instance, the project management department can monitor project progress in real time and track task progress. Furthermore, the project management department can optimize resource allocation and support the efficient progress of the project. For example, the project management department can dynamically allocate resources and adjust task priorities according to project progress. This allows for efficient management of project progress. Some or all of the above processes performed by the project management department may be carried out using AI, or not. For example, the project management department can input project progress into AI, which can then suggest optimal resource allocation and task priorities.

[0036] The posting support department provides posting support. For example, the posting support department handles posting scheduling and content optimization. For example, the posting support department can optimize posting timing and suggest the optimal posting time to attract viewers' attention. The posting support department can also optimize posting content and suggest effective content to attract viewers' attention. For example, the posting support department can suggest keywords and hashtags to attract viewers' attention and optimize posting content. This allows for efficient posting support. Some or all of the above processes in the posting support department may be performed using AI, or not. For example, the posting support department can input the posting schedule into AI, which can then suggest the optimal posting time and content.

[0037] The avatar generation unit can generate avatars using image generation AI. For example, the avatar generation unit uses image generation AI such as GAN (Generative Opposite Network) or VAE (Variational Autoencoder) to generate avatars. For instance, if a user uploads a photo, the AI ​​can generate an avatar based on that photo. Furthermore, the avatar generation unit can customize avatars based on styles and characteristics chosen by the user. For example, it can generate avatars based on hairstyles and clothing chosen by the user. This allows for intuitive avatar generation using image generation AI. Some or all of the above-described processes in the avatar generation unit may be performed using AI, or they may not. For example, the avatar generation unit can input a user's photo into the AI, which can then generate an avatar.

[0038] The script generation unit can generate scripts using LLM. For example, if a user inputs "Today I will introduce a new game," the AI ​​can generate a script based on that statement. The script generation unit can also customize scripts based on topics or themes selected by the user. For example, it can add relevant information to the script based on the theme selected by the user. This allows for efficient script generation using LLM. Some or all of the above-described processes in the script generation unit may be performed using AI, or not. For example, the script generation unit can input user input into the AI, which can then generate a script.

[0039] The speech synthesis unit can synthesize speech according to the tone and accent of the voice selected by the user. The speech synthesis unit synthesizes speech using, for example, a speech synthesis engine. For example, it can generate speech based on the voice characteristics selected by the user. The speech synthesis unit can also customize speech based on the language or dialect selected by the user. For example, it can generate speech based on the language selected by the user. This allows for the synthesis of speech tailored to the user's preferences. Some or all of the above-described processes in the speech synthesis unit may be performed using, for example, AI, or without AI. For example, the speech synthesis unit can input the voice characteristics selected by the user into the AI, and the AI ​​can generate speech.

[0040] The motion synchronization unit can synchronize the avatar's mouth movements with the speech. For example, the motion synchronization unit can synchronize the avatar's mouth movements with speech using speech recognition technology. For example, the avatar's movements can be customized based on movements selected by the user. The motion synchronization unit can also synchronize the avatar's movements based on gestures and facial expressions selected by the user. For example, it can generate avatar movements based on gestures selected by the user. This enables natural avatar movements that match the speech. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input speech data into AI, and the AI ​​can generate avatar movements.

[0041] The subtitle generation unit can automatically generate subtitles based on the generated audio and add them to the video. For example, the subtitle generation unit can automatically generate subtitles based on audio generated using speech recognition technology and add them to the video. For example, subtitles can be customized based on fonts and styles selected by the user. The subtitle generation unit can also generate subtitles based on languages ​​and formats selected by the user. For example, subtitles can be generated based on languages ​​selected by the user. This allows for automatic subtitle generation, making it easier for viewers to understand the content. Some or all of the above-described processes in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input audio data into AI, and the AI ​​can generate subtitles.

[0042] The avatar generation unit can analyze the user's past avatar creation history and propose the optimal avatar generation method. For example, the avatar generation unit can analyze the past avatar creation history and propose avatars with similar styles based on the styles of avatars the user has created in the past. For example, it can propose the optimal avatar color palette based on the colors and designs the user has selected in the past. The avatar generation unit can also propose the optimal accessories based on the accessories the user has used in the past. For example, it can propose the optimal accessories based on the accessories the user has used in the past. This allows the system to propose the optimal avatar generation method based on past history. Some or all of the above processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the past avatar creation history into AI, and the AI ​​can propose the optimal avatar generation method.

[0043] The avatar generation unit can automatically select the avatar's clothing and accessories based on the user's preferences during avatar generation. For example, the avatar generation unit can automatically select the avatar's clothing based on a casual style chosen by the user. For example, it can automatically select the avatar's clothing based on a formal style chosen by the user. The avatar generation unit can also automatically select the avatar's clothing based on a sporty style chosen by the user. For example, it can automatically select the avatar's clothing based on a sporty style chosen by the user. This allows for the automatic selection of the avatar's clothing and accessories based on the user's preferences. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's preferences into AI, and the AI ​​can select the avatar's clothing and accessories.

[0044] The avatar generation unit can incorporate region-specific elements by considering the user's geographical location information during avatar generation. For example, if the user is in Japan, the avatar generation unit can incorporate Japanese clothing and traditional Japanese accessories into the avatar. For example, if the user is in America, the avatar generation unit can incorporate casual American-style clothing into the avatar. Furthermore, if the user is in India, the avatar generation unit can incorporate a sari and traditional Indian accessories into the avatar. This allows for the generation of avatars that incorporate region-specific elements. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's geographical location information into AI, and the AI ​​can generate an avatar that incorporates region-specific elements.

[0045] The avatar generation unit can analyze the user's social media activity and suggest relevant avatars during avatar generation. For example, the avatar generation unit can suggest avatar expressions and poses based on emojis and stamps that the user frequently uses on social media. For example, it can suggest avatar styles based on the content that the user frequently posts on social media. The avatar generation unit can also suggest avatar designs based on the styles of influencers that the user follows on social media. For example, it can suggest avatar designs based on the styles of influencers that the user follows on social media. This allows the avatar generation unit to suggest relevant avatars based on social media activity. Some or all of the above processing in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's social media activity into AI, which can then suggest relevant avatars.

[0046] The script generation unit can generate the optimal script by referring to past script data during script generation. For example, the script generation unit can refer to past script data and generate a script with a similar style based on the style of scripts previously created by the user. For example, it can generate the optimal script based on phrases and expressions previously used by the user. The script generation unit can also generate related scripts based on the themes of scripts previously created by the user. For example, it can generate related scripts based on the themes of scripts previously created by the user. This allows for the generation of the optimal script based on past data. Some or all of the above processes in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input past script data into AI, and the AI ​​can generate the optimal script.

[0047] The script generation unit can customize the style of the script based on the user's preferences during script generation. For example, the script generation unit can customize the script based on a casual style chosen by the user. For example, it can customize the script based on a formal style chosen by the user. The script generation unit can also customize the script based on a humorous style chosen by the user. For example, it can customize the script based on a humorous style chosen by the user. This allows the script style to be customized based on the user's preferences. Some or all of the above processing in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input the user's preferences into AI, and the AI ​​can customize the style of the script.

[0048] The script generation unit can incorporate region-specific expressions by considering the user's geographical location information during script generation. For example, if the user is in Japan, the script generation unit can incorporate expressions that are appropriate for Japanese culture and customs. For example, if the user is in the United States, it can incorporate expressions that are appropriate for American culture and customs. Furthermore, if the user is in France, the script generation unit can incorporate expressions that are appropriate for French culture and customs. For example, if the user is in France, it can incorporate expressions that are appropriate for French culture and customs. This makes it possible to generate scripts that incorporate region-specific expressions. Some or all of the above processing in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input the user's geographical location information into the AI, and the AI ​​can generate a script that incorporates region-specific expressions.

[0049] The script generation unit can analyze the user's social media activity and suggest relevant scripts when generating a script. For example, the script generation unit can suggest relevant scripts based on the content the user frequently posts on social media. For example, it can suggest scripts based on the style of influencers the user follows on social media. The script generation unit can also suggest scripts based on phrases and expressions the user frequently uses on social media. For example, it can suggest scripts based on phrases and expressions the user frequently uses on social media. This allows the script generation unit to suggest relevant scripts based on social media activity. Some or all of the above processing in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input the user's social media activity into AI, which can then suggest relevant scripts.

[0050] The speech synthesis unit can generate the optimal speech by referring to past speech data during speech synthesis. For example, the speech synthesis unit can refer to past speech data and generate the optimal speech based on the tone and accent of speech previously selected by the user. For example, it can generate the optimal speech based on phrases and expressions previously used by the user. The speech synthesis unit can also generate speech with a similar style based on speech styles previously created by the user. For example, it can generate speech with a similar style based on speech styles previously created by the user. This allows for the generation of the optimal speech based on past data. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input past speech data into AI, and the AI ​​can generate the optimal speech.

[0051] The speech synthesis unit can customize the accent of the voice based on the user's preferences during speech synthesis. For example, the speech synthesis unit can customize the voice based on the accent of a region selected by the user. For example, it can customize the voice based on the voice of a character selected by the user. The speech synthesis unit can also customize the voice based on the emotional tone selected by the user. For example, it can customize the voice based on the emotional tone selected by the user. This allows the accent of the voice to be customized according to the user's preferences. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input the user's preferences into the AI, and the AI ​​can customize the accent of the voice.

[0052] The speech synthesis unit can incorporate regional accents by considering the user's geographical location information during speech synthesis. For example, if the user is in the UK, the speech synthesis unit can incorporate a British English accent. For example, if the user is in the US, it can incorporate an American English accent. The speech synthesis unit can also incorporate an Australian English accent if the user is in Australia. For example, if the user is in Australia, it can incorporate an Australian English accent. This makes it possible to generate speech that incorporates regional accents. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input the user's geographical location information into the AI, and the AI ​​can generate speech that incorporates regional accents.

[0053] The speech synthesis unit can analyze the user's social media activity during speech synthesis and suggest relevant audio. For example, the speech synthesis unit can suggest relevant audio based on phrases and expressions that the user frequently uses on social media. For example, it can suggest audio based on the voice style of influencers that the user follows on social media. The speech synthesis unit can also suggest relevant audio based on the content that the user frequently posts on social media. For example, it can suggest relevant audio based on the content that the user frequently posts on social media. In this way, relevant audio can be suggested based on social media activity. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input the user's social media activity into AI, and the AI ​​can suggest relevant audio.

[0054] The motion synchronization unit can generate optimal movements by referring to past motion data during motion synchronization. For example, the motion synchronization unit can refer to past motion data and generate similar movements based on motion data previously used by the user. For example, it can generate optimal movements based on movements that the user has preferred in the past. The motion synchronization unit can also analyze motion data previously used by the user and generate the most natural movements. For example, it can analyze motion data previously used by the user and generate the most natural movements. This allows for the generation of optimal movements based on past data. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input past motion data into AI, and the AI ​​can generate optimal movements.

[0055] The motion synchronization unit can customize the avatar's movements based on the user's preferences during motion synchronization. For example, the motion synchronization unit can customize the avatar's movements based on the dance style selected by the user. For example, it can customize the avatar's movements based on the gestures selected by the user. The motion synchronization unit can also customize the avatar's movements based on the expression method selected by the user. For example, it can customize the avatar's movements based on the expression method selected by the user. This allows the avatar's movements to be customized based on the user's preferences. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input the user's preferences into the AI, and the AI ​​can customize the avatar's movements.

[0056] The motion synchronization unit can incorporate region-specific movements by considering the user's geographical location information during motion synchronization. For example, if the user is in Japan, the motion synchronization unit can incorporate traditional Japanese movements into the avatar. For example, if the user is in America, it can incorporate casual American movements into the avatar. Furthermore, if the user is in India, the motion synchronization unit can incorporate traditional Indian dance movements into the avatar. For example, if the user is in India, it can incorporate traditional Indian dance movements into the avatar. This makes it possible to generate avatar movements that incorporate region-specific movements. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input the user's geographical location information into AI, and the AI ​​can generate avatar movements that incorporate region-specific movements.

[0057] The motion synchronization unit can analyze the user's social media activity during motion synchronization and suggest relevant movements. For example, the motion synchronization unit can suggest avatar movements based on gestures the user frequently uses on social media. For example, it can suggest avatar movements based on the movements of influencers the user follows on social media. The motion synchronization unit can also suggest relevant movements based on the content the user frequently posts on social media. For example, it can suggest relevant movements based on the content the user frequently posts on social media. This allows for the suggestion of relevant movements based on social media activity. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input the user's social media activity into AI, which can then suggest relevant movements.

[0058] The subtitle generation unit can generate optimal subtitles by referring to past subtitle data during subtitle generation. For example, the subtitle generation unit can refer to past subtitle data and generate optimal subtitles based on fonts and styles previously used by the user. For example, it can generate related subtitles based on the themes of subtitles previously created by the user. The subtitle generation unit can also generate optimal subtitles based on colors and designs previously used by the user. For example, it can generate optimal subtitles based on colors and designs previously used by the user. This allows for the generation of optimal subtitles based on past data. Some or all of the above-described processes in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input past subtitle data into AI, and the AI ​​can generate optimal subtitles.

[0059] The subtitle generation unit can customize the subtitle style based on the user's preferences when generating subtitles. For example, the subtitle generation unit can customize subtitles based on a casual style selected by the user. For example, it can customize subtitles based on a formal style selected by the user. The subtitle generation unit can also customize subtitles based on a humorous style selected by the user. For example, it can customize subtitles based on a humorous style selected by the user. This allows the subtitle style to be customized based on the user's preferences. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input the user's preferences into AI, and the AI ​​can customize the subtitle style.

[0060] The subtitle generation unit can incorporate region-specific expressions by considering the user's geographical location information during subtitle generation. For example, if the user is in Japan, the subtitle generation unit can incorporate expressions that are appropriate for Japanese culture and customs. For example, if the user is in the United States, it can incorporate expressions that are appropriate for American culture and customs. Furthermore, if the user is in France, the subtitle generation unit can incorporate expressions that are appropriate for French culture and customs. For example, if the user is in France, it can incorporate expressions that are appropriate for French culture and customs. This makes it possible to generate subtitles that incorporate region-specific expressions. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input the user's geographical location information into the AI, and the AI ​​can generate subtitles that incorporate region-specific expressions.

[0061] The subtitle generation unit can analyze the user's social media activity and suggest relevant subtitles when generating subtitles. For example, the subtitle generation unit can suggest relevant subtitles based on phrases and expressions that the user frequently uses on social media. For example, it can suggest subtitles based on the style of influencers that the user follows on social media. The subtitle generation unit can also suggest relevant subtitles based on the content that the user frequently posts on social media. For example, it can suggest relevant subtitles based on the content that the user frequently posts on social media. In this way, relevant subtitles can be suggested based on social media activity. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input the user's social media activity into AI, and the AI ​​can suggest relevant subtitles.

[0062] The project management department can propose the optimal project management method by referring to past project data during project management. For example, the project management department can refer to past project data and propose the optimal method based on the methods used in projects that have been successful in the past. For example, it can suggest that the user avoid the methods used in projects that have failed in the past. The project management department can also propose the optimal method based on the tools and resources that the user has used in the past. For example, it can propose the optimal method based on the tools and resources that the user has used in the past. This allows the project management department to propose the optimal method based on past data. Some or all of the above processes in the project management department may be performed using AI, for example, or not using AI. For example, the project management department can input past project data into AI, and the AI ​​can propose the optimal method.

[0063] The project management department can propose the optimal project management method while considering the user's geographical location. For example, if the user is in Japan, the project management department can propose a method that conforms to Japanese business practices. For example, if the user is in the United States, it can propose a method that conforms to American business practices. Furthermore, if the user is in France, the project management department can propose a method that conforms to French business practices. For example, if the user is in France, it can propose a method that conforms to French business practices. This allows for the proposal of the optimal project management method that takes geographical location into account. Some or all of the above processing in the project management department may be performed using AI, or not. For example, the project management department can input the user's geographical location information into AI, and the AI ​​can propose the optimal project management method.

[0064] The posting support unit can suggest the optimal posting method by referring to past posting data when providing posting support. For example, the posting support unit can refer to past posting data and suggest the optimal posting method based on posting methods that the user has successfully used in the past. For example, it can suggest that the user avoid posting methods that have failed in the past. The posting support unit can also suggest the optimal posting method based on hashtags and keywords that the user has used in the past. For example, it can suggest the optimal posting method based on hashtags and keywords that the user has used in the past. This allows the posting support unit to suggest the optimal posting method based on past data. Some or all of the above processing in the posting support unit may be performed using AI, for example, or without AI. For example, the posting support unit can input past posting data into AI, and the AI ​​can suggest the optimal posting method.

[0065] The posting support unit can suggest the optimal posting method when providing posting support, taking into account the user's geographical location. For example, if the user is in Japan, the posting support unit can suggest a posting method that suits Japanese culture and customs. For example, if the user is in the United States, it can suggest a posting method that suits American culture and customs. Furthermore, if the user is in France, the posting support unit can suggest a posting method that suits French culture and customs. For example, if the user is in France, it can suggest a posting method that suits French culture and customs. This allows the system to suggest the optimal posting method that takes geographical location into account. Some or all of the above processing in the posting support unit may be performed using AI, or not. For example, the posting support unit can input the user's geographical location information into the AI, which can then suggest the optimal posting method.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The AITuber creation platform can analyze a user's past avatar creation history and suggest the optimal avatar generation method. For example, it can analyze past avatar creation history and suggest avatars with similar styles based on the styles of avatars the user has created in the past. It can also suggest the optimal avatar color palette based on the colors and designs the user has chosen in the past. Furthermore, it can suggest the optimal accessories based on the accessories the user has used in the past. In this way, it can suggest the optimal avatar generation method based on past history. Some or all of the above processing in the avatar generation unit may be performed using AI or not. For example, the avatar generation unit can input past avatar creation history into AI, and the AI ​​can suggest the optimal avatar generation method.

[0068] The AITuber creation platform can incorporate region-specific elements by considering the user's geographical location. For example, if the user is in Japan, the avatar can incorporate traditional Japanese clothing and accessories. If the user is in the United States, the avatar can incorporate casual American-style clothing. If the user is in India, the avatar can incorporate a sari and traditional Indian accessories. This allows for the creation of avatars that incorporate region-specific elements. Some or all of the above processing in the avatar generation unit may be performed using AI or not. For example, the avatar generation unit can input the user's geographical location information into the AI, which can then generate an avatar that incorporates region-specific elements.

[0069] The AITuber creation platform can analyze a user's social media activity and suggest relevant avatars. For example, it can suggest avatar expressions and poses based on emojis and stickers that the user frequently uses on social media. It can also suggest avatar styles based on the content that the user frequently posts on social media. Furthermore, it can suggest avatar designs based on the styles of influencers that the user follows on social media. In this way, it can suggest relevant avatars based on social media activity. Some or all of the above processing in the avatar generation unit may be performed using AI or not. For example, the avatar generation unit can input the user's social media activity into AI, and the AI ​​can suggest relevant avatars.

[0070] The AITuber creation platform can incorporate region-specific expressions by considering the user's geographical location. For example, if the user is in Japan, the script can incorporate expressions that are appropriate for Japanese culture and customs. If the user is in the United States, the script can incorporate expressions that are appropriate for American culture and customs. Similarly, if the user is in France, the script can incorporate expressions that are appropriate for French culture and customs. This allows for the generation of scripts that incorporate region-specific expressions. Some or all of the above processing in the script generation unit may be performed using AI or not. For example, the script generation unit can input the user's geographical location information into the AI, which can then generate a script that incorporates region-specific expressions.

[0071] The AITuber creation platform can analyze a user's social media activity and suggest relevant scripts. For example, it can suggest relevant scripts based on the content a user frequently posts on social media. It can also suggest scripts based on the style of influencers a user follows on social media. Furthermore, it can suggest scripts based on phrases and expressions a user frequently uses on social media. This allows the platform to suggest relevant scripts based on social media activity. Some or all of the above processing in the script generation unit may be performed using AI or not. For example, the script generation unit can input the user's social media activity into the AI, which can then suggest relevant scripts.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The avatar generation unit generates avatars using 3D or Live2D. For example, it can generate avatars based on photos uploaded by the user using image generation AI. It can also customize avatars based on styles and characteristics chosen by the user. Step 2: The script generation unit generates a script for the content based on the avatar generated by the avatar generation unit. For example, a script can be generated and customized based on user input and selected topics using an LLM (Large-Scale Language Model). Step 3: The speech synthesis unit synthesizes speech based on the script generated by the script generation unit. For example, the speech can be customized based on the tone and accent, language and dialect selected by the user. Step 4: The motion synchronization unit synchronizes the avatar's movements based on the speech synthesized by the speech synthesis unit. For example, it can synchronize the avatar's mouth movements with speech, or customize the avatar's movements based on gestures and facial expressions selected by the user. Step 5: The subtitle generation unit generates subtitles based on the audio synthesized by the speech synthesis unit. For example, it can automatically generate subtitles based on the generated audio, and the subtitles can be customized based on the font, style, language, and format selected by the user.

[0074] (Example of form 2) The AITuber creation platform according to an embodiment of the present invention is a system that allows anyone to easily create an AI-based AITuber, or AITuber for short, without any programming skills. This system allows users to access an interface for creating an AITuber through a social networking app and sequentially perform common steps such as creating 3D or Live2D avatars, writing content scripts, synthesizing speech, synchronizing motion to match the speech, and adding subtitles. All of these steps are supported by AI, allowing users to operate intuitively. For example, when creating a 3D or Live2D avatar, the user can intuitively generate an avatar using an image generation AI. When the user uploads a photo, the AI ​​generates an avatar based on that photo. Next, the user creates a content script. Here, an LLM (Large-Scale Language Model) is used to generate AITuber speech based on text entered by the user. For example, if the user enters "Today I will introduce a new game," the AI ​​generates a script based on that statement. Furthermore, speech synthesis is performed. The AI ​​synthesizes speech based on the generated script. For example, the AI ​​generates speech to match the tone and accent of the voice chosen by the user. Finally, motion synchronization is performed to match the speech. The AI ​​synchronizes the avatar's movements based on the generated audio. For example, it makes the avatar's mouth move in accordance with the speech. Finally, it adds subtitles. The AI ​​automatically generates subtitles based on the generated audio and adds them to the video. This allows viewers to understand the content not only through audio but also through subtitles. In this way, anyone can easily create an AITuber without any programming skills. This mechanism is expected to lead to the rapid expansion of the domestic AITuber market, and the increase in creative content will spread new forms of entertainment. As a result, the AITuber creation platform makes it easy for anyone to create an AITuber, even without programming skills.

[0075] The AITuber creation platform according to this embodiment comprises an avatar generation unit, a script generation unit, a speech synthesis unit, a motion synchronization unit, and a subtitle generation unit. The avatar generation unit generates avatars using 3D or Live2D. The avatar generation unit generates avatars using, for example, an image generation AI. For example, if a user uploads their own photo, the AI ​​can generate an avatar based on that photo. The avatar generation unit can also customize avatars based on styles and characteristics chosen by the user. For example, it can generate avatars based on hairstyles and clothing chosen by the user. The script generation unit generates a script for content based on the avatar generated by the avatar generation unit. The script generation unit generates scripts using, for example, an LLM (Large-Scale Language Model). For example, if a user inputs "Today I will introduce a new game," the AI ​​can generate a script based on that statement. The script generation unit can also customize scripts based on topics and themes chosen by the user. For example, it can add relevant information to the script based on the theme chosen by the user. The speech synthesis unit synthesizes speech based on the script generated by the script generation unit. The speech synthesis unit synthesizes speech according to the tone and accent of the voice selected by the user, for example. For example, it can generate speech based on the characteristics of the voice selected by the user. The speech synthesis unit can also customize speech based on the language or dialect selected by the user, for example. For example, it can generate speech based on the language selected by the user. The motion synchronization unit synchronizes the avatar's movements based on the speech synthesized by the speech synthesis unit. For example, the motion synchronization unit synchronizes the avatar's mouth movements with the speech, for example. For example, it can customize the avatar's movements based on movements selected by the user. The motion synchronization unit can also synchronize the avatar's movements based on gestures or facial expressions selected by the user, for example. For example, it can generate avatar movements based on gestures selected by the user. The subtitle generation unit generates subtitles based on the speech synthesized by the speech synthesis unit. For example, the subtitle generation unit automatically generates subtitles based on the generated speech and adds them to the video.For example, subtitles can be customized based on the font and style selected by the user. The subtitle generation unit can also generate subtitles based on the language and format selected by the user. For instance, subtitles can be generated based on the language selected by the user. This allows anyone to easily create an AITuber using the AITuber creation platform according to this embodiment, even without programming skills.

[0076] The avatar generation unit generates avatars using 3D and Live2D methods. For example, it uses image generation AI to create avatars. Specifically, when a user uploads a photo, the AI ​​can generate an avatar based on that photo. This AI uses deep learning technology to extract facial features from the photo and convert them into a 3D or Live2D model. Furthermore, the avatar generation unit can customize avatars based on styles and features chosen by the user. For example, it can generate avatars based on the user's chosen hairstyle and clothing. The user selects hair color, eye shape, clothing type, etc., through the interface, and the AI ​​generates the avatar in real time based on these selections. This allows users to easily create avatars tailored to their preferences. The avatar generation unit can also add backgrounds and accessories chosen by the user, allowing for the creation of more unique avatars. For example, it can adjust the avatar's shadows and light reflections to match the background chosen by the user. This makes the avatar more realistic and appealing. Additionally, the avatar generation unit can save the generated avatars and allow for later re-editing. This allows users to customize their avatars multiple times and use them in different content.

[0077] The script generation unit generates content scripts based on avatars generated by the avatar generation unit. The script generation unit uses, for example, a Large-Scale Language Model (LLM) to generate scripts. Specifically, if a user inputs "Today I'll introduce a new game," the AI ​​can generate a script based on that statement. This LLM utilizes natural language processing technology to understand user input and generate an appropriate script accordingly. For example, the script can be customized based on a user-selected topic or theme. Relevant information can be added to the script based on the user's chosen theme. For instance, if a user selects "Review of a new game" as their theme, the AI ​​will generate a detailed script including the game's features, gameplay, and ratings. Furthermore, the script generation unit can learn from the user's past inputs and preferences to provide more personalized scripts. This allows users to create consistent content. Additionally, the script generation unit provides an interface for editing the generated scripts, allowing users to modify them in their own words. This enables users to create content tailored to their own style and tone, based on the AI-generated script.

[0078] The speech synthesis unit synthesizes speech based on the script generated by the script generation unit. The speech synthesis unit can, for example, synthesize speech to match the tone and accent of the user's voice. Specifically, it can generate speech based on the voice characteristics selected by the user. This speech synthesis technology uses a deep learning model to generate natural-sounding speech from text. For example, it can adjust the pitch, speed, and intonation of the speech based on the tone and accent of the user's voice. The speech synthesis unit can also customize the speech based on the language or dialect selected by the user. For example, it can generate speech based on the language selected by the user. This allows users to easily create speech that is best suited to their content. Furthermore, the speech synthesis unit also provides a real-time preview function of the generated speech, allowing users to check the quality of the speech and adjust it as needed. This enables users to easily create high-quality speech and enhance the appeal of their content.

[0079] The motion synchronization unit synchronizes the avatar's movements based on the speech synthesized by the speech synthesis unit. For example, the motion synchronization unit synchronizes the avatar's mouth movements to match the user's speech. Specifically, it analyzes the waveform and pitch of the speech and adjusts the avatar's mouth movements in real time based on that analysis. It can also customize the avatar's movements based on movements selected by the user. For example, it can synchronize the avatar's movements based on gestures and facial expressions selected by the user. This allows the avatar to move more naturally and realistically. Furthermore, the motion synchronization unit can adjust the avatar's movements to match the background and situation selected by the user. For example, it can adjust the avatar's movements and position to match the background selected by the user. This allows the avatar to move more consistently, improving the quality of the content. In addition, the motion synchronization unit can also capture the user's own movements and reflect them in the avatar. This allows users to reflect their own movements in the avatar and create more unique content.

[0080] The subtitle generation unit generates subtitles based on the audio synthesized by the speech synthesis unit. For example, the subtitle generation unit automatically generates subtitles based on the generated audio and adds them to the video. Specifically, it uses speech recognition technology to convert audio into text and displays it as subtitles. For example, users can customize subtitles based on their chosen font and style. Users can select font type, size, color, etc., through the interface and generate subtitles accordingly. The subtitle generation unit can also generate subtitles based on the user's chosen language and format. For example, it can generate subtitles based on the user's chosen language. This allows users to easily create multilingual content. Furthermore, the subtitle generation unit provides a real-time preview function for the generated subtitles, allowing users to check the quality of the subtitles and adjust them as needed. This enables users to easily create high-quality subtitles and improve the content viewing experience. The subtitle generation unit also has a function to automatically synchronize subtitles with the timing of the audio, allowing users to generate accurate subtitles without any effort.

[0081] The project management department performs project management. For example, the project management department handles tasks, progress tracking, and resource allocation. For instance, the project management department can monitor project progress in real time and track task progress. Furthermore, the project management department can optimize resource allocation and support the efficient progress of the project. For example, the project management department can dynamically allocate resources and adjust task priorities according to project progress. This allows for efficient management of project progress. Some or all of the above processes performed by the project management department may be carried out using AI, or not. For example, the project management department can input project progress into AI, which can then suggest optimal resource allocation and task priorities.

[0082] The posting support department provides posting support. For example, the posting support department handles posting scheduling and content optimization. For example, the posting support department can optimize posting timing and suggest the optimal posting time to attract viewers' attention. The posting support department can also optimize posting content and suggest effective content to attract viewers' attention. For example, the posting support department can suggest keywords and hashtags to attract viewers' attention and optimize posting content. This allows for efficient posting support. Some or all of the above processes in the posting support department may be performed using AI, or not. For example, the posting support department can input the posting schedule into AI, which can then suggest the optimal posting time and content.

[0083] The avatar generation unit can generate avatars using image generation AI. For example, the avatar generation unit uses image generation AI such as GAN (Generative Opposite Network) or VAE (Variational Autoencoder) to generate avatars. For instance, if a user uploads a photo, the AI ​​can generate an avatar based on that photo. Furthermore, the avatar generation unit can customize avatars based on styles and characteristics chosen by the user. For example, it can generate avatars based on hairstyles and clothing chosen by the user. This allows for intuitive avatar generation using image generation AI. Some or all of the above-described processes in the avatar generation unit may be performed using AI, or they may not. For example, the avatar generation unit can input a user's photo into the AI, which can then generate an avatar.

[0084] The script generation unit can generate scripts using LLM. For example, if a user inputs "Today I will introduce a new game," the AI ​​can generate a script based on that statement. The script generation unit can also customize scripts based on topics or themes selected by the user. For example, it can add relevant information to the script based on the theme selected by the user. This allows for efficient script generation using LLM. Some or all of the above-described processes in the script generation unit may be performed using AI, or not. For example, the script generation unit can input user input into the AI, which can then generate a script.

[0085] The speech synthesis unit can synthesize speech according to the tone and accent of the voice selected by the user. The speech synthesis unit synthesizes speech using, for example, a speech synthesis engine. For example, it can generate speech based on the voice characteristics selected by the user. The speech synthesis unit can also customize speech based on the language or dialect selected by the user. For example, it can generate speech based on the language selected by the user. This allows for the synthesis of speech tailored to the user's preferences. Some or all of the above-described processes in the speech synthesis unit may be performed using, for example, AI, or without AI. For example, the speech synthesis unit can input the voice characteristics selected by the user into the AI, and the AI ​​can generate speech.

[0086] The motion synchronization unit can synchronize the avatar's mouth movements with the speech. For example, the motion synchronization unit can synchronize the avatar's mouth movements with speech using speech recognition technology. For example, the avatar's movements can be customized based on movements selected by the user. The motion synchronization unit can also synchronize the avatar's movements based on gestures and facial expressions selected by the user. For example, it can generate avatar movements based on gestures selected by the user. This enables natural avatar movements that match the speech. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input speech data into AI, and the AI ​​can generate avatar movements.

[0087] The subtitle generation unit can automatically generate subtitles based on the generated audio and add them to the video. For example, the subtitle generation unit can automatically generate subtitles based on audio generated using speech recognition technology and add them to the video. For example, subtitles can be customized based on fonts and styles selected by the user. The subtitle generation unit can also generate subtitles based on languages ​​and formats selected by the user. For example, subtitles can be generated based on languages ​​selected by the user. This allows for automatic subtitle generation, making it easier for viewers to understand the content. Some or all of the above-described processes in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input audio data into AI, and the AI ​​can generate subtitles.

[0088] The avatar generation unit can estimate the user's emotions and automatically adjust the avatar's facial expression based on the estimated emotions. For example, the avatar generation unit estimates the user's emotions using facial recognition technology and automatically adjusts the avatar's facial expression based on the estimated emotions. For example, if the user is happy, the avatar's facial expression is automatically adjusted to a smile. If the user is sad, the avatar's facial expression can also be automatically adjusted to a sad expression. If the user is surprised, the avatar's facial expression can also be automatically adjusted to a surprised expression. This allows the avatar's facial expression to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input user facial expression data into an AI, and the AI ​​can generate the avatar's facial expression.

[0089] The avatar generation unit can analyze the user's past avatar creation history and propose the optimal avatar generation method. For example, the avatar generation unit can analyze the past avatar creation history and propose avatars with similar styles based on the styles of avatars the user has created in the past. For example, it can propose the optimal avatar color palette based on the colors and designs the user has selected in the past. The avatar generation unit can also propose the optimal accessories based on the accessories the user has used in the past. For example, it can propose the optimal accessories based on the accessories the user has used in the past. This allows the system to propose the optimal avatar generation method based on past history. Some or all of the above processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the past avatar creation history into AI, and the AI ​​can propose the optimal avatar generation method.

[0090] The avatar generation unit can automatically select the avatar's clothing and accessories based on the user's preferences during avatar generation. For example, the avatar generation unit can automatically select the avatar's clothing based on a casual style chosen by the user. For example, it can automatically select the avatar's clothing based on a formal style chosen by the user. The avatar generation unit can also automatically select the avatar's clothing based on a sporty style chosen by the user. For example, it can automatically select the avatar's clothing based on a sporty style chosen by the user. This allows for the automatic selection of the avatar's clothing and accessories based on the user's preferences. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's preferences into AI, and the AI ​​can select the avatar's clothing and accessories.

[0091] The avatar generation unit can estimate the user's emotions and automatically adjust the avatar's pose based on the estimated emotions. For example, the avatar generation unit estimates the user's emotions using facial recognition technology and automatically adjusts the avatar's pose based on the estimated emotions. For example, if the user is relaxed, the avatar's pose is automatically adjusted to a relaxed posture. If the user is tense, the avatar's pose can be automatically adjusted to a tense posture. If the user is having fun, the avatar's pose can be automatically adjusted to a cheerful posture. This allows the avatar's pose to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the avatar generation unit may be performed using AI, or not using AI. For example, the avatar generation unit can input the user's facial expression data into the AI, and the AI ​​can generate the avatar's pose.

[0092] The avatar generation unit can incorporate region-specific elements by considering the user's geographical location information during avatar generation. For example, if the user is in Japan, the avatar generation unit can incorporate Japanese clothing and traditional Japanese accessories into the avatar. For example, if the user is in America, the avatar generation unit can incorporate casual American-style clothing into the avatar. Furthermore, if the user is in India, the avatar generation unit can incorporate a sari and traditional Indian accessories into the avatar. This allows for the generation of avatars that incorporate region-specific elements. Some or all of the above-described processes in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's geographical location information into AI, and the AI ​​can generate an avatar that incorporates region-specific elements.

[0093] The avatar generation unit can analyze the user's social media activity and suggest relevant avatars during avatar generation. For example, the avatar generation unit can suggest avatar expressions and poses based on emojis and stamps that the user frequently uses on social media. For example, it can suggest avatar styles based on the content that the user frequently posts on social media. The avatar generation unit can also suggest avatar designs based on the styles of influencers that the user follows on social media. For example, it can suggest avatar designs based on the styles of influencers that the user follows on social media. This allows the avatar generation unit to suggest relevant avatars based on social media activity. Some or all of the above processing in the avatar generation unit may be performed using AI, for example, or without AI. For example, the avatar generation unit can input the user's social media activity into AI, which can then suggest relevant avatars.

[0094] The script generation unit can estimate the user's emotions and adjust the tone of the script based on the estimated emotions. For example, the script generation unit can estimate the user's emotions using emotion analysis technology and adjust the tone of the script based on the estimated emotions. For example, if the user is relaxed, the tone of the script can be softened. If the user is tense, the tone of the script can be adjusted to be calming. If the user is enjoying themselves, the tone of the script can be brightened. This allows the tone of the script to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input user emotion data into the AI, and the AI ​​can adjust the tone of the script.

[0095] The script generation unit can generate the optimal script by referring to past script data during script generation. For example, the script generation unit can refer to past script data and generate a script with a similar style based on the style of scripts previously created by the user. For example, it can generate the optimal script based on phrases and expressions previously used by the user. The script generation unit can also generate related scripts based on the themes of scripts previously created by the user. For example, it can generate related scripts based on the themes of scripts previously created by the user. This allows for the generation of the optimal script based on past data. Some or all of the above processes in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input past script data into AI, and the AI ​​can generate the optimal script.

[0096] The script generation unit can customize the style of the script based on the user's preferences during script generation. For example, the script generation unit can customize the script based on a casual style chosen by the user. For example, it can customize the script based on a formal style chosen by the user. The script generation unit can also customize the script based on a humorous style chosen by the user. For example, it can customize the script based on a humorous style chosen by the user. This allows the script style to be customized based on the user's preferences. Some or all of the above processing in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input the user's preferences into AI, and the AI ​​can customize the style of the script.

[0097] The script generation unit can estimate the user's emotions and adjust the length of the script based on the estimated emotions. For example, the script generation unit can estimate the user's emotions using emotion analysis technology and adjust the length of the script based on the estimated emotions. For example, if the user is in a hurry, it can generate a short script. If the user is relaxed, it can also generate a longer script that includes detailed explanations. If the user is having fun, it can also generate a highly entertaining script. This allows the length of the script to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the script generation unit may be performed using AI, for example, or not using AI. For example, the script generation unit can input user emotion data into the AI, and the AI ​​can adjust the length of the script.

[0098] The script generation unit can incorporate region-specific expressions by considering the user's geographical location information during script generation. For example, if the user is in Japan, the script generation unit can incorporate expressions that are appropriate for Japanese culture and customs. For example, if the user is in the United States, it can incorporate expressions that are appropriate for American culture and customs. Furthermore, if the user is in France, the script generation unit can incorporate expressions that are appropriate for French culture and customs. For example, if the user is in France, it can incorporate expressions that are appropriate for French culture and customs. This makes it possible to generate scripts that incorporate region-specific expressions. Some or all of the above processing in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input the user's geographical location information into the AI, and the AI ​​can generate a script that incorporates region-specific expressions.

[0099] The script generation unit can analyze the user's social media activity and suggest relevant scripts when generating a script. For example, the script generation unit can suggest relevant scripts based on the content the user frequently posts on social media. For example, it can suggest scripts based on the style of influencers the user follows on social media. The script generation unit can also suggest scripts based on phrases and expressions the user frequently uses on social media. For example, it can suggest scripts based on phrases and expressions the user frequently uses on social media. This allows the script generation unit to suggest relevant scripts based on social media activity. Some or all of the above processing in the script generation unit may be performed using AI, for example, or without AI. For example, the script generation unit can input the user's social media activity into AI, which can then suggest relevant scripts.

[0100] The speech synthesis unit can estimate the user's emotions and adjust the tone of the voice based on the estimated emotions. For example, the speech synthesis unit can estimate the user's emotions using emotion analysis technology and adjust the tone of the voice based on the estimated emotions. For example, if the user is relaxed, it can generate a soft tone of voice. If the user is tense, it can generate a calm tone of voice. If the user is enjoying themselves, it can generate a bright tone of voice. This allows the tone of voice to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input user emotion data into the AI, and the AI ​​can adjust the tone of the voice.

[0101] The speech synthesis unit can generate the optimal speech by referring to past speech data during speech synthesis. For example, the speech synthesis unit can refer to past speech data and generate the optimal speech based on the tone and accent of speech previously selected by the user. For example, it can generate the optimal speech based on phrases and expressions previously used by the user. The speech synthesis unit can also generate speech with a similar style based on speech styles previously created by the user. For example, it can generate speech with a similar style based on speech styles previously created by the user. This allows for the generation of the optimal speech based on past data. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input past speech data into AI, and the AI ​​can generate the optimal speech.

[0102] The speech synthesis unit can customize the accent of the voice based on the user's preferences during speech synthesis. For example, the speech synthesis unit can customize the voice based on the accent of a region selected by the user. For example, it can customize the voice based on the voice of a character selected by the user. The speech synthesis unit can also customize the voice based on the emotional tone selected by the user. For example, it can customize the voice based on the emotional tone selected by the user. This allows the accent of the voice to be customized according to the user's preferences. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input the user's preferences into the AI, and the AI ​​can customize the accent of the voice.

[0103] The speech synthesis unit can estimate the user's emotions and adjust the speech speed based on the estimated emotions. For example, the speech synthesis unit can estimate the user's emotions using emotion analysis technology and adjust the speech speed based on the estimated emotions. For example, if the user is in a hurry, it can generate speech at a fast speed. If the user is relaxed, it can generate speech at a slow speed. If the user is enjoying themselves, it can generate speech at a moderate speed. This allows for automatic adjustment of the speech speed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input user emotion data into the AI, and the AI ​​can adjust the speech speed.

[0104] The speech synthesis unit can incorporate regional accents by considering the user's geographical location information during speech synthesis. For example, if the user is in the UK, the speech synthesis unit can incorporate a British English accent. For example, if the user is in the US, it can incorporate an American English accent. The speech synthesis unit can also incorporate an Australian English accent if the user is in Australia. For example, if the user is in Australia, it can incorporate an Australian English accent. This makes it possible to generate speech that incorporates regional accents. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input the user's geographical location information into the AI, and the AI ​​can generate speech that incorporates regional accents.

[0105] The speech synthesis unit can analyze the user's social media activity during speech synthesis and suggest relevant audio. For example, the speech synthesis unit can suggest relevant audio based on phrases and expressions that the user frequently uses on social media. For example, it can suggest audio based on the voice style of influencers that the user follows on social media. The speech synthesis unit can also suggest relevant audio based on the content that the user frequently posts on social media. For example, it can suggest relevant audio based on the content that the user frequently posts on social media. In this way, relevant audio can be suggested based on social media activity. Some or all of the above processing in the speech synthesis unit may be performed using AI, for example, or without AI. For example, the speech synthesis unit can input the user's social media activity into AI, and the AI ​​can suggest relevant audio.

[0106] The motion synchronization unit can estimate the user's emotions and adjust the avatar's movements based on the estimated emotions. For example, the motion synchronization unit can estimate the user's emotions using emotion analysis technology and adjust the avatar's movements based on the estimated emotions. For example, if the user is relaxed, the avatar's movements can be adjusted to be more relaxed. If the user is tense, the avatar's movements can be adjusted to be more subdued. If the user is having fun, the avatar's movements can be adjusted to be more lively. This allows the avatar's movements to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input user emotion data into the AI, and the AI ​​can adjust the avatar's movements.

[0107] The motion synchronization unit can generate optimal movements by referring to past motion data during motion synchronization. For example, the motion synchronization unit can refer to past motion data and generate similar movements based on motion data previously used by the user. For example, it can generate optimal movements based on movements that the user has preferred in the past. The motion synchronization unit can also analyze motion data previously used by the user and generate the most natural movements. For example, it can analyze motion data previously used by the user and generate the most natural movements. This allows for the generation of optimal movements based on past data. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input past motion data into AI, and the AI ​​can generate optimal movements.

[0108] The motion synchronization unit can customize the avatar's movements based on the user's preferences during motion synchronization. For example, the motion synchronization unit can customize the avatar's movements based on the dance style selected by the user. For example, it can customize the avatar's movements based on the gestures selected by the user. The motion synchronization unit can also customize the avatar's movements based on the expression method selected by the user. For example, it can customize the avatar's movements based on the expression method selected by the user. This allows the avatar's movements to be customized based on the user's preferences. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input the user's preferences into the AI, and the AI ​​can customize the avatar's movements.

[0109] The motion synchronization unit can estimate the user's emotions and adjust the avatar's movement speed based on the estimated emotions. For example, the motion synchronization unit can estimate the user's emotions using emotion analysis technology and adjust the avatar's movement speed based on the estimated emotions. For example, if the user is in a hurry, the avatar's movements can be adjusted to be faster. If the user is relaxed, the avatar's movements can be adjusted to be slower. If the user is having fun, the avatar's movements can be adjusted to a moderate speed. This allows the avatar's movement speed to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the motion synchronization unit may be performed using AI, or not using AI. For example, the motion synchronization unit can input user emotion data into the AI, and the AI ​​can adjust the avatar's movement speed.

[0110] The motion synchronization unit can incorporate region-specific movements by considering the user's geographical location information during motion synchronization. For example, if the user is in Japan, the motion synchronization unit can incorporate traditional Japanese movements into the avatar. For example, if the user is in America, it can incorporate casual American movements into the avatar. Furthermore, if the user is in India, the motion synchronization unit can incorporate traditional Indian dance movements into the avatar. For example, if the user is in India, it can incorporate traditional Indian dance movements into the avatar. This makes it possible to generate avatar movements that incorporate region-specific movements. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input the user's geographical location information into AI, and the AI ​​can generate avatar movements that incorporate region-specific movements.

[0111] The motion synchronization unit can analyze the user's social media activity during motion synchronization and suggest relevant movements. For example, the motion synchronization unit can suggest avatar movements based on gestures the user frequently uses on social media. For example, it can suggest avatar movements based on the movements of influencers the user follows on social media. The motion synchronization unit can also suggest relevant movements based on the content the user frequently posts on social media. For example, it can suggest relevant movements based on the content the user frequently posts on social media. This allows for the suggestion of relevant movements based on social media activity. Some or all of the above processing in the motion synchronization unit may be performed using AI, for example, or without AI. For example, the motion synchronization unit can input the user's social media activity into AI, which can then suggest relevant movements.

[0112] The subtitle generation unit can estimate the user's emotions and adjust the subtitle display method based on the estimated emotions. For example, the subtitle generation unit can estimate the user's emotions using emotion analysis technology and adjust the subtitle display method based on the estimated emotions. For example, if the user is relaxed, the subtitles can be displayed in a soft font. If the user is tense, the subtitles can be displayed in a highly legible font. If the user is enjoying themselves, the subtitles can be displayed in a colorful font. This allows the subtitle display method to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input user emotion data into the AI, and the AI ​​can adjust the subtitle display method.

[0113] The subtitle generation unit can generate optimal subtitles by referring to past subtitle data during subtitle generation. For example, the subtitle generation unit can refer to past subtitle data and generate optimal subtitles based on fonts and styles previously used by the user. For example, it can generate related subtitles based on the themes of subtitles previously created by the user. The subtitle generation unit can also generate optimal subtitles based on colors and designs previously used by the user. For example, it can generate optimal subtitles based on colors and designs previously used by the user. This allows for the generation of optimal subtitles based on past data. Some or all of the above-described processes in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input past subtitle data into AI, and the AI ​​can generate optimal subtitles.

[0114] The subtitle generation unit can customize the subtitle style based on the user's preferences when generating subtitles. For example, the subtitle generation unit can customize subtitles based on a casual style selected by the user. For example, it can customize subtitles based on a formal style selected by the user. The subtitle generation unit can also customize subtitles based on a humorous style selected by the user. For example, it can customize subtitles based on a humorous style selected by the user. This allows the subtitle style to be customized based on the user's preferences. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input the user's preferences into AI, and the AI ​​can customize the subtitle style.

[0115] The subtitle generation unit can estimate the user's emotions and adjust the subtitle display speed based on the estimated emotions. For example, the subtitle generation unit can estimate the user's emotions using emotion analysis technology and adjust the subtitle display speed based on the estimated emotions. For example, if the user is in a hurry, the subtitles can be displayed at a fast speed. If the user is relaxed, the subtitles can be displayed at a slow speed. If the user is enjoying themselves, the subtitles can be displayed at a moderate speed. This allows the subtitle display speed to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input user emotion data into the AI, and the AI ​​can adjust the subtitle display speed.

[0116] The subtitle generation unit can incorporate region-specific expressions by considering the user's geographical location information during subtitle generation. For example, if the user is in Japan, the subtitle generation unit can incorporate expressions that are appropriate for Japanese culture and customs. For example, if the user is in the United States, it can incorporate expressions that are appropriate for American culture and customs. Furthermore, if the user is in France, the subtitle generation unit can incorporate expressions that are appropriate for French culture and customs. For example, if the user is in France, it can incorporate expressions that are appropriate for French culture and customs. This makes it possible to generate subtitles that incorporate region-specific expressions. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input the user's geographical location information into the AI, and the AI ​​can generate subtitles that incorporate region-specific expressions.

[0117] The subtitle generation unit can analyze the user's social media activity and suggest relevant subtitles when generating subtitles. For example, the subtitle generation unit can suggest relevant subtitles based on phrases and expressions that the user frequently uses on social media. For example, it can suggest subtitles based on the style of influencers that the user follows on social media. The subtitle generation unit can also suggest relevant subtitles based on the content that the user frequently posts on social media. For example, it can suggest relevant subtitles based on the content that the user frequently posts on social media. In this way, relevant subtitles can be suggested based on social media activity. Some or all of the above processing in the subtitle generation unit may be performed using AI, for example, or without AI. For example, the subtitle generation unit can input the user's social media activity into AI, and the AI ​​can suggest relevant subtitles.

[0118] The project management department can estimate the user's emotions and adjust the project's progress based on those emotions. For example, the project management department can use emotion analysis technology to estimate the user's emotions and adjust the project's progress based on those emotions. For example, if the user is stressed, the project's progress can be slowed down. If the user is relaxed, the project can proceed at its normal pace. If the user is in a hurry, the project can be accelerated. This allows for automatic adjustment of the project's progress according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the project management department may be performed using AI or not. For example, the project management department can input user emotion data into an AI, which can then adjust the project's progress.

[0119] The project management department can propose the optimal project management method by referring to past project data during project management. For example, the project management department can refer to past project data and propose the optimal method based on the methods used in projects that have been successful in the past. For example, it can suggest that the user avoid the methods used in projects that have failed in the past. The project management department can also propose the optimal method based on the tools and resources that the user has used in the past. For example, it can propose the optimal method based on the tools and resources that the user has used in the past. This allows the project management department to propose the optimal method based on past data. Some or all of the above processes in the project management department may be performed using AI, for example, or not using AI. For example, the project management department can input past project data into AI, and the AI ​​can propose the optimal method.

[0120] The project management department can estimate user emotions and determine project priorities based on those estimated emotions. For example, the project management department can use emotion analysis technology to estimate user emotions and determine project priorities based on those estimated emotions. For example, if a user is stressed, low-priority tasks can be prioritized. Conversely, if a user is relaxed, high-priority tasks can be prioritized. Also, if a user is in a hurry, tasks that can be completed quickly can be prioritized. This allows for the automatic determination of project priorities according to user emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the project management department may be performed using AI or not. For example, the project management department can input user emotion data into an AI, which can then determine project priorities.

[0121] The project management department can propose the optimal project management method while considering the user's geographical location. For example, if the user is in Japan, the project management department can propose a method that conforms to Japanese business practices. For example, if the user is in the United States, it can propose a method that conforms to American business practices. Furthermore, if the user is in France, the project management department can propose a method that conforms to French business practices. For example, if the user is in France, it can propose a method that conforms to French business practices. This allows for the proposal of the optimal project management method that takes geographical location into account. Some or all of the above processing in the project management department may be performed using AI, or not. For example, the project management department can input the user's geographical location information into AI, and the AI ​​can propose the optimal project management method.

[0122] The posting support unit can estimate the user's emotions and adjust the posting timing based on the estimated emotions. For example, the posting support unit can estimate the user's emotions using emotion analysis technology and adjust the posting timing based on the estimated emotions. For example, if the user is stressed, the posting timing may be delayed. If the user is relaxed, the posting timing may be kept normal. If the user is in a hurry, the posting timing may be advanced. This allows for automatic adjustment of posting timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the posting support unit may be performed using AI or not using AI. For example, the posting support unit can input user emotion data into AI, and the AI ​​can adjust the posting timing.

[0123] The posting support unit can suggest the optimal posting method by referring to past posting data when providing posting support. For example, the posting support unit can refer to past posting data and suggest the optimal posting method based on posting methods that the user has successfully used in the past. For example, it can suggest that the user avoid posting methods that have failed in the past. The posting support unit can also suggest the optimal posting method based on hashtags and keywords that the user has used in the past. For example, it can suggest the optimal posting method based on hashtags and keywords that the user has used in the past. This allows the posting support unit to suggest the optimal posting method based on past data. Some or all of the above processing in the posting support unit may be performed using AI, for example, or without AI. For example, the posting support unit can input past posting data into AI, and the AI ​​can suggest the optimal posting method.

[0124] The posting support unit can estimate the user's emotions and determine the priority of posts based on the estimated emotions. For example, the posting support unit can estimate the user's emotions using emotion analysis technology and determine the priority of posts based on the estimated emotions. For example, if the user is stressed, posts of low importance will be prioritized. Conversely, if the user is relaxed, posts of high importance may be prioritized. Also, if the user is in a hurry, posts that can be completed quickly may be prioritized. This allows for the automatic determination of post priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the posting support unit may be performed using AI, or not using AI. For example, the posting support unit can input user emotion data into an AI, and the AI ​​can determine the priority of posts.

[0125] The posting support unit can suggest the optimal posting method when providing posting support, taking into account the user's geographical location. For example, if the user is in Japan, the posting support unit can suggest a posting method that suits Japanese culture and customs. For example, if the user is in the United States, it can suggest a posting method that suits American culture and customs. Furthermore, if the user is in France, the posting support unit can suggest a posting method that suits French culture and customs. For example, if the user is in France, it can suggest a posting method that suits French culture and customs. This allows the system to suggest the optimal posting method that takes geographical location into account. Some or all of the above processing in the posting support unit may be performed using AI, or not. For example, the posting support unit can input the user's geographical location information into the AI, which can then suggest the optimal posting method.

[0126] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0127] The AITuber creation platform can estimate the user's emotions and adjust the avatar's movements based on those emotions. For example, if the user is relaxed, the avatar's movements can be adjusted to be more relaxed. If the user is tense, the avatar's movements can be adjusted to be more subdued. Furthermore, if the user is having fun, the avatar's movements can be adjusted to be more lively. This allows the avatar's movements to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI includes, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the motion synchronization unit may be performed using AI or not. For example, the motion synchronization unit can input user emotion data into the AI, which can then adjust the avatar's movements.

[0128] The AITuber creation platform can analyze a user's past avatar creation history and suggest the optimal avatar generation method. For example, it can analyze past avatar creation history and suggest avatars with similar styles based on the styles of avatars the user has created in the past. It can also suggest the optimal avatar color palette based on the colors and designs the user has chosen in the past. Furthermore, it can suggest the optimal accessories based on the accessories the user has used in the past. In this way, it can suggest the optimal avatar generation method based on past history. Some or all of the above processing in the avatar generation unit may be performed using AI or not. For example, the avatar generation unit can input past avatar creation history into AI, and the AI ​​can suggest the optimal avatar generation method.

[0129] The AITuber creation platform can estimate the user's emotions and adjust the tone of the script based on those emotions. For example, it can use emotion analysis technology to estimate the user's emotions and adjust the tone of the script based on those emotions. If the user is relaxed, the tone of the script can be softened. If the user is nervous, the tone of the script can be adjusted to be calming. Furthermore, if the user is having fun, the tone of the script can be brightened. This allows the script tone to be automatically adjusted according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI includes, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the script generation unit may be performed using AI or not. For example, the script generation unit can input user emotion data into the AI, and the AI ​​can adjust the tone of the script.

[0130] The AITuber creation platform can incorporate region-specific elements by considering the user's geographical location. For example, if the user is in Japan, the avatar can incorporate traditional Japanese clothing and accessories. If the user is in the United States, the avatar can incorporate casual American-style clothing. If the user is in India, the avatar can incorporate a sari and traditional Indian accessories. This allows for the creation of avatars that incorporate region-specific elements. Some or all of the above processing in the avatar generation unit may be performed using AI or not. For example, the avatar generation unit can input the user's geographical location information into the AI, which can then generate an avatar that incorporates region-specific elements.

[0131] The AITuber creation platform can estimate the user's emotions and adjust the tone of voice based on those emotions. For example, it can use emotion analysis technology to estimate the user's emotions and adjust the tone of voice based on those emotions. If the user is relaxed, it can generate a soft tone of voice. If the user is tense, it can generate a calm tone of voice. Furthermore, if the user is having fun, it can generate a bright tone of voice. This allows for automatic adjustment of the tone of voice according to the user's emotions. Emotion estimation is achieved using an emotion engine or a generative AI, etc. The generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the speech synthesis unit may be performed using AI or not. For example, the speech synthesis unit can input user emotion data into the AI, and the AI ​​can adjust the tone of voice.

[0132] The AITuber creation platform can analyze a user's social media activity and suggest relevant avatars. For example, it can suggest avatar expressions and poses based on emojis and stickers that the user frequently uses on social media. It can also suggest avatar styles based on the content that the user frequently posts on social media. Furthermore, it can suggest avatar designs based on the styles of influencers that the user follows on social media. In this way, it can suggest relevant avatars based on social media activity. Some or all of the above processing in the avatar generation unit may be performed using AI or not. For example, the avatar generation unit can input the user's social media activity into AI, and the AI ​​can suggest relevant avatars.

[0133] The AITuber creation platform can estimate the user's emotions and adjust the subtitle display method based on the estimated emotions. For example, it can use emotion analysis technology to estimate the user's emotions and adjust the subtitle display method based on the estimated emotions. If the user is relaxed, subtitles can be displayed in a soft font. If the user is tense, subtitles can be displayed in a highly legible font. Furthermore, if the user is enjoying themselves, subtitles can be displayed in a colorful font. This allows for automatic adjustment of the subtitle display method according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI is, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the subtitle generation unit may be performed using AI or not. For example, the subtitle generation unit can input user emotion data into the AI, and the AI ​​can adjust the subtitle display method.

[0134] The AITuber creation platform can incorporate region-specific expressions by considering the user's geographical location. For example, if the user is in Japan, the script can incorporate expressions that are appropriate for Japanese culture and customs. If the user is in the United States, the script can incorporate expressions that are appropriate for American culture and customs. Similarly, if the user is in France, the script can incorporate expressions that are appropriate for French culture and customs. This allows for the generation of scripts that incorporate region-specific expressions. Some or all of the above processing in the script generation unit may be performed using AI or not. For example, the script generation unit can input the user's geographical location information into the AI, which can then generate a script that incorporates region-specific expressions.

[0135] The AITuber creation platform can estimate the user's emotions and adjust the project's progress based on those emotions. For example, it can use emotion analysis technology to estimate the user's emotions and adjust the project's progress based on those emotions. If the user is stressed, the project's progress can be slowed down. If the user is relaxed, the project can proceed at a normal pace. Furthermore, if the user is in a hurry, the project can be accelerated. This allows for automatic adjustment of the project's progress according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, among other things. Generative AI includes, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processes in the project management department may be performed using AI or not. For example, the project management department can input user emotion data into the AI, which can then adjust the project's progress.

[0136] The AITuber creation platform can analyze a user's social media activity and suggest relevant scripts. For example, it can suggest relevant scripts based on the content a user frequently posts on social media. It can also suggest scripts based on the style of influencers a user follows on social media. Furthermore, it can suggest scripts based on phrases and expressions a user frequently uses on social media. This allows the platform to suggest relevant scripts based on social media activity. Some or all of the above processing in the script generation unit may be performed using AI or not. For example, the script generation unit can input the user's social media activity into the AI, which can then suggest relevant scripts.

[0137] The following briefly describes the processing flow for example form 2.

[0138] Step 1: The avatar generation unit generates avatars using 3D or Live2D. For example, it can generate avatars based on photos uploaded by the user using image generation AI. It can also customize avatars based on styles and characteristics chosen by the user. Step 2: The script generation unit generates a script for the content based on the avatar generated by the avatar generation unit. For example, a script can be generated and customized based on user input and selected topics using an LLM (Large-Scale Language Model). Step 3: The speech synthesis unit synthesizes speech based on the script generated by the script generation unit. For example, the speech can be customized based on the tone and accent, language and dialect selected by the user. Step 4: The motion synchronization unit synchronizes the avatar's movements based on the speech synthesized by the speech synthesis unit. For example, it can synchronize the avatar's mouth movements with speech, or customize the avatar's movements based on gestures and facial expressions selected by the user. Step 5: The subtitle generation unit generates subtitles based on the audio synthesized by the speech synthesis unit. For example, it can automatically generate subtitles based on the generated audio, and the subtitles can be customized based on the font, style, language, and format selected by the user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0140] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0141] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the avatar generation unit, script generation unit, speech synthesis unit, motion synchronization unit, subtitle generation unit, project management unit, and posting support unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the avatar generation unit is implemented by the computer 36 of the smart device 14 and the processor 28 of the data processing unit 12, and generates an avatar based on a user's photograph. The script generation unit is implemented by the specific processing unit 290 of the data processing unit 12, and generates a script using LLM. The speech synthesis unit is implemented by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing unit 12, and synthesizes speech based on the generated script. The motion synchronization unit is implemented by the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing unit 12, and synchronizes the avatar's movements with the speech. The subtitle generation unit is implemented by the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing unit 12, and generates subtitles based on the speech. The project management unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and manages the progress of the project. The posting support unit is implemented, for example, by the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing device 12, and performs posting scheduling and content optimization. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0143] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0144] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the avatar generation unit, script generation unit, speech synthesis unit, motion synchronization unit, subtitle generation unit, project management unit, and posting support unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the avatar generation unit is implemented by the computer 36 of the smart glasses 214 and the processor 28 of the data processing unit 12, and generates an avatar based on the user's photograph. The script generation unit is implemented by the specific processing unit 290 of the data processing unit 12, and generates a script using LLM. The speech synthesis unit is implemented by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12, and synthesizes speech based on the generated script. The motion synchronization unit is implemented by the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12, and synchronizes the avatar's movements with the speech. The subtitle generation unit is implemented by the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing unit 12, and generates subtitles based on the speech. The project management unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and manages the progress of the project. The submission support unit is implemented, for example, by the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing device 12, and performs submission scheduling and content optimization. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0159] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0160] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0167] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0168] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0169] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0170] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0171] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0172] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0173] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0174] Each of the multiple elements described above, including the avatar generation unit, script generation unit, speech synthesis unit, motion synchronization unit, subtitle generation unit, project management unit, and posting support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the avatar generation unit is implemented by the computer 36 of the headset terminal 314 and the processor 28 of the data processing unit 12, and generates an avatar based on the user's photograph. The script generation unit is implemented by the specific processing unit 290 of the data processing unit 12, and generates a script using LLM. The speech synthesis unit is implemented by the processor 46 of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12, and synthesizes speech based on the generated script. The motion synchronization unit is implemented by the control unit 46A of the headset terminal 314 and the specific processing unit 290 of the data processing unit 12, and synchronizes the avatar's movements with the speech. The subtitle generation unit is implemented, for example, by the control unit 46A of the headset terminal 314 and the specific processing unit 290 of the data processing device 12, and generates subtitles based on audio. The project management unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and manages the progress of the project. The posting support unit is implemented, for example, by the control unit 46A of the headset terminal 314 and the specific processing unit 290 of the data processing device 12, and performs posting scheduling and content optimization. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0175] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0176] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0177] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0178] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0179] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0180] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0181] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0182] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0183] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0184] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0185] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0186] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0187] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0188] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0189] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0190] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0191] Each of the multiple elements described above, including the avatar generation unit, script generation unit, speech synthesis unit, motion synchronization unit, subtitle generation unit, project management unit, and posting support unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the avatar generation unit is implemented by the computer 36 of the robot 414 and the processor 28 of the data processing unit 12, and generates an avatar based on a user's photograph. The script generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and generates a script using LLM. The speech synthesis unit is implemented by, for example, the processor 46 of the robot 414 and the specific processing unit 290 of the data processing unit 12, and synthesizes speech based on the generated script. The motion synchronization unit is implemented by, for example, the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing unit 12, and synchronizes the avatar's movements with the speech. The subtitle generation unit is implemented by, for example, the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing unit 12, and generates subtitles based on the speech. The project management unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and manages the progress of the project. The submission support unit is implemented, for example, by the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing device 12, and performs submission scheduling and content optimization. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various changes are possible.

[0192] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0193] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0194] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0195] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0196] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0197] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0198] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0199] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0200] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0201] 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.

[0202] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0203] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0204] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0205] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0206] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0207] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0208] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0209] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0210] (Note 1) An avatar generation unit that generates avatars using 3D or Live2D, A script generation unit generates a script for content based on the avatar generated by the avatar generation unit, A speech synthesis unit that synthesizes speech based on the script generated by the script generation unit, A motion synchronization unit synchronizes the avatar's movements based on the voice synthesized by the voice synthesis unit, The system includes a subtitle generation unit that generates subtitles based on the speech synthesized by the speech synthesis unit. A system characterized by the following features. (Note 2) The company has a project management department that handles project management. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a posting support department to provide support for posting. The system described in Appendix 1, characterized by the features described herein. (Note 4) The avatar generation unit is, Generate an avatar using image generation AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The script generation unit, Script generation using LLM The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned speech synthesis unit, The system synthesizes speech to match the tone and accent of the user's voice. The system described in Appendix 1, characterized by the features described herein. (Note 7) The motion synchronization unit is The avatar's mouth movements are synchronized with the spoken words. The system described in Appendix 1, characterized by the features described herein. (Note 8) The subtitle generation unit, Automatically generate subtitles based on the generated audio and add them to the video. The system described in Appendix 1, characterized by the features described herein. (Note 9) The avatar generation unit is, It estimates the user's emotions and automatically adjusts the avatar's facial expressions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The avatar generation unit is, We analyze the user's past avatar creation history and suggest the optimal avatar generation method. The system described in Appendix 1, characterized by the features described herein. (Note 11) The avatar generation unit is, When creating an avatar, the system automatically selects the avatar's clothing and accessories based on the user's preferences. The system described in Appendix 1, characterized by the features described herein. (Note 12) The avatar generation unit is, It estimates the user's emotions and automatically adjusts the avatar's pose based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The avatar generation unit is, When generating avatars, the system incorporates region-specific elements by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The avatar generation unit is, When generating an avatar, the system analyzes the user's social media activity and suggests relevant avatars. The system described in Appendix 1, characterized by the features described herein. (Note 15) The script generation unit, It estimates the user's emotions and adjusts the tone of the script based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The script generation unit, When generating a script, the system references past script data to generate the optimal script. The system described in Appendix 1, characterized by the features described herein. (Note 17) The script generation unit, When generating a script, customize the script style based on the user's preferences. The system described in Appendix 1, characterized by the features described herein. (Note 18) The script generation unit, The system estimates the user's emotions and adjusts the script length based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The script generation unit, When generating the script, the system takes the user's geographical location into consideration and incorporates region-specific expressions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The script generation unit, During script generation, the system analyzes the user's social media activity and suggests relevant scripts. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned speech synthesis unit, It estimates the user's emotions and adjusts the tone of voice based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned speech synthesis unit, During speech synthesis, the system generates the optimal speech by referencing past speech data. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned speech synthesis unit, During speech synthesis, the accent of the voice is customized based on the user's preferences. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned speech synthesis unit, It estimates the user's emotions and adjusts the audio speed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned speech synthesis unit, During speech synthesis, the system incorporates regional accents by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned speech synthesis unit, During speech synthesis, the system analyzes the user's social media activity and suggests relevant audio. The system described in Appendix 1, characterized by the features described herein. (Note 27) The motion synchronization unit is It estimates the user's emotions and adjusts the avatar's movements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The motion synchronization unit is During motion synchronization, the system generates optimal movements by referencing past motion data. The system described in Appendix 1, characterized by the features described herein. (Note 29) The motion synchronization unit is During motion synchronization, the avatar's movements are customized based on the user's preferences. The system described in Appendix 1, characterized by the features described herein. (Note 30) The motion synchronization unit is It estimates the user's emotions and adjusts the avatar's movement speed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The motion synchronization unit is During motion synchronization, the system incorporates region-specific movements by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 32) The motion synchronization unit is During motion synchronization, the system analyzes the user's social media activity and suggests relevant movements. The system described in Appendix 1, characterized by the features described herein. (Note 33) The subtitle generation unit, It estimates the user's emotions and adjusts how subtitles are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The subtitle generation unit, When generating subtitles, the system references past subtitle data to generate the most suitable subtitles. The system described in Appendix 1, characterized by the features described herein. (Note 35) The subtitle generation unit, When generating subtitles, customize the subtitle style based on user preferences. The system described in Appendix 1, characterized by the features described herein. (Note 36) The subtitle generation unit, It estimates the user's emotions and adjusts the subtitle display speed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The subtitle generation unit, When generating subtitles, the system takes into account the user's geographical location and incorporates region-specific expressions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The subtitle generation unit, When generating subtitles, the system analyzes the user's social media activity and suggests relevant subtitles. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned project management department, Estimate user emotions and adjust project progress based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned project management department, During project management, we refer to past project data to propose the optimal progress method. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned project management department, Estimate user sentiment and prioritize projects based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned project management department, During project management, we propose the optimal progress method while considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned submission support section, It estimates user sentiment and adjusts the timing of posts based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned submission support section, When providing support for posting, we refer to past posting data to suggest the most suitable posting method. The system described in Appendix 1, characterized by the features described herein. (Note 45) The aforementioned submission support section, It estimates user sentiment and determines the priority of posts based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 46) The aforementioned submission support section, When providing support for posting, we suggest the optimal posting method considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0211] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An avatar generation unit that generates avatars using 3D or Live2D, A script generation unit generates a script for content based on the avatar generated by the avatar generation unit, A speech synthesis unit that synthesizes speech based on the script generated by the script generation unit, A motion synchronization unit synchronizes the avatar's movements based on the voice synthesized by the voice synthesis unit, The system includes a subtitle generation unit that generates subtitles based on the speech synthesized by the speech synthesis unit. A system characterized by the following features.

2. The company has a project management department that handles project management. The system according to feature 1.

3. It has a posting support department to provide support for posting. The system according to feature 1.

4. The avatar generation unit is, Generate an avatar using image generation AI. The system according to feature 1.

5. The script generation unit, Script generation using LLM The system according to feature 1.

6. The aforementioned speech synthesis unit, The system synthesizes speech to match the tone and accent of the user's voice. The system according to feature 1.

7. The motion synchronization unit is The avatar's mouth movements are synchronized with the spoken words. The system according to feature 1.

8. The subtitle generation unit, Automatically generate subtitles based on the generated audio and add them to the video. The system according to feature 1.

9. The avatar generation unit is, It estimates the user's emotions and automatically adjusts the avatar's facial expressions based on those estimated emotions. The system according to feature 1.

10. The avatar generation unit is, We analyze the user's past avatar creation history and suggest the optimal avatar generation method. The system according to feature 1.

Images